string_tests.py 57 KB
Newer Older
1 2 3
"""
Common tests shared by test_str, test_unicode, test_userstring and test_string.
"""
4

5
import unittest, string, sys, struct
6
from test import support
7
from collections import UserList
8

9
class Sequence:
10
    def __init__(self, seq='wxyz'): self.seq = seq
11 12 13 14
    def __len__(self): return len(self.seq)
    def __getitem__(self, i): return self.seq[i]

class BadSeq1(Sequence):
15
    def __init__(self): self.seq = [7, 'hello', 123]
16
    def __str__(self): return '{0} {1} {2}'.format(*self.seq)
17 18 19 20 21

class BadSeq2(Sequence):
    def __init__(self): self.seq = ['a', 'b', 'c']
    def __len__(self): return 8

22 23 24 25
class BaseTest(unittest.TestCase):
    # These tests are for buffers of values (bytes) and not
    # specific to character interpretation, used for bytes objects
    # and various string implementations
26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43

    # The type to be tested
    # Change in subclasses to change the behaviour of fixtesttype()
    type2test = None

    # All tests pass their arguments to the testing methods
    # as str objects. fixtesttype() can be used to propagate
    # these arguments to the appropriate type
    def fixtype(self, obj):
        if isinstance(obj, str):
            return self.__class__.type2test(obj)
        elif isinstance(obj, list):
            return [self.fixtype(x) for x in obj]
        elif isinstance(obj, tuple):
            return tuple([self.fixtype(x) for x in obj])
        elif isinstance(obj, dict):
            return dict([
               (self.fixtype(key), self.fixtype(value))
44
               for (key, value) in obj.items()
45 46 47 48
            ])
        else:
            return obj

49 50
    # check that obj.method(*args) returns result
    def checkequal(self, result, obj, methodname, *args):
51
        result = self.fixtype(result)
52
        obj = self.fixtype(obj)
53
        args = self.fixtype(args)
54
        realresult = getattr(obj, methodname)(*args)
55 56 57 58 59 60
        self.assertEqual(
            result,
            realresult
        )
        # if the original is returned make sure that
        # this doesn't happen with subclasses
61 62 63 64 65 66 67 68 69 70 71 72 73 74
        if obj is realresult:
            try:
                class subtype(self.__class__.type2test):
                    pass
            except TypeError:
                pass  # Skip this if we can't subclass
            else:
                obj = subtype(obj)
                realresult = getattr(obj, methodname)(*args)
                self.assert_(obj is not realresult)

    # check that obj.method(*args) raises exc
    def checkraises(self, exc, obj, methodname, *args):
        obj = self.fixtype(obj)
75 76 77
        args = self.fixtype(args)
        self.assertRaises(
            exc,
78
            getattr(obj, methodname),
79 80 81
            *args
        )

82 83 84
    # call obj.method(*args) without any checks
    def checkcall(self, obj, methodname, *args):
        obj = self.fixtype(obj)
85
        args = self.fixtype(args)
86
        getattr(obj, methodname)(*args)
87 88 89 90 91 92 93 94 95

    def test_count(self):
        self.checkequal(3, 'aaa', 'count', 'a')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(3, 'aaa', 'count', 'a')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(3, 'aaa', 'count', 'a')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(0, 'aaa', 'count', 'b')
96 97
        self.checkequal(2, 'aaa', 'count', 'a', 1)
        self.checkequal(0, 'aaa', 'count', 'a', 10)
98 99
        self.checkequal(1, 'aaa', 'count', 'a', -1)
        self.checkequal(3, 'aaa', 'count', 'a', -10)
100 101
        self.checkequal(1, 'aaa', 'count', 'a', 0, 1)
        self.checkequal(3, 'aaa', 'count', 'a', 0, 10)
102 103
        self.checkequal(2, 'aaa', 'count', 'a', 0, -1)
        self.checkequal(0, 'aaa', 'count', 'a', 0, -10)
104 105 106 107 108
        self.checkequal(3, 'aaa', 'count', '', 1)
        self.checkequal(1, 'aaa', 'count', '', 3)
        self.checkequal(0, 'aaa', 'count', '', 10)
        self.checkequal(2, 'aaa', 'count', '', -1)
        self.checkequal(4, 'aaa', 'count', '', -10)
109

110 111 112 113 114 115 116 117
        self.checkequal(1, '', 'count', '')
        self.checkequal(0, '', 'count', '', 1, 1)
        self.checkequal(0, '', 'count', '', sys.maxsize, 0)

        self.checkequal(0, '', 'count', 'xx')
        self.checkequal(0, '', 'count', 'xx', 1, 1)
        self.checkequal(0, '', 'count', 'xx', sys.maxsize, 0)

118 119 120
        self.checkraises(TypeError, 'hello', 'count')
        self.checkraises(TypeError, 'hello', 'count', 42)

121 122 123 124 125 126 127
        # For a variety of combinations,
        #    verify that str.count() matches an equivalent function
        #    replacing all occurrences and then differencing the string lengths
        charset = ['', 'a', 'b']
        digits = 7
        base = len(charset)
        teststrings = set()
128
        for i in range(base ** digits):
129
            entry = []
130
            for j in range(digits):
131 132 133
                i, m = divmod(i, base)
                entry.append(charset[m])
            teststrings.add(''.join(entry))
134
        teststrings = [self.fixtype(ts) for ts in teststrings]
135 136 137 138 139
        for i in teststrings:
            n = len(i)
            for j in teststrings:
                r1 = i.count(j)
                if j:
140 141
                    r2, rem = divmod(n - len(i.replace(j, self.fixtype(''))),
                                     len(j))
142 143 144
                else:
                    r2, rem = len(i)+1, 0
                if rem or r1 != r2:
145 146
                    self.assertEqual(rem, 0, '%s != 0 for %s' % (rem, i))
                    self.assertEqual(r1, r2, '%s != %s for %s' % (r1, r2, i))
147

148 149 150 151 152
    def test_find(self):
        self.checkequal(0, 'abcdefghiabc', 'find', 'abc')
        self.checkequal(9, 'abcdefghiabc', 'find', 'abc', 1)
        self.checkequal(-1, 'abcdefghiabc', 'find', 'def', 4)

153 154 155 156
        self.checkequal(0, 'abc', 'find', '', 0)
        self.checkequal(3, 'abc', 'find', '', 3)
        self.checkequal(-1, 'abc', 'find', '', 4)

157 158 159 160 161 162 163
        # to check the ability to pass None as defaults
        self.checkequal( 2, 'rrarrrrrrrrra', 'find', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'find', 'a', 4)
        self.checkequal(-1, 'rrarrrrrrrrra', 'find', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'find', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'find', 'a', None, 6)

164 165 166
        self.checkraises(TypeError, 'hello', 'find')
        self.checkraises(TypeError, 'hello', 'find', 42)

167 168 169 170 171 172 173 174
        self.checkequal(0, '', 'find', '')
        self.checkequal(-1, '', 'find', '', 1, 1)
        self.checkequal(-1, '', 'find', '', sys.maxsize, 0)

        self.checkequal(-1, '', 'find', 'xx')
        self.checkequal(-1, '', 'find', 'xx', 1, 1)
        self.checkequal(-1, '', 'find', 'xx', sys.maxsize, 0)

175 176 177
        # issue 7458
        self.checkequal(-1, 'ab', 'find', 'xxx', sys.maxsize + 1, 0)

178 179 180 181 182 183 184
        # For a variety of combinations,
        #    verify that str.find() matches __contains__
        #    and that the found substring is really at that location
        charset = ['', 'a', 'b', 'c']
        digits = 5
        base = len(charset)
        teststrings = set()
185
        for i in range(base ** digits):
186
            entry = []
187
            for j in range(digits):
188 189 190
                i, m = divmod(i, base)
                entry.append(charset[m])
            teststrings.add(''.join(entry))
191
        teststrings = [self.fixtype(ts) for ts in teststrings]
192 193 194 195 196
        for i in teststrings:
            for j in teststrings:
                loc = i.find(j)
                r1 = (loc != -1)
                r2 = j in i
197
                self.assertEqual(r1, r2)
198 199 200
                if loc != -1:
                    self.assertEqual(i[loc:loc+len(j)], j)

201 202 203 204 205 206
    def test_rfind(self):
        self.checkequal(9,  'abcdefghiabc', 'rfind', 'abc')
        self.checkequal(12, 'abcdefghiabc', 'rfind', '')
        self.checkequal(0, 'abcdefghiabc', 'rfind', 'abcd')
        self.checkequal(-1, 'abcdefghiabc', 'rfind', 'abcz')

207 208 209 210
        self.checkequal(3, 'abc', 'rfind', '', 0)
        self.checkequal(3, 'abc', 'rfind', '', 3)
        self.checkequal(-1, 'abc', 'rfind', '', 4)

211 212 213 214 215 216 217
        # to check the ability to pass None as defaults
        self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a', 4)
        self.checkequal(-1, 'rrarrrrrrrrra', 'rfind', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'rfind', 'a', None, 6)

218 219 220
        self.checkraises(TypeError, 'hello', 'rfind')
        self.checkraises(TypeError, 'hello', 'rfind', 42)

221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
        # For a variety of combinations,
        #    verify that str.rfind() matches __contains__
        #    and that the found substring is really at that location
        charset = ['', 'a', 'b', 'c']
        digits = 5
        base = len(charset)
        teststrings = set()
        for i in range(base ** digits):
            entry = []
            for j in range(digits):
                i, m = divmod(i, base)
                entry.append(charset[m])
            teststrings.add(''.join(entry))
        teststrings = [self.fixtype(ts) for ts in teststrings]
        for i in teststrings:
            for j in teststrings:
                loc = i.rfind(j)
                r1 = (loc != -1)
                r2 = j in i
240
                self.assertEqual(r1, r2)
241 242 243
                if loc != -1:
                    self.assertEqual(i[loc:loc+len(j)], j)

244 245 246
        # issue 7458
        self.checkequal(-1, 'ab', 'rfind', 'xxx', sys.maxsize + 1, 0)

247 248 249 250 251 252 253 254 255 256 257
    def test_index(self):
        self.checkequal(0, 'abcdefghiabc', 'index', '')
        self.checkequal(3, 'abcdefghiabc', 'index', 'def')
        self.checkequal(0, 'abcdefghiabc', 'index', 'abc')
        self.checkequal(9, 'abcdefghiabc', 'index', 'abc', 1)

        self.checkraises(ValueError, 'abcdefghiabc', 'index', 'hib')
        self.checkraises(ValueError, 'abcdefghiab', 'index', 'abc', 1)
        self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', 8)
        self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', -1)

258 259 260 261 262 263 264
        # to check the ability to pass None as defaults
        self.checkequal( 2, 'rrarrrrrrrrra', 'index', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'index', 'a', 4)
        self.checkraises(ValueError, 'rrarrrrrrrrra', 'index', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'index', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'index', 'a', None, 6)

265 266 267 268 269 270 271 272 273 274 275 276 277 278 279
        self.checkraises(TypeError, 'hello', 'index')
        self.checkraises(TypeError, 'hello', 'index', 42)

    def test_rindex(self):
        self.checkequal(12, 'abcdefghiabc', 'rindex', '')
        self.checkequal(3,  'abcdefghiabc', 'rindex', 'def')
        self.checkequal(9,  'abcdefghiabc', 'rindex', 'abc')
        self.checkequal(0,  'abcdefghiabc', 'rindex', 'abc', 0, -1)

        self.checkraises(ValueError, 'abcdefghiabc', 'rindex', 'hib')
        self.checkraises(ValueError, 'defghiabc', 'rindex', 'def', 1)
        self.checkraises(ValueError, 'defghiabc', 'rindex', 'abc', 0, -1)
        self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, 8)
        self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, -1)

280 281 282 283 284 285 286
        # to check the ability to pass None as defaults
        self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a', 4)
        self.checkraises(ValueError, 'rrarrrrrrrrra', 'rindex', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'rindex', 'a', None, 6)

287 288 289
        self.checkraises(TypeError, 'hello', 'rindex')
        self.checkraises(TypeError, 'hello', 'rindex', 42)

290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
    def test_lower(self):
        self.checkequal('hello', 'HeLLo', 'lower')
        self.checkequal('hello', 'hello', 'lower')
        self.checkraises(TypeError, 'hello', 'lower', 42)

    def test_upper(self):
        self.checkequal('HELLO', 'HeLLo', 'upper')
        self.checkequal('HELLO', 'HELLO', 'upper')
        self.checkraises(TypeError, 'hello', 'upper', 42)

    def test_expandtabs(self):
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\rab  def\ng   hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\r\nab  def\ng   hi', 'abc\r\nab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4)
        self.checkequal('  a\n b', ' \ta\n\tb', 'expandtabs', 1)

        self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)
        # This test is only valid when sizeof(int) == sizeof(void*) == 4.
312
        if sys.maxsize < (1 << 32) and struct.calcsize('P') == 4:
313
            self.checkraises(OverflowError,
314
                             '\ta\n\tb', 'expandtabs', sys.maxsize)
315

316
    def test_split(self):
317 318
        # by a char
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
319
        self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
320 321 322 323
        self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1)
        self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4)
324
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|',
325
                        sys.maxsize-2)
326 327 328
        self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
        self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
        self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
329 330
        self.checkequal(['', ' startcase'], '| startcase', 'split', '|')
        self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|')
331 332
        self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2)

333 334 335 336
        self.checkequal(['a']*20, ('a|'*20)[:-1], 'split', '|')
        self.checkequal(['a']*15 +['a|a|a|a|a'],
                                   ('a|'*20)[:-1], 'split', '|', 15)

337
        # by string
338
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
339 340 341 342
        self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1)
        self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4)
343
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//',
344
                        sys.maxsize-10)
345 346
        self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0)
        self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2)
347
        self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
        self.checkequal(['', ' begincase'], 'test begincase', 'split', 'test')
        self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
                        'split', 'test')
        self.checkequal(['a', 'bc'], 'abbbc', 'split', 'bb')
        self.checkequal(['', ''], 'aaa', 'split', 'aaa')
        self.checkequal(['aaa'], 'aaa', 'split', 'aaa', 0)
        self.checkequal(['ab', 'ab'], 'abbaab', 'split', 'ba')
        self.checkequal(['aaaa'], 'aaaa', 'split', 'aab')
        self.checkequal([''], '', 'split', 'aaa')
        self.checkequal(['aa'], 'aa', 'split', 'aaa')
        self.checkequal(['A', 'bobb'], 'Abbobbbobb', 'split', 'bbobb')
        self.checkequal(['A', 'B', ''], 'AbbobbBbbobb', 'split', 'bbobb')

        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH')
        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH', 19)
        self.checkequal(['a']*18 + ['aBLAHa'], ('aBLAH'*20)[:-4],
                        'split', 'BLAH', 18)
365

366
        # argument type
367 368
        self.checkraises(TypeError, 'hello', 'split', 42, 42, 42)

369 370 371 372
        # null case
        self.checkraises(ValueError, 'hello', 'split', '')
        self.checkraises(ValueError, 'hello', 'split', '', 0)

373
    def test_rsplit(self):
374 375 376 377 378 379
        # by a char
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
        self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1)
        self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4)
380
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|',
381
                        sys.maxsize-100)
382 383 384
        self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
        self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
        self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
385 386 387
        self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|')
        self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|')

388 389
        self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2)

390 391 392 393
        self.checkequal(['a']*20, ('a|'*20)[:-1], 'rsplit', '|')
        self.checkequal(['a|a|a|a|a']+['a']*15,
                        ('a|'*20)[:-1], 'rsplit', '|', 15)

394 395 396 397 398 399
        # by string
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//')
        self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1)
        self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4)
400
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//',
401
                        sys.maxsize-5)
402 403 404
        self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0)
        self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2)
        self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test')
405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421
        self.checkequal(['endcase ', ''], 'endcase test', 'rsplit', 'test')
        self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
                        'rsplit', 'test')
        self.checkequal(['ab', 'c'], 'abbbc', 'rsplit', 'bb')
        self.checkequal(['', ''], 'aaa', 'rsplit', 'aaa')
        self.checkequal(['aaa'], 'aaa', 'rsplit', 'aaa', 0)
        self.checkequal(['ab', 'ab'], 'abbaab', 'rsplit', 'ba')
        self.checkequal(['aaaa'], 'aaaa', 'rsplit', 'aab')
        self.checkequal([''], '', 'rsplit', 'aaa')
        self.checkequal(['aa'], 'aa', 'rsplit', 'aaa')
        self.checkequal(['bbob', 'A'], 'bbobbbobbA', 'rsplit', 'bbobb')
        self.checkequal(['', 'B', 'A'], 'bbobbBbbobbA', 'rsplit', 'bbobb')

        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH')
        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH', 19)
        self.checkequal(['aBLAHa'] + ['a']*18, ('aBLAH'*20)[:-4],
                        'rsplit', 'BLAH', 18)
422 423 424

        # argument type
        self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42)
425

426 427 428 429
        # null case
        self.checkraises(ValueError, 'hello', 'rsplit', '')
        self.checkraises(ValueError, 'hello', 'rsplit', '', 0)

430
    def test_replace(self):
431 432 433 434
        EQ = self.checkequal

        # Operations on the empty string
        EQ("", "", "replace", "", "")
435
        EQ("A", "", "replace", "", "A")
436 437 438
        EQ("", "", "replace", "A", "")
        EQ("", "", "replace", "A", "A")
        EQ("", "", "replace", "", "", 100)
439
        EQ("", "", "replace", "", "", sys.maxsize)
440 441 442 443 444 445 446 447

        # interleave (from=="", 'to' gets inserted everywhere)
        EQ("A", "A", "replace", "", "")
        EQ("*A*", "A", "replace", "", "*")
        EQ("*1A*1", "A", "replace", "", "*1")
        EQ("*-#A*-#", "A", "replace", "", "*-#")
        EQ("*-A*-A*-", "AA", "replace", "", "*-")
        EQ("*-A*-A*-", "AA", "replace", "", "*-", -1)
448
        EQ("*-A*-A*-", "AA", "replace", "", "*-", sys.maxsize)
449 450 451 452 453 454 455 456 457 458
        EQ("*-A*-A*-", "AA", "replace", "", "*-", 4)
        EQ("*-A*-A*-", "AA", "replace", "", "*-", 3)
        EQ("*-A*-A", "AA", "replace", "", "*-", 2)
        EQ("*-AA", "AA", "replace", "", "*-", 1)
        EQ("AA", "AA", "replace", "", "*-", 0)

        # single character deletion (from=="A", to=="")
        EQ("", "A", "replace", "A", "")
        EQ("", "AAA", "replace", "A", "")
        EQ("", "AAA", "replace", "A", "", -1)
459
        EQ("", "AAA", "replace", "A", "", sys.maxsize)
460 461 462 463 464 465 466 467
        EQ("", "AAA", "replace", "A", "", 4)
        EQ("", "AAA", "replace", "A", "", 3)
        EQ("A", "AAA", "replace", "A", "", 2)
        EQ("AA", "AAA", "replace", "A", "", 1)
        EQ("AAA", "AAA", "replace", "A", "", 0)
        EQ("", "AAAAAAAAAA", "replace", "A", "")
        EQ("BCD", "ABACADA", "replace", "A", "")
        EQ("BCD", "ABACADA", "replace", "A", "", -1)
468
        EQ("BCD", "ABACADA", "replace", "A", "", sys.maxsize)
469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490
        EQ("BCD", "ABACADA", "replace", "A", "", 5)
        EQ("BCD", "ABACADA", "replace", "A", "", 4)
        EQ("BCDA", "ABACADA", "replace", "A", "", 3)
        EQ("BCADA", "ABACADA", "replace", "A", "", 2)
        EQ("BACADA", "ABACADA", "replace", "A", "", 1)
        EQ("ABACADA", "ABACADA", "replace", "A", "", 0)
        EQ("BCD", "ABCAD", "replace", "A", "")
        EQ("BCD", "ABCADAA", "replace", "A", "")
        EQ("BCD", "BCD", "replace", "A", "")
        EQ("*************", "*************", "replace", "A", "")
        EQ("^A^", "^"+"A"*1000+"^", "replace", "A", "", 999)

        # substring deletion (from=="the", to=="")
        EQ("", "the", "replace", "the", "")
        EQ("ater", "theater", "replace", "the", "")
        EQ("", "thethe", "replace", "the", "")
        EQ("", "thethethethe", "replace", "the", "")
        EQ("aaaa", "theatheatheathea", "replace", "the", "")
        EQ("that", "that", "replace", "the", "")
        EQ("thaet", "thaet", "replace", "the", "")
        EQ("here and re", "here and there", "replace", "the", "")
        EQ("here and re and re", "here and there and there",
491
           "replace", "the", "", sys.maxsize)
492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", -1)
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", 3)
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", 2)
        EQ("here and re and there", "here and there and there",
           "replace", "the", "", 1)
        EQ("here and there and there", "here and there and there",
           "replace", "the", "", 0)
        EQ("here and re and re", "here and there and there", "replace", "the", "")

        EQ("abc", "abc", "replace", "the", "")
        EQ("abcdefg", "abcdefg", "replace", "the", "")

        # substring deletion (from=="bob", to=="")
        EQ("bob", "bbobob", "replace", "bob", "")
        EQ("bobXbob", "bbobobXbbobob", "replace", "bob", "")
        EQ("aaaaaaa", "aaaaaaabob", "replace", "bob", "")
        EQ("aaaaaaa", "aaaaaaa", "replace", "bob", "")

        # single character replace in place (len(from)==len(to)==1)
        EQ("Who goes there?", "Who goes there?", "replace", "o", "o")
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O")
516
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", sys.maxsize)
517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", -1)
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 3)
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 2)
        EQ("WhO goes there?", "Who goes there?", "replace", "o", "O", 1)
        EQ("Who goes there?", "Who goes there?", "replace", "o", "O", 0)

        EQ("Who goes there?", "Who goes there?", "replace", "a", "q")
        EQ("who goes there?", "Who goes there?", "replace", "W", "w")
        EQ("wwho goes there?ww", "WWho goes there?WW", "replace", "W", "w")
        EQ("Who goes there!", "Who goes there?", "replace", "?", "!")
        EQ("Who goes there!!", "Who goes there??", "replace", "?", "!")

        EQ("Who goes there?", "Who goes there?", "replace", ".", "!")

        # substring replace in place (len(from)==len(to) > 1)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**")
533
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", sys.maxsize)
534 535 536 537 538 539 540 541 542 543 544 545 546
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", -1)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 4)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 3)
        EQ("Th** ** a tissue", "This is a tissue", "replace", "is", "**", 2)
        EQ("Th** is a tissue", "This is a tissue", "replace", "is", "**", 1)
        EQ("This is a tissue", "This is a tissue", "replace", "is", "**", 0)
        EQ("cobob", "bobob", "replace", "bob", "cob")
        EQ("cobobXcobocob", "bobobXbobobob", "replace", "bob", "cob")
        EQ("bobob", "bobob", "replace", "bot", "bot")

        # replace single character (len(from)==1, len(to)>1)
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK")
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", -1)
547
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", sys.maxsize)
548 549 550 551 552 553 554 555 556 557 558
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", 2)
        EQ("ReyKKjavik", "Reykjavik", "replace", "k", "KK", 1)
        EQ("Reykjavik", "Reykjavik", "replace", "k", "KK", 0)
        EQ("A----B----C----", "A.B.C.", "replace", ".", "----")

        EQ("Reykjavik", "Reykjavik", "replace", "q", "KK")

        # replace substring (len(from)>1, len(to)!=len(from))
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham")
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
559
           "replace", "spam", "ham", sys.maxsize)
560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", -1)
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 4)
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 3)
        EQ("ham, ham, eggs and spam", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 2)
        EQ("ham, spam, eggs and spam", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 1)
        EQ("spam, spam, eggs and spam", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 0)

        EQ("bobob", "bobobob", "replace", "bobob", "bob")
        EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob")
        EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby")

577 578
        # XXX Commented out. Is there any reason to support buffer objects
        # as arguments for str.replace()?  GvR
579 580
##         ba = bytearray('a')
##         bb = bytearray('b')
581 582
##         EQ("bbc", "abc", "replace", ba, bb)
##         EQ("aac", "abc", "replace", bb, ba)
583

584
        #
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611
        self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
        self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '')
        self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2)
        self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 3)
        self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 4)
        self.checkequal('one!two!three!', 'one!two!three!', 'replace', '!', '@', 0)
        self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@')
        self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@')
        self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@', 2)
        self.checkequal('-a-b-c-', 'abc', 'replace', '', '-')
        self.checkequal('-a-b-c', 'abc', 'replace', '', '-', 3)
        self.checkequal('abc', 'abc', 'replace', '', '-', 0)
        self.checkequal('', '', 'replace', '', '')
        self.checkequal('abc', 'abc', 'replace', 'ab', '--', 0)
        self.checkequal('abc', 'abc', 'replace', 'xy', '--')
        # Next three for SF bug 422088: [OSF1 alpha] string.replace(); died with
        # MemoryError due to empty result (platform malloc issue when requesting
        # 0 bytes).
        self.checkequal('', '123', 'replace', '123', '')
        self.checkequal('', '123123', 'replace', '123', '')
        self.checkequal('x', '123x123', 'replace', '123', '')

        self.checkraises(TypeError, 'hello', 'replace')
        self.checkraises(TypeError, 'hello', 'replace', 42)
        self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
        self.checkraises(TypeError, 'hello', 'replace', 'h', 42)

612 613
    def test_replace_overflow(self):
        # Check for overflow checking on 32 bit machines
614
        if sys.maxsize != 2147483647 or struct.calcsize("P") > 4:
615 616 617 618 619 620
            return
        A2_16 = "A" * (2**16)
        self.checkraises(OverflowError, A2_16, "replace", "", A2_16)
        self.checkraises(OverflowError, A2_16, "replace", "A", A2_16)
        self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16)

621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677


class CommonTest(BaseTest):
    # This testcase contains test that can be used in all
    # stringlike classes. Currently this is str, unicode
    # UserString and the string module.

    def test_hash(self):
        # SF bug 1054139:  += optimization was not invalidating cached hash value
        a = self.type2test('DNSSEC')
        b = self.type2test('')
        for c in a:
            b += c
            hash(b)
        self.assertEqual(hash(a), hash(b))

    def test_capitalize(self):
        self.checkequal(' hello ', ' hello ', 'capitalize')
        self.checkequal('Hello ', 'Hello ','capitalize')
        self.checkequal('Hello ', 'hello ','capitalize')
        self.checkequal('Aaaa', 'aaaa', 'capitalize')
        self.checkequal('Aaaa', 'AaAa', 'capitalize')

        self.checkraises(TypeError, 'hello', 'capitalize', 42)

    def test_lower(self):
        self.checkequal('hello', 'HeLLo', 'lower')
        self.checkequal('hello', 'hello', 'lower')
        self.checkraises(TypeError, 'hello', 'lower', 42)

    def test_upper(self):
        self.checkequal('HELLO', 'HeLLo', 'upper')
        self.checkequal('HELLO', 'HELLO', 'upper')
        self.checkraises(TypeError, 'hello', 'upper', 42)

    def test_expandtabs(self):
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\rab  def\ng   hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\r\nab  def\ng   hi', 'abc\r\nab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4)

        self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)

    def test_additional_split(self):
        self.checkequal(['this', 'is', 'the', 'split', 'function'],
            'this is the split function', 'split')

        # by whitespace
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
        self.checkequal(['a', 'b c d'], 'a b c d', 'split', None, 1)
        self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None,
678
                        sys.maxsize-1)
679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695
        self.checkequal(['a b c d'], 'a b c d', 'split', None, 0)
        self.checkequal(['a b c d'], '  a b c d', 'split', None, 0)
        self.checkequal(['a', 'b', 'c  d'], 'a  b  c  d', 'split', None, 2)

        self.checkequal([], '         ', 'split')
        self.checkequal(['a'], '  a    ', 'split')
        self.checkequal(['a', 'b'], '  a    b   ', 'split')
        self.checkequal(['a', 'b   '], '  a    b   ', 'split', None, 1)
        self.checkequal(['a', 'b   c   '], '  a    b   c   ', 'split', None, 1)
        self.checkequal(['a', 'b', 'c   '], '  a    b   c   ', 'split', None, 2)
        self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split')
        aaa = ' a '*20
        self.checkequal(['a']*20, aaa, 'split')
        self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1)
        self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19)

        # mixed use of str and unicode
696
        self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', ' ', 2)
697 698 699 700 701 702 703 704 705 706 707 708

    def test_additional_rsplit(self):
        self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
                         'this is the rsplit function', 'rsplit')

        # by whitespace
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit')
        self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1)
        self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None,
709
                        sys.maxsize-20)
710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
        self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0)
        self.checkequal(['a b c d'], 'a b c d  ', 'rsplit', None, 0)
        self.checkequal(['a  b', 'c', 'd'], 'a  b  c  d', 'rsplit', None, 2)

        self.checkequal([], '         ', 'rsplit')
        self.checkequal(['a'], '  a    ', 'rsplit')
        self.checkequal(['a', 'b'], '  a    b   ', 'rsplit')
        self.checkequal(['  a', 'b'], '  a    b   ', 'rsplit', None, 1)
        self.checkequal(['  a    b','c'], '  a    b   c   ', 'rsplit',
                        None, 1)
        self.checkequal(['  a', 'b', 'c'], '  a    b   c   ', 'rsplit',
                        None, 2)
        self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88)
        aaa = ' a '*20
        self.checkequal(['a']*20, aaa, 'rsplit')
        self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1)
        self.checkequal([' a  a'] + ['a']*18, aaa, 'rsplit', None, 18)

        # mixed use of str and unicode
729
        self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', ' ', 2)
730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781

    def test_strip(self):
        self.checkequal('hello', '   hello   ', 'strip')
        self.checkequal('hello   ', '   hello   ', 'lstrip')
        self.checkequal('   hello', '   hello   ', 'rstrip')
        self.checkequal('hello', 'hello', 'strip')

        # strip/lstrip/rstrip with None arg
        self.checkequal('hello', '   hello   ', 'strip', None)
        self.checkequal('hello   ', '   hello   ', 'lstrip', None)
        self.checkequal('   hello', '   hello   ', 'rstrip', None)
        self.checkequal('hello', 'hello', 'strip', None)

        # strip/lstrip/rstrip with str arg
        self.checkequal('hello', 'xyzzyhelloxyzzy', 'strip', 'xyz')
        self.checkequal('helloxyzzy', 'xyzzyhelloxyzzy', 'lstrip', 'xyz')
        self.checkequal('xyzzyhello', 'xyzzyhelloxyzzy', 'rstrip', 'xyz')
        self.checkequal('hello', 'hello', 'strip', 'xyz')

        self.checkraises(TypeError, 'hello', 'strip', 42, 42)
        self.checkraises(TypeError, 'hello', 'lstrip', 42, 42)
        self.checkraises(TypeError, 'hello', 'rstrip', 42, 42)

    def test_ljust(self):
        self.checkequal('abc       ', 'abc', 'ljust', 10)
        self.checkequal('abc   ', 'abc', 'ljust', 6)
        self.checkequal('abc', 'abc', 'ljust', 3)
        self.checkequal('abc', 'abc', 'ljust', 2)
        self.checkequal('abc*******', 'abc', 'ljust', 10, '*')
        self.checkraises(TypeError, 'abc', 'ljust')

    def test_rjust(self):
        self.checkequal('       abc', 'abc', 'rjust', 10)
        self.checkequal('   abc', 'abc', 'rjust', 6)
        self.checkequal('abc', 'abc', 'rjust', 3)
        self.checkequal('abc', 'abc', 'rjust', 2)
        self.checkequal('*******abc', 'abc', 'rjust', 10, '*')
        self.checkraises(TypeError, 'abc', 'rjust')

    def test_center(self):
        self.checkequal('   abc    ', 'abc', 'center', 10)
        self.checkequal(' abc  ', 'abc', 'center', 6)
        self.checkequal('abc', 'abc', 'center', 3)
        self.checkequal('abc', 'abc', 'center', 2)
        self.checkequal('***abc****', 'abc', 'center', 10, '*')
        self.checkraises(TypeError, 'abc', 'center')

    def test_swapcase(self):
        self.checkequal('hEllO CoMPuTErS', 'HeLLo cOmpUteRs', 'swapcase')

        self.checkraises(TypeError, 'hello', 'swapcase', 42)

782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927
    def test_zfill(self):
        self.checkequal('123', '123', 'zfill', 2)
        self.checkequal('123', '123', 'zfill', 3)
        self.checkequal('0123', '123', 'zfill', 4)
        self.checkequal('+123', '+123', 'zfill', 3)
        self.checkequal('+123', '+123', 'zfill', 4)
        self.checkequal('+0123', '+123', 'zfill', 5)
        self.checkequal('-123', '-123', 'zfill', 3)
        self.checkequal('-123', '-123', 'zfill', 4)
        self.checkequal('-0123', '-123', 'zfill', 5)
        self.checkequal('000', '', 'zfill', 3)
        self.checkequal('34', '34', 'zfill', 1)
        self.checkequal('0034', '34', 'zfill', 4)

        self.checkraises(TypeError, '123', 'zfill')

class MixinStrUnicodeUserStringTest:
    # additional tests that only work for
    # stringlike objects, i.e. str, unicode, UserString
    # (but not the string module)

    def test_islower(self):
        self.checkequal(False, '', 'islower')
        self.checkequal(True, 'a', 'islower')
        self.checkequal(False, 'A', 'islower')
        self.checkequal(False, '\n', 'islower')
        self.checkequal(True, 'abc', 'islower')
        self.checkequal(False, 'aBc', 'islower')
        self.checkequal(True, 'abc\n', 'islower')
        self.checkraises(TypeError, 'abc', 'islower', 42)

    def test_isupper(self):
        self.checkequal(False, '', 'isupper')
        self.checkequal(False, 'a', 'isupper')
        self.checkequal(True, 'A', 'isupper')
        self.checkequal(False, '\n', 'isupper')
        self.checkequal(True, 'ABC', 'isupper')
        self.checkequal(False, 'AbC', 'isupper')
        self.checkequal(True, 'ABC\n', 'isupper')
        self.checkraises(TypeError, 'abc', 'isupper', 42)

    def test_istitle(self):
        self.checkequal(False, '', 'istitle')
        self.checkequal(False, 'a', 'istitle')
        self.checkequal(True, 'A', 'istitle')
        self.checkequal(False, '\n', 'istitle')
        self.checkequal(True, 'A Titlecased Line', 'istitle')
        self.checkequal(True, 'A\nTitlecased Line', 'istitle')
        self.checkequal(True, 'A Titlecased, Line', 'istitle')
        self.checkequal(False, 'Not a capitalized String', 'istitle')
        self.checkequal(False, 'Not\ta Titlecase String', 'istitle')
        self.checkequal(False, 'Not--a Titlecase String', 'istitle')
        self.checkequal(False, 'NOT', 'istitle')
        self.checkraises(TypeError, 'abc', 'istitle', 42)

    def test_isspace(self):
        self.checkequal(False, '', 'isspace')
        self.checkequal(False, 'a', 'isspace')
        self.checkequal(True, ' ', 'isspace')
        self.checkequal(True, '\t', 'isspace')
        self.checkequal(True, '\r', 'isspace')
        self.checkequal(True, '\n', 'isspace')
        self.checkequal(True, ' \t\r\n', 'isspace')
        self.checkequal(False, ' \t\r\na', 'isspace')
        self.checkraises(TypeError, 'abc', 'isspace', 42)

    def test_isalpha(self):
        self.checkequal(False, '', 'isalpha')
        self.checkequal(True, 'a', 'isalpha')
        self.checkequal(True, 'A', 'isalpha')
        self.checkequal(False, '\n', 'isalpha')
        self.checkequal(True, 'abc', 'isalpha')
        self.checkequal(False, 'aBc123', 'isalpha')
        self.checkequal(False, 'abc\n', 'isalpha')
        self.checkraises(TypeError, 'abc', 'isalpha', 42)

    def test_isalnum(self):
        self.checkequal(False, '', 'isalnum')
        self.checkequal(True, 'a', 'isalnum')
        self.checkequal(True, 'A', 'isalnum')
        self.checkequal(False, '\n', 'isalnum')
        self.checkequal(True, '123abc456', 'isalnum')
        self.checkequal(True, 'a1b3c', 'isalnum')
        self.checkequal(False, 'aBc000 ', 'isalnum')
        self.checkequal(False, 'abc\n', 'isalnum')
        self.checkraises(TypeError, 'abc', 'isalnum', 42)

    def test_isdigit(self):
        self.checkequal(False, '', 'isdigit')
        self.checkequal(False, 'a', 'isdigit')
        self.checkequal(True, '0', 'isdigit')
        self.checkequal(True, '0123456789', 'isdigit')
        self.checkequal(False, '0123456789a', 'isdigit')

        self.checkraises(TypeError, 'abc', 'isdigit', 42)

    def test_title(self):
        self.checkequal(' Hello ', ' hello ', 'title')
        self.checkequal('Hello ', 'hello ', 'title')
        self.checkequal('Hello ', 'Hello ', 'title')
        self.checkequal('Format This As Title String', "fOrMaT thIs aS titLe String", 'title')
        self.checkequal('Format,This-As*Title;String', "fOrMaT,thIs-aS*titLe;String", 'title', )
        self.checkequal('Getint', "getInt", 'title')
        self.checkraises(TypeError, 'hello', 'title', 42)

    def test_splitlines(self):
        self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\rghi", 'splitlines')
        self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\r\nghi", 'splitlines')
        self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi", 'splitlines')
        self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi\n", 'splitlines')
        self.checkequal(['abc', 'def', 'ghi', ''], "abc\ndef\r\nghi\n\r", 'splitlines')
        self.checkequal(['', 'abc', 'def', 'ghi', ''], "\nabc\ndef\r\nghi\n\r", 'splitlines')
        self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'], "\nabc\ndef\r\nghi\n\r", 'splitlines', 1)

        self.checkraises(TypeError, 'abc', 'splitlines', 42, 42)

    def test_startswith(self):
        self.checkequal(True, 'hello', 'startswith', 'he')
        self.checkequal(True, 'hello', 'startswith', 'hello')
        self.checkequal(False, 'hello', 'startswith', 'hello world')
        self.checkequal(True, 'hello', 'startswith', '')
        self.checkequal(False, 'hello', 'startswith', 'ello')
        self.checkequal(True, 'hello', 'startswith', 'ello', 1)
        self.checkequal(True, 'hello', 'startswith', 'o', 4)
        self.checkequal(False, 'hello', 'startswith', 'o', 5)
        self.checkequal(True, 'hello', 'startswith', '', 5)
        self.checkequal(False, 'hello', 'startswith', 'lo', 6)
        self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3)
        self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3, 7)
        self.checkequal(False, 'helloworld', 'startswith', 'lowo', 3, 6)

        # test negative indices
        self.checkequal(True, 'hello', 'startswith', 'he', 0, -1)
        self.checkequal(True, 'hello', 'startswith', 'he', -53, -1)
        self.checkequal(False, 'hello', 'startswith', 'hello', 0, -1)
        self.checkequal(False, 'hello', 'startswith', 'hello world', -1, -10)
        self.checkequal(False, 'hello', 'startswith', 'ello', -5)
        self.checkequal(True, 'hello', 'startswith', 'ello', -4)
        self.checkequal(False, 'hello', 'startswith', 'o', -2)
        self.checkequal(True, 'hello', 'startswith', 'o', -1)
        self.checkequal(True, 'hello', 'startswith', '', -3, -3)
        self.checkequal(False, 'hello', 'startswith', 'lo', -9)

        self.checkraises(TypeError, 'hello', 'startswith')
        self.checkraises(TypeError, 'hello', 'startswith', 42)

928 929 930 931 932 933 934 935 936 937 938 939 940 941 942
        # test tuple arguments
        self.checkequal(True, 'hello', 'startswith', ('he', 'ha'))
        self.checkequal(False, 'hello', 'startswith', ('lo', 'llo'))
        self.checkequal(True, 'hello', 'startswith', ('hellox', 'hello'))
        self.checkequal(False, 'hello', 'startswith', ())
        self.checkequal(True, 'helloworld', 'startswith', ('hellowo',
                                                           'rld', 'lowo'), 3)
        self.checkequal(False, 'helloworld', 'startswith', ('hellowo', 'ello',
                                                            'rld'), 3)
        self.checkequal(True, 'hello', 'startswith', ('lo', 'he'), 0, -1)
        self.checkequal(False, 'hello', 'startswith', ('he', 'hel'), 0, 1)
        self.checkequal(True, 'hello', 'startswith', ('he', 'hel'), 0, 2)

        self.checkraises(TypeError, 'hello', 'startswith', (42,))

943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976
    def test_endswith(self):
        self.checkequal(True, 'hello', 'endswith', 'lo')
        self.checkequal(False, 'hello', 'endswith', 'he')
        self.checkequal(True, 'hello', 'endswith', '')
        self.checkequal(False, 'hello', 'endswith', 'hello world')
        self.checkequal(False, 'helloworld', 'endswith', 'worl')
        self.checkequal(True, 'helloworld', 'endswith', 'worl', 3, 9)
        self.checkequal(True, 'helloworld', 'endswith', 'world', 3, 12)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', 1, 7)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', 2, 7)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', 3, 7)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', 4, 7)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, 8)
        self.checkequal(False, 'ab', 'endswith', 'ab', 0, 1)
        self.checkequal(False, 'ab', 'endswith', 'ab', 0, 0)

        # test negative indices
        self.checkequal(True, 'hello', 'endswith', 'lo', -2)
        self.checkequal(False, 'hello', 'endswith', 'he', -2)
        self.checkequal(True, 'hello', 'endswith', '', -3, -3)
        self.checkequal(False, 'hello', 'endswith', 'hello world', -10, -2)
        self.checkequal(False, 'helloworld', 'endswith', 'worl', -6)
        self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, -1)
        self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, 9)
        self.checkequal(True, 'helloworld', 'endswith', 'world', -7, 12)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', -99, -3)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', -8, -3)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', -7, -3)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, -4)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', -8, -2)

        self.checkraises(TypeError, 'hello', 'endswith')
        self.checkraises(TypeError, 'hello', 'endswith', 42)

977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
        # test tuple arguments
        self.checkequal(False, 'hello', 'endswith', ('he', 'ha'))
        self.checkequal(True, 'hello', 'endswith', ('lo', 'llo'))
        self.checkequal(True, 'hello', 'endswith', ('hellox', 'hello'))
        self.checkequal(False, 'hello', 'endswith', ())
        self.checkequal(True, 'helloworld', 'endswith', ('hellowo',
                                                           'rld', 'lowo'), 3)
        self.checkequal(False, 'helloworld', 'endswith', ('hellowo', 'ello',
                                                            'rld'), 3, -1)
        self.checkequal(True, 'hello', 'endswith', ('hell', 'ell'), 0, -1)
        self.checkequal(False, 'hello', 'endswith', ('he', 'hel'), 0, 1)
        self.checkequal(True, 'hello', 'endswith', ('he', 'hell'), 0, 4)

        self.checkraises(TypeError, 'hello', 'endswith', (42,))

992 993 994 995 996 997 998 999 1000 1001 1002 1003
    def test___contains__(self):
        self.checkequal(True, '', '__contains__', '')         # vereq('' in '', True)
        self.checkequal(True, 'abc', '__contains__', '')      # vereq('' in 'abc', True)
        self.checkequal(False, 'abc', '__contains__', '\0')   # vereq('\0' in 'abc', False)
        self.checkequal(True, '\0abc', '__contains__', '\0')  # vereq('\0' in '\0abc', True)
        self.checkequal(True, 'abc\0', '__contains__', '\0')  # vereq('\0' in 'abc\0', True)
        self.checkequal(True, '\0abc', '__contains__', 'a')   # vereq('a' in '\0abc', True)
        self.checkequal(True, 'asdf', '__contains__', 'asdf') # vereq('asdf' in 'asdf', True)
        self.checkequal(False, 'asd', '__contains__', 'asdf') # vereq('asdf' in 'asd', False)
        self.checkequal(False, '', '__contains__', 'asdf')    # vereq('asdf' in '', False)

    def test_subscript(self):
1004 1005 1006 1007 1008 1009 1010
        self.checkequal('a', 'abc', '__getitem__', 0)
        self.checkequal('c', 'abc', '__getitem__', -1)
        self.checkequal('a', 'abc', '__getitem__', 0)
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 3))
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 1000))
        self.checkequal('a', 'abc', '__getitem__', slice(0, 1))
        self.checkequal('', 'abc', '__getitem__', slice(0, 0))
1011 1012 1013 1014

        self.checkraises(TypeError, 'abc', '__getitem__', 'def')

    def test_slice(self):
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 1000))
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 3))
        self.checkequal('ab', 'abc', '__getitem__', slice(0, 2))
        self.checkequal('bc', 'abc', '__getitem__', slice(1, 3))
        self.checkequal('b', 'abc', '__getitem__', slice(1, 2))
        self.checkequal('', 'abc', '__getitem__', slice(2, 2))
        self.checkequal('', 'abc', '__getitem__', slice(1000, 1000))
        self.checkequal('', 'abc', '__getitem__', slice(2000, 1000))
        self.checkequal('', 'abc', '__getitem__', slice(2, 1))

        self.checkraises(TypeError, 'abc', '__getitem__', 'def')
1026

1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
    def test_extended_getslice(self):
        # Test extended slicing by comparing with list slicing.
        s = string.ascii_letters + string.digits
        indices = (0, None, 1, 3, 41, -1, -2, -37)
        for start in indices:
            for stop in indices:
                # Skip step 0 (invalid)
                for step in indices[1:]:
                    L = list(s)[start:stop:step]
                    self.checkequal("".join(L), s, '__getitem__',
                                    slice(start, stop, step))

1039 1040 1041 1042 1043 1044 1045
    def test_mul(self):
        self.checkequal('', 'abc', '__mul__', -1)
        self.checkequal('', 'abc', '__mul__', 0)
        self.checkequal('abc', 'abc', '__mul__', 1)
        self.checkequal('abcabcabc', 'abc', '__mul__', 3)
        self.checkraises(TypeError, 'abc', '__mul__')
        self.checkraises(TypeError, 'abc', '__mul__', '')
Martin v. Löwis's avatar
Martin v. Löwis committed
1046 1047 1048
        # XXX: on a 64-bit system, this doesn't raise an overflow error,
        # but either raises a MemoryError, or succeeds (if you have 54TiB)
        #self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000)
1049 1050 1051 1052 1053 1054 1055 1056

    def test_join(self):
        # join now works with any sequence type
        # moved here, because the argument order is
        # different in string.join (see the test in
        # test.test_string.StringTest.test_join)
        self.checkequal('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
        self.checkequal('abcd', '', 'join', ('a', 'b', 'c', 'd'))
1057 1058
        self.checkequal('bd', '', 'join', ('', 'b', '', 'd'))
        self.checkequal('ac', '', 'join', ('a', '', 'c', ''))
1059 1060 1061
        self.checkequal('w x y z', ' ', 'join', Sequence())
        self.checkequal('abc', 'a', 'join', ('abc',))
        self.checkequal('z', 'a', 'join', UserList(['z']))
1062
        self.checkequal('a.b.c', '.', 'join', ['a', 'b', 'c'])
1063
        self.assertRaises(TypeError, '.'.join, ['a', 'b', 3])
1064 1065 1066 1067 1068 1069
        for i in [5, 25, 125]:
            self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
                 ['a' * i] * i)
            self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
                 ('a' * i,) * i)

1070
        #self.checkequal(str(BadSeq1()), ' ', 'join', BadSeq1())
1071 1072 1073 1074
        self.checkequal('a b c', ' ', 'join', BadSeq2())

        self.checkraises(TypeError, ' ', 'join')
        self.checkraises(TypeError, ' ', 'join', 7)
1075
        self.checkraises(TypeError, ' ', 'join', [1, 2, bytes()])
Michael W. Hudson's avatar
Michael W. Hudson committed
1076 1077 1078 1079
        try:
            def f():
                yield 4 + ""
            self.fixtype(' ').join(f())
1080
        except TypeError as e:
Michael W. Hudson's avatar
Michael W. Hudson committed
1081 1082 1083 1084
            if '+' not in str(e):
                self.fail('join() ate exception message')
        else:
            self.fail('exception not raised')
1085 1086 1087 1088 1089 1090 1091 1092 1093

    def test_formatting(self):
        self.checkequal('+hello+', '+%s+', '__mod__', 'hello')
        self.checkequal('+10+', '+%d+', '__mod__', 10)
        self.checkequal('a', "%c", '__mod__', "a")
        self.checkequal('a', "%c", '__mod__', "a")
        self.checkequal('"', "%c", '__mod__', 34)
        self.checkequal('$', "%c", '__mod__', 36)
        self.checkequal('10', "%d", '__mod__', 10)
1094
        self.checkequal('\x7f', "%c", '__mod__', 0x7f)
1095 1096 1097 1098 1099

        for ordinal in (-100, 0x200000):
            # unicode raises ValueError, str raises OverflowError
            self.checkraises((ValueError, OverflowError), '%c', '__mod__', ordinal)

1100 1101
        longvalue = sys.maxsize + 10
        slongvalue = str(longvalue)
1102
        self.checkequal(' 42', '%3ld', '__mod__', 42)
1103 1104 1105
        self.checkequal('42', '%d', '__mod__', 42.0)
        self.checkequal(slongvalue, '%d', '__mod__', longvalue)
        self.checkcall('%d', '__mod__', float(longvalue))
1106
        self.checkequal('0042.00', '%07.2f', '__mod__', 42)
1107
        self.checkequal('0042.00', '%07.2F', '__mod__', 42)
1108 1109 1110 1111 1112 1113 1114

        self.checkraises(TypeError, 'abc', '__mod__')
        self.checkraises(TypeError, '%(foo)s', '__mod__', 42)
        self.checkraises(TypeError, '%s%s', '__mod__', (42,))
        self.checkraises(TypeError, '%c', '__mod__', (None,))
        self.checkraises(ValueError, '%(foo', '__mod__', {})
        self.checkraises(TypeError, '%(foo)s %(bar)s', '__mod__', ('foo', 42))
1115
        self.checkraises(TypeError, '%d', '__mod__', "42") # not numeric
1116
        self.checkraises(TypeError, '%d', '__mod__', (42+0j)) # no int conversion provided
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129

        # argument names with properly nested brackets are supported
        self.checkequal('bar', '%((foo))s', '__mod__', {'(foo)': 'bar'})

        # 100 is a magic number in PyUnicode_Format, this forces a resize
        self.checkequal(103*'a'+'x', '%sx', '__mod__', 103*'a')

        self.checkraises(TypeError, '%*s', '__mod__', ('foo', 'bar'))
        self.checkraises(TypeError, '%10.*f', '__mod__', ('foo', 42.))
        self.checkraises(ValueError, '%10', '__mod__', (42,))

    def test_floatformatting(self):
        # float formatting
1130
        for prec in range(100):
1131 1132
            format = '%%.%if' % prec
            value = 0.01
1133
            for x in range(60):
1134
                value = value * 3.141592655 / 3.0 * 10.0
1135
                self.checkcall(format, "__mod__", value)
1136

1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
    def test_inplace_rewrites(self):
        # Check that strings don't copy and modify cached single-character strings
        self.checkequal('a', 'A', 'lower')
        self.checkequal(True, 'A', 'isupper')
        self.checkequal('A', 'a', 'upper')
        self.checkequal(True, 'a', 'islower')

        self.checkequal('a', 'A', 'replace', 'A', 'a')
        self.checkequal(True, 'A', 'isupper')

        self.checkequal('A', 'a', 'capitalize')
        self.checkequal(True, 'a', 'islower')

        self.checkequal('A', 'a', 'swapcase')
        self.checkequal(True, 'a', 'islower')

        self.checkequal('A', 'a', 'title')
        self.checkequal(True, 'a', 'islower')

    def test_partition(self):

        self.checkequal(('this is the par', 'ti', 'tion method'),
            'this is the partition method', 'partition', 'ti')

        # from raymond's original specification
        S = 'http://www.python.org'
        self.checkequal(('http', '://', 'www.python.org'), S, 'partition', '://')
        self.checkequal(('http://www.python.org', '', ''), S, 'partition', '?')
        self.checkequal(('', 'http://', 'www.python.org'), S, 'partition', 'http://')
        self.checkequal(('http://www.python.', 'org', ''), S, 'partition', 'org')

        self.checkraises(ValueError, S, 'partition', '')
        self.checkraises(TypeError, S, 'partition', None)

    def test_rpartition(self):

        self.checkequal(('this is the rparti', 'ti', 'on method'),
            'this is the rpartition method', 'rpartition', 'ti')

        # from raymond's original specification
        S = 'http://www.python.org'
        self.checkequal(('http', '://', 'www.python.org'), S, 'rpartition', '://')
1179
        self.checkequal(('', '', 'http://www.python.org'), S, 'rpartition', '?')
1180 1181 1182 1183 1184 1185
        self.checkequal(('', 'http://', 'www.python.org'), S, 'rpartition', 'http://')
        self.checkequal(('http://www.python.', 'org', ''), S, 'rpartition', 'org')

        self.checkraises(ValueError, S, 'rpartition', '')
        self.checkraises(TypeError, S, 'rpartition', None)

1186 1187

class MixinStrUnicodeTest:
1188
    # Additional tests that only work with str and unicode.
1189 1190 1191

    def test_bug1001011(self):
        # Make sure join returns a NEW object for single item sequences
1192 1193 1194
        # involving a subclass.
        # Make sure that it is of the appropriate type.
        # Check the optimisation still occurs for standard objects.
1195 1196 1197 1198 1199 1200 1201
        t = self.type2test
        class subclass(t):
            pass
        s1 = subclass("abcd")
        s2 = t().join([s1])
        self.assert_(s1 is not s2)
        self.assert_(type(s2) is t)
1202 1203 1204 1205 1206 1207

        s1 = t("abcd")
        s2 = t().join([s1])
        self.assert_(s1 is s2)

        # Should also test mixed-type join.
1208
        if t is str:
1209 1210 1211 1212 1213 1214 1215 1216 1217
            s1 = subclass("abcd")
            s2 = "".join([s1])
            self.assert_(s1 is not s2)
            self.assert_(type(s2) is t)

            s1 = t("abcd")
            s2 = "".join([s1])
            self.assert_(s1 is s2)

1218 1219 1220 1221 1222
##         elif t is str8:
##             s1 = subclass("abcd")
##             s2 = "".join([s1])
##             self.assert_(s1 is not s2)
##             self.assert_(type(s2) is str) # promotes!
1223

1224 1225 1226 1227
##             s1 = t("abcd")
##             s2 = "".join([s1])
##             self.assert_(s1 is not s2)
##             self.assert_(type(s2) is str) # promotes!
1228 1229 1230

        else:
            self.fail("unexpected type for MixinStrUnicodeTest %r" % t)