PageRenderTime 57ms CodeModel.GetById 20ms RepoModel.GetById 1ms app.codeStats 0ms

/lib-python/modified-2.7/test/test_unicode.py

https://bitbucket.org/dac_io/pypy
Python | 1406 lines | 1328 code | 28 blank | 50 comment | 21 complexity | 55bdadb49e8cdeb776b88be9b7a33a75 MD5 | raw file

Large files files are truncated, but you can click here to view the full file

    

  1. """ Test script for the Unicode implementation.
    2. 

    3. 

  3. Written by Marc-Andre Lemburg (mal@lemburg.com).
    4. 

  4. 

  5. (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
    6. 

  6. 

  7. """#"
    8. 

  8. import sys, struct, codecs
    9. 

  9. from test import test_support, string_tests
    10. 

  10. 

  11. # Error handling (bad decoder return)
    12. 

  12. def search_function(encoding):
    13. 

  13.     def decode1(input, errors="strict"):
    14. 

  14.         return 42 # not a tuple
    15. 

  15.     def encode1(input, errors="strict"):
    16. 

  16.         return 42 # not a tuple
    17. 

  17.     def encode2(input, errors="strict"):
    18. 

  18.         return (42, 42) # no unicode
    19. 

  19.     def decode2(input, errors="strict"):
    20. 

  20.         return (42, 42) # no unicode
    21. 

  21.     if encoding=="test.unicode1":
    22. 

  22.         return (encode1, decode1, None, None)
    23. 

  23.     elif encoding=="test.unicode2":
    24. 

  24.         return (encode2, decode2, None, None)
    25. 

  25.     else:
    26. 

  26.         return None
    27. 

  27. codecs.register(search_function)
    28. 

  28. 

  29. class UnicodeTest(
    30. 

  30.     string_tests.CommonTest,
    31. 

  31.     string_tests.MixinStrUnicodeUserStringTest,
    32. 

  32.     string_tests.MixinStrUnicodeTest,
    33. 

  33.     ):
    34. 

  34.     type2test = unicode
    35. 

  35. 

  36.     def assertEqual(self, first, second, msg=None):
    37. 

  37.         # strict assertEqual method: reject implicit bytes/unicode equality
    38. 

  38.         super(UnicodeTest, self).assertEqual(first, second, msg)
    39. 

  39.         if isinstance(first, unicode) or isinstance(second, unicode):
    40. 

  40.             self.assertIsInstance(first, unicode)
    41. 

  41.             self.assertIsInstance(second, unicode)
    42. 

  42.         elif isinstance(first, str) or isinstance(second, str):
    43. 

  43.             self.assertIsInstance(first, str)
    44. 

  44.             self.assertIsInstance(second, str)
    45. 

  45. 

  46.     def checkequalnofix(self, result, object, methodname, *args):
    47. 

  47.         method = getattr(object, methodname)
    48. 

  48.         realresult = method(*args)
    49. 

  49.         self.assertEqual(realresult, result)
    50. 

  50.         self.assertTrue(type(realresult) is type(result))
    51. 

  51. 

  52.         # if the original is returned make sure that
    53. 

  53.         # this doesn't happen with subclasses
    54. 

  54.         if realresult is object:
    55. 

  55.             class usub(unicode):
    56. 

  56.                 def __repr__(self):
    57. 

  57.                     return 'usub(%r)' % unicode.__repr__(self)
    58. 

  58.             object = usub(object)
    59. 

  59.             method = getattr(object, methodname)
    60. 

  60.             realresult = method(*args)
    61. 

  61.             self.assertEqual(realresult, result)
    62. 

  62.             self.assertTrue(object is not realresult)
    63. 

  63. 

  64.     def test_literals(self):
    65. 

  65.         self.assertEqual(u'\xff', u'\u00ff')
    66. 

  66.         self.assertEqual(u'\uffff', u'\U0000ffff')
    67. 

  67.         self.assertRaises(SyntaxError, eval, 'u\'\\Ufffffffe\'')
    68. 

  68.         self.assertRaises(SyntaxError, eval, 'u\'\\Uffffffff\'')
    69. 

  69.         self.assertRaises(SyntaxError, eval, 'u\'\\U%08x\'' % 0x110000)
    70. 

  70. 

  71.     def test_repr(self):
    72. 

  72.         if not sys.platform.startswith('java'):
    73. 

  73.             # Test basic sanity of repr()
    74. 

  74.             self.assertEqual(repr(u'abc'), "u'abc'")
    75. 

  75.             self.assertEqual(repr(u'ab\\c'), "u'ab\\\\c'")
    76. 

  76.             self.assertEqual(repr(u'ab\\'), "u'ab\\\\'")
    77. 

  77.             self.assertEqual(repr(u'\\c'), "u'\\\\c'")
    78. 

  78.             self.assertEqual(repr(u'\\'), "u'\\\\'")
    79. 

  79.             self.assertEqual(repr(u'\n'), "u'\\n'")
    80. 

  80.             self.assertEqual(repr(u'\r'), "u'\\r'")
    81. 

  81.             self.assertEqual(repr(u'\t'), "u'\\t'")
    82. 

  82.             self.assertEqual(repr(u'\b'), "u'\\x08'")
    83. 

  83.             self.assertEqual(repr(u"'\""), """u'\\'"'""")
    84. 

  84.             self.assertEqual(repr(u"'\""), """u'\\'"'""")
    85. 

  85.             self.assertEqual(repr(u"'"), '''u"'"''')
    86. 

  86.             self.assertEqual(repr(u'"'), """u'"'""")
    87. 

  87.             latin1repr = (
    88. 

  88.                 "u'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
    89. 

  89.                 "\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
    90. 

  90.                 "\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
    91. 

  91.                 "JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
    92. 

  92.                 "\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
    93. 

  93.                 "\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
    94. 

  94.                 "\\x9c\\x9d\\x9e\\x9f\\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9"
    95. 

  95.                 "\\xaa\\xab\\xac\\xad\\xae\\xaf\\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7"
    96. 

  96.                 "\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\\xc0\\xc1\\xc2\\xc3\\xc4\\xc5"
    97. 

  97.                 "\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\\xd0\\xd1\\xd2\\xd3"
    98. 

  98.                 "\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\\xe0\\xe1"
    99. 

  99.                 "\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef"
    100. 

  100.                 "\\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd"
    101. 

  101.                 "\\xfe\\xff'")
    102. 

  102.             testrepr = repr(u''.join(map(unichr, xrange(256))))
    103. 

  103.             self.assertEqual(testrepr, latin1repr)
    104. 

  104.             # Test repr works on wide unicode escapes without overflow.
    105. 

  105.             self.assertEqual(repr(u"\U00010000" * 39 + u"\uffff" * 4096),
    106. 

  106.                              repr(u"\U00010000" * 39 + u"\uffff" * 4096))
    107. 

  107. 

  108. 

  109.     def test_count(self):
    110. 

  110.         string_tests.CommonTest.test_count(self)
    111. 

  111.         # check mixed argument types
    112. 

  112.         self.checkequalnofix(3,  'aaa', 'count', u'a')
    113. 

  113.         self.checkequalnofix(0,  'aaa', 'count', u'b')
    114. 

  114.         self.checkequalnofix(3, u'aaa', 'count',  'a')
    115. 

  115.         self.checkequalnofix(0, u'aaa', 'count',  'b')
    116. 

  116.         self.checkequalnofix(0, u'aaa', 'count',  'b')
    117. 

  117.         self.checkequalnofix(1, u'aaa', 'count',  'a', -1)
    118. 

  118.         self.checkequalnofix(3, u'aaa', 'count',  'a', -10)
    119. 

  119.         self.checkequalnofix(2, u'aaa', 'count',  'a', 0, -1)
    120. 

  120.         self.checkequalnofix(0, u'aaa', 'count',  'a', 0, -10)
    121. 

  121. 

  122.     def test_find(self):
    123. 

  123.         self.checkequalnofix(0,  u'abcdefghiabc', 'find', u'abc')
    124. 

  124.         self.checkequalnofix(9,  u'abcdefghiabc', 'find', u'abc', 1)
    125. 

  125.         self.checkequalnofix(-1, u'abcdefghiabc', 'find', u'def', 4)
    126. 

  126. 

  127.         self.assertRaises(TypeError, u'hello'.find)
    128. 

  128.         self.assertRaises(TypeError, u'hello'.find, 42)
    129. 

  129. 

  130.     def test_rfind(self):
    131. 

  131.         string_tests.CommonTest.test_rfind(self)
    132. 

  132.         # check mixed argument types
    133. 

  133.         self.checkequalnofix(9,   'abcdefghiabc', 'rfind', u'abc')
    134. 

  134.         self.checkequalnofix(12,  'abcdefghiabc', 'rfind', u'')
    135. 

  135.         self.checkequalnofix(12, u'abcdefghiabc', 'rfind',  '')
    136. 

  136. 

  137.     def test_index(self):
    138. 

  138.         string_tests.CommonTest.test_index(self)
    139. 

  139.         # check mixed argument types
    140. 

  140.         for (t1, t2) in ((str, unicode), (unicode, str)):
    141. 

  141.             self.checkequalnofix(0, t1('abcdefghiabc'), 'index',  t2(''))
    142. 

  142.             self.checkequalnofix(3, t1('abcdefghiabc'), 'index',  t2('def'))
    143. 

  143.             self.checkequalnofix(0, t1('abcdefghiabc'), 'index',  t2('abc'))
    144. 

  144.             self.checkequalnofix(9, t1('abcdefghiabc'), 'index',  t2('abc'), 1)
    145. 

  145.             self.assertRaises(ValueError, t1('abcdefghiabc').index, t2('hib'))
    146. 

  146.             self.assertRaises(ValueError, t1('abcdefghiab').index,  t2('abc'), 1)
    147. 

  147.             self.assertRaises(ValueError, t1('abcdefghi').index,  t2('ghi'), 8)
    148. 

  148.             self.assertRaises(ValueError, t1('abcdefghi').index,  t2('ghi'), -1)
    149. 

  149. 

  150.     def test_rindex(self):
    151. 

  151.         string_tests.CommonTest.test_rindex(self)
    152. 

  152.         # check mixed argument types
    153. 

  153.         for (t1, t2) in ((str, unicode), (unicode, str)):
    154. 

  154.             self.checkequalnofix(12, t1('abcdefghiabc'), 'rindex',  t2(''))
    155. 

  155.             self.checkequalnofix(3,  t1('abcdefghiabc'), 'rindex',  t2('def'))
    156. 

  156.             self.checkequalnofix(9,  t1('abcdefghiabc'), 'rindex',  t2('abc'))
    157. 

  157.             self.checkequalnofix(0,  t1('abcdefghiabc'), 'rindex',  t2('abc'), 0, -1)
    158. 

  158. 

  159.             self.assertRaises(ValueError, t1('abcdefghiabc').rindex,  t2('hib'))
    160. 

  160.             self.assertRaises(ValueError, t1('defghiabc').rindex,  t2('def'), 1)
    161. 

  161.             self.assertRaises(ValueError, t1('defghiabc').rindex,  t2('abc'), 0, -1)
    162. 

  162.             self.assertRaises(ValueError, t1('abcdefghi').rindex,  t2('ghi'), 0, 8)
    163. 

  163.             self.assertRaises(ValueError, t1('abcdefghi').rindex,  t2('ghi'), 0, -1)
    164. 

  164. 

  165.     def test_translate(self):
    166. 

  166.         self.checkequalnofix(u'bbbc', u'abababc', 'translate', {ord('a'):None})
    167. 

  167.         self.checkequalnofix(u'iiic', u'abababc', 'translate', {ord('a'):None, ord('b'):ord('i')})
    168. 

  168.         self.checkequalnofix(u'iiix', u'abababc', 'translate', {ord('a'):None, ord('b'):ord('i'), ord('c'):u'x'})
    169. 

  169.         self.checkequalnofix(u'<i><i><i>c', u'abababc', 'translate', {ord('a'):None, ord('b'):u'<i>'})
    170. 

  170.         self.checkequalnofix(u'c', u'abababc', 'translate', {ord('a'):None, ord('b'):u''})
    171. 

  171.         self.checkequalnofix(u'xyyx', u'xzx', 'translate', {ord('z'):u'yy'})
    172. 

  172. 

  173.         self.assertRaises(TypeError, u'hello'.translate)
    174. 

  174.         self.assertRaises(TypeError, u'abababc'.translate, {ord('a'):''})
    175. 

  175. 

  176.     def test_split(self):
    177. 

  177.         string_tests.CommonTest.test_split(self)
    178. 

  178. 

  179.         # Mixed arguments
    180. 

  180.         self.checkequalnofix([u'a', u'b', u'c', u'd'], u'a//b//c//d', 'split', '//')
    181. 

  181.         self.checkequalnofix([u'a', u'b', u'c', u'd'], 'a//b//c//d', 'split', u'//')
    182. 

  182.         self.checkequalnofix([u'endcase ', u''], u'endcase test', 'split', 'test')
    183. 

  183. 

  184.     def test_join(self):
    185. 

  185.         string_tests.MixinStrUnicodeUserStringTest.test_join(self)
    186. 

  186. 

  187.         # mixed arguments
    188. 

  188.         self.checkequalnofix(u'a b c d', u' ', 'join', ['a', 'b', u'c', u'd'])
    189. 

  189.         self.checkequalnofix(u'abcd', u'', 'join', (u'a', u'b', u'c', u'd'))
    190. 

  190.         self.checkequalnofix(u'w x y z', u' ', 'join', string_tests.Sequence('wxyz'))
    191. 

  191.         self.checkequalnofix(u'a b c d', ' ', 'join', [u'a', u'b', u'c', u'd'])
    192. 

  192.         self.checkequalnofix(u'a b c d', ' ', 'join', ['a', 'b', u'c', u'd'])
    193. 

  193.         self.checkequalnofix(u'abcd', '', 'join', (u'a', u'b', u'c', u'd'))
    194. 

  194.         self.checkequalnofix(u'w x y z', ' ', 'join', string_tests.Sequence(u'wxyz'))
    195. 

  195. 

  196.     def test_strip(self):
    197. 

  197.         string_tests.CommonTest.test_strip(self)
    198. 

  198.         self.assertRaises(UnicodeError, u"hello".strip, "\xff")
    199. 

  199. 

  200.     def test_replace(self):
    201. 

  201.         string_tests.CommonTest.test_replace(self)
    202. 

  202. 

  203.         # method call forwarded from str implementation because of unicode argument
    204. 

  204.         self.checkequalnofix(u'one@two!three!', 'one!two!three!', 'replace', u'!', u'@', 1)
    205. 

  205.         self.assertRaises(TypeError, 'replace'.replace, u"r", 42)
    206. 

  206. 

  207.     def test_comparison(self):
    208. 

  208.         # Comparisons:
    209. 

  209.         self.assertTrue(u'abc' == 'abc')
    210. 

  210.         self.assertTrue('abc' == u'abc')
    211. 

  211.         self.assertTrue(u'abc' == u'abc')
    212. 

  212.         self.assertTrue(u'abcd' > 'abc')
    213. 

  213.         self.assertTrue('abcd' > u'abc')
    214. 

  214.         self.assertTrue(u'abcd' > u'abc')
    215. 

  215.         self.assertTrue(u'abc' < 'abcd')
    216. 

  216.         self.assertTrue('abc' < u'abcd')
    217. 

  217.         self.assertTrue(u'abc' < u'abcd')
    218. 

  218. 

  219.         if 0:
    220. 

  220.             # Move these tests to a Unicode collation module test...
    221. 

  221.             # Testing UTF-16 code point order comparisons...
    222. 

  222. 

  223.             # No surrogates, no fixup required.
    224. 

  224.             self.assertTrue(u'\u0061' < u'\u20ac')
    225. 

  225.             # Non surrogate below surrogate value, no fixup required
    226. 

  226.             self.assertTrue(u'\u0061' < u'\ud800\udc02')
    227. 

  227. 

  228.             # Non surrogate above surrogate value, fixup required
    229. 

  229.             def test_lecmp(s, s2):
    230. 

  230.                 self.assertTrue(s < s2)
    231. 

  231. 

  232.             def test_fixup(s):
    233. 

  233.                 s2 = u'\ud800\udc01'
    234. 

  234.                 test_lecmp(s, s2)
    235. 

  235.                 s2 = u'\ud900\udc01'
    236. 

  236.                 test_lecmp(s, s2)
    237. 

  237.                 s2 = u'\uda00\udc01'
    238. 

  238.                 test_lecmp(s, s2)
    239. 

  239.                 s2 = u'\udb00\udc01'
    240. 

  240.                 test_lecmp(s, s2)
    241. 

  241.                 s2 = u'\ud800\udd01'
    242. 

  242.                 test_lecmp(s, s2)
    243. 

  243.                 s2 = u'\ud900\udd01'
    244. 

  244.                 test_lecmp(s, s2)
    245. 

  245.                 s2 = u'\uda00\udd01'
    246. 

  246.                 test_lecmp(s, s2)
    247. 

  247.                 s2 = u'\udb00\udd01'
    248. 

  248.                 test_lecmp(s, s2)
    249. 

  249.                 s2 = u'\ud800\ude01'
    250. 

  250.                 test_lecmp(s, s2)
    251. 

  251.                 s2 = u'\ud900\ude01'
    252. 

  252.                 test_lecmp(s, s2)
    253. 

  253.                 s2 = u'\uda00\ude01'
    254. 

  254.                 test_lecmp(s, s2)
    255. 

  255.                 s2 = u'\udb00\ude01'
    256. 

  256.                 test_lecmp(s, s2)
    257. 

  257.                 s2 = u'\ud800\udfff'
    258. 

  258.                 test_lecmp(s, s2)
    259. 

  259.                 s2 = u'\ud900\udfff'
    260. 

  260.                 test_lecmp(s, s2)
    261. 

  261.                 s2 = u'\uda00\udfff'
    262. 

  262.                 test_lecmp(s, s2)
    263. 

  263.                 s2 = u'\udb00\udfff'
    264. 

  264.                 test_lecmp(s, s2)
    265. 

  265. 

  266.                 test_fixup(u'\ue000')
    267. 

  267.                 test_fixup(u'\uff61')
    268. 

  268. 

  269.         # Surrogates on both sides, no fixup required
    270. 

  270.         self.assertTrue(u'\ud800\udc02' < u'\ud84d\udc56')
    271. 

  271. 

  272.     def test_islower(self):
    273. 

  273.         string_tests.MixinStrUnicodeUserStringTest.test_islower(self)
    274. 

  274.         self.checkequalnofix(False, u'\u1FFc', 'islower')
    275. 

  275. 

  276.     def test_isupper(self):
    277. 

  277.         string_tests.MixinStrUnicodeUserStringTest.test_isupper(self)
    278. 

  278.         if not sys.platform.startswith('java'):
    279. 

  279.             self.checkequalnofix(False, u'\u1FFc', 'isupper')
    280. 

  280. 

  281.     def test_istitle(self):
    282. 

  282.         string_tests.MixinStrUnicodeUserStringTest.test_title(self)
    283. 

  283.         self.checkequalnofix(True, u'\u1FFc', 'istitle')
    284. 

  284.         self.checkequalnofix(True, u'Greek \u1FFcitlecases ...', 'istitle')
    285. 

  285. 

  286.     def test_isspace(self):
    287. 

  287.         string_tests.MixinStrUnicodeUserStringTest.test_isspace(self)
    288. 

  288.         self.checkequalnofix(True, u'\u2000', 'isspace')
    289. 

  289.         self.checkequalnofix(True, u'\u200a', 'isspace')
    290. 

  290.         self.checkequalnofix(False, u'\u2014', 'isspace')
    291. 

  291. 

  292.     def test_isalpha(self):
    293. 

  293.         string_tests.MixinStrUnicodeUserStringTest.test_isalpha(self)
    294. 

  294.         self.checkequalnofix(True, u'\u1FFc', 'isalpha')
    295. 

  295. 

  296.     def test_isdecimal(self):
    297. 

  297.         self.checkequalnofix(False, u'', 'isdecimal')
    298. 

  298.         self.checkequalnofix(False, u'a', 'isdecimal')
    299. 

  299.         self.checkequalnofix(True, u'0', 'isdecimal')
    300. 

  300.         self.checkequalnofix(False, u'\u2460', 'isdecimal') # CIRCLED DIGIT ONE
    301. 

  301.         self.checkequalnofix(False, u'\xbc', 'isdecimal') # VULGAR FRACTION ONE QUARTER
    302. 

  302.         self.checkequalnofix(True, u'\u0660', 'isdecimal') # ARABIC-INDIC DIGIT ZERO
    303. 

  303.         self.checkequalnofix(True, u'0123456789', 'isdecimal')
    304. 

  304.         self.checkequalnofix(False, u'0123456789a', 'isdecimal')
    305. 

  305. 

  306.         self.checkraises(TypeError, 'abc', 'isdecimal', 42)
    307. 

  307. 

  308.     def test_isdigit(self):
    309. 

  309.         string_tests.MixinStrUnicodeUserStringTest.test_isdigit(self)
    310. 

  310.         self.checkequalnofix(True, u'\u2460', 'isdigit')
    311. 

  311.         self.checkequalnofix(False, u'\xbc', 'isdigit')
    312. 

  312.         self.checkequalnofix(True, u'\u0660', 'isdigit')
    313. 

  313. 

  314.     def test_isnumeric(self):
    315. 

  315.         self.checkequalnofix(False, u'', 'isnumeric')
    316. 

  316.         self.checkequalnofix(False, u'a', 'isnumeric')
    317. 

  317.         self.checkequalnofix(True, u'0', 'isnumeric')
    318. 

  318.         self.checkequalnofix(True, u'\u2460', 'isnumeric')
    319. 

  319.         self.checkequalnofix(True, u'\xbc', 'isnumeric')
    320. 

  320.         self.checkequalnofix(True, u'\u0660', 'isnumeric')
    321. 

  321.         self.checkequalnofix(True, u'0123456789', 'isnumeric')
    322. 

  322.         self.checkequalnofix(False, u'0123456789a', 'isnumeric')
    323. 

  323. 

  324.         self.assertRaises(TypeError, u"abc".isnumeric, 42)
    325. 

  325. 

  326.     def test_contains(self):
    327. 

  327.         # Testing Unicode contains method
    328. 

  328.         self.assertIn('a', u'abdb')
    329. 

  329.         self.assertIn('a', u'bdab')
    330. 

  330.         self.assertIn('a', u'bdaba')
    331. 

  331.         self.assertIn('a', u'bdba')
    332. 

  332.         self.assertIn('a', u'bdba')
    333. 

  333.         self.assertIn(u'a', u'bdba')
    334. 

  334.         self.assertNotIn(u'a', u'bdb')
    335. 

  335.         self.assertNotIn(u'a', 'bdb')
    336. 

  336.         self.assertIn(u'a', 'bdba')
    337. 

  337.         self.assertIn(u'a', ('a',1,None))
    338. 

  338.         self.assertIn(u'a', (1,None,'a'))
    339. 

  339.         self.assertIn(u'a', (1,None,u'a'))
    340. 

  340.         self.assertIn('a', ('a',1,None))
    341. 

  341.         self.assertIn('a', (1,None,'a'))
    342. 

  342.         self.assertIn('a', (1,None,u'a'))
    343. 

  343.         self.assertNotIn('a', ('x',1,u'y'))
    344. 

  344.         self.assertNotIn('a', ('x',1,None))
    345. 

  345.         self.assertNotIn(u'abcd', u'abcxxxx')
    346. 

  346.         self.assertIn(u'ab', u'abcd')
    347. 

  347.         self.assertIn('ab', u'abc')
    348. 

  348.         self.assertIn(u'ab', 'abc')
    349. 

  349.         self.assertIn(u'ab', (1,None,u'ab'))
    350. 

  350.         self.assertIn(u'', u'abc')
    351. 

  351.         self.assertIn('', u'abc')
    352. 

  352. 

  353.         # If the following fails either
    354. 

  354.         # the contains operator does not propagate UnicodeErrors or
    355. 

  355.         # someone has changed the default encoding
    356. 

  356.         self.assertRaises(UnicodeDecodeError, 'g\xe2teau'.__contains__, u'\xe2')
    357. 

  357.         self.assertRaises(UnicodeDecodeError, u'g\xe2teau'.__contains__, '\xe2')
    358. 

  358. 

  359.         self.assertIn(u'', '')
    360. 

  360.         self.assertIn('', u'')
    361. 

  361.         self.assertIn(u'', u'')
    362. 

  362.         self.assertIn(u'', 'abc')
    363. 

  363.         self.assertIn('', u'abc')
    364. 

  364.         self.assertIn(u'', u'abc')
    365. 

  365.         self.assertNotIn(u'\0', 'abc')
    366. 

  366.         self.assertNotIn('\0', u'abc')
    367. 

  367.         self.assertNotIn(u'\0', u'abc')
    368. 

  368.         self.assertIn(u'\0', '\0abc')
    369. 

  369.         self.assertIn('\0', u'\0abc')
    370. 

  370.         self.assertIn(u'\0', u'\0abc')
    371. 

  371.         self.assertIn(u'\0', 'abc\0')
    372. 

  372.         self.assertIn('\0', u'abc\0')
    373. 

  373.         self.assertIn(u'\0', u'abc\0')
    374. 

  374.         self.assertIn(u'a', '\0abc')
    375. 

  375.         self.assertIn('a', u'\0abc')
    376. 

  376.         self.assertIn(u'a', u'\0abc')
    377. 

  377.         self.assertIn(u'asdf', 'asdf')
    378. 

  378.         self.assertIn('asdf', u'asdf')
    379. 

  379.         self.assertIn(u'asdf', u'asdf')
    380. 

  380.         self.assertNotIn(u'asdf', 'asd')
    381. 

  381.         self.assertNotIn('asdf', u'asd')
    382. 

  382.         self.assertNotIn(u'asdf', u'asd')
    383. 

  383.         self.assertNotIn(u'asdf', '')
    384. 

  384.         self.assertNotIn('asdf', u'')
    385. 

  385.         self.assertNotIn(u'asdf', u'')
    386. 

  386. 

  387.         self.assertRaises(TypeError, u"abc".__contains__)
    388. 

  388.         self.assertRaises(TypeError, u"abc".__contains__, object())
    389. 

  389. 

  390.     def test_formatting(self):
    391. 

  391.         string_tests.MixinStrUnicodeUserStringTest.test_formatting(self)
    392. 

  392.         # Testing Unicode formatting strings...
    393. 

  393.         self.assertEqual(u"%s, %s" % (u"abc", "abc"), u'abc, abc')
    394. 

  394.         self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, 2, 3), u'abc, abc, 1, 2.000000,  3.00')
    395. 

  395.         self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, -2, 3), u'abc, abc, 1, -2.000000,  3.00')
    396. 

  396.         self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.5), u'abc, abc, -1, -2.000000,  3.50')
    397. 

  397.         self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.57), u'abc, abc, -1, -2.000000,  3.57')
    398. 

  398.         self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 1003.57), u'abc, abc, -1, -2.000000, 1003.57')
    399. 

  399.         if not sys.platform.startswith('java'):
    400. 

  400.             self.assertEqual(u"%r, %r" % (u"abc", "abc"), u"u'abc', 'abc'")
    401. 

  401.         self.assertEqual(u"%(x)s, %(y)s" % {'x':u"abc", 'y':"def"}, u'abc, def')
    402. 

  402.         self.assertEqual(u"%(x)s, %(\xfc)s" % {'x':u"abc", u'\xfc':"def"}, u'abc, def')
    403. 

  403. 

  404.         self.assertEqual(u'%c' % 0x1234, u'\u1234')
    405. 

  405.         self.assertRaises(OverflowError, u"%c".__mod__, (sys.maxunicode+1,))
    406. 

  406.         self.assertRaises(ValueError, u"%.1\u1032f".__mod__, (1.0/3))
    407. 

  407. 

  408.         for num in range(0x00,0x80):
    409. 

  409.             char = chr(num)
    410. 

  410.             self.assertEqual(u"%c" % char, unicode(char))
    411. 

  411.             self.assertEqual(u"%c" % num, unicode(char))
    412. 

  412.             self.assertTrue(char == u"%c" % char)
    413. 

  413.             self.assertTrue(char == u"%c" % num)
    414. 

  414.         # Issue 7649
    415. 

  415.         for num in range(0x80,0x100):
    416. 

  416.             uchar = unichr(num)
    417. 

  417.             self.assertEqual(uchar, u"%c" % num)   # works only with ints
    418. 

  418.             self.assertEqual(uchar, u"%c" % uchar) # and unicode chars
    419. 

  419.             # the implicit decoding should fail for non-ascii chars
    420. 

  420.             self.assertRaises(UnicodeDecodeError, u"%c".__mod__, chr(num))
    421. 

  421.             self.assertRaises(UnicodeDecodeError, u"%s".__mod__, chr(num))
    422. 

  422. 

  423.         # formatting jobs delegated from the string implementation:
    424. 

  424.         self.assertEqual('...%(foo)s...' % {'foo':u"abc"}, u'...abc...')
    425. 

  425.         self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
    426. 

  426.         self.assertEqual('...%(foo)s...' % {u'foo':"abc"}, '...abc...')
    427. 

  427.         self.assertEqual('...%(foo)s...' % {u'foo':u"abc"}, u'...abc...')
    428. 

  428.         self.assertEqual('...%(foo)s...' % {u'foo':u"abc",'def':123},  u'...abc...')
    429. 

  429.         self.assertEqual('...%(foo)s...' % {u'foo':u"abc",u'def':123}, u'...abc...')
    430. 

  430.         self.assertEqual('...%s...%s...%s...%s...' % (1,2,3,u"abc"), u'...1...2...3...abc...')
    431. 

  431.         self.assertEqual('...%%...%%s...%s...%s...%s...%s...' % (1,2,3,u"abc"), u'...%...%s...1...2...3...abc...')
    432. 

  432.         self.assertEqual('...%s...' % u"abc", u'...abc...')
    433. 

  433.         self.assertEqual('%*s' % (5,u'abc',), u'  abc')
    434. 

  434.         self.assertEqual('%*s' % (-5,u'abc',), u'abc  ')
    435. 

  435.         self.assertEqual('%*.*s' % (5,2,u'abc',), u'   ab')
    436. 

  436.         self.assertEqual('%*.*s' % (5,3,u'abc',), u'  abc')
    437. 

  437.         self.assertEqual('%i %*.*s' % (10, 5,3,u'abc',), u'10   abc')
    438. 

  438.         self.assertEqual('%i%s %*.*s' % (10, 3, 5, 3, u'abc',), u'103   abc')
    439. 

  439.         self.assertEqual('%c' % u'a', u'a')
    440. 

  440.         class Wrapper:
    441. 

  441.             def __str__(self):
    442. 

  442.                 return u'\u1234'
    443. 

  443.         self.assertEqual('%s' % Wrapper(), u'\u1234')
    444. 

  444. 

  445.     def test_startswith_endswith_errors(self):
    446. 

  446.         for meth in (u'foo'.startswith, u'foo'.endswith):
    447. 

  447.             with self.assertRaises(UnicodeDecodeError):
    448. 

  448.                 meth('\xff')
    449. 

  449.             with self.assertRaises(TypeError) as cm:
    450. 

  450.                 meth(['f'])
    451. 

  451.             if test_support.check_impl_detail():
    452. 

  452.                 exc = str(cm.exception)
    453. 

  453.                 self.assertIn('unicode', exc)
    454. 

  454.                 self.assertIn('str', exc)
    455. 

  455.                 self.assertIn('tuple', exc)
    456. 

  456. 

  457.     @test_support.run_with_locale('LC_ALL', 'de_DE', 'fr_FR')
    458. 

  458.     def test_format_float(self):
    459. 

  459.         # should not format with a comma, but always with C locale
    460. 

  460.         self.assertEqual(u'1.0', u'%.1f' % 1.0)
    461. 

  461. 

  462.     def test_constructor(self):
    463. 

  463.         # unicode(obj) tests (this maps to PyObject_Unicode() at C level)
    464. 

  464. 

  465.         self.assertEqual(
    466. 

  466.             unicode(u'unicode remains unicode'),
    467. 

  467.             u'unicode remains unicode'
    468. 

  468.         )
    469. 

  469. 

  470.         class UnicodeSubclass(unicode):
    471. 

  471.             pass
    472. 

  472. 

  473.         self.assertEqual(
    474. 

  474.             unicode(UnicodeSubclass('unicode subclass becomes unicode')),
    475. 

  475.             u'unicode subclass becomes unicode'
    476. 

  476.         )
    477. 

  477. 

  478.         self.assertEqual(
    479. 

  479.             unicode('strings are converted to unicode'),
    480. 

  480.             u'strings are converted to unicode'
    481. 

  481.         )
    482. 

  482. 

  483.         class UnicodeCompat:
    484. 

  484.             def __init__(self, x):
    485. 

  485.                 self.x = x
    486. 

  486.             def __unicode__(self):
    487. 

  487.                 return self.x
    488. 

  488. 

  489.         self.assertEqual(
    490. 

  490.             unicode(UnicodeCompat('__unicode__ compatible objects are recognized')),
    491. 

  491.             u'__unicode__ compatible objects are recognized')
    492. 

  492. 

  493.         class StringCompat:
    494. 

  494.             def __init__(self, x):
    495. 

  495.                 self.x = x
    496. 

  496.             def __str__(self):
    497. 

  497.                 return self.x
    498. 

  498. 

  499.         self.assertEqual(
    500. 

  500.             unicode(StringCompat('__str__ compatible objects are recognized')),
    501. 

  501.             u'__str__ compatible objects are recognized'
    502. 

  502.         )
    503. 

  503. 

  504.         # unicode(obj) is compatible to str():
    505. 

  505. 

  506.         o = StringCompat('unicode(obj) is compatible to str()')
    507. 

  507.         self.assertEqual(unicode(o), u'unicode(obj) is compatible to str()')
    508. 

  508.         self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
    509. 

  509. 

  510.         # %-formatting and .__unicode__()
    511. 

  511.         self.assertEqual(u'%s' %
    512. 

  512.                          UnicodeCompat(u"u'%s' % obj uses obj.__unicode__()"),
    513. 

  513.                          u"u'%s' % obj uses obj.__unicode__()")
    514. 

  514.         self.assertEqual(u'%s' %
    515. 

  515.                          UnicodeCompat(u"u'%s' % obj falls back to obj.__str__()"),
    516. 

  516.                          u"u'%s' % obj falls back to obj.__str__()")
    517. 

  517. 

  518.         for obj in (123, 123.45, 123L):
    519. 

  519.             self.assertEqual(unicode(obj), unicode(str(obj)))
    520. 

  520. 

  521.         # unicode(obj, encoding, error) tests (this maps to
    522. 

  522.         # PyUnicode_FromEncodedObject() at C level)
    523. 

  523. 

  524.         if not sys.platform.startswith('java'):
    525. 

  525.             self.assertRaises(
    526. 

  526.                 TypeError,
    527. 

  527.                 unicode,
    528. 

  528.                 u'decoding unicode is not supported',
    529. 

  529.                 'utf-8',
    530. 

  530.                 'strict'
    531. 

  531.             )
    532. 

  532. 

  533.         self.assertEqual(
    534. 

  534.             unicode('strings are decoded to unicode', 'utf-8', 'strict'),
    535. 

  535.             u'strings are decoded to unicode'
    536. 

  536.         )
    537. 

  537. 

  538.         if not sys.platform.startswith('java'):
    539. 

  539.             with test_support.check_py3k_warnings():
    540. 

  540.                 buf = buffer('character buffers are decoded to unicode')
    541. 

  541.             self.assertEqual(
    542. 

  542.                 unicode(
    543. 

  543.                     buf,
    544. 

  544.                     'utf-8',
    545. 

  545.                     'strict'
    546. 

  546.                 ),
    547. 

  547.                 u'character buffers are decoded to unicode'
    548. 

  548.             )
    549. 

  549. 

  550.         self.assertRaises(TypeError, unicode, 42, 42, 42)
    551. 

  551. 

  552.     def test_codecs_utf7(self):
    553. 

  553.         utfTests = [
    554. 

  554.             (u'A\u2262\u0391.', 'A+ImIDkQ.'),             # RFC2152 example
    555. 

  555.             (u'Hi Mom -\u263a-!', 'Hi Mom -+Jjo--!'),     # RFC2152 example
    556. 

  556.             (u'\u65E5\u672C\u8A9E', '+ZeVnLIqe-'),        # RFC2152 example
    557. 

  557.             (u'Item 3 is \u00a31.', 'Item 3 is +AKM-1.'), # RFC2152 example
    558. 

  558.             (u'+', '+-'),
    559. 

  559.             (u'+-', '+--'),
    560. 

  560.             (u'+?', '+-?'),
    561. 

  561.             (u'\?', '+AFw?'),
    562. 

  562.             (u'+?', '+-?'),
    563. 

  563.             (ur'\\?', '+AFwAXA?'),
    564. 

  564.             (ur'\\\?', '+AFwAXABc?'),
    565. 

  565.             (ur'++--', '+-+---'),
    566. 

  566.             (u'\U000abcde', '+2m/c3g-'),                  # surrogate pairs
    567. 

  567.             (u'/', '/'),
    568. 

  568.         ]
    569. 

  569. 

  570.         for (x, y) in utfTests:
    571. 

  571.             self.assertEqual(x.encode('utf-7'), y)
    572. 

  572. 

  573.         # Unpaired surrogates not supported
    574. 

  574.         self.assertRaises(UnicodeError, unicode, '+3ADYAA-', 'utf-7')
    575. 

  575. 

  576.         self.assertEqual(unicode('+3ADYAA-', 'utf-7', 'replace'), u'\ufffd\ufffd')
    577. 

  577. 

  578.         # Direct encoded characters
    579. 

  579.         set_d = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'(),-./:?"
    580. 

  580.         # Optional direct characters
    581. 

  581.         set_o = '!"#$%&*;<=>@[]^_`{|}'
    582. 

  582.         for c in set_d:
    583. 

  583.             self.assertEqual(c.encode('utf7'), c.encode('ascii'))
    584. 

  584.             self.assertEqual(c.encode('ascii').decode('utf7'), unicode(c))
    585. 

  585.             self.assertTrue(c == c.encode('ascii').decode('utf7'))
    586. 

  586.         for c in set_o:
    587. 

  587.             self.assertEqual(c.encode('ascii').decode('utf7'), unicode(c))
    588. 

  588.             self.assertTrue(c == c.encode('ascii').decode('utf7'))
    589. 

  589. 

  590.     def test_codecs_utf8(self):
    591. 

  591.         self.assertEqual(u''.encode('utf-8'), '')
    592. 

  592.         self.assertEqual(u'\u20ac'.encode('utf-8'), '\xe2\x82\xac')
    593. 

  593.         self.assertEqual(u'\ud800\udc02'.encode('utf-8'), '\xf0\x90\x80\x82')
    594. 

  594.         self.assertEqual(u'\ud84d\udc56'.encode('utf-8'), '\xf0\xa3\x91\x96')
    595. 

  595.         self.assertEqual(u'\ud800'.encode('utf-8'), '\xed\xa0\x80')
    596. 

  596.         self.assertEqual(u'\udc00'.encode('utf-8'), '\xed\xb0\x80')
    597. 

  597.         self.assertEqual(
    598. 

  598.             (u'\ud800\udc02'*1000).encode('utf-8'),
    599. 

  599.             '\xf0\x90\x80\x82'*1000
    600. 

  600.         )
    601. 

  601.         self.assertEqual(
    602. 

  602.             u'\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f'
    603. 

  603.             u'\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00'
    604. 

  604.             u'\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c'
    605. 

  605.             u'\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067'
    606. 

  606.             u'\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das'
    607. 

  607.             u' Nunstuck git und'.encode('utf-8'),
    608. 

  608.             '\xe6\xad\xa3\xe7\xa2\xba\xe3\x81\xab\xe8\xa8\x80\xe3\x81'
    609. 

  609.             '\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3\xe3\x81\xaf\xe3'
    610. 

  610.             '\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3\x81\xbe'
    611. 

  611.             '\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
    612. 

  612.             '\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8'
    613. 

  613.             '\xaa\x9e\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81'
    614. 

  614.             '\xe3\x81\x82\xe3\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81'
    615. 

  615.             '\x9f\xe3\x82\x89\xe3\x82\x81\xe3\x81\xa7\xe3\x81\x99\xe3'
    616. 

  616.             '\x80\x82\xe5\xae\x9f\xe9\x9a\x9b\xe3\x81\xab\xe3\x81\xaf'
    617. 

  617.             '\xe3\x80\x8cWenn ist das Nunstuck git und'
    618. 

  618.         )
    619. 

  619. 

  620.         # UTF-8 specific decoding tests
    621. 

  621.         self.assertEqual(unicode('\xf0\xa3\x91\x96', 'utf-8'), u'\U00023456')
    622. 

  622.         self.assertEqual(unicode('\xf0\x90\x80\x82', 'utf-8'), u'\U00010002')
    623. 

  623.         self.assertEqual(unicode('\xe2\x82\xac', 'utf-8'), u'\u20ac')
    624. 

  624. 

  625.         # Other possible utf-8 test cases:
    626. 

  626.         # * strict decoding testing for all of the
    627. 

  627.         #   UTF8_ERROR cases in PyUnicode_DecodeUTF8
    628. 

  628. 

  629.     def test_utf8_decode_valid_sequences(self):
    630. 

  630.         sequences = [
    631. 

  631.             # single byte
    632. 

  632.             ('\x00', u'\x00'), ('a', u'a'), ('\x7f', u'\x7f'),
    633. 

  633.             # 2 bytes
    634. 

  634.             ('\xc2\x80', u'\x80'), ('\xdf\xbf', u'\u07ff'),
    635. 

  635.             # 3 bytes
    636. 

  636.             ('\xe0\xa0\x80', u'\u0800'), ('\xed\x9f\xbf', u'\ud7ff'),
    637. 

  637.             ('\xee\x80\x80', u'\uE000'), ('\xef\xbf\xbf', u'\uffff'),
    638. 

  638.             # 4 bytes
    639. 

  639.             ('\xF0\x90\x80\x80', u'\U00010000'),
    640. 

  640.             ('\xf4\x8f\xbf\xbf', u'\U0010FFFF')
    641. 

  641.         ]
    642. 

  642.         for seq, res in sequences:
    643. 

  643.             self.assertEqual(seq.decode('utf-8'), res)
    644. 

  644. 

  645.         for ch in map(unichr, range(0, sys.maxunicode)):
    646. 

  646.             self.assertEqual(ch, ch.encode('utf-8').decode('utf-8'))
    647. 

  647. 

  648.     def test_utf8_decode_invalid_sequences(self):
    649. 

  649.         # continuation bytes in a sequence of 2, 3, or 4 bytes
    650. 

  650.         continuation_bytes = map(chr, range(0x80, 0xC0))
    651. 

  651.         # start bytes of a 2-byte sequence equivalent to codepoints < 0x7F
    652. 

  652.         invalid_2B_seq_start_bytes = map(chr, range(0xC0, 0xC2))
    653. 

  653.         # start bytes of a 4-byte sequence equivalent to codepoints > 0x10FFFF
    654. 

  654.         invalid_4B_seq_start_bytes = map(chr, range(0xF5, 0xF8))
    655. 

  655.         invalid_start_bytes = (
    656. 

  656.             continuation_bytes + invalid_2B_seq_start_bytes +
    657. 

  657.             invalid_4B_seq_start_bytes + map(chr, range(0xF7, 0x100))
    658. 

  658.         )
    659. 

  659. 

  660.         for byte in invalid_start_bytes:
    661. 

  661.             self.assertRaises(UnicodeDecodeError, byte.decode, 'utf-8')
    662. 

  662. 

  663.         for sb in invalid_2B_seq_start_bytes:
    664. 

  664.             for cb in continuation_bytes:
    665. 

  665.                 self.assertRaises(UnicodeDecodeError, (sb+cb).decode, 'utf-8')
    666. 

  666. 

  667.         for sb in invalid_4B_seq_start_bytes:
    668. 

  668.             for cb1 in continuation_bytes[:3]:
    669. 

  669.                 for cb3 in continuation_bytes[:3]:
    670. 

  670.                     self.assertRaises(UnicodeDecodeError,
    671. 

  671.                                       (sb+cb1+'\x80'+cb3).decode, 'utf-8')
    672. 

  672. 

  673.         for cb in map(chr, range(0x80, 0xA0)):
    674. 

  674.             self.assertRaises(UnicodeDecodeError,
    675. 

  675.                               ('\xE0'+cb+'\x80').decode, 'utf-8')
    676. 

  676.             self.assertRaises(UnicodeDecodeError,
    677. 

  677.                               ('\xE0'+cb+'\xBF').decode, 'utf-8')
    678. 

  678.         # XXX: surrogates shouldn't be valid UTF-8!
    679. 

  679.         # see http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
    680. 

  680.         # (table 3-7) and http://www.rfc-editor.org/rfc/rfc3629.txt
    681. 

  681.         #for cb in map(chr, range(0xA0, 0xC0)):
    682. 

  682.             #self.assertRaises(UnicodeDecodeError,
    683. 

  683.                               #('\xED'+cb+'\x80').decode, 'utf-8')
    684. 

  684.             #self.assertRaises(UnicodeDecodeError,
    685. 

  685.                               #('\xED'+cb+'\xBF').decode, 'utf-8')
    686. 

  686.         # but since they are valid on Python 2 add a test for that:
    687. 

  687.         for cb, surrogate in zip(map(chr, range(0xA0, 0xC0)),
    688. 

  688.                                  map(unichr, range(0xd800, 0xe000, 64))):
    689. 

  689.             encoded = '\xED'+cb+'\x80'
    690. 

  690.             self.assertEqual(encoded.decode('utf-8'), surrogate)
    691. 

  691.             self.assertEqual(surrogate.encode('utf-8'), encoded)
    692. 

  692. 

  693.         for cb in map(chr, range(0x80, 0x90)):
    694. 

  694.             self.assertRaises(UnicodeDecodeError,
    695. 

  695.                               ('\xF0'+cb+'\x80\x80').decode, 'utf-8')
    696. 

  696.             self.assertRaises(UnicodeDecodeError,
    697. 

  697.                               ('\xF0'+cb+'\xBF\xBF').decode, 'utf-8')
    698. 

  698.         for cb in map(chr, range(0x90, 0xC0)):
    699. 

  699.             self.assertRaises(UnicodeDecodeError,
    700. 

  700.                               ('\xF4'+cb+'\x80\x80').decode, 'utf-8')
    701. 

  701.             self.assertRaises(UnicodeDecodeError,
    702. 

  702.                               ('\xF4'+cb+'\xBF\xBF').decode, 'utf-8')
    703. 

  703. 

  704.     def test_issue8271(self):
    705. 

  705.         # Issue #8271: during the decoding of an invalid UTF-8 byte sequence,
    706. 

  706.         # only the start byte and the continuation byte(s) are now considered
    707. 

  707.         # invalid, instead of the number of bytes specified by the start byte.
    708. 

  708.         # See http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf (page 95,
    709. 

  709.         # table 3-8, Row 2) for more information about the algorithm used.
    710. 

  710.         FFFD = u'\ufffd'
    711. 

  711.         sequences = [
    712. 

  712.             # invalid start bytes
    713. 

  713.             ('\x80', FFFD), # continuation byte
    714. 

  714.             ('\x80\x80', FFFD*2), # 2 continuation bytes
    715. 

  715.             ('\xc0', FFFD),
    716. 

  716.             ('\xc0\xc0', FFFD*2),
    717. 

  717.             ('\xc1', FFFD),
    718. 

  718.             ('\xc1\xc0', FFFD*2),
    719. 

  719.             ('\xc0\xc1', FFFD*2),
    720. 

  720.             # with start byte of a 2-byte sequence
    721. 

  721.             ('\xc2', FFFD), # only the start byte
    722. 

  722.             ('\xc2\xc2', FFFD*2), # 2 start bytes
    723. 

  723.             ('\xc2\xc2\xc2', FFFD*3), # 2 start bytes
    724. 

  724.             ('\xc2\x41', FFFD+'A'), # invalid continuation byte
    725. 

  725.             # with start byte of a 3-byte sequence
    726. 

  726.             ('\xe1', FFFD), # only the start byte
    727. 

  727.             ('\xe1\xe1', FFFD*2), # 2 start bytes
    728. 

  728.             ('\xe1\xe1\xe1', FFFD*3), # 3 start bytes
    729. 

  729.             ('\xe1\xe1\xe1\xe1', FFFD*4), # 4 start bytes
    730. 

  730.             ('\xe1\x80', FFFD), # only 1 continuation byte
    731. 

  731.             ('\xe1\x41', FFFD+'A'), # invalid continuation byte
    732. 

  732.             ('\xe1\x41\x80', FFFD+'A'+FFFD), # invalid cb followed by valid cb
    733. 

  733.             ('\xe1\x41\x41', FFFD+'AA'), # 2 invalid continuation bytes
    734. 

  734.             ('\xe1\x80\x41', FFFD+'A'), # only 1 valid continuation byte
    735. 

  735.             ('\xe1\x80\xe1\x41', FFFD*2+'A'), # 1 valid and the other invalid
    736. 

  736.             ('\xe1\x41\xe1\x80', FFFD+'A'+FFFD), # 1 invalid and the other valid
    737. 

  737.             # with start byte of a 4-byte sequence
    738. 

  738.             ('\xf1', FFFD), # only the start byte
    739. 

  739.             ('\xf1\xf1', FFFD*2), # 2 start bytes
    740. 

  740.             ('\xf1\xf1\xf1', FFFD*3), # 3 start bytes
    741. 

  741.             ('\xf1\xf1\xf1\xf1', FFFD*4), # 4 start bytes
    742. 

  742.             ('\xf1\xf1\xf1\xf1\xf1', FFFD*5), # 5 start bytes
    743. 

  743.             ('\xf1\x80', FFFD), # only 1 continuation bytes
    744. 

  744.             ('\xf1\x80\x80', FFFD), # only 2 continuation bytes
    745. 

  745.             ('\xf1\x80\x41', FFFD+'A'), # 1 valid cb and 1 invalid
    746. 

  746.             ('\xf1\x80\x41\x41', FFFD+'AA'), # 1 valid cb and 1 invalid
    747. 

  747.             ('\xf1\x80\x80\x41', FFFD+'A'), # 2 valid cb and 1 invalid
    748. 

  748.             ('\xf1\x41\x80', FFFD+'A'+FFFD), # 1 invalid cv and 1 valid
    749. 

  749.             ('\xf1\x41\x80\x80', FFFD+'A'+FFFD*2), # 1 invalid cb and 2 invalid
    750. 

  750.             ('\xf1\x41\x80\x41', FFFD+'A'+FFFD+'A'), # 2 invalid cb and 1 invalid
    751. 

  751.             ('\xf1\x41\x41\x80', FFFD+'AA'+FFFD), # 1 valid cb and 1 invalid
    752. 

  752.             ('\xf1\x41\xf1\x80', FFFD+'A'+FFFD),
    753. 

  753.             ('\xf1\x41\x80\xf1', FFFD+'A'+FFFD*2),
    754. 

  754.             ('\xf1\xf1\x80\x41', FFFD*2+'A'),
    755. 

  755.             ('\xf1\x41\xf1\xf1', FFFD+'A'+FFFD*2),
    756. 

  756.             # with invalid start byte of a 4-byte sequence (rfc2279)
    757. 

  757.             ('\xf5', FFFD), # only the start byte
    758. 

  758.             ('\xf5\xf5', FFFD*2), # 2 start bytes
    759. 

  759.             ('\xf5\x80', FFFD*2), # only 1 continuation byte
    760. 

  760.             ('\xf5\x80\x80', FFFD*3), # only 2 continuation byte
    761. 

  761.             ('\xf5\x80\x80\x80', FFFD*4), # 3 continuation bytes
    762. 

  762.             ('\xf5\x80\x41', FFFD*2+'A'), #  1 valid cb and 1 invalid
    763. 

  763.             ('\xf5\x80\x41\xf5', FFFD*2+'A'+FFFD),
    764. 

  764.             ('\xf5\x41\x80\x80\x41', FFFD+'A'+FFFD*2+'A'),
    765. 

  765.             # with invalid start byte of a 5-byte sequence (rfc2279)
    766. 

  766.             ('\xf8', FFFD), # only the start byte
    767. 

  767.             ('\xf8\xf8', FFFD*2), # 2 start bytes
    768. 

  768.             ('\xf8\x80', FFFD*2), # only one continuation byte
    769. 

  769.             ('\xf8\x80\x41', FFFD*2 + 'A'), # 1 valid cb and 1 invalid
    770. 

  770.             ('\xf8\x80\x80\x80\x80', FFFD*5), # invalid 5 bytes seq with 5 bytes
    771. 

  771.             # with invalid start byte of a 6-byte sequence (rfc2279)
    772. 

  772.             ('\xfc', FFFD), # only the start byte
    773. 

  773.             ('\xfc\xfc', FFFD*2), # 2 start bytes
    774. 

  774.             ('\xfc\x80\x80', FFFD*3), # only 2 continuation bytes
    775. 

  775.             ('\xfc\x80\x80\x80\x80\x80', FFFD*6), # 6 continuation bytes
    776. 

  776.             # invalid start byte
    777. 

  777.             ('\xfe', FFFD),
    778. 

  778.             ('\xfe\x80\x80', FFFD*3),
    779. 

  779.             # other sequences
    780. 

  780.             ('\xf1\x80\x41\x42\x43', u'\ufffd\x41\x42\x43'),
    781. 

  781.             ('\xf1\x80\xff\x42\x43', u'\ufffd\ufffd\x42\x43'),
    782. 

  782.             ('\xf1\x80\xc2\x81\x43', u'\ufffd\x81\x43'),
    783. 

  783.             ('\x61\xF1\x80\x80\xE1\x80\xC2\x62\x80\x63\x80\xBF\x64',
    784. 

  784.              u'\x61\uFFFD\uFFFD\uFFFD\x62\uFFFD\x63\uFFFD\uFFFD\x64'),
    785. 

  785.         ]
    786. 

  786.         for n, (seq, res) in enumerate(sequences):
    787. 

  787.             self.assertRaises(UnicodeDecodeError, seq.decode, 'utf-8', 'strict')
    788. 

  788.             self.assertEqual(seq.decode('utf-8', 'replace'), res)
    789. 

  789.             self.assertEqual((seq+'b').decode('utf-8', 'replace'), res+'b')
    790. 

  790.             self.assertEqual(seq.decode('utf-8', 'ignore'),
    791. 

  791.                              res.replace(u'\uFFFD', ''))
    792. 

  792. 

  793.     def test_codecs_idna(self):
    794. 

  794.         # Test whether trailing dot is preserved
    795. 

  795.         self.assertEqual(u"www.python.org.".encode("idna"), "www.python.org.")
    796. 

  796. 

  797.     def test_codecs_errors(self):
    798. 

  798.         # Error handling (encoding)
    799. 

  799.         self.assertRaises(UnicodeError, u'Andr\202 x'.encode, 'ascii')
    800. 

  800.         self.assertRaises(UnicodeError, u'Andr\202 x'.encode, 'ascii','strict')
    801. 

  801.         self.assertEqual(u'Andr\202 x'.encode('ascii','ignore'), "Andr x")
    802. 

  802.         self.assertEqual(u'Andr\202 x'.encode('ascii','replace'), "Andr? x")
    803. 

  803.         self.assertEqual(u'Andr\202 x'.encode('ascii', 'replace'),
    804. 

  804.                          u'Andr\202 x'.encode('ascii', errors='replace'))
    805. 

  805.         self.assertEqual(u'Andr\202 x'.encode('ascii', 'ignore'),
    806. 

  806.                          u'Andr\202 x'.encode(encoding='ascii', errors='ignore'))
    807. 

  807. 

  808.         # Error handling (decoding)
    809. 

  809.         self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii')
    810. 

  810.         self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii','strict')
    811. 

  811.         self.assertEqual(unicode('Andr\202 x','ascii','ignore'), u"Andr x")
    812. 

  812.         self.assertEqual(unicode('Andr\202 x','ascii','replace'), u'Andr\uFFFD x')
    813. 

  813.         self.assertEqual(u'abcde'.decode('ascii', 'ignore'),
    814. 

  814.                          u'abcde'.decode('ascii', errors='ignore'))
    815. 

  815.         self.assertEqual(u'abcde'.decode('ascii', 'replace'),
    816. 

  816.                          u'abcde'.decode(encoding='ascii', errors='replace'))
    817. 

  817. 

  818.         # Error handling (unknown character names)
    819. 

  819.         self.assertEqual("\\N{foo}xx".decode("unicode-escape", "ignore"), u"xx")
    820. 

  820. 

  821.         # Error handling (truncated escape sequence)
    822. 

  822.         self.assertRaises(UnicodeError, "\\".decode, "unicode-escape")
    823. 

  823. 

  824.         self.assertRaises(TypeError, "hello".decode, "test.unicode1")
    825. 

  825.         self.assertRaises(TypeError, unicode, "hello", "test.unicode2")
    826. 

  826.         self.assertRaises(TypeError, u"hello".encode, "test.unicode1")
    827. 

  827.         self.assertRaises(TypeError, u"hello".encode, "test.unicode2")
    828. 

  828.         # executes PyUnicode_Encode()
    829. 

  829.         import imp
    830. 

  830.         self.assertRaises(
    831. 

  831.             ImportError,
    832. 

  832.             imp.find_module,
    833. 

  833.             "non-existing module",
    834. 

  834.             [u"non-existing dir"]
    835. 

  835.         )
    836. 

  836. 

  837.         # Error handling (wrong arguments)
    838. 

  838.         self.assertRaises(TypeError, u"hello".encode, 42, 42, 42)
    839. 

  839. 

  840.         # Error handling (PyUnicode_EncodeDecimal())
    841. 

  841.         self.assertRaises(UnicodeError, int, u"\u0200")
    842. 

  842. 

  843.     def test_codecs(self):
    844. 

  844.         # Encoding
    845. 

  845.         self.assertEqual(u'hello'.encode('ascii'), 'hello')
    846. 

  846.         self.assertEqual(u'hello'.encode('utf-7'), 'hello')
    847. 

  847.         self.assertEqual(u'hello'.encode('utf-8'), 'hello')
    848. 

  848.         self.assertEqual(u'hello'.encode('utf8'), 'hello')
    849. 

  849.         self.assertEqual(u'hello'.encode('utf-16-le'), 'h\000e\000l\000l\000o\000')
    850. 

  850.         self.assertEqual(u'hello'.encode('utf-16-be'), '\000h\000e\000l\000l\000o')
    851. 

  851.         self.assertEqual(u'hello'.encode('latin-1'), 'hello')
    852. 

  852. 

  853.         # Roundtrip safety for BMP (just the first 1024 chars)
    854. 

  854.         for c in xrange(1024):
    855. 

  855.             u = unichr(c)
    856. 

  856.             for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le',
    857. 

  857.                              'utf-16-be', 'raw_unicode_escape',
    858. 

  858.                              'unicode_escape', 'unicode_internal'):
    859. 

  859.                 self.assertEqual(unicode(u.encode(encoding),encoding), u)
    860. 

  860. 

  861.         # Roundtrip safety for BMP (just the first 256 chars)
    862. 

  862.         for c in xrange(256):
    863. 

  863.             u = unichr(c)
    864. 

  864.             for encoding in ('latin-1',):
    865. 

  865.                 self.assertEqual(unicode(u.encode(encoding),encoding), u)
    866. 

  866. 

  867.         # Roundtrip safety for BMP (just the first 128 chars)
    868. 

  868.         for c in xrange(128):
    869. 

  869.             u = unichr(c)
    870. 

  870.             for encoding in ('ascii',):
    871. 

  871.                 self.assertEqual(unicode(u.encode(encoding),encoding), u)
    872. 

  872. 

  873.         # Roundtrip safety for non-BMP (just a few chars)
    874. 

  874.         u = u'\U00010001\U00020002\U00030003\U00040004\U00050005'
    875. 

  875.         for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
    876. 

  876.                          #'raw_unicode_escape',
    877. 

  877.                          'unicode_escape', 'unicode_internal'):
    878. 

  878.             self.assertEqual(unicode(u.encode(encoding),encoding), u)
    879. 

  879. 

  880.         # UTF-8 must be roundtrip safe for all UCS-2 code points
    881. 

  881.         # This excludes surrogates: in the full range, there would be
    882. 

  882.         # a surrogate pair (\udbff\udc00), which gets converted back
    883. 

  883.         # to a non-BMP character (\U0010fc00)
    884. 

  884.         u = u''.join(map(unichr, range(0,0xd800)+range(0xe000,0x10000)))
    885. 

  885.         for encoding in ('utf-8',):
    886. 

  886.             self.assertEqual(unicode(u.encode(encoding),encoding), u)
    887. 

  887. 

  888.     def test_codecs_charmap(self):
    889. 

  889.         # 0-127
    890. 

  890.         s = ''.join(map(chr, xrange(128)))
    891. 

  891.         for encoding in (
    892. 

  892.             'cp037', 'cp1026',
    893. 

  893.             'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
    894. 

  894.             'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
    895. 

  895.             'cp863', 'cp865', 'cp866',
    896. 

  896.             'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
    897. 

  897.             'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
    898. 

  898.             'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1',
    899. 

  899.             'mac_cyrillic', 'mac_latin2',
    900. 

  900. 

  901.             'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
    902. 

  902.             'cp1256', 'cp1257', 'cp1258',
    903. 

  903.             'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
    904. 

  904. 

  905.             'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
    906. 

  906.             'cp1006', 'iso8859_8',
    907. 

  907. 

  908.             ### These have undefined mappings:
    909. 

  909.             #'cp424',
    910. 

  910. 

  911.             ### These fail the round-trip:
    912. 

  912.             #'cp875'
    913. 

  913. 

  914.             ):
    915. 

  915.             self.assertEqual(unicode(s, encoding).encode(encoding), s)
    916. 

  916. 

  917.         # 128-255
    918. 

  918.         s = ''.join(map(chr, xrange(128, 256)))
    919. 

  919.         for encoding in (
    920. 

  920.             'cp037', 'cp1026',
    921. 

  921.             'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
    922. 

  922.             'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
    923. 

  923.             'cp863', 'cp865', 'cp866',
    924. 

  924.             'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
    925. 

  925.             'iso8859_2', 'iso8859_4', 'iso8859_5',
    926. 

  926.             'iso8859_9', 'koi8_r', 'latin_1',
    927. 

  927.             'mac_cyrillic', 'mac_latin2',
    928. 

  928. 

  929.             ### These have undefined mappings:
    930. 

  930.             #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
    931. 

  931.             #'cp1256', 'cp1257', 'cp1258',
    932. 

  932.             #'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
    933. 

  933.             #'iso8859_3', 'iso8859_6', 'iso8859_7',
    934. 

  934.             #'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
    935. 

  935. 

  936.             ### These fail the round-trip:
    937. 

  937.             #'cp1006', 'cp875', 'iso8859_8',
    938. 

  938. 

  939.             ):
    940. 

  940.             self.assertEqual(unicode(s, encoding).encode(encoding), s)
    941. 

  941. 

  942.     def test_concatenation(self):
    943. 

  943.         self.assertEqual((u"abc" u"def"), u"abcdef")
    944. 

  944.         self.assertEqual(("abc" u"def"), u"abcdef")
    945. 

  945.         self.assertEqual((u"abc" "def"), u"abcdef")
    946. 

  946.         self.assertEqual((u"abc" u"def" "ghi"), u"abcdefghi")
    947. 

  947.         self.assertEqual(("abc" "def" u"ghi"), u"abcdefghi")
    948. 

  948. 

  949.     def test_printing(self):
    950. 

  950.         class BitBucket:
    951. 

  951.             def write(self, text):
    952. 

  952.                 pass
    953. 

  953. 

  954.         out = BitBucket()
    955. 

  955.         print >>out, u'abc'
    956. 

  956.         print >>out, u'abc', u'def'
    957. 

  957.         print >>out, u'abc', 'def'
    958. 

  958.         print >>out, 'abc', u'def'
    959. 

  959.         print >>out, u'abc\n'
    960. 

  960.         print >>out, u'abc\n',
    961. 

  961.         print >>out, u'abc\n',
    962. 

  962.         print >>out, u'def\n'
    963. 

  963.         print >>out, u'def\n'
    964. 

  964. 

  965.     def test_ucs4(self):
    966. 

  966.         x = u'\U00100000'
    967. 

  967.         y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
    968. 

  968.         self.assertEqual(x, y)
    969. 

  969. 

  970.         y = r'\U00100000'
    971. 

  971.         x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
    972. 

  972.         self.assertEqual(x, y)
    973. 

  973.         y = r'\U00010000'
    974. 

  974.         x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
    975. 

  975.         self.assertEqual(x, y)
    976. 

  976. 

  977.         try:
    978. 

  978.             '\U11111111'.decode("raw-unicode-escape")
    979. 

  979.         except UnicodeDecodeError as e:
    980. 

  980.             self.assertEqual(e.start, 0)
    981. 

  981.             self.assertEqual(e.end, 10)
    982. 

  982.         else:
    983. 

  983.             self.fail("Should have raised UnicodeDecodeError")
    984. 

  984. 

  985.     def test_conversion(self):
    986. 

  986.         # Make sure __unicode__() works properly
    987. 

  987.         class Foo0:
    988. 

  988.             def __str__(self):
    989. 

  989.                 return "foo"
    990. 

  990. 

  991.         class Foo1:
    992. 

  992.             def __unicode__(self):
    993. 

  993.                 return u"foo"
    994. 

  994. 

  995.         class Foo2(object):
    996. 

  996.             def __unicode__(self):
    997. 

  997.                 return u"foo"
    998. 

  998. 

  999.         class Foo3(object):
    1000. 

  1000.             def __unicode__(self):
    1001. 

  1001.                 return "foo"
    1002. 

  1002. 

  1003.         class Foo4(str):
    1004. 

  1004.             def __unicode__(self):
    1005. 

  1005.                 return "foo"
    1006. 

  1006. 

  1007.         class Foo5(unicode):
    1008. 

  1008.             def __unicode__(self):
    1009. 

  1009.                 return "foo"
    1010. 

  1010. 

  1011.         class Foo6(str):
    1012. 

  1012.             def __str__(self):
    1013. 

  1013.                 return "foos"
    1014. 

  1014. 

  1015.             def __unicode__(self):
    1016. 

  1016.                 return u"foou"
    1017. 

  1017. 

  1018.         class Foo7(unicode):
    1019. 

  1019.             def __str__(self):
    1020. 

  1020.                 return "foos"
    1021. 

  1021.             def __unicode__(self):
    1022. 

  1022.                 return u"foou"
    1023. 

  1023. 

  1024.         class Foo8(unicode):
    1025. 

  1025.             def __new__(cls, content=""):
    1026. 

  1026.                 return unicode.__new__(cls, 2*content)
    1027. 

  1027.             def __unicode__(self):
    1028. 

  1028.                 return self
    1029. 

  1029. 

  1030.         class Foo9(unicode):
    1031. 

  1031.             def __str__(self):
    1032. 

  1032.                 return "string"
    1033. 

  1033.             def __unicode__(self):
    1034. 

  1034.                 return "not unicode"
    1035. 

  1035. 

  1036.         self.assertEqual(unicode(Foo0()), u"foo")
    1037. 

  1037.         self.assertEqual(unicode(Foo1()), u"foo")
    1038. 

  1038.         self.assertEqual(unicode(Foo2()), u"foo")
    1039. 

  1039.         self.assertEqual(unicode(Foo3()), u"foo")
    1040. 

  1040.         self.assertEqual(unicode(Foo4("bar")), u"foo")
    1041. 

  1041.         self.assertEqual(unicode(Foo5("bar")), u"foo")
    1042. 

  1042.         self.assertEqual(unicode(Foo6("bar")), u"foou")
    1043. 

  1043.         self.assertEqual(unicode(Foo7("bar")), u"foou")
    1044. 

  1044.         self.assertEqual(unicode(Foo8("foo")), u"foofoo")
    1045. 

  1045.         self.assertEqual(str(Foo9("foo")), "string")
    1046. 

  1046.         self.assertEqual(unicode(Foo9("foo")), u"not unicode")
    1047. 

  1047. 

  1048.     def test_unicode_repr(self):
    1049. 

  1049.         class s1:
    1050. 

  1050.             def __repr__(self):
    1051. 

  1051.                 return '\\n'
    1052. 

  1052. 

  1053.         class s2:
    1054. 

  1054.             def __repr__(self):
    1055. 

  1055.                 return u'\\n'
    1056. 

  1056. 

  1057.         self.assertEqual(repr(s1()), '\\n')
    1058. 

  1058.         self.assertEqual(repr(s2()), '\\n')
    1059. 

  1059. 

  1060.     def test_expandtabs_overflows_gracefully(self):
    1061. 

  1061.         # This test only affects 32-bit platforms because expandtabs can only take
    1062. 

  1062.         # an int as the max value, not a 64-bit C long.  If expandtabs is changed
    1063. 

  1063.         # to take a 64-bit long, this test should apply to all platforms.
    1064. 

  1064.         if sys.maxint > (1 << 32) or struct.calcsize('P') != 4:
    1065. 

  1065.             return
    1066. 

  1066.         self.assertRaises((OverflowError, MemoryError),
    1067. 

  1067.                           u't\tt\t'.expandtabs, sys.maxint)
    1068. 

  1068. 

  1069.     def test__format__(self):
    1070. 

  1070.         def test(value, format, expected):
    1071. 

  1071.             # test both with and without the trailing 's'
    1072. 

  1072.             self.assertEqual(value.__format__(format), expected)
    1073. 

  1073.             self.assertEqual(value.__format__(format + u's'), expected)
    1074. 

  1074. 

  1075.         test(u'', u'', u'')
    1076. 

  1076.         test(u'abc', u'', u'abc')
    1077. 

  1077.         test(u'abc', u'.3', u'abc')
    1078. 

  1078.         test(u'ab', u'.3', u'ab')
    1079. 

  1079.         test(u'abcdef', u'.3', u'abc')
    1080. 

  1080.         test(u'abcdef', u'.0', u'')
    1081. 

  1081.         test(u'abc', u'3.3', u'abc')
    1082. 

  1082.         test(u'abc', u'2.3', u'abc')
    1083. 

  1083.         test(u'abc', u'2.2', u'ab')
    1084. 

  1084.         test(u'abc', u'3.2', u'ab ')
    1085. 

  1085.         test(u'result', u'x<0', u'result')
    1086. 

  1086.         test(u'result', u'x<5', u'result')
    1087. 

  1087.         test(u'result', u'x<6', u'result')
    1088. 

  1088.         test(u'result', u'x<7', u'resultx')
    1089. 

  1089.         test(u'result', u'x<8', u'resultxx')
    1090. 

  1090.         test(u'result', u' <7', u'result ')
    1091. 

  1091.         test(u'result', u'<7', u'result ')
    1092. 

  1092.         test(u'result', u'>7', u' result')
    1093. 

  1093.         test(u'result', u'>8', u'  result')
    1094. 

  1094.         test(u'result', u'^8', u' result ')
    1095. 

  1095.         test(u'result', u'^9', u' result  ')
    1096. 

  1096.         test(u'result', u'^10', u'  result  ')
    1097. 

  1097.         test(u'a', u'10000', u'a' + u' ' * 9999)
    1098. 

  1098.         test(u'', u'10000', u' ' * 10000)
    1099. 

  1099.         test(u'', u'10000000', u' ' * 10000000)
    1100. 

  1100. 

  1101.         # test mixing unicode and str
    1102. 

  1102.         self.assertEqual(u'abc'.__format__('s'), u'abc')
    1103. 

  1103.         self.assertEqual(u'abc'.__format__('->10s'), u'-------abc')
    1104. 

  1104. 

  1105.     def test_format(self):
    1106. 

  1106.         self.assertEqual(u''.format(), u'')
    1107. 

  1107.         self.assertEqual(u'a'.format(), u'a')
    1108. 

  1108.         self.assertEqual(u'ab'.format(), u'ab')
    1109. 

  1109.         self.assertEqual(u'a{{'.format(), u'a{')
    1110. 

  1110.         self.assertEqual(u'a}}'.format(), u'a}')
    1111. 

  1111.         self.assertEqual(u'{{b'.format(), u'{b')
    1112. 

  1112.         self.assertEqual(u'}}b'.format(), u'}b')
    1113. 

  1113.         self.assertEqual(u'a{{b'.format(), u'a{b')
    1114. 

  1114. 

  1115.         # examples from the PEP:
    1116. 

  1116.         import datetime
    1117. 

  1117.         self.assertEqual(u"My name is {0}".format(u'Fred'), u"My name is Fred")
    1118. 

  1118.         self.assertEqual(u"My name is {0[name]}".format(dict(name=u'Fred')),
    1119. 

  1119.                          u"My name is Fred")
    1120. 

  1120.         self.assertEqual(u"My name is {0} :-{{}}".format(u'Fred'),
    1121. 

  1121.                          u"My name is Fred :-{}")
    1122. 

  1122. 

  1123.         # datetime.__format__ doesn't work with uni…
    1124.

Large files files are truncated, but you can click here to view the full file