1""" 2Common tests shared by test_str, test_unicode, test_userstring and test_string. 3""" 4 5import unittest, string, sys, struct 6from test import test_support 7from UserList import UserList 8 9class Sequence: 10 def __init__(self, seq='wxyz'): self.seq = seq 11 def __len__(self): return len(self.seq) 12 def __getitem__(self, i): return self.seq[i] 13 14class BadSeq1(Sequence): 15 def __init__(self): self.seq = [7, 'hello', 123L] 16 17class BadSeq2(Sequence): 18 def __init__(self): self.seq = ['a', 'b', 'c'] 19 def __len__(self): return 8 20 21class CommonTest(unittest.TestCase): 22 # This testcase contains test that can be used in all 23 # stringlike classes. Currently this is str, unicode 24 # UserString and the string module. 25 26 # The type to be tested 27 # Change in subclasses to change the behaviour of fixtesttype() 28 type2test = None 29 30 # All tests pass their arguments to the testing methods 31 # as str objects. fixtesttype() can be used to propagate 32 # these arguments to the appropriate type 33 def fixtype(self, obj): 34 if isinstance(obj, str): 35 return self.__class__.type2test(obj) 36 elif isinstance(obj, list): 37 return [self.fixtype(x) for x in obj] 38 elif isinstance(obj, tuple): 39 return tuple([self.fixtype(x) for x in obj]) 40 elif isinstance(obj, dict): 41 return dict([ 42 (self.fixtype(key), self.fixtype(value)) 43 for (key, value) in obj.iteritems() 44 ]) 45 else: 46 return obj 47 48 def test_fixtype(self): 49 self.assertIs(type(self.fixtype("123")), self.type2test) 50 51 # check that object.method(*args) returns result 52 def checkequal(self, result, object, methodname, *args): 53 result = self.fixtype(result) 54 object = self.fixtype(object) 55 args = self.fixtype(args) 56 realresult = getattr(object, methodname)(*args) 57 self.assertEqual( 58 result, 59 realresult 60 ) 61 # if the original is returned make sure that 62 # this doesn't happen with subclasses 63 if object == realresult: 64 class subtype(self.__class__.type2test): 65 pass 66 object = subtype(object) 67 realresult = getattr(object, methodname)(*args) 68 self.assertTrue(object is not realresult) 69 70 # check that object.method(*args) raises exc 71 def checkraises(self, exc, obj, methodname, *args): 72 obj = self.fixtype(obj) 73 args = self.fixtype(args) 74 with self.assertRaises(exc) as cm: 75 getattr(obj, methodname)(*args) 76 self.assertNotEqual(cm.exception.args[0], '') 77 78 # call object.method(*args) without any checks 79 def checkcall(self, object, methodname, *args): 80 object = self.fixtype(object) 81 args = self.fixtype(args) 82 getattr(object, methodname)(*args) 83 84 def test_hash(self): 85 # SF bug 1054139: += optimization was not invalidating cached hash value 86 a = self.type2test('DNSSEC') 87 b = self.type2test('') 88 for c in a: 89 b += c 90 hash(b) 91 self.assertEqual(hash(a), hash(b)) 92 93 def test_capitalize(self): 94 self.checkequal(' hello ', ' hello ', 'capitalize') 95 self.checkequal('Hello ', 'Hello ','capitalize') 96 self.checkequal('Hello ', 'hello ','capitalize') 97 self.checkequal('Aaaa', 'aaaa', 'capitalize') 98 self.checkequal('Aaaa', 'AaAa', 'capitalize') 99 100 self.checkraises(TypeError, 'hello', 'capitalize', 42) 101 102 def test_count(self): 103 self.checkequal(3, 'aaa', 'count', 'a') 104 self.checkequal(0, 'aaa', 'count', 'b') 105 self.checkequal(3, 'aaa', 'count', 'a') 106 self.checkequal(0, 'aaa', 'count', 'b') 107 self.checkequal(3, 'aaa', 'count', 'a') 108 self.checkequal(0, 'aaa', 'count', 'b') 109 self.checkequal(0, 'aaa', 'count', 'b') 110 self.checkequal(2, 'aaa', 'count', 'a', 1) 111 self.checkequal(0, 'aaa', 'count', 'a', 10) 112 self.checkequal(1, 'aaa', 'count', 'a', -1) 113 self.checkequal(3, 'aaa', 'count', 'a', -10) 114 self.checkequal(1, 'aaa', 'count', 'a', 0, 1) 115 self.checkequal(3, 'aaa', 'count', 'a', 0, 10) 116 self.checkequal(2, 'aaa', 'count', 'a', 0, -1) 117 self.checkequal(0, 'aaa', 'count', 'a', 0, -10) 118 self.checkequal(3, 'aaa', 'count', '', 1) 119 self.checkequal(1, 'aaa', 'count', '', 3) 120 self.checkequal(0, 'aaa', 'count', '', 10) 121 self.checkequal(2, 'aaa', 'count', '', -1) 122 self.checkequal(4, 'aaa', 'count', '', -10) 123 124 self.checkequal(1, '', 'count', '') 125 self.checkequal(0, '', 'count', '', 1, 1) 126 self.checkequal(0, '', 'count', '', sys.maxint, 0) 127 128 self.checkequal(0, '', 'count', 'xx') 129 self.checkequal(0, '', 'count', 'xx', 1, 1) 130 self.checkequal(0, '', 'count', 'xx', sys.maxint, 0) 131 132 self.checkraises(TypeError, 'hello', 'count') 133 self.checkraises(TypeError, 'hello', 'count', 42) 134 135 # For a variety of combinations, 136 # verify that str.count() matches an equivalent function 137 # replacing all occurrences and then differencing the string lengths 138 charset = ['', 'a', 'b'] 139 digits = 7 140 base = len(charset) 141 teststrings = set() 142 for i in xrange(base ** digits): 143 entry = [] 144 for j in xrange(digits): 145 i, m = divmod(i, base) 146 entry.append(charset[m]) 147 teststrings.add(''.join(entry)) 148 teststrings = list(teststrings) 149 for i in teststrings: 150 i = self.fixtype(i) 151 n = len(i) 152 for j in teststrings: 153 r1 = i.count(j) 154 if j: 155 r2, rem = divmod(n - len(i.replace(j, '')), len(j)) 156 else: 157 r2, rem = len(i)+1, 0 158 if rem or r1 != r2: 159 self.assertEqual(rem, 0, '%s != 0 for %s' % (rem, i)) 160 self.assertEqual(r1, r2, '%s != %s for %s' % (r1, r2, i)) 161 162 def test_find(self): 163 self.checkequal(0, 'abcdefghiabc', 'find', 'abc') 164 self.checkequal(9, 'abcdefghiabc', 'find', 'abc', 1) 165 self.checkequal(-1, 'abcdefghiabc', 'find', 'def', 4) 166 167 self.checkequal(0, 'abc', 'find', '', 0) 168 self.checkequal(3, 'abc', 'find', '', 3) 169 self.checkequal(-1, 'abc', 'find', '', 4) 170 171 # to check the ability to pass None as defaults 172 self.checkequal( 2, 'rrarrrrrrrrra', 'find', 'a') 173 self.checkequal(12, 'rrarrrrrrrrra', 'find', 'a', 4) 174 self.checkequal(-1, 'rrarrrrrrrrra', 'find', 'a', 4, 6) 175 self.checkequal(12, 'rrarrrrrrrrra', 'find', 'a', 4, None) 176 self.checkequal( 2, 'rrarrrrrrrrra', 'find', 'a', None, 6) 177 178 self.checkraises(TypeError, 'hello', 'find') 179 self.checkraises(TypeError, 'hello', 'find', 42) 180 181 self.checkequal(0, '', 'find', '') 182 self.checkequal(-1, '', 'find', '', 1, 1) 183 self.checkequal(-1, '', 'find', '', sys.maxint, 0) 184 185 self.checkequal(-1, '', 'find', 'xx') 186 self.checkequal(-1, '', 'find', 'xx', 1, 1) 187 self.checkequal(-1, '', 'find', 'xx', sys.maxint, 0) 188 189 # issue 7458 190 self.checkequal(-1, 'ab', 'find', 'xxx', sys.maxsize + 1, 0) 191 192 # For a variety of combinations, 193 # verify that str.find() matches __contains__ 194 # and that the found substring is really at that location 195 charset = ['', 'a', 'b', 'c'] 196 digits = 5 197 base = len(charset) 198 teststrings = set() 199 for i in xrange(base ** digits): 200 entry = [] 201 for j in xrange(digits): 202 i, m = divmod(i, base) 203 entry.append(charset[m]) 204 teststrings.add(''.join(entry)) 205 teststrings = list(teststrings) 206 for i in teststrings: 207 i = self.fixtype(i) 208 for j in teststrings: 209 loc = i.find(j) 210 r1 = (loc != -1) 211 r2 = j in i 212 self.assertEqual(r1, r2) 213 if loc != -1: 214 self.assertEqual(i[loc:loc+len(j)], j) 215 216 def test_rfind(self): 217 self.checkequal(9, 'abcdefghiabc', 'rfind', 'abc') 218 self.checkequal(12, 'abcdefghiabc', 'rfind', '') 219 self.checkequal(0, 'abcdefghiabc', 'rfind', 'abcd') 220 self.checkequal(-1, 'abcdefghiabc', 'rfind', 'abcz') 221 222 self.checkequal(3, 'abc', 'rfind', '', 0) 223 self.checkequal(3, 'abc', 'rfind', '', 3) 224 self.checkequal(-1, 'abc', 'rfind', '', 4) 225 226 # to check the ability to pass None as defaults 227 self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a') 228 self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a', 4) 229 self.checkequal(-1, 'rrarrrrrrrrra', 'rfind', 'a', 4, 6) 230 self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a', 4, None) 231 self.checkequal( 2, 'rrarrrrrrrrra', 'rfind', 'a', None, 6) 232 233 self.checkraises(TypeError, 'hello', 'rfind') 234 self.checkraises(TypeError, 'hello', 'rfind', 42) 235 236 # For a variety of combinations, 237 # verify that str.rfind() matches __contains__ 238 # and that the found substring is really at that location 239 charset = ['', 'a', 'b', 'c'] 240 digits = 5 241 base = len(charset) 242 teststrings = set() 243 for i in xrange(base ** digits): 244 entry = [] 245 for j in xrange(digits): 246 i, m = divmod(i, base) 247 entry.append(charset[m]) 248 teststrings.add(''.join(entry)) 249 teststrings = list(teststrings) 250 for i in teststrings: 251 i = self.fixtype(i) 252 for j in teststrings: 253 loc = i.rfind(j) 254 r1 = (loc != -1) 255 r2 = j in i 256 self.assertEqual(r1, r2) 257 if loc != -1: 258 self.assertEqual(i[loc:loc+len(j)], self.fixtype(j)) 259 260 # issue 7458 261 self.checkequal(-1, 'ab', 'rfind', 'xxx', sys.maxsize + 1, 0) 262 263 def test_index(self): 264 self.checkequal(0, 'abcdefghiabc', 'index', '') 265 self.checkequal(3, 'abcdefghiabc', 'index', 'def') 266 self.checkequal(0, 'abcdefghiabc', 'index', 'abc') 267 self.checkequal(9, 'abcdefghiabc', 'index', 'abc', 1) 268 269 self.checkraises(ValueError, 'abcdefghiabc', 'index', 'hib') 270 self.checkraises(ValueError, 'abcdefghiab', 'index', 'abc', 1) 271 self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', 8) 272 self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', -1) 273 274 # to check the ability to pass None as defaults 275 self.checkequal( 2, 'rrarrrrrrrrra', 'index', 'a') 276 self.checkequal(12, 'rrarrrrrrrrra', 'index', 'a', 4) 277 self.checkraises(ValueError, 'rrarrrrrrrrra', 'index', 'a', 4, 6) 278 self.checkequal(12, 'rrarrrrrrrrra', 'index', 'a', 4, None) 279 self.checkequal( 2, 'rrarrrrrrrrra', 'index', 'a', None, 6) 280 281 self.checkraises(TypeError, 'hello', 'index') 282 self.checkraises(TypeError, 'hello', 'index', 42) 283 284 def test_rindex(self): 285 self.checkequal(12, 'abcdefghiabc', 'rindex', '') 286 self.checkequal(3, 'abcdefghiabc', 'rindex', 'def') 287 self.checkequal(9, 'abcdefghiabc', 'rindex', 'abc') 288 self.checkequal(0, 'abcdefghiabc', 'rindex', 'abc', 0, -1) 289 290 self.checkraises(ValueError, 'abcdefghiabc', 'rindex', 'hib') 291 self.checkraises(ValueError, 'defghiabc', 'rindex', 'def', 1) 292 self.checkraises(ValueError, 'defghiabc', 'rindex', 'abc', 0, -1) 293 self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, 8) 294 self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, -1) 295 296 # to check the ability to pass None as defaults 297 self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a') 298 self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a', 4) 299 self.checkraises(ValueError, 'rrarrrrrrrrra', 'rindex', 'a', 4, 6) 300 self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a', 4, None) 301 self.checkequal( 2, 'rrarrrrrrrrra', 'rindex', 'a', None, 6) 302 303 self.checkraises(TypeError, 'hello', 'rindex') 304 self.checkraises(TypeError, 'hello', 'rindex', 42) 305 306 def test_lower(self): 307 self.checkequal('hello', 'HeLLo', 'lower') 308 self.checkequal('hello', 'hello', 'lower') 309 self.checkraises(TypeError, 'hello', 'lower', 42) 310 311 def test_upper(self): 312 self.checkequal('HELLO', 'HeLLo', 'upper') 313 self.checkequal('HELLO', 'HELLO', 'upper') 314 self.checkraises(TypeError, 'hello', 'upper', 42) 315 316 def test_expandtabs(self): 317 self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs') 318 self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8) 319 self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 4) 320 self.checkequal('abc\r\nab def\ng hi', 'abc\r\nab\tdef\ng\thi', 'expandtabs', 4) 321 self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs') 322 self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8) 323 self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4) 324 self.checkequal(' a\n b', ' \ta\n\tb', 'expandtabs', 1) 325 326 self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42) 327 # This test is only valid when sizeof(int) == sizeof(void*) == 4. 328 if sys.maxint < (1 << 32) and struct.calcsize('P') == 4: 329 self.checkraises(OverflowError, 330 '\ta\n\tb', 'expandtabs', sys.maxint) 331 332 def test_split(self): 333 self.checkequal(['this', 'is', 'the', 'split', 'function'], 334 'this is the split function', 'split') 335 336 # by whitespace 337 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split') 338 self.checkequal(['a', 'b c d'], 'a b c d', 'split', None, 1) 339 self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2) 340 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 3) 341 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 4) 342 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 343 sys.maxint-1) 344 self.checkequal(['a b c d'], 'a b c d', 'split', None, 0) 345 self.checkequal(['a b c d'], ' a b c d', 'split', None, 0) 346 self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2) 347 348 self.checkequal([], ' ', 'split') 349 self.checkequal(['a'], ' a ', 'split') 350 self.checkequal(['a', 'b'], ' a b ', 'split') 351 self.checkequal(['a', 'b '], ' a b ', 'split', None, 1) 352 self.checkequal(['a b c '], ' a b c ', 'split', None, 0) 353 self.checkequal(['a', 'b c '], ' a b c ', 'split', None, 1) 354 self.checkequal(['a', 'b', 'c '], ' a b c ', 'split', None, 2) 355 self.checkequal(['a', 'b', 'c'], ' a b c ', 'split', None, 3) 356 self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split') 357 aaa = ' a '*20 358 self.checkequal(['a']*20, aaa, 'split') 359 self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1) 360 self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19) 361 362 for b in ('arf\tbarf', 'arf\nbarf', 'arf\rbarf', 363 'arf\fbarf', 'arf\vbarf'): 364 self.checkequal(['arf', 'barf'], b, 'split') 365 self.checkequal(['arf', 'barf'], b, 'split', None) 366 self.checkequal(['arf', 'barf'], b, 'split', None, 2) 367 368 # by a char 369 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|') 370 self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0) 371 self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1) 372 self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2) 373 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3) 374 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4) 375 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 376 sys.maxint-2) 377 self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0) 378 self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2) 379 self.checkequal(['abcd'], 'abcd', 'split', '|') 380 self.checkequal([''], '', 'split', '|') 381 self.checkequal(['endcase ', ''], 'endcase |', 'split', '|') 382 self.checkequal(['', ' startcase'], '| startcase', 'split', '|') 383 self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|') 384 self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2) 385 386 self.checkequal(['a']*20, ('a|'*20)[:-1], 'split', '|') 387 self.checkequal(['a']*15 +['a|a|a|a|a'], 388 ('a|'*20)[:-1], 'split', '|', 15) 389 390 # by string 391 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//') 392 self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1) 393 self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2) 394 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3) 395 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4) 396 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 397 sys.maxint-10) 398 self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0) 399 self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2) 400 self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test') 401 self.checkequal(['', ' begincase'], 'test begincase', 'split', 'test') 402 self.checkequal(['', ' bothcase ', ''], 'test bothcase test', 403 'split', 'test') 404 self.checkequal(['a', 'bc'], 'abbbc', 'split', 'bb') 405 self.checkequal(['', ''], 'aaa', 'split', 'aaa') 406 self.checkequal(['aaa'], 'aaa', 'split', 'aaa', 0) 407 self.checkequal(['ab', 'ab'], 'abbaab', 'split', 'ba') 408 self.checkequal(['aaaa'], 'aaaa', 'split', 'aab') 409 self.checkequal([''], '', 'split', 'aaa') 410 self.checkequal(['aa'], 'aa', 'split', 'aaa') 411 self.checkequal(['A', 'bobb'], 'Abbobbbobb', 'split', 'bbobb') 412 self.checkequal(['A', 'B', ''], 'AbbobbBbbobb', 'split', 'bbobb') 413 414 self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH') 415 self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH', 19) 416 self.checkequal(['a']*18 + ['aBLAHa'], ('aBLAH'*20)[:-4], 417 'split', 'BLAH', 18) 418 419 # mixed use of str and unicode 420 if self.type2test is not bytearray: 421 result = [u'a', u'b', u'c d'] 422 self.checkequal(result, 'a b c d', 'split', u' ', 2) 423 424 # argument type 425 self.checkraises(TypeError, 'hello', 'split', 42, 42, 42) 426 427 # null case 428 self.checkraises(ValueError, 'hello', 'split', '') 429 self.checkraises(ValueError, 'hello', 'split', '', 0) 430 431 def test_rsplit(self): 432 self.checkequal(['this', 'is', 'the', 'rsplit', 'function'], 433 'this is the rsplit function', 'rsplit') 434 435 # by whitespace 436 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit') 437 self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1) 438 self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2) 439 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3) 440 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4) 441 self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 442 sys.maxint-20) 443 self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0) 444 self.checkequal(['a b c d'], 'a b c d ', 'rsplit', None, 0) 445 self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2) 446 447 self.checkequal([], ' ', 'rsplit') 448 self.checkequal(['a'], ' a ', 'rsplit') 449 self.checkequal(['a', 'b'], ' a b ', 'rsplit') 450 self.checkequal([' a', 'b'], ' a b ', 'rsplit', None, 1) 451 self.checkequal([' a b c'], ' a b c ', 'rsplit', 452 None, 0) 453 self.checkequal([' a b','c'], ' a b c ', 'rsplit', 454 None, 1) 455 self.checkequal([' a', 'b', 'c'], ' a b c ', 'rsplit', 456 None, 2) 457 self.checkequal(['a', 'b', 'c'], ' a b c ', 'rsplit', 458 None, 3) 459 self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88) 460 aaa = ' a '*20 461 self.checkequal(['a']*20, aaa, 'rsplit') 462 self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1) 463 self.checkequal([' a a'] + ['a']*18, aaa, 'rsplit', None, 18) 464 465 for b in ('arf\tbarf', 'arf\nbarf', 'arf\rbarf', 466 'arf\fbarf', 'arf\vbarf'): 467 self.checkequal(['arf', 'barf'], b, 'rsplit') 468 self.checkequal(['arf', 'barf'], b, 'rsplit', None) 469 self.checkequal(['arf', 'barf'], b, 'rsplit', None, 2) 470 471 # by a char 472 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|') 473 self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1) 474 self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2) 475 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3) 476 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4) 477 self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 478 sys.maxint-100) 479 self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0) 480 self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2) 481 self.checkequal(['abcd'], 'abcd', 'rsplit', '|') 482 self.checkequal([''], '', 'rsplit', '|') 483 self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|') 484 self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|') 485 self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|') 486 487 self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2) 488 489 self.checkequal(['a']*20, ('a|'*20)[:-1], 'rsplit', '|') 490 self.checkequal(['a|a|a|a|a']+['a']*15, 491 ('a|'*20)[:-1], 'rsplit', '|', 15) 492 493 # by string 494 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//') 495 self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1) 496 self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2) 497 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3) 498 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4) 499 self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 500 sys.maxint-5) 501 self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0) 502 self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2) 503 self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test') 504 self.checkequal(['endcase ', ''], 'endcase test', 'rsplit', 'test') 505 self.checkequal(['', ' bothcase ', ''], 'test bothcase test', 506 'rsplit', 'test') 507 self.checkequal(['ab', 'c'], 'abbbc', 'rsplit', 'bb') 508 self.checkequal(['', ''], 'aaa', 'rsplit', 'aaa') 509 self.checkequal(['aaa'], 'aaa', 'rsplit', 'aaa', 0) 510 self.checkequal(['ab', 'ab'], 'abbaab', 'rsplit', 'ba') 511 self.checkequal(['aaaa'], 'aaaa', 'rsplit', 'aab') 512 self.checkequal([''], '', 'rsplit', 'aaa') 513 self.checkequal(['aa'], 'aa', 'rsplit', 'aaa') 514 self.checkequal(['bbob', 'A'], 'bbobbbobbA', 'rsplit', 'bbobb') 515 self.checkequal(['', 'B', 'A'], 'bbobbBbbobbA', 'rsplit', 'bbobb') 516 517 self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH') 518 self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH', 19) 519 self.checkequal(['aBLAHa'] + ['a']*18, ('aBLAH'*20)[:-4], 520 'rsplit', 'BLAH', 18) 521 522 # mixed use of str and unicode 523 if self.type2test is not bytearray: 524 result = [u'a b', u'c', u'd'] 525 self.checkequal(result, 'a b c d', 'rsplit', u' ', 2) 526 527 # argument type 528 self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42) 529 530 # null case 531 self.checkraises(ValueError, 'hello', 'rsplit', '') 532 self.checkraises(ValueError, 'hello', 'rsplit', '', 0) 533 534 def test_strip_whitespace(self): 535 self.checkequal('hello', ' hello ', 'strip') 536 self.checkequal('hello ', ' hello ', 'lstrip') 537 self.checkequal(' hello', ' hello ', 'rstrip') 538 self.checkequal('hello', 'hello', 'strip') 539 540 b = ' \t\n\r\f\vabc \t\n\r\f\v' 541 self.checkequal('abc', b, 'strip') 542 self.checkequal('abc \t\n\r\f\v', b, 'lstrip') 543 self.checkequal(' \t\n\r\f\vabc', b, 'rstrip') 544 545 # strip/lstrip/rstrip with None arg 546 self.checkequal('hello', ' hello ', 'strip', None) 547 self.checkequal('hello ', ' hello ', 'lstrip', None) 548 self.checkequal(' hello', ' hello ', 'rstrip', None) 549 self.checkequal('hello', 'hello', 'strip', None) 550 551 def test_strip(self): 552 # strip/lstrip/rstrip with str arg 553 self.checkequal('hello', 'xyzzyhelloxyzzy', 'strip', 'xyz') 554 self.checkequal('helloxyzzy', 'xyzzyhelloxyzzy', 'lstrip', 'xyz') 555 self.checkequal('xyzzyhello', 'xyzzyhelloxyzzy', 'rstrip', 'xyz') 556 self.checkequal('hello', 'hello', 'strip', 'xyz') 557 self.checkequal('', 'mississippi', 'strip', 'mississippi') 558 559 # only trims the start and end, does not strip internal characters 560 self.checkequal('mississipp', 'mississippi', 'strip', 'i') 561 562 # strip/lstrip/rstrip with unicode arg 563 if self.type2test is not bytearray and test_support.have_unicode: 564 self.checkequal(unicode('hello', 'ascii'), 'xyzzyhelloxyzzy', 565 'strip', unicode('xyz', 'ascii')) 566 self.checkequal(unicode('helloxyzzy', 'ascii'), 'xyzzyhelloxyzzy', 567 'lstrip', unicode('xyz', 'ascii')) 568 self.checkequal(unicode('xyzzyhello', 'ascii'), 'xyzzyhelloxyzzy', 569 'rstrip', unicode('xyz', 'ascii')) 570 # XXX 571 #self.checkequal(unicode('hello', 'ascii'), 'hello', 572 # 'strip', unicode('xyz', 'ascii')) 573 574 self.checkraises(TypeError, 'hello', 'strip', 42, 42) 575 self.checkraises(TypeError, 'hello', 'lstrip', 42, 42) 576 self.checkraises(TypeError, 'hello', 'rstrip', 42, 42) 577 578 def test_ljust(self): 579 self.checkequal('abc ', 'abc', 'ljust', 10) 580 self.checkequal('abc ', 'abc', 'ljust', 6) 581 self.checkequal('abc', 'abc', 'ljust', 3) 582 self.checkequal('abc', 'abc', 'ljust', 2) 583 if self.type2test is bytearray: 584 # Special case because bytearray argument is not accepted 585 self.assertEqual(b'abc*******', bytearray(b'abc').ljust(10, '*')) 586 else: 587 self.checkequal('abc*******', 'abc', 'ljust', 10, '*') 588 self.checkraises(TypeError, 'abc', 'ljust') 589 590 def test_rjust(self): 591 self.checkequal(' abc', 'abc', 'rjust', 10) 592 self.checkequal(' abc', 'abc', 'rjust', 6) 593 self.checkequal('abc', 'abc', 'rjust', 3) 594 self.checkequal('abc', 'abc', 'rjust', 2) 595 if self.type2test is bytearray: 596 # Special case because bytearray argument is not accepted 597 self.assertEqual(b'*******abc', bytearray(b'abc').rjust(10, '*')) 598 else: 599 self.checkequal('*******abc', 'abc', 'rjust', 10, '*') 600 self.checkraises(TypeError, 'abc', 'rjust') 601 602 def test_center(self): 603 self.checkequal(' abc ', 'abc', 'center', 10) 604 self.checkequal(' abc ', 'abc', 'center', 6) 605 self.checkequal('abc', 'abc', 'center', 3) 606 self.checkequal('abc', 'abc', 'center', 2) 607 if self.type2test is bytearray: 608 # Special case because bytearray argument is not accepted 609 result = bytearray(b'abc').center(10, '*') 610 self.assertEqual(b'***abc****', result) 611 else: 612 self.checkequal('***abc****', 'abc', 'center', 10, '*') 613 self.checkraises(TypeError, 'abc', 'center') 614 615 def test_swapcase(self): 616 self.checkequal('hEllO CoMPuTErS', 'HeLLo cOmpUteRs', 'swapcase') 617 618 self.checkraises(TypeError, 'hello', 'swapcase', 42) 619 620 def test_replace(self): 621 EQ = self.checkequal 622 623 # Operations on the empty string 624 EQ("", "", "replace", "", "") 625 EQ("A", "", "replace", "", "A") 626 EQ("", "", "replace", "A", "") 627 EQ("", "", "replace", "A", "A") 628 EQ("", "", "replace", "", "", 100) 629 EQ("", "", "replace", "", "", sys.maxint) 630 631 # interleave (from=="", 'to' gets inserted everywhere) 632 EQ("A", "A", "replace", "", "") 633 EQ("*A*", "A", "replace", "", "*") 634 EQ("*1A*1", "A", "replace", "", "*1") 635 EQ("*-#A*-#", "A", "replace", "", "*-#") 636 EQ("*-A*-A*-", "AA", "replace", "", "*-") 637 EQ("*-A*-A*-", "AA", "replace", "", "*-", -1) 638 EQ("*-A*-A*-", "AA", "replace", "", "*-", sys.maxint) 639 EQ("*-A*-A*-", "AA", "replace", "", "*-", 4) 640 EQ("*-A*-A*-", "AA", "replace", "", "*-", 3) 641 EQ("*-A*-A", "AA", "replace", "", "*-", 2) 642 EQ("*-AA", "AA", "replace", "", "*-", 1) 643 EQ("AA", "AA", "replace", "", "*-", 0) 644 645 # single character deletion (from=="A", to=="") 646 EQ("", "A", "replace", "A", "") 647 EQ("", "AAA", "replace", "A", "") 648 EQ("", "AAA", "replace", "A", "", -1) 649 EQ("", "AAA", "replace", "A", "", sys.maxint) 650 EQ("", "AAA", "replace", "A", "", 4) 651 EQ("", "AAA", "replace", "A", "", 3) 652 EQ("A", "AAA", "replace", "A", "", 2) 653 EQ("AA", "AAA", "replace", "A", "", 1) 654 EQ("AAA", "AAA", "replace", "A", "", 0) 655 EQ("", "AAAAAAAAAA", "replace", "A", "") 656 EQ("BCD", "ABACADA", "replace", "A", "") 657 EQ("BCD", "ABACADA", "replace", "A", "", -1) 658 EQ("BCD", "ABACADA", "replace", "A", "", sys.maxint) 659 EQ("BCD", "ABACADA", "replace", "A", "", 5) 660 EQ("BCD", "ABACADA", "replace", "A", "", 4) 661 EQ("BCDA", "ABACADA", "replace", "A", "", 3) 662 EQ("BCADA", "ABACADA", "replace", "A", "", 2) 663 EQ("BACADA", "ABACADA", "replace", "A", "", 1) 664 EQ("ABACADA", "ABACADA", "replace", "A", "", 0) 665 EQ("BCD", "ABCAD", "replace", "A", "") 666 EQ("BCD", "ABCADAA", "replace", "A", "") 667 EQ("BCD", "BCD", "replace", "A", "") 668 EQ("*************", "*************", "replace", "A", "") 669 EQ("^A^", "^"+"A"*1000+"^", "replace", "A", "", 999) 670 671 # substring deletion (from=="the", to=="") 672 EQ("", "the", "replace", "the", "") 673 EQ("ater", "theater", "replace", "the", "") 674 EQ("", "thethe", "replace", "the", "") 675 EQ("", "thethethethe", "replace", "the", "") 676 EQ("aaaa", "theatheatheathea", "replace", "the", "") 677 EQ("that", "that", "replace", "the", "") 678 EQ("thaet", "thaet", "replace", "the", "") 679 EQ("here and re", "here and there", "replace", "the", "") 680 EQ("here and re and re", "here and there and there", 681 "replace", "the", "", sys.maxint) 682 EQ("here and re and re", "here and there and there", 683 "replace", "the", "", -1) 684 EQ("here and re and re", "here and there and there", 685 "replace", "the", "", 3) 686 EQ("here and re and re", "here and there and there", 687 "replace", "the", "", 2) 688 EQ("here and re and there", "here and there and there", 689 "replace", "the", "", 1) 690 EQ("here and there and there", "here and there and there", 691 "replace", "the", "", 0) 692 EQ("here and re and re", "here and there and there", "replace", "the", "") 693 694 EQ("abc", "abc", "replace", "the", "") 695 EQ("abcdefg", "abcdefg", "replace", "the", "") 696 697 # substring deletion (from=="bob", to=="") 698 EQ("bob", "bbobob", "replace", "bob", "") 699 EQ("bobXbob", "bbobobXbbobob", "replace", "bob", "") 700 EQ("aaaaaaa", "aaaaaaabob", "replace", "bob", "") 701 EQ("aaaaaaa", "aaaaaaa", "replace", "bob", "") 702 703 # single character replace in place (len(from)==len(to)==1) 704 EQ("Who goes there?", "Who goes there?", "replace", "o", "o") 705 EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O") 706 EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", sys.maxint) 707 EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", -1) 708 EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 3) 709 EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 2) 710 EQ("WhO goes there?", "Who goes there?", "replace", "o", "O", 1) 711 EQ("Who goes there?", "Who goes there?", "replace", "o", "O", 0) 712 713 EQ("Who goes there?", "Who goes there?", "replace", "a", "q") 714 EQ("who goes there?", "Who goes there?", "replace", "W", "w") 715 EQ("wwho goes there?ww", "WWho goes there?WW", "replace", "W", "w") 716 EQ("Who goes there!", "Who goes there?", "replace", "?", "!") 717 EQ("Who goes there!!", "Who goes there??", "replace", "?", "!") 718 719 EQ("Who goes there?", "Who goes there?", "replace", ".", "!") 720 721 # substring replace in place (len(from)==len(to) > 1) 722 EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**") 723 EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", sys.maxint) 724 EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", -1) 725 EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 4) 726 EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 3) 727 EQ("Th** ** a tissue", "This is a tissue", "replace", "is", "**", 2) 728 EQ("Th** is a tissue", "This is a tissue", "replace", "is", "**", 1) 729 EQ("This is a tissue", "This is a tissue", "replace", "is", "**", 0) 730 EQ("cobob", "bobob", "replace", "bob", "cob") 731 EQ("cobobXcobocob", "bobobXbobobob", "replace", "bob", "cob") 732 EQ("bobob", "bobob", "replace", "bot", "bot") 733 734 # replace single character (len(from)==1, len(to)>1) 735 EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK") 736 EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", -1) 737 EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", sys.maxint) 738 EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", 2) 739 EQ("ReyKKjavik", "Reykjavik", "replace", "k", "KK", 1) 740 EQ("Reykjavik", "Reykjavik", "replace", "k", "KK", 0) 741 EQ("A----B----C----", "A.B.C.", "replace", ".", "----") 742 743 EQ("Reykjavik", "Reykjavik", "replace", "q", "KK") 744 745 # replace substring (len(from)>1, len(to)!=len(from)) 746 EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam", 747 "replace", "spam", "ham") 748 EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam", 749 "replace", "spam", "ham", sys.maxint) 750 EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam", 751 "replace", "spam", "ham", -1) 752 EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam", 753 "replace", "spam", "ham", 4) 754 EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam", 755 "replace", "spam", "ham", 3) 756 EQ("ham, ham, eggs and spam", "spam, spam, eggs and spam", 757 "replace", "spam", "ham", 2) 758 EQ("ham, spam, eggs and spam", "spam, spam, eggs and spam", 759 "replace", "spam", "ham", 1) 760 EQ("spam, spam, eggs and spam", "spam, spam, eggs and spam", 761 "replace", "spam", "ham", 0) 762 763 EQ("bobob", "bobobob", "replace", "bobob", "bob") 764 EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob") 765 EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby") 766 767 with test_support.check_py3k_warnings(): 768 ba = buffer('a') 769 bb = buffer('b') 770 EQ("bbc", "abc", "replace", ba, bb) 771 EQ("aac", "abc", "replace", bb, ba) 772 773 # 774 self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1) 775 self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '') 776 self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2) 777 self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 3) 778 self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 4) 779 self.checkequal('one!two!three!', 'one!two!three!', 'replace', '!', '@', 0) 780 self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@') 781 self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@') 782 self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@', 2) 783 self.checkequal('-a-b-c-', 'abc', 'replace', '', '-') 784 self.checkequal('-a-b-c', 'abc', 'replace', '', '-', 3) 785 self.checkequal('abc', 'abc', 'replace', '', '-', 0) 786 self.checkequal('', '', 'replace', '', '') 787 self.checkequal('abc', 'abc', 'replace', 'ab', '--', 0) 788 self.checkequal('abc', 'abc', 'replace', 'xy', '--') 789 # Next three for SF bug 422088: [OSF1 alpha] string.replace(); died with 790 # MemoryError due to empty result (platform malloc issue when requesting 791 # 0 bytes). 792 self.checkequal('', '123', 'replace', '123', '') 793 self.checkequal('', '123123', 'replace', '123', '') 794 self.checkequal('x', '123x123', 'replace', '123', '') 795 796 self.checkraises(TypeError, 'hello', 'replace') 797 self.checkraises(TypeError, 'hello', 'replace', 42) 798 self.checkraises(TypeError, 'hello', 'replace', 42, 'h') 799 self.checkraises(TypeError, 'hello', 'replace', 'h', 42) 800 801 @unittest.skipIf(sys.maxint > (1 << 32) or struct.calcsize('P') != 4, 802 'only applies to 32-bit platforms') 803 def test_replace_overflow(self): 804 # Check for overflow checking on 32 bit machines 805 A2_16 = "A" * (2**16) 806 self.checkraises(OverflowError, A2_16, "replace", "", A2_16) 807 self.checkraises(OverflowError, A2_16, "replace", "A", A2_16) 808 self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16) 809 810 def test_zfill(self): 811 self.checkequal('123', '123', 'zfill', 2) 812 self.checkequal('123', '123', 'zfill', 3) 813 self.checkequal('0123', '123', 'zfill', 4) 814 self.checkequal('+123', '+123', 'zfill', 3) 815 self.checkequal('+123', '+123', 'zfill', 4) 816 self.checkequal('+0123', '+123', 'zfill', 5) 817 self.checkequal('-123', '-123', 'zfill', 3) 818 self.checkequal('-123', '-123', 'zfill', 4) 819 self.checkequal('-0123', '-123', 'zfill', 5) 820 self.checkequal('000', '', 'zfill', 3) 821 self.checkequal('34', '34', 'zfill', 1) 822 self.checkequal('0034', '34', 'zfill', 4) 823 824 self.checkraises(TypeError, '123', 'zfill') 825 826 827class NonStringModuleTest: 828 # additional test cases for all string classes from bytearray to 829 # UserString, but not valid for the "string" module 830 831 def test_islower(self): 832 self.checkequal(False, '', 'islower') 833 self.checkequal(True, 'a', 'islower') 834 self.checkequal(False, 'A', 'islower') 835 self.checkequal(False, '\n', 'islower') 836 self.checkequal(True, 'abc', 'islower') 837 self.checkequal(False, 'aBc', 'islower') 838 self.checkequal(True, 'abc\n', 'islower') 839 self.checkraises(TypeError, 'abc', 'islower', 42) 840 841 def test_isupper(self): 842 self.checkequal(False, '', 'isupper') 843 self.checkequal(False, 'a', 'isupper') 844 self.checkequal(True, 'A', 'isupper') 845 self.checkequal(False, '\n', 'isupper') 846 self.checkequal(True, 'ABC', 'isupper') 847 self.checkequal(False, 'AbC', 'isupper') 848 self.checkequal(True, 'ABC\n', 'isupper') 849 self.checkraises(TypeError, 'abc', 'isupper', 42) 850 851 def test_istitle(self): 852 self.checkequal(False, '', 'istitle') 853 self.checkequal(False, 'a', 'istitle') 854 self.checkequal(True, 'A', 'istitle') 855 self.checkequal(False, '\n', 'istitle') 856 self.checkequal(True, 'A Titlecased Line', 'istitle') 857 self.checkequal(True, 'A\nTitlecased Line', 'istitle') 858 self.checkequal(True, 'A Titlecased, Line', 'istitle') 859 self.checkequal(False, 'Not a capitalized String', 'istitle') 860 self.checkequal(False, 'Not\ta Titlecase String', 'istitle') 861 self.checkequal(False, 'Not--a Titlecase String', 'istitle') 862 self.checkequal(False, 'NOT', 'istitle') 863 self.checkraises(TypeError, 'abc', 'istitle', 42) 864 865 def test_isspace(self): 866 self.checkequal(False, '', 'isspace') 867 self.checkequal(False, 'a', 'isspace') 868 self.checkequal(True, ' ', 'isspace') 869 self.checkequal(True, '\t', 'isspace') 870 self.checkequal(True, '\r', 'isspace') 871 self.checkequal(True, '\n', 'isspace') 872 self.checkequal(True, ' \t\r\n', 'isspace') 873 self.checkequal(False, ' \t\r\na', 'isspace') 874 self.checkraises(TypeError, 'abc', 'isspace', 42) 875 876 def test_isalpha(self): 877 self.checkequal(False, '', 'isalpha') 878 self.checkequal(True, 'a', 'isalpha') 879 self.checkequal(True, 'A', 'isalpha') 880 self.checkequal(False, '\n', 'isalpha') 881 self.checkequal(True, 'abc', 'isalpha') 882 self.checkequal(False, 'aBc123', 'isalpha') 883 self.checkequal(False, 'abc\n', 'isalpha') 884 self.checkraises(TypeError, 'abc', 'isalpha', 42) 885 886 def test_isalnum(self): 887 self.checkequal(False, '', 'isalnum') 888 self.checkequal(True, 'a', 'isalnum') 889 self.checkequal(True, 'A', 'isalnum') 890 self.checkequal(False, '\n', 'isalnum') 891 self.checkequal(True, '123abc456', 'isalnum') 892 self.checkequal(True, 'a1b3c', 'isalnum') 893 self.checkequal(False, 'aBc000 ', 'isalnum') 894 self.checkequal(False, 'abc\n', 'isalnum') 895 self.checkraises(TypeError, 'abc', 'isalnum', 42) 896 897 def test_isdigit(self): 898 self.checkequal(False, '', 'isdigit') 899 self.checkequal(False, 'a', 'isdigit') 900 self.checkequal(True, '0', 'isdigit') 901 self.checkequal(True, '0123456789', 'isdigit') 902 self.checkequal(False, '0123456789a', 'isdigit') 903 904 self.checkraises(TypeError, 'abc', 'isdigit', 42) 905 906 def test_title(self): 907 self.checkequal(' Hello ', ' hello ', 'title') 908 self.checkequal('Hello ', 'hello ', 'title') 909 self.checkequal('Hello ', 'Hello ', 'title') 910 self.checkequal('Format This As Title String', "fOrMaT thIs aS titLe String", 'title') 911 self.checkequal('Format,This-As*Title;String', "fOrMaT,thIs-aS*titLe;String", 'title', ) 912 self.checkequal('Getint', "getInt", 'title') 913 self.checkraises(TypeError, 'hello', 'title', 42) 914 915 def test_splitlines(self): 916 self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\rghi", 'splitlines') 917 self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\r\nghi", 'splitlines') 918 self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi", 'splitlines') 919 self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi\n", 'splitlines') 920 self.checkequal(['abc', 'def', 'ghi', ''], "abc\ndef\r\nghi\n\r", 'splitlines') 921 self.checkequal(['', 'abc', 'def', 'ghi', ''], "\nabc\ndef\r\nghi\n\r", 'splitlines') 922 self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'], "\nabc\ndef\r\nghi\n\r", 'splitlines', 1) 923 924 self.checkraises(TypeError, 'abc', 'splitlines', 42, 42) 925 926 927class MixinStrUnicodeUserStringTest(NonStringModuleTest): 928 # additional tests that only work for 929 # stringlike objects, i.e. str, unicode, UserString 930 # (but not the string module) 931 932 def test_startswith(self): 933 self.checkequal(True, 'hello', 'startswith', 'he') 934 self.checkequal(True, 'hello', 'startswith', 'hello') 935 self.checkequal(False, 'hello', 'startswith', 'hello world') 936 self.checkequal(True, 'hello', 'startswith', '') 937 self.checkequal(False, 'hello', 'startswith', 'ello') 938 self.checkequal(True, 'hello', 'startswith', 'ello', 1) 939 self.checkequal(True, 'hello', 'startswith', 'o', 4) 940 self.checkequal(False, 'hello', 'startswith', 'o', 5) 941 self.checkequal(True, 'hello', 'startswith', '', 5) 942 self.checkequal(False, 'hello', 'startswith', 'lo', 6) 943 self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3) 944 self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3, 7) 945 self.checkequal(False, 'helloworld', 'startswith', 'lowo', 3, 6) 946 947 # test negative indices 948 self.checkequal(True, 'hello', 'startswith', 'he', 0, -1) 949 self.checkequal(True, 'hello', 'startswith', 'he', -53, -1) 950 self.checkequal(False, 'hello', 'startswith', 'hello', 0, -1) 951 self.checkequal(False, 'hello', 'startswith', 'hello world', -1, -10) 952 self.checkequal(False, 'hello', 'startswith', 'ello', -5) 953 self.checkequal(True, 'hello', 'startswith', 'ello', -4) 954 self.checkequal(False, 'hello', 'startswith', 'o', -2) 955 self.checkequal(True, 'hello', 'startswith', 'o', -1) 956 self.checkequal(True, 'hello', 'startswith', '', -3, -3) 957 self.checkequal(False, 'hello', 'startswith', 'lo', -9) 958 959 self.checkraises(TypeError, 'hello', 'startswith') 960 self.checkraises(TypeError, 'hello', 'startswith', 42) 961 962 # test tuple arguments 963 self.checkequal(True, 'hello', 'startswith', ('he', 'ha')) 964 self.checkequal(False, 'hello', 'startswith', ('lo', 'llo')) 965 self.checkequal(True, 'hello', 'startswith', ('hellox', 'hello')) 966 self.checkequal(False, 'hello', 'startswith', ()) 967 self.checkequal(True, 'helloworld', 'startswith', ('hellowo', 968 'rld', 'lowo'), 3) 969 self.checkequal(False, 'helloworld', 'startswith', ('hellowo', 'ello', 970 'rld'), 3) 971 self.checkequal(True, 'hello', 'startswith', ('lo', 'he'), 0, -1) 972 self.checkequal(False, 'hello', 'startswith', ('he', 'hel'), 0, 1) 973 self.checkequal(True, 'hello', 'startswith', ('he', 'hel'), 0, 2) 974 975 self.checkraises(TypeError, 'hello', 'startswith', (42,)) 976 977 def test_endswith(self): 978 self.checkequal(True, 'hello', 'endswith', 'lo') 979 self.checkequal(False, 'hello', 'endswith', 'he') 980 self.checkequal(True, 'hello', 'endswith', '') 981 self.checkequal(False, 'hello', 'endswith', 'hello world') 982 self.checkequal(False, 'helloworld', 'endswith', 'worl') 983 self.checkequal(True, 'helloworld', 'endswith', 'worl', 3, 9) 984 self.checkequal(True, 'helloworld', 'endswith', 'world', 3, 12) 985 self.checkequal(True, 'helloworld', 'endswith', 'lowo', 1, 7) 986 self.checkequal(True, 'helloworld', 'endswith', 'lowo', 2, 7) 987 self.checkequal(True, 'helloworld', 'endswith', 'lowo', 3, 7) 988 self.checkequal(False, 'helloworld', 'endswith', 'lowo', 4, 7) 989 self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, 8) 990 self.checkequal(False, 'ab', 'endswith', 'ab', 0, 1) 991 self.checkequal(False, 'ab', 'endswith', 'ab', 0, 0) 992 993 # test negative indices 994 self.checkequal(True, 'hello', 'endswith', 'lo', -2) 995 self.checkequal(False, 'hello', 'endswith', 'he', -2) 996 self.checkequal(True, 'hello', 'endswith', '', -3, -3) 997 self.checkequal(False, 'hello', 'endswith', 'hello world', -10, -2) 998 self.checkequal(False, 'helloworld', 'endswith', 'worl', -6) 999 self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, -1) 1000 self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, 9) 1001 self.checkequal(True, 'helloworld', 'endswith', 'world', -7, 12) 1002 self.checkequal(True, 'helloworld', 'endswith', 'lowo', -99, -3) 1003 self.checkequal(True, 'helloworld', 'endswith', 'lowo', -8, -3) 1004 self.checkequal(True, 'helloworld', 'endswith', 'lowo', -7, -3) 1005 self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, -4) 1006 self.checkequal(False, 'helloworld', 'endswith', 'lowo', -8, -2) 1007 1008 self.checkraises(TypeError, 'hello', 'endswith') 1009 self.checkraises(TypeError, 'hello', 'endswith', 42) 1010 1011 # test tuple arguments 1012 self.checkequal(False, 'hello', 'endswith', ('he', 'ha')) 1013 self.checkequal(True, 'hello', 'endswith', ('lo', 'llo')) 1014 self.checkequal(True, 'hello', 'endswith', ('hellox', 'hello')) 1015 self.checkequal(False, 'hello', 'endswith', ()) 1016 self.checkequal(True, 'helloworld', 'endswith', ('hellowo', 1017 'rld', 'lowo'), 3) 1018 self.checkequal(False, 'helloworld', 'endswith', ('hellowo', 'ello', 1019 'rld'), 3, -1) 1020 self.checkequal(True, 'hello', 'endswith', ('hell', 'ell'), 0, -1) 1021 self.checkequal(False, 'hello', 'endswith', ('he', 'hel'), 0, 1) 1022 self.checkequal(True, 'hello', 'endswith', ('he', 'hell'), 0, 4) 1023 1024 self.checkraises(TypeError, 'hello', 'endswith', (42,)) 1025 1026 def test___contains__(self): 1027 self.checkequal(True, '', '__contains__', '') 1028 self.checkequal(True, 'abc', '__contains__', '') 1029 self.checkequal(False, 'abc', '__contains__', '\0') 1030 self.checkequal(True, '\0abc', '__contains__', '\0') 1031 self.checkequal(True, 'abc\0', '__contains__', '\0') 1032 self.checkequal(True, '\0abc', '__contains__', 'a') 1033 self.checkequal(True, 'asdf', '__contains__', 'asdf') 1034 self.checkequal(False, 'asd', '__contains__', 'asdf') 1035 self.checkequal(False, '', '__contains__', 'asdf') 1036 1037 def test_subscript(self): 1038 self.checkequal(u'a', 'abc', '__getitem__', 0) 1039 self.checkequal(u'c', 'abc', '__getitem__', -1) 1040 self.checkequal(u'a', 'abc', '__getitem__', 0L) 1041 self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 3)) 1042 self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 1000)) 1043 self.checkequal(u'a', 'abc', '__getitem__', slice(0, 1)) 1044 self.checkequal(u'', 'abc', '__getitem__', slice(0, 0)) 1045 1046 self.checkraises(TypeError, 'abc', '__getitem__', 'def') 1047 1048 def test_slice(self): 1049 self.checkequal('abc', 'abc', '__getslice__', 0, 1000) 1050 self.checkequal('abc', 'abc', '__getslice__', 0, 3) 1051 self.checkequal('ab', 'abc', '__getslice__', 0, 2) 1052 self.checkequal('bc', 'abc', '__getslice__', 1, 3) 1053 self.checkequal('b', 'abc', '__getslice__', 1, 2) 1054 self.checkequal('', 'abc', '__getslice__', 2, 2) 1055 self.checkequal('', 'abc', '__getslice__', 1000, 1000) 1056 self.checkequal('', 'abc', '__getslice__', 2000, 1000) 1057 self.checkequal('', 'abc', '__getslice__', 2, 1) 1058 1059 self.checkraises(TypeError, 'abc', '__getslice__', 'def') 1060 1061 def test_extended_getslice(self): 1062 # Test extended slicing by comparing with list slicing. 1063 s = string.ascii_letters + string.digits 1064 indices = (0, None, 1, 3, 41, -1, -2, -37) 1065 for start in indices: 1066 for stop in indices: 1067 # Skip step 0 (invalid) 1068 for step in indices[1:]: 1069 L = list(s)[start:stop:step] 1070 self.checkequal(u"".join(L), s, '__getitem__', 1071 slice(start, stop, step)) 1072 1073 def test_mul(self): 1074 self.checkequal('', 'abc', '__mul__', -1) 1075 self.checkequal('', 'abc', '__mul__', 0) 1076 self.checkequal('abc', 'abc', '__mul__', 1) 1077 self.checkequal('abcabcabc', 'abc', '__mul__', 3) 1078 self.checkraises(TypeError, 'abc', '__mul__') 1079 self.checkraises(TypeError, 'abc', '__mul__', '') 1080 # XXX: on a 64-bit system, this doesn't raise an overflow error, 1081 # but either raises a MemoryError, or succeeds (if you have 54TiB) 1082 #self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000) 1083 1084 def test_join(self): 1085 # join now works with any sequence type 1086 # moved here, because the argument order is 1087 # different in string.join (see the test in 1088 # test.test_string.StringTest.test_join) 1089 self.checkequal('a b c d', ' ', 'join', ['a', 'b', 'c', 'd']) 1090 self.checkequal('abcd', '', 'join', ('a', 'b', 'c', 'd')) 1091 self.checkequal('bd', '', 'join', ('', 'b', '', 'd')) 1092 self.checkequal('ac', '', 'join', ('a', '', 'c', '')) 1093 self.checkequal('w x y z', ' ', 'join', Sequence()) 1094 self.checkequal('abc', 'a', 'join', ('abc',)) 1095 self.checkequal('z', 'a', 'join', UserList(['z'])) 1096 if test_support.have_unicode: 1097 self.checkequal(unicode('a.b.c'), unicode('.'), 'join', ['a', 'b', 'c']) 1098 self.checkequal(unicode('a.b.c'), '.', 'join', [unicode('a'), 'b', 'c']) 1099 self.checkequal(unicode('a.b.c'), '.', 'join', ['a', unicode('b'), 'c']) 1100 self.checkequal(unicode('a.b.c'), '.', 'join', ['a', 'b', unicode('c')]) 1101 self.checkraises(TypeError, '.', 'join', ['a', unicode('b'), 3]) 1102 for i in [5, 25, 125]: 1103 self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join', 1104 ['a' * i] * i) 1105 self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join', 1106 ('a' * i,) * i) 1107 1108 self.checkraises(TypeError, ' ', 'join', BadSeq1()) 1109 self.checkequal('a b c', ' ', 'join', BadSeq2()) 1110 1111 self.checkraises(TypeError, ' ', 'join') 1112 self.checkraises(TypeError, ' ', 'join', None) 1113 self.checkraises(TypeError, ' ', 'join', 7) 1114 self.checkraises(TypeError, ' ', 'join', Sequence([7, 'hello', 123L])) 1115 try: 1116 def f(): 1117 yield 4 + "" 1118 self.fixtype(' ').join(f()) 1119 except TypeError, e: 1120 if '+' not in str(e): 1121 self.fail('join() ate exception message') 1122 else: 1123 self.fail('exception not raised') 1124 1125 def test_formatting(self): 1126 self.checkequal('+hello+', '+%s+', '__mod__', 'hello') 1127 self.checkequal('+10+', '+%d+', '__mod__', 10) 1128 self.checkequal('a', "%c", '__mod__', "a") 1129 self.checkequal('a', "%c", '__mod__', "a") 1130 self.checkequal('"', "%c", '__mod__', 34) 1131 self.checkequal('$', "%c", '__mod__', 36) 1132 self.checkequal('10', "%d", '__mod__', 10) 1133 self.checkequal('\x7f', "%c", '__mod__', 0x7f) 1134 1135 for ordinal in (-100, 0x200000): 1136 # unicode raises ValueError, str raises OverflowError 1137 self.checkraises((ValueError, OverflowError), '%c', '__mod__', ordinal) 1138 1139 longvalue = sys.maxint + 10L 1140 slongvalue = str(longvalue) 1141 if slongvalue[-1] in ("L","l"): slongvalue = slongvalue[:-1] 1142 self.checkequal(' 42', '%3ld', '__mod__', 42) 1143 self.checkequal('42', '%d', '__mod__', 42L) 1144 self.checkequal('42', '%d', '__mod__', 42.0) 1145 self.checkequal(slongvalue, '%d', '__mod__', longvalue) 1146 self.checkcall('%d', '__mod__', float(longvalue)) 1147 self.checkequal('0042.00', '%07.2f', '__mod__', 42) 1148 self.checkequal('0042.00', '%07.2F', '__mod__', 42) 1149 1150 self.checkraises(TypeError, 'abc', '__mod__') 1151 self.checkraises(TypeError, '%(foo)s', '__mod__', 42) 1152 self.checkraises(TypeError, '%s%s', '__mod__', (42,)) 1153 self.checkraises(TypeError, '%c', '__mod__', (None,)) 1154 self.checkraises(ValueError, '%(foo', '__mod__', {}) 1155 self.checkraises(TypeError, '%(foo)s %(bar)s', '__mod__', ('foo', 42)) 1156 self.checkraises(TypeError, '%d', '__mod__', "42") # not numeric 1157 self.checkraises(TypeError, '%d', '__mod__', (42+0j)) # no int/long conversion provided 1158 1159 # argument names with properly nested brackets are supported 1160 self.checkequal('bar', '%((foo))s', '__mod__', {'(foo)': 'bar'}) 1161 1162 # 100 is a magic number in PyUnicode_Format, this forces a resize 1163 self.checkequal(103*'a'+'x', '%sx', '__mod__', 103*'a') 1164 1165 self.checkraises(TypeError, '%*s', '__mod__', ('foo', 'bar')) 1166 self.checkraises(TypeError, '%10.*f', '__mod__', ('foo', 42.)) 1167 self.checkraises(ValueError, '%10', '__mod__', (42,)) 1168 1169 class X(object): pass 1170 self.checkraises(TypeError, 'abc', '__mod__', X()) 1171 class X(Exception): 1172 def __getitem__(self, k): 1173 return k 1174 self.checkequal('melon apple', '%(melon)s %(apple)s', '__mod__', X()) 1175 1176 @test_support.cpython_only 1177 def test_formatting_c_limits(self): 1178 from _testcapi import PY_SSIZE_T_MAX, INT_MAX, UINT_MAX 1179 SIZE_MAX = (1 << (PY_SSIZE_T_MAX.bit_length() + 1)) - 1 1180 width = int(PY_SSIZE_T_MAX + 1) 1181 if width <= sys.maxint: 1182 self.checkraises(OverflowError, '%*s', '__mod__', (width, '')) 1183 prec = int(INT_MAX + 1) 1184 if prec <= sys.maxint: 1185 self.checkraises(OverflowError, '%.*f', '__mod__', (prec, 1. / 7)) 1186 # Issue 15989 1187 width = int(SIZE_MAX + 1) 1188 if width <= sys.maxint: 1189 self.checkraises(OverflowError, '%*s', '__mod__', (width, '')) 1190 prec = int(UINT_MAX + 1) 1191 if prec <= sys.maxint: 1192 self.checkraises(OverflowError, '%.*f', '__mod__', (prec, 1. / 7)) 1193 1194 def test_floatformatting(self): 1195 # float formatting 1196 for prec in xrange(100): 1197 format = '%%.%if' % prec 1198 value = 0.01 1199 for x in xrange(60): 1200 value = value * 3.14159265359 / 3.0 * 10.0 1201 self.checkcall(format, "__mod__", value) 1202 1203 def test_inplace_rewrites(self): 1204 # Check that strings don't copy and modify cached single-character strings 1205 self.checkequal('a', 'A', 'lower') 1206 self.checkequal(True, 'A', 'isupper') 1207 self.checkequal('A', 'a', 'upper') 1208 self.checkequal(True, 'a', 'islower') 1209 1210 self.checkequal('a', 'A', 'replace', 'A', 'a') 1211 self.checkequal(True, 'A', 'isupper') 1212 1213 self.checkequal('A', 'a', 'capitalize') 1214 self.checkequal(True, 'a', 'islower') 1215 1216 self.checkequal('A', 'a', 'swapcase') 1217 self.checkequal(True, 'a', 'islower') 1218 1219 self.checkequal('A', 'a', 'title') 1220 self.checkequal(True, 'a', 'islower') 1221 1222 def test_partition(self): 1223 1224 self.checkequal(('this is the par', 'ti', 'tion method'), 1225 'this is the partition method', 'partition', 'ti') 1226 1227 # from raymond's original specification 1228 S = 'http://www.python.org' 1229 self.checkequal(('http', '://', 'www.python.org'), S, 'partition', '://') 1230 self.checkequal(('http://www.python.org', '', ''), S, 'partition', '?') 1231 self.checkequal(('', 'http://', 'www.python.org'), S, 'partition', 'http://') 1232 self.checkequal(('http://www.python.', 'org', ''), S, 'partition', 'org') 1233 1234 self.checkraises(ValueError, S, 'partition', '') 1235 self.checkraises(TypeError, S, 'partition', None) 1236 1237 # mixed use of str and unicode 1238 self.assertEqual('a/b/c'.partition(u'/'), ('a', '/', 'b/c')) 1239 1240 def test_rpartition(self): 1241 1242 self.checkequal(('this is the rparti', 'ti', 'on method'), 1243 'this is the rpartition method', 'rpartition', 'ti') 1244 1245 # from raymond's original specification 1246 S = 'http://www.python.org' 1247 self.checkequal(('http', '://', 'www.python.org'), S, 'rpartition', '://') 1248 self.checkequal(('', '', 'http://www.python.org'), S, 'rpartition', '?') 1249 self.checkequal(('', 'http://', 'www.python.org'), S, 'rpartition', 'http://') 1250 self.checkequal(('http://www.python.', 'org', ''), S, 'rpartition', 'org') 1251 1252 self.checkraises(ValueError, S, 'rpartition', '') 1253 self.checkraises(TypeError, S, 'rpartition', None) 1254 1255 # mixed use of str and unicode 1256 self.assertEqual('a/b/c'.rpartition(u'/'), ('a/b', '/', 'c')) 1257 1258 def test_none_arguments(self): 1259 # issue 11828 1260 s = 'hello' 1261 self.checkequal(2, s, 'find', 'l', None) 1262 self.checkequal(3, s, 'find', 'l', -2, None) 1263 self.checkequal(2, s, 'find', 'l', None, -2) 1264 self.checkequal(0, s, 'find', 'h', None, None) 1265 1266 self.checkequal(3, s, 'rfind', 'l', None) 1267 self.checkequal(3, s, 'rfind', 'l', -2, None) 1268 self.checkequal(2, s, 'rfind', 'l', None, -2) 1269 self.checkequal(0, s, 'rfind', 'h', None, None) 1270 1271 self.checkequal(2, s, 'index', 'l', None) 1272 self.checkequal(3, s, 'index', 'l', -2, None) 1273 self.checkequal(2, s, 'index', 'l', None, -2) 1274 self.checkequal(0, s, 'index', 'h', None, None) 1275 1276 self.checkequal(3, s, 'rindex', 'l', None) 1277 self.checkequal(3, s, 'rindex', 'l', -2, None) 1278 self.checkequal(2, s, 'rindex', 'l', None, -2) 1279 self.checkequal(0, s, 'rindex', 'h', None, None) 1280 1281 self.checkequal(2, s, 'count', 'l', None) 1282 self.checkequal(1, s, 'count', 'l', -2, None) 1283 self.checkequal(1, s, 'count', 'l', None, -2) 1284 self.checkequal(0, s, 'count', 'x', None, None) 1285 1286 self.checkequal(True, s, 'endswith', 'o', None) 1287 self.checkequal(True, s, 'endswith', 'lo', -2, None) 1288 self.checkequal(True, s, 'endswith', 'l', None, -2) 1289 self.checkequal(False, s, 'endswith', 'x', None, None) 1290 1291 self.checkequal(True, s, 'startswith', 'h', None) 1292 self.checkequal(True, s, 'startswith', 'l', -2, None) 1293 self.checkequal(True, s, 'startswith', 'h', None, -2) 1294 self.checkequal(False, s, 'startswith', 'x', None, None) 1295 1296 def test_find_etc_raise_correct_error_messages(self): 1297 # issue 11828 1298 s = 'hello' 1299 x = 'x' 1300 self.assertRaisesRegexp(TypeError, r'\bfind\b', s.find, 1301 x, None, None, None) 1302 self.assertRaisesRegexp(TypeError, r'\brfind\b', s.rfind, 1303 x, None, None, None) 1304 self.assertRaisesRegexp(TypeError, r'\bindex\b', s.index, 1305 x, None, None, None) 1306 self.assertRaisesRegexp(TypeError, r'\brindex\b', s.rindex, 1307 x, None, None, None) 1308 self.assertRaisesRegexp(TypeError, r'^count\(', s.count, 1309 x, None, None, None) 1310 self.assertRaisesRegexp(TypeError, r'^startswith\(', s.startswith, 1311 x, None, None, None) 1312 self.assertRaisesRegexp(TypeError, r'^endswith\(', s.endswith, 1313 x, None, None, None) 1314 1315class MixinStrStringUserStringTest: 1316 # Additional tests for 8bit strings, i.e. str, UserString and 1317 # the string module 1318 1319 def test_maketrans(self): 1320 self.assertEqual( 1321 ''.join(map(chr, xrange(256))).replace('abc', 'xyz'), 1322 string.maketrans('abc', 'xyz') 1323 ) 1324 self.assertRaises(ValueError, string.maketrans, 'abc', 'xyzw') 1325 1326 def test_translate(self): 1327 table = string.maketrans('abc', 'xyz') 1328 self.checkequal('xyzxyz', 'xyzabcdef', 'translate', table, 'def') 1329 1330 table = string.maketrans('a', 'A') 1331 self.checkequal('Abc', 'abc', 'translate', table) 1332 self.checkequal('xyz', 'xyz', 'translate', table) 1333 self.checkequal('yz', 'xyz', 'translate', table, 'x') 1334 self.checkequal('yx', 'zyzzx', 'translate', None, 'z') 1335 self.checkequal('zyzzx', 'zyzzx', 'translate', None, '') 1336 self.checkequal('zyzzx', 'zyzzx', 'translate', None) 1337 self.checkraises(ValueError, 'xyz', 'translate', 'too short', 'strip') 1338 self.checkraises(ValueError, 'xyz', 'translate', 'too short') 1339 1340 1341class MixinStrUserStringTest: 1342 # Additional tests that only work with 1343 # 8bit compatible object, i.e. str and UserString 1344 1345 @unittest.skipUnless(test_support.have_unicode, 'no unicode support') 1346 def test_encoding_decoding(self): 1347 codecs = [('rot13', 'uryyb jbeyq'), 1348 ('base64', 'aGVsbG8gd29ybGQ=\n'), 1349 ('hex', '68656c6c6f20776f726c64'), 1350 ('uu', 'begin 666 <data>\n+:&5L;&\\@=V]R;&0 \n \nend\n')] 1351 for encoding, data in codecs: 1352 with test_support.check_py3k_warnings(): 1353 self.checkequal(data, 'hello world', 'encode', encoding) 1354 with test_support.check_py3k_warnings(): 1355 self.checkequal('hello world', data, 'decode', encoding) 1356 # zlib is optional, so we make the test optional too... 1357 try: 1358 import zlib 1359 except ImportError: 1360 pass 1361 else: 1362 data = 'x\x9c\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\x01\x00\x1a\x0b\x04]' 1363 with test_support.check_py3k_warnings(): 1364 self.checkequal(data, 'hello world', 'encode', 'zlib') 1365 with test_support.check_py3k_warnings(): 1366 self.checkequal('hello world', data, 'decode', 'zlib') 1367 1368 self.checkraises(TypeError, 'xyz', 'decode', 42) 1369 self.checkraises(TypeError, 'xyz', 'encode', 42) 1370 1371 1372class MixinStrUnicodeTest: 1373 # Additional tests that only work with str and unicode. 1374 1375 def test_bug1001011(self): 1376 # Make sure join returns a NEW object for single item sequences 1377 # involving a subclass. 1378 # Make sure that it is of the appropriate type. 1379 # Check the optimisation still occurs for standard objects. 1380 t = self.type2test 1381 class subclass(t): 1382 pass 1383 s1 = subclass("abcd") 1384 s2 = t().join([s1]) 1385 self.assertTrue(s1 is not s2) 1386 self.assertTrue(type(s2) is t) 1387 1388 s1 = t("abcd") 1389 s2 = t().join([s1]) 1390 self.assertTrue(s1 is s2) 1391 1392 # Should also test mixed-type join. 1393 if t is unicode: 1394 s1 = subclass("abcd") 1395 s2 = "".join([s1]) 1396 self.assertTrue(s1 is not s2) 1397 self.assertTrue(type(s2) is t) 1398 1399 s1 = t("abcd") 1400 s2 = "".join([s1]) 1401 self.assertTrue(s1 is s2) 1402 1403 elif t is str: 1404 s1 = subclass("abcd") 1405 s2 = u"".join([s1]) 1406 self.assertTrue(s1 is not s2) 1407 self.assertTrue(type(s2) is unicode) # promotes! 1408 1409 s1 = t("abcd") 1410 s2 = u"".join([s1]) 1411 self.assertTrue(s1 is not s2) 1412 self.assertTrue(type(s2) is unicode) # promotes! 1413 1414 else: 1415 self.fail("unexpected type for MixinStrUnicodeTest %r" % t) 1416