Loading...
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 | /* Extended regular expression matching and search library. Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. The GNU C Library is free software; you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation; either version 2.1 of the License, or (at your option) any later version. The GNU C Library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with the GNU C Library; if not, see <http://www.gnu.org/licenses/>. */ static void re_string_construct_common (const char *str, int len, re_string_t *pstr, __RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) internal_function; static re_dfastate_t *create_ci_newstate (const re_dfa_t *dfa, const re_node_set *nodes, unsigned int hash) internal_function; static re_dfastate_t *create_cd_newstate (const re_dfa_t *dfa, const re_node_set *nodes, unsigned int context, unsigned int hash) internal_function; /* Functions for string operation. */ /* This function allocate the buffers. It is necessary to call re_string_reconstruct before using the object. */ static reg_errcode_t internal_function re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len, __RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) { reg_errcode_t ret; int init_buf_len; /* Ensure at least one character fits into the buffers. */ if (init_len < dfa->mb_cur_max) init_len = dfa->mb_cur_max; init_buf_len = (len + 1 < init_len) ? len + 1: init_len; re_string_construct_common (str, len, pstr, trans, icase, dfa); ret = re_string_realloc_buffers (pstr, init_buf_len); if (BE (ret != REG_NOERROR, 0)) return ret; pstr->word_char = dfa->word_char; pstr->word_ops_used = dfa->word_ops_used; pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str; pstr->valid_len = (pstr->mbs_allocated || dfa->mb_cur_max > 1) ? 0 : len; pstr->valid_raw_len = pstr->valid_len; return REG_NOERROR; } /* This function allocate the buffers, and initialize them. */ static reg_errcode_t internal_function re_string_construct (re_string_t *pstr, const char *str, int len, __RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) { reg_errcode_t ret; memset (pstr, '\0', sizeof (re_string_t)); re_string_construct_common (str, len, pstr, trans, icase, dfa); if (len > 0) { ret = re_string_realloc_buffers (pstr, len + 1); if (BE (ret != REG_NOERROR, 0)) return ret; } pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str; if (icase) { #ifdef RE_ENABLE_I18N if (dfa->mb_cur_max > 1) { while (1) { ret = build_wcs_upper_buffer (pstr); if (BE (ret != REG_NOERROR, 0)) return ret; if (pstr->valid_raw_len >= len) break; if (pstr->bufs_len > pstr->valid_len + dfa->mb_cur_max) break; ret = re_string_realloc_buffers (pstr, pstr->bufs_len * 2); if (BE (ret != REG_NOERROR, 0)) return ret; } } else #endif /* RE_ENABLE_I18N */ build_upper_buffer (pstr); } else { #ifdef RE_ENABLE_I18N if (dfa->mb_cur_max > 1) build_wcs_buffer (pstr); else #endif { if (trans != NULL) re_string_translate_buffer (pstr); else { pstr->valid_len = pstr->bufs_len; pstr->valid_raw_len = pstr->bufs_len; } } } return REG_NOERROR; } /* Helper functions for re_string_allocate, and re_string_construct. */ static reg_errcode_t internal_function re_string_realloc_buffers (re_string_t *pstr, int new_buf_len) { #ifdef RE_ENABLE_I18N if (pstr->mb_cur_max > 1) { wint_t *new_wcs = re_realloc (pstr->wcs, wint_t, new_buf_len); if (BE (new_wcs == NULL, 0)) return REG_ESPACE; pstr->wcs = new_wcs; if (pstr->offsets != NULL) { int *new_offsets = re_realloc (pstr->offsets, int, new_buf_len); if (BE (new_offsets == NULL, 0)) return REG_ESPACE; pstr->offsets = new_offsets; } } #endif /* RE_ENABLE_I18N */ if (pstr->mbs_allocated) { unsigned char *new_mbs = re_realloc (pstr->mbs, unsigned char, new_buf_len); if (BE (new_mbs == NULL, 0)) return REG_ESPACE; pstr->mbs = new_mbs; } pstr->bufs_len = new_buf_len; return REG_NOERROR; } static void internal_function re_string_construct_common (const char *str, int len, re_string_t *pstr, __RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) { pstr->raw_mbs = (const unsigned char *) str; pstr->len = len; pstr->raw_len = len; pstr->trans = trans; pstr->icase = icase ? 1 : 0; pstr->mbs_allocated = (trans != NULL || icase); pstr->mb_cur_max = dfa->mb_cur_max; pstr->is_utf8 = dfa->is_utf8; pstr->map_notascii = dfa->map_notascii; pstr->stop = pstr->len; pstr->raw_stop = pstr->stop; } #ifdef RE_ENABLE_I18N /* Build wide character buffer PSTR->WCS. If the byte sequence of the string are: <mb1>(0), <mb1>(1), <mb2>(0), <mb2>(1), <sb3> Then wide character buffer will be: <wc1> , WEOF , <wc2> , WEOF , <wc3> We use WEOF for padding, they indicate that the position isn't a first byte of a multibyte character. Note that this function assumes PSTR->VALID_LEN elements are already built and starts from PSTR->VALID_LEN. */ static void internal_function build_wcs_buffer (re_string_t *pstr) { #if defined __UCLIBC__ unsigned char buf[MB_LEN_MAX]; assert (MB_LEN_MAX >= pstr->mb_cur_max); #else unsigned char buf[64]; #endif mbstate_t prev_st; int byte_idx, end_idx, remain_len; size_t mbclen; /* Build the buffers from pstr->valid_len to either pstr->len or pstr->bufs_len. */ end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; for (byte_idx = pstr->valid_len; byte_idx < end_idx;) { wchar_t wc; const char *p; remain_len = end_idx - byte_idx; prev_st = pstr->cur_state; /* Apply the translation if we need. */ if (BE (pstr->trans != NULL, 0)) { int i, ch; for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i) { ch = pstr->raw_mbs [pstr->raw_mbs_idx + byte_idx + i]; buf[i] = pstr->mbs[byte_idx + i] = pstr->trans[ch]; } p = (const char *) buf; } else p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx; mbclen = mbrtowc (&wc, p, remain_len, &pstr->cur_state); if (BE (mbclen == (size_t) -2, 0)) { /* The buffer doesn't have enough space, finish to build. */ pstr->cur_state = prev_st; break; } else if (BE (mbclen == (size_t) -1 || mbclen == 0, 0)) { /* We treat these cases as a singlebyte character. */ mbclen = 1; wc = (wchar_t) pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; if (BE (pstr->trans != NULL, 0)) wc = pstr->trans[wc]; pstr->cur_state = prev_st; } /* Write wide character and padding. */ pstr->wcs[byte_idx++] = wc; /* Write paddings. */ for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) pstr->wcs[byte_idx++] = WEOF; } pstr->valid_len = byte_idx; pstr->valid_raw_len = byte_idx; } /* Build wide character buffer PSTR->WCS like build_wcs_buffer, but for REG_ICASE. */ static reg_errcode_t internal_function build_wcs_upper_buffer (re_string_t *pstr) { mbstate_t prev_st; int src_idx, byte_idx, end_idx, remain_len; size_t mbclen; #if defined __UCLIBC__ char buf[MB_LEN_MAX]; assert (MB_LEN_MAX >= pstr->mb_cur_max); #else char buf[64]; #endif byte_idx = pstr->valid_len; end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; /* The following optimization assumes that ASCII characters can be mapped to wide characters with a simple cast. */ if (! pstr->map_notascii && pstr->trans == NULL && !pstr->offsets_needed) { while (byte_idx < end_idx) { wchar_t wc; if (isascii (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]) && mbsinit (&pstr->cur_state)) { /* In case of a singlebyte character. */ pstr->mbs[byte_idx] = toupper (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]); /* The next step uses the assumption that wchar_t is encoded ASCII-safe: all ASCII values can be converted like this. */ pstr->wcs[byte_idx] = (wchar_t) pstr->mbs[byte_idx]; ++byte_idx; continue; } remain_len = end_idx - byte_idx; prev_st = pstr->cur_state; mbclen = mbrtowc (&wc, ((const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx), remain_len, &pstr->cur_state); if (BE (mbclen + 2 > 2, 1)) { wchar_t wcu = wc; if (iswlower (wc)) { size_t mbcdlen; wcu = towupper (wc); mbcdlen = wcrtomb (buf, wcu, &prev_st); if (BE (mbclen == mbcdlen, 1)) memcpy (pstr->mbs + byte_idx, buf, mbclen); else { src_idx = byte_idx; goto offsets_needed; } } else memcpy (pstr->mbs + byte_idx, pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx, mbclen); pstr->wcs[byte_idx++] = wcu; /* Write paddings. */ for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) pstr->wcs[byte_idx++] = WEOF; } else if (mbclen == (size_t) -1 || mbclen == 0) { /* It is an invalid character or '\0'. Just use the byte. */ int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; pstr->mbs[byte_idx] = ch; /* And also cast it to wide char. */ pstr->wcs[byte_idx++] = (wchar_t) ch; if (BE (mbclen == (size_t) -1, 0)) pstr->cur_state = prev_st; } else { /* The buffer doesn't have enough space, finish to build. */ pstr->cur_state = prev_st; break; } } pstr->valid_len = byte_idx; pstr->valid_raw_len = byte_idx; return REG_NOERROR; } else for (src_idx = pstr->valid_raw_len; byte_idx < end_idx;) { wchar_t wc; const char *p; offsets_needed: remain_len = end_idx - byte_idx; prev_st = pstr->cur_state; if (BE (pstr->trans != NULL, 0)) { int i, ch; for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i) { ch = pstr->raw_mbs [pstr->raw_mbs_idx + src_idx + i]; buf[i] = pstr->trans[ch]; } p = (const char *) buf; } else p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + src_idx; mbclen = mbrtowc (&wc, p, remain_len, &pstr->cur_state); if (BE (mbclen + 2 > 2, 1)) { wchar_t wcu = wc; if (iswlower (wc)) { size_t mbcdlen; wcu = towupper (wc); mbcdlen = wcrtomb ((char *) buf, wcu, &prev_st); if (BE (mbclen == mbcdlen, 1)) memcpy (pstr->mbs + byte_idx, buf, mbclen); else if (mbcdlen != (size_t) -1) { size_t i; if (byte_idx + mbcdlen > pstr->bufs_len) { pstr->cur_state = prev_st; break; } if (pstr->offsets == NULL) { pstr->offsets = re_malloc (int, pstr->bufs_len); if (pstr->offsets == NULL) return REG_ESPACE; } if (!pstr->offsets_needed) { for (i = 0; i < (size_t) byte_idx; ++i) pstr->offsets[i] = i; pstr->offsets_needed = 1; } memcpy (pstr->mbs + byte_idx, buf, mbcdlen); pstr->wcs[byte_idx] = wcu; pstr->offsets[byte_idx] = src_idx; for (i = 1; i < mbcdlen; ++i) { pstr->offsets[byte_idx + i] = src_idx + (i < mbclen ? i : mbclen - 1); pstr->wcs[byte_idx + i] = WEOF; } pstr->len += mbcdlen - mbclen; if (pstr->raw_stop > src_idx) pstr->stop += mbcdlen - mbclen; end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; byte_idx += mbcdlen; src_idx += mbclen; continue; } else memcpy (pstr->mbs + byte_idx, p, mbclen); } else memcpy (pstr->mbs + byte_idx, p, mbclen); if (BE (pstr->offsets_needed != 0, 0)) { size_t i; for (i = 0; i < mbclen; ++i) pstr->offsets[byte_idx + i] = src_idx + i; } src_idx += mbclen; pstr->wcs[byte_idx++] = wcu; /* Write paddings. */ for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) pstr->wcs[byte_idx++] = WEOF; } else if (mbclen == (size_t) -1 || mbclen == 0) { /* It is an invalid character or '\0'. Just use the byte. */ int ch = pstr->raw_mbs[pstr->raw_mbs_idx + src_idx]; if (BE (pstr->trans != NULL, 0)) ch = pstr->trans [ch]; pstr->mbs[byte_idx] = ch; if (BE (pstr->offsets_needed != 0, 0)) pstr->offsets[byte_idx] = src_idx; ++src_idx; /* And also cast it to wide char. */ pstr->wcs[byte_idx++] = (wchar_t) ch; if (BE (mbclen == (size_t) -1, 0)) pstr->cur_state = prev_st; } else { /* The buffer doesn't have enough space, finish to build. */ pstr->cur_state = prev_st; break; } } pstr->valid_len = byte_idx; pstr->valid_raw_len = src_idx; return REG_NOERROR; } /* Skip characters until the index becomes greater than NEW_RAW_IDX. Return the index. */ static int internal_function re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc) { mbstate_t prev_st; int rawbuf_idx; size_t mbclen; wchar_t wc = 0; /* Skip the characters which are not necessary to check. */ for (rawbuf_idx = pstr->raw_mbs_idx + pstr->valid_raw_len; rawbuf_idx < new_raw_idx;) { int remain_len; remain_len = pstr->len - rawbuf_idx; prev_st = pstr->cur_state; mbclen = mbrtowc (&wc, (const char *) pstr->raw_mbs + rawbuf_idx, remain_len, &pstr->cur_state); if (BE (mbclen == (size_t) -2 || mbclen == (size_t) -1 || mbclen == 0, 0)) { /* We treat these cases as a singlebyte character. */ mbclen = 1; pstr->cur_state = prev_st; } /* Then proceed the next character. */ rawbuf_idx += mbclen; } *last_wc = (wint_t) wc; return rawbuf_idx; } #endif /* RE_ENABLE_I18N */ /* Build the buffer PSTR->MBS, and apply the translation if we need. This function is used in case of REG_ICASE. */ static void internal_function build_upper_buffer (re_string_t *pstr) { int char_idx, end_idx; end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; for (char_idx = pstr->valid_len; char_idx < end_idx; ++char_idx) { int ch = pstr->raw_mbs[pstr->raw_mbs_idx + char_idx]; if (BE (pstr->trans != NULL, 0)) ch = pstr->trans[ch]; if (islower (ch)) pstr->mbs[char_idx] = toupper (ch); else pstr->mbs[char_idx] = ch; } pstr->valid_len = char_idx; pstr->valid_raw_len = char_idx; } /* Apply TRANS to the buffer in PSTR. */ static void internal_function re_string_translate_buffer (re_string_t *pstr) { int buf_idx, end_idx; end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; for (buf_idx = pstr->valid_len; buf_idx < end_idx; ++buf_idx) { int ch = pstr->raw_mbs[pstr->raw_mbs_idx + buf_idx]; pstr->mbs[buf_idx] = pstr->trans[ch]; } pstr->valid_len = buf_idx; pstr->valid_raw_len = buf_idx; } /* This function re-construct the buffers. Concretely, convert to wide character in case of pstr->mb_cur_max > 1, convert to upper case in case of REG_ICASE, apply translation. */ static reg_errcode_t internal_function re_string_reconstruct (re_string_t *pstr, int idx, int eflags) { int offset = idx - pstr->raw_mbs_idx; if (BE (offset < 0, 0)) { /* Reset buffer. */ #ifdef RE_ENABLE_I18N if (pstr->mb_cur_max > 1) memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); #endif pstr->len = pstr->raw_len; pstr->stop = pstr->raw_stop; pstr->valid_len = 0; pstr->raw_mbs_idx = 0; pstr->valid_raw_len = 0; pstr->offsets_needed = 0; pstr->tip_context = ((eflags & REG_NOTBOL) ? CONTEXT_BEGBUF : CONTEXT_NEWLINE | CONTEXT_BEGBUF); if (!pstr->mbs_allocated) pstr->mbs = (unsigned char *) pstr->raw_mbs; offset = idx; } if (BE (offset != 0, 1)) { /* Are the characters which are already checked remain? */ if (BE (offset < pstr->valid_raw_len, 1) #ifdef RE_ENABLE_I18N /* Handling this would enlarge the code too much. Accept a slowdown in that case. */ && pstr->offsets_needed == 0 #endif ) { /* Yes, move them to the front of the buffer. */ pstr->tip_context = re_string_context_at (pstr, offset - 1, eflags); #ifdef RE_ENABLE_I18N if (pstr->mb_cur_max > 1) memmove (pstr->wcs, pstr->wcs + offset, (pstr->valid_len - offset) * sizeof (wint_t)); #endif if (BE (pstr->mbs_allocated, 0)) memmove (pstr->mbs, pstr->mbs + offset, pstr->valid_len - offset); pstr->valid_len -= offset; pstr->valid_raw_len -= offset; #ifdef DEBUG assert (pstr->valid_len > 0); #endif } else { /* No, skip all characters until IDX. */ #ifdef RE_ENABLE_I18N if (BE (pstr->offsets_needed, 0)) { pstr->len = pstr->raw_len - idx + offset; pstr->stop = pstr->raw_stop - idx + offset; pstr->offsets_needed = 0; } #endif pstr->valid_len = 0; pstr->valid_raw_len = 0; #ifdef RE_ENABLE_I18N if (pstr->mb_cur_max > 1) { int wcs_idx; wint_t wc = WEOF; if (pstr->is_utf8) { const unsigned char *raw, *p, *end; /* Special case UTF-8. Multi-byte chars start with any byte other than 0x80 - 0xbf. */ raw = pstr->raw_mbs + pstr->raw_mbs_idx; end = raw + (offset - pstr->mb_cur_max); p = raw + offset - 1; #if 0 /* We know the wchar_t encoding is UCS4, so for the simple case, ASCII characters, skip the conversion step. */ if (isascii (*p) && BE (pstr->trans == NULL, 1)) { memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); pstr->valid_len = 0; wc = (wchar_t) *p; } else #endif for (; p >= end; --p) if ((*p & 0xc0) != 0x80) { mbstate_t cur_state; wchar_t wc2; int mlen = raw + pstr->len - p; size_t mbclen; /* XXX Don't use mbrtowc, we know which conversion to use (UTF-8 -> UCS4). */ memset (&cur_state, 0, sizeof (cur_state)); mbclen = mbrtowc (&wc2, (const char *) p, mlen, &cur_state); if (raw + offset - p <= mbclen && mbclen < (size_t) -2) { memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); pstr->valid_len = mbclen - (raw + offset - p); wc = wc2; } break; } } if (wc == WEOF) pstr->valid_len = re_string_skip_chars (pstr, idx, &wc) - idx; if (BE (pstr->valid_len, 0)) { for (wcs_idx = 0; wcs_idx < pstr->valid_len; ++wcs_idx) pstr->wcs[wcs_idx] = WEOF; if (pstr->mbs_allocated) memset (pstr->mbs, 255, pstr->valid_len); } pstr->valid_raw_len = pstr->valid_len; pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0) && IS_WIDE_WORD_CHAR (wc)) ? CONTEXT_WORD : ((IS_WIDE_NEWLINE (wc) && pstr->newline_anchor) ? CONTEXT_NEWLINE : 0)); } else #endif /* RE_ENABLE_I18N */ { int c = pstr->raw_mbs[pstr->raw_mbs_idx + offset - 1]; if (pstr->trans) c = pstr->trans[c]; pstr->tip_context = (bitset_contain (pstr->word_char, c) ? CONTEXT_WORD : ((IS_NEWLINE (c) && pstr->newline_anchor) ? CONTEXT_NEWLINE : 0)); } } if (!BE (pstr->mbs_allocated, 0)) pstr->mbs += offset; } pstr->raw_mbs_idx = idx; pstr->len -= offset; pstr->stop -= offset; /* Then build the buffers. */ #ifdef RE_ENABLE_I18N if (pstr->mb_cur_max > 1) { if (pstr->icase) { reg_errcode_t ret = build_wcs_upper_buffer (pstr); if (BE (ret != REG_NOERROR, 0)) return ret; } else build_wcs_buffer (pstr); } else #endif if (BE (pstr->mbs_allocated, 0)) { if (pstr->icase) build_upper_buffer (pstr); else if (pstr->trans != NULL) re_string_translate_buffer (pstr); } else pstr->valid_len = pstr->len; pstr->cur_idx = 0; return REG_NOERROR; } static unsigned char internal_function __attribute ((pure)) re_string_peek_byte_case (const re_string_t *pstr, int idx) { int ch, off; /* Handle the common (easiest) cases first. */ if (BE (!pstr->mbs_allocated, 1)) return re_string_peek_byte (pstr, idx); #ifdef RE_ENABLE_I18N if (pstr->mb_cur_max > 1 && ! re_string_is_single_byte_char (pstr, pstr->cur_idx + idx)) return re_string_peek_byte (pstr, idx); #endif off = pstr->cur_idx + idx; #ifdef RE_ENABLE_I18N if (pstr->offsets_needed) off = pstr->offsets[off]; #endif ch = pstr->raw_mbs[pstr->raw_mbs_idx + off]; #ifdef RE_ENABLE_I18N /* Ensure that e.g. for tr_TR.UTF-8 BACKSLASH DOTLESS SMALL LETTER I this function returns CAPITAL LETTER I instead of first byte of DOTLESS SMALL LETTER I. The latter would confuse the parser, since peek_byte_case doesn't advance cur_idx in any way. */ if (pstr->offsets_needed && !isascii (ch)) return re_string_peek_byte (pstr, idx); #endif return ch; } static unsigned char internal_function __attribute ((pure)) re_string_fetch_byte_case (re_string_t *pstr) { if (BE (!pstr->mbs_allocated, 1)) return re_string_fetch_byte (pstr); #ifdef RE_ENABLE_I18N if (pstr->offsets_needed) { int off, ch; /* For tr_TR.UTF-8 [[:islower:]] there is [[: CAPITAL LETTER I WITH DOT lower:]] in mbs. Skip in that case the whole multi-byte character and return the original letter. On the other side, with [[: DOTLESS SMALL LETTER I return [[:I, as doing anything else would complicate things too much. */ if (!re_string_first_byte (pstr, pstr->cur_idx)) return re_string_fetch_byte (pstr); off = pstr->offsets[pstr->cur_idx]; ch = pstr->raw_mbs[pstr->raw_mbs_idx + off]; if (! isascii (ch)) return re_string_fetch_byte (pstr); re_string_skip_bytes (pstr, re_string_char_size_at (pstr, pstr->cur_idx)); return ch; } #endif return pstr->raw_mbs[pstr->raw_mbs_idx + pstr->cur_idx++]; } static void internal_function re_string_destruct (re_string_t *pstr) { #ifdef RE_ENABLE_I18N re_free (pstr->wcs); re_free (pstr->offsets); #endif /* RE_ENABLE_I18N */ if (pstr->mbs_allocated) re_free (pstr->mbs); } /* Return the context at IDX in INPUT. */ static unsigned int internal_function re_string_context_at (const re_string_t *input, int idx, int eflags) { int c; if (BE (idx < 0, 0)) /* In this case, we use the value stored in input->tip_context, since we can't know the character in input->mbs[-1] here. */ return input->tip_context; if (BE (idx == input->len, 0)) return ((eflags & REG_NOTEOL) ? CONTEXT_ENDBUF : CONTEXT_NEWLINE | CONTEXT_ENDBUF); #ifdef RE_ENABLE_I18N if (input->mb_cur_max > 1) { wint_t wc; int wc_idx = idx; while(input->wcs[wc_idx] == WEOF) { #ifdef DEBUG /* It must not happen. */ assert (wc_idx >= 0); #endif --wc_idx; if (wc_idx < 0) return input->tip_context; } wc = input->wcs[wc_idx]; if (BE (input->word_ops_used != 0, 0) && IS_WIDE_WORD_CHAR (wc)) return CONTEXT_WORD; return (IS_WIDE_NEWLINE (wc) && input->newline_anchor ? CONTEXT_NEWLINE : 0); } #endif c = re_string_byte_at (input, idx); if (bitset_contain (input->word_char, c)) return CONTEXT_WORD; return IS_NEWLINE (c) && input->newline_anchor ? CONTEXT_NEWLINE : 0; } /* Functions for set operation. */ static reg_errcode_t internal_function re_node_set_alloc (re_node_set *set, int size) { set->alloc = size; set->nelem = 0; set->elems = re_malloc (int, size); /* can be NULL if size == 0 (see re_node_set_init_empty(set)) */ if (BE (set->elems == NULL && size != 0, 0)) return REG_ESPACE; return REG_NOERROR; } static reg_errcode_t internal_function re_node_set_init_1 (re_node_set *set, int elem) { set->alloc = 1; set->nelem = 1; set->elems = re_malloc (int, 1); if (BE (set->elems == NULL, 0)) { set->alloc = set->nelem = 0; return REG_ESPACE; } set->elems[0] = elem; return REG_NOERROR; } static reg_errcode_t internal_function re_node_set_init_2 (re_node_set *set, int elem1, int elem2) { set->alloc = 2; set->elems = re_malloc (int, 2); if (BE (set->elems == NULL, 0)) return REG_ESPACE; if (elem1 == elem2) { set->nelem = 1; set->elems[0] = elem1; } else { set->nelem = 2; if (elem1 < elem2) { set->elems[0] = elem1; set->elems[1] = elem2; } else { set->elems[0] = elem2; set->elems[1] = elem1; } } return REG_NOERROR; } static reg_errcode_t internal_function re_node_set_init_copy (re_node_set *dest, const re_node_set *src) { dest->nelem = src->nelem; if (src->nelem > 0) { dest->alloc = dest->nelem; dest->elems = re_malloc (int, dest->alloc); if (BE (dest->elems == NULL, 0)) { dest->alloc = dest->nelem = 0; return REG_ESPACE; } memcpy (dest->elems, src->elems, src->nelem * sizeof (int)); } else re_node_set_init_empty (dest); return REG_NOERROR; } /* Calculate the intersection of the sets SRC1 and SRC2. And merge it to DEST. Return value indicate the error code or REG_NOERROR if succeeded. Note: We assume dest->elems is NULL, when dest->alloc is 0. */ static reg_errcode_t internal_function re_node_set_add_intersect (re_node_set *dest, const re_node_set *src1, const re_node_set *src2) { int i1, i2, is, id, delta, sbase; if (src1->nelem == 0 || src2->nelem == 0) return REG_NOERROR; /* We need dest->nelem + 2 * elems_in_intersection; this is a conservative estimate. */ if (src1->nelem + src2->nelem + dest->nelem > dest->alloc) { int new_alloc = src1->nelem + src2->nelem + dest->alloc; int *new_elems = re_realloc (dest->elems, int, new_alloc); if (BE (new_elems == NULL, 0)) return REG_ESPACE; dest->elems = new_elems; dest->alloc = new_alloc; } /* Find the items in the intersection of SRC1 and SRC2, and copy into the top of DEST those that are not already in DEST itself. */ sbase = dest->nelem + src1->nelem + src2->nelem; i1 = src1->nelem - 1; i2 = src2->nelem - 1; id = dest->nelem - 1; for (;;) { if (src1->elems[i1] == src2->elems[i2]) { /* Try to find the item in DEST. Maybe we could binary search? */ while (id >= 0 && dest->elems[id] > src1->elems[i1]) --id; if (id < 0 || dest->elems[id] != src1->elems[i1]) dest->elems[--sbase] = src1->elems[i1]; if (--i1 < 0 || --i2 < 0) break; } /* Lower the highest of the two items. */ else if (src1->elems[i1] < src2->elems[i2]) { if (--i2 < 0) break; } else { if (--i1 < 0) break; } } id = dest->nelem - 1; is = dest->nelem + src1->nelem + src2->nelem - 1; delta = is - sbase + 1; /* Now copy. When DELTA becomes zero, the remaining DEST elements are already in place; this is more or less the same loop that is in re_node_set_merge. */ dest->nelem += delta; if (delta > 0 && id >= 0) for (;;) { if (dest->elems[is] > dest->elems[id]) { /* Copy from the top. */ dest->elems[id + delta--] = dest->elems[is--]; if (delta == 0) break; } else { /* Slide from the bottom. */ dest->elems[id + delta] = dest->elems[id]; if (--id < 0) break; } } /* Copy remaining SRC elements. */ memcpy (dest->elems, dest->elems + sbase, delta * sizeof (int)); return REG_NOERROR; } /* Calculate the union set of the sets SRC1 and SRC2. And store it to DEST. Return value indicate the error code or REG_NOERROR if succeeded. */ static reg_errcode_t internal_function re_node_set_init_union (re_node_set *dest, const re_node_set *src1, const re_node_set *src2) { int i1, i2, id; if (src1 != NULL && src1->nelem > 0 && src2 != NULL && src2->nelem > 0) { dest->alloc = src1->nelem + src2->nelem; dest->elems = re_malloc (int, dest->alloc); if (BE (dest->elems == NULL, 0)) return REG_ESPACE; } else { if (src1 != NULL && src1->nelem > 0) return re_node_set_init_copy (dest, src1); if (src2 != NULL && src2->nelem > 0) return re_node_set_init_copy (dest, src2); re_node_set_init_empty (dest); return REG_NOERROR; } for (i1 = i2 = id = 0 ; i1 < src1->nelem && i2 < src2->nelem ;) { if (src1->elems[i1] > src2->elems[i2]) { dest->elems[id++] = src2->elems[i2++]; continue; } if (src1->elems[i1] == src2->elems[i2]) ++i2; dest->elems[id++] = src1->elems[i1++]; } if (i1 < src1->nelem) { memcpy (dest->elems + id, src1->elems + i1, (src1->nelem - i1) * sizeof (int)); id += src1->nelem - i1; } else if (i2 < src2->nelem) { memcpy (dest->elems + id, src2->elems + i2, (src2->nelem - i2) * sizeof (int)); id += src2->nelem - i2; } dest->nelem = id; return REG_NOERROR; } /* Calculate the union set of the sets DEST and SRC. And store it to DEST. Return value indicate the error code or REG_NOERROR if succeeded. */ static reg_errcode_t internal_function re_node_set_merge (re_node_set *dest, const re_node_set *src) { int is, id, sbase, delta; if (src == NULL || src->nelem == 0) return REG_NOERROR; if (dest->alloc < 2 * src->nelem + dest->nelem) { int new_alloc = 2 * (src->nelem + dest->alloc); int *new_buffer = re_realloc (dest->elems, int, new_alloc); if (BE (new_buffer == NULL, 0)) return REG_ESPACE; dest->elems = new_buffer; dest->alloc = new_alloc; } if (BE (dest->nelem == 0, 0)) { dest->nelem = src->nelem; memcpy (dest->elems, src->elems, src->nelem * sizeof (int)); return REG_NOERROR; } /* Copy into the top of DEST the items of SRC that are not found in DEST. Maybe we could binary search in DEST? */ for (sbase = dest->nelem + 2 * src->nelem, is = src->nelem - 1, id = dest->nelem - 1; is >= 0 && id >= 0; ) { if (dest->elems[id] == src->elems[is]) is--, id--; else if (dest->elems[id] < src->elems[is]) dest->elems[--sbase] = src->elems[is--]; else /* if (dest->elems[id] > src->elems[is]) */ --id; } if (is >= 0) { /* If DEST is exhausted, the remaining items of SRC must be unique. */ sbase -= is + 1; memcpy (dest->elems + sbase, src->elems, (is + 1) * sizeof (int)); } id = dest->nelem - 1; is = dest->nelem + 2 * src->nelem - 1; delta = is - sbase + 1; if (delta == 0) return REG_NOERROR; /* Now copy. When DELTA becomes zero, the remaining DEST elements are already in place. */ dest->nelem += delta; for (;;) { if (dest->elems[is] > dest->elems[id]) { /* Copy from the top. */ dest->elems[id + delta--] = dest->elems[is--]; if (delta == 0) break; } else { /* Slide from the bottom. */ dest->elems[id + delta] = dest->elems[id]; if (--id < 0) { /* Copy remaining SRC elements. */ memcpy (dest->elems, dest->elems + sbase, delta * sizeof (int)); break; } } } return REG_NOERROR; } /* Insert the new element ELEM to the re_node_set* SET. SET should not already have ELEM. return -1 if an error is occured, return 1 otherwise. */ static int internal_function re_node_set_insert (re_node_set *set, int elem) { int idx; /* In case the set is empty. */ if (set->alloc == 0) { if (BE (re_node_set_init_1 (set, elem) == REG_NOERROR, 1)) return 1; return -1; } if (BE (set->nelem, 0) == 0) { /* We already guaranteed above that set->alloc != 0. */ set->elems[0] = elem; ++set->nelem; return 1; } /* Realloc if we need. */ if (set->alloc == set->nelem) { int *new_elems; set->alloc = set->alloc * 2; new_elems = re_realloc (set->elems, int, set->alloc); if (BE (new_elems == NULL, 0)) return -1; set->elems = new_elems; } /* Move the elements which follows the new element. Test the first element separately to skip a check in the inner loop. */ if (elem < set->elems[0]) { idx = 0; for (idx = set->nelem; idx > 0; idx--) set->elems[idx] = set->elems[idx - 1]; } else { for (idx = set->nelem; set->elems[idx - 1] > elem; idx--) set->elems[idx] = set->elems[idx - 1]; } /* Insert the new element. */ set->elems[idx] = elem; ++set->nelem; return 1; } /* Insert the new element ELEM to the re_node_set* SET. SET should not already have any element greater than or equal to ELEM. Return -1 if an error is occured, return 1 otherwise. */ static int internal_function re_node_set_insert_last (re_node_set *set, int elem) { /* Realloc if we need. */ if (set->alloc == set->nelem) { int *new_elems; set->alloc = (set->alloc + 1) * 2; new_elems = re_realloc (set->elems, int, set->alloc); if (BE (new_elems == NULL, 0)) return -1; set->elems = new_elems; } /* Insert the new element. */ set->elems[set->nelem++] = elem; return 1; } /* Compare two node sets SET1 and SET2. return 1 if SET1 and SET2 are equivalent, return 0 otherwise. */ static int internal_function __attribute ((pure)) re_node_set_compare (const re_node_set *set1, const re_node_set *set2) { int i; if (set1 == NULL || set2 == NULL || set1->nelem != set2->nelem) return 0; for (i = set1->nelem ; --i >= 0 ; ) if (set1->elems[i] != set2->elems[i]) return 0; return 1; } /* Return (idx + 1) if SET contains the element ELEM, return 0 otherwise. */ static int internal_function __attribute ((pure)) re_node_set_contains (const re_node_set *set, int elem) { unsigned int idx, right, mid; if (set->nelem <= 0) return 0; /* Binary search the element. */ idx = 0; right = set->nelem - 1; while (idx < right) { mid = (idx + right) / 2; if (set->elems[mid] < elem) idx = mid + 1; else right = mid; } return set->elems[idx] == elem ? idx + 1 : 0; } static void internal_function re_node_set_remove_at (re_node_set *set, int idx) { if (idx < 0 || idx >= set->nelem) return; --set->nelem; for (; idx < set->nelem; idx++) set->elems[idx] = set->elems[idx + 1]; } /* Add the token TOKEN to dfa->nodes, and return the index of the token. Or return -1, if an error will be occured. */ static int internal_function re_dfa_add_node (re_dfa_t *dfa, re_token_t token) { #ifdef RE_ENABLE_I18N int type = token.type; #endif if (BE (dfa->nodes_len >= dfa->nodes_alloc, 0)) { size_t new_nodes_alloc = dfa->nodes_alloc * 2; int *new_nexts, *new_indices; re_node_set *new_edests, *new_eclosures; re_token_t *new_nodes; /* Avoid overflows. */ if (BE (new_nodes_alloc < dfa->nodes_alloc, 0)) return -1; new_nodes = re_realloc (dfa->nodes, re_token_t, new_nodes_alloc); if (BE (new_nodes == NULL, 0)) return -1; dfa->nodes = new_nodes; new_nexts = re_realloc (dfa->nexts, int, new_nodes_alloc); new_indices = re_realloc (dfa->org_indices, int, new_nodes_alloc); new_edests = re_realloc (dfa->edests, re_node_set, new_nodes_alloc); new_eclosures = re_realloc (dfa->eclosures, re_node_set, new_nodes_alloc); if (BE (new_nexts == NULL || new_indices == NULL || new_edests == NULL || new_eclosures == NULL, 0)) return -1; dfa->nexts = new_nexts; dfa->org_indices = new_indices; dfa->edests = new_edests; dfa->eclosures = new_eclosures; dfa->nodes_alloc = new_nodes_alloc; } dfa->nodes[dfa->nodes_len] = token; dfa->nodes[dfa->nodes_len].constraint = 0; #ifdef RE_ENABLE_I18N dfa->nodes[dfa->nodes_len].accept_mb = (type == OP_PERIOD && dfa->mb_cur_max > 1) || type == COMPLEX_BRACKET; #endif dfa->nexts[dfa->nodes_len] = -1; re_node_set_init_empty (dfa->edests + dfa->nodes_len); re_node_set_init_empty (dfa->eclosures + dfa->nodes_len); return dfa->nodes_len++; } static __inline__ unsigned int internal_function calc_state_hash (const re_node_set *nodes, unsigned int context) { unsigned int hash = nodes->nelem + context; int i; for (i = 0 ; i < nodes->nelem ; i++) hash += nodes->elems[i]; return hash; } /* Search for the state whose node_set is equivalent to NODES. Return the pointer to the state, if we found it in the DFA. Otherwise create the new one and return it. In case of an error return NULL and set the error code in ERR. Note: - We assume NULL as the invalid state, then it is possible that return value is NULL and ERR is REG_NOERROR. - We never return non-NULL value in case of any errors, it is for optimization. */ static re_dfastate_t * internal_function re_acquire_state (reg_errcode_t *err, const re_dfa_t *dfa, const re_node_set *nodes) { unsigned int hash; re_dfastate_t *new_state; struct re_state_table_entry *spot; int i; if (BE (nodes->nelem == 0, 0)) { *err = REG_NOERROR; return NULL; } hash = calc_state_hash (nodes, 0); spot = dfa->state_table + (hash & dfa->state_hash_mask); for (i = 0 ; i < spot->num ; i++) { re_dfastate_t *state = spot->array[i]; if (hash != state->hash) continue; if (re_node_set_compare (&state->nodes, nodes)) return state; } /* There are no appropriate state in the dfa, create the new one. */ new_state = create_ci_newstate (dfa, nodes, hash); if (BE (new_state == NULL, 0)) *err = REG_ESPACE; return new_state; } /* Search for the state whose node_set is equivalent to NODES and whose context is equivalent to CONTEXT. Return the pointer to the state, if we found it in the DFA. Otherwise create the new one and return it. In case of an error return NULL and set the error code in ERR. Note: - We assume NULL as the invalid state, then it is possible that return value is NULL and ERR is REG_NOERROR. - We never return non-NULL value in case of any errors, it is for optimization. */ static re_dfastate_t * internal_function re_acquire_state_context (reg_errcode_t *err, const re_dfa_t *dfa, const re_node_set *nodes, unsigned int context) { unsigned int hash; re_dfastate_t *new_state; struct re_state_table_entry *spot; int i; if (nodes->nelem == 0) { *err = REG_NOERROR; return NULL; } hash = calc_state_hash (nodes, context); spot = dfa->state_table + (hash & dfa->state_hash_mask); for (i = 0 ; i < spot->num ; i++) { re_dfastate_t *state = spot->array[i]; if (state->hash == hash && state->context == context && re_node_set_compare (state->entrance_nodes, nodes)) return state; } /* There are no appropriate state in `dfa', create the new one. */ new_state = create_cd_newstate (dfa, nodes, context, hash); if (BE (new_state == NULL, 0)) *err = REG_ESPACE; return new_state; } /* Finish initialization of the new state NEWSTATE, and using its hash value HASH put in the appropriate bucket of DFA's state table. Return value indicates the error code if failed. */ static reg_errcode_t register_state (const re_dfa_t *dfa, re_dfastate_t *newstate, unsigned int hash) { struct re_state_table_entry *spot; reg_errcode_t err; int i; newstate->hash = hash; err = re_node_set_alloc (&newstate->non_eps_nodes, newstate->nodes.nelem); if (BE (err != REG_NOERROR, 0)) return REG_ESPACE; for (i = 0; i < newstate->nodes.nelem; i++) { int elem = newstate->nodes.elems[i]; if (!IS_EPSILON_NODE (dfa->nodes[elem].type)) re_node_set_insert_last (&newstate->non_eps_nodes, elem); } spot = dfa->state_table + (hash & dfa->state_hash_mask); if (BE (spot->alloc <= spot->num, 0)) { int new_alloc = 2 * spot->num + 2; re_dfastate_t **new_array = re_realloc (spot->array, re_dfastate_t *, new_alloc); if (BE (new_array == NULL, 0)) return REG_ESPACE; spot->array = new_array; spot->alloc = new_alloc; } spot->array[spot->num++] = newstate; return REG_NOERROR; } static void free_state (re_dfastate_t *state) { re_node_set_free (&state->non_eps_nodes); re_node_set_free (&state->inveclosure); if (state->entrance_nodes != &state->nodes) { re_node_set_free (state->entrance_nodes); re_free (state->entrance_nodes); } re_node_set_free (&state->nodes); re_free (state->word_trtable); re_free (state->trtable); re_free (state); } /* Create the new state which is independ of contexts. Return the new state if succeeded, otherwise return NULL. */ static re_dfastate_t * internal_function create_ci_newstate (const re_dfa_t *dfa, const re_node_set *nodes, unsigned int hash) { int i; reg_errcode_t err; re_dfastate_t *newstate; newstate = calloc (sizeof (re_dfastate_t), 1); if (BE (newstate == NULL, 0)) return NULL; err = re_node_set_init_copy (&newstate->nodes, nodes); if (BE (err != REG_NOERROR, 0)) { re_free (newstate); return NULL; } newstate->entrance_nodes = &newstate->nodes; for (i = 0 ; i < nodes->nelem ; i++) { re_token_t *node = dfa->nodes + nodes->elems[i]; re_token_type_t type = node->type; if (type == CHARACTER && !node->constraint) continue; #ifdef RE_ENABLE_I18N newstate->accept_mb |= node->accept_mb; #endif /* If the state has the halt node, the state is a halt state. */ if (type == END_OF_RE) newstate->halt = 1; else if (type == OP_BACK_REF) newstate->has_backref = 1; else if (type == ANCHOR || node->constraint) newstate->has_constraint = 1; } err = register_state (dfa, newstate, hash); if (BE (err != REG_NOERROR, 0)) { free_state (newstate); newstate = NULL; } return newstate; } /* Create the new state which is depend on the context CONTEXT. Return the new state if succeeded, otherwise return NULL. */ static re_dfastate_t * internal_function create_cd_newstate (const re_dfa_t *dfa, const re_node_set *nodes, unsigned int context, unsigned int hash) { int i, nctx_nodes = 0; reg_errcode_t err; re_dfastate_t *newstate; newstate = calloc (sizeof (re_dfastate_t), 1); if (BE (newstate == NULL, 0)) return NULL; err = re_node_set_init_copy (&newstate->nodes, nodes); if (BE (err != REG_NOERROR, 0)) { re_free (newstate); return NULL; } newstate->context = context; newstate->entrance_nodes = &newstate->nodes; for (i = 0 ; i < nodes->nelem ; i++) { unsigned int constraint = 0; re_token_t *node = dfa->nodes + nodes->elems[i]; re_token_type_t type = node->type; if (node->constraint) constraint = node->constraint; if (type == CHARACTER && !constraint) continue; #ifdef RE_ENABLE_I18N newstate->accept_mb |= node->accept_mb; #endif /* RE_ENABLE_I18N */ /* If the state has the halt node, the state is a halt state. */ if (type == END_OF_RE) newstate->halt = 1; else if (type == OP_BACK_REF) newstate->has_backref = 1; else if (type == ANCHOR) constraint = node->opr.ctx_type; if (constraint) { if (newstate->entrance_nodes == &newstate->nodes) { newstate->entrance_nodes = re_malloc (re_node_set, 1); if (BE (newstate->entrance_nodes == NULL, 0)) { free_state (newstate); return NULL; } re_node_set_init_copy (newstate->entrance_nodes, nodes); nctx_nodes = 0; newstate->has_constraint = 1; } if (NOT_SATISFY_PREV_CONSTRAINT (constraint,context)) { re_node_set_remove_at (&newstate->nodes, i - nctx_nodes); ++nctx_nodes; } } } err = register_state (dfa, newstate, hash); if (BE (err != REG_NOERROR, 0)) { free_state (newstate); newstate = NULL; } return newstate; } |