PageRenderTime 52ms CodeModel.GetById 23ms RepoModel.GetById 1ms app.codeStats 0ms

/Library/python26/lib/python2.6/test/test_re.py

http://github.com/jyr/MNPP
Python | 822 lines | 783 code | 21 blank | 18 comment | 4 complexity | 4820c250459d4b7bac501fdc4142a345 MD5 | raw file
Possible License(s): LGPL-2.1, Apache-2.0, LGPL-2.0, LGPL-3.0, MPL-2.0-no-copyleft-exception, GPL-2.0, BSD-3-Clause, GPL-3.0, BSD-2-Clause 
    

  1. from test.test_support import verbose, run_unittest, import_module
    2. 

  2. import re
    3. 

  3. from re import Scanner
    4. 

  4. import sys, os, traceback
    5. 

  5. from weakref import proxy
    6. 

  6. 

  7. # Misc tests from Tim Peters' re.doc
    8. 

    9. 

  9. # WARNING: Don't change details in these tests if you don't know
    10. 

  10. # what you're doing. Some of these tests were carefuly modeled to
    11. 

  11. # cover most of the code.
    12. 

  12. 

  13. import unittest
    14. 

  14. 

  15. class ReTests(unittest.TestCase):
    16. 

  16. 

  17.     def test_weakref(self):
    18. 

  18.         s = 'QabbbcR'
    19. 

  19.         x = re.compile('ab+c')
    20. 

  20.         y = proxy(x)
    21. 

  21.         self.assertEqual(x.findall('QabbbcR'), y.findall('QabbbcR'))
    22. 

  22. 

  23.     def test_search_star_plus(self):
    24. 

  24.         self.assertEqual(re.search('x*', 'axx').span(0), (0, 0))
    25. 

  25.         self.assertEqual(re.search('x*', 'axx').span(), (0, 0))
    26. 

  26.         self.assertEqual(re.search('x+', 'axx').span(0), (1, 3))
    27. 

  27.         self.assertEqual(re.search('x+', 'axx').span(), (1, 3))
    28. 

  28.         self.assertEqual(re.search('x', 'aaa'), None)
    29. 

  29.         self.assertEqual(re.match('a*', 'xxx').span(0), (0, 0))
    30. 

  30.         self.assertEqual(re.match('a*', 'xxx').span(), (0, 0))
    31. 

  31.         self.assertEqual(re.match('x*', 'xxxa').span(0), (0, 3))
    32. 

  32.         self.assertEqual(re.match('x*', 'xxxa').span(), (0, 3))
    33. 

  33.         self.assertEqual(re.match('a+', 'xxx'), None)
    34. 

  34. 

  35.     def bump_num(self, matchobj):
    36. 

  36.         int_value = int(matchobj.group(0))
    37. 

  37.         return str(int_value + 1)
    38. 

  38. 

  39.     def test_basic_re_sub(self):
    40. 

  40.         self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x')
    41. 

  41.         self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'),
    42. 

  42.                          '9.3 -3 24x100y')
    43. 

  43.         self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3),
    44. 

  44.                          '9.3 -3 23x99y')
    45. 

  45. 

  46.         self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n')
    47. 

  47.         self.assertEqual(re.sub('.', r"\n", 'x'), '\n')
    48. 

  48. 

  49.         s = r"\1\1"
    50. 

  50.         self.assertEqual(re.sub('(.)', s, 'x'), 'xx')
    51. 

  51.         self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s)
    52. 

  52.         self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s)
    53. 

  53. 

  54.         self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx')
    55. 

  55.         self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx')
    56. 

  56.         self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx')
    57. 

  57.         self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx')
    58. 

  58. 

  59.         self.assertEqual(re.sub('a',r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D','a'),
    60. 

  60.                          '\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D')
    61. 

  61.         self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), '\t\n\v\r\f\a')
    62. 

  62.         self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'),
    63. 

  63.                          (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)))
    64. 

  64. 

  65.         self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest')
    66. 

  66. 

  67.     def test_bug_449964(self):
    68. 

  68.         # fails for group followed by other escape
    69. 

  69.         self.assertEqual(re.sub(r'(?P<unk>x)', '\g<1>\g<1>\\b', 'xx'),
    70. 

  70.                          'xx\bxx\b')
    71. 

  71. 

  72.     def test_bug_449000(self):
    73. 

  73.         # Test for sub() on escaped characters
    74. 

  74.         self.assertEqual(re.sub(r'\r\n', r'\n', 'abc\r\ndef\r\n'),
    75. 

  75.                          'abc\ndef\n')
    76. 

  76.         self.assertEqual(re.sub('\r\n', r'\n', 'abc\r\ndef\r\n'),
    77. 

  77.                          'abc\ndef\n')
    78. 

  78.         self.assertEqual(re.sub(r'\r\n', '\n', 'abc\r\ndef\r\n'),
    79. 

  79.                          'abc\ndef\n')
    80. 

  80.         self.assertEqual(re.sub('\r\n', '\n', 'abc\r\ndef\r\n'),
    81. 

  81.                          'abc\ndef\n')
    82. 

  82. 

  83.     def test_bug_1140(self):
    84. 

  84.         # re.sub(x, y, u'') should return u'', not '', and
    85. 

  85.         # re.sub(x, y, '') should return '', not u''.
    86. 

  86.         # Also:
    87. 

  87.         # re.sub(x, y, unicode(x)) should return unicode(y), and
    88. 

  88.         # re.sub(x, y, str(x)) should return
    89. 

  89.         #     str(y) if isinstance(y, str) else unicode(y).
    90. 

  90.         for x in 'x', u'x':
    91. 

  91.             for y in 'y', u'y':
    92. 

  92.                 z = re.sub(x, y, u'')
    93. 

  93.                 self.assertEqual(z, u'')
    94. 

  94.                 self.assertEqual(type(z), unicode)
    95. 

  95.                 #
    96. 

  96.                 z = re.sub(x, y, '')
    97. 

  97.                 self.assertEqual(z, '')
    98. 

  98.                 self.assertEqual(type(z), str)
    99. 

  99.                 #
    100. 

  100.                 z = re.sub(x, y, unicode(x))
    101. 

  101.                 self.assertEqual(z, y)
    102. 

  102.                 self.assertEqual(type(z), unicode)
    103. 

  103.                 #
    104. 

  104.                 z = re.sub(x, y, str(x))
    105. 

  105.                 self.assertEqual(z, y)
    106. 

  106.                 self.assertEqual(type(z), type(y))
    107. 

  107. 

  108.     def test_bug_1661(self):
    109. 

  109.         # Verify that flags do not get silently ignored with compiled patterns
    110. 

  110.         pattern = re.compile('.')
    111. 

  111.         self.assertRaises(ValueError, re.match, pattern, 'A', re.I)
    112. 

  112.         self.assertRaises(ValueError, re.search, pattern, 'A', re.I)
    113. 

  113.         self.assertRaises(ValueError, re.findall, pattern, 'A', re.I)
    114. 

  114.         self.assertRaises(ValueError, re.compile, pattern, re.I)
    115. 

  115. 

  116.     def test_bug_3629(self):
    117. 

  117.         # A regex that triggered a bug in the sre-code validator
    118. 

  118.         re.compile("(?P<quote>)(?(quote))")
    119. 

  119. 

  120.     def test_sub_template_numeric_escape(self):
    121. 

  121.         # bug 776311 and friends
    122. 

  122.         self.assertEqual(re.sub('x', r'\0', 'x'), '\0')
    123. 

  123.         self.assertEqual(re.sub('x', r'\000', 'x'), '\000')
    124. 

  124.         self.assertEqual(re.sub('x', r'\001', 'x'), '\001')
    125. 

  125.         self.assertEqual(re.sub('x', r'\008', 'x'), '\0' + '8')
    126. 

  126.         self.assertEqual(re.sub('x', r'\009', 'x'), '\0' + '9')
    127. 

  127.         self.assertEqual(re.sub('x', r'\111', 'x'), '\111')
    128. 

  128.         self.assertEqual(re.sub('x', r'\117', 'x'), '\117')
    129. 

  129. 

  130.         self.assertEqual(re.sub('x', r'\1111', 'x'), '\1111')
    131. 

  131.         self.assertEqual(re.sub('x', r'\1111', 'x'), '\111' + '1')
    132. 

  132. 

  133.         self.assertEqual(re.sub('x', r'\00', 'x'), '\x00')
    134. 

  134.         self.assertEqual(re.sub('x', r'\07', 'x'), '\x07')
    135. 

  135.         self.assertEqual(re.sub('x', r'\08', 'x'), '\0' + '8')
    136. 

  136.         self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9')
    137. 

  137.         self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a')
    138. 

  138. 

  139.         self.assertEqual(re.sub('x', r'\400', 'x'), '\0')
    140. 

  140.         self.assertEqual(re.sub('x', r'\777', 'x'), '\377')
    141. 

  141. 

  142.         self.assertRaises(re.error, re.sub, 'x', r'\1', 'x')
    143. 

  143.         self.assertRaises(re.error, re.sub, 'x', r'\8', 'x')
    144. 

  144.         self.assertRaises(re.error, re.sub, 'x', r'\9', 'x')
    145. 

  145.         self.assertRaises(re.error, re.sub, 'x', r'\11', 'x')
    146. 

  146.         self.assertRaises(re.error, re.sub, 'x', r'\18', 'x')
    147. 

  147.         self.assertRaises(re.error, re.sub, 'x', r'\1a', 'x')
    148. 

  148.         self.assertRaises(re.error, re.sub, 'x', r'\90', 'x')
    149. 

  149.         self.assertRaises(re.error, re.sub, 'x', r'\99', 'x')
    150. 

  150.         self.assertRaises(re.error, re.sub, 'x', r'\118', 'x') # r'\11' + '8'
    151. 

  151.         self.assertRaises(re.error, re.sub, 'x', r'\11a', 'x')
    152. 

  152.         self.assertRaises(re.error, re.sub, 'x', r'\181', 'x') # r'\18' + '1'
    153. 

  153.         self.assertRaises(re.error, re.sub, 'x', r'\800', 'x') # r'\80' + '0'
    154. 

  154. 

  155.         # in python2.3 (etc), these loop endlessly in sre_parser.py
    156. 

  156.         self.assertEqual(re.sub('(((((((((((x)))))))))))', r'\11', 'x'), 'x')
    157. 

  157.         self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\118', 'xyz'),
    158. 

  158.                          'xz8')
    159. 

  159.         self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\11a', 'xyz'),
    160. 

  160.                          'xza')
    161. 

  161. 

  162.     def test_qualified_re_sub(self):
    163. 

  163.         self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb')
    164. 

  164.         self.assertEqual(re.sub('a', 'b', 'aaaaa', 1), 'baaaa')
    165. 

  165. 

  166.     def test_bug_114660(self):
    167. 

  167.         self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello  there'),
    168. 

  168.                          'hello there')
    169. 

  169. 

  170.     def test_bug_462270(self):
    171. 

  171.         # Test for empty sub() behaviour, see SF bug #462270
    172. 

  172.         self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-')
    173. 

  173.         self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d')
    174. 

  174. 

  175.     def test_symbolic_refs(self):
    176. 

  176.         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a', 'xx')
    177. 

  177.         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<', 'xx')
    178. 

  178.         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g', 'xx')
    179. 

  179.         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a a>', 'xx')
    180. 

  180.         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<1a1>', 'xx')
    181. 

  181.         self.assertRaises(IndexError, re.sub, '(?P<a>x)', '\g<ab>', 'xx')
    182. 

  182.         self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\g<b>', 'xx')
    183. 

  183.         self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\\2', 'xx')
    184. 

  184.         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<-1>', 'xx')
    185. 

  185. 

  186.     def test_re_subn(self):
    187. 

  187.         self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2))
    188. 

  188.         self.assertEqual(re.subn("b+", "x", "bbbb BBBB"), ('x BBBB', 1))
    189. 

  189.         self.assertEqual(re.subn("b+", "x", "xyz"), ('xyz', 0))
    190. 

  190.         self.assertEqual(re.subn("b*", "x", "xyz"), ('xxxyxzx', 4))
    191. 

  191.         self.assertEqual(re.subn("b*", "x", "xyz", 2), ('xxxyz', 2))
    192. 

  192. 

  193.     def test_re_split(self):
    194. 

  194.         self.assertEqual(re.split(":", ":a:b::c"), ['', 'a', 'b', '', 'c'])
    195. 

  195.         self.assertEqual(re.split(":*", ":a:b::c"), ['', 'a', 'b', 'c'])
    196. 

  196.         self.assertEqual(re.split("(:*)", ":a:b::c"),
    197. 

  197.                          ['', ':', 'a', ':', 'b', '::', 'c'])
    198. 

  198.         self.assertEqual(re.split("(?::*)", ":a:b::c"), ['', 'a', 'b', 'c'])
    199. 

  199.         self.assertEqual(re.split("(:)*", ":a:b::c"),
    200. 

  200.                          ['', ':', 'a', ':', 'b', ':', 'c'])
    201. 

  201.         self.assertEqual(re.split("([b:]+)", ":a:b::c"),
    202. 

  202.                          ['', ':', 'a', ':b::', 'c'])
    203. 

  203.         self.assertEqual(re.split("(b)|(:+)", ":a:b::c"),
    204. 

  204.                          ['', None, ':', 'a', None, ':', '', 'b', None, '',
    205. 

  205.                           None, '::', 'c'])
    206. 

  206.         self.assertEqual(re.split("(?:b)|(?::+)", ":a:b::c"),
    207. 

  207.                          ['', 'a', '', '', 'c'])
    208. 

  208. 

  209.     def test_qualified_re_split(self):
    210. 

  210.         self.assertEqual(re.split(":", ":a:b::c", 2), ['', 'a', 'b::c'])
    211. 

  211.         self.assertEqual(re.split(':', 'a:b:c:d', 2), ['a', 'b', 'c:d'])
    212. 

  212.         self.assertEqual(re.split("(:)", ":a:b::c", 2),
    213. 

  213.                          ['', ':', 'a', ':', 'b::c'])
    214. 

  214.         self.assertEqual(re.split("(:*)", ":a:b::c", 2),
    215. 

  215.                          ['', ':', 'a', ':', 'b::c'])
    216. 

  216. 

  217.     def test_re_findall(self):
    218. 

  218.         self.assertEqual(re.findall(":+", "abc"), [])
    219. 

  219.         self.assertEqual(re.findall(":+", "a:b::c:::d"), [":", "::", ":::"])
    220. 

  220.         self.assertEqual(re.findall("(:+)", "a:b::c:::d"), [":", "::", ":::"])
    221. 

  221.         self.assertEqual(re.findall("(:)(:*)", "a:b::c:::d"), [(":", ""),
    222. 

  222.                                                                (":", ":"),
    223. 

  223.                                                                (":", "::")])
    224. 

  224. 

  225.     def test_bug_117612(self):
    226. 

  226.         self.assertEqual(re.findall(r"(a|(b))", "aba"),
    227. 

  227.                          [("a", ""),("b", "b"),("a", "")])
    228. 

  228. 

  229.     def test_re_match(self):
    230. 

  230.         self.assertEqual(re.match('a', 'a').groups(), ())
    231. 

  231.         self.assertEqual(re.match('(a)', 'a').groups(), ('a',))
    232. 

  232.         self.assertEqual(re.match(r'(a)', 'a').group(0), 'a')
    233. 

  233.         self.assertEqual(re.match(r'(a)', 'a').group(1), 'a')
    234. 

  234.         self.assertEqual(re.match(r'(a)', 'a').group(1, 1), ('a', 'a'))
    235. 

  235. 

  236.         pat = re.compile('((a)|(b))(c)?')
    237. 

  237.         self.assertEqual(pat.match('a').groups(), ('a', 'a', None, None))
    238. 

  238.         self.assertEqual(pat.match('b').groups(), ('b', None, 'b', None))
    239. 

  239.         self.assertEqual(pat.match('ac').groups(), ('a', 'a', None, 'c'))
    240. 

  240.         self.assertEqual(pat.match('bc').groups(), ('b', None, 'b', 'c'))
    241. 

  241.         self.assertEqual(pat.match('bc').groups(""), ('b', "", 'b', 'c'))
    242. 

  242. 

  243.         # A single group
    244. 

  244.         m = re.match('(a)', 'a')
    245. 

  245.         self.assertEqual(m.group(0), 'a')
    246. 

  246.         self.assertEqual(m.group(0), 'a')
    247. 

  247.         self.assertEqual(m.group(1), 'a')
    248. 

  248.         self.assertEqual(m.group(1, 1), ('a', 'a'))
    249. 

  249. 

  250.         pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?')
    251. 

  251.         self.assertEqual(pat.match('a').group(1, 2, 3), ('a', None, None))
    252. 

  252.         self.assertEqual(pat.match('b').group('a1', 'b2', 'c3'),
    253. 

  253.                          (None, 'b', None))
    254. 

  254.         self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c'))
    255. 

  255. 

  256.     def test_re_groupref_exists(self):
    257. 

  257.         self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
    258. 

  258.                          ('(', 'a'))
    259. 

  259.         self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(),
    260. 

  260.                          (None, 'a'))
    261. 

  261.         self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'), None)
    262. 

  262.         self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a'), None)
    263. 

  263.         self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(),
    264. 

  264.                          ('a', 'b'))
    265. 

  265.         self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(),
    266. 

  266.                          (None, 'd'))
    267. 

  267.         self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(),
    268. 

  268.                          (None, 'd'))
    269. 

  269.         self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(),
    270. 

  270.                          ('a', ''))
    271. 

  271. 

  272.         # Tests for bug #1177831: exercise groups other than the first group
    273. 

  273.         p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
    274. 

  274.         self.assertEqual(p.match('abc').groups(),
    275. 

  275.                          ('a', 'b', 'c'))
    276. 

  276.         self.assertEqual(p.match('ad').groups(),
    277. 

  277.                          ('a', None, 'd'))
    278. 

  278.         self.assertEqual(p.match('abd'), None)
    279. 

  279.         self.assertEqual(p.match('ac'), None)
    280. 

  280. 

  281. 

  282.     def test_re_groupref(self):
    283. 

  283.         self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(),
    284. 

  284.                          ('|', 'a'))
    285. 

  285.         self.assertEqual(re.match(r'^(\|)?([^()]+)\1?$', 'a').groups(),
    286. 

  286.                          (None, 'a'))
    287. 

  287.         self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', 'a|'), None)
    288. 

  288.         self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a'), None)
    289. 

  289.         self.assertEqual(re.match(r'^(?:(a)|c)(\1)$', 'aa').groups(),
    290. 

  290.                          ('a', 'a'))
    291. 

  291.         self.assertEqual(re.match(r'^(?:(a)|c)(\1)?$', 'c').groups(),
    292. 

  292.                          (None, None))
    293. 

  293. 

  294.     def test_groupdict(self):
    295. 

  295.         self.assertEqual(re.match('(?P<first>first) (?P<second>second)',
    296. 

  296.                                   'first second').groupdict(),
    297. 

  297.                          {'first':'first', 'second':'second'})
    298. 

  298. 

  299.     def test_expand(self):
    300. 

  300.         self.assertEqual(re.match("(?P<first>first) (?P<second>second)",
    301. 

  301.                                   "first second")
    302. 

  302.                                   .expand(r"\2 \1 \g<second> \g<first>"),
    303. 

  303.                          "second first second first")
    304. 

  304. 

  305.     def test_repeat_minmax(self):
    306. 

  306.         self.assertEqual(re.match("^(\w){1}$", "abc"), None)
    307. 

  307.         self.assertEqual(re.match("^(\w){1}?$", "abc"), None)
    308. 

  308.         self.assertEqual(re.match("^(\w){1,2}$", "abc"), None)
    309. 

  309.         self.assertEqual(re.match("^(\w){1,2}?$", "abc"), None)
    310. 

  310. 

  311.         self.assertEqual(re.match("^(\w){3}$", "abc").group(1), "c")
    312. 

  312.         self.assertEqual(re.match("^(\w){1,3}$", "abc").group(1), "c")
    313. 

  313.         self.assertEqual(re.match("^(\w){1,4}$", "abc").group(1), "c")
    314. 

  314.         self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
    315. 

  315.         self.assertEqual(re.match("^(\w){3}?$", "abc").group(1), "c")
    316. 

  316.         self.assertEqual(re.match("^(\w){1,3}?$", "abc").group(1), "c")
    317. 

  317.         self.assertEqual(re.match("^(\w){1,4}?$", "abc").group(1), "c")
    318. 

  318.         self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
    319. 

  319. 

  320.         self.assertEqual(re.match("^x{1}$", "xxx"), None)
    321. 

  321.         self.assertEqual(re.match("^x{1}?$", "xxx"), None)
    322. 

  322.         self.assertEqual(re.match("^x{1,2}$", "xxx"), None)
    323. 

  323.         self.assertEqual(re.match("^x{1,2}?$", "xxx"), None)
    324. 

  324. 

  325.         self.assertNotEqual(re.match("^x{3}$", "xxx"), None)
    326. 

  326.         self.assertNotEqual(re.match("^x{1,3}$", "xxx"), None)
    327. 

  327.         self.assertNotEqual(re.match("^x{1,4}$", "xxx"), None)
    328. 

  328.         self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None)
    329. 

  329.         self.assertNotEqual(re.match("^x{3}?$", "xxx"), None)
    330. 

  330.         self.assertNotEqual(re.match("^x{1,3}?$", "xxx"), None)
    331. 

  331.         self.assertNotEqual(re.match("^x{1,4}?$", "xxx"), None)
    332. 

  332.         self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None)
    333. 

  333. 

  334.         self.assertEqual(re.match("^x{}$", "xxx"), None)
    335. 

  335.         self.assertNotEqual(re.match("^x{}$", "x{}"), None)
    336. 

  336. 

  337.     def test_getattr(self):
    338. 

  338.         self.assertEqual(re.match("(a)", "a").pos, 0)
    339. 

  339.         self.assertEqual(re.match("(a)", "a").endpos, 1)
    340. 

  340.         self.assertEqual(re.match("(a)", "a").string, "a")
    341. 

  341.         self.assertEqual(re.match("(a)", "a").regs, ((0, 1), (0, 1)))
    342. 

  342.         self.assertNotEqual(re.match("(a)", "a").re, None)
    343. 

  343. 

  344.     def test_special_escapes(self):
    345. 

  345.         self.assertEqual(re.search(r"\b(b.)\b",
    346. 

  346.                                    "abcd abc bcd bx").group(1), "bx")
    347. 

  347.         self.assertEqual(re.search(r"\B(b.)\B",
    348. 

  348.                                    "abc bcd bc abxd").group(1), "bx")
    349. 

  349.         self.assertEqual(re.search(r"\b(b.)\b",
    350. 

  350.                                    "abcd abc bcd bx", re.LOCALE).group(1), "bx")
    351. 

  351.         self.assertEqual(re.search(r"\B(b.)\B",
    352. 

  352.                                    "abc bcd bc abxd", re.LOCALE).group(1), "bx")
    353. 

  353.         self.assertEqual(re.search(r"\b(b.)\b",
    354. 

  354.                                    "abcd abc bcd bx", re.UNICODE).group(1), "bx")
    355. 

  355.         self.assertEqual(re.search(r"\B(b.)\B",
    356. 

  356.                                    "abc bcd bc abxd", re.UNICODE).group(1), "bx")
    357. 

  357.         self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc")
    358. 

  358.         self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc")
    359. 

  359.         self.assertEqual(re.search(r"^\Aabc\Z$", "\nabc\n", re.M), None)
    360. 

  360.         self.assertEqual(re.search(r"\b(b.)\b",
    361. 

  361.                                    u"abcd abc bcd bx").group(1), "bx")
    362. 

  362.         self.assertEqual(re.search(r"\B(b.)\B",
    363. 

  363.                                    u"abc bcd bc abxd").group(1), "bx")
    364. 

  364.         self.assertEqual(re.search(r"^abc$", u"\nabc\n", re.M).group(0), "abc")
    365. 

  365.         self.assertEqual(re.search(r"^\Aabc\Z$", u"abc", re.M).group(0), "abc")
    366. 

  366.         self.assertEqual(re.search(r"^\Aabc\Z$", u"\nabc\n", re.M), None)
    367. 

  367.         self.assertEqual(re.search(r"\d\D\w\W\s\S",
    368. 

  368.                                    "1aa! a").group(0), "1aa! a")
    369. 

  369.         self.assertEqual(re.search(r"\d\D\w\W\s\S",
    370. 

  370.                                    "1aa! a", re.LOCALE).group(0), "1aa! a")
    371. 

  371.         self.assertEqual(re.search(r"\d\D\w\W\s\S",
    372. 

  372.                                    "1aa! a", re.UNICODE).group(0), "1aa! a")
    373. 

  373. 

  374.     def test_bigcharset(self):
    375. 

  375.         self.assertEqual(re.match(u"([\u2222\u2223])",
    376. 

  376.                                   u"\u2222").group(1), u"\u2222")
    377. 

  377.         self.assertEqual(re.match(u"([\u2222\u2223])",
    378. 

  378.                                   u"\u2222", re.UNICODE).group(1), u"\u2222")
    379. 

  379. 

  380.     def test_anyall(self):
    381. 

  381.         self.assertEqual(re.match("a.b", "a\nb", re.DOTALL).group(0),
    382. 

  382.                          "a\nb")
    383. 

  383.         self.assertEqual(re.match("a.*b", "a\n\nb", re.DOTALL).group(0),
    384. 

  384.                          "a\n\nb")
    385. 

  385. 

  386.     def test_non_consuming(self):
    387. 

  387.         self.assertEqual(re.match("(a(?=\s[^a]))", "a b").group(1), "a")
    388. 

  388.         self.assertEqual(re.match("(a(?=\s[^a]*))", "a b").group(1), "a")
    389. 

  389.         self.assertEqual(re.match("(a(?=\s[abc]))", "a b").group(1), "a")
    390. 

  390.         self.assertEqual(re.match("(a(?=\s[abc]*))", "a bc").group(1), "a")
    391. 

  391.         self.assertEqual(re.match(r"(a)(?=\s\1)", "a a").group(1), "a")
    392. 

  392.         self.assertEqual(re.match(r"(a)(?=\s\1*)", "a aa").group(1), "a")
    393. 

  393.         self.assertEqual(re.match(r"(a)(?=\s(abc|a))", "a a").group(1), "a")
    394. 

  394. 

  395.         self.assertEqual(re.match(r"(a(?!\s[^a]))", "a a").group(1), "a")
    396. 

  396.         self.assertEqual(re.match(r"(a(?!\s[abc]))", "a d").group(1), "a")
    397. 

  397.         self.assertEqual(re.match(r"(a)(?!\s\1)", "a b").group(1), "a")
    398. 

  398.         self.assertEqual(re.match(r"(a)(?!\s(abc|a))", "a b").group(1), "a")
    399. 

  399. 

  400.     def test_ignore_case(self):
    401. 

  401.         self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
    402. 

  402.         self.assertEqual(re.match("abc", u"ABC", re.I).group(0), "ABC")
    403. 

  403.         self.assertEqual(re.match(r"(a\s[^a])", "a b", re.I).group(1), "a b")
    404. 

  404.         self.assertEqual(re.match(r"(a\s[^a]*)", "a bb", re.I).group(1), "a bb")
    405. 

  405.         self.assertEqual(re.match(r"(a\s[abc])", "a b", re.I).group(1), "a b")
    406. 

  406.         self.assertEqual(re.match(r"(a\s[abc]*)", "a bb", re.I).group(1), "a bb")
    407. 

  407.         self.assertEqual(re.match(r"((a)\s\2)", "a a", re.I).group(1), "a a")
    408. 

  408.         self.assertEqual(re.match(r"((a)\s\2*)", "a aa", re.I).group(1), "a aa")
    409. 

  409.         self.assertEqual(re.match(r"((a)\s(abc|a))", "a a", re.I).group(1), "a a")
    410. 

  410.         self.assertEqual(re.match(r"((a)\s(abc|a)*)", "a aa", re.I).group(1), "a aa")
    411. 

  411. 

  412.     def test_category(self):
    413. 

  413.         self.assertEqual(re.match(r"(\s)", " ").group(1), " ")
    414. 

  414. 

  415.     def test_getlower(self):
    416. 

  416.         import _sre
    417. 

  417.         self.assertEqual(_sre.getlower(ord('A'), 0), ord('a'))
    418. 

  418.         self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a'))
    419. 

  419.         self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a'))
    420. 

  420. 

  421.         self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
    422. 

  422.         self.assertEqual(re.match("abc", u"ABC", re.I).group(0), "ABC")
    423. 

  423. 

  424.     def test_not_literal(self):
    425. 

  425.         self.assertEqual(re.search("\s([^a])", " b").group(1), "b")
    426. 

  426.         self.assertEqual(re.search("\s([^a]*)", " bb").group(1), "bb")
    427. 

  427. 

  428.     def test_search_coverage(self):
    429. 

  429.         self.assertEqual(re.search("\s(b)", " b").group(1), "b")
    430. 

  430.         self.assertEqual(re.search("a\s", "a ").group(0), "a ")
    431. 

  431. 

  432.     def test_re_escape(self):
    433. 

  433.         p=""
    434. 

  434.         for i in range(0, 256):
    435. 

  435.             p = p + chr(i)
    436. 

  436.             self.assertEqual(re.match(re.escape(chr(i)), chr(i)) is not None,
    437. 

  437.                              True)
    438. 

  438.             self.assertEqual(re.match(re.escape(chr(i)), chr(i)).span(), (0,1))
    439. 

  439. 

  440.         pat=re.compile(re.escape(p))
    441. 

  441.         self.assertEqual(pat.match(p) is not None, True)
    442. 

  442.         self.assertEqual(pat.match(p).span(), (0,256))
    443. 

  443. 

  444.     def test_pickling(self):
    445. 

  445.         import pickle
    446. 

  446.         self.pickle_test(pickle)
    447. 

  447.         import cPickle
    448. 

  448.         self.pickle_test(cPickle)
    449. 

  449.         # old pickles expect the _compile() reconstructor in sre module
    450. 

  450.         import_module("sre", deprecated=True)
    451. 

  451.         from sre import _compile
    452. 

  452. 

  453.     def pickle_test(self, pickle):
    454. 

  454.         oldpat = re.compile('a(?:b|(c|e){1,2}?|d)+?(.)')
    455. 

  455.         s = pickle.dumps(oldpat)
    456. 

  456.         newpat = pickle.loads(s)
    457. 

  457.         self.assertEqual(oldpat, newpat)
    458. 

  458. 

  459.     def test_constants(self):
    460. 

  460.         self.assertEqual(re.I, re.IGNORECASE)
    461. 

  461.         self.assertEqual(re.L, re.LOCALE)
    462. 

  462.         self.assertEqual(re.M, re.MULTILINE)
    463. 

  463.         self.assertEqual(re.S, re.DOTALL)
    464. 

  464.         self.assertEqual(re.X, re.VERBOSE)
    465. 

  465. 

  466.     def test_flags(self):
    467. 

  467.         for flag in [re.I, re.M, re.X, re.S, re.L]:
    468. 

  468.             self.assertNotEqual(re.compile('^pattern$', flag), None)
    469. 

  469. 

  470.     def test_sre_character_literals(self):
    471. 

  471.         for i in [0, 8, 16, 32, 64, 127, 128, 255]:
    472. 

  472.             self.assertNotEqual(re.match(r"\%03o" % i, chr(i)), None)
    473. 

  473.             self.assertNotEqual(re.match(r"\%03o0" % i, chr(i)+"0"), None)
    474. 

  474.             self.assertNotEqual(re.match(r"\%03o8" % i, chr(i)+"8"), None)
    475. 

  475.             self.assertNotEqual(re.match(r"\x%02x" % i, chr(i)), None)
    476. 

  476.             self.assertNotEqual(re.match(r"\x%02x0" % i, chr(i)+"0"), None)
    477. 

  477.             self.assertNotEqual(re.match(r"\x%02xz" % i, chr(i)+"z"), None)
    478. 

  478.         self.assertRaises(re.error, re.match, "\911", "")
    479. 

  479. 

  480.     def test_sre_character_class_literals(self):
    481. 

  481.         for i in [0, 8, 16, 32, 64, 127, 128, 255]:
    482. 

  482.             self.assertNotEqual(re.match(r"[\%03o]" % i, chr(i)), None)
    483. 

  483.             self.assertNotEqual(re.match(r"[\%03o0]" % i, chr(i)), None)
    484. 

  484.             self.assertNotEqual(re.match(r"[\%03o8]" % i, chr(i)), None)
    485. 

  485.             self.assertNotEqual(re.match(r"[\x%02x]" % i, chr(i)), None)
    486. 

  486.             self.assertNotEqual(re.match(r"[\x%02x0]" % i, chr(i)), None)
    487. 

  487.             self.assertNotEqual(re.match(r"[\x%02xz]" % i, chr(i)), None)
    488. 

  488.         self.assertRaises(re.error, re.match, "[\911]", "")
    489. 

  489. 

  490.     def test_bug_113254(self):
    491. 

  491.         self.assertEqual(re.match(r'(a)|(b)', 'b').start(1), -1)
    492. 

  492.         self.assertEqual(re.match(r'(a)|(b)', 'b').end(1), -1)
    493. 

  493.         self.assertEqual(re.match(r'(a)|(b)', 'b').span(1), (-1, -1))
    494. 

  494. 

  495.     def test_bug_527371(self):
    496. 

  496.         # bug described in patches 527371/672491
    497. 

  497.         self.assertEqual(re.match(r'(a)?a','a').lastindex, None)
    498. 

  498.         self.assertEqual(re.match(r'(a)(b)?b','ab').lastindex, 1)
    499. 

  499.         self.assertEqual(re.match(r'(?P<a>a)(?P<b>b)?b','ab').lastgroup, 'a')
    500. 

  500.         self.assertEqual(re.match("(?P<a>a(b))", "ab").lastgroup, 'a')
    501. 

  501.         self.assertEqual(re.match("((a))", "a").lastindex, 1)
    502. 

  502. 

  503.     def test_bug_545855(self):
    504. 

  504.         # bug 545855 -- This pattern failed to cause a compile error as it
    505. 

  505.         # should, instead provoking a TypeError.
    506. 

  506.         self.assertRaises(re.error, re.compile, 'foo[a-')
    507. 

  507. 

  508.     def test_bug_418626(self):
    509. 

  509.         # bugs 418626 at al. -- Testing Greg Chapman's addition of op code
    510. 

  510.         # SRE_OP_MIN_REPEAT_ONE for eliminating recursion on simple uses of
    511. 

  511.         # pattern '*?' on a long string.
    512. 

  512.         self.assertEqual(re.match('.*?c', 10000*'ab'+'cd').end(0), 20001)
    513. 

  513.         self.assertEqual(re.match('.*?cd', 5000*'ab'+'c'+5000*'ab'+'cde').end(0),
    514. 

  514.                          20003)
    515. 

  515.         self.assertEqual(re.match('.*?cd', 20000*'abc'+'de').end(0), 60001)
    516. 

  516.         # non-simple '*?' still used to hit the recursion limit, before the
    517. 

  517.         # non-recursive scheme was implemented.
    518. 

  518.         self.assertEqual(re.search('(a|b)*?c', 10000*'ab'+'cd').end(0), 20001)
    519. 

  519. 

  520.     def test_bug_612074(self):
    521. 

  521.         pat=u"["+re.escape(u"\u2039")+u"]"
    522. 

  522.         self.assertEqual(re.compile(pat) and 1, 1)
    523. 

  523. 

  524.     def test_stack_overflow(self):
    525. 

  525.         # nasty cases that used to overflow the straightforward recursive
    526. 

  526.         # implementation of repeated groups.
    527. 

  527.         self.assertEqual(re.match('(x)*', 50000*'x').group(1), 'x')
    528. 

  528.         self.assertEqual(re.match('(x)*y', 50000*'x'+'y').group(1), 'x')
    529. 

  529.         self.assertEqual(re.match('(x)*?y', 50000*'x'+'y').group(1), 'x')
    530. 

  530. 

  531.     def test_scanner(self):
    532. 

  532.         def s_ident(scanner, token): return token
    533. 

  533.         def s_operator(scanner, token): return "op%s" % token
    534. 

  534.         def s_float(scanner, token): return float(token)
    535. 

  535.         def s_int(scanner, token): return int(token)
    536. 

  536. 

  537.         scanner = Scanner([
    538. 

  538.             (r"[a-zA-Z_]\w*", s_ident),
    539. 

  539.             (r"\d+\.\d*", s_float),
    540. 

  540.             (r"\d+", s_int),
    541. 

  541.             (r"=|\+|-|\*|/", s_operator),
    542. 

  542.             (r"\s+", None),
    543. 

  543.             ])
    544. 

  544. 

  545.         self.assertNotEqual(scanner.scanner.scanner("").pattern, None)
    546. 

  546. 

  547.         self.assertEqual(scanner.scan("sum = 3*foo + 312.50 + bar"),
    548. 

  548.                          (['sum', 'op=', 3, 'op*', 'foo', 'op+', 312.5,
    549. 

  549.                            'op+', 'bar'], ''))
    550. 

  550. 

  551.     def test_bug_448951(self):
    552. 

  552.         # bug 448951 (similar to 429357, but with single char match)
    553. 

  553.         # (Also test greedy matches.)
    554. 

  554.         for op in '','?','*':
    555. 

  555.             self.assertEqual(re.match(r'((.%s):)?z'%op, 'z').groups(),
    556. 

  556.                              (None, None))
    557. 

  557.             self.assertEqual(re.match(r'((.%s):)?z'%op, 'a:z').groups(),
    558. 

  558.                              ('a:', 'a'))
    559. 

  559. 

  560.     def test_bug_725106(self):
    561. 

  561.         # capturing groups in alternatives in repeats
    562. 

  562.         self.assertEqual(re.match('^((a)|b)*', 'abc').groups(),
    563. 

  563.                          ('b', 'a'))
    564. 

  564.         self.assertEqual(re.match('^(([ab])|c)*', 'abc').groups(),
    565. 

  565.                          ('c', 'b'))
    566. 

  566.         self.assertEqual(re.match('^((d)|[ab])*', 'abc').groups(),
    567. 

  567.                          ('b', None))
    568. 

  568.         self.assertEqual(re.match('^((a)c|[ab])*', 'abc').groups(),
    569. 

  569.                          ('b', None))
    570. 

  570.         self.assertEqual(re.match('^((a)|b)*?c', 'abc').groups(),
    571. 

  571.                          ('b', 'a'))
    572. 

  572.         self.assertEqual(re.match('^(([ab])|c)*?d', 'abcd').groups(),
    573. 

  573.                          ('c', 'b'))
    574. 

  574.         self.assertEqual(re.match('^((d)|[ab])*?c', 'abc').groups(),
    575. 

  575.                          ('b', None))
    576. 

  576.         self.assertEqual(re.match('^((a)c|[ab])*?c', 'abc').groups(),
    577. 

  577.                          ('b', None))
    578. 

  578. 

  579.     def test_bug_725149(self):
    580. 

  580.         # mark_stack_base restoring before restoring marks
    581. 

  581.         self.assertEqual(re.match('(a)(?:(?=(b)*)c)*', 'abb').groups(),
    582. 

  582.                          ('a', None))
    583. 

  583.         self.assertEqual(re.match('(a)((?!(b)*))*', 'abb').groups(),
    584. 

  584.                          ('a', None, None))
    585. 

  585. 

  586.     def test_bug_764548(self):
    587. 

  587.         # bug 764548, re.compile() barfs on str/unicode subclasses
    588. 

  588.         try:
    589. 

  589.             unicode
    590. 

  590.         except NameError:
    591. 

  591.             return  # no problem if we have no unicode
    592. 

  592.         class my_unicode(unicode): pass
    593. 

  593.         pat = re.compile(my_unicode("abc"))
    594. 

  594.         self.assertEqual(pat.match("xyz"), None)
    595. 

  595. 

  596.     def test_finditer(self):
    597. 

  597.         iter = re.finditer(r":+", "a:b::c:::d")
    598. 

  598.         self.assertEqual([item.group(0) for item in iter],
    599. 

  599.                          [":", "::", ":::"])
    600. 

  600. 

  601.     def test_bug_926075(self):
    602. 

  602.         try:
    603. 

  603.             unicode
    604. 

  604.         except NameError:
    605. 

  605.             return # no problem if we have no unicode
    606. 

  606.         self.assert_(re.compile('bug_926075') is not
    607. 

  607.                      re.compile(eval("u'bug_926075'")))
    608. 

  608. 

  609.     def test_bug_931848(self):
    610. 

  610.         try:
    611. 

  611.             unicode
    612. 

  612.         except NameError:
    613. 

  613.             pass
    614. 

  614.         pattern = eval('u"[\u002E\u3002\uFF0E\uFF61]"')
    615. 

  615.         self.assertEqual(re.compile(pattern).split("a.b.c"),
    616. 

  616.                          ['a','b','c'])
    617. 

  617. 

  618.     def test_bug_581080(self):
    619. 

  619.         iter = re.finditer(r"\s", "a b")
    620. 

  620.         self.assertEqual(iter.next().span(), (1,2))
    621. 

  621.         self.assertRaises(StopIteration, iter.next)
    622. 

  622. 

  623.         scanner = re.compile(r"\s").scanner("a b")
    624. 

  624.         self.assertEqual(scanner.search().span(), (1, 2))
    625. 

  625.         self.assertEqual(scanner.search(), None)
    626. 

  626. 

  627.     def test_bug_817234(self):
    628. 

  628.         iter = re.finditer(r".*", "asdf")
    629. 

  629.         self.assertEqual(iter.next().span(), (0, 4))
    630. 

  630.         self.assertEqual(iter.next().span(), (4, 4))
    631. 

  631.         self.assertRaises(StopIteration, iter.next)
    632. 

  632. 

  633.     def test_empty_array(self):
    634. 

  634.         # SF buf 1647541
    635. 

  635.         import array
    636. 

  636.         for typecode in 'cbBuhHiIlLfd':
    637. 

  637.             a = array.array(typecode)
    638. 

  638.             self.assertEqual(re.compile("bla").match(a), None)
    639. 

  639.             self.assertEqual(re.compile("").match(a).groups(), ())
    640. 

  640. 

  641.     def test_inline_flags(self):
    642. 

  642.         # Bug #1700
    643. 

  643.         upper_char = unichr(0x1ea0) # Latin Capital Letter A with Dot Bellow
    644. 

  644.         lower_char = unichr(0x1ea1) # Latin Small Letter A with Dot Bellow
    645. 

  645. 

  646.         p = re.compile(upper_char, re.I | re.U)
    647. 

  647.         q = p.match(lower_char)
    648. 

  648.         self.assertNotEqual(q, None)
    649. 

  649. 

  650.         p = re.compile(lower_char, re.I | re.U)
    651. 

  651.         q = p.match(upper_char)
    652. 

  652.         self.assertNotEqual(q, None)
    653. 

  653. 

  654.         p = re.compile('(?i)' + upper_char, re.U)
    655. 

  655.         q = p.match(lower_char)
    656. 

  656.         self.assertNotEqual(q, None)
    657. 

  657. 

  658.         p = re.compile('(?i)' + lower_char, re.U)
    659. 

  659.         q = p.match(upper_char)
    660. 

  660.         self.assertNotEqual(q, None)
    661. 

  661. 

  662.         p = re.compile('(?iu)' + upper_char)
    663. 

  663.         q = p.match(lower_char)
    664. 

  664.         self.assertNotEqual(q, None)
    665. 

  665. 

  666.         p = re.compile('(?iu)' + lower_char)
    667. 

  667.         q = p.match(upper_char)
    668. 

  668.         self.assertNotEqual(q, None)
    669. 

  669. 

  670.     def test_dollar_matches_twice(self):
    671. 

  671.         "$ matches the end of string, and just before the terminating \n"
    672. 

  672.         pattern = re.compile('$')
    673. 

  673.         self.assertEqual(pattern.sub('#', 'a\nb\n'), 'a\nb#\n#')
    674. 

  674.         self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a\nb\nc#')
    675. 

  675.         self.assertEqual(pattern.sub('#', '\n'), '#\n#')
    676. 

  676. 

  677.         pattern = re.compile('$', re.MULTILINE)
    678. 

  678.         self.assertEqual(pattern.sub('#', 'a\nb\n' ), 'a#\nb#\n#' )
    679. 

  679.         self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a#\nb#\nc#')
    680. 

  680.         self.assertEqual(pattern.sub('#', '\n'), '#\n#')
    681. 

  681. 

  682.     def test_dealloc(self):
    683. 

  683.         # issue 3299: check for segfault in debug build
    684. 

  684.         import _sre
    685. 

  685.         # the overflow limit is different on wide and narrow builds and it
    686. 

  686.         # depends on the definition of SRE_CODE (see sre.h).
    687. 

  687.         # 2**128 should be big enough to overflow on both. For smaller values
    688. 

  688.         # a RuntimeError is raised instead of OverflowError.
    689. 

  689.         long_overflow = 2**128
    690. 

  690.         self.assertRaises(TypeError, re.finditer, "a", {})
    691. 

  691.         self.assertRaises(OverflowError, _sre.compile, "abc", 0, [long_overflow])
    692. 

  692. 

  693. def run_re_tests():
    694. 

  694.     from test.re_tests import benchmarks, tests, SUCCEED, FAIL, SYNTAX_ERROR
    695. 

  695.     if verbose:
    696. 

  696.         print 'Running re_tests test suite'
    697. 

  697.     else:
    698. 

  698.         # To save time, only run the first and last 10 tests
    699. 

  699.         #tests = tests[:10] + tests[-10:]
    700. 

  700.         pass
    701. 

  701. 

  702.     for t in tests:
    703. 

  703.         sys.stdout.flush()
    704. 

  704.         pattern = s = outcome = repl = expected = None
    705. 

  705.         if len(t) == 5:
    706. 

  706.             pattern, s, outcome, repl, expected = t
    707. 

  707.         elif len(t) == 3:
    708. 

  708.             pattern, s, outcome = t
    709. 

  709.         else:
    710. 

  710.             raise ValueError, ('Test tuples should have 3 or 5 fields', t)
    711. 

  711. 

  712.         try:
    713. 

  713.             obj = re.compile(pattern)
    714. 

  714.         except re.error:
    715. 

  715.             if outcome == SYNTAX_ERROR: pass  # Expected a syntax error
    716. 

  716.             else:
    717. 

  717.                 print '=== Syntax error:', t
    718. 

  718.         except KeyboardInterrupt: raise KeyboardInterrupt
    719. 

  719.         except:
    720. 

  720.             print '*** Unexpected error ***', t
    721. 

  721.             if verbose:
    722. 

  722.                 traceback.print_exc(file=sys.stdout)
    723. 

  723.         else:
    724. 

  724.             try:
    725. 

  725.                 result = obj.search(s)
    726. 

  726.             except re.error, msg:
    727. 

  727.                 print '=== Unexpected exception', t, repr(msg)
    728. 

  728.             if outcome == SYNTAX_ERROR:
    729. 

  729.                 # This should have been a syntax error; forget it.
    730. 

  730.                 pass
    731. 

  731.             elif outcome == FAIL:
    732. 

  732.                 if result is None: pass   # No match, as expected
    733. 

  733.                 else: print '=== Succeeded incorrectly', t
    734. 

  734.             elif outcome == SUCCEED:
    735. 

  735.                 if result is not None:
    736. 

  736.                     # Matched, as expected, so now we compute the
    737. 

  737.                     # result string and compare it to our expected result.
    738. 

  738.                     start, end = result.span(0)
    739. 

  739.                     vardict={'found': result.group(0),
    740. 

  740.                              'groups': result.group(),
    741. 

  741.                              'flags': result.re.flags}
    742. 

  742.                     for i in range(1, 100):
    743. 

  743.                         try:
    744. 

  744.                             gi = result.group(i)
    745. 

  745.                             # Special hack because else the string concat fails:
    746. 

  746.                             if gi is None:
    747. 

  747.                                 gi = "None"
    748. 

  748.                         except IndexError:
    749. 

  749.                             gi = "Error"
    750. 

  750.                         vardict['g%d' % i] = gi
    751. 

  751.                     for i in result.re.groupindex.keys():
    752. 

  752.                         try:
    753. 

  753.                             gi = result.group(i)
    754. 

  754.                             if gi is None:
    755. 

  755.                                 gi = "None"
    756. 

  756.                         except IndexError:
    757. 

  757.                             gi = "Error"
    758. 

  758.                         vardict[i] = gi
    759. 

  759.                     repl = eval(repl, vardict)
    760. 

  760.                     if repl != expected:
    761. 

  761.                         print '=== grouping error', t,
    762. 

  762.                         print repr(repl) + ' should be ' + repr(expected)
    763. 

  763.                 else:
    764. 

  764.                     print '=== Failed incorrectly', t
    765. 

  765. 

  766.                 # Try the match on a unicode string, and check that it
    767. 

  767.                 # still succeeds.
    768. 

  768.                 try:
    769. 

  769.                     result = obj.search(unicode(s, "latin-1"))
    770. 

  770.                     if result is None:
    771. 

  771.                         print '=== Fails on unicode match', t
    772. 

  772.                 except NameError:
    773. 

  773.                     continue # 1.5.2
    774. 

  774.                 except TypeError:
    775. 

  775.                     continue # unicode test case
    776. 

  776. 

  777.                 # Try the match on a unicode pattern, and check that it
    778. 

  778.                 # still succeeds.
    779. 

  779.                 obj=re.compile(unicode(pattern, "latin-1"))
    780. 

  780.                 result = obj.search(s)
    781. 

  781.                 if result is None:
    782. 

  782.                     print '=== Fails on unicode pattern match', t
    783. 

  783. 

  784.                 # Try the match with the search area limited to the extent
    785. 

  785.                 # of the match and see if it still succeeds.  \B will
    786. 

  786.                 # break (because it won't match at the end or start of a
    787. 

  787.                 # string), so we'll ignore patterns that feature it.
    788. 

    789. 

  789.                 if pattern[:2] != '\\B' and pattern[-2:] != '\\B' \
    790. 

  790.                                and result is not None:
    791. 

  791.                     obj = re.compile(pattern)
    792. 

  792.                     result = obj.search(s, result.start(0), result.end(0) + 1)
    793. 

  793.                     if result is None:
    794. 

  794.                         print '=== Failed on range-limited match', t
    795. 

  795. 

  796.                 # Try the match with IGNORECASE enabled, and check that it
    797. 

  797.                 # still succeeds.
    798. 

  798.                 obj = re.compile(pattern, re.IGNORECASE)
    799. 

  799.                 result = obj.search(s)
    800. 

  800.                 if result is None:
    801. 

  801.                     print '=== Fails on case-insensitive match', t
    802. 

  802. 

  803.                 # Try the match with LOCALE enabled, and check that it
    804. 

  804.                 # still succeeds.
    805. 

  805.                 obj = re.compile(pattern, re.LOCALE)
    806. 

  806.                 result = obj.search(s)
    807. 

  807.                 if result is None:
    808. 

  808.                     print '=== Fails on locale-sensitive match', t
    809. 

  809. 

  810.                 # Try the match with UNICODE locale enabled, and check
    811. 

  811.                 # that it still succeeds.
    812. 

  812.                 obj = re.compile(pattern, re.UNICODE)
    813. 

  813.                 result = obj.search(s)
    814. 

  814.                 if result is None:
    815. 

  815.                     print '=== Fails on unicode-sensitive match', t
    816. 

  816. 

  817. def test_main():
    818. 

  818.     run_unittest(ReTests)
    819. 

  819.     run_re_tests()
    820. 

  820. 

  821. if __name__ == "__main__":
    822. 

  822.     test_main()
    823. 

  823.