1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988
|
<html><body>
<style>
body, h1, h2, h3, div, span, p, pre, a {
margin: 0;
padding: 0;
border: 0;
font-weight: inherit;
font-style: inherit;
font-size: 100%;
font-family: inherit;
vertical-align: baseline;
}
body {
font-size: 13px;
padding: 1em;
}
h1 {
font-size: 26px;
margin-bottom: 1em;
}
h2 {
font-size: 24px;
margin-bottom: 1em;
}
h3 {
font-size: 20px;
margin-bottom: 1em;
margin-top: 1em;
}
pre, code {
line-height: 1.5;
font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}
pre {
margin-top: 0.5em;
}
h1, h2, h3, p {
font-family: Arial, sans serif;
}
h1, h2, h3 {
border-bottom: solid #CCC 1px;
}
.toc_element {
margin-top: 0.5em;
}
.firstline {
margin-left: 2 em;
}
.method {
margin-top: 1em;
border: solid 1px #CCC;
padding: 1em;
background: #EEE;
}
.details {
font-weight: bold;
font-size: 14px;
}
</style>
<h1><a href="dlp_v2.html">Sensitive Data Protection (DLP)</a> . <a href="dlp_v2.projects.html">projects</a> . <a href="dlp_v2.projects.jobTriggers.html">jobTriggers</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
<code><a href="#activate">activate(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Activate a job trigger. Causes the immediate execute of a trigger instead of waiting on the trigger event to occur.</p>
<p class="toc_element">
<code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
<code><a href="#create">create(parent, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Creates a job trigger to run DLP actions such as scanning storage for sensitive information on a set schedule. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.</p>
<p class="toc_element">
<code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes a job trigger. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.</p>
<p class="toc_element">
<code><a href="#get">get(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets a job trigger. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.</p>
<p class="toc_element">
<code><a href="#list">list(parent, filter=None, locationId=None, orderBy=None, pageSize=None, pageToken=None, type=None, x__xgafv=None)</a></code></p>
<p class="firstline">Lists job triggers. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.</p>
<p class="toc_element">
<code><a href="#list_next">list_next()</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<p class="toc_element">
<code><a href="#patch">patch(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Updates a job trigger. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.</p>
<h3>Method Details</h3>
<div class="method">
<code class="details" id="activate">activate(name, body=None, x__xgafv=None)</code>
<pre>Activate a job trigger. Causes the immediate execute of a trigger instead of waiting on the trigger event to occur.
Args:
name: string, Required. Resource name of the trigger to activate, for example `projects/dlp-test-project/jobTriggers/53234423`. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ActivateJobTrigger.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Combines all of the information about a DLP job.
"actionDetails": [ # Events that should occur after the job has completed.
{ # The results of an Action.
"deidentifyDetails": { # The results of a Deidentify action from an inspect job. # Outcome of a de-identification action.
"deidentifyStats": { # Summary of what was modified during a transformation. # Stats about the de-identification operation.
"transformationCount": "A String", # Number of successfully applied transformations.
"transformationErrorCount": "A String", # Number of errors encountered while trying to apply transformations.
"transformedBytes": "A String", # Total size in bytes that were transformed in some way.
},
"requestedOptions": { # De-identification options. # De-identification config used for the request.
"snapshotDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the `DeidentifyTemplate` from the Deidentify action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotImageRedactTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the image transformation `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotStructuredDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the structured `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. FPE incurs significant latency costs. # Ffx-Fpe. Strongly discouraged, consider using CryptoDeterministicConfig instead. Fpe is computationally expensive incurring latency costs.
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
},
},
],
"createTime": "A String", # Time when the job was created.
"endTime": "A String", # Time when the job finished.
"errors": [ # A stream of errors encountered running the job.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job.
"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data to be detected) to be used anywhere you otherwise would normally specify InspectConfig. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # If run with an InspectTemplate, a snapshot of its state at the time of this run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # The core content of the template. Configuration of the scanning process.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
"result": { # All Result fields are updated while the job is processing. # A summary of the outcome of this inspection job.
"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.
"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran out of quota or was ended before they could be processed.
"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated when called via method `getDlpJob`. A burst of traffic may cause hybrid inspect requests to be enqueued. Processing will take place as quickly as possible, but resource limitations may impact how long a request is enqueued for.
"processedCount": "A String", # The number of hybrid inspection requests processed within this job.
},
"infoTypeStats": [ # Statistics of how many instances of each info type were found during inspect job.
{ # Statistics regarding a specific InfoType.
"count": "A String", # Number of findings for this infoType.
"infoType": { # Type of information detected by the API. # The type of finding this stat is for.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"numRowsProcessed": "A String", # Number of rows scanned after sampling and time filtering (applicable for row based stores such as BigQuery).
"processedBytes": "A String", # Total size in bytes that were processed.
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
},
},
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that instantiated the job.
"lastModified": "A String", # Time when the job was last modified by the system.
"name": "A String", # The server-assigned name.
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{ # Histogram of value frequencies in the column.
"bucketSize": "A String", # Total number of values in this bucket.
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"bucketValues": [ # Sample of value frequencies in this bucket. The total number of values returned per bucket is capped at 20.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an estimation, not exact values. # Delta-presence result
"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_probability: 0, max_probability: 0.1, frequency: 17} {min_probability: 0.2, max_probability: 0.3, frequency: 42} {min_probability: 0.3, max_probability: 0.4, frequency: 99} mean that there are no record with an estimated probability in [0.1, 0.2) nor larger or equal to 0.4.
{ # A DeltaPresenceEstimationHistogramBucket message with the following values: min_probability: 0.1 max_probability: 0.2 frequency: 42 means that there are 42 records for which δ is in [0.1, 0.2). An important particular case is when min_probability = max_probability = 1: then, every individual who shares this quasi-identifier combination is in the dataset.
"bucketSize": "A String", # Number of records within these probability bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these quasi-identifier values is in the dataset. This value, typically called δ, is the ratio between the number of records in the dataset with these quasi-identifier values, and the total number of individuals (inside *and* outside the dataset) with these quasi-identifier values. For example, if there are 15 individuals in the dataset who share the same quasi-identifier values, and an estimated 100 people in the entire population with these values, then δ is 0.15.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{ # Histogram of k-anonymity equivalence classes.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the above set of values.
"quasiIdsValues": [ # Set of values defining the equivalence class. One value per quasi-identifier column in the original KAnonymity metric message. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.
"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.
},
],
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an estimation, not exact values. # K-map result
"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_anonymity: 1, max_anonymity: 1, frequency: 17} {min_anonymity: 2, max_anonymity: 3, frequency: 42} {min_anonymity: 5, max_anonymity: 10, frequency: 99} mean that there are no record with an estimated anonymity of 4, 5, or larger than 10.
{ # A KMapEstimationHistogramBucket message with the following values: min_anonymity: 3 max_anonymity: 5 frequency: 42 means that there are 42 records whose quasi-identifier values correspond to 3, 4 or 5 people in the overlying population. An important particular case is when min_anonymity = max_anonymity = 1: the frequency field then corresponds to the number of uniquely identifiable records.
"bucketSize": "A String", # Number of records within these anonymity bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"minAnonymity": "A String", # Always positive.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{ # Histogram of l-diversity equivalence class sensitive value frequencies.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value.
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.
"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence class. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
"topSensitiveValues": [ # Estimated frequencies of top sensitive values.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
],
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence classes in this bucket.
},
],
},
"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result
"maxValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Maximum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"minValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Minimum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal sized buckets.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
"requestedOptions": { # Risk analysis options. # The configuration used for this job.
"jobConfig": { # Configuration for a risk analysis job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-risk-analysis to learn more. # The job config for the risk job.
"actions": [ # Actions to execute at the completion of the job. Are executed in the order provided.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column.
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column.
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column.
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column.
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"startTime": "A String", # Time when the job started.
"state": "A String", # State of a job.
"type": "A String", # The type of job.
}</pre>
</div>
<div class="method">
<code class="details" id="close">close()</code>
<pre>Close httplib2 connections.</pre>
</div>
<div class="method">
<code class="details" id="create">create(parent, body=None, x__xgafv=None)</code>
<pre>Creates a job trigger to run DLP actions such as scanning storage for sensitive information on a set schedule. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.
Args:
parent: string, Required. Parent resource name. The format of this value varies depending on whether you have [specified a processing location](https://cloud.google.com/sensitive-data-protection/docs/specifying-location): + Projects scope, location specified: `projects/{project_id}/locations/{location_id}` + Projects scope, no location specified (defaults to global): `projects/{project_id}` The following example `parent` string specifies a parent project with the identifier `example-project`, and specifies the `europe-west3` location for processing data: parent=projects/example-project/locations/europe-west3 (required)
body: object, The request body.
The object takes the form of:
{ # Request message for CreateJobTrigger.
"jobTrigger": { # Contains a configuration to make API calls on a repeating basis. See https://cloud.google.com/sensitive-data-protection/docs/concepts-job-triggers to learn more. # Required. The JobTrigger to create.
"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
"description": "A String", # User provided description (max 256 chars)
"displayName": "A String", # Display name (max 100 chars)
"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated errors may result in the JobTrigger automatically being paused. Will return the last 100 errors. Whenever the JobTrigger is modified this list will be cleared.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the triggeredJob is created, for example `projects/dlp-test-project/jobTriggers/53234423`.
"status": "A String", # Required. A status for this trigger.
"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list needs to trigger for a job to be started. The list may contain only a single Schedule trigger and must have at least one object.
{ # What event needs to occur for a new job to be started.
"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created and finished. # For use with hybrid jobs. Jobs must be manually created and finished.
},
"schedule": { # Schedule for inspect job triggers. # Create a job on a repeating basis based on the elapse of time.
"recurrencePeriodDuration": "A String", # With this option a job is started on a regular periodic basis. For example: every day (86400 seconds). A scheduled start time will be skipped if the previous execution has not ended when its scheduled time occurs. This value must be set to a time duration greater than or equal to 1 day and can be no longer than 60 days.
},
},
],
"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
},
"locationId": "A String", # Deprecated. This field has no effect.
"triggerId": "A String", # The trigger id can contain uppercase and lowercase letters, numbers, and hyphens; that is, it must match the regular expression: `[a-zA-Z\d-_]+`. The maximum length is 100 characters. Can be empty to allow the system to generate one.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Contains a configuration to make API calls on a repeating basis. See https://cloud.google.com/sensitive-data-protection/docs/concepts-job-triggers to learn more.
"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
"description": "A String", # User provided description (max 256 chars)
"displayName": "A String", # Display name (max 100 chars)
"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated errors may result in the JobTrigger automatically being paused. Will return the last 100 errors. Whenever the JobTrigger is modified this list will be cleared.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the triggeredJob is created, for example `projects/dlp-test-project/jobTriggers/53234423`.
"status": "A String", # Required. A status for this trigger.
"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list needs to trigger for a job to be started. The list may contain only a single Schedule trigger and must have at least one object.
{ # What event needs to occur for a new job to be started.
"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created and finished. # For use with hybrid jobs. Jobs must be manually created and finished.
},
"schedule": { # Schedule for inspect job triggers. # Create a job on a repeating basis based on the elapse of time.
"recurrencePeriodDuration": "A String", # With this option a job is started on a regular periodic basis. For example: every day (86400 seconds). A scheduled start time will be skipped if the previous execution has not ended when its scheduled time occurs. This value must be set to a time duration greater than or equal to 1 day and can be no longer than 60 days.
},
},
],
"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
}</pre>
</div>
<div class="method">
<code class="details" id="delete">delete(name, x__xgafv=None)</code>
<pre>Deletes a job trigger. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.
Args:
name: string, Required. Resource name of the project and the triggeredJob, for example `projects/dlp-test-project/jobTriggers/53234423`. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
}</pre>
</div>
<div class="method">
<code class="details" id="get">get(name, x__xgafv=None)</code>
<pre>Gets a job trigger. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.
Args:
name: string, Required. Resource name of the project and the triggeredJob, for example `projects/dlp-test-project/jobTriggers/53234423`. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Contains a configuration to make API calls on a repeating basis. See https://cloud.google.com/sensitive-data-protection/docs/concepts-job-triggers to learn more.
"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
"description": "A String", # User provided description (max 256 chars)
"displayName": "A String", # Display name (max 100 chars)
"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated errors may result in the JobTrigger automatically being paused. Will return the last 100 errors. Whenever the JobTrigger is modified this list will be cleared.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the triggeredJob is created, for example `projects/dlp-test-project/jobTriggers/53234423`.
"status": "A String", # Required. A status for this trigger.
"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list needs to trigger for a job to be started. The list may contain only a single Schedule trigger and must have at least one object.
{ # What event needs to occur for a new job to be started.
"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created and finished. # For use with hybrid jobs. Jobs must be manually created and finished.
},
"schedule": { # Schedule for inspect job triggers. # Create a job on a repeating basis based on the elapse of time.
"recurrencePeriodDuration": "A String", # With this option a job is started on a regular periodic basis. For example: every day (86400 seconds). A scheduled start time will be skipped if the previous execution has not ended when its scheduled time occurs. This value must be set to a time duration greater than or equal to 1 day and can be no longer than 60 days.
},
},
],
"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
}</pre>
</div>
<div class="method">
<code class="details" id="list">list(parent, filter=None, locationId=None, orderBy=None, pageSize=None, pageToken=None, type=None, x__xgafv=None)</code>
<pre>Lists job triggers. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.
Args:
parent: string, Required. Parent resource name. The format of this value varies depending on whether you have [specified a processing location](https://cloud.google.com/sensitive-data-protection/docs/specifying-location): + Projects scope, location specified: `projects/{project_id}/locations/{location_id}` + Projects scope, no location specified (defaults to global): `projects/{project_id}` The following example `parent` string specifies a parent project with the identifier `example-project`, and specifies the `europe-west3` location for processing data: parent=projects/example-project/locations/europe-west3 (required)
filter: string, Allows filtering. Supported syntax: * Filter expressions are made up of one or more restrictions. * Restrictions can be combined by `AND` or `OR` logical operators. A sequence of restrictions implicitly uses `AND`. * A restriction has the form of `{field} {operator} {value}`. * Supported fields/values for inspect triggers: - `status` - HEALTHY|PAUSED|CANCELLED - `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY - 'last_run_time` - RFC 3339 formatted timestamp, surrounded by quotation marks. Nanoseconds are ignored. - 'error_count' - Number of errors that have occurred while running. * The operator must be `=` or `!=` for status and inspected_storage. Examples: * inspected_storage = cloud_storage AND status = HEALTHY * inspected_storage = cloud_storage OR inspected_storage = bigquery * inspected_storage = cloud_storage AND (state = PAUSED OR state = HEALTHY) * last_run_time > \"2017-12-12T00:00:00+00:00\" The length of this field should be no more than 500 characters.
locationId: string, Deprecated. This field has no effect.
orderBy: string, Comma-separated list of triggeredJob fields to order by, followed by `asc` or `desc` postfix. This list is case insensitive. The default sorting order is ascending. Redundant space characters are insignificant. Example: `name asc,update_time, create_time desc` Supported fields are: - `create_time`: corresponds to the time the JobTrigger was created. - `update_time`: corresponds to the time the JobTrigger was last updated. - `last_run_time`: corresponds to the last time the JobTrigger ran. - `name`: corresponds to the JobTrigger's name. - `display_name`: corresponds to the JobTrigger's display name. - `status`: corresponds to JobTrigger's status.
pageSize: integer, Size of the page. This value can be limited by a server.
pageToken: string, Page token to continue retrieval. Comes from the previous call to ListJobTriggers. `order_by` field must not change for subsequent calls.
type: string, The type of jobs. Will use `DlpJobType.INSPECT` if not set.
Allowed values
DLP_JOB_TYPE_UNSPECIFIED - Defaults to INSPECT_JOB.
INSPECT_JOB - The job inspected Google Cloud for sensitive data.
RISK_ANALYSIS_JOB - The job executed a Risk Analysis computation.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for ListJobTriggers.
"jobTriggers": [ # List of triggeredJobs, up to page_size in ListJobTriggersRequest.
{ # Contains a configuration to make API calls on a repeating basis. See https://cloud.google.com/sensitive-data-protection/docs/concepts-job-triggers to learn more.
"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
"description": "A String", # User provided description (max 256 chars)
"displayName": "A String", # Display name (max 100 chars)
"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated errors may result in the JobTrigger automatically being paused. Will return the last 100 errors. Whenever the JobTrigger is modified this list will be cleared.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the triggeredJob is created, for example `projects/dlp-test-project/jobTriggers/53234423`.
"status": "A String", # Required. A status for this trigger.
"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list needs to trigger for a job to be started. The list may contain only a single Schedule trigger and must have at least one object.
{ # What event needs to occur for a new job to be started.
"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created and finished. # For use with hybrid jobs. Jobs must be manually created and finished.
},
"schedule": { # Schedule for inspect job triggers. # Create a job on a repeating basis based on the elapse of time.
"recurrencePeriodDuration": "A String", # With this option a job is started on a regular periodic basis. For example: every day (86400 seconds). A scheduled start time will be skipped if the previous execution has not ended when its scheduled time occurs. This value must be set to a time duration greater than or equal to 1 day and can be no longer than 60 days.
},
},
],
"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
},
],
"nextPageToken": "A String", # If the next page is available then this value is the next page token to be used in the following ListJobTriggers request.
}</pre>
</div>
<div class="method">
<code class="details" id="list_next">list_next()</code>
<pre>Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
</pre>
</div>
<div class="method">
<code class="details" id="patch">patch(name, body=None, x__xgafv=None)</code>
<pre>Updates a job trigger. See https://cloud.google.com/sensitive-data-protection/docs/creating-job-triggers to learn more.
Args:
name: string, Required. Resource name of the project and the triggeredJob, for example `projects/dlp-test-project/jobTriggers/53234423`. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for UpdateJobTrigger.
"jobTrigger": { # Contains a configuration to make API calls on a repeating basis. See https://cloud.google.com/sensitive-data-protection/docs/concepts-job-triggers to learn more. # New JobTrigger value.
"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
"description": "A String", # User provided description (max 256 chars)
"displayName": "A String", # Display name (max 100 chars)
"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated errors may result in the JobTrigger automatically being paused. Will return the last 100 errors. Whenever the JobTrigger is modified this list will be cleared.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the triggeredJob is created, for example `projects/dlp-test-project/jobTriggers/53234423`.
"status": "A String", # Required. A status for this trigger.
"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list needs to trigger for a job to be started. The list may contain only a single Schedule trigger and must have at least one object.
{ # What event needs to occur for a new job to be started.
"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created and finished. # For use with hybrid jobs. Jobs must be manually created and finished.
},
"schedule": { # Schedule for inspect job triggers. # Create a job on a repeating basis based on the elapse of time.
"recurrencePeriodDuration": "A String", # With this option a job is started on a regular periodic basis. For example: every day (86400 seconds). A scheduled start time will be skipped if the previous execution has not ended when its scheduled time occurs. This value must be set to a time duration greater than or equal to 1 day and can be no longer than 60 days.
},
},
],
"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
},
"updateMask": "A String", # Mask to control which fields get updated.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Contains a configuration to make API calls on a repeating basis. See https://cloud.google.com/sensitive-data-protection/docs/concepts-job-triggers to learn more.
"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
"description": "A String", # User provided description (max 256 chars)
"displayName": "A String", # Display name (max 100 chars)
"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated errors may result in the JobTrigger automatically being paused. Will return the last 100 errors. Whenever the JobTrigger is modified this list will be cleared.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of a storage bucket. Only compatible with Cloud Storage buckets. A TransformationDetail will be created for each transformation. Compatible with: Inspection of Cloud Storage # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types are transformed. If empty, all supported files are transformed. Supported types may be automatically added over time. Any unsupported file types that are set in this field are excluded from de-identification. An error is recorded for each unsupported file in the TransformationDetails output table. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This field specifies the configuration for storing detailed metadata about each transformation performed during a de-identification process. The metadata is stored separately from the de-identified content itself and provides a granular record of both successful transformations and any failures that occurred. Enabling this configuration is essential for users who need to access comprehensive information about the status, outcome, and specifics of each transformation. The details are captured in the TransformationDetails message for each operation. Key use cases: * **Auditing and compliance** * Provides a verifiable audit trail of de-identification activities, which is crucial for meeting regulatory requirements and internal data governance policies. * Logs what data was transformed, what transformations were applied, when they occurred, and their success status. This helps demonstrate accountability and due diligence in protecting sensitive data. * **Troubleshooting and debugging** * Offers detailed error messages and context if a transformation fails. This information is useful for diagnosing and resolving issues in the de-identification pipeline. * Helps pinpoint the exact location and nature of failures, speeding up the debugging process. * **Process verification and quality assurance** * Allows users to confirm that de-identification rules and transformations were applied correctly and consistently across the dataset as intended. * Helps in verifying the effectiveness of the chosen de-identification strategies. * **Data lineage and impact analysis** * Creates a record of how data elements were modified, contributing to data lineage. This is useful for understanding the provenance of de-identified data. * Aids in assessing the potential impact of de-identification choices on downstream analytical processes or data usability. * **Reporting and operational insights** * You can analyze the metadata stored in a queryable BigQuery table to generate reports on transformation success rates, common error types, processing volumes (e.g., transformedBytes), and the types of transformations applied. * These insights can inform optimization of de-identification configurations and resource planning. To take advantage of these benefits, set this configuration. The stored details include a description of the transformation, success or error codes, error messages, the number of bytes transformed, the location of the transformed content, and identifiers for the job and source data.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "\(\d{3}\) \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "\(xxx\)", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the triggeredJob is created, for example `projects/dlp-test-project/jobTriggers/53234423`.
"status": "A String", # Required. A status for this trigger.
"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list needs to trigger for a job to be started. The list may contain only a single Schedule trigger and must have at least one object.
{ # What event needs to occur for a new job to be started.
"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created and finished. # For use with hybrid jobs. Jobs must be manually created and finished.
},
"schedule": { # Schedule for inspect job triggers. # Create a job on a repeating basis based on the elapse of time.
"recurrencePeriodDuration": "A String", # With this option a job is started on a regular periodic basis. For example: every day (86400 seconds). A scheduled start time will be skipped if the previous execution has not ended when its scheduled time occurs. This value must be set to a time duration greater than or equal to 1 day and can be no longer than 60 days.
},
},
],
"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
}</pre>
</div>
</body></html>
|