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
|
#!/usr/bin/env python2.4
# Copyright (c) 2005-2006 LOGILAB S.A. (Paris, FRANCE).
# Copyright (c) 2005-2006 CEA Grenoble
# http://www.logilab.fr/ -- mailto:contact@logilab.fr
#
# This program is free software; you can redistribute it and/or modify it under
# the terms of the CECILL license, available at
# http://www.inria.fr/valorisation/logiciels/Licence.CeCILL-V2.pdf
#
__revision__ = '$Id: test_wcwidth.py,v 1.7 2006-02-15 10:24:02 alf Exp $'
## http://www.cl.cam.ac.uk/~mgk25/ucs/scw-proposal.html is the right place
from pyqonsole.helpers import wcWidth
import unittest
import unicodedata as udata
def widths():
""" toy function to explore the unicodedata module """
global CATS
for cat, chars in CATS.iteritems():
print '-'*80
print cat
print '-'*80
for c in chars:
print '%06X'%c, wcWidth(c), udata.east_asian_width(unichr(c))
print
def makeCats():
cats = {}
for i in xrange(0x110000):
char = unichr(i)
cats.setdefault(udata.category(char), []).append(i)
return cats
category_names = {'Cc': 'Other, control',
'Cf': 'Other, format',
'Cn': 'Other, not assigned',
'Co': 'Other, private use',
'Cs': 'Other, surrogate',
'Ll': 'Letter, lowercase',
'Lm': 'Letter, modifier',
'Lo': 'Letter, other',
'Lt': 'Letter, titlecase',
'Lu': 'Letter, uppercase',
'Mc': 'Mark, spacing combining',
'Me': 'Mark, enclosing',
'Mn': 'Mark, non-spacing',
'Nd': 'Number, decimal digit',
'Nl': 'Number, letter',
'No': 'Number other',
'Pc': 'Punctuation, connector',
'Pd': 'Punctuation, dash',
'Pe': 'Punctuation, close',
'Pf': 'Punctuation, final quote',
'Pi': 'Puntuation, initial quote',
'Po': 'Punctuation, other',
'Ps': 'Punctuation, open',
'Sc': 'Symbol, currency',
'Sk': 'Symbol, modifier',
'Sm': 'Symbol, math',
'So': 'Symbol, other',
'Zl': 'Seaprator, line',
'Zp': 'Seaparator, paragraph',
'Zs': 'Separator, space',
}
print "Initializing test data..."
CATS = makeCats()
single_width = []
double_width = []
for cp in xrange(33,0x110000):
ch = unichr(cp)
if (udata.category(ch) in ('Mn', 'Me', 'Cf', 'Cn') and cp != 0xAD) or \
(0x7f<= cp < 0xa0) or \
(0x1160 <= cp <= 0x11ff) or \
(cp == 0x200B):
continue
if cp >= 0x1100 and (
cp <= 0x115f or \
cp in (0x2329, 0x232A) or \
(0x2e80 <= cp < 0x303f) or \
(0x303f < cp <= 0xa4cf) or \
(0xac00 <= cp <= 0xd7a3) or \
(0xf900 <= cp <= 0xfaff) or \
(0xfe30 <= cp <= 0xfe6f) or \
(0xff00 <= cp <= 0xff60) or \
(0xffe0 <= cp <= 0xffe6) or \
(0x20000 <= cp <= 0x2fffd) or \
(0x30000 <= cp <= 0x3fffd)):
double_width.append(cp)
else:
single_width.append(cp)
print "done"
class Wcwidth_TC(unittest.TestCase):
def testNullChar(self):
self.assertEquals(wcWidth(0), 0)
def check_range(self, codepoints, expected):
failures = []
for cp in codepoints:
unichar = unichr(cp)
## print cp, udata.name(unichar, 'XXX Unknown Code Point')
if wcWidth(cp) != expected:
failures.append('codepoint %X [%s] [cat: %s (%s)] width %d expected %d' % \
(cp,
udata.name(unichar, 'XXX Unknown Code Point'),
udata.category(unichar),
category_names[udata.category(unichar)],
wcWidth(cp),
expected))
self.assertEquals(failures, [])
def testControlChar(self):
codepoints = range(1,32) + range(0x7f, 0xa0)
self.check_range(codepoints, -1)
def skiptestFormatChar(self):
# This test fails because of problems in unidata
self.check_range(CATS['Cf'], 0)
def testCombiningChar(self):
self.check_range(CATS['Mn'], 0)
self.check_range(CATS['Me'], 0)
def testHangulJamo(self):
codepoints = xrange(0x1160, 0x11FF+1)
self.check_range(codepoints, 0)
def testZeroWidthSpace(self):
self.check_range([0x200B], 0)
def testWideChars(self):
self.check_range(double_width, 2)
def skiptestRemainingChars(self):
# This test fails because of problems in unidata
self.check_range(single_width, 1)
class UnidataErrors_TC(unittest.TestCase):
"""The tests below fail because of an error in unicodedata.
The category mappings are not comformant with
http://www.unicode.org/Public/UNIDATA/UnicodeData.txt maybe it is
a version mismatch (3.2 for unicodedata, 4.X for the file above)."""
def skiptest_MongolianVowelSeparator(self):
char = unichr(0x180E)
self.assertEquals(udata.name(char), 'MONGOLIAN VOWEL SEPARATOR')
self.assertEquals(udata.category(char), 'Zs')
def skiptest_KhmerVowelInherentAa(self):
char = unichr(0x17B5)
self.assertEquals(udata.name(char), 'KHMER VOWEL INHERENT AA')
self.assertEquals(udata.category(char), 'Cf')
def skiptest_KhmerVowelInherentAq(self):
char = unichr(0x17B4)
self.assertEquals(udata.name(char), 'KHMER VOWEL INHERENT AQ')
self.assertEquals(udata.category(char), 'Cf')
if __name__ == '__main__':
unittest.main()
|
