/usr/lib/python3.5/test/test_re.py is in libpython3.5-testsuite 3.5.1-10.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | from test.support import verbose, run_unittest, gc_collect, bigmemtest, _2G, \
cpython_only, captured_stdout
import io
import locale
import re
from re import Scanner
import sre_compile
import sre_constants
import sys
import string
import traceback
import unittest
from weakref import proxy
# Misc tests from Tim Peters' re.doc
# WARNING: Don't change details in these tests if you don't know
# what you're doing. Some of these tests were carefully modeled to
# cover most of the code.
class S(str):
def __getitem__(self, index):
return S(super().__getitem__(index))
class B(bytes):
def __getitem__(self, index):
return B(super().__getitem__(index))
class ReTests(unittest.TestCase):
def assertTypedEqual(self, actual, expect, msg=None):
self.assertEqual(actual, expect, msg)
def recurse(actual, expect):
if isinstance(expect, (tuple, list)):
for x, y in zip(actual, expect):
recurse(x, y)
else:
self.assertIs(type(actual), type(expect), msg)
recurse(actual, expect)
def checkPatternError(self, pattern, errmsg, pos=None):
with self.assertRaises(re.error) as cm:
re.compile(pattern)
with self.subTest(pattern=pattern):
err = cm.exception
self.assertEqual(err.msg, errmsg)
if pos is not None:
self.assertEqual(err.pos, pos)
def checkTemplateError(self, pattern, repl, string, errmsg, pos=None):
with self.assertRaises(re.error) as cm:
re.sub(pattern, repl, string)
with self.subTest(pattern=pattern, repl=repl):
err = cm.exception
self.assertEqual(err.msg, errmsg)
if pos is not None:
self.assertEqual(err.pos, pos)
def test_keep_buffer(self):
# See bug 14212
b = bytearray(b'x')
it = re.finditer(b'a', b)
with self.assertRaises(BufferError):
b.extend(b'x'*400)
list(it)
del it
gc_collect()
b.extend(b'x'*400)
def test_weakref(self):
s = 'QabbbcR'
x = re.compile('ab+c')
y = proxy(x)
self.assertEqual(x.findall('QabbbcR'), y.findall('QabbbcR'))
def test_search_star_plus(self):
self.assertEqual(re.search('x*', 'axx').span(0), (0, 0))
self.assertEqual(re.search('x*', 'axx').span(), (0, 0))
self.assertEqual(re.search('x+', 'axx').span(0), (1, 3))
self.assertEqual(re.search('x+', 'axx').span(), (1, 3))
self.assertIsNone(re.search('x', 'aaa'))
self.assertEqual(re.match('a*', 'xxx').span(0), (0, 0))
self.assertEqual(re.match('a*', 'xxx').span(), (0, 0))
self.assertEqual(re.match('x*', 'xxxa').span(0), (0, 3))
self.assertEqual(re.match('x*', 'xxxa').span(), (0, 3))
self.assertIsNone(re.match('a+', 'xxx'))
def bump_num(self, matchobj):
int_value = int(matchobj.group(0))
return str(int_value + 1)
def test_basic_re_sub(self):
self.assertTypedEqual(re.sub('y', 'a', 'xyz'), 'xaz')
self.assertTypedEqual(re.sub('y', S('a'), S('xyz')), 'xaz')
self.assertTypedEqual(re.sub(b'y', b'a', b'xyz'), b'xaz')
self.assertTypedEqual(re.sub(b'y', B(b'a'), B(b'xyz')), b'xaz')
self.assertTypedEqual(re.sub(b'y', bytearray(b'a'), bytearray(b'xyz')), b'xaz')
self.assertTypedEqual(re.sub(b'y', memoryview(b'a'), memoryview(b'xyz')), b'xaz')
for y in ("\xe0", "\u0430", "\U0001d49c"):
self.assertEqual(re.sub(y, 'a', 'x%sz' % y), 'xaz')
self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x')
self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'),
'9.3 -3 24x100y')
self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', count=3),
'9.3 -3 23x99y')
self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n')
self.assertEqual(re.sub('.', r"\n", 'x'), '\n')
s = r"\1\1"
self.assertEqual(re.sub('(.)', s, 'x'), 'xx')
self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s)
self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s)
self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx')
self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx')
self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx')
self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx')
self.assertEqual(re.sub('a', r'\t\n\v\r\f\a\b', 'a'), '\t\n\v\r\f\a\b')
self.assertEqual(re.sub('a', '\t\n\v\r\f\a\b', 'a'), '\t\n\v\r\f\a\b')
self.assertEqual(re.sub('a', '\t\n\v\r\f\a\b', 'a'),
(chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)+chr(8)))
for c in 'cdehijklmopqsuwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ':
with self.subTest(c):
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.sub('a', '\\' + c, 'a'), '\\' + c)
self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest')
def test_bug_449964(self):
# fails for group followed by other escape
self.assertEqual(re.sub(r'(?P<unk>x)', '\g<1>\g<1>\\b', 'xx'),
'xx\bxx\b')
def test_bug_449000(self):
# Test for sub() on escaped characters
self.assertEqual(re.sub(r'\r\n', r'\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
self.assertEqual(re.sub('\r\n', r'\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
self.assertEqual(re.sub(r'\r\n', '\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
self.assertEqual(re.sub('\r\n', '\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
def test_bug_1661(self):
# Verify that flags do not get silently ignored with compiled patterns
pattern = re.compile('.')
self.assertRaises(ValueError, re.match, pattern, 'A', re.I)
self.assertRaises(ValueError, re.search, pattern, 'A', re.I)
self.assertRaises(ValueError, re.findall, pattern, 'A', re.I)
self.assertRaises(ValueError, re.compile, pattern, re.I)
def test_bug_3629(self):
# A regex that triggered a bug in the sre-code validator
re.compile("(?P<quote>)(?(quote))")
def test_sub_template_numeric_escape(self):
# bug 776311 and friends
self.assertEqual(re.sub('x', r'\0', 'x'), '\0')
self.assertEqual(re.sub('x', r'\000', 'x'), '\000')
self.assertEqual(re.sub('x', r'\001', 'x'), '\001')
self.assertEqual(re.sub('x', r'\008', 'x'), '\0' + '8')
self.assertEqual(re.sub('x', r'\009', 'x'), '\0' + '9')
self.assertEqual(re.sub('x', r'\111', 'x'), '\111')
self.assertEqual(re.sub('x', r'\117', 'x'), '\117')
self.assertEqual(re.sub('x', r'\377', 'x'), '\377')
self.assertEqual(re.sub('x', r'\1111', 'x'), '\1111')
self.assertEqual(re.sub('x', r'\1111', 'x'), '\111' + '1')
self.assertEqual(re.sub('x', r'\00', 'x'), '\x00')
self.assertEqual(re.sub('x', r'\07', 'x'), '\x07')
self.assertEqual(re.sub('x', r'\08', 'x'), '\0' + '8')
self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9')
self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a')
self.checkTemplateError('x', r'\400', 'x',
r'octal escape value \400 outside of '
r'range 0-0o377', 0)
self.checkTemplateError('x', r'\777', 'x',
r'octal escape value \777 outside of '
r'range 0-0o377', 0)
self.checkTemplateError('x', r'\1', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\8', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\9', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\11', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\18', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\1a', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\90', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\99', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\118', 'x', 'invalid group reference') # r'\11' + '8'
self.checkTemplateError('x', r'\11a', 'x', 'invalid group reference')
self.checkTemplateError('x', r'\181', 'x', 'invalid group reference') # r'\18' + '1'
self.checkTemplateError('x', r'\800', 'x', 'invalid group reference') # r'\80' + '0'
# in python2.3 (etc), these loop endlessly in sre_parser.py
self.assertEqual(re.sub('(((((((((((x)))))))))))', r'\11', 'x'), 'x')
self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\118', 'xyz'),
'xz8')
self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\11a', 'xyz'),
'xza')
def test_qualified_re_sub(self):
self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb')
self.assertEqual(re.sub('a', 'b', 'aaaaa', count=1), 'baaaa')
def test_bug_114660(self):
self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello there'),
'hello there')
def test_bug_462270(self):
# Test for empty sub() behaviour, see SF bug #462270
self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-')
self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d')
def test_symbolic_groups(self):
re.compile('(?P<a>x)(?P=a)(?(a)y)')
re.compile('(?P<a1>x)(?P=a1)(?(a1)y)')
re.compile('(?P<a1>x)\1(?(1)y)')
self.checkPatternError('(?P<a>)(?P<a>)',
"redefinition of group name 'a' as group 2; "
"was group 1")
self.checkPatternError('(?P<a>(?P=a))',
"cannot refer to an open group", 10)
self.checkPatternError('(?Pxy)', 'unknown extension ?Px')
self.checkPatternError('(?P<a>)(?P=a', 'missing ), unterminated name', 11)
self.checkPatternError('(?P=', 'missing group name', 4)
self.checkPatternError('(?P=)', 'missing group name', 4)
self.checkPatternError('(?P=1)', "bad character in group name '1'", 4)
self.checkPatternError('(?P=a)', "unknown group name 'a'")
self.checkPatternError('(?P=a1)', "unknown group name 'a1'")
self.checkPatternError('(?P=a.)', "bad character in group name 'a.'", 4)
self.checkPatternError('(?P<)', 'missing >, unterminated name', 4)
self.checkPatternError('(?P<a', 'missing >, unterminated name', 4)
self.checkPatternError('(?P<', 'missing group name', 4)
self.checkPatternError('(?P<>)', 'missing group name', 4)
self.checkPatternError(r'(?P<1>)', "bad character in group name '1'", 4)
self.checkPatternError(r'(?P<a.>)', "bad character in group name 'a.'", 4)
self.checkPatternError(r'(?(', 'missing group name', 3)
self.checkPatternError(r'(?())', 'missing group name', 3)
self.checkPatternError(r'(?(a))', "unknown group name 'a'", 3)
self.checkPatternError(r'(?(-1))', "bad character in group name '-1'", 3)
self.checkPatternError(r'(?(1a))', "bad character in group name '1a'", 3)
self.checkPatternError(r'(?(a.))', "bad character in group name 'a.'", 3)
# New valid/invalid identifiers in Python 3
re.compile('(?P<µ>x)(?P=µ)(?(µ)y)')
re.compile('(?P<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>x)(?P=𝔘𝔫𝔦𝔠𝔬𝔡𝔢)(?(𝔘𝔫𝔦𝔠𝔬𝔡𝔢)y)')
self.checkPatternError('(?P<©>x)', "bad character in group name '©'", 4)
# Support > 100 groups.
pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1))
pat = '(?:%s)(?(200)z|t)' % pat
self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5))
def test_symbolic_refs(self):
self.checkTemplateError('(?P<a>x)', '\g<a', 'xx',
'missing >, unterminated name', 3)
self.checkTemplateError('(?P<a>x)', '\g<', 'xx',
'missing group name', 3)
self.checkTemplateError('(?P<a>x)', '\g', 'xx', 'missing <', 2)
self.checkTemplateError('(?P<a>x)', '\g<a a>', 'xx',
"bad character in group name 'a a'", 3)
self.checkTemplateError('(?P<a>x)', '\g<>', 'xx',
'missing group name', 3)
self.checkTemplateError('(?P<a>x)', '\g<1a1>', 'xx',
"bad character in group name '1a1'", 3)
self.checkTemplateError('(?P<a>x)', r'\g<2>', 'xx',
'invalid group reference')
self.checkTemplateError('(?P<a>x)', r'\2', 'xx',
'invalid group reference')
with self.assertRaisesRegex(IndexError, "unknown group name 'ab'"):
re.sub('(?P<a>x)', '\g<ab>', 'xx')
self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\g<b>', 'xx'), '')
self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\2', 'xx'), '')
self.checkTemplateError('(?P<a>x)', '\g<-1>', 'xx',
"bad character in group name '-1'", 3)
# New valid/invalid identifiers in Python 3
self.assertEqual(re.sub('(?P<µ>x)', r'\g<µ>', 'xx'), 'xx')
self.assertEqual(re.sub('(?P<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>x)', r'\g<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>', 'xx'), 'xx')
self.checkTemplateError('(?P<a>x)', '\g<©>', 'xx',
"bad character in group name '©'", 3)
# Support > 100 groups.
pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1))
self.assertEqual(re.sub(pat, '\g<200>', 'xc8yzxc8y'), 'c8zc8')
def test_re_subn(self):
self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2))
self.assertEqual(re.subn("b+", "x", "bbbb BBBB"), ('x BBBB', 1))
self.assertEqual(re.subn("b+", "x", "xyz"), ('xyz', 0))
self.assertEqual(re.subn("b*", "x", "xyz"), ('xxxyxzx', 4))
self.assertEqual(re.subn("b*", "x", "xyz", count=2), ('xxxyz', 2))
def test_re_split(self):
for string in ":a:b::c", S(":a:b::c"):
self.assertTypedEqual(re.split(":", string),
['', 'a', 'b', '', 'c'])
self.assertTypedEqual(re.split(":+", string),
['', 'a', 'b', 'c'])
self.assertTypedEqual(re.split("(:+)", string),
['', ':', 'a', ':', 'b', '::', 'c'])
for string in (b":a:b::c", B(b":a:b::c"), bytearray(b":a:b::c"),
memoryview(b":a:b::c")):
self.assertTypedEqual(re.split(b":", string),
[b'', b'a', b'b', b'', b'c'])
self.assertTypedEqual(re.split(b":+", string),
[b'', b'a', b'b', b'c'])
self.assertTypedEqual(re.split(b"(:+)", string),
[b'', b':', b'a', b':', b'b', b'::', b'c'])
for a, b, c in ("\xe0\xdf\xe7", "\u0430\u0431\u0432",
"\U0001d49c\U0001d49e\U0001d4b5"):
string = ":%s:%s::%s" % (a, b, c)
self.assertEqual(re.split(":", string), ['', a, b, '', c])
self.assertEqual(re.split(":+", string), ['', a, b, c])
self.assertEqual(re.split("(:+)", string),
['', ':', a, ':', b, '::', c])
self.assertEqual(re.split("(?::+)", ":a:b::c"), ['', 'a', 'b', 'c'])
self.assertEqual(re.split("(:)+", ":a:b::c"),
['', ':', 'a', ':', 'b', ':', 'c'])
self.assertEqual(re.split("([b:]+)", ":a:b::c"),
['', ':', 'a', ':b::', 'c'])
self.assertEqual(re.split("(b)|(:+)", ":a:b::c"),
['', None, ':', 'a', None, ':', '', 'b', None, '',
None, '::', 'c'])
self.assertEqual(re.split("(?:b)|(?::+)", ":a:b::c"),
['', 'a', '', '', 'c'])
for sep, expected in [
(':*', ['', 'a', 'b', 'c']),
('(?::*)', ['', 'a', 'b', 'c']),
('(:*)', ['', ':', 'a', ':', 'b', '::', 'c']),
('(:)*', ['', ':', 'a', ':', 'b', ':', 'c']),
]:
with self.subTest(sep=sep), self.assertWarns(FutureWarning):
self.assertTypedEqual(re.split(sep, ':a:b::c'), expected)
for sep, expected in [
('', [':a:b::c']),
(r'\b', [':a:b::c']),
(r'(?=:)', [':a:b::c']),
(r'(?<=:)', [':a:b::c']),
]:
with self.subTest(sep=sep), self.assertRaises(ValueError):
self.assertTypedEqual(re.split(sep, ':a:b::c'), expected)
def test_qualified_re_split(self):
self.assertEqual(re.split(":", ":a:b::c", maxsplit=2), ['', 'a', 'b::c'])
self.assertEqual(re.split(':', 'a:b:c:d', maxsplit=2), ['a', 'b', 'c:d'])
self.assertEqual(re.split("(:)", ":a:b::c", maxsplit=2),
['', ':', 'a', ':', 'b::c'])
self.assertEqual(re.split("(:+)", ":a:b::c", maxsplit=2),
['', ':', 'a', ':', 'b::c'])
with self.assertWarns(FutureWarning):
self.assertEqual(re.split("(:*)", ":a:b::c", maxsplit=2),
['', ':', 'a', ':', 'b::c'])
def test_re_findall(self):
self.assertEqual(re.findall(":+", "abc"), [])
for string in "a:b::c:::d", S("a:b::c:::d"):
self.assertTypedEqual(re.findall(":+", string),
[":", "::", ":::"])
self.assertTypedEqual(re.findall("(:+)", string),
[":", "::", ":::"])
self.assertTypedEqual(re.findall("(:)(:*)", string),
[(":", ""), (":", ":"), (":", "::")])
for string in (b"a:b::c:::d", B(b"a:b::c:::d"), bytearray(b"a:b::c:::d"),
memoryview(b"a:b::c:::d")):
self.assertTypedEqual(re.findall(b":+", string),
[b":", b"::", b":::"])
self.assertTypedEqual(re.findall(b"(:+)", string),
[b":", b"::", b":::"])
self.assertTypedEqual(re.findall(b"(:)(:*)", string),
[(b":", b""), (b":", b":"), (b":", b"::")])
for x in ("\xe0", "\u0430", "\U0001d49c"):
xx = x * 2
xxx = x * 3
string = "a%sb%sc%sd" % (x, xx, xxx)
self.assertEqual(re.findall("%s+" % x, string), [x, xx, xxx])
self.assertEqual(re.findall("(%s+)" % x, string), [x, xx, xxx])
self.assertEqual(re.findall("(%s)(%s*)" % (x, x), string),
[(x, ""), (x, x), (x, xx)])
def test_bug_117612(self):
self.assertEqual(re.findall(r"(a|(b))", "aba"),
[("a", ""),("b", "b"),("a", "")])
def test_re_match(self):
for string in 'a', S('a'):
self.assertEqual(re.match('a', string).groups(), ())
self.assertEqual(re.match('(a)', string).groups(), ('a',))
self.assertEqual(re.match('(a)', string).group(0), 'a')
self.assertEqual(re.match('(a)', string).group(1), 'a')
self.assertEqual(re.match('(a)', string).group(1, 1), ('a', 'a'))
for string in b'a', B(b'a'), bytearray(b'a'), memoryview(b'a'):
self.assertEqual(re.match(b'a', string).groups(), ())
self.assertEqual(re.match(b'(a)', string).groups(), (b'a',))
self.assertEqual(re.match(b'(a)', string).group(0), b'a')
self.assertEqual(re.match(b'(a)', string).group(1), b'a')
self.assertEqual(re.match(b'(a)', string).group(1, 1), (b'a', b'a'))
for a in ("\xe0", "\u0430", "\U0001d49c"):
self.assertEqual(re.match(a, a).groups(), ())
self.assertEqual(re.match('(%s)' % a, a).groups(), (a,))
self.assertEqual(re.match('(%s)' % a, a).group(0), a)
self.assertEqual(re.match('(%s)' % a, a).group(1), a)
self.assertEqual(re.match('(%s)' % a, a).group(1, 1), (a, a))
pat = re.compile('((a)|(b))(c)?')
self.assertEqual(pat.match('a').groups(), ('a', 'a', None, None))
self.assertEqual(pat.match('b').groups(), ('b', None, 'b', None))
self.assertEqual(pat.match('ac').groups(), ('a', 'a', None, 'c'))
self.assertEqual(pat.match('bc').groups(), ('b', None, 'b', 'c'))
self.assertEqual(pat.match('bc').groups(""), ('b', "", 'b', 'c'))
# A single group
m = re.match('(a)', 'a')
self.assertEqual(m.group(0), 'a')
self.assertEqual(m.group(0), 'a')
self.assertEqual(m.group(1), 'a')
self.assertEqual(m.group(1, 1), ('a', 'a'))
pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?')
self.assertEqual(pat.match('a').group(1, 2, 3), ('a', None, None))
self.assertEqual(pat.match('b').group('a1', 'b2', 'c3'),
(None, 'b', None))
self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c'))
def test_re_fullmatch(self):
# Issue 16203: Proposal: add re.fullmatch() method.
self.assertEqual(re.fullmatch(r"a", "a").span(), (0, 1))
for string in "ab", S("ab"):
self.assertEqual(re.fullmatch(r"a|ab", string).span(), (0, 2))
for string in b"ab", B(b"ab"), bytearray(b"ab"), memoryview(b"ab"):
self.assertEqual(re.fullmatch(br"a|ab", string).span(), (0, 2))
for a, b in "\xe0\xdf", "\u0430\u0431", "\U0001d49c\U0001d49e":
r = r"%s|%s" % (a, a + b)
self.assertEqual(re.fullmatch(r, a + b).span(), (0, 2))
self.assertEqual(re.fullmatch(r".*?$", "abc").span(), (0, 3))
self.assertEqual(re.fullmatch(r".*?", "abc").span(), (0, 3))
self.assertEqual(re.fullmatch(r"a.*?b", "ab").span(), (0, 2))
self.assertEqual(re.fullmatch(r"a.*?b", "abb").span(), (0, 3))
self.assertEqual(re.fullmatch(r"a.*?b", "axxb").span(), (0, 4))
self.assertIsNone(re.fullmatch(r"a+", "ab"))
self.assertIsNone(re.fullmatch(r"abc$", "abc\n"))
self.assertIsNone(re.fullmatch(r"abc\Z", "abc\n"))
self.assertIsNone(re.fullmatch(r"(?m)abc$", "abc\n"))
self.assertEqual(re.fullmatch(r"ab(?=c)cd", "abcd").span(), (0, 4))
self.assertEqual(re.fullmatch(r"ab(?<=b)cd", "abcd").span(), (0, 4))
self.assertEqual(re.fullmatch(r"(?=a|ab)ab", "ab").span(), (0, 2))
self.assertEqual(
re.compile(r"bc").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3))
self.assertEqual(
re.compile(r".*?$").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3))
self.assertEqual(
re.compile(r".*?").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3))
def test_re_groupref_exists(self):
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
('(', 'a'))
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(),
(None, 'a'))
self.assertIsNone(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'))
self.assertIsNone(re.match('^(\()?([^()]+)(?(1)\))$', '(a'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(),
('a', 'b'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(),
(None, 'd'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(),
(None, 'd'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(),
('a', ''))
# Tests for bug #1177831: exercise groups other than the first group
p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
self.assertEqual(p.match('abc').groups(),
('a', 'b', 'c'))
self.assertEqual(p.match('ad').groups(),
('a', None, 'd'))
self.assertIsNone(p.match('abd'))
self.assertIsNone(p.match('ac'))
# Support > 100 groups.
pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1))
pat = '(?:%s)(?(200)z)' % pat
self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5))
self.checkPatternError(r'(?P<a>)(?(0))', 'bad group number', 10)
self.checkPatternError(r'()(?(1)a|b',
'missing ), unterminated subpattern', 2)
self.checkPatternError(r'()(?(1)a|b|c)',
'conditional backref with more than '
'two branches', 10)
def test_re_groupref_overflow(self):
self.checkTemplateError('()', '\g<%s>' % sre_constants.MAXGROUPS, 'xx',
'invalid group reference', 3)
self.checkPatternError(r'(?P<a>)(?(%d))' % sre_constants.MAXGROUPS,
'invalid group reference', 10)
def test_re_groupref(self):
self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(),
('|', 'a'))
self.assertEqual(re.match(r'^(\|)?([^()]+)\1?$', 'a').groups(),
(None, 'a'))
self.assertIsNone(re.match(r'^(\|)?([^()]+)\1$', 'a|'))
self.assertIsNone(re.match(r'^(\|)?([^()]+)\1$', '|a'))
self.assertEqual(re.match(r'^(?:(a)|c)(\1)$', 'aa').groups(),
('a', 'a'))
self.assertEqual(re.match(r'^(?:(a)|c)(\1)?$', 'c').groups(),
(None, None))
self.checkPatternError(r'(abc\1)', 'cannot refer to an open group', 4)
def test_groupdict(self):
self.assertEqual(re.match('(?P<first>first) (?P<second>second)',
'first second').groupdict(),
{'first':'first', 'second':'second'})
def test_expand(self):
self.assertEqual(re.match("(?P<first>first) (?P<second>second)",
"first second")
.expand(r"\2 \1 \g<second> \g<first>"),
"second first second first")
self.assertEqual(re.match("(?P<first>first)|(?P<second>second)",
"first")
.expand(r"\2 \g<second>"),
" ")
def test_repeat_minmax(self):
self.assertIsNone(re.match("^(\w){1}$", "abc"))
self.assertIsNone(re.match("^(\w){1}?$", "abc"))
self.assertIsNone(re.match("^(\w){1,2}$", "abc"))
self.assertIsNone(re.match("^(\w){1,2}?$", "abc"))
self.assertEqual(re.match("^(\w){3}$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,3}$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,4}$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){3}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,3}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,4}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
self.assertIsNone(re.match("^x{1}$", "xxx"))
self.assertIsNone(re.match("^x{1}?$", "xxx"))
self.assertIsNone(re.match("^x{1,2}$", "xxx"))
self.assertIsNone(re.match("^x{1,2}?$", "xxx"))
self.assertTrue(re.match("^x{3}$", "xxx"))
self.assertTrue(re.match("^x{1,3}$", "xxx"))
self.assertTrue(re.match("^x{3,3}$", "xxx"))
self.assertTrue(re.match("^x{1,4}$", "xxx"))
self.assertTrue(re.match("^x{3,4}?$", "xxx"))
self.assertTrue(re.match("^x{3}?$", "xxx"))
self.assertTrue(re.match("^x{1,3}?$", "xxx"))
self.assertTrue(re.match("^x{1,4}?$", "xxx"))
self.assertTrue(re.match("^x{3,4}?$", "xxx"))
self.assertIsNone(re.match("^x{}$", "xxx"))
self.assertTrue(re.match("^x{}$", "x{}"))
self.checkPatternError(r'x{2,1}',
'min repeat greater than max repeat', 2)
def test_getattr(self):
self.assertEqual(re.compile("(?i)(a)(b)").pattern, "(?i)(a)(b)")
self.assertEqual(re.compile("(?i)(a)(b)").flags, re.I | re.U)
self.assertEqual(re.compile("(?i)(a)(b)").groups, 2)
self.assertEqual(re.compile("(?i)(a)(b)").groupindex, {})
self.assertEqual(re.compile("(?i)(?P<first>a)(?P<other>b)").groupindex,
{'first': 1, 'other': 2})
self.assertEqual(re.match("(a)", "a").pos, 0)
self.assertEqual(re.match("(a)", "a").endpos, 1)
self.assertEqual(re.match("(a)", "a").string, "a")
self.assertEqual(re.match("(a)", "a").regs, ((0, 1), (0, 1)))
self.assertTrue(re.match("(a)", "a").re)
# Issue 14260. groupindex should be non-modifiable mapping.
p = re.compile(r'(?i)(?P<first>a)(?P<other>b)')
self.assertEqual(sorted(p.groupindex), ['first', 'other'])
self.assertEqual(p.groupindex['other'], 2)
with self.assertRaises(TypeError):
p.groupindex['other'] = 0
self.assertEqual(p.groupindex['other'], 2)
def test_special_escapes(self):
self.assertEqual(re.search(r"\b(b.)\b",
"abcd abc bcd bx").group(1), "bx")
self.assertEqual(re.search(r"\B(b.)\B",
"abc bcd bc abxd").group(1), "bx")
self.assertEqual(re.search(r"\b(b.)\b",
"abcd abc bcd bx", re.ASCII).group(1), "bx")
self.assertEqual(re.search(r"\B(b.)\B",
"abc bcd bc abxd", re.ASCII).group(1), "bx")
self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc")
self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc")
self.assertIsNone(re.search(r"^\Aabc\Z$", "\nabc\n", re.M))
self.assertEqual(re.search(br"\b(b.)\b",
b"abcd abc bcd bx").group(1), b"bx")
self.assertEqual(re.search(br"\B(b.)\B",
b"abc bcd bc abxd").group(1), b"bx")
self.assertEqual(re.search(br"\b(b.)\b",
b"abcd abc bcd bx", re.LOCALE).group(1), b"bx")
self.assertEqual(re.search(br"\B(b.)\B",
b"abc bcd bc abxd", re.LOCALE).group(1), b"bx")
self.assertEqual(re.search(br"^abc$", b"\nabc\n", re.M).group(0), b"abc")
self.assertEqual(re.search(br"^\Aabc\Z$", b"abc", re.M).group(0), b"abc")
self.assertIsNone(re.search(br"^\Aabc\Z$", b"\nabc\n", re.M))
self.assertEqual(re.search(r"\d\D\w\W\s\S",
"1aa! a").group(0), "1aa! a")
self.assertEqual(re.search(br"\d\D\w\W\s\S",
b"1aa! a").group(0), b"1aa! a")
self.assertEqual(re.search(r"\d\D\w\W\s\S",
"1aa! a", re.ASCII).group(0), "1aa! a")
self.assertEqual(re.search(br"\d\D\w\W\s\S",
b"1aa! a", re.LOCALE).group(0), b"1aa! a")
def test_other_escapes(self):
self.checkPatternError("\\", 'bad escape (end of pattern)', 0)
self.assertEqual(re.match(r"\(", '(').group(), '(')
self.assertIsNone(re.match(r"\(", ')'))
self.assertEqual(re.match(r"\\", '\\').group(), '\\')
self.assertEqual(re.match(r"[\]]", ']').group(), ']')
self.assertIsNone(re.match(r"[\]]", '['))
self.assertEqual(re.match(r"[a\-c]", '-').group(), '-')
self.assertIsNone(re.match(r"[a\-c]", 'b'))
self.assertEqual(re.match(r"[\^a]+", 'a^').group(), 'a^')
self.assertIsNone(re.match(r"[\^a]+", 'b'))
re.purge() # for warnings
for c in 'ceghijklmopqyzCEFGHIJKLMNOPQRTVXY':
with self.subTest(c):
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.fullmatch('\\%c' % c, c).group(), c)
self.assertIsNone(re.match('\\%c' % c, 'a'))
for c in 'ceghijklmopqyzABCEFGHIJKLMNOPQRTVXYZ':
with self.subTest(c):
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.fullmatch('[\\%c]' % c, c).group(), c)
self.assertIsNone(re.match('[\\%c]' % c, 'a'))
def test_string_boundaries(self):
# See http://bugs.python.org/issue10713
self.assertEqual(re.search(r"\b(abc)\b", "abc").group(1),
"abc")
# There's a word boundary at the start of a string.
self.assertTrue(re.match(r"\b", "abc"))
# A non-empty string includes a non-boundary zero-length match.
self.assertTrue(re.search(r"\B", "abc"))
# There is no non-boundary match at the start of a string.
self.assertFalse(re.match(r"\B", "abc"))
# However, an empty string contains no word boundaries, and also no
# non-boundaries.
self.assertIsNone(re.search(r"\B", ""))
# This one is questionable and different from the perlre behaviour,
# but describes current behavior.
self.assertIsNone(re.search(r"\b", ""))
# A single word-character string has two boundaries, but no
# non-boundary gaps.
self.assertEqual(len(re.findall(r"\b", "a")), 2)
self.assertEqual(len(re.findall(r"\B", "a")), 0)
# If there are no words, there are no boundaries
self.assertEqual(len(re.findall(r"\b", " ")), 0)
self.assertEqual(len(re.findall(r"\b", " ")), 0)
# Can match around the whitespace.
self.assertEqual(len(re.findall(r"\B", " ")), 2)
def test_bigcharset(self):
self.assertEqual(re.match("([\u2222\u2223])",
"\u2222").group(1), "\u2222")
r = '[%s]' % ''.join(map(chr, range(256, 2**16, 255)))
self.assertEqual(re.match(r, "\uff01").group(), "\uff01")
def test_big_codesize(self):
# Issue #1160
r = re.compile('|'.join(('%d'%x for x in range(10000))))
self.assertTrue(r.match('1000'))
self.assertTrue(r.match('9999'))
def test_anyall(self):
self.assertEqual(re.match("a.b", "a\nb", re.DOTALL).group(0),
"a\nb")
self.assertEqual(re.match("a.*b", "a\n\nb", re.DOTALL).group(0),
"a\n\nb")
def test_lookahead(self):
self.assertEqual(re.match("(a(?=\s[^a]))", "a b").group(1), "a")
self.assertEqual(re.match("(a(?=\s[^a]*))", "a b").group(1), "a")
self.assertEqual(re.match("(a(?=\s[abc]))", "a b").group(1), "a")
self.assertEqual(re.match("(a(?=\s[abc]*))", "a bc").group(1), "a")
self.assertEqual(re.match(r"(a)(?=\s\1)", "a a").group(1), "a")
self.assertEqual(re.match(r"(a)(?=\s\1*)", "a aa").group(1), "a")
self.assertEqual(re.match(r"(a)(?=\s(abc|a))", "a a").group(1), "a")
self.assertEqual(re.match(r"(a(?!\s[^a]))", "a a").group(1), "a")
self.assertEqual(re.match(r"(a(?!\s[abc]))", "a d").group(1), "a")
self.assertEqual(re.match(r"(a)(?!\s\1)", "a b").group(1), "a")
self.assertEqual(re.match(r"(a)(?!\s(abc|a))", "a b").group(1), "a")
# Group reference.
self.assertTrue(re.match(r'(a)b(?=\1)a', 'aba'))
self.assertIsNone(re.match(r'(a)b(?=\1)c', 'abac'))
# Conditional group reference.
self.assertTrue(re.match(r'(?:(a)|(x))b(?=(?(2)x|c))c', 'abc'))
self.assertIsNone(re.match(r'(?:(a)|(x))b(?=(?(2)c|x))c', 'abc'))
self.assertTrue(re.match(r'(?:(a)|(x))b(?=(?(2)x|c))c', 'abc'))
self.assertIsNone(re.match(r'(?:(a)|(x))b(?=(?(1)b|x))c', 'abc'))
self.assertTrue(re.match(r'(?:(a)|(x))b(?=(?(1)c|x))c', 'abc'))
# Group used before defined.
self.assertTrue(re.match(r'(a)b(?=(?(2)x|c))(c)', 'abc'))
self.assertIsNone(re.match(r'(a)b(?=(?(2)b|x))(c)', 'abc'))
self.assertTrue(re.match(r'(a)b(?=(?(1)c|x))(c)', 'abc'))
def test_lookbehind(self):
self.assertTrue(re.match(r'ab(?<=b)c', 'abc'))
self.assertIsNone(re.match(r'ab(?<=c)c', 'abc'))
self.assertIsNone(re.match(r'ab(?<!b)c', 'abc'))
self.assertTrue(re.match(r'ab(?<!c)c', 'abc'))
# Group reference.
self.assertTrue(re.match(r'(a)a(?<=\1)c', 'aac'))
self.assertIsNone(re.match(r'(a)b(?<=\1)a', 'abaa'))
self.assertIsNone(re.match(r'(a)a(?<!\1)c', 'aac'))
self.assertTrue(re.match(r'(a)b(?<!\1)a', 'abaa'))
# Conditional group reference.
self.assertIsNone(re.match(r'(?:(a)|(x))b(?<=(?(2)x|c))c', 'abc'))
self.assertIsNone(re.match(r'(?:(a)|(x))b(?<=(?(2)b|x))c', 'abc'))
self.assertTrue(re.match(r'(?:(a)|(x))b(?<=(?(2)x|b))c', 'abc'))
self.assertIsNone(re.match(r'(?:(a)|(x))b(?<=(?(1)c|x))c', 'abc'))
self.assertTrue(re.match(r'(?:(a)|(x))b(?<=(?(1)b|x))c', 'abc'))
# Group used before defined.
self.assertRaises(re.error, re.compile, r'(a)b(?<=(?(2)b|x))(c)')
self.assertIsNone(re.match(r'(a)b(?<=(?(1)c|x))(c)', 'abc'))
self.assertTrue(re.match(r'(a)b(?<=(?(1)b|x))(c)', 'abc'))
# Group defined in the same lookbehind pattern
self.assertRaises(re.error, re.compile, r'(a)b(?<=(.)\2)(c)')
self.assertRaises(re.error, re.compile, r'(a)b(?<=(?P<a>.)(?P=a))(c)')
self.assertRaises(re.error, re.compile, r'(a)b(?<=(a)(?(2)b|x))(c)')
self.assertRaises(re.error, re.compile, r'(a)b(?<=(.)(?<=\2))(c)')
def test_ignore_case(self):
self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
self.assertEqual(re.match(b"abc", b"ABC", re.I).group(0), b"ABC")
self.assertEqual(re.match(r"(a\s[^a])", "a b", re.I).group(1), "a b")
self.assertEqual(re.match(r"(a\s[^a]*)", "a bb", re.I).group(1), "a bb")
self.assertEqual(re.match(r"(a\s[abc])", "a b", re.I).group(1), "a b")
self.assertEqual(re.match(r"(a\s[abc]*)", "a bb", re.I).group(1), "a bb")
self.assertEqual(re.match(r"((a)\s\2)", "a a", re.I).group(1), "a a")
self.assertEqual(re.match(r"((a)\s\2*)", "a aa", re.I).group(1), "a aa")
self.assertEqual(re.match(r"((a)\s(abc|a))", "a a", re.I).group(1), "a a")
self.assertEqual(re.match(r"((a)\s(abc|a)*)", "a aa", re.I).group(1), "a aa")
assert '\u212a'.lower() == 'k' # 'K'
self.assertTrue(re.match(r'K', '\u212a', re.I))
self.assertTrue(re.match(r'k', '\u212a', re.I))
self.assertTrue(re.match(r'\u212a', 'K', re.I))
self.assertTrue(re.match(r'\u212a', 'k', re.I))
assert '\u017f'.upper() == 'S' # 'ſ'
self.assertTrue(re.match(r'S', '\u017f', re.I))
self.assertTrue(re.match(r's', '\u017f', re.I))
self.assertTrue(re.match(r'\u017f', 'S', re.I))
self.assertTrue(re.match(r'\u017f', 's', re.I))
assert '\ufb05'.upper() == '\ufb06'.upper() == 'ST' # 'ſt', 'st'
self.assertTrue(re.match(r'\ufb05', '\ufb06', re.I))
self.assertTrue(re.match(r'\ufb06', '\ufb05', re.I))
def test_ignore_case_set(self):
self.assertTrue(re.match(r'[19A]', 'A', re.I))
self.assertTrue(re.match(r'[19a]', 'a', re.I))
self.assertTrue(re.match(r'[19a]', 'A', re.I))
self.assertTrue(re.match(r'[19A]', 'a', re.I))
self.assertTrue(re.match(br'[19A]', b'A', re.I))
self.assertTrue(re.match(br'[19a]', b'a', re.I))
self.assertTrue(re.match(br'[19a]', b'A', re.I))
self.assertTrue(re.match(br'[19A]', b'a', re.I))
assert '\u212a'.lower() == 'k' # 'K'
self.assertTrue(re.match(r'[19K]', '\u212a', re.I))
self.assertTrue(re.match(r'[19k]', '\u212a', re.I))
self.assertTrue(re.match(r'[19\u212a]', 'K', re.I))
self.assertTrue(re.match(r'[19\u212a]', 'k', re.I))
assert '\u017f'.upper() == 'S' # 'ſ'
self.assertTrue(re.match(r'[19S]', '\u017f', re.I))
self.assertTrue(re.match(r'[19s]', '\u017f', re.I))
self.assertTrue(re.match(r'[19\u017f]', 'S', re.I))
self.assertTrue(re.match(r'[19\u017f]', 's', re.I))
assert '\ufb05'.upper() == '\ufb06'.upper() == 'ST' # 'ſt', 'st'
self.assertTrue(re.match(r'[19\ufb05]', '\ufb06', re.I))
self.assertTrue(re.match(r'[19\ufb06]', '\ufb05', re.I))
def test_ignore_case_range(self):
# Issues #3511, #17381.
self.assertTrue(re.match(r'[9-a]', '_', re.I))
self.assertIsNone(re.match(r'[9-A]', '_', re.I))
self.assertTrue(re.match(br'[9-a]', b'_', re.I))
self.assertIsNone(re.match(br'[9-A]', b'_', re.I))
self.assertTrue(re.match(r'[\xc0-\xde]', '\xd7', re.I))
self.assertIsNone(re.match(r'[\xc0-\xde]', '\xf7', re.I))
self.assertTrue(re.match(r'[\xe0-\xfe]', '\xf7', re.I))
self.assertIsNone(re.match(r'[\xe0-\xfe]', '\xd7', re.I))
self.assertTrue(re.match(r'[\u0430-\u045f]', '\u0450', re.I))
self.assertTrue(re.match(r'[\u0430-\u045f]', '\u0400', re.I))
self.assertTrue(re.match(r'[\u0400-\u042f]', '\u0450', re.I))
self.assertTrue(re.match(r'[\u0400-\u042f]', '\u0400', re.I))
self.assertTrue(re.match(r'[\U00010428-\U0001044f]', '\U00010428', re.I))
self.assertTrue(re.match(r'[\U00010428-\U0001044f]', '\U00010400', re.I))
self.assertTrue(re.match(r'[\U00010400-\U00010427]', '\U00010428', re.I))
self.assertTrue(re.match(r'[\U00010400-\U00010427]', '\U00010400', re.I))
assert '\u212a'.lower() == 'k' # 'K'
self.assertTrue(re.match(r'[J-M]', '\u212a', re.I))
self.assertTrue(re.match(r'[j-m]', '\u212a', re.I))
self.assertTrue(re.match(r'[\u2129-\u212b]', 'K', re.I))
self.assertTrue(re.match(r'[\u2129-\u212b]', 'k', re.I))
assert '\u017f'.upper() == 'S' # 'ſ'
self.assertTrue(re.match(r'[R-T]', '\u017f', re.I))
self.assertTrue(re.match(r'[r-t]', '\u017f', re.I))
self.assertTrue(re.match(r'[\u017e-\u0180]', 'S', re.I))
self.assertTrue(re.match(r'[\u017e-\u0180]', 's', re.I))
assert '\ufb05'.upper() == '\ufb06'.upper() == 'ST' # 'ſt', 'st'
self.assertTrue(re.match(r'[\ufb04-\ufb05]', '\ufb06', re.I))
self.assertTrue(re.match(r'[\ufb06-\ufb07]', '\ufb05', re.I))
def test_category(self):
self.assertEqual(re.match(r"(\s)", " ").group(1), " ")
def test_getlower(self):
import _sre
self.assertEqual(_sre.getlower(ord('A'), 0), ord('a'))
self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a'))
self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a'))
self.assertEqual(_sre.getlower(ord('A'), re.ASCII), ord('a'))
self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
self.assertEqual(re.match(b"abc", b"ABC", re.I).group(0), b"ABC")
self.assertEqual(re.match("abc", "ABC", re.I|re.A).group(0), "ABC")
self.assertEqual(re.match(b"abc", b"ABC", re.I|re.L).group(0), b"ABC")
def test_not_literal(self):
self.assertEqual(re.search("\s([^a])", " b").group(1), "b")
self.assertEqual(re.search("\s([^a]*)", " bb").group(1), "bb")
def test_search_coverage(self):
self.assertEqual(re.search("\s(b)", " b").group(1), "b")
self.assertEqual(re.search("a\s", "a ").group(0), "a ")
def assertMatch(self, pattern, text, match=None, span=None,
matcher=re.match):
if match is None and span is None:
# the pattern matches the whole text
match = text
span = (0, len(text))
elif match is None or span is None:
raise ValueError('If match is not None, span should be specified '
'(and vice versa).')
m = matcher(pattern, text)
self.assertTrue(m)
self.assertEqual(m.group(), match)
self.assertEqual(m.span(), span)
def test_re_escape(self):
alnum_chars = string.ascii_letters + string.digits + '_'
p = ''.join(chr(i) for i in range(256))
for c in p:
if c in alnum_chars:
self.assertEqual(re.escape(c), c)
elif c == '\x00':
self.assertEqual(re.escape(c), '\\000')
else:
self.assertEqual(re.escape(c), '\\' + c)
self.assertMatch(re.escape(c), c)
self.assertMatch(re.escape(p), p)
def test_re_escape_byte(self):
alnum_chars = (string.ascii_letters + string.digits + '_').encode('ascii')
p = bytes(range(256))
for i in p:
b = bytes([i])
if b in alnum_chars:
self.assertEqual(re.escape(b), b)
elif i == 0:
self.assertEqual(re.escape(b), b'\\000')
else:
self.assertEqual(re.escape(b), b'\\' + b)
self.assertMatch(re.escape(b), b)
self.assertMatch(re.escape(p), p)
def test_re_escape_non_ascii(self):
s = 'xxx\u2620\u2620\u2620xxx'
s_escaped = re.escape(s)
self.assertEqual(s_escaped, 'xxx\\\u2620\\\u2620\\\u2620xxx')
self.assertMatch(s_escaped, s)
self.assertMatch('.%s+.' % re.escape('\u2620'), s,
'x\u2620\u2620\u2620x', (2, 7), re.search)
def test_re_escape_non_ascii_bytes(self):
b = 'y\u2620y\u2620y'.encode('utf-8')
b_escaped = re.escape(b)
self.assertEqual(b_escaped, b'y\\\xe2\\\x98\\\xa0y\\\xe2\\\x98\\\xa0y')
self.assertMatch(b_escaped, b)
res = re.findall(re.escape('\u2620'.encode('utf-8')), b)
self.assertEqual(len(res), 2)
def test_pickling(self):
import pickle
oldpat = re.compile('a(?:b|(c|e){1,2}?|d)+?(.)', re.UNICODE)
for proto in range(pickle.HIGHEST_PROTOCOL + 1):
pickled = pickle.dumps(oldpat, proto)
newpat = pickle.loads(pickled)
self.assertEqual(newpat, oldpat)
# current pickle expects the _compile() reconstructor in re module
from re import _compile
def test_constants(self):
self.assertEqual(re.I, re.IGNORECASE)
self.assertEqual(re.L, re.LOCALE)
self.assertEqual(re.M, re.MULTILINE)
self.assertEqual(re.S, re.DOTALL)
self.assertEqual(re.X, re.VERBOSE)
def test_flags(self):
for flag in [re.I, re.M, re.X, re.S, re.A, re.U]:
self.assertTrue(re.compile('^pattern$', flag))
for flag in [re.I, re.M, re.X, re.S, re.A, re.L]:
self.assertTrue(re.compile(b'^pattern$', flag))
def test_sre_character_literals(self):
for i in [0, 8, 16, 32, 64, 127, 128, 255, 256, 0xFFFF, 0x10000, 0x10FFFF]:
if i < 256:
self.assertTrue(re.match(r"\%03o" % i, chr(i)))
self.assertTrue(re.match(r"\%03o0" % i, chr(i)+"0"))
self.assertTrue(re.match(r"\%03o8" % i, chr(i)+"8"))
self.assertTrue(re.match(r"\x%02x" % i, chr(i)))
self.assertTrue(re.match(r"\x%02x0" % i, chr(i)+"0"))
self.assertTrue(re.match(r"\x%02xz" % i, chr(i)+"z"))
if i < 0x10000:
self.assertTrue(re.match(r"\u%04x" % i, chr(i)))
self.assertTrue(re.match(r"\u%04x0" % i, chr(i)+"0"))
self.assertTrue(re.match(r"\u%04xz" % i, chr(i)+"z"))
self.assertTrue(re.match(r"\U%08x" % i, chr(i)))
self.assertTrue(re.match(r"\U%08x0" % i, chr(i)+"0"))
self.assertTrue(re.match(r"\U%08xz" % i, chr(i)+"z"))
self.assertTrue(re.match(r"\0", "\000"))
self.assertTrue(re.match(r"\08", "\0008"))
self.assertTrue(re.match(r"\01", "\001"))
self.assertTrue(re.match(r"\018", "\0018"))
self.checkPatternError(r"\567",
r'octal escape value \567 outside of '
r'range 0-0o377', 0)
self.checkPatternError(r"\911", 'invalid group reference', 0)
self.checkPatternError(r"\x1", r'incomplete escape \x1', 0)
self.checkPatternError(r"\x1z", r'incomplete escape \x1', 0)
self.checkPatternError(r"\u123", r'incomplete escape \u123', 0)
self.checkPatternError(r"\u123z", r'incomplete escape \u123', 0)
self.checkPatternError(r"\U0001234", r'incomplete escape \U0001234', 0)
self.checkPatternError(r"\U0001234z", r'incomplete escape \U0001234', 0)
self.checkPatternError(r"\U00110000", r'bad escape \U00110000', 0)
def test_sre_character_class_literals(self):
for i in [0, 8, 16, 32, 64, 127, 128, 255, 256, 0xFFFF, 0x10000, 0x10FFFF]:
if i < 256:
self.assertTrue(re.match(r"[\%o]" % i, chr(i)))
self.assertTrue(re.match(r"[\%o8]" % i, chr(i)))
self.assertTrue(re.match(r"[\%03o]" % i, chr(i)))
self.assertTrue(re.match(r"[\%03o0]" % i, chr(i)))
self.assertTrue(re.match(r"[\%03o8]" % i, chr(i)))
self.assertTrue(re.match(r"[\x%02x]" % i, chr(i)))
self.assertTrue(re.match(r"[\x%02x0]" % i, chr(i)))
self.assertTrue(re.match(r"[\x%02xz]" % i, chr(i)))
if i < 0x10000:
self.assertTrue(re.match(r"[\u%04x]" % i, chr(i)))
self.assertTrue(re.match(r"[\u%04x0]" % i, chr(i)))
self.assertTrue(re.match(r"[\u%04xz]" % i, chr(i)))
self.assertTrue(re.match(r"[\U%08x]" % i, chr(i)))
self.assertTrue(re.match(r"[\U%08x0]" % i, chr(i)+"0"))
self.assertTrue(re.match(r"[\U%08xz]" % i, chr(i)+"z"))
self.checkPatternError(r"[\567]",
r'octal escape value \567 outside of '
r'range 0-0o377', 1)
self.checkPatternError(r"[\911]", r'bad escape \9', 1)
self.checkPatternError(r"[\x1z]", r'incomplete escape \x1', 1)
self.checkPatternError(r"[\u123z]", r'incomplete escape \u123', 1)
self.checkPatternError(r"[\U0001234z]", r'incomplete escape \U0001234', 1)
self.checkPatternError(r"[\U00110000]", r'bad escape \U00110000', 1)
self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e"))
def test_sre_byte_literals(self):
for i in [0, 8, 16, 32, 64, 127, 128, 255]:
self.assertTrue(re.match((r"\%03o" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"\%03o0" % i).encode(), bytes([i])+b"0"))
self.assertTrue(re.match((r"\%03o8" % i).encode(), bytes([i])+b"8"))
self.assertTrue(re.match((r"\x%02x" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"\x%02x0" % i).encode(), bytes([i])+b"0"))
self.assertTrue(re.match((r"\x%02xz" % i).encode(), bytes([i])+b"z"))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"\u1234", b'u1234'))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"\U00012345", b'U00012345'))
self.assertTrue(re.match(br"\0", b"\000"))
self.assertTrue(re.match(br"\08", b"\0008"))
self.assertTrue(re.match(br"\01", b"\001"))
self.assertTrue(re.match(br"\018", b"\0018"))
self.checkPatternError(br"\567",
r'octal escape value \567 outside of '
r'range 0-0o377', 0)
self.checkPatternError(br"\911", 'invalid group reference', 0)
self.checkPatternError(br"\x1", r'incomplete escape \x1', 0)
self.checkPatternError(br"\x1z", r'incomplete escape \x1', 0)
def test_sre_byte_class_literals(self):
for i in [0, 8, 16, 32, 64, 127, 128, 255]:
self.assertTrue(re.match((r"[\%o]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\%o8]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\%03o]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\%03o0]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\%03o8]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\x%02x]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\x%02x0]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\x%02xz]" % i).encode(), bytes([i])))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"[\u1234]", b'u'))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"[\U00012345]", b'U'))
self.checkPatternError(br"[\567]",
r'octal escape value \567 outside of '
r'range 0-0o377', 1)
self.checkPatternError(br"[\911]", r'bad escape \9', 1)
self.checkPatternError(br"[\x1z]", r'incomplete escape \x1', 1)
def test_character_set_errors(self):
self.checkPatternError(r'[', 'unterminated character set', 0)
self.checkPatternError(r'[^', 'unterminated character set', 0)
self.checkPatternError(r'[a', 'unterminated character set', 0)
# bug 545855 -- This pattern failed to cause a compile error as it
# should, instead provoking a TypeError.
self.checkPatternError(r"[a-", 'unterminated character set', 0)
self.checkPatternError(r"[\w-b]", r'bad character range \w-b', 1)
self.checkPatternError(r"[a-\w]", r'bad character range a-\w', 1)
self.checkPatternError(r"[b-a]", 'bad character range b-a', 1)
def test_bug_113254(self):
self.assertEqual(re.match(r'(a)|(b)', 'b').start(1), -1)
self.assertEqual(re.match(r'(a)|(b)', 'b').end(1), -1)
self.assertEqual(re.match(r'(a)|(b)', 'b').span(1), (-1, -1))
def test_bug_527371(self):
# bug described in patches 527371/672491
self.assertIsNone(re.match(r'(a)?a','a').lastindex)
self.assertEqual(re.match(r'(a)(b)?b','ab').lastindex, 1)
self.assertEqual(re.match(r'(?P<a>a)(?P<b>b)?b','ab').lastgroup, 'a')
self.assertEqual(re.match("(?P<a>a(b))", "ab").lastgroup, 'a')
self.assertEqual(re.match("((a))", "a").lastindex, 1)
def test_bug_418626(self):
# bugs 418626 at al. -- Testing Greg Chapman's addition of op code
# SRE_OP_MIN_REPEAT_ONE for eliminating recursion on simple uses of
# pattern '*?' on a long string.
self.assertEqual(re.match('.*?c', 10000*'ab'+'cd').end(0), 20001)
self.assertEqual(re.match('.*?cd', 5000*'ab'+'c'+5000*'ab'+'cde').end(0),
20003)
self.assertEqual(re.match('.*?cd', 20000*'abc'+'de').end(0), 60001)
# non-simple '*?' still used to hit the recursion limit, before the
# non-recursive scheme was implemented.
self.assertEqual(re.search('(a|b)*?c', 10000*'ab'+'cd').end(0), 20001)
def test_bug_612074(self):
pat="["+re.escape("\u2039")+"]"
self.assertEqual(re.compile(pat) and 1, 1)
def test_stack_overflow(self):
# nasty cases that used to overflow the straightforward recursive
# implementation of repeated groups.
self.assertEqual(re.match('(x)*', 50000*'x').group(1), 'x')
self.assertEqual(re.match('(x)*y', 50000*'x'+'y').group(1), 'x')
self.assertEqual(re.match('(x)*?y', 50000*'x'+'y').group(1), 'x')
def test_nothing_to_repeat(self):
for reps in '*', '+', '?', '{1,2}':
for mod in '', '?':
self.checkPatternError('%s%s' % (reps, mod),
'nothing to repeat', 0)
self.checkPatternError('(?:%s%s)' % (reps, mod),
'nothing to repeat', 3)
def test_multiple_repeat(self):
for outer_reps in '*', '+', '{1,2}':
for outer_mod in '', '?':
outer_op = outer_reps + outer_mod
for inner_reps in '*', '+', '?', '{1,2}':
for inner_mod in '', '?':
inner_op = inner_reps + inner_mod
self.checkPatternError(r'x%s%s' % (inner_op, outer_op),
'multiple repeat', 1 + len(inner_op))
def test_unlimited_zero_width_repeat(self):
# Issue #9669
self.assertIsNone(re.match(r'(?:a?)*y', 'z'))
self.assertIsNone(re.match(r'(?:a?)+y', 'z'))
self.assertIsNone(re.match(r'(?:a?){2,}y', 'z'))
self.assertIsNone(re.match(r'(?:a?)*?y', 'z'))
self.assertIsNone(re.match(r'(?:a?)+?y', 'z'))
self.assertIsNone(re.match(r'(?:a?){2,}?y', 'z'))
def test_scanner(self):
def s_ident(scanner, token): return token
def s_operator(scanner, token): return "op%s" % token
def s_float(scanner, token): return float(token)
def s_int(scanner, token): return int(token)
scanner = Scanner([
(r"[a-zA-Z_]\w*", s_ident),
(r"\d+\.\d*", s_float),
(r"\d+", s_int),
(r"=|\+|-|\*|/", s_operator),
(r"\s+", None),
])
self.assertTrue(scanner.scanner.scanner("").pattern)
self.assertEqual(scanner.scan("sum = 3*foo + 312.50 + bar"),
(['sum', 'op=', 3, 'op*', 'foo', 'op+', 312.5,
'op+', 'bar'], ''))
def test_bug_448951(self):
# bug 448951 (similar to 429357, but with single char match)
# (Also test greedy matches.)
for op in '','?','*':
self.assertEqual(re.match(r'((.%s):)?z'%op, 'z').groups(),
(None, None))
self.assertEqual(re.match(r'((.%s):)?z'%op, 'a:z').groups(),
('a:', 'a'))
def test_bug_725106(self):
# capturing groups in alternatives in repeats
self.assertEqual(re.match('^((a)|b)*', 'abc').groups(),
('b', 'a'))
self.assertEqual(re.match('^(([ab])|c)*', 'abc').groups(),
('c', 'b'))
self.assertEqual(re.match('^((d)|[ab])*', 'abc').groups(),
('b', None))
self.assertEqual(re.match('^((a)c|[ab])*', 'abc').groups(),
('b', None))
self.assertEqual(re.match('^((a)|b)*?c', 'abc').groups(),
('b', 'a'))
self.assertEqual(re.match('^(([ab])|c)*?d', 'abcd').groups(),
('c', 'b'))
self.assertEqual(re.match('^((d)|[ab])*?c', 'abc').groups(),
('b', None))
self.assertEqual(re.match('^((a)c|[ab])*?c', 'abc').groups(),
('b', None))
def test_bug_725149(self):
# mark_stack_base restoring before restoring marks
self.assertEqual(re.match('(a)(?:(?=(b)*)c)*', 'abb').groups(),
('a', None))
self.assertEqual(re.match('(a)((?!(b)*))*', 'abb').groups(),
('a', None, None))
def test_bug_764548(self):
# bug 764548, re.compile() barfs on str/unicode subclasses
class my_unicode(str): pass
pat = re.compile(my_unicode("abc"))
self.assertIsNone(pat.match("xyz"))
def test_finditer(self):
iter = re.finditer(r":+", "a:b::c:::d")
self.assertEqual([item.group(0) for item in iter],
[":", "::", ":::"])
pat = re.compile(r":+")
iter = pat.finditer("a:b::c:::d", 1, 10)
self.assertEqual([item.group(0) for item in iter],
[":", "::", ":::"])
pat = re.compile(r":+")
iter = pat.finditer("a:b::c:::d", pos=1, endpos=10)
self.assertEqual([item.group(0) for item in iter],
[":", "::", ":::"])
pat = re.compile(r":+")
iter = pat.finditer("a:b::c:::d", endpos=10, pos=1)
self.assertEqual([item.group(0) for item in iter],
[":", "::", ":::"])
pat = re.compile(r":+")
iter = pat.finditer("a:b::c:::d", pos=3, endpos=8)
self.assertEqual([item.group(0) for item in iter],
["::", "::"])
def test_bug_926075(self):
self.assertIsNot(re.compile('bug_926075'),
re.compile(b'bug_926075'))
def test_bug_931848(self):
pattern = "[\u002E\u3002\uFF0E\uFF61]"
self.assertEqual(re.compile(pattern).split("a.b.c"),
['a','b','c'])
def test_bug_581080(self):
iter = re.finditer(r"\s", "a b")
self.assertEqual(next(iter).span(), (1,2))
self.assertRaises(StopIteration, next, iter)
scanner = re.compile(r"\s").scanner("a b")
self.assertEqual(scanner.search().span(), (1, 2))
self.assertIsNone(scanner.search())
def test_bug_817234(self):
iter = re.finditer(r".*", "asdf")
self.assertEqual(next(iter).span(), (0, 4))
self.assertEqual(next(iter).span(), (4, 4))
self.assertRaises(StopIteration, next, iter)
def test_bug_6561(self):
# '\d' should match characters in Unicode category 'Nd'
# (Number, Decimal Digit), but not those in 'Nl' (Number,
# Letter) or 'No' (Number, Other).
decimal_digits = [
'\u0037', # '\N{DIGIT SEVEN}', category 'Nd'
'\u0e58', # '\N{THAI DIGIT SIX}', category 'Nd'
'\uff10', # '\N{FULLWIDTH DIGIT ZERO}', category 'Nd'
]
for x in decimal_digits:
self.assertEqual(re.match('^\d$', x).group(0), x)
not_decimal_digits = [
'\u2165', # '\N{ROMAN NUMERAL SIX}', category 'Nl'
'\u3039', # '\N{HANGZHOU NUMERAL TWENTY}', category 'Nl'
'\u2082', # '\N{SUBSCRIPT TWO}', category 'No'
'\u32b4', # '\N{CIRCLED NUMBER THIRTY NINE}', category 'No'
]
for x in not_decimal_digits:
self.assertIsNone(re.match('^\d$', x))
def test_empty_array(self):
# SF buf 1647541
import array
for typecode in 'bBuhHiIlLfd':
a = array.array(typecode)
self.assertIsNone(re.compile(b"bla").match(a))
self.assertEqual(re.compile(b"").match(a).groups(), ())
def test_inline_flags(self):
# Bug #1700
upper_char = '\u1ea0' # Latin Capital Letter A with Dot Below
lower_char = '\u1ea1' # Latin Small Letter A with Dot Below
p = re.compile(upper_char, re.I | re.U)
q = p.match(lower_char)
self.assertTrue(q)
p = re.compile(lower_char, re.I | re.U)
q = p.match(upper_char)
self.assertTrue(q)
p = re.compile('(?i)' + upper_char, re.U)
q = p.match(lower_char)
self.assertTrue(q)
p = re.compile('(?i)' + lower_char, re.U)
q = p.match(upper_char)
self.assertTrue(q)
p = re.compile('(?iu)' + upper_char)
q = p.match(lower_char)
self.assertTrue(q)
p = re.compile('(?iu)' + lower_char)
q = p.match(upper_char)
self.assertTrue(q)
def test_dollar_matches_twice(self):
"$ matches the end of string, and just before the terminating \n"
pattern = re.compile('$')
self.assertEqual(pattern.sub('#', 'a\nb\n'), 'a\nb#\n#')
self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a\nb\nc#')
self.assertEqual(pattern.sub('#', '\n'), '#\n#')
pattern = re.compile('$', re.MULTILINE)
self.assertEqual(pattern.sub('#', 'a\nb\n' ), 'a#\nb#\n#' )
self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a#\nb#\nc#')
self.assertEqual(pattern.sub('#', '\n'), '#\n#')
def test_bytes_str_mixing(self):
# Mixing str and bytes is disallowed
pat = re.compile('.')
bpat = re.compile(b'.')
self.assertRaises(TypeError, pat.match, b'b')
self.assertRaises(TypeError, bpat.match, 'b')
self.assertRaises(TypeError, pat.sub, b'b', 'c')
self.assertRaises(TypeError, pat.sub, 'b', b'c')
self.assertRaises(TypeError, pat.sub, b'b', b'c')
self.assertRaises(TypeError, bpat.sub, b'b', 'c')
self.assertRaises(TypeError, bpat.sub, 'b', b'c')
self.assertRaises(TypeError, bpat.sub, 'b', 'c')
def test_ascii_and_unicode_flag(self):
# String patterns
for flags in (0, re.UNICODE):
pat = re.compile('\xc0', flags | re.IGNORECASE)
self.assertTrue(pat.match('\xe0'))
pat = re.compile('\w', flags)
self.assertTrue(pat.match('\xe0'))
pat = re.compile('\xc0', re.ASCII | re.IGNORECASE)
self.assertIsNone(pat.match('\xe0'))
pat = re.compile('(?a)\xc0', re.IGNORECASE)
self.assertIsNone(pat.match('\xe0'))
pat = re.compile('\w', re.ASCII)
self.assertIsNone(pat.match('\xe0'))
pat = re.compile('(?a)\w')
self.assertIsNone(pat.match('\xe0'))
# Bytes patterns
for flags in (0, re.ASCII):
pat = re.compile(b'\xc0', flags | re.IGNORECASE)
self.assertIsNone(pat.match(b'\xe0'))
pat = re.compile(b'\w', flags)
self.assertIsNone(pat.match(b'\xe0'))
# Incompatibilities
self.assertRaises(ValueError, re.compile, b'\w', re.UNICODE)
self.assertRaises(ValueError, re.compile, b'(?u)\w')
self.assertRaises(ValueError, re.compile, '\w', re.UNICODE | re.ASCII)
self.assertRaises(ValueError, re.compile, '(?u)\w', re.ASCII)
self.assertRaises(ValueError, re.compile, '(?a)\w', re.UNICODE)
self.assertRaises(ValueError, re.compile, '(?au)\w')
def test_locale_flag(self):
import locale
_, enc = locale.getlocale(locale.LC_CTYPE)
# Search non-ASCII letter
for i in range(128, 256):
try:
c = bytes([i]).decode(enc)
sletter = c.lower()
if sletter == c: continue
bletter = sletter.encode(enc)
if len(bletter) != 1: continue
if bletter.decode(enc) != sletter: continue
bpat = re.escape(bytes([i]))
break
except (UnicodeError, TypeError):
pass
else:
bletter = None
bpat = b'A'
# Bytes patterns
pat = re.compile(bpat, re.LOCALE | re.IGNORECASE)
if bletter:
self.assertTrue(pat.match(bletter))
pat = re.compile(b'(?L)' + bpat, re.IGNORECASE)
if bletter:
self.assertTrue(pat.match(bletter))
pat = re.compile(bpat, re.IGNORECASE)
if bletter:
self.assertIsNone(pat.match(bletter))
pat = re.compile(b'\w', re.LOCALE)
if bletter:
self.assertTrue(pat.match(bletter))
pat = re.compile(b'(?L)\w')
if bletter:
self.assertTrue(pat.match(bletter))
pat = re.compile(b'\w')
if bletter:
self.assertIsNone(pat.match(bletter))
# Incompatibilities
self.assertWarns(DeprecationWarning, re.compile, '', re.LOCALE)
self.assertWarns(DeprecationWarning, re.compile, '(?L)')
self.assertWarns(DeprecationWarning, re.compile, b'', re.LOCALE | re.ASCII)
self.assertWarns(DeprecationWarning, re.compile, b'(?L)', re.ASCII)
self.assertWarns(DeprecationWarning, re.compile, b'(?a)', re.LOCALE)
self.assertWarns(DeprecationWarning, re.compile, b'(?aL)')
def test_bug_6509(self):
# Replacement strings of both types must parse properly.
# all strings
pat = re.compile('a(\w)')
self.assertEqual(pat.sub('b\\1', 'ac'), 'bc')
pat = re.compile('a(.)')
self.assertEqual(pat.sub('b\\1', 'a\u1234'), 'b\u1234')
pat = re.compile('..')
self.assertEqual(pat.sub(lambda m: 'str', 'a5'), 'str')
# all bytes
pat = re.compile(b'a(\w)')
self.assertEqual(pat.sub(b'b\\1', b'ac'), b'bc')
pat = re.compile(b'a(.)')
self.assertEqual(pat.sub(b'b\\1', b'a\xCD'), b'b\xCD')
pat = re.compile(b'..')
self.assertEqual(pat.sub(lambda m: b'bytes', b'a5'), b'bytes')
def test_dealloc(self):
# issue 3299: check for segfault in debug build
import _sre
# the overflow limit is different on wide and narrow builds and it
# depends on the definition of SRE_CODE (see sre.h).
# 2**128 should be big enough to overflow on both. For smaller values
# a RuntimeError is raised instead of OverflowError.
long_overflow = 2**128
self.assertRaises(TypeError, re.finditer, "a", {})
with self.assertRaises(OverflowError):
_sre.compile("abc", 0, [long_overflow], 0, [], [])
with self.assertRaises(TypeError):
_sre.compile({}, 0, [], 0, [], [])
def test_search_dot_unicode(self):
self.assertTrue(re.search("123.*-", '123abc-'))
self.assertTrue(re.search("123.*-", '123\xe9-'))
self.assertTrue(re.search("123.*-", '123\u20ac-'))
self.assertTrue(re.search("123.*-", '123\U0010ffff-'))
self.assertTrue(re.search("123.*-", '123\xe9\u20ac\U0010ffff-'))
def test_compile(self):
# Test return value when given string and pattern as parameter
pattern = re.compile('random pattern')
self.assertIsInstance(pattern, re._pattern_type)
same_pattern = re.compile(pattern)
self.assertIsInstance(same_pattern, re._pattern_type)
self.assertIs(same_pattern, pattern)
# Test behaviour when not given a string or pattern as parameter
self.assertRaises(TypeError, re.compile, 0)
def test_bug_13899(self):
# Issue #13899: re pattern r"[\A]" should work like "A" but matches
# nothing. Ditto B and Z.
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.findall(r'[\A\B\b\C\Z]', 'AB\bCZ'),
['A', 'B', '\b', 'C', 'Z'])
@bigmemtest(size=_2G, memuse=1)
def test_large_search(self, size):
# Issue #10182: indices were 32-bit-truncated.
s = 'a' * size
m = re.search('$', s)
self.assertIsNotNone(m)
self.assertEqual(m.start(), size)
self.assertEqual(m.end(), size)
# The huge memuse is because of re.sub() using a list and a join()
# to create the replacement result.
@bigmemtest(size=_2G, memuse=16 + 2)
def test_large_subn(self, size):
# Issue #10182: indices were 32-bit-truncated.
s = 'a' * size
r, n = re.subn('', '', s)
self.assertEqual(r, s)
self.assertEqual(n, size + 1)
def test_bug_16688(self):
# Issue 16688: Backreferences make case-insensitive regex fail on
# non-ASCII strings.
self.assertEqual(re.findall(r"(?i)(a)\1", "aa \u0100"), ['a'])
self.assertEqual(re.match(r"(?s).{1,3}", "\u0100\u0100").span(), (0, 2))
def test_repeat_minmax_overflow(self):
# Issue #13169
string = "x" * 100000
self.assertEqual(re.match(r".{65535}", string).span(), (0, 65535))
self.assertEqual(re.match(r".{,65535}", string).span(), (0, 65535))
self.assertEqual(re.match(r".{65535,}?", string).span(), (0, 65535))
self.assertEqual(re.match(r".{65536}", string).span(), (0, 65536))
self.assertEqual(re.match(r".{,65536}", string).span(), (0, 65536))
self.assertEqual(re.match(r".{65536,}?", string).span(), (0, 65536))
# 2**128 should be big enough to overflow both SRE_CODE and Py_ssize_t.
self.assertRaises(OverflowError, re.compile, r".{%d}" % 2**128)
self.assertRaises(OverflowError, re.compile, r".{,%d}" % 2**128)
self.assertRaises(OverflowError, re.compile, r".{%d,}?" % 2**128)
self.assertRaises(OverflowError, re.compile, r".{%d,%d}" % (2**129, 2**128))
@cpython_only
def test_repeat_minmax_overflow_maxrepeat(self):
try:
from _sre import MAXREPEAT
except ImportError:
self.skipTest('requires _sre.MAXREPEAT constant')
string = "x" * 100000
self.assertIsNone(re.match(r".{%d}" % (MAXREPEAT - 1), string))
self.assertEqual(re.match(r".{,%d}" % (MAXREPEAT - 1), string).span(),
(0, 100000))
self.assertIsNone(re.match(r".{%d,}?" % (MAXREPEAT - 1), string))
self.assertRaises(OverflowError, re.compile, r".{%d}" % MAXREPEAT)
self.assertRaises(OverflowError, re.compile, r".{,%d}" % MAXREPEAT)
self.assertRaises(OverflowError, re.compile, r".{%d,}?" % MAXREPEAT)
def test_backref_group_name_in_exception(self):
# Issue 17341: Poor error message when compiling invalid regex
self.checkPatternError('(?P=<foo>)',
"bad character in group name '<foo>'", 4)
def test_group_name_in_exception(self):
# Issue 17341: Poor error message when compiling invalid regex
self.checkPatternError('(?P<?foo>)',
"bad character in group name '?foo'", 4)
def test_issue17998(self):
for reps in '*', '+', '?', '{1}':
for mod in '', '?':
pattern = '.' + reps + mod + 'yz'
self.assertEqual(re.compile(pattern, re.S).findall('xyz'),
['xyz'], msg=pattern)
pattern = pattern.encode()
self.assertEqual(re.compile(pattern, re.S).findall(b'xyz'),
[b'xyz'], msg=pattern)
def test_match_repr(self):
for string in '[abracadabra]', S('[abracadabra]'):
m = re.search(r'(.+)(.*?)\1', string)
self.assertEqual(repr(m), "<%s.%s object; "
"span=(1, 12), match='abracadabra'>" %
(type(m).__module__, type(m).__qualname__))
for string in (b'[abracadabra]', B(b'[abracadabra]'),
bytearray(b'[abracadabra]'),
memoryview(b'[abracadabra]')):
m = re.search(rb'(.+)(.*?)\1', string)
self.assertEqual(repr(m), "<%s.%s object; "
"span=(1, 12), match=b'abracadabra'>" %
(type(m).__module__, type(m).__qualname__))
first, second = list(re.finditer("(aa)|(bb)", "aa bb"))
self.assertEqual(repr(first), "<%s.%s object; "
"span=(0, 2), match='aa'>" %
(type(second).__module__, type(first).__qualname__))
self.assertEqual(repr(second), "<%s.%s object; "
"span=(3, 5), match='bb'>" %
(type(second).__module__, type(second).__qualname__))
def test_bug_2537(self):
# issue 2537: empty submatches
for outer_op in ('{0,}', '*', '+', '{1,187}'):
for inner_op in ('{0,}', '*', '?'):
r = re.compile("^((x|y)%s)%s" % (inner_op, outer_op))
m = r.match("xyyzy")
self.assertEqual(m.group(0), "xyy")
self.assertEqual(m.group(1), "")
self.assertEqual(m.group(2), "y")
def test_debug_flag(self):
pat = r'(\.)(?:[ch]|py)(?(1)$|: )'
with captured_stdout() as out:
re.compile(pat, re.DEBUG)
dump = '''\
SUBPATTERN 1
LITERAL 46
SUBPATTERN None
BRANCH
IN
LITERAL 99
LITERAL 104
OR
LITERAL 112
LITERAL 121
SUBPATTERN None
GROUPREF_EXISTS 1
AT AT_END
ELSE
LITERAL 58
LITERAL 32
'''
self.assertEqual(out.getvalue(), dump)
# Debug output is output again even a second time (bypassing
# the cache -- issue #20426).
with captured_stdout() as out:
re.compile(pat, re.DEBUG)
self.assertEqual(out.getvalue(), dump)
def test_keyword_parameters(self):
# Issue #20283: Accepting the string keyword parameter.
pat = re.compile(r'(ab)')
self.assertEqual(
pat.match(string='abracadabra', pos=7, endpos=10).span(), (7, 9))
self.assertEqual(
pat.fullmatch(string='abracadabra', pos=7, endpos=9).span(), (7, 9))
self.assertEqual(
pat.search(string='abracadabra', pos=3, endpos=10).span(), (7, 9))
self.assertEqual(
pat.findall(string='abracadabra', pos=3, endpos=10), ['ab'])
self.assertEqual(
pat.split(string='abracadabra', maxsplit=1),
['', 'ab', 'racadabra'])
self.assertEqual(
pat.scanner(string='abracadabra', pos=3, endpos=10).search().span(),
(7, 9))
def test_bug_20998(self):
# Issue #20998: Fullmatch of repeated single character pattern
# with ignore case.
self.assertEqual(re.fullmatch('[a-c]+', 'ABC', re.I).span(), (0, 3))
def test_locale_caching(self):
# Issue #22410
oldlocale = locale.setlocale(locale.LC_CTYPE)
self.addCleanup(locale.setlocale, locale.LC_CTYPE, oldlocale)
for loc in 'en_US.iso88591', 'en_US.utf8':
try:
locale.setlocale(locale.LC_CTYPE, loc)
except locale.Error:
# Unsupported locale on this system
self.skipTest('test needs %s locale' % loc)
re.purge()
self.check_en_US_iso88591()
self.check_en_US_utf8()
re.purge()
self.check_en_US_utf8()
self.check_en_US_iso88591()
def check_en_US_iso88591(self):
locale.setlocale(locale.LC_CTYPE, 'en_US.iso88591')
self.assertTrue(re.match(b'\xc5\xe5', b'\xc5\xe5', re.L|re.I))
self.assertTrue(re.match(b'\xc5', b'\xe5', re.L|re.I))
self.assertTrue(re.match(b'\xe5', b'\xc5', re.L|re.I))
self.assertTrue(re.match(b'(?Li)\xc5\xe5', b'\xc5\xe5'))
self.assertTrue(re.match(b'(?Li)\xc5', b'\xe5'))
self.assertTrue(re.match(b'(?Li)\xe5', b'\xc5'))
def check_en_US_utf8(self):
locale.setlocale(locale.LC_CTYPE, 'en_US.utf8')
self.assertTrue(re.match(b'\xc5\xe5', b'\xc5\xe5', re.L|re.I))
self.assertIsNone(re.match(b'\xc5', b'\xe5', re.L|re.I))
self.assertIsNone(re.match(b'\xe5', b'\xc5', re.L|re.I))
self.assertTrue(re.match(b'(?Li)\xc5\xe5', b'\xc5\xe5'))
self.assertIsNone(re.match(b'(?Li)\xc5', b'\xe5'))
self.assertIsNone(re.match(b'(?Li)\xe5', b'\xc5'))
def test_error(self):
with self.assertRaises(re.error) as cm:
re.compile('(\u20ac))')
err = cm.exception
self.assertIsInstance(err.pattern, str)
self.assertEqual(err.pattern, '(\u20ac))')
self.assertEqual(err.pos, 3)
self.assertEqual(err.lineno, 1)
self.assertEqual(err.colno, 4)
self.assertIn(err.msg, str(err))
self.assertIn(' at position 3', str(err))
self.assertNotIn(' at position 3', err.msg)
# Bytes pattern
with self.assertRaises(re.error) as cm:
re.compile(b'(\xa4))')
err = cm.exception
self.assertIsInstance(err.pattern, bytes)
self.assertEqual(err.pattern, b'(\xa4))')
self.assertEqual(err.pos, 3)
# Multiline pattern
with self.assertRaises(re.error) as cm:
re.compile("""
(
abc
)
)
(
""", re.VERBOSE)
err = cm.exception
self.assertEqual(err.pos, 77)
self.assertEqual(err.lineno, 5)
self.assertEqual(err.colno, 17)
self.assertIn(err.msg, str(err))
self.assertIn(' at position 77', str(err))
self.assertIn('(line 5, column 17)', str(err))
def test_misc_errors(self):
self.checkPatternError(r'(', 'missing ), unterminated subpattern', 0)
self.checkPatternError(r'((a|b)', 'missing ), unterminated subpattern', 0)
self.checkPatternError(r'(a|b))', 'unbalanced parenthesis', 5)
self.checkPatternError(r'(?P', 'unexpected end of pattern', 3)
self.checkPatternError(r'(?z)', 'unknown extension ?z', 1)
self.checkPatternError(r'(?iz)', 'unknown flag', 3)
self.checkPatternError(r'(?i', 'missing )', 3)
self.checkPatternError(r'(?#abc', 'missing ), unterminated comment', 0)
self.checkPatternError(r'(?<', 'unexpected end of pattern', 3)
self.checkPatternError(r'(?<>)', 'unknown extension ?<>', 1)
self.checkPatternError(r'(?', 'unexpected end of pattern', 2)
class PatternReprTests(unittest.TestCase):
def check(self, pattern, expected):
self.assertEqual(repr(re.compile(pattern)), expected)
def check_flags(self, pattern, flags, expected):
self.assertEqual(repr(re.compile(pattern, flags)), expected)
def test_without_flags(self):
self.check('random pattern',
"re.compile('random pattern')")
def test_single_flag(self):
self.check_flags('random pattern', re.IGNORECASE,
"re.compile('random pattern', re.IGNORECASE)")
def test_multiple_flags(self):
self.check_flags('random pattern', re.I|re.S|re.X,
"re.compile('random pattern', "
"re.IGNORECASE|re.DOTALL|re.VERBOSE)")
def test_unicode_flag(self):
self.check_flags('random pattern', re.U,
"re.compile('random pattern')")
self.check_flags('random pattern', re.I|re.S|re.U,
"re.compile('random pattern', "
"re.IGNORECASE|re.DOTALL)")
def test_inline_flags(self):
self.check('(?i)pattern',
"re.compile('(?i)pattern', re.IGNORECASE)")
def test_unknown_flags(self):
self.check_flags('random pattern', 0x123000,
"re.compile('random pattern', 0x123000)")
self.check_flags('random pattern', 0x123000|re.I,
"re.compile('random pattern', re.IGNORECASE|0x123000)")
def test_bytes(self):
self.check(b'bytes pattern',
"re.compile(b'bytes pattern')")
self.check_flags(b'bytes pattern', re.A,
"re.compile(b'bytes pattern', re.ASCII)")
def test_locale(self):
self.check_flags(b'bytes pattern', re.L,
"re.compile(b'bytes pattern', re.LOCALE)")
def test_quotes(self):
self.check('random "double quoted" pattern',
'''re.compile('random "double quoted" pattern')''')
self.check("random 'single quoted' pattern",
'''re.compile("random 'single quoted' pattern")''')
self.check('''both 'single' and "double" quotes''',
'''re.compile('both \\'single\\' and "double" quotes')''')
def test_long_pattern(self):
pattern = 'Very %spattern' % ('long ' * 1000)
r = repr(re.compile(pattern))
self.assertLess(len(r), 300)
self.assertEqual(r[:30], "re.compile('Very long long lon")
r = repr(re.compile(pattern, re.I))
self.assertLess(len(r), 300)
self.assertEqual(r[:30], "re.compile('Very long long lon")
self.assertEqual(r[-16:], ", re.IGNORECASE)")
class ImplementationTest(unittest.TestCase):
"""
Test implementation details of the re module.
"""
def test_overlap_table(self):
f = sre_compile._generate_overlap_table
self.assertEqual(f(""), [])
self.assertEqual(f("a"), [0])
self.assertEqual(f("abcd"), [0, 0, 0, 0])
self.assertEqual(f("aaaa"), [0, 1, 2, 3])
self.assertEqual(f("ababba"), [0, 0, 1, 2, 0, 1])
self.assertEqual(f("abcabdac"), [0, 0, 0, 1, 2, 0, 1, 0])
class ExternalTests(unittest.TestCase):
def test_re_benchmarks(self):
're_tests benchmarks'
from test.re_tests import benchmarks
for pattern, s in benchmarks:
with self.subTest(pattern=pattern, string=s):
p = re.compile(pattern)
self.assertTrue(p.search(s))
self.assertTrue(p.match(s))
self.assertTrue(p.fullmatch(s))
s2 = ' '*10000 + s + ' '*10000
self.assertTrue(p.search(s2))
self.assertTrue(p.match(s2, 10000))
self.assertTrue(p.match(s2, 10000, 10000 + len(s)))
self.assertTrue(p.fullmatch(s2, 10000, 10000 + len(s)))
def test_re_tests(self):
're_tests test suite'
from test.re_tests import tests, SUCCEED, FAIL, SYNTAX_ERROR
for t in tests:
pattern = s = outcome = repl = expected = None
if len(t) == 5:
pattern, s, outcome, repl, expected = t
elif len(t) == 3:
pattern, s, outcome = t
else:
raise ValueError('Test tuples should have 3 or 5 fields', t)
with self.subTest(pattern=pattern, string=s):
if outcome == SYNTAX_ERROR: # Expected a syntax error
with self.assertRaises(re.error):
re.compile(pattern)
continue
obj = re.compile(pattern)
result = obj.search(s)
if outcome == FAIL:
self.assertIsNone(result, 'Succeeded incorrectly')
continue
with self.subTest():
self.assertTrue(result, 'Failed incorrectly')
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
start, end = result.span(0)
vardict = {'found': result.group(0),
'groups': result.group(),
'flags': result.re.flags}
for i in range(1, 100):
try:
gi = result.group(i)
# Special hack because else the string concat fails:
if gi is None:
gi = "None"
except IndexError:
gi = "Error"
vardict['g%d' % i] = gi
for i in result.re.groupindex.keys():
try:
gi = result.group(i)
if gi is None:
gi = "None"
except IndexError:
gi = "Error"
vardict[i] = gi
self.assertEqual(eval(repl, vardict), expected,
'grouping error')
# Try the match with both pattern and string converted to
# bytes, and check that it still succeeds.
try:
bpat = bytes(pattern, "ascii")
bs = bytes(s, "ascii")
except UnicodeEncodeError:
# skip non-ascii tests
pass
else:
with self.subTest('bytes pattern match'):
obj = re.compile(bpat)
self.assertTrue(obj.search(bs))
# Try the match with LOCALE enabled, and check that it
# still succeeds.
with self.subTest('locale-sensitive match'):
obj = re.compile(bpat, re.LOCALE)
result = obj.search(bs)
if result is None:
print('=== Fails on locale-sensitive match', t)
# Try the match with the search area limited to the extent
# of the match and see if it still succeeds. \B will
# break (because it won't match at the end or start of a
# string), so we'll ignore patterns that feature it.
if (pattern[:2] != r'\B' and pattern[-2:] != r'\B'
and result is not None):
with self.subTest('range-limited match'):
obj = re.compile(pattern)
self.assertTrue(obj.search(s, start, end + 1))
# Try the match with IGNORECASE enabled, and check that it
# still succeeds.
with self.subTest('case-insensitive match'):
obj = re.compile(pattern, re.IGNORECASE)
self.assertTrue(obj.search(s))
# Try the match with UNICODE locale enabled, and check
# that it still succeeds.
with self.subTest('unicode-sensitive match'):
obj = re.compile(pattern, re.UNICODE)
self.assertTrue(obj.search(s))
if __name__ == "__main__":
unittest.main()
|