1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
|
""" Test script for the Unicode implementation.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""
from test_support import verbose
import sys
def test(method, input, output, *args):
if verbose:
print '%s.%s%s =? %s... ' % (repr(input), method, args, output),
try:
f = getattr(input, method)
value = apply(f, args)
except:
value = sys.exc_type
exc = sys.exc_info()
else:
exc = None
if value != output:
if verbose:
print 'no'
print '*',f, `input`, `output`, `value`
if exc:
print ' value == %s: %s' % (exc[:2])
else:
if verbose:
print 'yes'
test('capitalize', u' hello ', u' hello ')
test('capitalize', u'hello ', u'Hello ')
test('title', u' hello ', u' Hello ')
test('title', u'hello ', u'Hello ')
test('title', u"fOrMaT thIs aS titLe String", u'Format This As Title String')
test('title', u"fOrMaT,thIs-aS*titLe;String", u'Format,This-As*Title;String')
test('title', u"getInt", u'Getint')
test('find', u'abcdefghiabc', 0, u'abc')
test('find', u'abcdefghiabc', 9, u'abc', 1)
test('find', u'abcdefghiabc', -1, u'def', 4)
test('rfind', u'abcdefghiabc', 9, u'abc')
test('lower', u'HeLLo', u'hello')
test('lower', u'hello', u'hello')
test('upper', u'HeLLo', u'HELLO')
test('upper', u'HELLO', u'HELLO')
if 0:
transtable = '\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037 !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`xyzdefghijklmnopqrstuvwxyz{|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377'
test('maketrans', u'abc', transtable, u'xyz')
test('maketrans', u'abc', ValueError, u'xyzq')
test('split', u'this is the split function',
[u'this', u'is', u'the', u'split', u'function'])
test('split', u'a|b|c|d', [u'a', u'b', u'c', u'd'], u'|')
test('split', u'a|b|c|d', [u'a', u'b', u'c|d'], u'|', 2)
test('split', u'a b c d', [u'a', u'b c d'], None, 1)
test('split', u'a b c d', [u'a', u'b', u'c d'], None, 2)
test('split', u'a b c d', [u'a', u'b', u'c', u'd'], None, 3)
test('split', u'a b c d', [u'a', u'b', u'c', u'd'], None, 4)
test('split', u'a b c d', [u'a b c d'], None, 0)
test('split', u'a b c d', [u'a', u'b', u'c d'], None, 2)
test('split', u'a b c d ', [u'a', u'b', u'c', u'd'])
# join now works with any sequence type
class Sequence:
def __init__(self): self.seq = 'wxyz'
def __len__(self): return len(self.seq)
def __getitem__(self, i): return self.seq[i]
test('join', u' ', u'a b c d', [u'a', u'b', u'c', u'd'])
test('join', u'', u'abcd', (u'a', u'b', u'c', u'd'))
test('join', u' ', u'w x y z', Sequence())
test('join', u' ', TypeError, 7)
class BadSeq(Sequence):
def __init__(self): self.seq = [7, u'hello', 123L]
test('join', u' ', TypeError, BadSeq())
result = u''
for i in range(10):
if i > 0:
result = result + u':'
result = result + u'x'*10
test('join', u':', result, [u'x' * 10] * 10)
test('join', u':', result, (u'x' * 10,) * 10)
test('strip', u' hello ', u'hello')
test('lstrip', u' hello ', u'hello ')
test('rstrip', u' hello ', u' hello')
test('strip', u'hello', u'hello')
test('swapcase', u'HeLLo cOmpUteRs', u'hEllO CoMPuTErS')
if 0:
test('translate', u'xyzabcdef', u'xyzxyz', transtable, u'def')
table = string.maketrans('a', u'A')
test('translate', u'abc', u'Abc', table)
test('translate', u'xyz', u'xyz', table)
test('replace', u'one!two!three!', u'one@two!three!', u'!', u'@', 1)
test('replace', u'one!two!three!', u'one@two@three!', u'!', u'@', 2)
test('replace', u'one!two!three!', u'one@two@three@', u'!', u'@', 3)
test('replace', u'one!two!three!', u'one@two@three@', u'!', u'@', 4)
test('replace', u'one!two!three!', u'one!two!three!', u'!', u'@', 0)
test('replace', u'one!two!three!', u'one@two@three@', u'!', u'@')
test('replace', u'one!two!three!', u'one!two!three!', u'x', u'@')
test('replace', u'one!two!three!', u'one!two!three!', u'x', u'@', 2)
test('startswith', u'hello', 1, u'he')
test('startswith', u'hello', 1, u'hello')
test('startswith', u'hello', 0, u'hello world')
test('startswith', u'hello', 1, u'')
test('startswith', u'hello', 0, u'ello')
test('startswith', u'hello', 1, u'ello', 1)
test('startswith', u'hello', 1, u'o', 4)
test('startswith', u'hello', 0, u'o', 5)
test('startswith', u'hello', 1, u'', 5)
test('startswith', u'hello', 0, u'lo', 6)
test('startswith', u'helloworld', 1, u'lowo', 3)
test('startswith', u'helloworld', 1, u'lowo', 3, 7)
test('startswith', u'helloworld', 0, u'lowo', 3, 6)
test('endswith', u'hello', 1, u'lo')
test('endswith', u'hello', 0, u'he')
test('endswith', u'hello', 1, u'')
test('endswith', u'hello', 0, u'hello world')
test('endswith', u'helloworld', 0, u'worl')
test('endswith', u'helloworld', 1, u'worl', 3, 9)
test('endswith', u'helloworld', 1, u'world', 3, 12)
test('endswith', u'helloworld', 1, u'lowo', 1, 7)
test('endswith', u'helloworld', 1, u'lowo', 2, 7)
test('endswith', u'helloworld', 1, u'lowo', 3, 7)
test('endswith', u'helloworld', 0, u'lowo', 4, 7)
test('endswith', u'helloworld', 0, u'lowo', 3, 8)
test('endswith', u'ab', 0, u'ab', 0, 1)
test('endswith', u'ab', 0, u'ab', 0, 0)
test('expandtabs', u'abc\rab\tdef\ng\thi', u'abc\rab def\ng hi')
test('expandtabs', u'abc\rab\tdef\ng\thi', u'abc\rab def\ng hi', 8)
test('expandtabs', u'abc\rab\tdef\ng\thi', u'abc\rab def\ng hi', 4)
test('expandtabs', u'abc\r\nab\tdef\ng\thi', u'abc\r\nab def\ng hi', 4)
if 0:
test('capwords', u'abc def ghi', u'Abc Def Ghi')
test('capwords', u'abc\tdef\nghi', u'Abc Def Ghi')
test('capwords', u'abc\t def \nghi', u'Abc Def Ghi')
# Comparisons:
print 'Testing Unicode comparisons...',
assert u'abc' == 'abc'
assert 'abc' == u'abc'
assert u'abc' == u'abc'
assert u'abcd' > 'abc'
assert 'abcd' > u'abc'
assert u'abcd' > u'abc'
assert u'abc' < 'abcd'
assert 'abc' < u'abcd'
assert u'abc' < u'abcd'
print 'done.'
test('ljust', u'abc', u'abc ', 10)
test('rjust', u'abc', u' abc', 10)
test('center', u'abc', u' abc ', 10)
test('ljust', u'abc', u'abc ', 6)
test('rjust', u'abc', u' abc', 6)
test('center', u'abc', u' abc ', 6)
test('ljust', u'abc', u'abc', 2)
test('rjust', u'abc', u'abc', 2)
test('center', u'abc', u'abc', 2)
test('islower', u'a', 1)
test('islower', u'A', 0)
test('islower', u'\n', 0)
test('islower', u'\u1FFc', 0)
test('islower', u'abc', 1)
test('islower', u'aBc', 0)
test('islower', u'abc\n', 1)
test('isupper', u'a', 0)
test('isupper', u'A', 1)
test('isupper', u'\n', 0)
test('isupper', u'\u1FFc', 0)
test('isupper', u'ABC', 1)
test('isupper', u'AbC', 0)
test('isupper', u'ABC\n', 1)
test('istitle', u'a', 0)
test('istitle', u'A', 1)
test('istitle', u'\n', 0)
test('istitle', u'\u1FFc', 1)
test('istitle', u'A Titlecased Line', 1)
test('istitle', u'A\nTitlecased Line', 1)
test('istitle', u'A Titlecased, Line', 1)
test('istitle', u'Greek \u1FFcitlecases ...', 1)
test('istitle', u'Not a capitalized String', 0)
test('istitle', u'Not\ta Titlecase String', 0)
test('istitle', u'Not--a Titlecase String', 0)
test('splitlines', u"abc\ndef\n\rghi", [u'abc', u'def', u'', u'ghi'])
test('splitlines', u"abc\ndef\n\r\nghi", [u'abc', u'def', u'', u'ghi'])
test('splitlines', u"abc\ndef\r\nghi", [u'abc', u'def', u'ghi'])
test('splitlines', u"abc\ndef\r\nghi\n", [u'abc', u'def', u'ghi'])
test('splitlines', u"abc\ndef\r\nghi\n\r", [u'abc', u'def', u'ghi', u''])
test('splitlines', u"\nabc\ndef\r\nghi\n\r", [u'', u'abc', u'def', u'ghi', u''])
test('splitlines', u"\nabc\ndef\r\nghi\n\r", [u'', u'abc\012def\015\012ghi\012\015'], 1)
test('splitlines', u"\nabc\ndef\r\nghi\n\r", [u'', u'abc', u'def\015\012ghi\012\015'], 2)
test('translate', u"abababc", u'bbbc', {ord('a'):None})
test('translate', u"abababc", u'iiic', {ord('a'):None, ord('b'):ord('i')})
test('translate', u"abababc", u'iiix', {ord('a'):None, ord('b'):ord('i'), ord('c'):u'x'})
# Contains:
print 'Testing Unicode contains method...',
assert ('a' in 'abdb') == 1
assert ('a' in 'bdab') == 1
assert ('a' in 'bdaba') == 1
assert ('a' in 'bdba') == 1
assert ('a' in u'bdba') == 1
assert (u'a' in u'bdba') == 1
assert (u'a' in u'bdb') == 0
assert (u'a' in 'bdb') == 0
assert (u'a' in 'bdba') == 1
print 'done.'
# Formatting:
print 'Testing Unicode formatting strings...',
assert u"%s, %s" % (u"abc", "abc") == u'abc, abc'
assert u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, 2, 3) == u'abc, abc, 1, 2.000000, 3.00'
assert u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, -2, 3) == u'abc, abc, 1, -2.000000, 3.00'
assert u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.5) == u'abc, abc, -1, -2.000000, 3.50'
assert u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.57) == u'abc, abc, -1, -2.000000, 3.57'
assert u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 1003.57) == u'abc, abc, -1, -2.000000, 1003.57'
assert u"%c" % (u"abc",) == u'a'
assert u"%c" % ("abc",) == u'a'
assert u"%c" % (34,) == u'"'
assert u"%c" % (36,) == u'$'
assert u"%r, %r" % (u"abc", "abc") == u"u'abc', 'abc'"
assert u"%(x)s, %(y)s" % {'x':u"abc", 'y':"def"} == u'abc, def'
assert u"%(x)s, %(ä)s" % {'x':u"abc", u'ä'.encode('utf-8'):"def"} == u'abc, def'
print 'done.'
# Test Unicode database APIs
try:
import unicodedata
except ImportError:
pass
else:
print 'Testing unicodedata module...',
assert unicodedata.digit(u'A',None) is None
assert unicodedata.digit(u'9') == 9
assert unicodedata.digit(u'\u215b',None) is None
assert unicodedata.digit(u'\u2468') == 9
assert unicodedata.numeric(u'A',None) is None
assert unicodedata.numeric(u'9') == 9
assert unicodedata.numeric(u'\u215b') == 0.125
assert unicodedata.numeric(u'\u2468') == 9.0
assert unicodedata.decimal(u'A',None) is None
assert unicodedata.decimal(u'9') == 9
assert unicodedata.decimal(u'\u215b',None) is None
assert unicodedata.decimal(u'\u2468',None) is None
assert unicodedata.category(u'\uFFFE') == 'Cn'
assert unicodedata.category(u'a') == 'Ll'
assert unicodedata.category(u'A') == 'Lu'
assert unicodedata.bidirectional(u'\uFFFE') == ''
assert unicodedata.bidirectional(u' ') == 'WS'
assert unicodedata.bidirectional(u'A') == 'L'
assert unicodedata.decomposition(u'\uFFFE') == ''
assert unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034'
assert unicodedata.mirrored(u'\uFFFE') == 0
assert unicodedata.mirrored(u'a') == 0
assert unicodedata.mirrored(u'\u2201') == 1
assert unicodedata.combining(u'\uFFFE') == 0
assert unicodedata.combining(u'a') == 0
assert unicodedata.combining(u'\u20e1') == 230
print 'done.'
|
