| 1 | # -*- coding: iso-8859-1 -*-
|
|---|
| 2 | """ Test script for the Unicode implementation.
|
|---|
| 3 |
|
|---|
| 4 | Written by Marc-Andre Lemburg ([email protected]).
|
|---|
| 5 |
|
|---|
| 6 | (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|---|
| 7 |
|
|---|
| 8 | """#"
|
|---|
| 9 | import unittest, sys, string, codecs, new
|
|---|
| 10 | from test import test_support, string_tests
|
|---|
| 11 |
|
|---|
| 12 | # Error handling (bad decoder return)
|
|---|
| 13 | def search_function(encoding):
|
|---|
| 14 | def decode1(input, errors="strict"):
|
|---|
| 15 | return 42 # not a tuple
|
|---|
| 16 | def encode1(input, errors="strict"):
|
|---|
| 17 | return 42 # not a tuple
|
|---|
| 18 | def encode2(input, errors="strict"):
|
|---|
| 19 | return (42, 42) # no unicode
|
|---|
| 20 | def decode2(input, errors="strict"):
|
|---|
| 21 | return (42, 42) # no unicode
|
|---|
| 22 | if encoding=="test.unicode1":
|
|---|
| 23 | return (encode1, decode1, None, None)
|
|---|
| 24 | elif encoding=="test.unicode2":
|
|---|
| 25 | return (encode2, decode2, None, None)
|
|---|
| 26 | else:
|
|---|
| 27 | return None
|
|---|
| 28 | codecs.register(search_function)
|
|---|
| 29 |
|
|---|
| 30 | class UnicodeTest(
|
|---|
| 31 | string_tests.CommonTest,
|
|---|
| 32 | string_tests.MixinStrUnicodeUserStringTest,
|
|---|
| 33 | string_tests.MixinStrUnicodeTest,
|
|---|
| 34 | ):
|
|---|
| 35 | type2test = unicode
|
|---|
| 36 |
|
|---|
| 37 | def checkequalnofix(self, result, object, methodname, *args):
|
|---|
| 38 | method = getattr(object, methodname)
|
|---|
| 39 | realresult = method(*args)
|
|---|
| 40 | self.assertEqual(realresult, result)
|
|---|
| 41 | self.assert_(type(realresult) is type(result))
|
|---|
| 42 |
|
|---|
| 43 | # if the original is returned make sure that
|
|---|
| 44 | # this doesn't happen with subclasses
|
|---|
| 45 | if realresult is object:
|
|---|
| 46 | class usub(unicode):
|
|---|
| 47 | def __repr__(self):
|
|---|
| 48 | return 'usub(%r)' % unicode.__repr__(self)
|
|---|
| 49 | object = usub(object)
|
|---|
| 50 | method = getattr(object, methodname)
|
|---|
| 51 | realresult = method(*args)
|
|---|
| 52 | self.assertEqual(realresult, result)
|
|---|
| 53 | self.assert_(object is not realresult)
|
|---|
| 54 |
|
|---|
| 55 | def test_literals(self):
|
|---|
| 56 | self.assertEqual(u'\xff', u'\u00ff')
|
|---|
| 57 | self.assertEqual(u'\uffff', u'\U0000ffff')
|
|---|
| 58 | self.assertRaises(UnicodeError, eval, 'u\'\\Ufffffffe\'')
|
|---|
| 59 | self.assertRaises(UnicodeError, eval, 'u\'\\Uffffffff\'')
|
|---|
| 60 | self.assertRaises(UnicodeError, eval, 'u\'\\U%08x\'' % 0x110000)
|
|---|
| 61 |
|
|---|
| 62 | def test_repr(self):
|
|---|
| 63 | if not sys.platform.startswith('java'):
|
|---|
| 64 | # Test basic sanity of repr()
|
|---|
| 65 | self.assertEqual(repr(u'abc'), "u'abc'")
|
|---|
| 66 | self.assertEqual(repr(u'ab\\c'), "u'ab\\\\c'")
|
|---|
| 67 | self.assertEqual(repr(u'ab\\'), "u'ab\\\\'")
|
|---|
| 68 | self.assertEqual(repr(u'\\c'), "u'\\\\c'")
|
|---|
| 69 | self.assertEqual(repr(u'\\'), "u'\\\\'")
|
|---|
| 70 | self.assertEqual(repr(u'\n'), "u'\\n'")
|
|---|
| 71 | self.assertEqual(repr(u'\r'), "u'\\r'")
|
|---|
| 72 | self.assertEqual(repr(u'\t'), "u'\\t'")
|
|---|
| 73 | self.assertEqual(repr(u'\b'), "u'\\x08'")
|
|---|
| 74 | self.assertEqual(repr(u"'\""), """u'\\'"'""")
|
|---|
| 75 | self.assertEqual(repr(u"'\""), """u'\\'"'""")
|
|---|
| 76 | self.assertEqual(repr(u"'"), '''u"'"''')
|
|---|
| 77 | self.assertEqual(repr(u'"'), """u'"'""")
|
|---|
| 78 | latin1repr = (
|
|---|
| 79 | "u'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
|
|---|
| 80 | "\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
|
|---|
| 81 | "\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
|
|---|
| 82 | "JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
|
|---|
| 83 | "\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
|
|---|
| 84 | "\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
|
|---|
| 85 | "\\x9c\\x9d\\x9e\\x9f\\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9"
|
|---|
| 86 | "\\xaa\\xab\\xac\\xad\\xae\\xaf\\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7"
|
|---|
| 87 | "\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\\xc0\\xc1\\xc2\\xc3\\xc4\\xc5"
|
|---|
| 88 | "\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\\xd0\\xd1\\xd2\\xd3"
|
|---|
| 89 | "\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\\xe0\\xe1"
|
|---|
| 90 | "\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef"
|
|---|
| 91 | "\\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd"
|
|---|
| 92 | "\\xfe\\xff'")
|
|---|
| 93 | testrepr = repr(u''.join(map(unichr, xrange(256))))
|
|---|
| 94 | self.assertEqual(testrepr, latin1repr)
|
|---|
| 95 | # Test repr works on wide unicode escapes without overflow.
|
|---|
| 96 | self.assertEqual(repr(u"\U00010000" * 39 + u"\uffff" * 4096),
|
|---|
| 97 | repr(u"\U00010000" * 39 + u"\uffff" * 4096))
|
|---|
| 98 |
|
|---|
| 99 |
|
|---|
| 100 | def test_count(self):
|
|---|
| 101 | string_tests.CommonTest.test_count(self)
|
|---|
| 102 | # check mixed argument types
|
|---|
| 103 | self.checkequalnofix(3, 'aaa', 'count', u'a')
|
|---|
| 104 | self.checkequalnofix(0, 'aaa', 'count', u'b')
|
|---|
| 105 | self.checkequalnofix(3, u'aaa', 'count', 'a')
|
|---|
| 106 | self.checkequalnofix(0, u'aaa', 'count', 'b')
|
|---|
| 107 | self.checkequalnofix(0, u'aaa', 'count', 'b')
|
|---|
| 108 | self.checkequalnofix(1, u'aaa', 'count', 'a', -1)
|
|---|
| 109 | self.checkequalnofix(3, u'aaa', 'count', 'a', -10)
|
|---|
| 110 | self.checkequalnofix(2, u'aaa', 'count', 'a', 0, -1)
|
|---|
| 111 | self.checkequalnofix(0, u'aaa', 'count', 'a', 0, -10)
|
|---|
| 112 |
|
|---|
| 113 | def test_find(self):
|
|---|
| 114 | self.checkequalnofix(0, u'abcdefghiabc', 'find', u'abc')
|
|---|
| 115 | self.checkequalnofix(9, u'abcdefghiabc', 'find', u'abc', 1)
|
|---|
| 116 | self.checkequalnofix(-1, u'abcdefghiabc', 'find', u'def', 4)
|
|---|
| 117 |
|
|---|
| 118 | self.assertRaises(TypeError, u'hello'.find)
|
|---|
| 119 | self.assertRaises(TypeError, u'hello'.find, 42)
|
|---|
| 120 |
|
|---|
| 121 | def test_rfind(self):
|
|---|
| 122 | string_tests.CommonTest.test_rfind(self)
|
|---|
| 123 | # check mixed argument types
|
|---|
| 124 | self.checkequalnofix(9, 'abcdefghiabc', 'rfind', u'abc')
|
|---|
| 125 | self.checkequalnofix(12, 'abcdefghiabc', 'rfind', u'')
|
|---|
| 126 | self.checkequalnofix(12, u'abcdefghiabc', 'rfind', '')
|
|---|
| 127 |
|
|---|
| 128 | def test_index(self):
|
|---|
| 129 | string_tests.CommonTest.test_index(self)
|
|---|
| 130 | # check mixed argument types
|
|---|
| 131 | for (t1, t2) in ((str, unicode), (unicode, str)):
|
|---|
| 132 | self.checkequalnofix(0, t1('abcdefghiabc'), 'index', t2(''))
|
|---|
| 133 | self.checkequalnofix(3, t1('abcdefghiabc'), 'index', t2('def'))
|
|---|
| 134 | self.checkequalnofix(0, t1('abcdefghiabc'), 'index', t2('abc'))
|
|---|
| 135 | self.checkequalnofix(9, t1('abcdefghiabc'), 'index', t2('abc'), 1)
|
|---|
| 136 | self.assertRaises(ValueError, t1('abcdefghiabc').index, t2('hib'))
|
|---|
| 137 | self.assertRaises(ValueError, t1('abcdefghiab').index, t2('abc'), 1)
|
|---|
| 138 | self.assertRaises(ValueError, t1('abcdefghi').index, t2('ghi'), 8)
|
|---|
| 139 | self.assertRaises(ValueError, t1('abcdefghi').index, t2('ghi'), -1)
|
|---|
| 140 |
|
|---|
| 141 | def test_rindex(self):
|
|---|
| 142 | string_tests.CommonTest.test_rindex(self)
|
|---|
| 143 | # check mixed argument types
|
|---|
| 144 | for (t1, t2) in ((str, unicode), (unicode, str)):
|
|---|
| 145 | self.checkequalnofix(12, t1('abcdefghiabc'), 'rindex', t2(''))
|
|---|
| 146 | self.checkequalnofix(3, t1('abcdefghiabc'), 'rindex', t2('def'))
|
|---|
| 147 | self.checkequalnofix(9, t1('abcdefghiabc'), 'rindex', t2('abc'))
|
|---|
| 148 | self.checkequalnofix(0, t1('abcdefghiabc'), 'rindex', t2('abc'), 0, -1)
|
|---|
| 149 |
|
|---|
| 150 | self.assertRaises(ValueError, t1('abcdefghiabc').rindex, t2('hib'))
|
|---|
| 151 | self.assertRaises(ValueError, t1('defghiabc').rindex, t2('def'), 1)
|
|---|
| 152 | self.assertRaises(ValueError, t1('defghiabc').rindex, t2('abc'), 0, -1)
|
|---|
| 153 | self.assertRaises(ValueError, t1('abcdefghi').rindex, t2('ghi'), 0, 8)
|
|---|
| 154 | self.assertRaises(ValueError, t1('abcdefghi').rindex, t2('ghi'), 0, -1)
|
|---|
| 155 |
|
|---|
| 156 | def test_translate(self):
|
|---|
| 157 | self.checkequalnofix(u'bbbc', u'abababc', 'translate', {ord('a'):None})
|
|---|
| 158 | self.checkequalnofix(u'iiic', u'abababc', 'translate', {ord('a'):None, ord('b'):ord('i')})
|
|---|
| 159 | self.checkequalnofix(u'iiix', u'abababc', 'translate', {ord('a'):None, ord('b'):ord('i'), ord('c'):u'x'})
|
|---|
| 160 | self.checkequalnofix(u'<i><i><i>c', u'abababc', 'translate', {ord('a'):None, ord('b'):u'<i>'})
|
|---|
| 161 | self.checkequalnofix(u'c', u'abababc', 'translate', {ord('a'):None, ord('b'):u''})
|
|---|
| 162 | self.checkequalnofix(u'xyyx', u'xzx', 'translate', {ord('z'):u'yy'})
|
|---|
| 163 |
|
|---|
| 164 | self.assertRaises(TypeError, u'hello'.translate)
|
|---|
| 165 | self.assertRaises(TypeError, u'abababc'.translate, {ord('a'):''})
|
|---|
| 166 |
|
|---|
| 167 | def test_split(self):
|
|---|
| 168 | string_tests.CommonTest.test_split(self)
|
|---|
| 169 |
|
|---|
| 170 | # Mixed arguments
|
|---|
| 171 | self.checkequalnofix([u'a', u'b', u'c', u'd'], u'a//b//c//d', 'split', '//')
|
|---|
| 172 | self.checkequalnofix([u'a', u'b', u'c', u'd'], 'a//b//c//d', 'split', u'//')
|
|---|
| 173 | self.checkequalnofix([u'endcase ', u''], u'endcase test', 'split', 'test')
|
|---|
| 174 |
|
|---|
| 175 | def test_join(self):
|
|---|
| 176 | string_tests.MixinStrUnicodeUserStringTest.test_join(self)
|
|---|
| 177 |
|
|---|
| 178 | # mixed arguments
|
|---|
| 179 | self.checkequalnofix(u'a b c d', u' ', 'join', ['a', 'b', u'c', u'd'])
|
|---|
| 180 | self.checkequalnofix(u'abcd', u'', 'join', (u'a', u'b', u'c', u'd'))
|
|---|
| 181 | self.checkequalnofix(u'w x y z', u' ', 'join', string_tests.Sequence('wxyz'))
|
|---|
| 182 | self.checkequalnofix(u'a b c d', ' ', 'join', [u'a', u'b', u'c', u'd'])
|
|---|
| 183 | self.checkequalnofix(u'a b c d', ' ', 'join', ['a', 'b', u'c', u'd'])
|
|---|
| 184 | self.checkequalnofix(u'abcd', '', 'join', (u'a', u'b', u'c', u'd'))
|
|---|
| 185 | self.checkequalnofix(u'w x y z', ' ', 'join', string_tests.Sequence(u'wxyz'))
|
|---|
| 186 |
|
|---|
| 187 | def test_strip(self):
|
|---|
| 188 | string_tests.CommonTest.test_strip(self)
|
|---|
| 189 | self.assertRaises(UnicodeError, u"hello".strip, "\xff")
|
|---|
| 190 |
|
|---|
| 191 | def test_replace(self):
|
|---|
| 192 | string_tests.CommonTest.test_replace(self)
|
|---|
| 193 |
|
|---|
| 194 | # method call forwarded from str implementation because of unicode argument
|
|---|
| 195 | self.checkequalnofix(u'one@two!three!', 'one!two!three!', 'replace', u'!', u'@', 1)
|
|---|
| 196 | self.assertRaises(TypeError, 'replace'.replace, u"r", 42)
|
|---|
| 197 |
|
|---|
| 198 | def test_comparison(self):
|
|---|
| 199 | # Comparisons:
|
|---|
| 200 | self.assertEqual(u'abc', 'abc')
|
|---|
| 201 | self.assertEqual('abc', u'abc')
|
|---|
| 202 | self.assertEqual(u'abc', u'abc')
|
|---|
| 203 | self.assert_(u'abcd' > 'abc')
|
|---|
| 204 | self.assert_('abcd' > u'abc')
|
|---|
| 205 | self.assert_(u'abcd' > u'abc')
|
|---|
| 206 | self.assert_(u'abc' < 'abcd')
|
|---|
| 207 | self.assert_('abc' < u'abcd')
|
|---|
| 208 | self.assert_(u'abc' < u'abcd')
|
|---|
| 209 |
|
|---|
| 210 | if 0:
|
|---|
| 211 | # Move these tests to a Unicode collation module test...
|
|---|
| 212 | # Testing UTF-16 code point order comparisons...
|
|---|
| 213 |
|
|---|
| 214 | # No surrogates, no fixup required.
|
|---|
| 215 | self.assert_(u'\u0061' < u'\u20ac')
|
|---|
| 216 | # Non surrogate below surrogate value, no fixup required
|
|---|
| 217 | self.assert_(u'\u0061' < u'\ud800\udc02')
|
|---|
| 218 |
|
|---|
| 219 | # Non surrogate above surrogate value, fixup required
|
|---|
| 220 | def test_lecmp(s, s2):
|
|---|
| 221 | self.assert_(s < s2)
|
|---|
| 222 |
|
|---|
| 223 | def test_fixup(s):
|
|---|
| 224 | s2 = u'\ud800\udc01'
|
|---|
| 225 | test_lecmp(s, s2)
|
|---|
| 226 | s2 = u'\ud900\udc01'
|
|---|
| 227 | test_lecmp(s, s2)
|
|---|
| 228 | s2 = u'\uda00\udc01'
|
|---|
| 229 | test_lecmp(s, s2)
|
|---|
| 230 | s2 = u'\udb00\udc01'
|
|---|
| 231 | test_lecmp(s, s2)
|
|---|
| 232 | s2 = u'\ud800\udd01'
|
|---|
| 233 | test_lecmp(s, s2)
|
|---|
| 234 | s2 = u'\ud900\udd01'
|
|---|
| 235 | test_lecmp(s, s2)
|
|---|
| 236 | s2 = u'\uda00\udd01'
|
|---|
| 237 | test_lecmp(s, s2)
|
|---|
| 238 | s2 = u'\udb00\udd01'
|
|---|
| 239 | test_lecmp(s, s2)
|
|---|
| 240 | s2 = u'\ud800\ude01'
|
|---|
| 241 | test_lecmp(s, s2)
|
|---|
| 242 | s2 = u'\ud900\ude01'
|
|---|
| 243 | test_lecmp(s, s2)
|
|---|
| 244 | s2 = u'\uda00\ude01'
|
|---|
| 245 | test_lecmp(s, s2)
|
|---|
| 246 | s2 = u'\udb00\ude01'
|
|---|
| 247 | test_lecmp(s, s2)
|
|---|
| 248 | s2 = u'\ud800\udfff'
|
|---|
| 249 | test_lecmp(s, s2)
|
|---|
| 250 | s2 = u'\ud900\udfff'
|
|---|
| 251 | test_lecmp(s, s2)
|
|---|
| 252 | s2 = u'\uda00\udfff'
|
|---|
| 253 | test_lecmp(s, s2)
|
|---|
| 254 | s2 = u'\udb00\udfff'
|
|---|
| 255 | test_lecmp(s, s2)
|
|---|
| 256 |
|
|---|
| 257 | test_fixup(u'\ue000')
|
|---|
| 258 | test_fixup(u'\uff61')
|
|---|
| 259 |
|
|---|
| 260 | # Surrogates on both sides, no fixup required
|
|---|
| 261 | self.assert_(u'\ud800\udc02' < u'\ud84d\udc56')
|
|---|
| 262 |
|
|---|
| 263 | def test_islower(self):
|
|---|
| 264 | string_tests.MixinStrUnicodeUserStringTest.test_islower(self)
|
|---|
| 265 | self.checkequalnofix(False, u'\u1FFc', 'islower')
|
|---|
| 266 |
|
|---|
| 267 | def test_isupper(self):
|
|---|
| 268 | string_tests.MixinStrUnicodeUserStringTest.test_isupper(self)
|
|---|
| 269 | if not sys.platform.startswith('java'):
|
|---|
| 270 | self.checkequalnofix(False, u'\u1FFc', 'isupper')
|
|---|
| 271 |
|
|---|
| 272 | def test_istitle(self):
|
|---|
| 273 | string_tests.MixinStrUnicodeUserStringTest.test_title(self)
|
|---|
| 274 | self.checkequalnofix(True, u'\u1FFc', 'istitle')
|
|---|
| 275 | self.checkequalnofix(True, u'Greek \u1FFcitlecases ...', 'istitle')
|
|---|
| 276 |
|
|---|
| 277 | def test_isspace(self):
|
|---|
| 278 | string_tests.MixinStrUnicodeUserStringTest.test_isspace(self)
|
|---|
| 279 | self.checkequalnofix(True, u'\u2000', 'isspace')
|
|---|
| 280 | self.checkequalnofix(True, u'\u200a', 'isspace')
|
|---|
| 281 | self.checkequalnofix(False, u'\u2014', 'isspace')
|
|---|
| 282 |
|
|---|
| 283 | def test_isalpha(self):
|
|---|
| 284 | string_tests.MixinStrUnicodeUserStringTest.test_isalpha(self)
|
|---|
| 285 | self.checkequalnofix(True, u'\u1FFc', 'isalpha')
|
|---|
| 286 |
|
|---|
| 287 | def test_isdecimal(self):
|
|---|
| 288 | self.checkequalnofix(False, u'', 'isdecimal')
|
|---|
| 289 | self.checkequalnofix(False, u'a', 'isdecimal')
|
|---|
| 290 | self.checkequalnofix(True, u'0', 'isdecimal')
|
|---|
| 291 | self.checkequalnofix(False, u'\u2460', 'isdecimal') # CIRCLED DIGIT ONE
|
|---|
| 292 | self.checkequalnofix(False, u'\xbc', 'isdecimal') # VULGAR FRACTION ONE QUARTER
|
|---|
| 293 | self.checkequalnofix(True, u'\u0660', 'isdecimal') # ARABIC-INDIC DIGIT ZERO
|
|---|
| 294 | self.checkequalnofix(True, u'0123456789', 'isdecimal')
|
|---|
| 295 | self.checkequalnofix(False, u'0123456789a', 'isdecimal')
|
|---|
| 296 |
|
|---|
| 297 | self.checkraises(TypeError, 'abc', 'isdecimal', 42)
|
|---|
| 298 |
|
|---|
| 299 | def test_isdigit(self):
|
|---|
| 300 | string_tests.MixinStrUnicodeUserStringTest.test_isdigit(self)
|
|---|
| 301 | self.checkequalnofix(True, u'\u2460', 'isdigit')
|
|---|
| 302 | self.checkequalnofix(False, u'\xbc', 'isdigit')
|
|---|
| 303 | self.checkequalnofix(True, u'\u0660', 'isdigit')
|
|---|
| 304 |
|
|---|
| 305 | def test_isnumeric(self):
|
|---|
| 306 | self.checkequalnofix(False, u'', 'isnumeric')
|
|---|
| 307 | self.checkequalnofix(False, u'a', 'isnumeric')
|
|---|
| 308 | self.checkequalnofix(True, u'0', 'isnumeric')
|
|---|
| 309 | self.checkequalnofix(True, u'\u2460', 'isnumeric')
|
|---|
| 310 | self.checkequalnofix(True, u'\xbc', 'isnumeric')
|
|---|
| 311 | self.checkequalnofix(True, u'\u0660', 'isnumeric')
|
|---|
| 312 | self.checkequalnofix(True, u'0123456789', 'isnumeric')
|
|---|
| 313 | self.checkequalnofix(False, u'0123456789a', 'isnumeric')
|
|---|
| 314 |
|
|---|
| 315 | self.assertRaises(TypeError, u"abc".isnumeric, 42)
|
|---|
| 316 |
|
|---|
| 317 | def test_contains(self):
|
|---|
| 318 | # Testing Unicode contains method
|
|---|
| 319 | self.assert_('a' in u'abdb')
|
|---|
| 320 | self.assert_('a' in u'bdab')
|
|---|
| 321 | self.assert_('a' in u'bdaba')
|
|---|
| 322 | self.assert_('a' in u'bdba')
|
|---|
| 323 | self.assert_('a' in u'bdba')
|
|---|
| 324 | self.assert_(u'a' in u'bdba')
|
|---|
| 325 | self.assert_(u'a' not in u'bdb')
|
|---|
| 326 | self.assert_(u'a' not in 'bdb')
|
|---|
| 327 | self.assert_(u'a' in 'bdba')
|
|---|
| 328 | self.assert_(u'a' in ('a',1,None))
|
|---|
| 329 | self.assert_(u'a' in (1,None,'a'))
|
|---|
| 330 | self.assert_(u'a' in (1,None,u'a'))
|
|---|
| 331 | self.assert_('a' in ('a',1,None))
|
|---|
| 332 | self.assert_('a' in (1,None,'a'))
|
|---|
| 333 | self.assert_('a' in (1,None,u'a'))
|
|---|
| 334 | self.assert_('a' not in ('x',1,u'y'))
|
|---|
| 335 | self.assert_('a' not in ('x',1,None))
|
|---|
| 336 | self.assert_(u'abcd' not in u'abcxxxx')
|
|---|
| 337 | self.assert_(u'ab' in u'abcd')
|
|---|
| 338 | self.assert_('ab' in u'abc')
|
|---|
| 339 | self.assert_(u'ab' in 'abc')
|
|---|
| 340 | self.assert_(u'ab' in (1,None,u'ab'))
|
|---|
| 341 | self.assert_(u'' in u'abc')
|
|---|
| 342 | self.assert_('' in u'abc')
|
|---|
| 343 |
|
|---|
| 344 | # If the following fails either
|
|---|
| 345 | # the contains operator does not propagate UnicodeErrors or
|
|---|
| 346 | # someone has changed the default encoding
|
|---|
| 347 | self.assertRaises(UnicodeError, 'g\xe2teau'.__contains__, u'\xe2')
|
|---|
| 348 |
|
|---|
| 349 | self.assert_(u'' in '')
|
|---|
| 350 | self.assert_('' in u'')
|
|---|
| 351 | self.assert_(u'' in u'')
|
|---|
| 352 | self.assert_(u'' in 'abc')
|
|---|
| 353 | self.assert_('' in u'abc')
|
|---|
| 354 | self.assert_(u'' in u'abc')
|
|---|
| 355 | self.assert_(u'\0' not in 'abc')
|
|---|
| 356 | self.assert_('\0' not in u'abc')
|
|---|
| 357 | self.assert_(u'\0' not in u'abc')
|
|---|
| 358 | self.assert_(u'\0' in '\0abc')
|
|---|
| 359 | self.assert_('\0' in u'\0abc')
|
|---|
| 360 | self.assert_(u'\0' in u'\0abc')
|
|---|
| 361 | self.assert_(u'\0' in 'abc\0')
|
|---|
| 362 | self.assert_('\0' in u'abc\0')
|
|---|
| 363 | self.assert_(u'\0' in u'abc\0')
|
|---|
| 364 | self.assert_(u'a' in '\0abc')
|
|---|
| 365 | self.assert_('a' in u'\0abc')
|
|---|
| 366 | self.assert_(u'a' in u'\0abc')
|
|---|
| 367 | self.assert_(u'asdf' in 'asdf')
|
|---|
| 368 | self.assert_('asdf' in u'asdf')
|
|---|
| 369 | self.assert_(u'asdf' in u'asdf')
|
|---|
| 370 | self.assert_(u'asdf' not in 'asd')
|
|---|
| 371 | self.assert_('asdf' not in u'asd')
|
|---|
| 372 | self.assert_(u'asdf' not in u'asd')
|
|---|
| 373 | self.assert_(u'asdf' not in '')
|
|---|
| 374 | self.assert_('asdf' not in u'')
|
|---|
| 375 | self.assert_(u'asdf' not in u'')
|
|---|
| 376 |
|
|---|
| 377 | self.assertRaises(TypeError, u"abc".__contains__)
|
|---|
| 378 |
|
|---|
| 379 | def test_formatting(self):
|
|---|
| 380 | string_tests.MixinStrUnicodeUserStringTest.test_formatting(self)
|
|---|
| 381 | # Testing Unicode formatting strings...
|
|---|
| 382 | self.assertEqual(u"%s, %s" % (u"abc", "abc"), u'abc, abc')
|
|---|
| 383 | self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, 2, 3), u'abc, abc, 1, 2.000000, 3.00')
|
|---|
| 384 | self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, -2, 3), u'abc, abc, 1, -2.000000, 3.00')
|
|---|
| 385 | self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.5), u'abc, abc, -1, -2.000000, 3.50')
|
|---|
| 386 | self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.57), u'abc, abc, -1, -2.000000, 3.57')
|
|---|
| 387 | self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 1003.57), u'abc, abc, -1, -2.000000, 1003.57')
|
|---|
| 388 | if not sys.platform.startswith('java'):
|
|---|
| 389 | self.assertEqual(u"%r, %r" % (u"abc", "abc"), u"u'abc', 'abc'")
|
|---|
| 390 | self.assertEqual(u"%(x)s, %(y)s" % {'x':u"abc", 'y':"def"}, u'abc, def')
|
|---|
| 391 | self.assertEqual(u"%(x)s, %(\xfc)s" % {'x':u"abc", u'\xfc':"def"}, u'abc, def')
|
|---|
| 392 |
|
|---|
| 393 | self.assertEqual(u'%c' % 0x1234, u'\u1234')
|
|---|
| 394 | self.assertRaises(OverflowError, u"%c".__mod__, (sys.maxunicode+1,))
|
|---|
| 395 |
|
|---|
| 396 | # formatting jobs delegated from the string implementation:
|
|---|
| 397 | self.assertEqual('...%(foo)s...' % {'foo':u"abc"}, u'...abc...')
|
|---|
| 398 | self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
|
|---|
| 399 | self.assertEqual('...%(foo)s...' % {u'foo':"abc"}, '...abc...')
|
|---|
| 400 | self.assertEqual('...%(foo)s...' % {u'foo':u"abc"}, u'...abc...')
|
|---|
| 401 | self.assertEqual('...%(foo)s...' % {u'foo':u"abc",'def':123}, u'...abc...')
|
|---|
| 402 | self.assertEqual('...%(foo)s...' % {u'foo':u"abc",u'def':123}, u'...abc...')
|
|---|
| 403 | self.assertEqual('...%s...%s...%s...%s...' % (1,2,3,u"abc"), u'...1...2...3...abc...')
|
|---|
| 404 | self.assertEqual('...%%...%%s...%s...%s...%s...%s...' % (1,2,3,u"abc"), u'...%...%s...1...2...3...abc...')
|
|---|
| 405 | self.assertEqual('...%s...' % u"abc", u'...abc...')
|
|---|
| 406 | self.assertEqual('%*s' % (5,u'abc',), u' abc')
|
|---|
| 407 | self.assertEqual('%*s' % (-5,u'abc',), u'abc ')
|
|---|
| 408 | self.assertEqual('%*.*s' % (5,2,u'abc',), u' ab')
|
|---|
| 409 | self.assertEqual('%*.*s' % (5,3,u'abc',), u' abc')
|
|---|
| 410 | self.assertEqual('%i %*.*s' % (10, 5,3,u'abc',), u'10 abc')
|
|---|
| 411 | self.assertEqual('%i%s %*.*s' % (10, 3, 5, 3, u'abc',), u'103 abc')
|
|---|
| 412 | self.assertEqual('%c' % u'a', u'a')
|
|---|
| 413 | class Wrapper:
|
|---|
| 414 | def __str__(self):
|
|---|
| 415 | return u'\u1234'
|
|---|
| 416 | self.assertEqual('%s' % Wrapper(), u'\u1234')
|
|---|
| 417 |
|
|---|
| 418 | @test_support.run_with_locale('LC_ALL', 'de_DE', 'fr_FR')
|
|---|
| 419 | def test_format_float(self):
|
|---|
| 420 | # should not format with a comma, but always with C locale
|
|---|
| 421 | self.assertEqual(u'1.0', u'%.1f' % 1.0)
|
|---|
| 422 |
|
|---|
| 423 | def test_constructor(self):
|
|---|
| 424 | # unicode(obj) tests (this maps to PyObject_Unicode() at C level)
|
|---|
| 425 |
|
|---|
| 426 | self.assertEqual(
|
|---|
| 427 | unicode(u'unicode remains unicode'),
|
|---|
| 428 | u'unicode remains unicode'
|
|---|
| 429 | )
|
|---|
| 430 |
|
|---|
| 431 | class UnicodeSubclass(unicode):
|
|---|
| 432 | pass
|
|---|
| 433 |
|
|---|
| 434 | self.assertEqual(
|
|---|
| 435 | unicode(UnicodeSubclass('unicode subclass becomes unicode')),
|
|---|
| 436 | u'unicode subclass becomes unicode'
|
|---|
| 437 | )
|
|---|
| 438 |
|
|---|
| 439 | self.assertEqual(
|
|---|
| 440 | unicode('strings are converted to unicode'),
|
|---|
| 441 | u'strings are converted to unicode'
|
|---|
| 442 | )
|
|---|
| 443 |
|
|---|
| 444 | class UnicodeCompat:
|
|---|
| 445 | def __init__(self, x):
|
|---|
| 446 | self.x = x
|
|---|
| 447 | def __unicode__(self):
|
|---|
| 448 | return self.x
|
|---|
| 449 |
|
|---|
| 450 | self.assertEqual(
|
|---|
| 451 | unicode(UnicodeCompat('__unicode__ compatible objects are recognized')),
|
|---|
| 452 | u'__unicode__ compatible objects are recognized')
|
|---|
| 453 |
|
|---|
| 454 | class StringCompat:
|
|---|
| 455 | def __init__(self, x):
|
|---|
| 456 | self.x = x
|
|---|
| 457 | def __str__(self):
|
|---|
| 458 | return self.x
|
|---|
| 459 |
|
|---|
| 460 | self.assertEqual(
|
|---|
| 461 | unicode(StringCompat('__str__ compatible objects are recognized')),
|
|---|
| 462 | u'__str__ compatible objects are recognized'
|
|---|
| 463 | )
|
|---|
| 464 |
|
|---|
| 465 | # unicode(obj) is compatible to str():
|
|---|
| 466 |
|
|---|
| 467 | o = StringCompat('unicode(obj) is compatible to str()')
|
|---|
| 468 | self.assertEqual(unicode(o), u'unicode(obj) is compatible to str()')
|
|---|
| 469 | self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
|
|---|
| 470 |
|
|---|
| 471 | # %-formatting and .__unicode__()
|
|---|
| 472 | self.assertEqual(u'%s' %
|
|---|
| 473 | UnicodeCompat(u"u'%s' % obj uses obj.__unicode__()"),
|
|---|
| 474 | u"u'%s' % obj uses obj.__unicode__()")
|
|---|
| 475 | self.assertEqual(u'%s' %
|
|---|
| 476 | UnicodeCompat(u"u'%s' % obj falls back to obj.__str__()"),
|
|---|
| 477 | u"u'%s' % obj falls back to obj.__str__()")
|
|---|
| 478 |
|
|---|
| 479 | for obj in (123, 123.45, 123L):
|
|---|
| 480 | self.assertEqual(unicode(obj), unicode(str(obj)))
|
|---|
| 481 |
|
|---|
| 482 | # unicode(obj, encoding, error) tests (this maps to
|
|---|
| 483 | # PyUnicode_FromEncodedObject() at C level)
|
|---|
| 484 |
|
|---|
| 485 | if not sys.platform.startswith('java'):
|
|---|
| 486 | self.assertRaises(
|
|---|
| 487 | TypeError,
|
|---|
| 488 | unicode,
|
|---|
| 489 | u'decoding unicode is not supported',
|
|---|
| 490 | 'utf-8',
|
|---|
| 491 | 'strict'
|
|---|
| 492 | )
|
|---|
| 493 |
|
|---|
| 494 | self.assertEqual(
|
|---|
| 495 | unicode('strings are decoded to unicode', 'utf-8', 'strict'),
|
|---|
| 496 | u'strings are decoded to unicode'
|
|---|
| 497 | )
|
|---|
| 498 |
|
|---|
| 499 | if not sys.platform.startswith('java'):
|
|---|
| 500 | self.assertEqual(
|
|---|
| 501 | unicode(
|
|---|
| 502 | buffer('character buffers are decoded to unicode'),
|
|---|
| 503 | 'utf-8',
|
|---|
| 504 | 'strict'
|
|---|
| 505 | ),
|
|---|
| 506 | u'character buffers are decoded to unicode'
|
|---|
| 507 | )
|
|---|
| 508 |
|
|---|
| 509 | self.assertRaises(TypeError, unicode, 42, 42, 42)
|
|---|
| 510 |
|
|---|
| 511 | def test_codecs_utf7(self):
|
|---|
| 512 | utfTests = [
|
|---|
| 513 | (u'A\u2262\u0391.', 'A+ImIDkQ.'), # RFC2152 example
|
|---|
| 514 | (u'Hi Mom -\u263a-!', 'Hi Mom -+Jjo--!'), # RFC2152 example
|
|---|
| 515 | (u'\u65E5\u672C\u8A9E', '+ZeVnLIqe-'), # RFC2152 example
|
|---|
| 516 | (u'Item 3 is \u00a31.', 'Item 3 is +AKM-1.'), # RFC2152 example
|
|---|
| 517 | (u'+', '+-'),
|
|---|
| 518 | (u'+-', '+--'),
|
|---|
| 519 | (u'+?', '+-?'),
|
|---|
| 520 | (u'\?', '+AFw?'),
|
|---|
| 521 | (u'+?', '+-?'),
|
|---|
| 522 | (ur'\\?', '+AFwAXA?'),
|
|---|
| 523 | (ur'\\\?', '+AFwAXABc?'),
|
|---|
| 524 | (ur'++--', '+-+---')
|
|---|
| 525 | ]
|
|---|
| 526 |
|
|---|
| 527 | for (x, y) in utfTests:
|
|---|
| 528 | self.assertEqual(x.encode('utf-7'), y)
|
|---|
| 529 |
|
|---|
| 530 | # surrogates not supported
|
|---|
| 531 | self.assertRaises(UnicodeError, unicode, '+3ADYAA-', 'utf-7')
|
|---|
| 532 |
|
|---|
| 533 | self.assertEqual(unicode('+3ADYAA-', 'utf-7', 'replace'), u'\ufffd')
|
|---|
| 534 |
|
|---|
| 535 | def test_codecs_utf8(self):
|
|---|
| 536 | self.assertEqual(u''.encode('utf-8'), '')
|
|---|
| 537 | self.assertEqual(u'\u20ac'.encode('utf-8'), '\xe2\x82\xac')
|
|---|
| 538 | self.assertEqual(u'\ud800\udc02'.encode('utf-8'), '\xf0\x90\x80\x82')
|
|---|
| 539 | self.assertEqual(u'\ud84d\udc56'.encode('utf-8'), '\xf0\xa3\x91\x96')
|
|---|
| 540 | self.assertEqual(u'\ud800'.encode('utf-8'), '\xed\xa0\x80')
|
|---|
| 541 | self.assertEqual(u'\udc00'.encode('utf-8'), '\xed\xb0\x80')
|
|---|
| 542 | self.assertEqual(
|
|---|
| 543 | (u'\ud800\udc02'*1000).encode('utf-8'),
|
|---|
| 544 | '\xf0\x90\x80\x82'*1000
|
|---|
| 545 | )
|
|---|
| 546 | self.assertEqual(
|
|---|
| 547 | u'\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f'
|
|---|
| 548 | u'\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00'
|
|---|
| 549 | u'\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c'
|
|---|
| 550 | u'\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067'
|
|---|
| 551 | u'\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das'
|
|---|
| 552 | u' Nunstuck git und'.encode('utf-8'),
|
|---|
| 553 | '\xe6\xad\xa3\xe7\xa2\xba\xe3\x81\xab\xe8\xa8\x80\xe3\x81'
|
|---|
| 554 | '\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3\xe3\x81\xaf\xe3'
|
|---|
| 555 | '\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3\x81\xbe'
|
|---|
| 556 | '\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
|
|---|
| 557 | '\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8'
|
|---|
| 558 | '\xaa\x9e\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81'
|
|---|
| 559 | '\xe3\x81\x82\xe3\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81'
|
|---|
| 560 | '\x9f\xe3\x82\x89\xe3\x82\x81\xe3\x81\xa7\xe3\x81\x99\xe3'
|
|---|
| 561 | '\x80\x82\xe5\xae\x9f\xe9\x9a\x9b\xe3\x81\xab\xe3\x81\xaf'
|
|---|
| 562 | '\xe3\x80\x8cWenn ist das Nunstuck git und'
|
|---|
| 563 | )
|
|---|
| 564 |
|
|---|
| 565 | # UTF-8 specific decoding tests
|
|---|
| 566 | self.assertEqual(unicode('\xf0\xa3\x91\x96', 'utf-8'), u'\U00023456' )
|
|---|
| 567 | self.assertEqual(unicode('\xf0\x90\x80\x82', 'utf-8'), u'\U00010002' )
|
|---|
| 568 | self.assertEqual(unicode('\xe2\x82\xac', 'utf-8'), u'\u20ac' )
|
|---|
| 569 |
|
|---|
| 570 | # Other possible utf-8 test cases:
|
|---|
| 571 | # * strict decoding testing for all of the
|
|---|
| 572 | # UTF8_ERROR cases in PyUnicode_DecodeUTF8
|
|---|
| 573 |
|
|---|
| 574 | def test_codecs_idna(self):
|
|---|
| 575 | # Test whether trailing dot is preserved
|
|---|
| 576 | self.assertEqual(u"www.python.org.".encode("idna"), "www.python.org.")
|
|---|
| 577 |
|
|---|
| 578 | def test_codecs_errors(self):
|
|---|
| 579 | # Error handling (encoding)
|
|---|
| 580 | self.assertRaises(UnicodeError, u'Andr\202 x'.encode, 'ascii')
|
|---|
| 581 | self.assertRaises(UnicodeError, u'Andr\202 x'.encode, 'ascii','strict')
|
|---|
| 582 | self.assertEqual(u'Andr\202 x'.encode('ascii','ignore'), "Andr x")
|
|---|
| 583 | self.assertEqual(u'Andr\202 x'.encode('ascii','replace'), "Andr? x")
|
|---|
| 584 |
|
|---|
| 585 | # Error handling (decoding)
|
|---|
| 586 | self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii')
|
|---|
| 587 | self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii','strict')
|
|---|
| 588 | self.assertEqual(unicode('Andr\202 x','ascii','ignore'), u"Andr x")
|
|---|
| 589 | self.assertEqual(unicode('Andr\202 x','ascii','replace'), u'Andr\uFFFD x')
|
|---|
| 590 |
|
|---|
| 591 | # Error handling (unknown character names)
|
|---|
| 592 | self.assertEqual("\\N{foo}xx".decode("unicode-escape", "ignore"), u"xx")
|
|---|
| 593 |
|
|---|
| 594 | # Error handling (truncated escape sequence)
|
|---|
| 595 | self.assertRaises(UnicodeError, "\\".decode, "unicode-escape")
|
|---|
| 596 |
|
|---|
| 597 | self.assertRaises(TypeError, "hello".decode, "test.unicode1")
|
|---|
| 598 | self.assertRaises(TypeError, unicode, "hello", "test.unicode2")
|
|---|
| 599 | self.assertRaises(TypeError, u"hello".encode, "test.unicode1")
|
|---|
| 600 | self.assertRaises(TypeError, u"hello".encode, "test.unicode2")
|
|---|
| 601 | # executes PyUnicode_Encode()
|
|---|
| 602 | import imp
|
|---|
| 603 | self.assertRaises(
|
|---|
| 604 | ImportError,
|
|---|
| 605 | imp.find_module,
|
|---|
| 606 | "non-existing module",
|
|---|
| 607 | [u"non-existing dir"]
|
|---|
| 608 | )
|
|---|
| 609 |
|
|---|
| 610 | # Error handling (wrong arguments)
|
|---|
| 611 | self.assertRaises(TypeError, u"hello".encode, 42, 42, 42)
|
|---|
| 612 |
|
|---|
| 613 | # Error handling (PyUnicode_EncodeDecimal())
|
|---|
| 614 | self.assertRaises(UnicodeError, int, u"\u0200")
|
|---|
| 615 |
|
|---|
| 616 | def test_codecs(self):
|
|---|
| 617 | # Encoding
|
|---|
| 618 | self.assertEqual(u'hello'.encode('ascii'), 'hello')
|
|---|
| 619 | self.assertEqual(u'hello'.encode('utf-7'), 'hello')
|
|---|
| 620 | self.assertEqual(u'hello'.encode('utf-8'), 'hello')
|
|---|
| 621 | self.assertEqual(u'hello'.encode('utf8'), 'hello')
|
|---|
| 622 | self.assertEqual(u'hello'.encode('utf-16-le'), 'h\000e\000l\000l\000o\000')
|
|---|
| 623 | self.assertEqual(u'hello'.encode('utf-16-be'), '\000h\000e\000l\000l\000o')
|
|---|
| 624 | self.assertEqual(u'hello'.encode('latin-1'), 'hello')
|
|---|
| 625 |
|
|---|
| 626 | # Roundtrip safety for BMP (just the first 1024 chars)
|
|---|
| 627 | for c in xrange(1024):
|
|---|
| 628 | u = unichr(c)
|
|---|
| 629 | for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le',
|
|---|
| 630 | 'utf-16-be', 'raw_unicode_escape',
|
|---|
| 631 | 'unicode_escape', 'unicode_internal'):
|
|---|
| 632 | self.assertEqual(unicode(u.encode(encoding),encoding), u)
|
|---|
| 633 |
|
|---|
| 634 | # Roundtrip safety for BMP (just the first 256 chars)
|
|---|
| 635 | for c in xrange(256):
|
|---|
| 636 | u = unichr(c)
|
|---|
| 637 | for encoding in ('latin-1',):
|
|---|
| 638 | self.assertEqual(unicode(u.encode(encoding),encoding), u)
|
|---|
| 639 |
|
|---|
| 640 | # Roundtrip safety for BMP (just the first 128 chars)
|
|---|
| 641 | for c in xrange(128):
|
|---|
| 642 | u = unichr(c)
|
|---|
| 643 | for encoding in ('ascii',):
|
|---|
| 644 | self.assertEqual(unicode(u.encode(encoding),encoding), u)
|
|---|
| 645 |
|
|---|
| 646 | # Roundtrip safety for non-BMP (just a few chars)
|
|---|
| 647 | u = u'\U00010001\U00020002\U00030003\U00040004\U00050005'
|
|---|
| 648 | for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
|
|---|
| 649 | #'raw_unicode_escape',
|
|---|
| 650 | 'unicode_escape', 'unicode_internal'):
|
|---|
| 651 | self.assertEqual(unicode(u.encode(encoding),encoding), u)
|
|---|
| 652 |
|
|---|
| 653 | # UTF-8 must be roundtrip safe for all UCS-2 code points
|
|---|
| 654 | # This excludes surrogates: in the full range, there would be
|
|---|
| 655 | # a surrogate pair (\udbff\udc00), which gets converted back
|
|---|
| 656 | # to a non-BMP character (\U0010fc00)
|
|---|
| 657 | u = u''.join(map(unichr, range(0,0xd800)+range(0xe000,0x10000)))
|
|---|
| 658 | for encoding in ('utf-8',):
|
|---|
| 659 | self.assertEqual(unicode(u.encode(encoding),encoding), u)
|
|---|
| 660 |
|
|---|
| 661 | def test_codecs_charmap(self):
|
|---|
| 662 | # 0-127
|
|---|
| 663 | s = ''.join(map(chr, xrange(128)))
|
|---|
| 664 | for encoding in (
|
|---|
| 665 | 'cp037', 'cp1026',
|
|---|
| 666 | 'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
|
|---|
| 667 | 'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
|
|---|
| 668 | 'cp863', 'cp865', 'cp866',
|
|---|
| 669 | 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
|
|---|
| 670 | 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
|
|---|
| 671 | 'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1',
|
|---|
| 672 | 'mac_cyrillic', 'mac_latin2',
|
|---|
| 673 |
|
|---|
| 674 | 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
|
|---|
| 675 | 'cp1256', 'cp1257', 'cp1258',
|
|---|
| 676 | 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
|
|---|
| 677 |
|
|---|
| 678 | 'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
|
|---|
| 679 | 'cp1006', 'iso8859_8',
|
|---|
| 680 |
|
|---|
| 681 | ### These have undefined mappings:
|
|---|
| 682 | #'cp424',
|
|---|
| 683 |
|
|---|
| 684 | ### These fail the round-trip:
|
|---|
| 685 | #'cp875'
|
|---|
| 686 |
|
|---|
| 687 | ):
|
|---|
| 688 | self.assertEqual(unicode(s, encoding).encode(encoding), s)
|
|---|
| 689 |
|
|---|
| 690 | # 128-255
|
|---|
| 691 | s = ''.join(map(chr, xrange(128, 256)))
|
|---|
| 692 | for encoding in (
|
|---|
| 693 | 'cp037', 'cp1026',
|
|---|
| 694 | 'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
|
|---|
| 695 | 'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
|
|---|
| 696 | 'cp863', 'cp865', 'cp866',
|
|---|
| 697 | 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
|
|---|
| 698 | 'iso8859_2', 'iso8859_4', 'iso8859_5',
|
|---|
| 699 | 'iso8859_9', 'koi8_r', 'latin_1',
|
|---|
| 700 | 'mac_cyrillic', 'mac_latin2',
|
|---|
| 701 |
|
|---|
| 702 | ### These have undefined mappings:
|
|---|
| 703 | #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
|
|---|
| 704 | #'cp1256', 'cp1257', 'cp1258',
|
|---|
| 705 | #'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
|
|---|
| 706 | #'iso8859_3', 'iso8859_6', 'iso8859_7',
|
|---|
| 707 | #'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
|
|---|
| 708 |
|
|---|
| 709 | ### These fail the round-trip:
|
|---|
| 710 | #'cp1006', 'cp875', 'iso8859_8',
|
|---|
| 711 |
|
|---|
| 712 | ):
|
|---|
| 713 | self.assertEqual(unicode(s, encoding).encode(encoding), s)
|
|---|
| 714 |
|
|---|
| 715 | def test_concatenation(self):
|
|---|
| 716 | self.assertEqual((u"abc" u"def"), u"abcdef")
|
|---|
| 717 | self.assertEqual(("abc" u"def"), u"abcdef")
|
|---|
| 718 | self.assertEqual((u"abc" "def"), u"abcdef")
|
|---|
| 719 | self.assertEqual((u"abc" u"def" "ghi"), u"abcdefghi")
|
|---|
| 720 | self.assertEqual(("abc" "def" u"ghi"), u"abcdefghi")
|
|---|
| 721 |
|
|---|
| 722 | def test_printing(self):
|
|---|
| 723 | class BitBucket:
|
|---|
| 724 | def write(self, text):
|
|---|
| 725 | pass
|
|---|
| 726 |
|
|---|
| 727 | out = BitBucket()
|
|---|
| 728 | print >>out, u'abc'
|
|---|
| 729 | print >>out, u'abc', u'def'
|
|---|
| 730 | print >>out, u'abc', 'def'
|
|---|
| 731 | print >>out, 'abc', u'def'
|
|---|
| 732 | print >>out, u'abc\n'
|
|---|
| 733 | print >>out, u'abc\n',
|
|---|
| 734 | print >>out, u'abc\n',
|
|---|
| 735 | print >>out, u'def\n'
|
|---|
| 736 | print >>out, u'def\n'
|
|---|
| 737 |
|
|---|
| 738 | def test_ucs4(self):
|
|---|
| 739 | if sys.maxunicode == 0xFFFF:
|
|---|
| 740 | return
|
|---|
| 741 | x = u'\U00100000'
|
|---|
| 742 | y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
|
|---|
| 743 | self.assertEqual(x, y)
|
|---|
| 744 |
|
|---|
| 745 | def test_conversion(self):
|
|---|
| 746 | # Make sure __unicode__() works properly
|
|---|
| 747 | class Foo0:
|
|---|
| 748 | def __str__(self):
|
|---|
| 749 | return "foo"
|
|---|
| 750 |
|
|---|
| 751 | class Foo1:
|
|---|
| 752 | def __unicode__(self):
|
|---|
| 753 | return u"foo"
|
|---|
| 754 |
|
|---|
| 755 | class Foo2(object):
|
|---|
| 756 | def __unicode__(self):
|
|---|
| 757 | return u"foo"
|
|---|
| 758 |
|
|---|
| 759 | class Foo3(object):
|
|---|
| 760 | def __unicode__(self):
|
|---|
| 761 | return "foo"
|
|---|
| 762 |
|
|---|
| 763 | class Foo4(str):
|
|---|
| 764 | def __unicode__(self):
|
|---|
| 765 | return "foo"
|
|---|
| 766 |
|
|---|
| 767 | class Foo5(unicode):
|
|---|
| 768 | def __unicode__(self):
|
|---|
| 769 | return "foo"
|
|---|
| 770 |
|
|---|
| 771 | class Foo6(str):
|
|---|
| 772 | def __str__(self):
|
|---|
| 773 | return "foos"
|
|---|
| 774 |
|
|---|
| 775 | def __unicode__(self):
|
|---|
| 776 | return u"foou"
|
|---|
| 777 |
|
|---|
| 778 | class Foo7(unicode):
|
|---|
| 779 | def __str__(self):
|
|---|
| 780 | return "foos"
|
|---|
| 781 | def __unicode__(self):
|
|---|
| 782 | return u"foou"
|
|---|
| 783 |
|
|---|
| 784 | class Foo8(unicode):
|
|---|
| 785 | def __new__(cls, content=""):
|
|---|
| 786 | return unicode.__new__(cls, 2*content)
|
|---|
| 787 | def __unicode__(self):
|
|---|
| 788 | return self
|
|---|
| 789 |
|
|---|
| 790 | class Foo9(unicode):
|
|---|
| 791 | def __str__(self):
|
|---|
| 792 | return "string"
|
|---|
| 793 | def __unicode__(self):
|
|---|
| 794 | return "not unicode"
|
|---|
| 795 |
|
|---|
| 796 | self.assertEqual(unicode(Foo0()), u"foo")
|
|---|
| 797 | self.assertEqual(unicode(Foo1()), u"foo")
|
|---|
| 798 | self.assertEqual(unicode(Foo2()), u"foo")
|
|---|
| 799 | self.assertEqual(unicode(Foo3()), u"foo")
|
|---|
| 800 | self.assertEqual(unicode(Foo4("bar")), u"foo")
|
|---|
| 801 | self.assertEqual(unicode(Foo5("bar")), u"foo")
|
|---|
| 802 | self.assertEqual(unicode(Foo6("bar")), u"foou")
|
|---|
| 803 | self.assertEqual(unicode(Foo7("bar")), u"foou")
|
|---|
| 804 | self.assertEqual(unicode(Foo8("foo")), u"foofoo")
|
|---|
| 805 | self.assertEqual(str(Foo9("foo")), "string")
|
|---|
| 806 | self.assertEqual(unicode(Foo9("foo")), u"not unicode")
|
|---|
| 807 |
|
|---|
| 808 | def test_unicode_repr(self):
|
|---|
| 809 | class s1:
|
|---|
| 810 | def __repr__(self):
|
|---|
| 811 | return '\\n'
|
|---|
| 812 |
|
|---|
| 813 | class s2:
|
|---|
| 814 | def __repr__(self):
|
|---|
| 815 | return u'\\n'
|
|---|
| 816 |
|
|---|
| 817 | self.assertEqual(repr(s1()), '\\n')
|
|---|
| 818 | self.assertEqual(repr(s2()), '\\n')
|
|---|
| 819 |
|
|---|
| 820 |
|
|---|
| 821 |
|
|---|
| 822 |
|
|---|
| 823 |
|
|---|
| 824 | def test_main():
|
|---|
| 825 | test_support.run_unittest(UnicodeTest)
|
|---|
| 826 |
|
|---|
| 827 | if __name__ == "__main__":
|
|---|
| 828 | test_main()
|
|---|
