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
|
""" Test script for the Unicode implementation.
Written by Bill Tutt.
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
from test_support import verify, verbose
print 'Testing General Unicode Character Name, and case insensitivity...',
# General and case insensitivity test:
s = u"\N{LATIN CAPITAL LETTER T}" \
u"\N{LATIN SMALL LETTER H}" \
u"\N{LATIN SMALL LETTER E}" \
u"\N{SPACE}" \
u"\N{LATIN SMALL LETTER R}" \
u"\N{LATIN CAPITAL LETTER E}" \
u"\N{LATIN SMALL LETTER D}" \
u"\N{SPACE}" \
u"\N{LATIN SMALL LETTER f}" \
u"\N{LATIN CAPITAL LeTtEr o}" \
u"\N{LATIN SMaLl LETTER x}" \
u"\N{SPACE}" \
u"\N{LATIN SMALL LETTER A}" \
u"\N{LATIN SMALL LETTER T}" \
u"\N{LATIN SMALL LETTER E}" \
u"\N{SPACE}" \
u"\N{LATIN SMALL LETTER T}" \
u"\N{LATIN SMALL LETTER H}" \
u"\N{LATIN SMALL LETTER E}" \
u"\N{SpAcE}" \
u"\N{LATIN SMALL LETTER S}" \
u"\N{LATIN SMALL LETTER H}" \
u"\N{LATIN SMALL LETTER E}" \
u"\N{LATIN SMALL LETTER E}" \
u"\N{LATIN SMALL LETTER P}" \
u"\N{FULL STOP}"
verify(s == u"The rEd fOx ate the sheep.", s)
print "done."
import ucnhash
print "Testing name to code mapping....",
for char in "SPAM":
name = "LATIN SMALL LETTER %s" % char
code = ucnhash.getcode(name)
verify(ucnhash.getname(code) == name)
print "done."
print "Testing code to name mapping for all characters....",
count = 0
for code in range(65536):
try:
name = ucnhash.getname(code)
verify(ucnhash.getcode(name) == code)
count += 1
except ValueError:
pass
print "done."
print "Found", count, "characters in the unicode name database"
# misc. symbol testing
print "Testing misc. symbols for unicode character name expansion....",
verify(u"\N{PILCROW SIGN}" == u"\u00b6")
verify(u"\N{REPLACEMENT CHARACTER}" == u"\uFFFD")
verify(u"\N{HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK}" == u"\uFF9F")
verify(u"\N{FULLWIDTH LATIN SMALL LETTER A}" == u"\uFF41")
print "done."
# strict error testing:
print "Testing unicode character name expansion strict error handling....",
try:
unicode("\N{blah}", 'unicode-escape', 'strict')
except UnicodeError:
pass
else:
raise AssertionError, "failed to raise an exception when given a bogus character name"
try:
unicode("\N{" + "x" * 100000 + "}", 'unicode-escape', 'strict')
except UnicodeError:
pass
else:
raise AssertionError, "failed to raise an exception when given a very " \
"long bogus character name"
try:
unicode("\N{SPACE", 'unicode-escape', 'strict')
except UnicodeError:
pass
else:
raise AssertionError, "failed to raise an exception for a missing closing brace."
try:
unicode("\NSPACE", 'unicode-escape', 'strict')
except UnicodeError:
pass
else:
raise AssertionError, "failed to raise an exception for a missing opening brace."
print "done."
|
