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
|
{# This template is generated by gen_cbor_templates.py. #}
// Generated by lib/encoding_cpp.template.
// Copyright 2019 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
{% if config.encoding_lib.header == "" %}
#include <algorithm>
#include <cassert>
#include <cmath>
#include <cstring>
#include <limits>
#include <stack>
{% for namespace in config.protocol.namespace %}
namespace {{namespace}} {
{% endfor %}
// ===== encoding/encoding.cc =====
// =============================================================================
// Status and Error codes
// =============================================================================
std::string Status::ToASCIIString() const {
switch (error) {
case Error::OK:
return "OK";
case Error::JSON_PARSER_UNPROCESSED_INPUT_REMAINS:
return ToASCIIString("JSON: unprocessed input remains");
case Error::JSON_PARSER_STACK_LIMIT_EXCEEDED:
return ToASCIIString("JSON: stack limit exceeded");
case Error::JSON_PARSER_NO_INPUT:
return ToASCIIString("JSON: no input");
case Error::JSON_PARSER_INVALID_TOKEN:
return ToASCIIString("JSON: invalid token");
case Error::JSON_PARSER_INVALID_NUMBER:
return ToASCIIString("JSON: invalid number");
case Error::JSON_PARSER_INVALID_STRING:
return ToASCIIString("JSON: invalid string");
case Error::JSON_PARSER_UNEXPECTED_ARRAY_END:
return ToASCIIString("JSON: unexpected array end");
case Error::JSON_PARSER_COMMA_OR_ARRAY_END_EXPECTED:
return ToASCIIString("JSON: comma or array end expected");
case Error::JSON_PARSER_STRING_LITERAL_EXPECTED:
return ToASCIIString("JSON: string literal expected");
case Error::JSON_PARSER_COLON_EXPECTED:
return ToASCIIString("JSON: colon expected");
case Error::JSON_PARSER_UNEXPECTED_MAP_END:
return ToASCIIString("JSON: unexpected map end");
case Error::JSON_PARSER_COMMA_OR_MAP_END_EXPECTED:
return ToASCIIString("JSON: comma or map end expected");
case Error::JSON_PARSER_VALUE_EXPECTED:
return ToASCIIString("JSON: value expected");
case Error::CBOR_INVALID_INT32:
return ToASCIIString("CBOR: invalid int32");
case Error::CBOR_INVALID_DOUBLE:
return ToASCIIString("CBOR: invalid double");
case Error::CBOR_INVALID_ENVELOPE:
return ToASCIIString("CBOR: invalid envelope");
case Error::CBOR_INVALID_STRING8:
return ToASCIIString("CBOR: invalid string8");
case Error::CBOR_INVALID_STRING16:
return ToASCIIString("CBOR: invalid string16");
case Error::CBOR_INVALID_BINARY:
return ToASCIIString("CBOR: invalid binary");
case Error::CBOR_UNSUPPORTED_VALUE:
return ToASCIIString("CBOR: unsupported value");
case Error::CBOR_NO_INPUT:
return ToASCIIString("CBOR: no input");
case Error::CBOR_INVALID_START_BYTE:
return ToASCIIString("CBOR: invalid start byte");
case Error::CBOR_UNEXPECTED_EOF_EXPECTED_VALUE:
return ToASCIIString("CBOR: unexpected eof expected value");
case Error::CBOR_UNEXPECTED_EOF_IN_ARRAY:
return ToASCIIString("CBOR: unexpected eof in array");
case Error::CBOR_UNEXPECTED_EOF_IN_MAP:
return ToASCIIString("CBOR: unexpected eof in map");
case Error::CBOR_INVALID_MAP_KEY:
return ToASCIIString("CBOR: invalid map key");
case Error::CBOR_STACK_LIMIT_EXCEEDED:
return ToASCIIString("CBOR: stack limit exceeded");
case Error::CBOR_TRAILING_JUNK:
return ToASCIIString("CBOR: trailing junk");
case Error::CBOR_MAP_START_EXPECTED:
return ToASCIIString("CBOR: map start expected");
case Error::CBOR_MAP_STOP_EXPECTED:
return ToASCIIString("CBOR: map stop expected");
case Error::CBOR_ENVELOPE_SIZE_LIMIT_EXCEEDED:
return ToASCIIString("CBOR: envelope size limit exceeded");
}
// Some compilers can't figure out that we can't get here.
return "INVALID ERROR CODE";
}
std::string Status::ToASCIIString(const char* msg) const {
return std::string(msg) + " at position " + std::to_string(pos);
}
namespace cbor {
namespace {
// Indicates the number of bits the "initial byte" needs to be shifted to the
// right after applying |kMajorTypeMask| to produce the major type in the
// lowermost bits.
static constexpr uint8_t kMajorTypeBitShift = 5u;
// Mask selecting the low-order 5 bits of the "initial byte", which is where
// the additional information is encoded.
static constexpr uint8_t kAdditionalInformationMask = 0x1f;
// Mask selecting the high-order 3 bits of the "initial byte", which indicates
// the major type of the encoded value.
static constexpr uint8_t kMajorTypeMask = 0xe0;
// Indicates the integer is in the following byte.
static constexpr uint8_t kAdditionalInformation1Byte = 24u;
// Indicates the integer is in the next 2 bytes.
static constexpr uint8_t kAdditionalInformation2Bytes = 25u;
// Indicates the integer is in the next 4 bytes.
static constexpr uint8_t kAdditionalInformation4Bytes = 26u;
// Indicates the integer is in the next 8 bytes.
static constexpr uint8_t kAdditionalInformation8Bytes = 27u;
// Encodes the initial byte, consisting of the |type| in the first 3 bits
// followed by 5 bits of |additional_info|.
constexpr uint8_t EncodeInitialByte(MajorType type, uint8_t additional_info) {
return (static_cast<uint8_t>(type) << kMajorTypeBitShift) |
(additional_info & kAdditionalInformationMask);
}
// TAG 24 indicates that what follows is a byte string which is
// encoded in CBOR format. We use this as a wrapper for
// maps and arrays, allowing us to skip them, because the
// byte string carries its size (byte length).
// https://tools.ietf.org/html/rfc7049#section-2.4.4.1
static constexpr uint8_t kInitialByteForEnvelope =
EncodeInitialByte(MajorType::TAG, 24);
// The initial byte for a byte string with at most 2^32 bytes
// of payload. This is used for envelope encoding, even if
// the byte string is shorter.
static constexpr uint8_t kInitialByteFor32BitLengthByteString =
EncodeInitialByte(MajorType::BYTE_STRING, 26);
// See RFC 7049 Section 2.2.1, indefinite length arrays / maps have additional
// info = 31.
static constexpr uint8_t kInitialByteIndefiniteLengthArray =
EncodeInitialByte(MajorType::ARRAY, 31);
static constexpr uint8_t kInitialByteIndefiniteLengthMap =
EncodeInitialByte(MajorType::MAP, 31);
// See RFC 7049 Section 2.3, Table 1; this is used for finishing indefinite
// length maps / arrays.
static constexpr uint8_t kStopByte =
EncodeInitialByte(MajorType::SIMPLE_VALUE, 31);
// See RFC 7049 Section 2.3, Table 2.
static constexpr uint8_t kEncodedTrue =
EncodeInitialByte(MajorType::SIMPLE_VALUE, 21);
static constexpr uint8_t kEncodedFalse =
EncodeInitialByte(MajorType::SIMPLE_VALUE, 20);
static constexpr uint8_t kEncodedNull =
EncodeInitialByte(MajorType::SIMPLE_VALUE, 22);
static constexpr uint8_t kInitialByteForDouble =
EncodeInitialByte(MajorType::SIMPLE_VALUE, 27);
// See RFC 7049 Table 3 and Section 2.4.4.2. This is used as a prefix for
// arbitrary binary data encoded as BYTE_STRING.
static constexpr uint8_t kExpectedConversionToBase64Tag =
EncodeInitialByte(MajorType::TAG, 22);
// Writes the bytes for |v| to |out|, starting with the most significant byte.
// See also: https://commandcenter.blogspot.com/2012/04/byte-order-fallacy.html
template <typename T, class C>
void WriteBytesMostSignificantByteFirst(T v, C* out) {
for (int shift_bytes = sizeof(T) - 1; shift_bytes >= 0; --shift_bytes)
out->push_back(0xff & (v >> (shift_bytes * 8)));
}
// Extracts sizeof(T) bytes from |in| to extract a value of type T
// (e.g. uint64_t, uint32_t, ...), most significant byte first.
// See also: https://commandcenter.blogspot.com/2012/04/byte-order-fallacy.html
template <typename T>
T ReadBytesMostSignificantByteFirst(span<uint8_t> in) {
assert(in.size() >= sizeof(T));
T result = 0;
for (size_t shift_bytes = 0; shift_bytes < sizeof(T); ++shift_bytes)
result |= T(in[sizeof(T) - 1 - shift_bytes]) << (shift_bytes * 8);
return result;
}
} // namespace
namespace internals {
// Reads the start of a token with definitive size from |bytes|.
// |type| is the major type as specified in RFC 7049 Section 2.1.
// |value| is the payload (e.g. for MajorType::UNSIGNED) or is the size
// (e.g. for BYTE_STRING).
// If successful, returns the number of bytes read. Otherwise returns 0.
size_t ReadTokenStart(span<uint8_t> bytes, MajorType* type, uint64_t* value) {
if (bytes.empty())
return 0;
uint8_t initial_byte = bytes[0];
*type = MajorType((initial_byte & kMajorTypeMask) >> kMajorTypeBitShift);
uint8_t additional_information = initial_byte & kAdditionalInformationMask;
if (additional_information < 24) {
// Values 0-23 are encoded directly into the additional info of the
// initial byte.
*value = additional_information;
return 1;
}
if (additional_information == kAdditionalInformation1Byte) {
// Values 24-255 are encoded with one initial byte, followed by the value.
if (bytes.size() < 2)
return 0;
*value = ReadBytesMostSignificantByteFirst<uint8_t>(bytes.subspan(1));
return 2;
}
if (additional_information == kAdditionalInformation2Bytes) {
// Values 256-65535: 1 initial byte + 2 bytes payload.
if (bytes.size() < 1 + sizeof(uint16_t))
return 0;
*value = ReadBytesMostSignificantByteFirst<uint16_t>(bytes.subspan(1));
return 3;
}
if (additional_information == kAdditionalInformation4Bytes) {
// 32 bit uint: 1 initial byte + 4 bytes payload.
if (bytes.size() < 1 + sizeof(uint32_t))
return 0;
*value = ReadBytesMostSignificantByteFirst<uint32_t>(bytes.subspan(1));
return 5;
}
if (additional_information == kAdditionalInformation8Bytes) {
// 64 bit uint: 1 initial byte + 8 bytes payload.
if (bytes.size() < 1 + sizeof(uint64_t))
return 0;
*value = ReadBytesMostSignificantByteFirst<uint64_t>(bytes.subspan(1));
return 9;
}
return 0;
}
// Writes the start of a token with |type|. The |value| may indicate the size,
// or it may be the payload if the value is an unsigned integer.
template <typename C>
void WriteTokenStartTmpl(MajorType type, uint64_t value, C* encoded) {
if (value < 24) {
// Values 0-23 are encoded directly into the additional info of the
// initial byte.
encoded->push_back(EncodeInitialByte(type, /*additional_info=*/value));
return;
}
if (value <= std::numeric_limits<uint8_t>::max()) {
// Values 24-255 are encoded with one initial byte, followed by the value.
encoded->push_back(EncodeInitialByte(type, kAdditionalInformation1Byte));
encoded->push_back(value);
return;
}
if (value <= std::numeric_limits<uint16_t>::max()) {
// Values 256-65535: 1 initial byte + 2 bytes payload.
encoded->push_back(EncodeInitialByte(type, kAdditionalInformation2Bytes));
WriteBytesMostSignificantByteFirst<uint16_t>(value, encoded);
return;
}
if (value <= std::numeric_limits<uint32_t>::max()) {
// 32 bit uint: 1 initial byte + 4 bytes payload.
encoded->push_back(EncodeInitialByte(type, kAdditionalInformation4Bytes));
WriteBytesMostSignificantByteFirst<uint32_t>(static_cast<uint32_t>(value),
encoded);
return;
}
// 64 bit uint: 1 initial byte + 8 bytes payload.
encoded->push_back(EncodeInitialByte(type, kAdditionalInformation8Bytes));
WriteBytesMostSignificantByteFirst<uint64_t>(value, encoded);
}
void WriteTokenStart(MajorType type,
uint64_t value,
std::vector<uint8_t>* encoded) {
WriteTokenStartTmpl(type, value, encoded);
}
void WriteTokenStart(MajorType type, uint64_t value, std::string* encoded) {
WriteTokenStartTmpl(type, value, encoded);
}
} // namespace internals
// =============================================================================
// Detecting CBOR content
// =============================================================================
uint8_t InitialByteForEnvelope() {
return kInitialByteForEnvelope;
}
uint8_t InitialByteFor32BitLengthByteString() {
return kInitialByteFor32BitLengthByteString;
}
bool IsCBORMessage(span<uint8_t> msg) {
return msg.size() >= 6 && msg[0] == InitialByteForEnvelope() &&
msg[1] == InitialByteFor32BitLengthByteString();
}
// =============================================================================
// Encoding invidiual CBOR items
// =============================================================================
uint8_t EncodeTrue() {
return kEncodedTrue;
}
uint8_t EncodeFalse() {
return kEncodedFalse;
}
uint8_t EncodeNull() {
return kEncodedNull;
}
uint8_t EncodeIndefiniteLengthArrayStart() {
return kInitialByteIndefiniteLengthArray;
}
uint8_t EncodeIndefiniteLengthMapStart() {
return kInitialByteIndefiniteLengthMap;
}
uint8_t EncodeStop() {
return kStopByte;
}
template <typename C>
void EncodeInt32Tmpl(int32_t value, C* out) {
if (value >= 0) {
internals::WriteTokenStart(MajorType::UNSIGNED, value, out);
} else {
uint64_t representation = static_cast<uint64_t>(-(value + 1));
internals::WriteTokenStart(MajorType::NEGATIVE, representation, out);
}
}
void EncodeInt32(int32_t value, std::vector<uint8_t>* out) {
EncodeInt32Tmpl(value, out);
}
void EncodeInt32(int32_t value, std::string* out) {
EncodeInt32Tmpl(value, out);
}
template <typename C>
void EncodeString16Tmpl(span<uint16_t> in, C* out) {
uint64_t byte_length = static_cast<uint64_t>(in.size_bytes());
internals::WriteTokenStart(MajorType::BYTE_STRING, byte_length, out);
// When emitting UTF16 characters, we always write the least significant byte
// first; this is because it's the native representation for X86.
// TODO(johannes): Implement a more efficient thing here later, e.g.
// casting *iff* the machine has this byte order.
// The wire format for UTF16 chars will probably remain the same
// (least significant byte first) since this way we can have
// golden files, unittests, etc. that port easily and universally.
// See also:
// https://commandcenter.blogspot.com/2012/04/byte-order-fallacy.html
for (const uint16_t two_bytes : in) {
out->push_back(two_bytes);
out->push_back(two_bytes >> 8);
}
}
void EncodeString16(span<uint16_t> in, std::vector<uint8_t>* out) {
EncodeString16Tmpl(in, out);
}
void EncodeString16(span<uint16_t> in, std::string* out) {
EncodeString16Tmpl(in, out);
}
template <typename C>
void EncodeString8Tmpl(span<uint8_t> in, C* out) {
internals::WriteTokenStart(MajorType::STRING,
static_cast<uint64_t>(in.size_bytes()), out);
out->insert(out->end(), in.begin(), in.end());
}
void EncodeString8(span<uint8_t> in, std::vector<uint8_t>* out) {
EncodeString8Tmpl(in, out);
}
void EncodeString8(span<uint8_t> in, std::string* out) {
EncodeString8Tmpl(in, out);
}
template <typename C>
void EncodeFromLatin1Tmpl(span<uint8_t> latin1, C* out) {
for (size_t ii = 0; ii < latin1.size(); ++ii) {
if (latin1[ii] <= 127)
continue;
// If there's at least one non-ASCII char, convert to UTF8.
std::vector<uint8_t> utf8(latin1.begin(), latin1.begin() + ii);
for (; ii < latin1.size(); ++ii) {
if (latin1[ii] <= 127) {
utf8.push_back(latin1[ii]);
} else {
// 0xC0 means it's a UTF8 sequence with 2 bytes.
utf8.push_back((latin1[ii] >> 6) | 0xc0);
utf8.push_back((latin1[ii] | 0x80) & 0xbf);
}
}
EncodeString8(SpanFrom(utf8), out);
return;
}
EncodeString8(latin1, out);
}
void EncodeFromLatin1(span<uint8_t> latin1, std::vector<uint8_t>* out) {
EncodeFromLatin1Tmpl(latin1, out);
}
void EncodeFromLatin1(span<uint8_t> latin1, std::string* out) {
EncodeFromLatin1Tmpl(latin1, out);
}
template <typename C>
void EncodeFromUTF16Tmpl(span<uint16_t> utf16, C* out) {
// If there's at least one non-ASCII char, encode as STRING16 (UTF16).
for (uint16_t ch : utf16) {
if (ch <= 127)
continue;
EncodeString16(utf16, out);
return;
}
// It's all US-ASCII, strip out every second byte and encode as UTF8.
internals::WriteTokenStart(MajorType::STRING,
static_cast<uint64_t>(utf16.size()), out);
out->insert(out->end(), utf16.begin(), utf16.end());
}
void EncodeFromUTF16(span<uint16_t> utf16, std::vector<uint8_t>* out) {
EncodeFromUTF16Tmpl(utf16, out);
}
void EncodeFromUTF16(span<uint16_t> utf16, std::string* out) {
EncodeFromUTF16Tmpl(utf16, out);
}
template <typename C>
void EncodeBinaryTmpl(span<uint8_t> in, C* out) {
out->push_back(kExpectedConversionToBase64Tag);
uint64_t byte_length = static_cast<uint64_t>(in.size_bytes());
internals::WriteTokenStart(MajorType::BYTE_STRING, byte_length, out);
out->insert(out->end(), in.begin(), in.end());
}
void EncodeBinary(span<uint8_t> in, std::vector<uint8_t>* out) {
EncodeBinaryTmpl(in, out);
}
void EncodeBinary(span<uint8_t> in, std::string* out) {
EncodeBinaryTmpl(in, out);
}
// A double is encoded with a specific initial byte
// (kInitialByteForDouble) plus the 64 bits of payload for its value.
constexpr size_t kEncodedDoubleSize = 1 + sizeof(uint64_t);
// An envelope is encoded with a specific initial byte
// (kInitialByteForEnvelope), plus the start byte for a BYTE_STRING with a 32
// bit wide length, plus a 32 bit length for that string.
constexpr size_t kEncodedEnvelopeHeaderSize = 1 + 1 + sizeof(uint32_t);
template <typename C>
void EncodeDoubleTmpl(double value, C* out) {
// The additional_info=27 indicates 64 bits for the double follow.
// See RFC 7049 Section 2.3, Table 1.
out->push_back(kInitialByteForDouble);
union {
double from_double;
uint64_t to_uint64;
} reinterpret;
reinterpret.from_double = value;
WriteBytesMostSignificantByteFirst<uint64_t>(reinterpret.to_uint64, out);
}
void EncodeDouble(double value, std::vector<uint8_t>* out) {
EncodeDoubleTmpl(value, out);
}
void EncodeDouble(double value, std::string* out) {
EncodeDoubleTmpl(value, out);
}
// =============================================================================
// cbor::EnvelopeEncoder - for wrapping submessages
// =============================================================================
template <typename C>
void EncodeStartTmpl(C* out, size_t* byte_size_pos) {
assert(*byte_size_pos == 0);
out->push_back(kInitialByteForEnvelope);
out->push_back(kInitialByteFor32BitLengthByteString);
*byte_size_pos = out->size();
out->resize(out->size() + sizeof(uint32_t));
}
void EnvelopeEncoder::EncodeStart(std::vector<uint8_t>* out) {
EncodeStartTmpl<std::vector<uint8_t>>(out, &byte_size_pos_);
}
void EnvelopeEncoder::EncodeStart(std::string* out) {
EncodeStartTmpl<std::string>(out, &byte_size_pos_);
}
template <typename C>
bool EncodeStopTmpl(C* out, size_t* byte_size_pos) {
assert(*byte_size_pos != 0);
// The byte size is the size of the payload, that is, all the
// bytes that were written past the byte size position itself.
uint64_t byte_size = out->size() - (*byte_size_pos + sizeof(uint32_t));
// We store exactly 4 bytes, so at most INT32MAX, with most significant
// byte first.
if (byte_size > std::numeric_limits<uint32_t>::max())
return false;
for (int shift_bytes = sizeof(uint32_t) - 1; shift_bytes >= 0;
--shift_bytes) {
(*out)[(*byte_size_pos)++] = 0xff & (byte_size >> (shift_bytes * 8));
}
return true;
}
bool EnvelopeEncoder::EncodeStop(std::vector<uint8_t>* out) {
return EncodeStopTmpl(out, &byte_size_pos_);
}
bool EnvelopeEncoder::EncodeStop(std::string* out) {
return EncodeStopTmpl(out, &byte_size_pos_);
}
// =============================================================================
// cbor::NewCBOREncoder - for encoding from a streaming parser
// =============================================================================
namespace {
template <typename C>
class CBOREncoder : public StreamingParserHandler {
public:
CBOREncoder(C* out, Status* status) : out_(out), status_(status) {
*status_ = Status();
}
void HandleMapBegin() override {
if (!status_->ok())
return;
envelopes_.emplace_back();
envelopes_.back().EncodeStart(out_);
out_->push_back(kInitialByteIndefiniteLengthMap);
}
void HandleMapEnd() override {
if (!status_->ok())
return;
out_->push_back(kStopByte);
assert(!envelopes_.empty());
if (!envelopes_.back().EncodeStop(out_)) {
HandleError(
Status(Error::CBOR_ENVELOPE_SIZE_LIMIT_EXCEEDED, out_->size()));
return;
}
envelopes_.pop_back();
}
void HandleArrayBegin() override {
if (!status_->ok())
return;
envelopes_.emplace_back();
envelopes_.back().EncodeStart(out_);
out_->push_back(kInitialByteIndefiniteLengthArray);
}
void HandleArrayEnd() override {
if (!status_->ok())
return;
out_->push_back(kStopByte);
assert(!envelopes_.empty());
if (!envelopes_.back().EncodeStop(out_)) {
HandleError(
Status(Error::CBOR_ENVELOPE_SIZE_LIMIT_EXCEEDED, out_->size()));
return;
}
envelopes_.pop_back();
}
void HandleString8(span<uint8_t> chars) override {
if (!status_->ok())
return;
EncodeString8(chars, out_);
}
void HandleString16(span<uint16_t> chars) override {
if (!status_->ok())
return;
EncodeFromUTF16(chars, out_);
}
void HandleBinary(span<uint8_t> bytes) override {
if (!status_->ok())
return;
EncodeBinary(bytes, out_);
}
void HandleDouble(double value) override {
if (!status_->ok())
return;
EncodeDouble(value, out_);
}
void HandleInt32(int32_t value) override {
if (!status_->ok())
return;
EncodeInt32(value, out_);
}
void HandleBool(bool value) override {
if (!status_->ok())
return;
// See RFC 7049 Section 2.3, Table 2.
out_->push_back(value ? kEncodedTrue : kEncodedFalse);
}
void HandleNull() override {
if (!status_->ok())
return;
// See RFC 7049 Section 2.3, Table 2.
out_->push_back(kEncodedNull);
}
void HandleError(Status error) override {
if (!status_->ok())
return;
*status_ = error;
out_->clear();
}
private:
C* out_;
std::vector<EnvelopeEncoder> envelopes_;
Status* status_;
};
} // namespace
std::unique_ptr<StreamingParserHandler> NewCBOREncoder(
std::vector<uint8_t>* out,
Status* status) {
return std::unique_ptr<StreamingParserHandler>(
new CBOREncoder<std::vector<uint8_t>>(out, status));
}
std::unique_ptr<StreamingParserHandler> NewCBOREncoder(std::string* out,
Status* status) {
return std::unique_ptr<StreamingParserHandler>(
new CBOREncoder<std::string>(out, status));
}
// =============================================================================
// cbor::CBORTokenizer - for parsing individual CBOR items
// =============================================================================
CBORTokenizer::CBORTokenizer(span<uint8_t> bytes) : bytes_(bytes) {
ReadNextToken(/*enter_envelope=*/false);
}
CBORTokenizer::~CBORTokenizer() {}
CBORTokenTag CBORTokenizer::TokenTag() const {
return token_tag_;
}
void CBORTokenizer::Next() {
if (token_tag_ == CBORTokenTag::ERROR_VALUE ||
token_tag_ == CBORTokenTag::DONE)
return;
ReadNextToken(/*enter_envelope=*/false);
}
void CBORTokenizer::EnterEnvelope() {
assert(token_tag_ == CBORTokenTag::ENVELOPE);
ReadNextToken(/*enter_envelope=*/true);
}
Status CBORTokenizer::Status() const {
return status_;
}
// The following accessor functions ::GetInt32, ::GetDouble,
// ::GetString8, ::GetString16WireRep, ::GetBinary, ::GetEnvelopeContents
// assume that a particular token was recognized in ::ReadNextToken.
// That's where all the error checking is done. By design,
// the accessors (assuming the token was recognized) never produce
// an error.
int32_t CBORTokenizer::GetInt32() const {
assert(token_tag_ == CBORTokenTag::INT32);
// The range checks happen in ::ReadNextToken().
return static_cast<int32_t>(
token_start_type_ == MajorType::UNSIGNED
? token_start_internal_value_
: -static_cast<int64_t>(token_start_internal_value_) - 1);
}
double CBORTokenizer::GetDouble() const {
assert(token_tag_ == CBORTokenTag::DOUBLE);
union {
uint64_t from_uint64;
double to_double;
} reinterpret;
reinterpret.from_uint64 = ReadBytesMostSignificantByteFirst<uint64_t>(
bytes_.subspan(status_.pos + 1));
return reinterpret.to_double;
}
span<uint8_t> CBORTokenizer::GetString8() const {
assert(token_tag_ == CBORTokenTag::STRING8);
auto length = static_cast<size_t>(token_start_internal_value_);
return bytes_.subspan(status_.pos + (token_byte_length_ - length), length);
}
span<uint8_t> CBORTokenizer::GetString16WireRep() const {
assert(token_tag_ == CBORTokenTag::STRING16);
auto length = static_cast<size_t>(token_start_internal_value_);
return bytes_.subspan(status_.pos + (token_byte_length_ - length), length);
}
span<uint8_t> CBORTokenizer::GetBinary() const {
assert(token_tag_ == CBORTokenTag::BINARY);
auto length = static_cast<size_t>(token_start_internal_value_);
return bytes_.subspan(status_.pos + (token_byte_length_ - length), length);
}
span<uint8_t> CBORTokenizer::GetEnvelopeContents() const {
assert(token_tag_ == CBORTokenTag::ENVELOPE);
auto length = static_cast<size_t>(token_start_internal_value_);
return bytes_.subspan(status_.pos + kEncodedEnvelopeHeaderSize, length);
}
// All error checking happens in ::ReadNextToken, so that the accessors
// can avoid having to carry an error return value.
//
// With respect to checking the encoded lengths of strings, arrays, etc:
// On the wire, CBOR uses 1,2,4, and 8 byte unsigned integers, so
// we initially read them as uint64_t, usually into token_start_internal_value_.
//
// However, since these containers have a representation on the machine,
// we need to do corresponding size computations on the input byte array,
// output span (e.g. the payload for a string), etc., and size_t is
// machine specific (in practice either 32 bit or 64 bit).
//
// Further, we must avoid overflowing size_t. Therefore, we use this
// kMaxValidLength constant to:
// - Reject values that are larger than the architecture specific
// max size_t (differs between 32 bit and 64 bit arch).
// - Reserve at least one bit so that we can check against overflows
// when adding lengths (array / string length / etc.); we do this by
// ensuring that the inputs to an addition are <= kMaxValidLength,
// and then checking whether the sum went past it.
//
// See also
// https://chromium.googlesource.com/chromium/src/+/HEAD/docs/security/integer-semantics.md
static const uint64_t kMaxValidLength =
std::min<uint64_t>(std::numeric_limits<uint64_t>::max() >> 2,
std::numeric_limits<size_t>::max());
void CBORTokenizer::ReadNextToken(bool enter_envelope) {
if (enter_envelope) {
status_.pos += kEncodedEnvelopeHeaderSize;
} else {
status_.pos =
status_.pos == Status::npos() ? 0 : status_.pos + token_byte_length_;
}
status_.error = Error::OK;
if (status_.pos >= bytes_.size()) {
token_tag_ = CBORTokenTag::DONE;
return;
}
const size_t remaining_bytes = bytes_.size() - status_.pos;
switch (bytes_[status_.pos]) {
case kStopByte:
SetToken(CBORTokenTag::STOP, 1);
return;
case kInitialByteIndefiniteLengthMap:
SetToken(CBORTokenTag::MAP_START, 1);
return;
case kInitialByteIndefiniteLengthArray:
SetToken(CBORTokenTag::ARRAY_START, 1);
return;
case kEncodedTrue:
SetToken(CBORTokenTag::TRUE_VALUE, 1);
return;
case kEncodedFalse:
SetToken(CBORTokenTag::FALSE_VALUE, 1);
return;
case kEncodedNull:
SetToken(CBORTokenTag::NULL_VALUE, 1);
return;
case kExpectedConversionToBase64Tag: { // BINARY
const size_t bytes_read = internals::ReadTokenStart(
bytes_.subspan(status_.pos + 1), &token_start_type_,
&token_start_internal_value_);
if (!bytes_read || token_start_type_ != MajorType::BYTE_STRING ||
token_start_internal_value_ > kMaxValidLength) {
SetError(Error::CBOR_INVALID_BINARY);
return;
}
const uint64_t token_byte_length = token_start_internal_value_ +
/* tag before token start: */ 1 +
/* token start: */ bytes_read;
if (token_byte_length > remaining_bytes) {
SetError(Error::CBOR_INVALID_BINARY);
return;
}
SetToken(CBORTokenTag::BINARY, static_cast<size_t>(token_byte_length));
return;
}
case kInitialByteForDouble: { // DOUBLE
if (kEncodedDoubleSize > remaining_bytes) {
SetError(Error::CBOR_INVALID_DOUBLE);
return;
}
SetToken(CBORTokenTag::DOUBLE, kEncodedDoubleSize);
return;
}
case kInitialByteForEnvelope: { // ENVELOPE
if (kEncodedEnvelopeHeaderSize > remaining_bytes) {
SetError(Error::CBOR_INVALID_ENVELOPE);
return;
}
// The envelope must be a byte string with 32 bit length.
if (bytes_[status_.pos + 1] != kInitialByteFor32BitLengthByteString) {
SetError(Error::CBOR_INVALID_ENVELOPE);
return;
}
// Read the length of the byte string.
token_start_internal_value_ = ReadBytesMostSignificantByteFirst<uint32_t>(
bytes_.subspan(status_.pos + 2));
if (token_start_internal_value_ > kMaxValidLength) {
SetError(Error::CBOR_INVALID_ENVELOPE);
return;
}
uint64_t token_byte_length =
token_start_internal_value_ + kEncodedEnvelopeHeaderSize;
if (token_byte_length > remaining_bytes) {
SetError(Error::CBOR_INVALID_ENVELOPE);
return;
}
SetToken(CBORTokenTag::ENVELOPE, static_cast<size_t>(token_byte_length));
return;
}
default: {
const size_t bytes_read = internals::ReadTokenStart(
bytes_.subspan(status_.pos), &token_start_type_,
&token_start_internal_value_);
switch (token_start_type_) {
case MajorType::UNSIGNED: // INT32.
// INT32 is a signed int32 (int32 makes sense for the
// inspector_protocol, it's not a CBOR limitation), so we check
// against the signed max, so that the allowable values are
// 0, 1, 2, ... 2^31 - 1.
if (!bytes_read ||
static_cast<int64_t>(std::numeric_limits<int32_t>::max()) <
static_cast<int64_t>(token_start_internal_value_)) {
SetError(Error::CBOR_INVALID_INT32);
return;
}
SetToken(CBORTokenTag::INT32, bytes_read);
return;
case MajorType::NEGATIVE: { // INT32.
// INT32 is a signed int32 (int32 makes sense for the
// inspector_protocol, it's not a CBOR limitation); in CBOR, the
// negative values for INT32 are represented as NEGATIVE, that is, -1
// INT32 is represented as 1 << 5 | 0 (major type 1, additional info
// value 0).
// The represented allowed values range is -1 to -2^31.
// They are mapped into the encoded range of 0 to 2^31-1.
// We check the payload in token_start_internal_value_ against
// that range (2^31-1 is also known as
// std::numeric_limits<int32_t>::max()).
if (!bytes_read ||
static_cast<int64_t>(token_start_internal_value_) >
static_cast<int64_t>(std::numeric_limits<int32_t>::max())) {
SetError(Error::CBOR_INVALID_INT32);
return;
}
SetToken(CBORTokenTag::INT32, bytes_read);
return;
}
case MajorType::STRING: { // STRING8.
if (!bytes_read || token_start_internal_value_ > kMaxValidLength) {
SetError(Error::CBOR_INVALID_STRING8);
return;
}
uint64_t token_byte_length = token_start_internal_value_ + bytes_read;
if (token_byte_length > remaining_bytes) {
SetError(Error::CBOR_INVALID_STRING8);
return;
}
SetToken(CBORTokenTag::STRING8,
static_cast<size_t>(token_byte_length));
return;
}
case MajorType::BYTE_STRING: { // STRING16.
// Length must be divisible by 2 since UTF16 is 2 bytes per
// character, hence the &1 check.
if (!bytes_read || token_start_internal_value_ > kMaxValidLength ||
token_start_internal_value_ & 1) {
SetError(Error::CBOR_INVALID_STRING16);
return;
}
uint64_t token_byte_length = token_start_internal_value_ + bytes_read;
if (token_byte_length > remaining_bytes) {
SetError(Error::CBOR_INVALID_STRING16);
return;
}
SetToken(CBORTokenTag::STRING16,
static_cast<size_t>(token_byte_length));
return;
}
case MajorType::ARRAY:
case MajorType::MAP:
case MajorType::TAG:
case MajorType::SIMPLE_VALUE:
SetError(Error::CBOR_UNSUPPORTED_VALUE);
return;
}
}
}
}
void CBORTokenizer::SetToken(CBORTokenTag token_tag, size_t token_byte_length) {
token_tag_ = token_tag;
token_byte_length_ = token_byte_length;
}
void CBORTokenizer::SetError(Error error) {
token_tag_ = CBORTokenTag::ERROR_VALUE;
status_.error = error;
}
// =============================================================================
// cbor::ParseCBOR - for receiving streaming parser events for CBOR messages
// =============================================================================
namespace {
// When parsing CBOR, we limit recursion depth for objects and arrays
// to this constant.
static constexpr int kStackLimit = 300;
// Below are three parsing routines for CBOR, which cover enough
// to roundtrip JSON messages.
bool ParseMap(int32_t stack_depth,
CBORTokenizer* tokenizer,
StreamingParserHandler* out);
bool ParseArray(int32_t stack_depth,
CBORTokenizer* tokenizer,
StreamingParserHandler* out);
bool ParseValue(int32_t stack_depth,
CBORTokenizer* tokenizer,
StreamingParserHandler* out);
void ParseUTF16String(CBORTokenizer* tokenizer, StreamingParserHandler* out) {
std::vector<uint16_t> value;
span<uint8_t> rep = tokenizer->GetString16WireRep();
for (size_t ii = 0; ii < rep.size(); ii += 2)
value.push_back((rep[ii + 1] << 8) | rep[ii]);
out->HandleString16(span<uint16_t>(value.data(), value.size()));
tokenizer->Next();
}
bool ParseUTF8String(CBORTokenizer* tokenizer, StreamingParserHandler* out) {
assert(tokenizer->TokenTag() == CBORTokenTag::STRING8);
out->HandleString8(tokenizer->GetString8());
tokenizer->Next();
return true;
}
bool ParseValue(int32_t stack_depth,
CBORTokenizer* tokenizer,
StreamingParserHandler* out) {
if (stack_depth > kStackLimit) {
out->HandleError(
Status{Error::CBOR_STACK_LIMIT_EXCEEDED, tokenizer->Status().pos});
return false;
}
// Skip past the envelope to get to what's inside.
if (tokenizer->TokenTag() == CBORTokenTag::ENVELOPE)
tokenizer->EnterEnvelope();
switch (tokenizer->TokenTag()) {
case CBORTokenTag::ERROR_VALUE:
out->HandleError(tokenizer->Status());
return false;
case CBORTokenTag::DONE:
out->HandleError(Status{Error::CBOR_UNEXPECTED_EOF_EXPECTED_VALUE,
tokenizer->Status().pos});
return false;
case CBORTokenTag::TRUE_VALUE:
out->HandleBool(true);
tokenizer->Next();
return true;
case CBORTokenTag::FALSE_VALUE:
out->HandleBool(false);
tokenizer->Next();
return true;
case CBORTokenTag::NULL_VALUE:
out->HandleNull();
tokenizer->Next();
return true;
case CBORTokenTag::INT32:
out->HandleInt32(tokenizer->GetInt32());
tokenizer->Next();
return true;
case CBORTokenTag::DOUBLE:
out->HandleDouble(tokenizer->GetDouble());
tokenizer->Next();
return true;
case CBORTokenTag::STRING8:
return ParseUTF8String(tokenizer, out);
case CBORTokenTag::STRING16:
ParseUTF16String(tokenizer, out);
return true;
case CBORTokenTag::BINARY: {
out->HandleBinary(tokenizer->GetBinary());
tokenizer->Next();
return true;
}
case CBORTokenTag::MAP_START:
return ParseMap(stack_depth + 1, tokenizer, out);
case CBORTokenTag::ARRAY_START:
return ParseArray(stack_depth + 1, tokenizer, out);
default:
out->HandleError(
Status{Error::CBOR_UNSUPPORTED_VALUE, tokenizer->Status().pos});
return false;
}
}
// |bytes| must start with the indefinite length array byte, so basically,
// ParseArray may only be called after an indefinite length array has been
// detected.
bool ParseArray(int32_t stack_depth,
CBORTokenizer* tokenizer,
StreamingParserHandler* out) {
assert(tokenizer->TokenTag() == CBORTokenTag::ARRAY_START);
tokenizer->Next();
out->HandleArrayBegin();
while (tokenizer->TokenTag() != CBORTokenTag::STOP) {
if (tokenizer->TokenTag() == CBORTokenTag::DONE) {
out->HandleError(
Status{Error::CBOR_UNEXPECTED_EOF_IN_ARRAY, tokenizer->Status().pos});
return false;
}
if (tokenizer->TokenTag() == CBORTokenTag::ERROR_VALUE) {
out->HandleError(tokenizer->Status());
return false;
}
// Parse value.
if (!ParseValue(stack_depth, tokenizer, out))
return false;
}
out->HandleArrayEnd();
tokenizer->Next();
return true;
}
// |bytes| must start with the indefinite length array byte, so basically,
// ParseArray may only be called after an indefinite length array has been
// detected.
bool ParseMap(int32_t stack_depth,
CBORTokenizer* tokenizer,
StreamingParserHandler* out) {
assert(tokenizer->TokenTag() == CBORTokenTag::MAP_START);
out->HandleMapBegin();
tokenizer->Next();
while (tokenizer->TokenTag() != CBORTokenTag::STOP) {
if (tokenizer->TokenTag() == CBORTokenTag::DONE) {
out->HandleError(
Status{Error::CBOR_UNEXPECTED_EOF_IN_MAP, tokenizer->Status().pos});
return false;
}
if (tokenizer->TokenTag() == CBORTokenTag::ERROR_VALUE) {
out->HandleError(tokenizer->Status());
return false;
}
// Parse key.
if (tokenizer->TokenTag() == CBORTokenTag::STRING8) {
if (!ParseUTF8String(tokenizer, out))
return false;
} else if (tokenizer->TokenTag() == CBORTokenTag::STRING16) {
ParseUTF16String(tokenizer, out);
} else {
out->HandleError(
Status{Error::CBOR_INVALID_MAP_KEY, tokenizer->Status().pos});
return false;
}
// Parse value.
if (!ParseValue(stack_depth, tokenizer, out))
return false;
}
out->HandleMapEnd();
tokenizer->Next();
return true;
}
} // namespace
void ParseCBOR(span<uint8_t> bytes, StreamingParserHandler* out) {
if (bytes.empty()) {
out->HandleError(Status{Error::CBOR_NO_INPUT, 0});
return;
}
if (bytes[0] != kInitialByteForEnvelope) {
out->HandleError(Status{Error::CBOR_INVALID_START_BYTE, 0});
return;
}
CBORTokenizer tokenizer(bytes);
if (tokenizer.TokenTag() == CBORTokenTag::ERROR_VALUE) {
out->HandleError(tokenizer.Status());
return;
}
// We checked for the envelope start byte above, so the tokenizer
// must agree here, since it's not an error.
assert(tokenizer.TokenTag() == CBORTokenTag::ENVELOPE);
tokenizer.EnterEnvelope();
if (tokenizer.TokenTag() != CBORTokenTag::MAP_START) {
out->HandleError(
Status{Error::CBOR_MAP_START_EXPECTED, tokenizer.Status().pos});
return;
}
if (!ParseMap(/*stack_depth=*/1, &tokenizer, out))
return;
if (tokenizer.TokenTag() == CBORTokenTag::DONE)
return;
if (tokenizer.TokenTag() == CBORTokenTag::ERROR_VALUE) {
out->HandleError(tokenizer.Status());
return;
}
out->HandleError(Status{Error::CBOR_TRAILING_JUNK, tokenizer.Status().pos});
}
// =============================================================================
// cbor::AppendString8EntryToMap - for limited in-place editing of messages
// =============================================================================
template <typename C>
Status AppendString8EntryToCBORMapTmpl(span<uint8_t> string8_key,
span<uint8_t> string8_value,
C* cbor) {
// Careful below: Don't compare (*cbor)[idx] with a uint8_t, since
// it could be a char (signed!). Instead, use bytes.
span<uint8_t> bytes(reinterpret_cast<const uint8_t*>(cbor->data()),
cbor->size());
CBORTokenizer tokenizer(bytes);
if (tokenizer.TokenTag() == CBORTokenTag::ERROR_VALUE)
return tokenizer.Status();
if (tokenizer.TokenTag() != CBORTokenTag::ENVELOPE)
return Status(Error::CBOR_INVALID_ENVELOPE, 0);
size_t envelope_size = tokenizer.GetEnvelopeContents().size();
size_t old_size = cbor->size();
if (old_size != envelope_size + kEncodedEnvelopeHeaderSize)
return Status(Error::CBOR_INVALID_ENVELOPE, 0);
if (envelope_size == 0 ||
(tokenizer.GetEnvelopeContents()[0] != EncodeIndefiniteLengthMapStart()))
return Status(Error::CBOR_MAP_START_EXPECTED, kEncodedEnvelopeHeaderSize);
if (bytes[bytes.size() - 1] != EncodeStop())
return Status(Error::CBOR_MAP_STOP_EXPECTED, cbor->size() - 1);
cbor->pop_back();
EncodeString8(string8_key, cbor);
EncodeString8(string8_value, cbor);
cbor->push_back(EncodeStop());
size_t new_envelope_size = envelope_size + (cbor->size() - old_size);
if (new_envelope_size > std::numeric_limits<uint32_t>::max())
return Status(Error::CBOR_ENVELOPE_SIZE_LIMIT_EXCEEDED, 0);
size_t size_pos = cbor->size() - new_envelope_size - sizeof(uint32_t);
uint8_t* out = reinterpret_cast<uint8_t*>(&cbor->at(size_pos));
*(out++) = (new_envelope_size >> 24) & 0xff;
*(out++) = (new_envelope_size >> 16) & 0xff;
*(out++) = (new_envelope_size >> 8) & 0xff;
*(out) = new_envelope_size & 0xff;
return Status();
}
Status AppendString8EntryToCBORMap(span<uint8_t> string8_key,
span<uint8_t> string8_value,
std::vector<uint8_t>* cbor) {
return AppendString8EntryToCBORMapTmpl(string8_key, string8_value, cbor);
}
Status AppendString8EntryToCBORMap(span<uint8_t> string8_key,
span<uint8_t> string8_value,
std::string* cbor) {
return AppendString8EntryToCBORMapTmpl(string8_key, string8_value, cbor);
}
} // namespace cbor
namespace json {
// =============================================================================
// json::NewJSONEncoder - for encoding streaming parser events as JSON
// =============================================================================
namespace {
// Prints |value| to |out| with 4 hex digits, most significant chunk first.
template <typename C>
void PrintHex(uint16_t value, C* out) {
for (int ii = 3; ii >= 0; --ii) {
int four_bits = 0xf & (value >> (4 * ii));
out->push_back(four_bits + ((four_bits <= 9) ? '0' : ('a' - 10)));
}
}
// In the writer below, we maintain a stack of State instances.
// It is just enough to emit the appropriate delimiters and brackets
// in JSON.
enum class Container {
// Used for the top-level, initial state.
NONE,
// Inside a JSON object.
MAP,
// Inside a JSON array.
ARRAY
};
class State {
public:
explicit State(Container container) : container_(container) {}
void StartElement(std::vector<uint8_t>* out) { StartElementTmpl(out); }
void StartElement(std::string* out) { StartElementTmpl(out); }
Container container() const { return container_; }
private:
template <typename C>
void StartElementTmpl(C* out) {
assert(container_ != Container::NONE || size_ == 0);
if (size_ != 0) {
char delim = (!(size_ & 1) || container_ == Container::ARRAY) ? ',' : ':';
out->push_back(delim);
}
++size_;
}
Container container_ = Container::NONE;
int size_ = 0;
};
constexpr char kBase64Table[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz0123456789+/";
template <typename C>
void Base64Encode(const span<uint8_t>& in, C* out) {
// The following three cases are based on the tables in the example
// section in https://en.wikipedia.org/wiki/Base64. We process three
// input bytes at a time, emitting 4 output bytes at a time.
size_t ii = 0;
// While possible, process three input bytes.
for (; ii + 3 <= in.size(); ii += 3) {
uint32_t twentyfour_bits = (in[ii] << 16) | (in[ii + 1] << 8) | in[ii + 2];
out->push_back(kBase64Table[(twentyfour_bits >> 18)]);
out->push_back(kBase64Table[(twentyfour_bits >> 12) & 0x3f]);
out->push_back(kBase64Table[(twentyfour_bits >> 6) & 0x3f]);
out->push_back(kBase64Table[twentyfour_bits & 0x3f]);
}
if (ii + 2 <= in.size()) { // Process two input bytes.
uint32_t twentyfour_bits = (in[ii] << 16) | (in[ii + 1] << 8);
out->push_back(kBase64Table[(twentyfour_bits >> 18)]);
out->push_back(kBase64Table[(twentyfour_bits >> 12) & 0x3f]);
out->push_back(kBase64Table[(twentyfour_bits >> 6) & 0x3f]);
out->push_back('='); // Emit padding.
return;
}
if (ii + 1 <= in.size()) { // Process a single input byte.
uint32_t twentyfour_bits = (in[ii] << 16);
out->push_back(kBase64Table[(twentyfour_bits >> 18)]);
out->push_back(kBase64Table[(twentyfour_bits >> 12) & 0x3f]);
out->push_back('='); // Emit padding.
out->push_back('='); // Emit padding.
}
}
// Implements a handler for JSON parser events to emit a JSON string.
template <typename C>
class JSONEncoder : public StreamingParserHandler {
public:
JSONEncoder(const Platform* platform, C* out, Status* status)
: platform_(platform), out_(out), status_(status) {
*status_ = Status();
state_.emplace(Container::NONE);
}
void HandleMapBegin() override {
if (!status_->ok())
return;
assert(!state_.empty());
state_.top().StartElement(out_);
state_.emplace(Container::MAP);
Emit('{');
}
void HandleMapEnd() override {
if (!status_->ok())
return;
assert(state_.size() >= 2 && state_.top().container() == Container::MAP);
state_.pop();
Emit('}');
}
void HandleArrayBegin() override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
state_.emplace(Container::ARRAY);
Emit('[');
}
void HandleArrayEnd() override {
if (!status_->ok())
return;
assert(state_.size() >= 2 && state_.top().container() == Container::ARRAY);
state_.pop();
Emit(']');
}
void HandleString16(span<uint16_t> chars) override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
Emit('"');
for (const uint16_t ch : chars) {
if (ch == '"') {
Emit("\\\"");
} else if (ch == '\\') {
Emit("\\\\");
} else if (ch == '\b') {
Emit("\\b");
} else if (ch == '\f') {
Emit("\\f");
} else if (ch == '\n') {
Emit("\\n");
} else if (ch == '\r') {
Emit("\\r");
} else if (ch == '\t') {
Emit("\\t");
} else if (ch >= 32 && ch <= 126) {
Emit(ch);
} else {
Emit("\\u");
PrintHex(ch, out_);
}
}
Emit('"');
}
void HandleString8(span<uint8_t> chars) override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
Emit('"');
for (size_t ii = 0; ii < chars.size(); ++ii) {
uint8_t c = chars[ii];
if (c == '"') {
Emit("\\\"");
} else if (c == '\\') {
Emit("\\\\");
} else if (c == '\b') {
Emit("\\b");
} else if (c == '\f') {
Emit("\\f");
} else if (c == '\n') {
Emit("\\n");
} else if (c == '\r') {
Emit("\\r");
} else if (c == '\t') {
Emit("\\t");
} else if (c >= 32 && c <= 126) {
Emit(c);
} else if (c < 32) {
Emit("\\u");
PrintHex(static_cast<uint16_t>(c), out_);
} else {
// Inspect the leading byte to figure out how long the utf8
// byte sequence is; while doing this initialize |codepoint|
// with the first few bits.
// See table in: https://en.wikipedia.org/wiki/UTF-8
// byte one is 110x xxxx -> 2 byte utf8 sequence
// byte one is 1110 xxxx -> 3 byte utf8 sequence
// byte one is 1111 0xxx -> 4 byte utf8 sequence
uint32_t codepoint;
int num_bytes_left;
if ((c & 0xe0) == 0xc0) { // 2 byte utf8 sequence
num_bytes_left = 1;
codepoint = c & 0x1f;
} else if ((c & 0xf0) == 0xe0) { // 3 byte utf8 sequence
num_bytes_left = 2;
codepoint = c & 0x0f;
} else if ((c & 0xf8) == 0xf0) { // 4 byte utf8 sequence
codepoint = c & 0x07;
num_bytes_left = 3;
} else {
continue; // invalid leading byte
}
// If we have enough bytes in our input, decode the remaining ones
// belonging to this Unicode character into |codepoint|.
if (ii + num_bytes_left > chars.size())
continue;
while (num_bytes_left > 0) {
c = chars[++ii];
--num_bytes_left;
// Check the next byte is a continuation byte, that is 10xx xxxx.
if ((c & 0xc0) != 0x80)
continue;
codepoint = (codepoint << 6) | (c & 0x3f);
}
// Disallow overlong encodings for ascii characters, as these
// would include " and other characters significant to JSON
// string termination / control.
if (codepoint <= 0x7f)
continue;
// Invalid in UTF8, and can't be represented in UTF16 anyway.
if (codepoint > 0x10ffff)
continue;
// So, now we transcode to UTF16,
// using the math described at https://en.wikipedia.org/wiki/UTF-16,
// for either one or two 16 bit characters.
if (codepoint < 0xffff) {
Emit("\\u");
PrintHex(static_cast<uint16_t>(codepoint), out_);
continue;
}
codepoint -= 0x10000;
// high surrogate
Emit("\\u");
PrintHex(static_cast<uint16_t>((codepoint >> 10) + 0xd800), out_);
// low surrogate
Emit("\\u");
PrintHex(static_cast<uint16_t>((codepoint & 0x3ff) + 0xdc00), out_);
}
}
Emit('"');
}
void HandleBinary(span<uint8_t> bytes) override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
Emit('"');
Base64Encode(bytes, out_);
Emit('"');
}
void HandleDouble(double value) override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
// JSON cannot represent NaN or Infinity. So, for compatibility,
// we behave like the JSON object in web browsers: emit 'null'.
if (!std::isfinite(value)) {
Emit("null");
return;
}
std::unique_ptr<char[]> str_value = platform_->DToStr(value);
// DToStr may fail to emit a 0 before the decimal dot. E.g. this is
// the case in base::NumberToString in Chromium (which is based on
// dmg_fp). So, much like
// https://cs.chromium.org/chromium/src/base/json/json_writer.cc
// we probe for this and emit the leading 0 anyway if necessary.
const char* chars = str_value.get();
if (chars[0] == '.') {
Emit('0');
} else if (chars[0] == '-' && chars[1] == '.') {
Emit("-0");
++chars;
}
Emit(chars);
}
void HandleInt32(int32_t value) override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
Emit(std::to_string(value));
}
void HandleBool(bool value) override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
Emit(value ? "true" : "false");
}
void HandleNull() override {
if (!status_->ok())
return;
state_.top().StartElement(out_);
Emit("null");
}
void HandleError(Status error) override {
assert(!error.ok());
*status_ = error;
out_->clear();
}
private:
void Emit(char c) { out_->push_back(c); }
void Emit(const char* str) {
out_->insert(out_->end(), str, str + strlen(str));
}
void Emit(const std::string& str) {
out_->insert(out_->end(), str.begin(), str.end());
}
const Platform* platform_;
C* out_;
Status* status_;
std::stack<State> state_;
};
} // namespace
std::unique_ptr<StreamingParserHandler> NewJSONEncoder(
const Platform* platform,
std::vector<uint8_t>* out,
Status* status) {
return std::unique_ptr<StreamingParserHandler>(
new JSONEncoder<std::vector<uint8_t>>(platform, out, status));
}
std::unique_ptr<StreamingParserHandler> NewJSONEncoder(const Platform* platform,
std::string* out,
Status* status) {
return std::unique_ptr<StreamingParserHandler>(
new JSONEncoder<std::string>(platform, out, status));
}
// =============================================================================
// json::ParseJSON - for receiving streaming parser events for JSON.
// =============================================================================
namespace {
const int kStackLimit = 300;
enum Token {
ObjectBegin,
ObjectEnd,
ArrayBegin,
ArrayEnd,
StringLiteral,
Number,
BoolTrue,
BoolFalse,
NullToken,
ListSeparator,
ObjectPairSeparator,
InvalidToken,
NoInput
};
const char* const kNullString = "null";
const char* const kTrueString = "true";
const char* const kFalseString = "false";
template <typename Char>
class JsonParser {
public:
JsonParser(const Platform* platform, StreamingParserHandler* handler)
: platform_(platform), handler_(handler) {}
void Parse(const Char* start, size_t length) {
start_pos_ = start;
const Char* end = start + length;
const Char* tokenEnd = nullptr;
ParseValue(start, end, &tokenEnd, 0);
if (error_)
return;
if (tokenEnd != end) {
HandleError(Error::JSON_PARSER_UNPROCESSED_INPUT_REMAINS, tokenEnd);
}
}
private:
bool CharsToDouble(const uint16_t* chars, size_t length, double* result) {
std::string buffer;
buffer.reserve(length + 1);
for (size_t ii = 0; ii < length; ++ii) {
bool is_ascii = !(chars[ii] & ~0x7F);
if (!is_ascii)
return false;
buffer.push_back(static_cast<char>(chars[ii]));
}
return platform_->StrToD(buffer.c_str(), result);
}
bool CharsToDouble(const uint8_t* chars, size_t length, double* result) {
std::string buffer(reinterpret_cast<const char*>(chars), length);
return platform_->StrToD(buffer.c_str(), result);
}
static bool ParseConstToken(const Char* start,
const Char* end,
const Char** token_end,
const char* token) {
// |token| is \0 terminated, it's one of the constants at top of the file.
while (start < end && *token != '\0' && *start++ == *token++) {
}
if (*token != '\0')
return false;
*token_end = start;
return true;
}
static bool ReadInt(const Char* start,
const Char* end,
const Char** token_end,
bool allow_leading_zeros) {
if (start == end)
return false;
bool has_leading_zero = '0' == *start;
int length = 0;
while (start < end && '0' <= *start && *start <= '9') {
++start;
++length;
}
if (!length)
return false;
if (!allow_leading_zeros && length > 1 && has_leading_zero)
return false;
*token_end = start;
return true;
}
static bool ParseNumberToken(const Char* start,
const Char* end,
const Char** token_end) {
// We just grab the number here. We validate the size in DecodeNumber.
// According to RFC4627, a valid number is: [minus] int [frac] [exp]
if (start == end)
return false;
Char c = *start;
if ('-' == c)
++start;
if (!ReadInt(start, end, &start, /*allow_leading_zeros=*/false))
return false;
if (start == end) {
*token_end = start;
return true;
}
// Optional fraction part
c = *start;
if ('.' == c) {
++start;
if (!ReadInt(start, end, &start, /*allow_leading_zeros=*/true))
return false;
if (start == end) {
*token_end = start;
return true;
}
c = *start;
}
// Optional exponent part
if ('e' == c || 'E' == c) {
++start;
if (start == end)
return false;
c = *start;
if ('-' == c || '+' == c) {
++start;
if (start == end)
return false;
}
if (!ReadInt(start, end, &start, /*allow_leading_zeros=*/true))
return false;
}
*token_end = start;
return true;
}
static bool ReadHexDigits(const Char* start,
const Char* end,
const Char** token_end,
int digits) {
if (end - start < digits)
return false;
for (int i = 0; i < digits; ++i) {
Char c = *start++;
if (!(('0' <= c && c <= '9') || ('a' <= c && c <= 'f') ||
('A' <= c && c <= 'F')))
return false;
}
*token_end = start;
return true;
}
static bool ParseStringToken(const Char* start,
const Char* end,
const Char** token_end) {
while (start < end) {
Char c = *start++;
if ('\\' == c) {
if (start == end)
return false;
c = *start++;
// Make sure the escaped char is valid.
switch (c) {
case 'x':
if (!ReadHexDigits(start, end, &start, 2))
return false;
break;
case 'u':
if (!ReadHexDigits(start, end, &start, 4))
return false;
break;
case '\\':
case '/':
case 'b':
case 'f':
case 'n':
case 'r':
case 't':
case 'v':
case '"':
break;
default:
return false;
}
} else if ('"' == c) {
*token_end = start;
return true;
}
}
return false;
}
static bool SkipComment(const Char* start,
const Char* end,
const Char** comment_end) {
if (start == end)
return false;
if (*start != '/' || start + 1 >= end)
return false;
++start;
if (*start == '/') {
// Single line comment, read to newline.
for (++start; start < end; ++start) {
if (*start == '\n' || *start == '\r') {
*comment_end = start + 1;
return true;
}
}
*comment_end = end;
// Comment reaches end-of-input, which is fine.
return true;
}
if (*start == '*') {
Char previous = '\0';
// Block comment, read until end marker.
for (++start; start < end; previous = *start++) {
if (previous == '*' && *start == '/') {
*comment_end = start + 1;
return true;
}
}
// Block comment must close before end-of-input.
return false;
}
return false;
}
static bool IsSpaceOrNewLine(Char c) {
// \v = vertial tab; \f = form feed page break.
return c == ' ' || c == '\n' || c == '\v' || c == '\f' || c == '\r' ||
c == '\t';
}
static void SkipWhitespaceAndComments(const Char* start,
const Char* end,
const Char** whitespace_end) {
while (start < end) {
if (IsSpaceOrNewLine(*start)) {
++start;
} else if (*start == '/') {
const Char* comment_end = nullptr;
if (!SkipComment(start, end, &comment_end))
break;
start = comment_end;
} else {
break;
}
}
*whitespace_end = start;
}
static Token ParseToken(const Char* start,
const Char* end,
const Char** tokenStart,
const Char** token_end) {
SkipWhitespaceAndComments(start, end, tokenStart);
start = *tokenStart;
if (start == end)
return NoInput;
switch (*start) {
case 'n':
if (ParseConstToken(start, end, token_end, kNullString))
return NullToken;
break;
case 't':
if (ParseConstToken(start, end, token_end, kTrueString))
return BoolTrue;
break;
case 'f':
if (ParseConstToken(start, end, token_end, kFalseString))
return BoolFalse;
break;
case '[':
*token_end = start + 1;
return ArrayBegin;
case ']':
*token_end = start + 1;
return ArrayEnd;
case ',':
*token_end = start + 1;
return ListSeparator;
case '{':
*token_end = start + 1;
return ObjectBegin;
case '}':
*token_end = start + 1;
return ObjectEnd;
case ':':
*token_end = start + 1;
return ObjectPairSeparator;
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
case '-':
if (ParseNumberToken(start, end, token_end))
return Number;
break;
case '"':
if (ParseStringToken(start + 1, end, token_end))
return StringLiteral;
break;
}
return InvalidToken;
}
static int HexToInt(Char c) {
if ('0' <= c && c <= '9')
return c - '0';
if ('A' <= c && c <= 'F')
return c - 'A' + 10;
if ('a' <= c && c <= 'f')
return c - 'a' + 10;
assert(false); // Unreachable.
return 0;
}
static bool DecodeString(const Char* start,
const Char* end,
std::vector<uint16_t>* output) {
if (start == end)
return true;
if (start > end)
return false;
output->reserve(end - start);
while (start < end) {
uint16_t c = *start++;
// If the |Char| we're dealing with is really a byte, then
// we have utf8 here, and we need to check for multibyte characters
// and transcode them to utf16 (either one or two utf16 chars).
if (sizeof(Char) == sizeof(uint8_t) && c > 0x7f) {
// Inspect the leading byte to figure out how long the utf8
// byte sequence is; while doing this initialize |codepoint|
// with the first few bits.
// See table in: https://en.wikipedia.org/wiki/UTF-8
// byte one is 110x xxxx -> 2 byte utf8 sequence
// byte one is 1110 xxxx -> 3 byte utf8 sequence
// byte one is 1111 0xxx -> 4 byte utf8 sequence
uint32_t codepoint;
int num_bytes_left;
if ((c & 0xe0) == 0xc0) { // 2 byte utf8 sequence
num_bytes_left = 1;
codepoint = c & 0x1f;
} else if ((c & 0xf0) == 0xe0) { // 3 byte utf8 sequence
num_bytes_left = 2;
codepoint = c & 0x0f;
} else if ((c & 0xf8) == 0xf0) { // 4 byte utf8 sequence
codepoint = c & 0x07;
num_bytes_left = 3;
} else {
return false; // invalid leading byte
}
// If we have enough bytes in our inpput, decode the remaining ones
// belonging to this Unicode character into |codepoint|.
if (start + num_bytes_left > end)
return false;
while (num_bytes_left > 0) {
c = *start++;
--num_bytes_left;
// Check the next byte is a continuation byte, that is 10xx xxxx.
if ((c & 0xc0) != 0x80)
return false;
codepoint = (codepoint << 6) | (c & 0x3f);
}
// Disallow overlong encodings for ascii characters, as these
// would include " and other characters significant to JSON
// string termination / control.
if (codepoint <= 0x7f)
return false;
// Invalid in UTF8, and can't be represented in UTF16 anyway.
if (codepoint > 0x10ffff)
return false;
// So, now we transcode to UTF16,
// using the math described at https://en.wikipedia.org/wiki/UTF-16,
// for either one or two 16 bit characters.
if (codepoint < 0xffff) {
output->push_back(codepoint);
continue;
}
codepoint -= 0x10000;
output->push_back((codepoint >> 10) + 0xd800); // high surrogate
output->push_back((codepoint & 0x3ff) + 0xdc00); // low surrogate
continue;
}
if ('\\' != c) {
output->push_back(c);
continue;
}
if (start == end)
return false;
c = *start++;
if (c == 'x') {
// \x is not supported.
return false;
}
switch (c) {
case '"':
case '/':
case '\\':
break;
case 'b':
c = '\b';
break;
case 'f':
c = '\f';
break;
case 'n':
c = '\n';
break;
case 'r':
c = '\r';
break;
case 't':
c = '\t';
break;
case 'v':
c = '\v';
break;
case 'u':
c = (HexToInt(*start) << 12) + (HexToInt(*(start + 1)) << 8) +
(HexToInt(*(start + 2)) << 4) + HexToInt(*(start + 3));
start += 4;
break;
default:
return false;
}
output->push_back(c);
}
return true;
}
void ParseValue(const Char* start,
const Char* end,
const Char** value_token_end,
int depth) {
if (depth > kStackLimit) {
HandleError(Error::JSON_PARSER_STACK_LIMIT_EXCEEDED, start);
return;
}
const Char* token_start = nullptr;
const Char* token_end = nullptr;
Token token = ParseToken(start, end, &token_start, &token_end);
switch (token) {
case NoInput:
HandleError(Error::JSON_PARSER_NO_INPUT, token_start);
return;
case InvalidToken:
HandleError(Error::JSON_PARSER_INVALID_TOKEN, token_start);
return;
case NullToken:
handler_->HandleNull();
break;
case BoolTrue:
handler_->HandleBool(true);
break;
case BoolFalse:
handler_->HandleBool(false);
break;
case Number: {
double value;
if (!CharsToDouble(token_start, token_end - token_start, &value)) {
HandleError(Error::JSON_PARSER_INVALID_NUMBER, token_start);
return;
}
if (value >= std::numeric_limits<int32_t>::min() &&
value <= std::numeric_limits<int32_t>::max() &&
static_cast<int32_t>(value) == value)
handler_->HandleInt32(static_cast<int32_t>(value));
else
handler_->HandleDouble(value);
break;
}
case StringLiteral: {
std::vector<uint16_t> value;
bool ok = DecodeString(token_start + 1, token_end - 1, &value);
if (!ok) {
HandleError(Error::JSON_PARSER_INVALID_STRING, token_start);
return;
}
handler_->HandleString16(span<uint16_t>(value.data(), value.size()));
break;
}
case ArrayBegin: {
handler_->HandleArrayBegin();
start = token_end;
token = ParseToken(start, end, &token_start, &token_end);
while (token != ArrayEnd) {
ParseValue(start, end, &token_end, depth + 1);
if (error_)
return;
// After a list value, we expect a comma or the end of the list.
start = token_end;
token = ParseToken(start, end, &token_start, &token_end);
if (token == ListSeparator) {
start = token_end;
token = ParseToken(start, end, &token_start, &token_end);
if (token == ArrayEnd) {
HandleError(Error::JSON_PARSER_UNEXPECTED_ARRAY_END, token_start);
return;
}
} else if (token != ArrayEnd) {
// Unexpected value after list value. Bail out.
HandleError(Error::JSON_PARSER_COMMA_OR_ARRAY_END_EXPECTED,
token_start);
return;
}
}
handler_->HandleArrayEnd();
break;
}
case ObjectBegin: {
handler_->HandleMapBegin();
start = token_end;
token = ParseToken(start, end, &token_start, &token_end);
while (token != ObjectEnd) {
if (token != StringLiteral) {
HandleError(Error::JSON_PARSER_STRING_LITERAL_EXPECTED,
token_start);
return;
}
std::vector<uint16_t> key;
if (!DecodeString(token_start + 1, token_end - 1, &key)) {
HandleError(Error::JSON_PARSER_INVALID_STRING, token_start);
return;
}
handler_->HandleString16(span<uint16_t>(key.data(), key.size()));
start = token_end;
token = ParseToken(start, end, &token_start, &token_end);
if (token != ObjectPairSeparator) {
HandleError(Error::JSON_PARSER_COLON_EXPECTED, token_start);
return;
}
start = token_end;
ParseValue(start, end, &token_end, depth + 1);
if (error_)
return;
start = token_end;
// After a key/value pair, we expect a comma or the end of the
// object.
token = ParseToken(start, end, &token_start, &token_end);
if (token == ListSeparator) {
start = token_end;
token = ParseToken(start, end, &token_start, &token_end);
if (token == ObjectEnd) {
HandleError(Error::JSON_PARSER_UNEXPECTED_MAP_END, token_start);
return;
}
} else if (token != ObjectEnd) {
// Unexpected value after last object value. Bail out.
HandleError(Error::JSON_PARSER_COMMA_OR_MAP_END_EXPECTED,
token_start);
return;
}
}
handler_->HandleMapEnd();
break;
}
default:
// We got a token that's not a value.
HandleError(Error::JSON_PARSER_VALUE_EXPECTED, token_start);
return;
}
SkipWhitespaceAndComments(token_end, end, value_token_end);
}
void HandleError(Error error, const Char* pos) {
assert(error != Error::OK);
if (!error_) {
handler_->HandleError(
Status{error, static_cast<size_t>(pos - start_pos_)});
error_ = true;
}
}
const Char* start_pos_ = nullptr;
bool error_ = false;
const Platform* platform_;
StreamingParserHandler* handler_;
};
} // namespace
void ParseJSON(const Platform& platform,
span<uint8_t> chars,
StreamingParserHandler* handler) {
JsonParser<uint8_t> parser(&platform, handler);
parser.Parse(chars.data(), chars.size());
}
void ParseJSON(const Platform& platform,
span<uint16_t> chars,
StreamingParserHandler* handler) {
JsonParser<uint16_t> parser(&platform, handler);
parser.Parse(chars.data(), chars.size());
}
// =============================================================================
// json::ConvertCBORToJSON, json::ConvertJSONToCBOR - for transcoding
// =============================================================================
template <typename C>
Status ConvertCBORToJSONTmpl(const Platform& platform,
span<uint8_t> cbor,
C* json) {
Status status;
std::unique_ptr<StreamingParserHandler> json_writer =
NewJSONEncoder(&platform, json, &status);
cbor::ParseCBOR(cbor, json_writer.get());
return status;
}
Status ConvertCBORToJSON(const Platform& platform,
span<uint8_t> cbor,
std::vector<uint8_t>* json) {
return ConvertCBORToJSONTmpl(platform, cbor, json);
}
Status ConvertCBORToJSON(const Platform& platform,
span<uint8_t> cbor,
std::string* json) {
return ConvertCBORToJSONTmpl(platform, cbor, json);
}
template <typename T, typename C>
Status ConvertJSONToCBORTmpl(const Platform& platform, span<T> json, C* cbor) {
Status status;
std::unique_ptr<StreamingParserHandler> encoder =
cbor::NewCBOREncoder(cbor, &status);
ParseJSON(platform, json, encoder.get());
return status;
}
Status ConvertJSONToCBOR(const Platform& platform,
span<uint8_t> json,
std::string* cbor) {
return ConvertJSONToCBORTmpl(platform, json, cbor);
}
Status ConvertJSONToCBOR(const Platform& platform,
span<uint16_t> json,
std::string* cbor) {
return ConvertJSONToCBORTmpl(platform, json, cbor);
}
Status ConvertJSONToCBOR(const Platform& platform,
span<uint8_t> json,
std::vector<uint8_t>* cbor) {
return ConvertJSONToCBORTmpl(platform, json, cbor);
}
Status ConvertJSONToCBOR(const Platform& platform,
span<uint16_t> json,
std::vector<uint8_t>* cbor) {
return ConvertJSONToCBORTmpl(platform, json, cbor);
}
} // namespace json
{% for namespace in config.protocol.namespace %}
} // namespace {{namespace}}
{% endfor %}
{% endif %}
|