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
|
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
* This file is part of the LibreOffice project.
*
* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/.
*
* This file incorporates work covered by the following license notice:
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed
* with this work for additional information regarding copyright
* ownership. The ASF licenses this file to you under the Apache
* License, Version 2.0 (the "License"); you may not use this file
* except in compliance with the License. You may obtain a copy of
* the License at http://www.apache.org/licenses/LICENSE-2.0 .
*/
#include "sc.hrc"
#include <comphelper/processfactory.hxx>
#include <i18nlangtag/languagetag.hxx>
#include <sot/formats.hxx>
#include <sfx2/mieclip.hxx>
#include <com/sun/star/i18n/CalendarFieldIndex.hpp>
#include "global.hxx"
#include "scerrors.hxx"
#include "docsh.hxx"
#include "undoblk.hxx"
#include "rangenam.hxx"
#include "viewdata.hxx"
#include "tabvwsh.hxx"
#include "filter.hxx"
#include "asciiopt.hxx"
#include "formulacell.hxx"
#include "docoptio.hxx"
#include "progress.hxx"
#include "scitems.hxx"
#include "editable.hxx"
#include "compiler.hxx"
#include "warnbox.hxx"
#include "clipparam.hxx"
#include "impex.hxx"
#include "editutil.hxx"
#include "patattr.hxx"
#include "docpool.hxx"
#include "stringutil.hxx"
#include "cellvalue.hxx"
#include "tokenarray.hxx"
#include "documentimport.hxx"
#include "globstr.hrc"
#include <vcl/svapp.hxx>
#include <boost/scoped_ptr.hpp>
// We don't want to end up with 2GB read in one line just because of malformed
// multiline fields, so chop it _somewhere_, which is twice supported columns
// times maximum cell content length, 2*1024*64K=128M, and because it's
// sal_Unicode that's 256MB. If it's 2GB of data without LF we're out of luck
// anyway.
static const sal_Int32 nArbitraryLineLengthLimit = 2 * MAXCOLCOUNT * 65536;
namespace
{
const char SYLK_LF[] = "\x1b :";
const char DOUBLE_SEMICOLON[] = ";;";
const char DOUBLE_DOUBLEQUOTE[] = "\"\"";
}
enum SylkVersion
{
SYLK_SCALC3, // Wrote wrongly quoted strings and unescaped semicolons.
SYLK_OOO32, // Correct strings, plus multiline content.
SYLK_OWN, // Place our new versions, if any, before this value.
SYLK_OTHER // Assume that aliens wrote correct strings.
};
// Whole document without Undo
ScImportExport::ScImportExport( ScDocument* p )
: pDocSh( PTR_CAST(ScDocShell,p->GetDocumentShell()) ), pDoc( p ),
nSizeLimit( 0 ), cSep( '\t' ), cStr( '"' ),
bFormulas( false ), bIncludeFiltered( true ),
bAll( true ), bSingle( true ), bUndo( false ),
bOverflowRow( false ), bOverflowCol( false ), bOverflowCell( false ),
mbApi( true ), mbImportBroadcast(false), mExportTextOptions()
{
pUndoDoc = NULL;
pExtOptions = NULL;
}
// Insert am current cell without range(es)
ScImportExport::ScImportExport( ScDocument* p, const ScAddress& rPt )
: pDocSh( PTR_CAST(ScDocShell,p->GetDocumentShell()) ), pDoc( p ),
aRange( rPt ),
nSizeLimit( 0 ), cSep( '\t' ), cStr( '"' ),
bFormulas( false ), bIncludeFiltered( true ),
bAll( false ), bSingle( true ), bUndo( pDocSh != NULL ),
bOverflowRow( false ), bOverflowCol( false ), bOverflowCell( false ),
mbApi( true ), mbImportBroadcast(false), mExportTextOptions()
{
pUndoDoc = NULL;
pExtOptions = NULL;
}
// ctor with a range is only used for export
//! ctor with a string (and bSingle=true) is also used for DdeSetData
ScImportExport::ScImportExport( ScDocument* p, const ScRange& r )
: pDocSh( PTR_CAST(ScDocShell,p->GetDocumentShell()) ), pDoc( p ),
aRange( r ),
nSizeLimit( 0 ), cSep( '\t' ), cStr( '"' ),
bFormulas( false ), bIncludeFiltered( true ),
bAll( false ), bSingle( false ), bUndo( pDocSh != NULL ),
bOverflowRow( false ), bOverflowCol( false ), bOverflowCell( false ),
mbApi( true ), mbImportBroadcast(false), mExportTextOptions()
{
pUndoDoc = NULL;
pExtOptions = NULL;
// Only one sheet (table) supported
aRange.aEnd.SetTab( aRange.aStart.Tab() );
}
// Evaluate input string - either range, cell or the whole document (when error)
// If a View exists, the TabNo of the view will be used.
ScImportExport::ScImportExport( ScDocument* p, const OUString& rPos )
: pDocSh( PTR_CAST(ScDocShell,p->GetDocumentShell()) ), pDoc( p ),
nSizeLimit( 0 ), cSep( '\t' ), cStr( '"' ),
bFormulas( false ), bIncludeFiltered( true ),
bAll( false ), bSingle( true ), bUndo( pDocSh != NULL ),
bOverflowRow( false ), bOverflowCol( false ), bOverflowCell( false ),
mbApi( true ), mbImportBroadcast(false), mExportTextOptions()
{
pUndoDoc = NULL;
pExtOptions = NULL;
SCTAB nTab = ScDocShell::GetCurTab();
aRange.aStart.SetTab( nTab );
OUString aPos( rPos );
// Named range?
ScRangeName* pRange = pDoc->GetRangeName();
if (pRange)
{
const ScRangeData* pData = pRange->findByUpperName(ScGlobal::pCharClass->uppercase(aPos));
if (pData)
{
if( pData->HasType( RT_REFAREA )
|| pData->HasType( RT_ABSAREA )
|| pData->HasType( RT_ABSPOS ) )
{
pData->GetSymbol(aPos);
}
}
}
formula::FormulaGrammar::AddressConvention eConv = pDoc->GetAddressConvention();
// Range?
if (aRange.Parse(aPos, pDoc, eConv) & SCA_VALID)
bSingle = false;
// Cell?
else if (aRange.aStart.Parse(aPos, pDoc, eConv) & SCA_VALID)
aRange.aEnd = aRange.aStart;
else
bAll = true;
}
ScImportExport::~ScImportExport()
{
delete pUndoDoc;
delete pExtOptions;
}
void ScImportExport::SetExtOptions( const ScAsciiOptions& rOpt )
{
if ( pExtOptions )
*pExtOptions = rOpt;
else
pExtOptions = new ScAsciiOptions( rOpt );
// "normal" Options
cSep = ScAsciiOptions::GetWeightedFieldSep( rOpt.GetFieldSeps(), false);
cStr = rOpt.GetTextSep();
}
void ScImportExport::SetFilterOptions(const OUString& rFilterOptions)
{
maFilterOptions = rFilterOptions;
}
bool ScImportExport::IsFormatSupported( sal_uLong nFormat )
{
return nFormat == FORMAT_STRING
|| nFormat == SOT_FORMATSTR_ID_SYLK
|| nFormat == SOT_FORMATSTR_ID_LINK
|| nFormat == SOT_FORMATSTR_ID_HTML
|| nFormat == SOT_FORMATSTR_ID_HTML_SIMPLE
|| nFormat == SOT_FORMATSTR_ID_DIF;
}
// Prepare for Undo
bool ScImportExport::StartPaste()
{
if ( !bAll )
{
ScEditableTester aTester( pDoc, aRange );
if ( !aTester.IsEditable() )
{
InfoBox aInfoBox(Application::GetDefDialogParent(),
ScGlobal::GetRscString( aTester.GetMessageId() ) );
aInfoBox.Execute();
return false;
}
}
if( bUndo && pDocSh && pDoc->IsUndoEnabled())
{
pUndoDoc = new ScDocument( SCDOCMODE_UNDO );
pUndoDoc->InitUndo( pDoc, aRange.aStart.Tab(), aRange.aEnd.Tab() );
pDoc->CopyToDocument( aRange, IDF_ALL | IDF_NOCAPTIONS, false, pUndoDoc );
}
return true;
}
// Create Undo/Redo actions, Invalidate/Repaint
void ScImportExport::EndPaste(bool bAutoRowHeight)
{
bool bHeight = bAutoRowHeight && pDocSh && pDocSh->AdjustRowHeight(
aRange.aStart.Row(), aRange.aEnd.Row(), aRange.aStart.Tab() );
if( pUndoDoc && pDoc->IsUndoEnabled() && pDocSh )
{
ScDocument* pRedoDoc = new ScDocument( SCDOCMODE_UNDO );
pRedoDoc->InitUndo( pDoc, aRange.aStart.Tab(), aRange.aEnd.Tab() );
pDoc->CopyToDocument( aRange, IDF_ALL | IDF_NOCAPTIONS, false, pRedoDoc );
ScMarkData aDestMark;
aDestMark.SetMarkArea(aRange);
pDocSh->GetUndoManager()->AddUndoAction(
new ScUndoPaste(pDocSh, aRange, aDestMark, pUndoDoc, pRedoDoc, IDF_ALL, NULL));
}
pUndoDoc = NULL;
if( pDocSh )
{
if (!bHeight)
pDocSh->PostPaint( aRange, PAINT_GRID );
pDocSh->SetDocumentModified();
}
ScTabViewShell* pViewSh = ScTabViewShell::GetActiveViewShell();
if ( pViewSh )
pViewSh->UpdateInputHandler();
}
bool ScImportExport::ImportData( const OUString& /* rMimeType */,
const ::com::sun::star::uno::Any & /* rValue */ )
{
OSL_ENSURE( !this, "Implementation is missing" );
return false;
}
bool ScImportExport::ExportData( const OUString& rMimeType,
::com::sun::star::uno::Any & rValue )
{
SvMemoryStream aStrm;
// mba: no BaseURL for data exchange
if( ExportStream( aStrm, OUString(),
SotExchange::GetFormatIdFromMimeType( rMimeType ) ))
{
aStrm.WriteUChar( (sal_uInt8) 0 );
rValue <<= ::com::sun::star::uno::Sequence< sal_Int8 >(
(sal_Int8*)aStrm.GetData(),
aStrm.Seek( STREAM_SEEK_TO_END ) );
return true;
}
return false;
}
bool ScImportExport::ImportString( const OUString& rText, sal_uLong nFmt )
{
switch ( nFmt )
{
// formats supporting unicode
case FORMAT_STRING :
{
ScImportStringStream aStrm( rText);
return ImportStream( aStrm, OUString(), nFmt );
// ImportStream must handle RTL_TEXTENCODING_UNICODE
}
//break;
default:
{
rtl_TextEncoding eEnc = osl_getThreadTextEncoding();
OString aTmp( rText.getStr(), rText.getLength(), eEnc );
SvMemoryStream aStrm( (void*)aTmp.getStr(), aTmp.getLength() * sizeof(sal_Char), STREAM_READ );
aStrm.SetStreamCharSet( eEnc );
SetNoEndianSwap( aStrm ); //! no swapping in memory
return ImportStream( aStrm, OUString(), nFmt );
}
}
}
bool ScImportExport::ExportString( OUString& rText, sal_uLong nFmt )
{
OSL_ENSURE( nFmt == FORMAT_STRING, "ScImportExport::ExportString: Unicode not supported for other formats than FORMAT_STRING" );
if ( nFmt != FORMAT_STRING )
{
rtl_TextEncoding eEnc = osl_getThreadTextEncoding();
OString aTmp;
bool bOk = ExportByteString( aTmp, eEnc, nFmt );
rText = OStringToOUString( aTmp, eEnc );
return bOk;
}
// nSizeLimit not needed for OUString
SvMemoryStream aStrm;
aStrm.SetStreamCharSet( RTL_TEXTENCODING_UNICODE );
SetNoEndianSwap( aStrm ); //! no swapping in memory
// mba: no BaseURL for data exc
if( ExportStream( aStrm, OUString(), nFmt ) )
{
aStrm.WriteUInt16( (sal_Unicode) 0 );
aStrm.Seek( STREAM_SEEK_TO_END );
rText = OUString( (const sal_Unicode*) aStrm.GetData() );
return true;
}
rText = OUString();
return false;
// ExportStream must handle RTL_TEXTENCODING_UNICODE
}
bool ScImportExport::ExportByteString( OString& rText, rtl_TextEncoding eEnc, sal_uLong nFmt )
{
OSL_ENSURE( eEnc != RTL_TEXTENCODING_UNICODE, "ScImportExport::ExportByteString: Unicode not supported" );
if ( eEnc == RTL_TEXTENCODING_UNICODE )
eEnc = osl_getThreadTextEncoding();
if (!nSizeLimit)
nSizeLimit = SAL_MAX_UINT16;
SvMemoryStream aStrm;
aStrm.SetStreamCharSet( eEnc );
SetNoEndianSwap( aStrm ); //! no swapping in memory
// mba: no BaseURL for data exchange
if( ExportStream( aStrm, OUString(), nFmt ) )
{
aStrm.WriteChar( (sal_Char) 0 );
aStrm.Seek( STREAM_SEEK_TO_END );
if( aStrm.Tell() <= nSizeLimit )
{
rText = (const sal_Char*) aStrm.GetData();
return true;
}
}
rText = OString();
return false;
}
bool ScImportExport::ImportStream( SvStream& rStrm, const OUString& rBaseURL, sal_uLong nFmt )
{
if( nFmt == FORMAT_STRING )
{
if( ExtText2Doc( rStrm ) ) // evaluate pExtOptions
return true;
}
if( nFmt == SOT_FORMATSTR_ID_SYLK )
{
if( Sylk2Doc( rStrm ) )
return true;
}
if( nFmt == SOT_FORMATSTR_ID_DIF )
{
if( Dif2Doc( rStrm ) )
return true;
}
if( nFmt == FORMAT_RTF )
{
if( RTF2Doc( rStrm, rBaseURL ) )
return true;
}
if( nFmt == SOT_FORMATSTR_ID_LINK )
return true; // Link-Import?
if ( nFmt == SOT_FORMATSTR_ID_HTML )
{
if( HTML2Doc( rStrm, rBaseURL ) )
return true;
}
if ( nFmt == SOT_FORMATSTR_ID_HTML_SIMPLE )
{
MSE40HTMLClipFormatObj aMSE40ClpObj; // needed to skip the header data
SvStream* pHTML = aMSE40ClpObj.IsValid( rStrm );
if ( pHTML && HTML2Doc( *pHTML, rBaseURL ) )
return true;
}
return false;
}
bool ScImportExport::ExportStream( SvStream& rStrm, const OUString& rBaseURL, sal_uLong nFmt )
{
if( nFmt == FORMAT_STRING )
{
if( Doc2Text( rStrm ) )
return true;
}
if( nFmt == SOT_FORMATSTR_ID_SYLK )
{
if( Doc2Sylk( rStrm ) )
return true;
}
if( nFmt == SOT_FORMATSTR_ID_DIF )
{
if( Doc2Dif( rStrm ) )
return true;
}
if( nFmt == SOT_FORMATSTR_ID_LINK && !bAll )
{
OUString aDocName;
if ( pDoc->IsClipboard() )
aDocName = ScGlobal::GetClipDocName();
else
{
SfxObjectShell* pShell = pDoc->GetDocumentShell();
if (pShell)
aDocName = pShell->GetTitle( SFX_TITLE_FULLNAME );
}
OSL_ENSURE( !aDocName.isEmpty(), "ClipBoard document has no name! :-/" );
if( !aDocName.isEmpty() )
{
// Always use Calc A1 syntax for paste link.
OUString aRefName;
sal_uInt16 nFlags = SCA_VALID | SCA_TAB_3D;
if( bSingle )
aRefName = aRange.aStart.Format(nFlags, pDoc, formula::FormulaGrammar::CONV_OOO);
else
{
if( aRange.aStart.Tab() != aRange.aEnd.Tab() )
nFlags |= SCA_TAB2_3D;
aRefName = aRange.Format(nFlags, pDoc, formula::FormulaGrammar::CONV_OOO);
}
OUString aAppName = Application::GetAppName();
// extra bits are used to tell the client to prefer external
// reference link.
OUString aExtraBits("calc:extref");
WriteUnicodeOrByteString( rStrm, aAppName, true );
WriteUnicodeOrByteString( rStrm, aDocName, true );
WriteUnicodeOrByteString( rStrm, aRefName, true );
WriteUnicodeOrByteString( rStrm, aExtraBits, true );
if ( rStrm.GetStreamCharSet() == RTL_TEXTENCODING_UNICODE )
rStrm.WriteUInt16( sal_Unicode(0) );
else
rStrm.WriteChar( sal_Char(0) );
return rStrm.GetError() == SVSTREAM_OK;
}
}
if( nFmt == SOT_FORMATSTR_ID_HTML )
{
if( Doc2HTML( rStrm, rBaseURL ) )
return true;
}
if( nFmt == FORMAT_RTF )
{
if( Doc2RTF( rStrm ) )
return true;
}
return false;
}
void ScImportExport::WriteUnicodeOrByteString( SvStream& rStrm, const OUString& rString, bool bZero )
{
rtl_TextEncoding eEnc = rStrm.GetStreamCharSet();
if ( eEnc == RTL_TEXTENCODING_UNICODE )
{
if ( !IsEndianSwap( rStrm ) )
rStrm.Write( rString.getStr(), rString.getLength() * sizeof(sal_Unicode) );
else
{
const sal_Unicode* p = rString.getStr();
const sal_Unicode* const pStop = p + rString.getLength();
while ( p < pStop )
{
rStrm.WriteUInt16( *p );
}
}
if ( bZero )
rStrm.WriteUInt16( sal_Unicode(0) );
}
else
{
OString aByteStr(OUStringToOString(rString, eEnc));
rStrm.WriteCharPtr( aByteStr.getStr() );
if ( bZero )
rStrm.WriteChar( sal_Char(0) );
}
}
// This function could be replaced by endlub()
void ScImportExport::WriteUnicodeOrByteEndl( SvStream& rStrm )
{
if ( rStrm.GetStreamCharSet() == RTL_TEXTENCODING_UNICODE )
{ // same as endl() but unicode
switch ( rStrm.GetLineDelimiter() )
{
case LINEEND_CR :
rStrm.WriteUInt16( sal_Unicode('\r') );
break;
case LINEEND_LF :
rStrm.WriteUInt16( sal_Unicode('\n') );
break;
default:
rStrm.WriteUInt16( sal_Unicode('\r') ).WriteUInt16( sal_Unicode('\n') );
}
}
else
endl( rStrm );
}
enum QuoteType
{
FIELDSTART_QUOTE,
FIRST_QUOTE,
SECOND_QUOTE,
FIELDEND_QUOTE,
DONTKNOW_QUOTE
};
/** Determine if *p is a quote that ends a quoted field.
Precondition: we are parsing a quoted field already and *p is a quote.
@return
FIELDEND_QUOTE if end of field quote
DONTKNOW_QUOTE anything else
*/
static QuoteType lcl_isFieldEndQuote( const sal_Unicode* p, const sal_Unicode* pSeps )
{
// Due to broken CSV generators that don't double embedded quotes check if
// a field separator immediately or with trailing spaces follows the quote,
// only then end the field, or at end of string.
const sal_Unicode cBlank = ' ';
if (p[1] == cBlank && ScGlobal::UnicodeStrChr( pSeps, cBlank))
return FIELDEND_QUOTE;
while (p[1] == cBlank)
++p;
if (!p[1] || ScGlobal::UnicodeStrChr( pSeps, p[1]))
return FIELDEND_QUOTE;
return DONTKNOW_QUOTE;
}
/** Determine if *p is a quote that is escaped by being doubled or ends a
quoted field.
Precondition: *p is a quote.
@param nQuotes
Quote characters encountered so far.
Odd (after opening quote) means either no embedded quotes or only quote
pairs so far.
Even means either not in a quoted field or already one quote
encountered, the first of a pair.
@return
FIELDSTART_QUOTE if first quote in a field, either starting content or
embedded so caller should check beforehand.
FIRST_QUOTE if first of a doubled quote
SECOND_QUOTE if second of a doubled quote
FIELDEND_QUOTE if end of field quote
DONTKNOW_QUOTE if an unescaped quote we don't consider as end of field,
do not increment nQuotes in caller then!
*/
static QuoteType lcl_isEscapedOrFieldEndQuote( sal_Int32 nQuotes, const sal_Unicode* p,
const sal_Unicode* pSeps, sal_Unicode cStr )
{
if ((nQuotes % 2) == 0)
{
if (p[-1] == cStr)
return SECOND_QUOTE;
else
{
SAL_WARN( "sc", "lcl_isEscapedOrFieldEndQuote: really want a FIELDSTART_QUOTE?");
return FIELDSTART_QUOTE;
}
}
if (p[1] == cStr)
return FIRST_QUOTE;
return lcl_isFieldEndQuote( p, pSeps);
}
/** Append characters of [p1,p2) to rField.
@returns TRUE if ok; FALSE if data overflow, truncated
*/
static bool lcl_appendLineData( OUString& rField, const sal_Unicode* p1, const sal_Unicode* p2 )
{
OSL_ENSURE( rField.getLength() + (p2 - p1) <= SAL_MAX_UINT16, "lcl_appendLineData: data overflow");
if (rField.getLength() + (p2 - p1) <= SAL_MAX_UINT16)
{
rField += OUString( p1, sal::static_int_cast<sal_Int32>( p2 - p1 ) );
return true;
}
else
{
rField += OUString( p1, SAL_MAX_UINT16 - rField.getLength() );
return false;
}
}
enum DoubledQuoteMode
{
DQM_KEEP_ALL, // both are taken, additionally start and end quote are included in string
DQM_KEEP, // both are taken
DQM_ESCAPE, // escaped quote, one is taken, one ignored
DQM_CONCAT, // first is end, next is start, both ignored => strings combined
DQM_SEPARATE // end one string and begin next
};
static const sal_Unicode* lcl_ScanString( const sal_Unicode* p, OUString& rString,
const sal_Unicode* pSeps, sal_Unicode cStr, DoubledQuoteMode eMode, bool& rbOverflowCell )
{
if (eMode != DQM_KEEP_ALL)
p++; //! jump over opening quote
bool bCont;
do
{
bCont = false;
const sal_Unicode* p0 = p;
for( ;; )
{
if( !*p )
break;
if( *p == cStr )
{
if ( *++p != cStr )
{
// break or continue for loop
if (eMode == DQM_ESCAPE)
{
if (lcl_isFieldEndQuote( p-1, pSeps) == FIELDEND_QUOTE)
break;
else
continue;
}
else
break;
}
// doubled quote char
switch ( eMode )
{
case DQM_KEEP_ALL :
case DQM_KEEP :
p++; // both for us (not breaking for-loop)
break;
case DQM_ESCAPE :
p++; // one for us (breaking for-loop)
bCont = true; // and more
break;
case DQM_CONCAT :
if ( p0+1 < p )
{
// first part
if (!lcl_appendLineData( rString, p0, p-1))
rbOverflowCell = true;
}
p0 = ++p; // text of next part starts here
break;
case DQM_SEPARATE :
// positioned on next opening quote
break;
}
if ( eMode == DQM_ESCAPE || eMode == DQM_SEPARATE )
break;
}
else
p++;
}
if ( p0 < p )
{
if (!lcl_appendLineData( rString, p0, ((eMode != DQM_KEEP_ALL && (*p || *(p-1) == cStr)) ? p-1 : p)))
rbOverflowCell = true;
}
} while ( bCont );
return p;
}
static void lcl_UnescapeSylk( OUString & rString, SylkVersion eVersion )
{
// Older versions didn't escape the semicolon.
// Older versions quoted the string and doubled embedded quotes, but not
// the semicolons, which was plain wrong.
if (eVersion >= SYLK_OOO32)
rString = rString.replaceAll( OUString(DOUBLE_SEMICOLON), OUString(';') );
else
rString = rString.replaceAll( OUString(DOUBLE_DOUBLEQUOTE), OUString('"') );
rString = rString.replaceAll( OUString(SYLK_LF), OUString('\n') );
}
static const sal_Unicode* lcl_ScanSylkString( const sal_Unicode* p,
OUString& rString, SylkVersion eVersion )
{
const sal_Unicode* pStartQuote = p;
const sal_Unicode* pEndQuote = 0;
while( *(++p) )
{
if( *p == '"' )
{
pEndQuote = p;
if (eVersion >= SYLK_OOO32)
{
if (*(p+1) == ';')
{
if (*(p+2) == ';')
{
p += 2; // escaped ';'
pEndQuote = 0;
}
else
break; // end field
}
}
else
{
if (*(p+1) == '"')
{
++p; // escaped '"'
pEndQuote = 0;
}
else if (*(p+1) == ';')
break; // end field
}
}
}
if (!pEndQuote)
pEndQuote = p; // Take all data as string.
rString += OUString(pStartQuote + 1, sal::static_int_cast<sal_Int32>( pEndQuote - pStartQuote - 1 ) );
lcl_UnescapeSylk( rString, eVersion);
return p;
}
static const sal_Unicode* lcl_ScanSylkFormula( const sal_Unicode* p,
OUString& rString, SylkVersion eVersion )
{
const sal_Unicode* pStart = p;
if (eVersion >= SYLK_OOO32)
{
while (*p)
{
if (*p == ';')
{
if (*(p+1) == ';')
++p; // escaped ';'
else
break; // end field
}
++p;
}
rString += OUString( pStart, sal::static_int_cast<sal_Int32>( p - pStart));
lcl_UnescapeSylk( rString, eVersion);
}
else
{
// Nasty. If in old versions the formula contained a semicolon, it was
// quoted and embedded quotes were doubled, but semicolons were not. If
// there was no semicolon, it could still contain quotes and doubled
// embedded quotes if it was something like ="a""b", which was saved as
// E"a""b" as is and has to be preserved, even if older versions
// couldn't even load it correctly. However, theoretically another
// field might follow and thus the line contain a semicolon again, such
// as ...;E"a""b";...
bool bQuoted = false;
if (*p == '"')
{
// May be a quoted expression or just a string constant expression
// with quotes.
while (*(++p))
{
if (*p == '"')
{
if (*(p+1) == '"')
++p; // escaped '"'
else
break; // closing '"', had no ';' yet
}
else if (*p == ';')
{
bQuoted = true; // ';' within quoted expression
break;
}
}
p = pStart;
}
if (bQuoted)
p = lcl_ScanSylkString( p, rString, eVersion);
else
{
while (*p && *p != ';')
++p;
rString += OUString( pStart, sal::static_int_cast<sal_Int32>( p - pStart));
}
}
return p;
}
static void lcl_DoubleEscapeChar( OUString& rString, sal_Unicode cStr )
{
sal_Int32 n = 0;
while( ( n = rString.indexOf( cStr, n ) ) != -1 )
{
rString = rString.replaceAt( n, 0, OUString(cStr) );
n += 2;
}
}
static void lcl_WriteString( SvStream& rStrm, OUString& rString, sal_Unicode cQuote, sal_Unicode cEsc )
{
if (cEsc)
lcl_DoubleEscapeChar( rString, cEsc );
if (cQuote)
{
rString = OUString(cQuote) + rString + OUString(cQuote);
}
ScImportExport::WriteUnicodeOrByteString( rStrm, rString );
}
static inline void lcl_WriteSimpleString( SvStream& rStrm, const OUString& rString )
{
ScImportExport::WriteUnicodeOrByteString( rStrm, rString );
}
bool ScImportExport::Text2Doc( SvStream& rStrm )
{
bool bOk = true;
sal_Unicode pSeps[2];
pSeps[0] = cSep;
pSeps[1] = 0;
SCCOL nStartCol = aRange.aStart.Col();
SCROW nStartRow = aRange.aStart.Row();
SCCOL nEndCol = aRange.aEnd.Col();
SCROW nEndRow = aRange.aEnd.Row();
sal_uLong nOldPos = rStrm.Tell();
rStrm.StartReadingUnicodeText( rStrm.GetStreamCharSet() );
bool bData = !bSingle;
if( !bSingle)
bOk = StartPaste();
while( bOk )
{
OUString aLine;
OUString aCell;
SCROW nRow = nStartRow;
rStrm.Seek( nOldPos );
for( ;; )
{
rStrm.ReadUniOrByteStringLine( aLine, rStrm.GetStreamCharSet(), nArbitraryLineLengthLimit );
if( rStrm.IsEof() )
break;
SCCOL nCol = nStartCol;
const sal_Unicode* p = aLine.getStr();
while( *p )
{
aCell = "";
const sal_Unicode* q = p;
while (*p && *p != cSep)
{
// Always look for a pairing quote and ignore separator in between.
while (*p && *p == cStr)
q = p = lcl_ScanString( p, aCell, pSeps, cStr, DQM_KEEP_ALL, bOverflowCell );
// All until next separator or quote.
while (*p && *p != cSep && *p != cStr)
++p;
if (!lcl_appendLineData( aCell, q, p))
bOverflowCell = true; // display warning on import
q = p;
}
if (*p)
++p;
if (ValidCol(nCol) && ValidRow(nRow) )
{
if( bSingle )
{
if (nCol>nEndCol) nEndCol = nCol;
if (nRow>nEndRow) nEndRow = nRow;
}
if( bData && nCol <= nEndCol && nRow <= nEndRow )
pDoc->SetString( nCol, nRow, aRange.aStart.Tab(), aCell );
}
else // zuviele Spalten/Zeilen
{
if (!ValidRow(nRow))
bOverflowRow = true; // display warning on import
if (!ValidCol(nCol))
bOverflowCol = true; // display warning on import
}
++nCol;
}
++nRow;
}
if( !bData )
{
aRange.aEnd.SetCol( nEndCol );
aRange.aEnd.SetRow( nEndRow );
bOk = StartPaste();
bData = true;
}
else
break;
}
EndPaste();
if (bOk && mbImportBroadcast)
{
pDoc->BroadcastCells(aRange, SC_HINT_DATACHANGED);
pDocSh->PostDataChanged();
}
return bOk;
}
// Extended Ascii-Import
static bool lcl_PutString(
ScDocumentImport& rDocImport, SCCOL nCol, SCROW nRow, SCTAB nTab, const OUString& rStr, sal_uInt8 nColFormat,
SvNumberFormatter* pFormatter, bool bDetectNumFormat,
::utl::TransliterationWrapper& rTransliteration, CalendarWrapper& rCalendar,
::utl::TransliterationWrapper* pSecondTransliteration, CalendarWrapper* pSecondCalendar )
{
ScDocument* pDoc = &rDocImport.getDoc();
bool bMultiLine = false;
if ( nColFormat == SC_COL_SKIP || rStr.isEmpty() || !ValidCol(nCol) || !ValidRow(nRow) )
return bMultiLine;
if ( nColFormat == SC_COL_TEXT )
{
double fDummy;
sal_uInt32 nIndex = 0;
if (pFormatter->IsNumberFormat(rStr, nIndex, fDummy))
{
// Set the format of this cell to Text.
sal_uInt32 nFormat = pFormatter->GetStandardFormat(NUMBERFORMAT_TEXT);
ScPatternAttr aNewAttrs(pDoc->GetPool());
SfxItemSet& rSet = aNewAttrs.GetItemSet();
rSet.Put( SfxUInt32Item(ATTR_VALUE_FORMAT, nFormat) );
pDoc->ApplyPattern(nCol, nRow, nTab, aNewAttrs);
}
if(ScStringUtil::isMultiline(rStr))
{
ScFieldEditEngine& rEngine = pDoc->GetEditEngine();
rEngine.SetText(rStr);
rDocImport.setEditCell(ScAddress(nCol, nRow, nTab), rEngine.CreateTextObject());
return true;
}
else
{
rDocImport.setStringCell(ScAddress(nCol, nRow, nTab), rStr);
return false;
}
}
if ( nColFormat == SC_COL_ENGLISH )
{
//! SetString with Extra-Flag ???
SvNumberFormatter* pDocFormatter = pDoc->GetFormatTable();
sal_uInt32 nEnglish = pDocFormatter->GetStandardIndex(LANGUAGE_ENGLISH_US);
double fVal;
if ( pDocFormatter->IsNumberFormat( rStr, nEnglish, fVal ) )
{
// Numberformat will not be set to English
rDocImport.setNumericCell( ScAddress( nCol, nRow, nTab ), fVal );
return bMultiLine;
}
// else, continue with SetString
}
else if ( nColFormat != SC_COL_STANDARD ) // Datumformats
{
const sal_uInt16 nMaxNumberParts = 7; // Y-M-D h:m:s.t
sal_Int32 nLen = rStr.getLength();
sal_Int32 nStart[nMaxNumberParts];
sal_Int32 nEnd[nMaxNumberParts];
sal_uInt16 nDP, nMP, nYP;
switch ( nColFormat )
{
case SC_COL_YMD: nDP = 2; nMP = 1; nYP = 0; break;
case SC_COL_MDY: nDP = 1; nMP = 0; nYP = 2; break;
case SC_COL_DMY:
default: nDP = 0; nMP = 1; nYP = 2; break;
}
sal_uInt16 nFound = 0;
bool bInNum = false;
for ( sal_Int32 nPos=0; nPos<nLen && (bInNum ||
nFound<nMaxNumberParts); nPos++ )
{
if (bInNum && nFound == 3 && nColFormat == SC_COL_YMD &&
nPos <= nStart[nFound]+2 && rStr[nPos] == 'T')
bInNum = false; // ISO-8601: YYYY-MM-DDThh:mm...
else if ((((!bInNum && nFound==nMP) || (bInNum && nFound==nMP+1))
&& ScGlobal::pCharClass->isLetterNumeric( rStr, nPos))
|| ScGlobal::pCharClass->isDigit( rStr, nPos))
{
if (!bInNum)
{
bInNum = true;
nStart[nFound] = nPos;
++nFound;
}
nEnd[nFound-1] = nPos;
}
else
bInNum = false;
}
if ( nFound == 1 )
{
// try to break one number (without separators) into date fields
sal_Int32 nDateStart = nStart[0];
sal_Int32 nDateLen = nEnd[0] + 1 - nDateStart;
if ( nDateLen >= 5 && nDateLen <= 8 &&
ScGlobal::pCharClass->isNumeric( rStr.copy( nDateStart, nDateLen ) ) )
{
// 6 digits: 2 each for day, month, year
// 8 digits: 4 for year, 2 each for day and month
// 5 or 7 digits: first field is shortened by 1
bool bLongYear = ( nDateLen >= 7 );
bool bShortFirst = ( nDateLen == 5 || nDateLen == 7 );
sal_uInt16 nFieldStart = nDateStart;
for (sal_uInt16 nPos=0; nPos<3; nPos++)
{
sal_uInt16 nFieldEnd = nFieldStart + 1; // default: 2 digits
if ( bLongYear && nPos == nYP )
nFieldEnd += 2; // 2 extra digits for long year
if ( bShortFirst && nPos == 0 )
--nFieldEnd; // first field shortened?
nStart[nPos] = nFieldStart;
nEnd[nPos] = nFieldEnd;
nFieldStart = nFieldEnd + 1;
}
nFound = 3;
}
}
if ( nFound >= 3 )
{
using namespace ::com::sun::star;
bool bSecondCal = false;
sal_uInt16 nDay = (sal_uInt16) rStr.copy( nStart[nDP], nEnd[nDP]+1-nStart[nDP] ).toInt32();
sal_uInt16 nYear = (sal_uInt16) rStr.copy( nStart[nYP], nEnd[nYP]+1-nStart[nYP] ).toInt32();
OUString aMStr = rStr.copy( nStart[nMP], nEnd[nMP]+1-nStart[nMP] );
sal_Int16 nMonth = (sal_Int16) aMStr.toInt32();
if (!nMonth)
{
static const OUString aSeptCorrect( "SEPT" );
static const OUString aSepShortened( "SEP" );
uno::Sequence< i18n::CalendarItem2 > xMonths;
sal_Int32 i, nMonthCount;
// first test all month names from local international
xMonths = rCalendar.getMonths();
nMonthCount = xMonths.getLength();
for (i=0; i<nMonthCount && !nMonth; i++)
{
if ( rTransliteration.isEqual( aMStr, xMonths[i].FullName ) ||
rTransliteration.isEqual( aMStr, xMonths[i].AbbrevName ) )
nMonth = sal::static_int_cast<sal_Int16>( i+1 );
else if ( i == 8 && rTransliteration.isEqual( aSeptCorrect,
xMonths[i].AbbrevName ) &&
rTransliteration.isEqual( aMStr, aSepShortened ) )
{ // correct English abbreviation is SEPT,
// but data mostly contains SEP only
nMonth = sal::static_int_cast<sal_Int16>( i+1 );
}
}
// if none found, then test english month names
if ( !nMonth && pSecondCalendar && pSecondTransliteration )
{
xMonths = pSecondCalendar->getMonths();
nMonthCount = xMonths.getLength();
for (i=0; i<nMonthCount && !nMonth; i++)
{
if ( pSecondTransliteration->isEqual( aMStr, xMonths[i].FullName ) ||
pSecondTransliteration->isEqual( aMStr, xMonths[i].AbbrevName ) )
{
nMonth = sal::static_int_cast<sal_Int16>( i+1 );
bSecondCal = true;
}
else if ( i == 8 && pSecondTransliteration->isEqual(
aMStr, aSepShortened ) )
{ // correct English abbreviation is SEPT,
// but data mostly contains SEP only
nMonth = sal::static_int_cast<sal_Int16>( i+1 );
bSecondCal = true;
}
}
}
}
SvNumberFormatter* pDocFormatter = pDoc->GetFormatTable();
if ( nYear < 100 )
nYear = pDocFormatter->ExpandTwoDigitYear( nYear );
CalendarWrapper* pCalendar = (bSecondCal ? pSecondCalendar : &rCalendar);
sal_Int16 nNumMonths = pCalendar->getNumberOfMonthsInYear();
if ( nDay && nMonth && nDay<=31 && nMonth<=nNumMonths )
{
--nMonth;
pCalendar->setValue( i18n::CalendarFieldIndex::DAY_OF_MONTH, nDay );
pCalendar->setValue( i18n::CalendarFieldIndex::MONTH, nMonth );
pCalendar->setValue( i18n::CalendarFieldIndex::YEAR, nYear );
sal_Int16 nHour, nMinute, nSecond, nMilli;
// #i14974# The imported value should have no fractional value, so set the
// time fields to zero (ICU calendar instance defaults to current date/time)
nHour = nMinute = nSecond = nMilli = 0;
if (nFound > 3)
nHour = (sal_Int16) rStr.copy( nStart[3], nEnd[3]+1-nStart[3]).toInt32();
if (nFound > 4)
nMinute = (sal_Int16) rStr.copy( nStart[4], nEnd[4]+1-nStart[4]).toInt32();
if (nFound > 5)
nSecond = (sal_Int16) rStr.copy( nStart[5], nEnd[5]+1-nStart[5]).toInt32();
if (nFound > 6)
{
sal_Unicode cDec = '.';
OUString aT( &cDec, 1);
aT += rStr.copy( nStart[6], nEnd[6]+1-nStart[6]);
rtl_math_ConversionStatus eStatus;
double fV = rtl::math::stringToDouble( aT, cDec, 0, &eStatus, 0);
if (eStatus == rtl_math_ConversionStatus_Ok)
nMilli = (sal_Int16) (1000.0 * fV + 0.5);
}
pCalendar->setValue( i18n::CalendarFieldIndex::HOUR, nHour );
pCalendar->setValue( i18n::CalendarFieldIndex::MINUTE, nMinute );
pCalendar->setValue( i18n::CalendarFieldIndex::SECOND, nSecond );
pCalendar->setValue( i18n::CalendarFieldIndex::MILLISECOND, nMilli );
if ( pCalendar->isValid() )
{
double fDiff = DateTime(*pDocFormatter->GetNullDate()) -
pCalendar->getEpochStart();
// #i14974# must use getLocalDateTime to get the same
// date values as set above
double fDays = pCalendar->getLocalDateTime();
fDays -= fDiff;
LanguageType eLatin, eCjk, eCtl;
pDoc->GetLanguage( eLatin, eCjk, eCtl );
LanguageType eDocLang = eLatin; //! which language for date formats?
short nType = (nFound > 3 ? NUMBERFORMAT_DATETIME : NUMBERFORMAT_DATE);
sal_uLong nFormat = pDocFormatter->GetStandardFormat( nType, eDocLang );
// maybe there is a special format including seconds or milliseconds
if (nFound > 5)
nFormat = pDocFormatter->GetStandardFormat( fDays, nFormat, nType, eDocLang);
ScAddress aPos(nCol,nRow,nTab);
rDocImport.setNumericCell(aPos, fDays);
pDoc->SetNumberFormat(aPos, nFormat);
return bMultiLine; // success
}
}
}
}
// Standard or date not determined -> SetString / EditCell
if( rStr.indexOf( '\n' ) == -1 )
{
ScSetStringParam aParam;
aParam.mpNumFormatter = pFormatter;
aParam.mbDetectNumberFormat = bDetectNumFormat;
aParam.meSetTextNumFormat = ScSetStringParam::SpecialNumberOnly;
aParam.mbHandleApostrophe = false;
rDocImport.setAutoInput(ScAddress(nCol, nRow, nTab), rStr, &aParam);
}
else
{
bMultiLine = true;
ScFieldEditEngine& rEngine = pDoc->GetEditEngine();
rEngine.SetText(rStr);
rDocImport.setEditCell(ScAddress(nCol, nRow, nTab), rEngine.CreateTextObject());
}
return bMultiLine;
}
static OUString lcl_GetFixed( const OUString& rLine, sal_Int32 nStart, sal_Int32 nNext,
bool& rbIsQuoted, bool& rbOverflowCell )
{
sal_Int32 nLen = rLine.getLength();
if (nNext > nLen)
nNext = nLen;
if ( nNext <= nStart )
return EMPTY_OUSTRING;
const sal_Unicode* pStr = rLine.getStr();
sal_Int32 nSpace = nNext;
while ( nSpace > nStart && pStr[nSpace-1] == ' ' )
--nSpace;
rbIsQuoted = (pStr[nStart] == '"' && pStr[nSpace-1] == '"');
if (rbIsQuoted)
{
bool bFits = (nSpace - nStart - 3 <= SAL_MAX_UINT16);
OSL_ENSURE( bFits, "lcl_GetFixed: line doesn't fit into data");
if (bFits)
return rLine.copy(nStart+1, nSpace-nStart-2);
else
{
rbOverflowCell = true;
return rLine.copy(nStart+1, SAL_MAX_UINT16);
}
}
else
{
bool bFits = (nSpace - nStart <= SAL_MAX_UINT16);
OSL_ENSURE( bFits, "lcl_GetFixed: line doesn't fit into data");
if (bFits)
return rLine.copy(nStart, nSpace-nStart);
else
{
rbOverflowCell = true;
return rLine.copy(nStart, SAL_MAX_UINT16);
}
}
}
bool ScImportExport::ExtText2Doc( SvStream& rStrm )
{
if (!pExtOptions)
return Text2Doc( rStrm );
sal_uInt64 const nOldPos = rStrm.Tell();
sal_uInt64 const nRemaining = rStrm.remainingSize();
boost::scoped_ptr<ScProgress> xProgress( new ScProgress( pDocSh,
ScGlobal::GetRscString( STR_LOAD_DOC ), nRemaining ));
rStrm.StartReadingUnicodeText( rStrm.GetStreamCharSet() );
SCCOL nStartCol = aRange.aStart.Col();
SCCOL nEndCol = aRange.aEnd.Col();
SCROW nStartRow = aRange.aStart.Row();
SCTAB nTab = aRange.aStart.Tab();
bool bFixed = pExtOptions->IsFixedLen();
const OUString& rSeps = pExtOptions->GetFieldSeps();
const sal_Unicode* pSeps = rSeps.getStr();
bool bMerge = pExtOptions->IsMergeSeps();
sal_uInt16 nInfoCount = pExtOptions->GetInfoCount();
const sal_Int32* pColStart = pExtOptions->GetColStart();
const sal_uInt8* pColFormat = pExtOptions->GetColFormat();
long nSkipLines = pExtOptions->GetStartRow();
LanguageType eDocLang = pExtOptions->GetLanguage();
SvNumberFormatter aNumFormatter( comphelper::getProcessComponentContext(), eDocLang);
bool bDetectNumFormat = pExtOptions->IsDetectSpecialNumber();
// For date recognition
::utl::TransliterationWrapper aTransliteration(
comphelper::getProcessComponentContext(), SC_TRANSLITERATION_IGNORECASE );
aTransliteration.loadModuleIfNeeded( eDocLang );
CalendarWrapper aCalendar( comphelper::getProcessComponentContext() );
aCalendar.loadDefaultCalendar(
LanguageTag::convertToLocale( eDocLang ) );
boost::scoped_ptr< ::utl::TransliterationWrapper > pEnglishTransliteration;
boost::scoped_ptr< CalendarWrapper > pEnglishCalendar;
if ( eDocLang != LANGUAGE_ENGLISH_US )
{
pEnglishTransliteration.reset(new ::utl::TransliterationWrapper (
comphelper::getProcessComponentContext(), SC_TRANSLITERATION_IGNORECASE ));
aTransliteration.loadModuleIfNeeded( LANGUAGE_ENGLISH_US );
pEnglishCalendar.reset(new CalendarWrapper ( comphelper::getProcessComponentContext() ));
pEnglishCalendar->loadDefaultCalendar(
LanguageTag::convertToLocale( LANGUAGE_ENGLISH_US ) );
}
OUString aLine;
OUString aCell;
sal_uInt16 i;
SCROW nRow = nStartRow;
while(--nSkipLines>0)
{
aLine = ReadCsvLine(rStrm, !bFixed, rSeps, cStr); // content is ignored
if ( rStrm.IsEof() )
break;
}
// Determine range for Undo.
// TODO: we don't need this during import of a file to a new sheet or
// document, could set bDetermineRange=false then.
bool bDetermineRange = true;
// Row heights don't need to be adjusted on the fly if EndPaste() is called
// afterwards, which happens only if bDetermineRange. This variable also
// survives the toggle of bDetermineRange down at the end of the do{} loop.
bool bRangeIsDetermined = bDetermineRange;
bool bQuotedAsText = pExtOptions && pExtOptions->IsQuotedAsText();
sal_uLong nOriginalStreamPos = rStrm.Tell();
ScDocumentImport aDocImport(*pDoc);
do
{
for( ;; )
{
aLine = ReadCsvLine(rStrm, !bFixed, rSeps, cStr);
if ( rStrm.IsEof() && aLine.isEmpty() )
break;
EmbeddedNullTreatment( aLine);
sal_Int32 nLineLen = aLine.getLength();
SCCOL nCol = nStartCol;
bool bMultiLine = false;
if ( bFixed ) // Fixed line length
{
// Yes, the check is nCol<=MAXCOL+1, +1 because it is only an
// overflow if there is really data following to be put behind
// the last column, which doesn't happen if info is
// SC_COL_SKIP.
for ( i=0; i<nInfoCount && nCol <= MAXCOL+1; i++ )
{
sal_uInt8 nFmt = pColFormat[i];
if (nFmt != SC_COL_SKIP) // sonst auch nCol nicht hochzaehlen
{
if (nCol > MAXCOL)
bOverflowCol = true; // display warning on import
else if (!bDetermineRange)
{
sal_Int32 nStart = pColStart[i];
sal_Int32 nNext = ( i+1 < nInfoCount ) ? pColStart[i+1] : nLineLen;
bool bIsQuoted = false;
aCell = lcl_GetFixed( aLine, nStart, nNext, bIsQuoted, bOverflowCell );
if (bIsQuoted && bQuotedAsText)
nFmt = SC_COL_TEXT;
bMultiLine |= lcl_PutString(
aDocImport, nCol, nRow, nTab, aCell, nFmt,
&aNumFormatter, bDetectNumFormat, aTransliteration, aCalendar,
pEnglishTransliteration.get(), pEnglishCalendar.get());
}
++nCol;
}
}
}
else // Search for the separator
{
SCCOL nSourceCol = 0;
sal_uInt16 nInfoStart = 0;
const sal_Unicode* p = aLine.getStr();
// Yes, the check is nCol<=MAXCOL+1, +1 because it is only an
// overflow if there is really data following to be put behind
// the last column, which doesn't happen if info is
// SC_COL_SKIP.
while (*p && nCol <= MAXCOL+1)
{
bool bIsQuoted = false;
p = ScImportExport::ScanNextFieldFromString( p, aCell,
cStr, pSeps, bMerge, bIsQuoted, bOverflowCell );
sal_uInt8 nFmt = SC_COL_STANDARD;
for ( i=nInfoStart; i<nInfoCount; i++ )
{
if ( pColStart[i] == nSourceCol + 1 ) // pColStart ist 1-basiert
{
nFmt = pColFormat[i];
nInfoStart = i + 1; // ColInfos sind in Reihenfolge
break; // for
}
}
if ( nFmt != SC_COL_SKIP )
{
if (nCol > MAXCOL)
bOverflowCol = true; // display warning on import
else if (!bDetermineRange)
{
if (bIsQuoted && bQuotedAsText)
nFmt = SC_COL_TEXT;
bMultiLine |= lcl_PutString(
aDocImport, nCol, nRow, nTab, aCell, nFmt,
&aNumFormatter, bDetectNumFormat, aTransliteration,
aCalendar, pEnglishTransliteration.get(), pEnglishCalendar.get());
}
++nCol;
}
++nSourceCol;
}
}
if (nEndCol < nCol)
nEndCol = nCol; //! points to the next free or even MAXCOL+2
if (!bDetermineRange)
{
if (bMultiLine && !bRangeIsDetermined && pDocSh)
pDocSh->AdjustRowHeight( nRow, nRow, nTab);
xProgress->SetStateOnPercent( rStrm.Tell() - nOldPos );
}
++nRow;
if ( nRow > MAXROW )
{
bOverflowRow = true; // display warning on import
break; // for
}
}
// so far nRow/nEndCol pointed to the next free
if (nRow > nStartRow)
--nRow;
if (nEndCol > nStartCol)
nEndCol = ::std::min( static_cast<SCCOL>(nEndCol - 1), MAXCOL);
if (bDetermineRange)
{
aRange.aEnd.SetCol( nEndCol );
aRange.aEnd.SetRow( nRow );
if ( !mbApi && nStartCol != nEndCol &&
!pDoc->IsBlockEmpty( nTab, nStartCol + 1, nStartRow, nEndCol, nRow ) )
{
ScReplaceWarnBox aBox( pDocSh->GetActiveDialogParent() );
if ( aBox.Execute() != RET_YES )
{
return false;
}
}
rStrm.Seek( nOriginalStreamPos );
nRow = nStartRow;
if (!StartPaste())
{
EndPaste(false);
return false;
}
}
bDetermineRange = !bDetermineRange; // toggle
} while (!bDetermineRange);
aDocImport.finalize();
xProgress.reset(); // make room for AdjustRowHeight progress
if (bRangeIsDetermined)
EndPaste(false);
if (mbImportBroadcast)
{
pDoc->BroadcastCells(aRange, SC_HINT_DATACHANGED);
pDocSh->PostDataChanged();
}
return true;
}
void ScImportExport::EmbeddedNullTreatment( OUString & rStr )
{
// A nasty workaround for data with embedded NULL characters. As long as we
// can't handle them properly as cell content (things assume 0-terminated
// strings at too many places) simply strip all NULL characters from raw
// data. Excel does the same. See fdo#57841 for sample data.
// The normal case is no embedded NULL, check first before de-/allocating
// ustring stuff.
sal_Unicode cNull = 0;
if (rStr.indexOf( cNull) >= 0)
{
rStr = rStr.replaceAll( OUString( &cNull, 1), OUString());
}
}
const sal_Unicode* ScImportExport::ScanNextFieldFromString( const sal_Unicode* p,
OUString& rField, sal_Unicode cStr, const sal_Unicode* pSeps, bool bMergeSeps, bool& rbIsQuoted,
bool& rbOverflowCell )
{
rbIsQuoted = false;
rField = "";
const sal_Unicode cBlank = ' ';
if (!ScGlobal::UnicodeStrChr( pSeps, cBlank))
{
// Cope with broken generators that put leading blanks before a quoted
// field, like "field1", "field2", "..."
// NOTE: this is not in conformance with http://tools.ietf.org/html/rfc4180
const sal_Unicode* pb = p;
while (*pb == cBlank)
++pb;
if (*pb == cStr)
p = pb;
}
if ( *p == cStr ) // String in quotes
{
rbIsQuoted = true;
const sal_Unicode* p1;
p1 = p = lcl_ScanString( p, rField, pSeps, cStr, DQM_ESCAPE, rbOverflowCell );
while ( *p && !ScGlobal::UnicodeStrChr( pSeps, *p ) )
p++;
// Append remaining unquoted and undelimited data (dirty, dirty) to
// this field.
if (p > p1)
{
if (!lcl_appendLineData( rField, p1, p))
rbOverflowCell = true;
}
if( *p )
p++;
}
else // up to delimiter
{
const sal_Unicode* p0 = p;
while ( *p && !ScGlobal::UnicodeStrChr( pSeps, *p ) )
p++;
if (!lcl_appendLineData( rField, p0, p))
rbOverflowCell = true;
if( *p )
p++;
}
if ( bMergeSeps ) // skip following delimiters
{
while ( *p && ScGlobal::UnicodeStrChr( pSeps, *p ) )
p++;
}
return p;
}
namespace {
/**
* Check if a given string has any line break characters or separators.
*
* @param rStr string to inspect.
* @param cSep separator character.
*/
bool hasLineBreaksOrSeps( const OUString& rStr, sal_Unicode cSep )
{
const sal_Unicode* p = rStr.getStr();
for (sal_Int32 i = 0, n = rStr.getLength(); i < n; ++i, ++p)
{
sal_Unicode c = *p;
if (c == cSep)
// separator found.
return true;
switch (c)
{
case '\n':
case '\r':
// line break found.
return true;
default:
;
}
}
return false;
}
}
bool ScImportExport::Doc2Text( SvStream& rStrm )
{
SCCOL nCol;
SCROW nRow;
SCCOL nStartCol = aRange.aStart.Col();
SCROW nStartRow = aRange.aStart.Row();
SCTAB nStartTab = aRange.aStart.Tab();
SCCOL nEndCol = aRange.aEnd.Col();
SCROW nEndRow = aRange.aEnd.Row();
SCTAB nEndTab = aRange.aEnd.Tab();
if (!pDoc->GetClipParam().isMultiRange() && nStartTab == nEndTab)
pDoc->ShrinkToDataArea( nStartTab, nStartCol, nStartRow, nEndCol, nEndRow );
OUString aCell;
bool bConvertLF = (GetSystemLineEnd() != LINEEND_LF);
for (nRow = nStartRow; nRow <= nEndRow; nRow++)
{
if (bIncludeFiltered || !pDoc->RowFiltered( nRow, nStartTab ))
{
for (nCol = nStartCol; nCol <= nEndCol; nCol++)
{
CellType eType;
pDoc->GetCellType( nCol, nRow, nStartTab, eType );
switch (eType)
{
case CELLTYPE_FORMULA:
{
if (bFormulas)
{
pDoc->GetFormula( nCol, nRow, nStartTab, aCell );
if( aCell.indexOf( cSep ) != -1 )
lcl_WriteString( rStrm, aCell, cStr, cStr );
else
lcl_WriteSimpleString( rStrm, aCell );
}
else
{
aCell = pDoc->GetString(nCol, nRow, nStartTab);
bool bMultiLineText = ( aCell.indexOf( '\n' ) != -1 );
if( bMultiLineText )
{
if( mExportTextOptions.meNewlineConversion == ScExportTextOptions::ToSpace )
aCell = aCell.replaceAll( "\n", " " );
else if ( mExportTextOptions.meNewlineConversion == ScExportTextOptions::ToSystem && bConvertLF )
aCell = convertLineEnd(aCell, GetSystemLineEnd());
}
if( mExportTextOptions.mcSeparatorConvertTo && cSep )
aCell = aCell.replaceAll( OUString(cSep), OUString(mExportTextOptions.mcSeparatorConvertTo) );
if( mExportTextOptions.mbAddQuotes && ( aCell.indexOf( cSep ) != -1 ) )
lcl_WriteString( rStrm, aCell, cStr, cStr );
else
lcl_WriteSimpleString( rStrm, aCell );
}
}
break;
case CELLTYPE_VALUE:
{
aCell = pDoc->GetString(nCol, nRow, nStartTab);
lcl_WriteSimpleString( rStrm, aCell );
}
break;
case CELLTYPE_NONE:
break;
default:
{
aCell = pDoc->GetString(nCol, nRow, nStartTab);
bool bMultiLineText = ( aCell.indexOf( '\n' ) != -1 );
if( bMultiLineText )
{
if( mExportTextOptions.meNewlineConversion == ScExportTextOptions::ToSpace )
aCell = aCell.replaceAll( "\n", " " );
else if ( mExportTextOptions.meNewlineConversion == ScExportTextOptions::ToSystem && bConvertLF )
aCell = convertLineEnd(aCell, GetSystemLineEnd());
}
if( mExportTextOptions.mcSeparatorConvertTo && cSep )
aCell = aCell.replaceAll( OUString(cSep), OUString(mExportTextOptions.mcSeparatorConvertTo) );
if( mExportTextOptions.mbAddQuotes && hasLineBreaksOrSeps(aCell, cSep) )
lcl_WriteString( rStrm, aCell, cStr, cStr );
else
lcl_WriteSimpleString( rStrm, aCell );
}
}
if( nCol < nEndCol )
lcl_WriteSimpleString( rStrm, OUString(cSep) );
}
WriteUnicodeOrByteEndl( rStrm );
if( rStrm.GetError() != SVSTREAM_OK )
break;
if( nSizeLimit && rStrm.Tell() > nSizeLimit )
break;
}
}
return rStrm.GetError() == SVSTREAM_OK;
}
bool ScImportExport::Sylk2Doc( SvStream& rStrm )
{
bool bOk = true;
bool bMyDoc = false;
SylkVersion eVersion = SYLK_OTHER;
// US-English separators for StringToDouble
sal_Unicode cDecSep = '.';
sal_Unicode cGrpSep = ',';
SCCOL nStartCol = aRange.aStart.Col();
SCROW nStartRow = aRange.aStart.Row();
SCCOL nEndCol = aRange.aEnd.Col();
SCROW nEndRow = aRange.aEnd.Row();
sal_uLong nOldPos = rStrm.Tell();
bool bData = !bSingle;
::std::vector< sal_uInt32 > aFormats;
if( !bSingle)
bOk = StartPaste();
while( bOk )
{
OUString aLine;
OUString aText;
OString aByteLine;
SCCOL nCol = nStartCol;
SCROW nRow = nStartRow;
SCCOL nRefCol = 1;
SCROW nRefRow = 1;
rStrm.Seek( nOldPos );
for( ;; )
{
//! allow unicode
rStrm.ReadLine( aByteLine );
aLine = OStringToOUString(aByteLine, rStrm.GetStreamCharSet());
if( rStrm.IsEof() )
break;
const sal_Unicode* p = aLine.getStr();
sal_Unicode cTag = *p++;
if( cTag == 'C' ) // Content
{
if( *p++ != ';' )
return false;
while( *p )
{
sal_Unicode ch = *p++;
ch = ScGlobal::ToUpperAlpha( ch );
switch( ch )
{
case 'X':
nCol = static_cast<SCCOL>(OUString(p).toInt32()) + nStartCol - 1;
break;
case 'Y':
nRow = OUString(p).toInt32() + nStartRow - 1;
break;
case 'C':
nRefCol = static_cast<SCCOL>(OUString(p).toInt32()) + nStartCol - 1;
break;
case 'R':
nRefRow = OUString(p).toInt32() + nStartRow - 1;
break;
case 'K':
{
if( !bSingle &&
( nCol < nStartCol || nCol > nEndCol
|| nRow < nStartRow || nRow > nEndRow
|| nCol > MAXCOL || nRow > MAXROW ) )
break;
if( !bData )
{
if( nRow > nEndRow )
nEndRow = nRow;
if( nCol > nEndCol )
nEndCol = nCol;
break;
}
bool bText;
if( *p == '"' )
{
bText = true;
aText = "";
p = lcl_ScanSylkString( p, aText, eVersion);
}
else
bText = false;
const sal_Unicode* q = p;
while( *q && *q != ';' )
q++;
if ( !(*q == ';' && *(q+1) == 'I') )
{ // don't ignore value
if( bText )
{
pDoc->EnsureTable(aRange.aStart.Tab());
pDoc->SetTextCell(
ScAddress(nCol, nRow, aRange.aStart.Tab()), aText);
}
else
{
double fVal = rtl_math_uStringToDouble( p,
aLine.getStr() + aLine.getLength(),
cDecSep, cGrpSep, NULL, NULL );
pDoc->SetValue( nCol, nRow, aRange.aStart.Tab(), fVal );
}
}
}
break;
case 'E':
case 'M':
{
if ( ch == 'M' )
{
if ( nRefCol < nCol )
nRefCol = nCol;
if ( nRefRow < nRow )
nRefRow = nRow;
if ( !bData )
{
if( nRefRow > nEndRow )
nEndRow = nRefRow;
if( nRefCol > nEndCol )
nEndCol = nRefCol;
}
}
if( !bMyDoc || !bData )
break;
aText = "=";
p = lcl_ScanSylkFormula( p, aText, eVersion);
ScAddress aPos( nCol, nRow, aRange.aStart.Tab() );
/* FIXME: do we want GRAM_ODFF_A1 instead? At the
* end it probably should be GRAM_ODFF_R1C1, since
* R1C1 is what Excel writes in SYLK. */
const formula::FormulaGrammar::Grammar eGrammar = formula::FormulaGrammar::GRAM_PODF_A1;
ScCompiler aComp( pDoc, aPos);
aComp.SetGrammar(eGrammar);
ScTokenArray* pCode = aComp.CompileString( aText );
if ( ch == 'M' )
{
ScMarkData aMark;
aMark.SelectTable( aPos.Tab(), true );
pDoc->InsertMatrixFormula( nCol, nRow, nRefCol,
nRefRow, aMark, EMPTY_OUSTRING, pCode );
}
else
{
ScFormulaCell* pFCell = new ScFormulaCell(
pDoc, aPos, *pCode, eGrammar, MM_NONE);
pDoc->SetFormulaCell(aPos, pFCell);
}
delete pCode; // ctor/InsertMatrixFormula did copy TokenArray
}
break;
}
while( *p && *p != ';' )
p++;
if( *p )
p++;
}
}
else if( cTag == 'F' ) // Format
{
if( *p++ != ';' )
return false;
sal_Int32 nFormat = -1;
while( *p )
{
sal_Unicode ch = *p++;
ch = ScGlobal::ToUpperAlpha( ch );
switch( ch )
{
case 'X':
nCol = static_cast<SCCOL>(OUString(p).toInt32()) + nStartCol - 1;
break;
case 'Y':
nRow = OUString(p).toInt32() + nStartRow - 1;
break;
case 'P' :
if ( bData )
{
// F;P<n> sets format code of P;P<code> at
// current position, or at ;X;Y if specified.
// Note that ;X;Y may appear after ;P
const sal_Unicode* p0 = p;
while( *p && *p != ';' )
p++;
OUString aNumber(p0, p - p0);
nFormat = aNumber.toInt32();
}
break;
}
while( *p && *p != ';' )
p++;
if( *p )
p++;
}
if ( !bData )
{
if( nRow > nEndRow )
nEndRow = nRow;
if( nCol > nEndCol )
nEndCol = nCol;
}
if ( 0 <= nFormat && nFormat < (sal_Int32)aFormats.size() )
{
sal_uInt32 nKey = aFormats[nFormat];
pDoc->ApplyAttr( nCol, nRow, aRange.aStart.Tab(),
SfxUInt32Item( ATTR_VALUE_FORMAT, nKey ) );
}
}
else if( cTag == 'P' )
{
if ( bData && *p == ';' && *(p+1) == 'P' )
{
OUString aCode( p+2 );
// unescape doubled semicolons
aCode = aCode.replaceAll(";;", ";");
// get rid of Xcl escape characters
aCode = aCode.replaceAll(OUString(static_cast<sal_Unicode>(0x1b)), OUString());
sal_Int32 nCheckPos;
short nType;
sal_uInt32 nKey;
pDoc->GetFormatTable()->PutandConvertEntry( aCode, nCheckPos, nType, nKey,
LANGUAGE_ENGLISH_US, ScGlobal::eLnge );
if ( nCheckPos )
nKey = 0;
aFormats.push_back( nKey );
}
}
else if( cTag == 'I' && *p == 'D' )
{
aLine = aLine.copy(4);
if (aLine == "CALCOOO32")
eVersion = SYLK_OOO32;
else if (aLine == "SCALC3")
eVersion = SYLK_SCALC3;
bMyDoc = (eVersion <= SYLK_OWN);
}
else if( cTag == 'E' ) // Ende
break;
}
if( !bData )
{
aRange.aEnd.SetCol( nEndCol );
aRange.aEnd.SetRow( nEndRow );
bOk = StartPaste();
bData = true;
}
else
break;
}
EndPaste();
return bOk;
}
bool ScImportExport::Doc2Sylk( SvStream& rStrm )
{
SCCOL nCol;
SCROW nRow;
SCCOL nStartCol = aRange.aStart.Col();
SCROW nStartRow = aRange.aStart.Row();
SCCOL nEndCol = aRange.aEnd.Col();
SCROW nEndRow = aRange.aEnd.Row();
OUString aCellStr;
OUString aValStr;
lcl_WriteSimpleString( rStrm, OUString("ID;PCALCOOO32") );
WriteUnicodeOrByteEndl( rStrm );
for (nRow = nStartRow; nRow <= nEndRow; nRow++)
{
for (nCol = nStartCol; nCol <= nEndCol; nCol++)
{
OUString aBufStr;
double nVal;
bool bForm = false;
SCROW r = nRow - nStartRow + 1;
SCCOL c = nCol - nStartCol + 1;
ScRefCellValue aCell;
aCell.assign(*pDoc, ScAddress(nCol, nRow, aRange.aStart.Tab()));
CellType eType = aCell.meType;
switch( eType )
{
case CELLTYPE_FORMULA:
bForm = bFormulas;
if( pDoc->HasValueData( nCol, nRow, aRange.aStart.Tab()) )
goto hasvalue;
else
goto hasstring;
case CELLTYPE_VALUE:
hasvalue:
pDoc->GetValue( nCol, nRow, aRange.aStart.Tab(), nVal );
aValStr = ::rtl::math::doubleToUString( nVal,
rtl_math_StringFormat_Automatic,
rtl_math_DecimalPlaces_Max, '.', true );
aBufStr = "C;X";
aBufStr += OUString::number( c );
aBufStr += ";Y";
aBufStr += OUString::number( r );
aBufStr += ";K";
aBufStr += aValStr;
lcl_WriteSimpleString( rStrm, aBufStr );
goto checkformula;
case CELLTYPE_STRING:
case CELLTYPE_EDIT:
hasstring:
aCellStr = pDoc->GetString(nCol, nRow, aRange.aStart.Tab());
aCellStr = aCellStr.replaceAll( OUString('\n'), OUString(SYLK_LF) );
aBufStr = "C;X";
aBufStr += OUString::number( c );
aBufStr += ";Y";
aBufStr += OUString::number( r );
aBufStr += ";K";
lcl_WriteSimpleString( rStrm, aBufStr );
lcl_WriteString( rStrm, aCellStr, '"', ';' );
checkformula:
if( bForm )
{
const ScFormulaCell* pFCell = aCell.mpFormula;
switch ( pFCell->GetMatrixFlag() )
{
case MM_REFERENCE :
aCellStr = "";
break;
default:
OUString aOUCellStr;
pFCell->GetFormula( aOUCellStr,formula::FormulaGrammar::GRAM_PODF_A1);
aCellStr = aOUCellStr;
/* FIXME: do we want GRAM_ODFF_A1 instead? At
* the end it probably should be
* GRAM_ODFF_R1C1, since R1C1 is what Excel
* writes in SYLK. */
}
if ( pFCell->GetMatrixFlag() != MM_NONE &&
aCellStr.startsWith("{") &&
aCellStr.endsWith("}") )
{ // cut off matrix {} characters
aCellStr = aCellStr.copy(1, aCellStr.getLength()-2);
}
if ( aCellStr[0] == '=' )
aCellStr = aCellStr.copy(1);
OUString aPrefix;
switch ( pFCell->GetMatrixFlag() )
{
case MM_FORMULA :
{ // diff expression with 'M' M$-extension
SCCOL nC;
SCROW nR;
pFCell->GetMatColsRows( nC, nR );
nC += c - 1;
nR += r - 1;
aPrefix = ";R";
aPrefix += OUString::number( nR );
aPrefix += ";C";
aPrefix += OUString::number( nC );
aPrefix += ";M";
}
break;
case MM_REFERENCE :
{ // diff expression with 'I' M$-extension
ScAddress aPos;
pFCell->GetMatrixOrigin( aPos );
aPrefix = ";I;R";
aPrefix += OUString::number( aPos.Row() - nStartRow + 1 );
aPrefix += ";C";
aPrefix += OUString::number( aPos.Col() - nStartCol + 1 );
}
break;
default:
// formula Expression
aPrefix = ";E";
}
lcl_WriteSimpleString( rStrm, aPrefix );
if ( !aCellStr.isEmpty() )
lcl_WriteString( rStrm, aCellStr, 0, ';' );
}
WriteUnicodeOrByteEndl( rStrm );
break;
default:
{
// added to avoid warnings
}
}
}
}
lcl_WriteSimpleString( rStrm, OUString( 'E' ) );
WriteUnicodeOrByteEndl( rStrm );
return rStrm.GetError() == SVSTREAM_OK;
}
bool ScImportExport::Doc2HTML( SvStream& rStrm, const OUString& rBaseURL )
{
// rtl_TextEncoding is ignored in ScExportHTML, read from Load/Save HTML options
ScFormatFilter::Get().ScExportHTML( rStrm, rBaseURL, pDoc, aRange, RTL_TEXTENCODING_DONTKNOW, bAll,
aStreamPath, aNonConvertibleChars, maFilterOptions );
return rStrm.GetError() == SVSTREAM_OK;
}
bool ScImportExport::Doc2RTF( SvStream& rStrm )
{
// rtl_TextEncoding is ignored in ScExportRTF
ScFormatFilter::Get().ScExportRTF( rStrm, pDoc, aRange, RTL_TEXTENCODING_DONTKNOW );
return rStrm.GetError() == SVSTREAM_OK;
}
bool ScImportExport::Doc2Dif( SvStream& rStrm )
{
// for DIF in the clipboard, IBM_850 is always used
ScFormatFilter::Get().ScExportDif( rStrm, pDoc, aRange, RTL_TEXTENCODING_IBM_850 );
return true;
}
bool ScImportExport::Dif2Doc( SvStream& rStrm )
{
SCTAB nTab = aRange.aStart.Tab();
ScDocument* pImportDoc = new ScDocument( SCDOCMODE_UNDO );
pImportDoc->InitUndo( pDoc, nTab, nTab );
// for DIF in the clipboard, IBM_850 is always used
ScFormatFilter::Get().ScImportDif( rStrm, pImportDoc, aRange.aStart, RTL_TEXTENCODING_IBM_850 );
SCCOL nEndCol;
SCROW nEndRow;
pImportDoc->GetCellArea( nTab, nEndCol, nEndRow );
// if there are no cells in the imported content, nEndCol/nEndRow may be before the start
if ( nEndCol < aRange.aStart.Col() )
nEndCol = aRange.aStart.Col();
if ( nEndRow < aRange.aStart.Row() )
nEndRow = aRange.aStart.Row();
aRange.aEnd = ScAddress( nEndCol, nEndRow, nTab );
bool bOk = StartPaste();
if (bOk)
{
sal_uInt16 nFlags = IDF_ALL & ~IDF_STYLES;
pDoc->DeleteAreaTab( aRange, nFlags );
pImportDoc->CopyToDocument( aRange, nFlags, false, pDoc );
EndPaste();
}
delete pImportDoc;
return bOk;
}
bool ScImportExport::RTF2Doc( SvStream& rStrm, const OUString& rBaseURL )
{
ScEEAbsImport *pImp = ScFormatFilter::Get().CreateRTFImport( pDoc, aRange );
if (!pImp)
return false;
pImp->Read( rStrm, rBaseURL );
aRange = pImp->GetRange();
bool bOk = StartPaste();
if (bOk)
{
sal_uInt16 nFlags = IDF_ALL & ~IDF_STYLES;
pDoc->DeleteAreaTab( aRange, nFlags );
pImp->WriteToDocument();
EndPaste();
}
delete pImp;
return bOk;
}
bool ScImportExport::HTML2Doc( SvStream& rStrm, const OUString& rBaseURL )
{
ScEEAbsImport *pImp = ScFormatFilter::Get().CreateHTMLImport( pDoc, rBaseURL, aRange, true);
if (!pImp)
return false;
pImp->Read( rStrm, rBaseURL );
aRange = pImp->GetRange();
bool bOk = StartPaste();
if (bOk)
{
// ScHTMLImport may call ScDocument::InitDrawLayer, resulting in
// a Draw Layer but no Draw View -> create Draw Layer and View here
if (pDocSh)
pDocSh->MakeDrawLayer();
sal_uInt16 nFlags = IDF_ALL & ~IDF_STYLES;
pDoc->DeleteAreaTab( aRange, nFlags );
if (pExtOptions)
{
// Pick up import options if available.
LanguageType eLang = pExtOptions->GetLanguage();
SvNumberFormatter aNumFormatter( comphelper::getProcessComponentContext(), eLang);
bool bSpecialNumber = pExtOptions->IsDetectSpecialNumber();
pImp->WriteToDocument(false, 1.0, &aNumFormatter, bSpecialNumber);
}
else
// Regular import, with no options.
pImp->WriteToDocument();
EndPaste();
}
delete pImp;
return bOk;
}
#ifndef DISABLE_DYNLOADING
class ScFormatFilterMissing : public ScFormatFilterPlugin {
public:
ScFormatFilterMissing()
{
OSL_FAIL("Missing file filters");
}
virtual ~ScFormatFilterMissing() {}
virtual FltError ScImportLotus123( SfxMedium&, ScDocument*, rtl_TextEncoding ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScImportQuattroPro( SfxMedium &, ScDocument * ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScImportExcel( SfxMedium&, ScDocument*, const EXCIMPFORMAT ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScImportStarCalc10( SvStream&, ScDocument* ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScImportDif( SvStream&, ScDocument*, const ScAddress&,
const rtl_TextEncoding, sal_uInt32 ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScImportRTF( SvStream&, const OUString&, ScDocument*, ScRange& ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScImportHTML( SvStream&, const OUString&, ScDocument*, ScRange&, double, bool, SvNumberFormatter*, bool ) SAL_OVERRIDE { return eERR_INTERN; }
virtual ScEEAbsImport *CreateRTFImport( ScDocument*, const ScRange& ) SAL_OVERRIDE { return NULL; }
virtual ScEEAbsImport *CreateHTMLImport( ScDocument*, const OUString&, const ScRange&, bool ) SAL_OVERRIDE { return NULL; }
virtual OUString GetHTMLRangeNameList( ScDocument*, const OUString& ) SAL_OVERRIDE { return OUString(); }
virtual FltError ScExportExcel5( SfxMedium&, ScDocument*, ExportFormatExcel, rtl_TextEncoding ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScExportDif( SvStream&, ScDocument*, const ScAddress&, const rtl_TextEncoding, sal_uInt32 ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScExportDif( SvStream&, ScDocument*, const ScRange&, const rtl_TextEncoding, sal_uInt32 ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScExportHTML( SvStream&, const OUString&, ScDocument*, const ScRange&, const rtl_TextEncoding, bool,
const OUString&, OUString&, const OUString& ) SAL_OVERRIDE { return eERR_INTERN; }
virtual FltError ScExportRTF( SvStream&, ScDocument*, const ScRange&, const rtl_TextEncoding ) SAL_OVERRIDE { return eERR_INTERN; }
virtual ScOrcusFilters* GetOrcusFilters() SAL_OVERRIDE { return NULL; }
};
extern "C" { static void SAL_CALL thisModule() {} }
#else
extern "C" {
ScFormatFilterPlugin* ScFilterCreate();
}
#endif
typedef ScFormatFilterPlugin * (*FilterFn)(void);
ScFormatFilterPlugin &ScFormatFilter::Get()
{
static ScFormatFilterPlugin *plugin;
if (plugin != NULL)
return *plugin;
#ifndef DISABLE_DYNLOADING
OUString sFilterLib(SVLIBRARY("scfilt"));
static ::osl::Module aModule;
bool bLoaded = aModule.loadRelative(&thisModule, sFilterLib);
if (!bLoaded)
bLoaded = aModule.load(sFilterLib);
if (bLoaded)
{
oslGenericFunction fn = aModule.getFunctionSymbol( OUString( "ScFilterCreate" ) );
if (fn != NULL)
plugin = reinterpret_cast<FilterFn>(fn)();
}
if (plugin == NULL)
plugin = new ScFormatFilterMissing();
#else
plugin = ScFilterCreate();
#endif
return *plugin;
}
// Precondition: pStr is guaranteed to be non-NULL and points to a 0-terminated
// array.
static inline const sal_Unicode* lcl_UnicodeStrChr( const sal_Unicode* pStr,
sal_Unicode c )
{
while (*pStr)
{
if (*pStr == c)
return pStr;
++pStr;
}
return 0;
}
OUString ReadCsvLine( SvStream &rStream, bool bEmbeddedLineBreak,
const OUString& rFieldSeparators, sal_Unicode cFieldQuote )
{
OUString aStr;
rStream.ReadUniOrByteStringLine(aStr, rStream.GetStreamCharSet(), nArbitraryLineLengthLimit);
if (bEmbeddedLineBreak)
{
const sal_Unicode* pSeps = rFieldSeparators.getStr();
QuoteType eQuoteState = FIELDEND_QUOTE;
bool bFieldStart = true;
sal_Int32 nLastOffset = 0;
sal_Int32 nQuotes = 0;
while (!rStream.IsEof() && aStr.getLength() < nArbitraryLineLengthLimit)
{
const sal_Unicode *p, *pStart;
p = pStart = aStr.getStr();
p += nLastOffset;
while (*p)
{
if (nQuotes)
{
if (*p == cFieldQuote)
{
if (bFieldStart)
{
++nQuotes;
bFieldStart = false;
eQuoteState = FIELDSTART_QUOTE;
}
// Do not detect a FIELDSTART_QUOTE if not in
// bFieldStart mode, in which case for unquoted content
// we are in FIELDEND_QUOTE state.
else if (eQuoteState != FIELDEND_QUOTE)
{
eQuoteState = lcl_isEscapedOrFieldEndQuote( nQuotes, p, pSeps, cFieldQuote);
// DONTKNOW_QUOTE is an embedded unescaped quote we
// don't count for pairing.
if (eQuoteState != DONTKNOW_QUOTE)
++nQuotes;
}
}
else if (eQuoteState == FIELDEND_QUOTE)
{
if (bFieldStart)
// If blank is a separator it starts a field, if it
// is not and thus maybe leading before quote we
// are still at start of field regarding quotes.
bFieldStart = (*p == ' ' || lcl_UnicodeStrChr( pSeps, *p) != NULL);
else
bFieldStart = (lcl_UnicodeStrChr( pSeps, *p) != NULL);
}
}
else
{
if (*p == cFieldQuote && bFieldStart)
{
nQuotes = 1;
eQuoteState = FIELDSTART_QUOTE;
bFieldStart = false;
}
else if (eQuoteState == FIELDEND_QUOTE)
{
// This also skips leading blanks at beginning of line
// if followed by a quote. It's debatable whether we
// actually want that or not, but congruent with what
// ScanNextFieldFromString() does.
if (bFieldStart)
bFieldStart = (*p == ' ' || lcl_UnicodeStrChr( pSeps, *p) != NULL);
else
bFieldStart = (lcl_UnicodeStrChr( pSeps, *p) != NULL);
}
}
// A quote character inside a field content does not start
// a quote.
++p;
}
if (nQuotes % 2 == 0)
// We still have a (theoretical?) problem here if due to
// nArbitraryLineLengthLimit we split a string right between a
// doubled quote pair.
break;
else
{
nLastOffset = aStr.getLength();
OUString aNext;
rStream.ReadUniOrByteStringLine(aNext, rStream.GetStreamCharSet(), nArbitraryLineLengthLimit);
aStr += OUString('\n');
aStr += aNext;
}
}
}
return aStr;
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|