{{ message }}
forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathformathelper.py
More file actions
342 lines (318 loc) · 11.3 KB
/
Copy pathformathelper.py
File metadata and controls
342 lines (318 loc) · 11.3 KB
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
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
#
# Copyright (c) 2008-2012 Stefan Krah. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#
# 1. Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS "AS IS" AND
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
# Generate PEP-3101 format strings.
import os, sys, locale, random
import platform, subprocess
from test.support import import_fresh_module
from distutils.spawn import find_executable
C = import_fresh_module('decimal', fresh=['_decimal'])
P = import_fresh_module('decimal', blocked=['_decimal'])
windows_lang_strings = [
"chinese", "chinese-simplified", "chinese-traditional", "czech", "danish",
"dutch", "belgian", "english", "australian", "canadian", "english-nz",
"english-uk", "english-us", "finnish", "french", "french-belgian",
"french-canadian", "french-swiss", "german", "german-austrian",
"german-swiss", "greek", "hungarian", "icelandic", "italian", "italian-swiss",
"japanese", "korean", "norwegian", "norwegian-bokmal", "norwegian-nynorsk",
"polish", "portuguese", "portuguese-brazil", "russian", "slovak", "spanish",
"spanish-mexican", "spanish-modern", "swedish", "turkish",
]
preferred_encoding = {
'cs_CZ': 'ISO8859-2',
'cs_CZ.iso88592': 'ISO8859-2',
'czech': 'ISO8859-2',
'eesti': 'ISO8859-1',
'estonian': 'ISO8859-1',
'et_EE': 'ISO8859-15',
'et_EE.ISO-8859-15': 'ISO8859-15',
'et_EE.iso885915': 'ISO8859-15',
'et_EE.iso88591': 'ISO8859-1',
'fi_FI.iso88591': 'ISO8859-1',
'fi_FI': 'ISO8859-15',
'fi_FI@euro': 'ISO8859-15',
'fi_FI.iso885915@euro': 'ISO8859-15',
'finnish': 'ISO8859-1',
'lv_LV': 'ISO8859-13',
'lv_LV.iso885913': 'ISO8859-13',
'nb_NO': 'ISO8859-1',
'nb_NO.iso88591': 'ISO8859-1',
'bokmal': 'ISO8859-1',
'nn_NO': 'ISO8859-1',
'nn_NO.iso88591': 'ISO8859-1',
'no_NO': 'ISO8859-1',
'norwegian': 'ISO8859-1',
'nynorsk': 'ISO8859-1',
'ru_RU': 'ISO8859-5',
'ru_RU.iso88595': 'ISO8859-5',
'russian': 'ISO8859-5',
'ru_RU.KOI8-R': 'KOI8-R',
'ru_RU.koi8r': 'KOI8-R',
'ru_RU.CP1251': 'CP1251',
'ru_RU.cp1251': 'CP1251',
'sk_SK': 'ISO8859-2',
'sk_SK.iso88592': 'ISO8859-2',
'slovak': 'ISO8859-2',
'sv_FI': 'ISO8859-1',
'sv_FI.iso88591': 'ISO8859-1',
'sv_FI@euro': 'ISO8859-15',
'sv_FI.iso885915@euro': 'ISO8859-15',
'uk_UA': 'KOI8-U',
'uk_UA.koi8u': 'KOI8-U'
}
integers = [
"",
"1",
"12",
"123",
"1234",
"12345",
"123456",
"1234567",
"12345678",
"123456789",
"1234567890",
"12345678901",
"123456789012",
"1234567890123",
"12345678901234",
"123456789012345",
"1234567890123456",
"12345678901234567",
"123456789012345678",
"1234567890123456789",
"12345678901234567890",
"123456789012345678901",
"1234567890123456789012",
]
numbers = [
"0", "-0", "+0",
"0.0", "-0.0", "+0.0",
"0e0", "-0e0", "+0e0",
".0", "-.0",
".1", "-.1",
"1.1", "-1.1",
"1e1", "-1e1"
]
# Get the list of available locales.
if platform.system() == 'Windows':
locale_list = windows_lang_strings
else:
locale_list = ['C']
if os.path.isfile("/var/lib/locales/supported.d/local"):
# On Ubuntu, `locale -a` gives the wrong case for some locales,
# so we get the correct names directly:
with open("/var/lib/locales/supported.d/local") as f:
locale_list = [loc.split()[0] for loc in f.readlines() \
if not loc.startswith('#')]
elif find_executable('locale'):
locale_list = subprocess.Popen(["locale", "-a"],
stdout=subprocess.PIPE).communicate()[0]
try:
locale_list = locale_list.decode()
except UnicodeDecodeError:
# Some distributions insist on using latin-1 characters
# in their locale names.
locale_list = locale_list.decode('latin-1')
locale_list = locale_list.split('\n')
try:
locale_list.remove('')
except ValueError:
pass
# Debian
if os.path.isfile("/etc/locale.alias"):
with open("/etc/locale.alias") as f:
while 1:
try:
line = f.readline()
except UnicodeDecodeError:
continue
if line == "":
break
if line.startswith('#'):
continue
x = line.split()
if len(x) == 2:
if x[0] in locale_list:
locale_list.remove(x[0])
# FreeBSD
if platform.system() == 'FreeBSD':
# http://www.freebsd.org/cgi/query-pr.cgi?pr=142173
# en_GB.US-ASCII has 163 as the currency symbol.
for loc in ['it_CH.ISO8859-1', 'it_CH.ISO8859-15', 'it_CH.UTF-8',
'it_IT.ISO8859-1', 'it_IT.ISO8859-15', 'it_IT.UTF-8',
'sl_SI.ISO8859-2', 'sl_SI.UTF-8',
'en_GB.US-ASCII']:
try:
locale_list.remove(loc)
except ValueError:
pass
# Print a testcase in the format of the IBM tests (for runtest.c):
def get_preferred_encoding():
loc = locale.setlocale(locale.LC_CTYPE)
if loc in preferred_encoding:
return preferred_encoding[loc]
else:
return locale.getpreferredencoding()
def printit(testno, s, fmt, encoding=None):
if not encoding:
encoding = get_preferred_encoding()
try:
result = format(P.Decimal(s), fmt)
fmt = str(fmt.encode(encoding))[2:-1]
result = str(result.encode(encoding))[2:-1]
if "'" in result:
sys.stdout.write("xfmt%d format %s '%s' -> \"%s\"\n"
% (testno, s, fmt, result))
else:
sys.stdout.write("xfmt%d format %s '%s' -> '%s'\n"
% (testno, s, fmt, result))
except Exception as err:
sys.stderr.write("%s %s %s\n" % (err, s, fmt))
# Check if an integer can be converted to a valid fill character.
def check_fillchar(i):
try:
c = chr(i)
c.encode('utf-8').decode()
format(P.Decimal(0), c + '<19g')
return c
except:
return None
# Generate all unicode characters that are accepted as
# fill characters by decimal.py.
def all_fillchars():
for i in range(0, 0x110002):
c = check_fillchar(i)
if c: yield c
# Return random fill character.
def rand_fillchar():
while 1:
i = random.randrange(0, 0x110002)
c = check_fillchar(i)
if c: return c
# Generate random format strings
# [[fill]align][sign][#][0][width][.precision][type]
def rand_format(fill, typespec='EeGgFfn%'):
active = sorted(random.sample(range(7), random.randrange(8)))
have_align = 0
s = ''
for elem in active:
if elem == 0: # fill+align
s += fill
s += random.choice('<>=^')
have_align = 1
elif elem == 1: # sign
s += random.choice('+- ')
elif elem == 2 and not have_align: # zeropad
s += '0'
elif elem == 3: # width
s += str(random.randrange(1, 100))
elif elem == 4: # thousands separator
s += ','
elif elem == 5: # prec
s += '.'
s += str(random.randrange(100))
elif elem == 6:
if 4 in active: c = typespec.replace('n', '')
else: c = typespec
s += random.choice(c)
return s
# Partially brute force all possible format strings containing a thousands
# separator. Fall back to random where the runtime would become excessive.
# [[fill]align][sign][#][0][width][,][.precision][type]
def all_format_sep():
for align in ('', '<', '>', '=', '^'):
for fill in ('', 'x'):
if align == '': fill = ''
for sign in ('', '+', '-', ' '):
for zeropad in ('', '0'):
if align != '': zeropad = ''
for width in ['']+[str(y) for y in range(1, 15)]+['101']:
for prec in ['']+['.'+str(y) for y in range(15)]:
# for type in ('', 'E', 'e', 'G', 'g', 'F', 'f', '%'):
type = random.choice(('', 'E', 'e', 'G', 'g', 'F', 'f', '%'))
yield ''.join((fill, align, sign, zeropad, width, ',', prec, type))
# Partially brute force all possible format strings with an 'n' specifier.
# [[fill]align][sign][#][0][width][,][.precision][type]
def all_format_loc():
for align in ('', '<', '>', '=', '^'):
for fill in ('', 'x'):
if align == '': fill = ''
for sign in ('', '+', '-', ' '):
for zeropad in ('', '0'):
if align != '': zeropad = ''
for width in ['']+[str(y) for y in range(1, 20)]+['101']:
for prec in ['']+['.'+str(y) for y in range(1, 20)]:
yield ''.join((fill, align, sign, zeropad, width, prec, 'n'))
# Generate random format strings with a unicode fill character
# [[fill]align][sign][#][0][width][,][.precision][type]
def randfill(fill):
active = sorted(random.sample(range(5), random.randrange(6)))
s = ''
s += str(fill)
s += random.choice('<>=^')
for elem in active:
if elem == 0: # sign
s += random.choice('+- ')
elif elem == 1: # width
s += str(random.randrange(1, 100))
elif elem == 2: # thousands separator
s += ','
elif elem == 3: # prec
s += '.'
s += str(random.randrange(100))
elif elem == 4:
if 2 in active: c = 'EeGgFf%'
else: c = 'EeGgFfn%'
s += random.choice(c)
return s
# Generate random format strings with random locale setting
# [[fill]align][sign][#][0][width][,][.precision][type]
def rand_locale():
try:
loc = random.choice(locale_list)
locale.setlocale(locale.LC_ALL, loc)
except locale.Error as err:
pass
active = sorted(random.sample(range(5), random.randrange(6)))
s = ''
have_align = 0
for elem in active:
if elem == 0: # fill+align
s += chr(random.randrange(32, 128))
s += random.choice('<>=^')
have_align = 1
elif elem == 1: # sign
s += random.choice('+- ')
elif elem == 2 and not have_align: # zeropad
s += '0'
elif elem == 3: # width
s += str(random.randrange(1, 100))
elif elem == 4: # prec
s += '.'
s += str(random.randrange(100))
s += 'n'
return s
You can’t perform that action at this time.