1 | """
|
---|
2 | Common tests shared by test_str, test_unicode, test_userstring and test_string.
|
---|
3 | """
|
---|
4 |
|
---|
5 | import unittest, string, sys, struct
|
---|
6 | from test import test_support
|
---|
7 | from UserList import UserList
|
---|
8 | import _testcapi
|
---|
9 |
|
---|
10 | class Sequence:
|
---|
11 | def __init__(self, seq='wxyz'): self.seq = seq
|
---|
12 | def __len__(self): return len(self.seq)
|
---|
13 | def __getitem__(self, i): return self.seq[i]
|
---|
14 |
|
---|
15 | class BadSeq1(Sequence):
|
---|
16 | def __init__(self): self.seq = [7, 'hello', 123L]
|
---|
17 |
|
---|
18 | class BadSeq2(Sequence):
|
---|
19 | def __init__(self): self.seq = ['a', 'b', 'c']
|
---|
20 | def __len__(self): return 8
|
---|
21 |
|
---|
22 | class CommonTest(unittest.TestCase):
|
---|
23 | # This testcase contains test that can be used in all
|
---|
24 | # stringlike classes. Currently this is str, unicode
|
---|
25 | # UserString and the string module.
|
---|
26 |
|
---|
27 | # The type to be tested
|
---|
28 | # Change in subclasses to change the behaviour of fixtesttype()
|
---|
29 | type2test = None
|
---|
30 |
|
---|
31 | # All tests pass their arguments to the testing methods
|
---|
32 | # as str objects. fixtesttype() can be used to propagate
|
---|
33 | # these arguments to the appropriate type
|
---|
34 | def fixtype(self, obj):
|
---|
35 | if isinstance(obj, str):
|
---|
36 | return self.__class__.type2test(obj)
|
---|
37 | elif isinstance(obj, list):
|
---|
38 | return [self.fixtype(x) for x in obj]
|
---|
39 | elif isinstance(obj, tuple):
|
---|
40 | return tuple([self.fixtype(x) for x in obj])
|
---|
41 | elif isinstance(obj, dict):
|
---|
42 | return dict([
|
---|
43 | (self.fixtype(key), self.fixtype(value))
|
---|
44 | for (key, value) in obj.iteritems()
|
---|
45 | ])
|
---|
46 | else:
|
---|
47 | return obj
|
---|
48 |
|
---|
49 | # check that object.method(*args) returns result
|
---|
50 | def checkequal(self, result, object, methodname, *args):
|
---|
51 | result = self.fixtype(result)
|
---|
52 | object = self.fixtype(object)
|
---|
53 | args = self.fixtype(args)
|
---|
54 | realresult = getattr(object, methodname)(*args)
|
---|
55 | self.assertEqual(
|
---|
56 | result,
|
---|
57 | realresult
|
---|
58 | )
|
---|
59 | # if the original is returned make sure that
|
---|
60 | # this doesn't happen with subclasses
|
---|
61 | if object == realresult:
|
---|
62 | class subtype(self.__class__.type2test):
|
---|
63 | pass
|
---|
64 | object = subtype(object)
|
---|
65 | realresult = getattr(object, methodname)(*args)
|
---|
66 | self.assertTrue(object is not realresult)
|
---|
67 |
|
---|
68 | # check that object.method(*args) raises exc
|
---|
69 | def checkraises(self, exc, object, methodname, *args):
|
---|
70 | object = self.fixtype(object)
|
---|
71 | args = self.fixtype(args)
|
---|
72 | self.assertRaises(
|
---|
73 | exc,
|
---|
74 | getattr(object, methodname),
|
---|
75 | *args
|
---|
76 | )
|
---|
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, 1)
|
---|
353 | self.checkequal(['a', 'b', 'c '], ' a b c ', 'split', None, 2)
|
---|
354 | self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split')
|
---|
355 | aaa = ' a '*20
|
---|
356 | self.checkequal(['a']*20, aaa, 'split')
|
---|
357 | self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1)
|
---|
358 | self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19)
|
---|
359 |
|
---|
360 | # by a char
|
---|
361 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
|
---|
362 | self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
|
---|
363 | self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1)
|
---|
364 | self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
|
---|
365 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3)
|
---|
366 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4)
|
---|
367 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|',
|
---|
368 | sys.maxint-2)
|
---|
369 | self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
|
---|
370 | self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
|
---|
371 | self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
|
---|
372 | self.checkequal(['', ' startcase'], '| startcase', 'split', '|')
|
---|
373 | self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|')
|
---|
374 | self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2)
|
---|
375 |
|
---|
376 | self.checkequal(['a']*20, ('a|'*20)[:-1], 'split', '|')
|
---|
377 | self.checkequal(['a']*15 +['a|a|a|a|a'],
|
---|
378 | ('a|'*20)[:-1], 'split', '|', 15)
|
---|
379 |
|
---|
380 | # by string
|
---|
381 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
|
---|
382 | self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1)
|
---|
383 | self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2)
|
---|
384 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3)
|
---|
385 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4)
|
---|
386 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//',
|
---|
387 | sys.maxint-10)
|
---|
388 | self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0)
|
---|
389 | self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2)
|
---|
390 | self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
|
---|
391 | self.checkequal(['', ' begincase'], 'test begincase', 'split', 'test')
|
---|
392 | self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
|
---|
393 | 'split', 'test')
|
---|
394 | self.checkequal(['a', 'bc'], 'abbbc', 'split', 'bb')
|
---|
395 | self.checkequal(['', ''], 'aaa', 'split', 'aaa')
|
---|
396 | self.checkequal(['aaa'], 'aaa', 'split', 'aaa', 0)
|
---|
397 | self.checkequal(['ab', 'ab'], 'abbaab', 'split', 'ba')
|
---|
398 | self.checkequal(['aaaa'], 'aaaa', 'split', 'aab')
|
---|
399 | self.checkequal([''], '', 'split', 'aaa')
|
---|
400 | self.checkequal(['aa'], 'aa', 'split', 'aaa')
|
---|
401 | self.checkequal(['A', 'bobb'], 'Abbobbbobb', 'split', 'bbobb')
|
---|
402 | self.checkequal(['A', 'B', ''], 'AbbobbBbbobb', 'split', 'bbobb')
|
---|
403 |
|
---|
404 | self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH')
|
---|
405 | self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH', 19)
|
---|
406 | self.checkequal(['a']*18 + ['aBLAHa'], ('aBLAH'*20)[:-4],
|
---|
407 | 'split', 'BLAH', 18)
|
---|
408 |
|
---|
409 | # mixed use of str and unicode
|
---|
410 | self.checkequal([u'a', u'b', u'c d'], 'a b c d', 'split', u' ', 2)
|
---|
411 |
|
---|
412 | # argument type
|
---|
413 | self.checkraises(TypeError, 'hello', 'split', 42, 42, 42)
|
---|
414 |
|
---|
415 | # null case
|
---|
416 | self.checkraises(ValueError, 'hello', 'split', '')
|
---|
417 | self.checkraises(ValueError, 'hello', 'split', '', 0)
|
---|
418 |
|
---|
419 | def test_rsplit(self):
|
---|
420 | self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
|
---|
421 | 'this is the rsplit function', 'rsplit')
|
---|
422 |
|
---|
423 | # by whitespace
|
---|
424 | self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit')
|
---|
425 | self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1)
|
---|
426 | self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
|
---|
427 | self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3)
|
---|
428 | self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4)
|
---|
429 | self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None,
|
---|
430 | sys.maxint-20)
|
---|
431 | self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0)
|
---|
432 | self.checkequal(['a b c d'], 'a b c d ', 'rsplit', None, 0)
|
---|
433 | self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
|
---|
434 |
|
---|
435 | self.checkequal([], ' ', 'rsplit')
|
---|
436 | self.checkequal(['a'], ' a ', 'rsplit')
|
---|
437 | self.checkequal(['a', 'b'], ' a b ', 'rsplit')
|
---|
438 | self.checkequal([' a', 'b'], ' a b ', 'rsplit', None, 1)
|
---|
439 | self.checkequal([' a b','c'], ' a b c ', 'rsplit',
|
---|
440 | None, 1)
|
---|
441 | self.checkequal([' a', 'b', 'c'], ' a b c ', 'rsplit',
|
---|
442 | None, 2)
|
---|
443 | self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88)
|
---|
444 | aaa = ' a '*20
|
---|
445 | self.checkequal(['a']*20, aaa, 'rsplit')
|
---|
446 | self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1)
|
---|
447 | self.checkequal([' a a'] + ['a']*18, aaa, 'rsplit', None, 18)
|
---|
448 |
|
---|
449 |
|
---|
450 | # by a char
|
---|
451 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
|
---|
452 | self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1)
|
---|
453 | self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
|
---|
454 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3)
|
---|
455 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4)
|
---|
456 | self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|',
|
---|
457 | sys.maxint-100)
|
---|
458 | self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
|
---|
459 | self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
|
---|
460 | self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
|
---|
461 | self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|')
|
---|
462 | self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|')
|
---|
463 |
|
---|
464 | self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2)
|
---|
465 |
|
---|
466 | self.checkequal(['a']*20, ('a|'*20)[:-1], 'rsplit', '|')
|
---|
467 | self.checkequal(['a|a|a|a|a']+['a']*15,
|
---|
468 | ('a|'*20)[:-1], 'rsplit', '|', 15)
|
---|
469 |
|
---|
470 | # by string
|
---|
471 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//')
|
---|
472 | self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1)
|
---|
473 | self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2)
|
---|
474 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3)
|
---|
475 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4)
|
---|
476 | self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//',
|
---|
477 | sys.maxint-5)
|
---|
478 | self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0)
|
---|
479 | self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2)
|
---|
480 | self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test')
|
---|
481 | self.checkequal(['endcase ', ''], 'endcase test', 'rsplit', 'test')
|
---|
482 | self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
|
---|
483 | 'rsplit', 'test')
|
---|
484 | self.checkequal(['ab', 'c'], 'abbbc', 'rsplit', 'bb')
|
---|
485 | self.checkequal(['', ''], 'aaa', 'rsplit', 'aaa')
|
---|
486 | self.checkequal(['aaa'], 'aaa', 'rsplit', 'aaa', 0)
|
---|
487 | self.checkequal(['ab', 'ab'], 'abbaab', 'rsplit', 'ba')
|
---|
488 | self.checkequal(['aaaa'], 'aaaa', 'rsplit', 'aab')
|
---|
489 | self.checkequal([''], '', 'rsplit', 'aaa')
|
---|
490 | self.checkequal(['aa'], 'aa', 'rsplit', 'aaa')
|
---|
491 | self.checkequal(['bbob', 'A'], 'bbobbbobbA', 'rsplit', 'bbobb')
|
---|
492 | self.checkequal(['', 'B', 'A'], 'bbobbBbbobbA', 'rsplit', 'bbobb')
|
---|
493 |
|
---|
494 | self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH')
|
---|
495 | self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH', 19)
|
---|
496 | self.checkequal(['aBLAHa'] + ['a']*18, ('aBLAH'*20)[:-4],
|
---|
497 | 'rsplit', 'BLAH', 18)
|
---|
498 |
|
---|
499 | # mixed use of str and unicode
|
---|
500 | self.checkequal([u'a b', u'c', u'd'], 'a b c d', 'rsplit', u' ', 2)
|
---|
501 |
|
---|
502 | # argument type
|
---|
503 | self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42)
|
---|
504 |
|
---|
505 | # null case
|
---|
506 | self.checkraises(ValueError, 'hello', 'rsplit', '')
|
---|
507 | self.checkraises(ValueError, 'hello', 'rsplit', '', 0)
|
---|
508 |
|
---|
509 | def test_strip(self):
|
---|
510 | self.checkequal('hello', ' hello ', 'strip')
|
---|
511 | self.checkequal('hello ', ' hello ', 'lstrip')
|
---|
512 | self.checkequal(' hello', ' hello ', 'rstrip')
|
---|
513 | self.checkequal('hello', 'hello', 'strip')
|
---|
514 |
|
---|
515 | # strip/lstrip/rstrip with None arg
|
---|
516 | self.checkequal('hello', ' hello ', 'strip', None)
|
---|
517 | self.checkequal('hello ', ' hello ', 'lstrip', None)
|
---|
518 | self.checkequal(' hello', ' hello ', 'rstrip', None)
|
---|
519 | self.checkequal('hello', 'hello', 'strip', None)
|
---|
520 |
|
---|
521 | # strip/lstrip/rstrip with str arg
|
---|
522 | self.checkequal('hello', 'xyzzyhelloxyzzy', 'strip', 'xyz')
|
---|
523 | self.checkequal('helloxyzzy', 'xyzzyhelloxyzzy', 'lstrip', 'xyz')
|
---|
524 | self.checkequal('xyzzyhello', 'xyzzyhelloxyzzy', 'rstrip', 'xyz')
|
---|
525 | self.checkequal('hello', 'hello', 'strip', 'xyz')
|
---|
526 |
|
---|
527 | # strip/lstrip/rstrip with unicode arg
|
---|
528 | if test_support.have_unicode:
|
---|
529 | self.checkequal(unicode('hello', 'ascii'), 'xyzzyhelloxyzzy',
|
---|
530 | 'strip', unicode('xyz', 'ascii'))
|
---|
531 | self.checkequal(unicode('helloxyzzy', 'ascii'), 'xyzzyhelloxyzzy',
|
---|
532 | 'lstrip', unicode('xyz', 'ascii'))
|
---|
533 | self.checkequal(unicode('xyzzyhello', 'ascii'), 'xyzzyhelloxyzzy',
|
---|
534 | 'rstrip', unicode('xyz', 'ascii'))
|
---|
535 | # XXX
|
---|
536 | #self.checkequal(unicode('hello', 'ascii'), 'hello',
|
---|
537 | # 'strip', unicode('xyz', 'ascii'))
|
---|
538 |
|
---|
539 | self.checkraises(TypeError, 'hello', 'strip', 42, 42)
|
---|
540 | self.checkraises(TypeError, 'hello', 'lstrip', 42, 42)
|
---|
541 | self.checkraises(TypeError, 'hello', 'rstrip', 42, 42)
|
---|
542 |
|
---|
543 | def test_ljust(self):
|
---|
544 | self.checkequal('abc ', 'abc', 'ljust', 10)
|
---|
545 | self.checkequal('abc ', 'abc', 'ljust', 6)
|
---|
546 | self.checkequal('abc', 'abc', 'ljust', 3)
|
---|
547 | self.checkequal('abc', 'abc', 'ljust', 2)
|
---|
548 | self.checkequal('abc*******', 'abc', 'ljust', 10, '*')
|
---|
549 | self.checkraises(TypeError, 'abc', 'ljust')
|
---|
550 |
|
---|
551 | def test_rjust(self):
|
---|
552 | self.checkequal(' abc', 'abc', 'rjust', 10)
|
---|
553 | self.checkequal(' abc', 'abc', 'rjust', 6)
|
---|
554 | self.checkequal('abc', 'abc', 'rjust', 3)
|
---|
555 | self.checkequal('abc', 'abc', 'rjust', 2)
|
---|
556 | self.checkequal('*******abc', 'abc', 'rjust', 10, '*')
|
---|
557 | self.checkraises(TypeError, 'abc', 'rjust')
|
---|
558 |
|
---|
559 | def test_center(self):
|
---|
560 | self.checkequal(' abc ', 'abc', 'center', 10)
|
---|
561 | self.checkequal(' abc ', 'abc', 'center', 6)
|
---|
562 | self.checkequal('abc', 'abc', 'center', 3)
|
---|
563 | self.checkequal('abc', 'abc', 'center', 2)
|
---|
564 | self.checkequal('***abc****', 'abc', 'center', 10, '*')
|
---|
565 | self.checkraises(TypeError, 'abc', 'center')
|
---|
566 |
|
---|
567 | def test_swapcase(self):
|
---|
568 | self.checkequal('hEllO CoMPuTErS', 'HeLLo cOmpUteRs', 'swapcase')
|
---|
569 |
|
---|
570 | self.checkraises(TypeError, 'hello', 'swapcase', 42)
|
---|
571 |
|
---|
572 | def test_replace(self):
|
---|
573 | EQ = self.checkequal
|
---|
574 |
|
---|
575 | # Operations on the empty string
|
---|
576 | EQ("", "", "replace", "", "")
|
---|
577 | EQ("A", "", "replace", "", "A")
|
---|
578 | EQ("", "", "replace", "A", "")
|
---|
579 | EQ("", "", "replace", "A", "A")
|
---|
580 | EQ("", "", "replace", "", "", 100)
|
---|
581 | EQ("", "", "replace", "", "", sys.maxint)
|
---|
582 |
|
---|
583 | # interleave (from=="", 'to' gets inserted everywhere)
|
---|
584 | EQ("A", "A", "replace", "", "")
|
---|
585 | EQ("*A*", "A", "replace", "", "*")
|
---|
586 | EQ("*1A*1", "A", "replace", "", "*1")
|
---|
587 | EQ("*-#A*-#", "A", "replace", "", "*-#")
|
---|
588 | EQ("*-A*-A*-", "AA", "replace", "", "*-")
|
---|
589 | EQ("*-A*-A*-", "AA", "replace", "", "*-", -1)
|
---|
590 | EQ("*-A*-A*-", "AA", "replace", "", "*-", sys.maxint)
|
---|
591 | EQ("*-A*-A*-", "AA", "replace", "", "*-", 4)
|
---|
592 | EQ("*-A*-A*-", "AA", "replace", "", "*-", 3)
|
---|
593 | EQ("*-A*-A", "AA", "replace", "", "*-", 2)
|
---|
594 | EQ("*-AA", "AA", "replace", "", "*-", 1)
|
---|
595 | EQ("AA", "AA", "replace", "", "*-", 0)
|
---|
596 |
|
---|
597 | # single character deletion (from=="A", to=="")
|
---|
598 | EQ("", "A", "replace", "A", "")
|
---|
599 | EQ("", "AAA", "replace", "A", "")
|
---|
600 | EQ("", "AAA", "replace", "A", "", -1)
|
---|
601 | EQ("", "AAA", "replace", "A", "", sys.maxint)
|
---|
602 | EQ("", "AAA", "replace", "A", "", 4)
|
---|
603 | EQ("", "AAA", "replace", "A", "", 3)
|
---|
604 | EQ("A", "AAA", "replace", "A", "", 2)
|
---|
605 | EQ("AA", "AAA", "replace", "A", "", 1)
|
---|
606 | EQ("AAA", "AAA", "replace", "A", "", 0)
|
---|
607 | EQ("", "AAAAAAAAAA", "replace", "A", "")
|
---|
608 | EQ("BCD", "ABACADA", "replace", "A", "")
|
---|
609 | EQ("BCD", "ABACADA", "replace", "A", "", -1)
|
---|
610 | EQ("BCD", "ABACADA", "replace", "A", "", sys.maxint)
|
---|
611 | EQ("BCD", "ABACADA", "replace", "A", "", 5)
|
---|
612 | EQ("BCD", "ABACADA", "replace", "A", "", 4)
|
---|
613 | EQ("BCDA", "ABACADA", "replace", "A", "", 3)
|
---|
614 | EQ("BCADA", "ABACADA", "replace", "A", "", 2)
|
---|
615 | EQ("BACADA", "ABACADA", "replace", "A", "", 1)
|
---|
616 | EQ("ABACADA", "ABACADA", "replace", "A", "", 0)
|
---|
617 | EQ("BCD", "ABCAD", "replace", "A", "")
|
---|
618 | EQ("BCD", "ABCADAA", "replace", "A", "")
|
---|
619 | EQ("BCD", "BCD", "replace", "A", "")
|
---|
620 | EQ("*************", "*************", "replace", "A", "")
|
---|
621 | EQ("^A^", "^"+"A"*1000+"^", "replace", "A", "", 999)
|
---|
622 |
|
---|
623 | # substring deletion (from=="the", to=="")
|
---|
624 | EQ("", "the", "replace", "the", "")
|
---|
625 | EQ("ater", "theater", "replace", "the", "")
|
---|
626 | EQ("", "thethe", "replace", "the", "")
|
---|
627 | EQ("", "thethethethe", "replace", "the", "")
|
---|
628 | EQ("aaaa", "theatheatheathea", "replace", "the", "")
|
---|
629 | EQ("that", "that", "replace", "the", "")
|
---|
630 | EQ("thaet", "thaet", "replace", "the", "")
|
---|
631 | EQ("here and re", "here and there", "replace", "the", "")
|
---|
632 | EQ("here and re and re", "here and there and there",
|
---|
633 | "replace", "the", "", sys.maxint)
|
---|
634 | EQ("here and re and re", "here and there and there",
|
---|
635 | "replace", "the", "", -1)
|
---|
636 | EQ("here and re and re", "here and there and there",
|
---|
637 | "replace", "the", "", 3)
|
---|
638 | EQ("here and re and re", "here and there and there",
|
---|
639 | "replace", "the", "", 2)
|
---|
640 | EQ("here and re and there", "here and there and there",
|
---|
641 | "replace", "the", "", 1)
|
---|
642 | EQ("here and there and there", "here and there and there",
|
---|
643 | "replace", "the", "", 0)
|
---|
644 | EQ("here and re and re", "here and there and there", "replace", "the", "")
|
---|
645 |
|
---|
646 | EQ("abc", "abc", "replace", "the", "")
|
---|
647 | EQ("abcdefg", "abcdefg", "replace", "the", "")
|
---|
648 |
|
---|
649 | # substring deletion (from=="bob", to=="")
|
---|
650 | EQ("bob", "bbobob", "replace", "bob", "")
|
---|
651 | EQ("bobXbob", "bbobobXbbobob", "replace", "bob", "")
|
---|
652 | EQ("aaaaaaa", "aaaaaaabob", "replace", "bob", "")
|
---|
653 | EQ("aaaaaaa", "aaaaaaa", "replace", "bob", "")
|
---|
654 |
|
---|
655 | # single character replace in place (len(from)==len(to)==1)
|
---|
656 | EQ("Who goes there?", "Who goes there?", "replace", "o", "o")
|
---|
657 | EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O")
|
---|
658 | EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", sys.maxint)
|
---|
659 | EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", -1)
|
---|
660 | EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 3)
|
---|
661 | EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 2)
|
---|
662 | EQ("WhO goes there?", "Who goes there?", "replace", "o", "O", 1)
|
---|
663 | EQ("Who goes there?", "Who goes there?", "replace", "o", "O", 0)
|
---|
664 |
|
---|
665 | EQ("Who goes there?", "Who goes there?", "replace", "a", "q")
|
---|
666 | EQ("who goes there?", "Who goes there?", "replace", "W", "w")
|
---|
667 | EQ("wwho goes there?ww", "WWho goes there?WW", "replace", "W", "w")
|
---|
668 | EQ("Who goes there!", "Who goes there?", "replace", "?", "!")
|
---|
669 | EQ("Who goes there!!", "Who goes there??", "replace", "?", "!")
|
---|
670 |
|
---|
671 | EQ("Who goes there?", "Who goes there?", "replace", ".", "!")
|
---|
672 |
|
---|
673 | # substring replace in place (len(from)==len(to) > 1)
|
---|
674 | EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**")
|
---|
675 | EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", sys.maxint)
|
---|
676 | EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", -1)
|
---|
677 | EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 4)
|
---|
678 | EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 3)
|
---|
679 | EQ("Th** ** a tissue", "This is a tissue", "replace", "is", "**", 2)
|
---|
680 | EQ("Th** is a tissue", "This is a tissue", "replace", "is", "**", 1)
|
---|
681 | EQ("This is a tissue", "This is a tissue", "replace", "is", "**", 0)
|
---|
682 | EQ("cobob", "bobob", "replace", "bob", "cob")
|
---|
683 | EQ("cobobXcobocob", "bobobXbobobob", "replace", "bob", "cob")
|
---|
684 | EQ("bobob", "bobob", "replace", "bot", "bot")
|
---|
685 |
|
---|
686 | # replace single character (len(from)==1, len(to)>1)
|
---|
687 | EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK")
|
---|
688 | EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", -1)
|
---|
689 | EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", sys.maxint)
|
---|
690 | EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", 2)
|
---|
691 | EQ("ReyKKjavik", "Reykjavik", "replace", "k", "KK", 1)
|
---|
692 | EQ("Reykjavik", "Reykjavik", "replace", "k", "KK", 0)
|
---|
693 | EQ("A----B----C----", "A.B.C.", "replace", ".", "----")
|
---|
694 |
|
---|
695 | EQ("Reykjavik", "Reykjavik", "replace", "q", "KK")
|
---|
696 |
|
---|
697 | # replace substring (len(from)>1, len(to)!=len(from))
|
---|
698 | EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
|
---|
699 | "replace", "spam", "ham")
|
---|
700 | EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
|
---|
701 | "replace", "spam", "ham", sys.maxint)
|
---|
702 | EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
|
---|
703 | "replace", "spam", "ham", -1)
|
---|
704 | EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
|
---|
705 | "replace", "spam", "ham", 4)
|
---|
706 | EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
|
---|
707 | "replace", "spam", "ham", 3)
|
---|
708 | EQ("ham, ham, eggs and spam", "spam, spam, eggs and spam",
|
---|
709 | "replace", "spam", "ham", 2)
|
---|
710 | EQ("ham, spam, eggs and spam", "spam, spam, eggs and spam",
|
---|
711 | "replace", "spam", "ham", 1)
|
---|
712 | EQ("spam, spam, eggs and spam", "spam, spam, eggs and spam",
|
---|
713 | "replace", "spam", "ham", 0)
|
---|
714 |
|
---|
715 | EQ("bobob", "bobobob", "replace", "bobob", "bob")
|
---|
716 | EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob")
|
---|
717 | EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby")
|
---|
718 |
|
---|
719 | with test_support.check_py3k_warnings():
|
---|
720 | ba = buffer('a')
|
---|
721 | bb = buffer('b')
|
---|
722 | EQ("bbc", "abc", "replace", ba, bb)
|
---|
723 | EQ("aac", "abc", "replace", bb, ba)
|
---|
724 |
|
---|
725 | #
|
---|
726 | self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
|
---|
727 | self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '')
|
---|
728 | self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2)
|
---|
729 | self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 3)
|
---|
730 | self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 4)
|
---|
731 | self.checkequal('one!two!three!', 'one!two!three!', 'replace', '!', '@', 0)
|
---|
732 | self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@')
|
---|
733 | self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@')
|
---|
734 | self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@', 2)
|
---|
735 | self.checkequal('-a-b-c-', 'abc', 'replace', '', '-')
|
---|
736 | self.checkequal('-a-b-c', 'abc', 'replace', '', '-', 3)
|
---|
737 | self.checkequal('abc', 'abc', 'replace', '', '-', 0)
|
---|
738 | self.checkequal('', '', 'replace', '', '')
|
---|
739 | self.checkequal('abc', 'abc', 'replace', 'ab', '--', 0)
|
---|
740 | self.checkequal('abc', 'abc', 'replace', 'xy', '--')
|
---|
741 | # Next three for SF bug 422088: [OSF1 alpha] string.replace(); died with
|
---|
742 | # MemoryError due to empty result (platform malloc issue when requesting
|
---|
743 | # 0 bytes).
|
---|
744 | self.checkequal('', '123', 'replace', '123', '')
|
---|
745 | self.checkequal('', '123123', 'replace', '123', '')
|
---|
746 | self.checkequal('x', '123x123', 'replace', '123', '')
|
---|
747 |
|
---|
748 | self.checkraises(TypeError, 'hello', 'replace')
|
---|
749 | self.checkraises(TypeError, 'hello', 'replace', 42)
|
---|
750 | self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
|
---|
751 | self.checkraises(TypeError, 'hello', 'replace', 'h', 42)
|
---|
752 |
|
---|
753 | def test_replace_overflow(self):
|
---|
754 | # Check for overflow checking on 32 bit machines
|
---|
755 | if sys.maxint != 2147483647 or struct.calcsize("P") > 4:
|
---|
756 | return
|
---|
757 | A2_16 = "A" * (2**16)
|
---|
758 | self.checkraises(OverflowError, A2_16, "replace", "", A2_16)
|
---|
759 | self.checkraises(OverflowError, A2_16, "replace", "A", A2_16)
|
---|
760 | self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16)
|
---|
761 |
|
---|
762 | def test_zfill(self):
|
---|
763 | self.checkequal('123', '123', 'zfill', 2)
|
---|
764 | self.checkequal('123', '123', 'zfill', 3)
|
---|
765 | self.checkequal('0123', '123', 'zfill', 4)
|
---|
766 | self.checkequal('+123', '+123', 'zfill', 3)
|
---|
767 | self.checkequal('+123', '+123', 'zfill', 4)
|
---|
768 | self.checkequal('+0123', '+123', 'zfill', 5)
|
---|
769 | self.checkequal('-123', '-123', 'zfill', 3)
|
---|
770 | self.checkequal('-123', '-123', 'zfill', 4)
|
---|
771 | self.checkequal('-0123', '-123', 'zfill', 5)
|
---|
772 | self.checkequal('000', '', 'zfill', 3)
|
---|
773 | self.checkequal('34', '34', 'zfill', 1)
|
---|
774 | self.checkequal('0034', '34', 'zfill', 4)
|
---|
775 |
|
---|
776 | self.checkraises(TypeError, '123', 'zfill')
|
---|
777 |
|
---|
778 | # XXX alias for py3k forward compatibility
|
---|
779 | BaseTest = CommonTest
|
---|
780 |
|
---|
781 | class MixinStrUnicodeUserStringTest:
|
---|
782 | # additional tests that only work for
|
---|
783 | # stringlike objects, i.e. str, unicode, UserString
|
---|
784 | # (but not the string module)
|
---|
785 |
|
---|
786 | def test_islower(self):
|
---|
787 | self.checkequal(False, '', 'islower')
|
---|
788 | self.checkequal(True, 'a', 'islower')
|
---|
789 | self.checkequal(False, 'A', 'islower')
|
---|
790 | self.checkequal(False, '\n', 'islower')
|
---|
791 | self.checkequal(True, 'abc', 'islower')
|
---|
792 | self.checkequal(False, 'aBc', 'islower')
|
---|
793 | self.checkequal(True, 'abc\n', 'islower')
|
---|
794 | self.checkraises(TypeError, 'abc', 'islower', 42)
|
---|
795 |
|
---|
796 | def test_isupper(self):
|
---|
797 | self.checkequal(False, '', 'isupper')
|
---|
798 | self.checkequal(False, 'a', 'isupper')
|
---|
799 | self.checkequal(True, 'A', 'isupper')
|
---|
800 | self.checkequal(False, '\n', 'isupper')
|
---|
801 | self.checkequal(True, 'ABC', 'isupper')
|
---|
802 | self.checkequal(False, 'AbC', 'isupper')
|
---|
803 | self.checkequal(True, 'ABC\n', 'isupper')
|
---|
804 | self.checkraises(TypeError, 'abc', 'isupper', 42)
|
---|
805 |
|
---|
806 | def test_istitle(self):
|
---|
807 | self.checkequal(False, '', 'istitle')
|
---|
808 | self.checkequal(False, 'a', 'istitle')
|
---|
809 | self.checkequal(True, 'A', 'istitle')
|
---|
810 | self.checkequal(False, '\n', 'istitle')
|
---|
811 | self.checkequal(True, 'A Titlecased Line', 'istitle')
|
---|
812 | self.checkequal(True, 'A\nTitlecased Line', 'istitle')
|
---|
813 | self.checkequal(True, 'A Titlecased, Line', 'istitle')
|
---|
814 | self.checkequal(False, 'Not a capitalized String', 'istitle')
|
---|
815 | self.checkequal(False, 'Not\ta Titlecase String', 'istitle')
|
---|
816 | self.checkequal(False, 'Not--a Titlecase String', 'istitle')
|
---|
817 | self.checkequal(False, 'NOT', 'istitle')
|
---|
818 | self.checkraises(TypeError, 'abc', 'istitle', 42)
|
---|
819 |
|
---|
820 | def test_isspace(self):
|
---|
821 | self.checkequal(False, '', 'isspace')
|
---|
822 | self.checkequal(False, 'a', 'isspace')
|
---|
823 | self.checkequal(True, ' ', 'isspace')
|
---|
824 | self.checkequal(True, '\t', 'isspace')
|
---|
825 | self.checkequal(True, '\r', 'isspace')
|
---|
826 | self.checkequal(True, '\n', 'isspace')
|
---|
827 | self.checkequal(True, ' \t\r\n', 'isspace')
|
---|
828 | self.checkequal(False, ' \t\r\na', 'isspace')
|
---|
829 | self.checkraises(TypeError, 'abc', 'isspace', 42)
|
---|
830 |
|
---|
831 | def test_isalpha(self):
|
---|
832 | self.checkequal(False, '', 'isalpha')
|
---|
833 | self.checkequal(True, 'a', 'isalpha')
|
---|
834 | self.checkequal(True, 'A', 'isalpha')
|
---|
835 | self.checkequal(False, '\n', 'isalpha')
|
---|
836 | self.checkequal(True, 'abc', 'isalpha')
|
---|
837 | self.checkequal(False, 'aBc123', 'isalpha')
|
---|
838 | self.checkequal(False, 'abc\n', 'isalpha')
|
---|
839 | self.checkraises(TypeError, 'abc', 'isalpha', 42)
|
---|
840 |
|
---|
841 | def test_isalnum(self):
|
---|
842 | self.checkequal(False, '', 'isalnum')
|
---|
843 | self.checkequal(True, 'a', 'isalnum')
|
---|
844 | self.checkequal(True, 'A', 'isalnum')
|
---|
845 | self.checkequal(False, '\n', 'isalnum')
|
---|
846 | self.checkequal(True, '123abc456', 'isalnum')
|
---|
847 | self.checkequal(True, 'a1b3c', 'isalnum')
|
---|
848 | self.checkequal(False, 'aBc000 ', 'isalnum')
|
---|
849 | self.checkequal(False, 'abc\n', 'isalnum')
|
---|
850 | self.checkraises(TypeError, 'abc', 'isalnum', 42)
|
---|
851 |
|
---|
852 | def test_isdigit(self):
|
---|
853 | self.checkequal(False, '', 'isdigit')
|
---|
854 | self.checkequal(False, 'a', 'isdigit')
|
---|
855 | self.checkequal(True, '0', 'isdigit')
|
---|
856 | self.checkequal(True, '0123456789', 'isdigit')
|
---|
857 | self.checkequal(False, '0123456789a', 'isdigit')
|
---|
858 |
|
---|
859 | self.checkraises(TypeError, 'abc', 'isdigit', 42)
|
---|
860 |
|
---|
861 | def test_title(self):
|
---|
862 | self.checkequal(' Hello ', ' hello ', 'title')
|
---|
863 | self.checkequal('Hello ', 'hello ', 'title')
|
---|
864 | self.checkequal('Hello ', 'Hello ', 'title')
|
---|
865 | self.checkequal('Format This As Title String', "fOrMaT thIs aS titLe String", 'title')
|
---|
866 | self.checkequal('Format,This-As*Title;String', "fOrMaT,thIs-aS*titLe;String", 'title', )
|
---|
867 | self.checkequal('Getint', "getInt", 'title')
|
---|
868 | self.checkraises(TypeError, 'hello', 'title', 42)
|
---|
869 |
|
---|
870 | def test_splitlines(self):
|
---|
871 | self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\rghi", 'splitlines')
|
---|
872 | self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\r\nghi", 'splitlines')
|
---|
873 | self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi", 'splitlines')
|
---|
874 | self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi\n", 'splitlines')
|
---|
875 | self.checkequal(['abc', 'def', 'ghi', ''], "abc\ndef\r\nghi\n\r", 'splitlines')
|
---|
876 | self.checkequal(['', 'abc', 'def', 'ghi', ''], "\nabc\ndef\r\nghi\n\r", 'splitlines')
|
---|
877 | self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'], "\nabc\ndef\r\nghi\n\r", 'splitlines', 1)
|
---|
878 |
|
---|
879 | self.checkraises(TypeError, 'abc', 'splitlines', 42, 42)
|
---|
880 |
|
---|
881 | def test_startswith(self):
|
---|
882 | self.checkequal(True, 'hello', 'startswith', 'he')
|
---|
883 | self.checkequal(True, 'hello', 'startswith', 'hello')
|
---|
884 | self.checkequal(False, 'hello', 'startswith', 'hello world')
|
---|
885 | self.checkequal(True, 'hello', 'startswith', '')
|
---|
886 | self.checkequal(False, 'hello', 'startswith', 'ello')
|
---|
887 | self.checkequal(True, 'hello', 'startswith', 'ello', 1)
|
---|
888 | self.checkequal(True, 'hello', 'startswith', 'o', 4)
|
---|
889 | self.checkequal(False, 'hello', 'startswith', 'o', 5)
|
---|
890 | self.checkequal(True, 'hello', 'startswith', '', 5)
|
---|
891 | self.checkequal(False, 'hello', 'startswith', 'lo', 6)
|
---|
892 | self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3)
|
---|
893 | self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3, 7)
|
---|
894 | self.checkequal(False, 'helloworld', 'startswith', 'lowo', 3, 6)
|
---|
895 |
|
---|
896 | # test negative indices
|
---|
897 | self.checkequal(True, 'hello', 'startswith', 'he', 0, -1)
|
---|
898 | self.checkequal(True, 'hello', 'startswith', 'he', -53, -1)
|
---|
899 | self.checkequal(False, 'hello', 'startswith', 'hello', 0, -1)
|
---|
900 | self.checkequal(False, 'hello', 'startswith', 'hello world', -1, -10)
|
---|
901 | self.checkequal(False, 'hello', 'startswith', 'ello', -5)
|
---|
902 | self.checkequal(True, 'hello', 'startswith', 'ello', -4)
|
---|
903 | self.checkequal(False, 'hello', 'startswith', 'o', -2)
|
---|
904 | self.checkequal(True, 'hello', 'startswith', 'o', -1)
|
---|
905 | self.checkequal(True, 'hello', 'startswith', '', -3, -3)
|
---|
906 | self.checkequal(False, 'hello', 'startswith', 'lo', -9)
|
---|
907 |
|
---|
908 | self.checkraises(TypeError, 'hello', 'startswith')
|
---|
909 | self.checkraises(TypeError, 'hello', 'startswith', 42)
|
---|
910 |
|
---|
911 | # test tuple arguments
|
---|
912 | self.checkequal(True, 'hello', 'startswith', ('he', 'ha'))
|
---|
913 | self.checkequal(False, 'hello', 'startswith', ('lo', 'llo'))
|
---|
914 | self.checkequal(True, 'hello', 'startswith', ('hellox', 'hello'))
|
---|
915 | self.checkequal(False, 'hello', 'startswith', ())
|
---|
916 | self.checkequal(True, 'helloworld', 'startswith', ('hellowo',
|
---|
917 | 'rld', 'lowo'), 3)
|
---|
918 | self.checkequal(False, 'helloworld', 'startswith', ('hellowo', 'ello',
|
---|
919 | 'rld'), 3)
|
---|
920 | self.checkequal(True, 'hello', 'startswith', ('lo', 'he'), 0, -1)
|
---|
921 | self.checkequal(False, 'hello', 'startswith', ('he', 'hel'), 0, 1)
|
---|
922 | self.checkequal(True, 'hello', 'startswith', ('he', 'hel'), 0, 2)
|
---|
923 |
|
---|
924 | self.checkraises(TypeError, 'hello', 'startswith', (42,))
|
---|
925 |
|
---|
926 | def test_endswith(self):
|
---|
927 | self.checkequal(True, 'hello', 'endswith', 'lo')
|
---|
928 | self.checkequal(False, 'hello', 'endswith', 'he')
|
---|
929 | self.checkequal(True, 'hello', 'endswith', '')
|
---|
930 | self.checkequal(False, 'hello', 'endswith', 'hello world')
|
---|
931 | self.checkequal(False, 'helloworld', 'endswith', 'worl')
|
---|
932 | self.checkequal(True, 'helloworld', 'endswith', 'worl', 3, 9)
|
---|
933 | self.checkequal(True, 'helloworld', 'endswith', 'world', 3, 12)
|
---|
934 | self.checkequal(True, 'helloworld', 'endswith', 'lowo', 1, 7)
|
---|
935 | self.checkequal(True, 'helloworld', 'endswith', 'lowo', 2, 7)
|
---|
936 | self.checkequal(True, 'helloworld', 'endswith', 'lowo', 3, 7)
|
---|
937 | self.checkequal(False, 'helloworld', 'endswith', 'lowo', 4, 7)
|
---|
938 | self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, 8)
|
---|
939 | self.checkequal(False, 'ab', 'endswith', 'ab', 0, 1)
|
---|
940 | self.checkequal(False, 'ab', 'endswith', 'ab', 0, 0)
|
---|
941 |
|
---|
942 | # test negative indices
|
---|
943 | self.checkequal(True, 'hello', 'endswith', 'lo', -2)
|
---|
944 | self.checkequal(False, 'hello', 'endswith', 'he', -2)
|
---|
945 | self.checkequal(True, 'hello', 'endswith', '', -3, -3)
|
---|
946 | self.checkequal(False, 'hello', 'endswith', 'hello world', -10, -2)
|
---|
947 | self.checkequal(False, 'helloworld', 'endswith', 'worl', -6)
|
---|
948 | self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, -1)
|
---|
949 | self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, 9)
|
---|
950 | self.checkequal(True, 'helloworld', 'endswith', 'world', -7, 12)
|
---|
951 | self.checkequal(True, 'helloworld', 'endswith', 'lowo', -99, -3)
|
---|
952 | self.checkequal(True, 'helloworld', 'endswith', 'lowo', -8, -3)
|
---|
953 | self.checkequal(True, 'helloworld', 'endswith', 'lowo', -7, -3)
|
---|
954 | self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, -4)
|
---|
955 | self.checkequal(False, 'helloworld', 'endswith', 'lowo', -8, -2)
|
---|
956 |
|
---|
957 | self.checkraises(TypeError, 'hello', 'endswith')
|
---|
958 | self.checkraises(TypeError, 'hello', 'endswith', 42)
|
---|
959 |
|
---|
960 | # test tuple arguments
|
---|
961 | self.checkequal(False, 'hello', 'endswith', ('he', 'ha'))
|
---|
962 | self.checkequal(True, 'hello', 'endswith', ('lo', 'llo'))
|
---|
963 | self.checkequal(True, 'hello', 'endswith', ('hellox', 'hello'))
|
---|
964 | self.checkequal(False, 'hello', 'endswith', ())
|
---|
965 | self.checkequal(True, 'helloworld', 'endswith', ('hellowo',
|
---|
966 | 'rld', 'lowo'), 3)
|
---|
967 | self.checkequal(False, 'helloworld', 'endswith', ('hellowo', 'ello',
|
---|
968 | 'rld'), 3, -1)
|
---|
969 | self.checkequal(True, 'hello', 'endswith', ('hell', 'ell'), 0, -1)
|
---|
970 | self.checkequal(False, 'hello', 'endswith', ('he', 'hel'), 0, 1)
|
---|
971 | self.checkequal(True, 'hello', 'endswith', ('he', 'hell'), 0, 4)
|
---|
972 |
|
---|
973 | self.checkraises(TypeError, 'hello', 'endswith', (42,))
|
---|
974 |
|
---|
975 | def test___contains__(self):
|
---|
976 | self.checkequal(True, '', '__contains__', '')
|
---|
977 | self.checkequal(True, 'abc', '__contains__', '')
|
---|
978 | self.checkequal(False, 'abc', '__contains__', '\0')
|
---|
979 | self.checkequal(True, '\0abc', '__contains__', '\0')
|
---|
980 | self.checkequal(True, 'abc\0', '__contains__', '\0')
|
---|
981 | self.checkequal(True, '\0abc', '__contains__', 'a')
|
---|
982 | self.checkequal(True, 'asdf', '__contains__', 'asdf')
|
---|
983 | self.checkequal(False, 'asd', '__contains__', 'asdf')
|
---|
984 | self.checkequal(False, '', '__contains__', 'asdf')
|
---|
985 |
|
---|
986 | def test_subscript(self):
|
---|
987 | self.checkequal(u'a', 'abc', '__getitem__', 0)
|
---|
988 | self.checkequal(u'c', 'abc', '__getitem__', -1)
|
---|
989 | self.checkequal(u'a', 'abc', '__getitem__', 0L)
|
---|
990 | self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 3))
|
---|
991 | self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 1000))
|
---|
992 | self.checkequal(u'a', 'abc', '__getitem__', slice(0, 1))
|
---|
993 | self.checkequal(u'', 'abc', '__getitem__', slice(0, 0))
|
---|
994 |
|
---|
995 | self.checkraises(TypeError, 'abc', '__getitem__', 'def')
|
---|
996 |
|
---|
997 | def test_slice(self):
|
---|
998 | self.checkequal('abc', 'abc', '__getslice__', 0, 1000)
|
---|
999 | self.checkequal('abc', 'abc', '__getslice__', 0, 3)
|
---|
1000 | self.checkequal('ab', 'abc', '__getslice__', 0, 2)
|
---|
1001 | self.checkequal('bc', 'abc', '__getslice__', 1, 3)
|
---|
1002 | self.checkequal('b', 'abc', '__getslice__', 1, 2)
|
---|
1003 | self.checkequal('', 'abc', '__getslice__', 2, 2)
|
---|
1004 | self.checkequal('', 'abc', '__getslice__', 1000, 1000)
|
---|
1005 | self.checkequal('', 'abc', '__getslice__', 2000, 1000)
|
---|
1006 | self.checkequal('', 'abc', '__getslice__', 2, 1)
|
---|
1007 |
|
---|
1008 | self.checkraises(TypeError, 'abc', '__getslice__', 'def')
|
---|
1009 |
|
---|
1010 | def test_extended_getslice(self):
|
---|
1011 | # Test extended slicing by comparing with list slicing.
|
---|
1012 | s = string.ascii_letters + string.digits
|
---|
1013 | indices = (0, None, 1, 3, 41, -1, -2, -37)
|
---|
1014 | for start in indices:
|
---|
1015 | for stop in indices:
|
---|
1016 | # Skip step 0 (invalid)
|
---|
1017 | for step in indices[1:]:
|
---|
1018 | L = list(s)[start:stop:step]
|
---|
1019 | self.checkequal(u"".join(L), s, '__getitem__',
|
---|
1020 | slice(start, stop, step))
|
---|
1021 |
|
---|
1022 | def test_mul(self):
|
---|
1023 | self.checkequal('', 'abc', '__mul__', -1)
|
---|
1024 | self.checkequal('', 'abc', '__mul__', 0)
|
---|
1025 | self.checkequal('abc', 'abc', '__mul__', 1)
|
---|
1026 | self.checkequal('abcabcabc', 'abc', '__mul__', 3)
|
---|
1027 | self.checkraises(TypeError, 'abc', '__mul__')
|
---|
1028 | self.checkraises(TypeError, 'abc', '__mul__', '')
|
---|
1029 | # XXX: on a 64-bit system, this doesn't raise an overflow error,
|
---|
1030 | # but either raises a MemoryError, or succeeds (if you have 54TiB)
|
---|
1031 | #self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000)
|
---|
1032 |
|
---|
1033 | def test_join(self):
|
---|
1034 | # join now works with any sequence type
|
---|
1035 | # moved here, because the argument order is
|
---|
1036 | # different in string.join (see the test in
|
---|
1037 | # test.test_string.StringTest.test_join)
|
---|
1038 | self.checkequal('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
|
---|
1039 | self.checkequal('abcd', '', 'join', ('a', 'b', 'c', 'd'))
|
---|
1040 | self.checkequal('bd', '', 'join', ('', 'b', '', 'd'))
|
---|
1041 | self.checkequal('ac', '', 'join', ('a', '', 'c', ''))
|
---|
1042 | self.checkequal('w x y z', ' ', 'join', Sequence())
|
---|
1043 | self.checkequal('abc', 'a', 'join', ('abc',))
|
---|
1044 | self.checkequal('z', 'a', 'join', UserList(['z']))
|
---|
1045 | if test_support.have_unicode:
|
---|
1046 | self.checkequal(unicode('a.b.c'), unicode('.'), 'join', ['a', 'b', 'c'])
|
---|
1047 | self.checkequal(unicode('a.b.c'), '.', 'join', [unicode('a'), 'b', 'c'])
|
---|
1048 | self.checkequal(unicode('a.b.c'), '.', 'join', ['a', unicode('b'), 'c'])
|
---|
1049 | self.checkequal(unicode('a.b.c'), '.', 'join', ['a', 'b', unicode('c')])
|
---|
1050 | self.checkraises(TypeError, '.', 'join', ['a', unicode('b'), 3])
|
---|
1051 | for i in [5, 25, 125]:
|
---|
1052 | self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
|
---|
1053 | ['a' * i] * i)
|
---|
1054 | self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
|
---|
1055 | ('a' * i,) * i)
|
---|
1056 |
|
---|
1057 | self.checkraises(TypeError, ' ', 'join', BadSeq1())
|
---|
1058 | self.checkequal('a b c', ' ', 'join', BadSeq2())
|
---|
1059 |
|
---|
1060 | self.checkraises(TypeError, ' ', 'join')
|
---|
1061 | self.checkraises(TypeError, ' ', 'join', 7)
|
---|
1062 | self.checkraises(TypeError, ' ', 'join', Sequence([7, 'hello', 123L]))
|
---|
1063 | try:
|
---|
1064 | def f():
|
---|
1065 | yield 4 + ""
|
---|
1066 | self.fixtype(' ').join(f())
|
---|
1067 | except TypeError, e:
|
---|
1068 | if '+' not in str(e):
|
---|
1069 | self.fail('join() ate exception message')
|
---|
1070 | else:
|
---|
1071 | self.fail('exception not raised')
|
---|
1072 |
|
---|
1073 | def test_formatting(self):
|
---|
1074 | self.checkequal('+hello+', '+%s+', '__mod__', 'hello')
|
---|
1075 | self.checkequal('+10+', '+%d+', '__mod__', 10)
|
---|
1076 | self.checkequal('a', "%c", '__mod__', "a")
|
---|
1077 | self.checkequal('a', "%c", '__mod__', "a")
|
---|
1078 | self.checkequal('"', "%c", '__mod__', 34)
|
---|
1079 | self.checkequal('$', "%c", '__mod__', 36)
|
---|
1080 | self.checkequal('10', "%d", '__mod__', 10)
|
---|
1081 | self.checkequal('\x7f', "%c", '__mod__', 0x7f)
|
---|
1082 |
|
---|
1083 | for ordinal in (-100, 0x200000):
|
---|
1084 | # unicode raises ValueError, str raises OverflowError
|
---|
1085 | self.checkraises((ValueError, OverflowError), '%c', '__mod__', ordinal)
|
---|
1086 |
|
---|
1087 | longvalue = sys.maxint + 10L
|
---|
1088 | slongvalue = str(longvalue)
|
---|
1089 | if slongvalue[-1] in ("L","l"): slongvalue = slongvalue[:-1]
|
---|
1090 | self.checkequal(' 42', '%3ld', '__mod__', 42)
|
---|
1091 | self.checkequal('42', '%d', '__mod__', 42L)
|
---|
1092 | self.checkequal('42', '%d', '__mod__', 42.0)
|
---|
1093 | self.checkequal(slongvalue, '%d', '__mod__', longvalue)
|
---|
1094 | self.checkcall('%d', '__mod__', float(longvalue))
|
---|
1095 | self.checkequal('0042.00', '%07.2f', '__mod__', 42)
|
---|
1096 | self.checkequal('0042.00', '%07.2F', '__mod__', 42)
|
---|
1097 |
|
---|
1098 | self.checkraises(TypeError, 'abc', '__mod__')
|
---|
1099 | self.checkraises(TypeError, '%(foo)s', '__mod__', 42)
|
---|
1100 | self.checkraises(TypeError, '%s%s', '__mod__', (42,))
|
---|
1101 | self.checkraises(TypeError, '%c', '__mod__', (None,))
|
---|
1102 | self.checkraises(ValueError, '%(foo', '__mod__', {})
|
---|
1103 | self.checkraises(TypeError, '%(foo)s %(bar)s', '__mod__', ('foo', 42))
|
---|
1104 | self.checkraises(TypeError, '%d', '__mod__', "42") # not numeric
|
---|
1105 | self.checkraises(TypeError, '%d', '__mod__', (42+0j)) # no int/long conversion provided
|
---|
1106 |
|
---|
1107 | # argument names with properly nested brackets are supported
|
---|
1108 | self.checkequal('bar', '%((foo))s', '__mod__', {'(foo)': 'bar'})
|
---|
1109 |
|
---|
1110 | # 100 is a magic number in PyUnicode_Format, this forces a resize
|
---|
1111 | self.checkequal(103*'a'+'x', '%sx', '__mod__', 103*'a')
|
---|
1112 |
|
---|
1113 | self.checkraises(TypeError, '%*s', '__mod__', ('foo', 'bar'))
|
---|
1114 | self.checkraises(TypeError, '%10.*f', '__mod__', ('foo', 42.))
|
---|
1115 | self.checkraises(ValueError, '%10', '__mod__', (42,))
|
---|
1116 |
|
---|
1117 | width = int(_testcapi.PY_SSIZE_T_MAX + 1)
|
---|
1118 | if width <= sys.maxint:
|
---|
1119 | self.checkraises(OverflowError, '%*s', '__mod__', (width, ''))
|
---|
1120 | prec = int(_testcapi.INT_MAX + 1)
|
---|
1121 | if prec <= sys.maxint:
|
---|
1122 | self.checkraises(OverflowError, '%.*f', '__mod__', (prec, 1. / 7))
|
---|
1123 | # Issue 15989
|
---|
1124 | width = int(1 << (_testcapi.PY_SSIZE_T_MAX.bit_length() + 1))
|
---|
1125 | if width <= sys.maxint:
|
---|
1126 | self.checkraises(OverflowError, '%*s', '__mod__', (width, ''))
|
---|
1127 | prec = int(_testcapi.UINT_MAX + 1)
|
---|
1128 | if prec <= sys.maxint:
|
---|
1129 | self.checkraises(OverflowError, '%.*f', '__mod__', (prec, 1. / 7))
|
---|
1130 |
|
---|
1131 | class X(object): pass
|
---|
1132 | self.checkraises(TypeError, 'abc', '__mod__', X())
|
---|
1133 | class X(Exception):
|
---|
1134 | def __getitem__(self, k):
|
---|
1135 | return k
|
---|
1136 | self.checkequal('melon apple', '%(melon)s %(apple)s', '__mod__', X())
|
---|
1137 |
|
---|
1138 | def test_floatformatting(self):
|
---|
1139 | # float formatting
|
---|
1140 | for prec in xrange(100):
|
---|
1141 | format = '%%.%if' % prec
|
---|
1142 | value = 0.01
|
---|
1143 | for x in xrange(60):
|
---|
1144 | value = value * 3.14159265359 / 3.0 * 10.0
|
---|
1145 | self.checkcall(format, "__mod__", value)
|
---|
1146 |
|
---|
1147 | def test_inplace_rewrites(self):
|
---|
1148 | # Check that strings don't copy and modify cached single-character strings
|
---|
1149 | self.checkequal('a', 'A', 'lower')
|
---|
1150 | self.checkequal(True, 'A', 'isupper')
|
---|
1151 | self.checkequal('A', 'a', 'upper')
|
---|
1152 | self.checkequal(True, 'a', 'islower')
|
---|
1153 |
|
---|
1154 | self.checkequal('a', 'A', 'replace', 'A', 'a')
|
---|
1155 | self.checkequal(True, 'A', 'isupper')
|
---|
1156 |
|
---|
1157 | self.checkequal('A', 'a', 'capitalize')
|
---|
1158 | self.checkequal(True, 'a', 'islower')
|
---|
1159 |
|
---|
1160 | self.checkequal('A', 'a', 'swapcase')
|
---|
1161 | self.checkequal(True, 'a', 'islower')
|
---|
1162 |
|
---|
1163 | self.checkequal('A', 'a', 'title')
|
---|
1164 | self.checkequal(True, 'a', 'islower')
|
---|
1165 |
|
---|
1166 | def test_partition(self):
|
---|
1167 |
|
---|
1168 | self.checkequal(('this is the par', 'ti', 'tion method'),
|
---|
1169 | 'this is the partition method', 'partition', 'ti')
|
---|
1170 |
|
---|
1171 | # from raymond's original specification
|
---|
1172 | S = 'http://www.python.org'
|
---|
1173 | self.checkequal(('http', '://', 'www.python.org'), S, 'partition', '://')
|
---|
1174 | self.checkequal(('http://www.python.org', '', ''), S, 'partition', '?')
|
---|
1175 | self.checkequal(('', 'http://', 'www.python.org'), S, 'partition', 'http://')
|
---|
1176 | self.checkequal(('http://www.python.', 'org', ''), S, 'partition', 'org')
|
---|
1177 |
|
---|
1178 | self.checkraises(ValueError, S, 'partition', '')
|
---|
1179 | self.checkraises(TypeError, S, 'partition', None)
|
---|
1180 |
|
---|
1181 | # mixed use of str and unicode
|
---|
1182 | self.assertEqual('a/b/c'.partition(u'/'), ('a', '/', 'b/c'))
|
---|
1183 |
|
---|
1184 | def test_rpartition(self):
|
---|
1185 |
|
---|
1186 | self.checkequal(('this is the rparti', 'ti', 'on method'),
|
---|
1187 | 'this is the rpartition method', 'rpartition', 'ti')
|
---|
1188 |
|
---|
1189 | # from raymond's original specification
|
---|
1190 | S = 'http://www.python.org'
|
---|
1191 | self.checkequal(('http', '://', 'www.python.org'), S, 'rpartition', '://')
|
---|
1192 | self.checkequal(('', '', 'http://www.python.org'), S, 'rpartition', '?')
|
---|
1193 | self.checkequal(('', 'http://', 'www.python.org'), S, 'rpartition', 'http://')
|
---|
1194 | self.checkequal(('http://www.python.', 'org', ''), S, 'rpartition', 'org')
|
---|
1195 |
|
---|
1196 | self.checkraises(ValueError, S, 'rpartition', '')
|
---|
1197 | self.checkraises(TypeError, S, 'rpartition', None)
|
---|
1198 |
|
---|
1199 | # mixed use of str and unicode
|
---|
1200 | self.assertEqual('a/b/c'.rpartition(u'/'), ('a/b', '/', 'c'))
|
---|
1201 |
|
---|
1202 | def test_none_arguments(self):
|
---|
1203 | # issue 11828
|
---|
1204 | s = 'hello'
|
---|
1205 | self.checkequal(2, s, 'find', 'l', None)
|
---|
1206 | self.checkequal(3, s, 'find', 'l', -2, None)
|
---|
1207 | self.checkequal(2, s, 'find', 'l', None, -2)
|
---|
1208 | self.checkequal(0, s, 'find', 'h', None, None)
|
---|
1209 |
|
---|
1210 | self.checkequal(3, s, 'rfind', 'l', None)
|
---|
1211 | self.checkequal(3, s, 'rfind', 'l', -2, None)
|
---|
1212 | self.checkequal(2, s, 'rfind', 'l', None, -2)
|
---|
1213 | self.checkequal(0, s, 'rfind', 'h', None, None)
|
---|
1214 |
|
---|
1215 | self.checkequal(2, s, 'index', 'l', None)
|
---|
1216 | self.checkequal(3, s, 'index', 'l', -2, None)
|
---|
1217 | self.checkequal(2, s, 'index', 'l', None, -2)
|
---|
1218 | self.checkequal(0, s, 'index', 'h', None, None)
|
---|
1219 |
|
---|
1220 | self.checkequal(3, s, 'rindex', 'l', None)
|
---|
1221 | self.checkequal(3, s, 'rindex', 'l', -2, None)
|
---|
1222 | self.checkequal(2, s, 'rindex', 'l', None, -2)
|
---|
1223 | self.checkequal(0, s, 'rindex', 'h', None, None)
|
---|
1224 |
|
---|
1225 | self.checkequal(2, s, 'count', 'l', None)
|
---|
1226 | self.checkequal(1, s, 'count', 'l', -2, None)
|
---|
1227 | self.checkequal(1, s, 'count', 'l', None, -2)
|
---|
1228 | self.checkequal(0, s, 'count', 'x', None, None)
|
---|
1229 |
|
---|
1230 | self.checkequal(True, s, 'endswith', 'o', None)
|
---|
1231 | self.checkequal(True, s, 'endswith', 'lo', -2, None)
|
---|
1232 | self.checkequal(True, s, 'endswith', 'l', None, -2)
|
---|
1233 | self.checkequal(False, s, 'endswith', 'x', None, None)
|
---|
1234 |
|
---|
1235 | self.checkequal(True, s, 'startswith', 'h', None)
|
---|
1236 | self.checkequal(True, s, 'startswith', 'l', -2, None)
|
---|
1237 | self.checkequal(True, s, 'startswith', 'h', None, -2)
|
---|
1238 | self.checkequal(False, s, 'startswith', 'x', None, None)
|
---|
1239 |
|
---|
1240 | def test_find_etc_raise_correct_error_messages(self):
|
---|
1241 | # issue 11828
|
---|
1242 | s = 'hello'
|
---|
1243 | x = 'x'
|
---|
1244 | self.assertRaisesRegexp(TypeError, r'\bfind\b', s.find,
|
---|
1245 | x, None, None, None)
|
---|
1246 | self.assertRaisesRegexp(TypeError, r'\brfind\b', s.rfind,
|
---|
1247 | x, None, None, None)
|
---|
1248 | self.assertRaisesRegexp(TypeError, r'\bindex\b', s.index,
|
---|
1249 | x, None, None, None)
|
---|
1250 | self.assertRaisesRegexp(TypeError, r'\brindex\b', s.rindex,
|
---|
1251 | x, None, None, None)
|
---|
1252 | self.assertRaisesRegexp(TypeError, r'^count\(', s.count,
|
---|
1253 | x, None, None, None)
|
---|
1254 | self.assertRaisesRegexp(TypeError, r'^startswith\(', s.startswith,
|
---|
1255 | x, None, None, None)
|
---|
1256 | self.assertRaisesRegexp(TypeError, r'^endswith\(', s.endswith,
|
---|
1257 | x, None, None, None)
|
---|
1258 |
|
---|
1259 | class MixinStrStringUserStringTest:
|
---|
1260 | # Additional tests for 8bit strings, i.e. str, UserString and
|
---|
1261 | # the string module
|
---|
1262 |
|
---|
1263 | def test_maketrans(self):
|
---|
1264 | self.assertEqual(
|
---|
1265 | ''.join(map(chr, xrange(256))).replace('abc', 'xyz'),
|
---|
1266 | string.maketrans('abc', 'xyz')
|
---|
1267 | )
|
---|
1268 | self.assertRaises(ValueError, string.maketrans, 'abc', 'xyzw')
|
---|
1269 |
|
---|
1270 | def test_translate(self):
|
---|
1271 | table = string.maketrans('abc', 'xyz')
|
---|
1272 | self.checkequal('xyzxyz', 'xyzabcdef', 'translate', table, 'def')
|
---|
1273 |
|
---|
1274 | table = string.maketrans('a', 'A')
|
---|
1275 | self.checkequal('Abc', 'abc', 'translate', table)
|
---|
1276 | self.checkequal('xyz', 'xyz', 'translate', table)
|
---|
1277 | self.checkequal('yz', 'xyz', 'translate', table, 'x')
|
---|
1278 | self.checkequal('yx', 'zyzzx', 'translate', None, 'z')
|
---|
1279 | self.checkequal('zyzzx', 'zyzzx', 'translate', None, '')
|
---|
1280 | self.checkequal('zyzzx', 'zyzzx', 'translate', None)
|
---|
1281 | self.checkraises(ValueError, 'xyz', 'translate', 'too short', 'strip')
|
---|
1282 | self.checkraises(ValueError, 'xyz', 'translate', 'too short')
|
---|
1283 |
|
---|
1284 |
|
---|
1285 | class MixinStrUserStringTest:
|
---|
1286 | # Additional tests that only work with
|
---|
1287 | # 8bit compatible object, i.e. str and UserString
|
---|
1288 |
|
---|
1289 | if test_support.have_unicode:
|
---|
1290 | def test_encoding_decoding(self):
|
---|
1291 | codecs = [('rot13', 'uryyb jbeyq'),
|
---|
1292 | ('base64', 'aGVsbG8gd29ybGQ=\n'),
|
---|
1293 | ('hex', '68656c6c6f20776f726c64'),
|
---|
1294 | ('uu', 'begin 666 <data>\n+:&5L;&\\@=V]R;&0 \n \nend\n')]
|
---|
1295 | for encoding, data in codecs:
|
---|
1296 | self.checkequal(data, 'hello world', 'encode', encoding)
|
---|
1297 | self.checkequal('hello world', data, 'decode', encoding)
|
---|
1298 | # zlib is optional, so we make the test optional too...
|
---|
1299 | try:
|
---|
1300 | import zlib
|
---|
1301 | except ImportError:
|
---|
1302 | pass
|
---|
1303 | else:
|
---|
1304 | data = 'x\x9c\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\x01\x00\x1a\x0b\x04]'
|
---|
1305 | self.checkequal(data, 'hello world', 'encode', 'zlib')
|
---|
1306 | self.checkequal('hello world', data, 'decode', 'zlib')
|
---|
1307 |
|
---|
1308 | self.checkraises(TypeError, 'xyz', 'decode', 42)
|
---|
1309 | self.checkraises(TypeError, 'xyz', 'encode', 42)
|
---|
1310 |
|
---|
1311 |
|
---|
1312 | class MixinStrUnicodeTest:
|
---|
1313 | # Additional tests that only work with str and unicode.
|
---|
1314 |
|
---|
1315 | def test_bug1001011(self):
|
---|
1316 | # Make sure join returns a NEW object for single item sequences
|
---|
1317 | # involving a subclass.
|
---|
1318 | # Make sure that it is of the appropriate type.
|
---|
1319 | # Check the optimisation still occurs for standard objects.
|
---|
1320 | t = self.type2test
|
---|
1321 | class subclass(t):
|
---|
1322 | pass
|
---|
1323 | s1 = subclass("abcd")
|
---|
1324 | s2 = t().join([s1])
|
---|
1325 | self.assertTrue(s1 is not s2)
|
---|
1326 | self.assertTrue(type(s2) is t)
|
---|
1327 |
|
---|
1328 | s1 = t("abcd")
|
---|
1329 | s2 = t().join([s1])
|
---|
1330 | self.assertTrue(s1 is s2)
|
---|
1331 |
|
---|
1332 | # Should also test mixed-type join.
|
---|
1333 | if t is unicode:
|
---|
1334 | s1 = subclass("abcd")
|
---|
1335 | s2 = "".join([s1])
|
---|
1336 | self.assertTrue(s1 is not s2)
|
---|
1337 | self.assertTrue(type(s2) is t)
|
---|
1338 |
|
---|
1339 | s1 = t("abcd")
|
---|
1340 | s2 = "".join([s1])
|
---|
1341 | self.assertTrue(s1 is s2)
|
---|
1342 |
|
---|
1343 | elif t is str:
|
---|
1344 | s1 = subclass("abcd")
|
---|
1345 | s2 = u"".join([s1])
|
---|
1346 | self.assertTrue(s1 is not s2)
|
---|
1347 | self.assertTrue(type(s2) is unicode) # promotes!
|
---|
1348 |
|
---|
1349 | s1 = t("abcd")
|
---|
1350 | s2 = u"".join([s1])
|
---|
1351 | self.assertTrue(s1 is not s2)
|
---|
1352 | self.assertTrue(type(s2) is unicode) # promotes!
|
---|
1353 |
|
---|
1354 | else:
|
---|
1355 | self.fail("unexpected type for MixinStrUnicodeTest %r" % t)
|
---|