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
|
""" Test script for the unicodedata module.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""
import sys
import unittest
import hashlib
import subprocess
import test.support
encoding = 'utf-8'
errors = 'surrogatepass'
### Run tests
class UnicodeMethodsTest(unittest.TestCase):
# update this, if the database changes
expectedchecksum = '618e2c1a22ee79d2235319709f16c50f987ee21f'
def test_method_checksum(self):
h = hashlib.sha1()
for i in range(0x10000):
char = chr(i)
data = [
# Predicates (single char)
"01"[char.isalnum()],
"01"[char.isalpha()],
"01"[char.isdecimal()],
"01"[char.isdigit()],
"01"[char.islower()],
"01"[char.isnumeric()],
"01"[char.isspace()],
"01"[char.istitle()],
"01"[char.isupper()],
# Predicates (multiple chars)
"01"[(char + 'abc').isalnum()],
"01"[(char + 'abc').isalpha()],
"01"[(char + '123').isdecimal()],
"01"[(char + '123').isdigit()],
"01"[(char + 'abc').islower()],
"01"[(char + '123').isnumeric()],
"01"[(char + ' \t').isspace()],
"01"[(char + 'abc').istitle()],
"01"[(char + 'ABC').isupper()],
# Mappings (single char)
char.lower(),
char.upper(),
char.title(),
# Mappings (multiple chars)
(char + 'abc').lower(),
(char + 'ABC').upper(),
(char + 'abc').title(),
(char + 'ABC').title(),
]
h.update(''.join(data).encode(encoding, errors))
result = h.hexdigest()
self.assertEqual(result, self.expectedchecksum)
class UnicodeDatabaseTest(unittest.TestCase):
def setUp(self):
# In case unicodedata is not available, this will raise an ImportError,
# but the other test cases will still be run
import unicodedata
self.db = unicodedata
def tearDown(self):
del self.db
class UnicodeFunctionsTest(UnicodeDatabaseTest):
# Update this if the database changes. Make sure to do a full rebuild
# (e.g. 'make distclean && make') to get the correct checksum.
expectedchecksum = '585302895deead0c1c8478c51da9241d4efedca9'
def test_function_checksum(self):
data = []
h = hashlib.sha1()
for i in range(0x10000):
char = chr(i)
data = [
# Properties
format(self.db.digit(char, -1), '.12g'),
format(self.db.numeric(char, -1), '.12g'),
format(self.db.decimal(char, -1), '.12g'),
self.db.category(char),
self.db.bidirectional(char),
self.db.decomposition(char),
str(self.db.mirrored(char)),
str(self.db.combining(char)),
]
h.update(''.join(data).encode("ascii"))
result = h.hexdigest()
self.assertEqual(result, self.expectedchecksum)
def test_digit(self):
self.assertEqual(self.db.digit('A', None), None)
self.assertEqual(self.db.digit('9'), 9)
self.assertEqual(self.db.digit('\u215b', None), None)
self.assertEqual(self.db.digit('\u2468'), 9)
self.assertEqual(self.db.digit('\U00020000', None), None)
self.assertEqual(self.db.digit('\U0001D7FD'), 7)
self.assertRaises(TypeError, self.db.digit)
self.assertRaises(TypeError, self.db.digit, 'xx')
self.assertRaises(ValueError, self.db.digit, 'x')
def test_numeric(self):
self.assertEqual(self.db.numeric('A',None), None)
self.assertEqual(self.db.numeric('9'), 9)
self.assertEqual(self.db.numeric('\u215b'), 0.125)
self.assertEqual(self.db.numeric('\u2468'), 9.0)
self.assertEqual(self.db.numeric('\ua627'), 7.0)
self.assertEqual(self.db.numeric('\U00020000', None), None)
self.assertEqual(self.db.numeric('\U0001012A'), 9000)
self.assertRaises(TypeError, self.db.numeric)
self.assertRaises(TypeError, self.db.numeric, 'xx')
self.assertRaises(ValueError, self.db.numeric, 'x')
def test_decimal(self):
self.assertEqual(self.db.decimal('A',None), None)
self.assertEqual(self.db.decimal('9'), 9)
self.assertEqual(self.db.decimal('\u215b', None), None)
self.assertEqual(self.db.decimal('\u2468', None), None)
self.assertEqual(self.db.decimal('\U00020000', None), None)
self.assertEqual(self.db.decimal('\U0001D7FD'), 7)
self.assertRaises(TypeError, self.db.decimal)
self.assertRaises(TypeError, self.db.decimal, 'xx')
self.assertRaises(ValueError, self.db.decimal, 'x')
def test_category(self):
self.assertEqual(self.db.category('\uFFFE'), 'Cn')
self.assertEqual(self.db.category('a'), 'Ll')
self.assertEqual(self.db.category('A'), 'Lu')
self.assertEqual(self.db.category('\U00020000'), 'Lo')
self.assertEqual(self.db.category('\U0001012A'), 'No')
self.assertRaises(TypeError, self.db.category)
self.assertRaises(TypeError, self.db.category, 'xx')
def test_bidirectional(self):
self.assertEqual(self.db.bidirectional('\uFFFE'), '')
self.assertEqual(self.db.bidirectional(' '), 'WS')
self.assertEqual(self.db.bidirectional('A'), 'L')
self.assertEqual(self.db.bidirectional('\U00020000'), 'L')
self.assertRaises(TypeError, self.db.bidirectional)
self.assertRaises(TypeError, self.db.bidirectional, 'xx')
def test_decomposition(self):
self.assertEqual(self.db.decomposition('\uFFFE'),'')
self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034')
self.assertRaises(TypeError, self.db.decomposition)
self.assertRaises(TypeError, self.db.decomposition, 'xx')
def test_mirrored(self):
self.assertEqual(self.db.mirrored('\uFFFE'), 0)
self.assertEqual(self.db.mirrored('a'), 0)
self.assertEqual(self.db.mirrored('\u2201'), 1)
self.assertEqual(self.db.mirrored('\U00020000'), 0)
self.assertRaises(TypeError, self.db.mirrored)
self.assertRaises(TypeError, self.db.mirrored, 'xx')
def test_combining(self):
self.assertEqual(self.db.combining('\uFFFE'), 0)
self.assertEqual(self.db.combining('a'), 0)
self.assertEqual(self.db.combining('\u20e1'), 230)
self.assertEqual(self.db.combining('\U00020000'), 0)
self.assertRaises(TypeError, self.db.combining)
self.assertRaises(TypeError, self.db.combining, 'xx')
def test_normalize(self):
self.assertRaises(TypeError, self.db.normalize)
self.assertRaises(ValueError, self.db.normalize, 'unknown', 'xx')
self.assertEqual(self.db.normalize('NFKC', ''), '')
# The rest can be found in test_normalization.py
# which requires an external file.
def test_pr29(self):
# http://www.unicode.org/review/pr-29.html
# See issues #1054943 and #10254.
composed = ("\u0b47\u0300\u0b3e", "\u1100\u0300\u1161",
'Li\u030dt-s\u1e73\u0301',
'\u092e\u093e\u0930\u094d\u0915 \u091c\u093c'
+ '\u0941\u0915\u0947\u0930\u092c\u0930\u094d\u0917',
'\u0915\u093f\u0930\u094d\u0917\u093f\u091c\u093c'
+ '\u0938\u094d\u0924\u093e\u0928')
for text in composed:
self.assertEqual(self.db.normalize('NFC', text), text)
def test_issue10254(self):
# Crash reported in #10254
a = 'C\u0338' * 20 + 'C\u0327'
b = 'C\u0338' * 20 + '\xC7'
self.assertEqual(self.db.normalize('NFC', a), b)
def test_east_asian_width(self):
eaw = self.db.east_asian_width
self.assertRaises(TypeError, eaw, b'a')
self.assertRaises(TypeError, eaw, bytearray())
self.assertRaises(TypeError, eaw, '')
self.assertRaises(TypeError, eaw, 'ra')
self.assertEqual(eaw('\x1e'), 'N')
self.assertEqual(eaw('\x20'), 'Na')
self.assertEqual(eaw('\uC894'), 'W')
self.assertEqual(eaw('\uFF66'), 'H')
self.assertEqual(eaw('\uFF1F'), 'F')
self.assertEqual(eaw('\u2010'), 'A')
self.assertEqual(eaw('\U00020000'), 'W')
class UnicodeMiscTest(UnicodeDatabaseTest):
def test_failed_import_during_compiling(self):
# Issue 4367
# Decoding \N escapes requires the unicodedata module. If it can't be
# imported, we shouldn't segfault.
# This program should raise a SyntaxError in the eval.
code = "import sys;" \
"sys.modules['unicodedata'] = None;" \
"""eval("'\\\\N{SOFT HYPHEN}'")"""
args = [sys.executable, "-c", code]
# We use a subprocess because the unicodedata module may already have
# been loaded in this process.
popen = subprocess.Popen(args, stderr=subprocess.PIPE)
popen.wait()
self.assertEqual(popen.returncode, 1)
error = "SyntaxError: (unicode error) \\N escapes not supported " \
"(can't load unicodedata module)"
self.assertIn(error, popen.stderr.read().decode("ascii"))
popen.stderr.close()
def test_decimal_numeric_consistent(self):
# Test that decimal and numeric are consistent,
# i.e. if a character has a decimal value,
# its numeric value should be the same.
count = 0
for i in range(0x10000):
c = chr(i)
dec = self.db.decimal(c, -1)
if dec != -1:
self.assertEqual(dec, self.db.numeric(c))
count += 1
self.assertTrue(count >= 10) # should have tested at least the ASCII digits
def test_digit_numeric_consistent(self):
# Test that digit and numeric are consistent,
# i.e. if a character has a digit value,
# its numeric value should be the same.
count = 0
for i in range(0x10000):
c = chr(i)
dec = self.db.digit(c, -1)
if dec != -1:
self.assertEqual(dec, self.db.numeric(c))
count += 1
self.assertTrue(count >= 10) # should have tested at least the ASCII digits
def test_bug_1704793(self):
self.assertEqual(self.db.lookup("GOTHIC LETTER FAIHU"), '\U00010346')
def test_ucd_510(self):
import unicodedata
# In UCD 5.1.0, a mirrored property changed wrt. UCD 3.2.0
self.assertTrue(unicodedata.mirrored("\u0f3a"))
self.assertTrue(not unicodedata.ucd_3_2_0.mirrored("\u0f3a"))
# Also, we now have two ways of representing
# the upper-case mapping: as delta, or as absolute value
self.assertTrue("a".upper()=='A')
self.assertTrue("\u1d79".upper()=='\ua77d')
self.assertTrue(".".upper()=='.')
def test_bug_5828(self):
self.assertEqual("\u1d79".lower(), "\u1d79")
# Only U+0000 should have U+0000 as its upper/lower/titlecase variant
self.assertEqual(
[
c for c in range(sys.maxunicode+1)
if "\x00" in chr(c).lower()+chr(c).upper()+chr(c).title()
],
[0]
)
def test_bug_4971(self):
# LETTER DZ WITH CARON: DZ, Dz, dz
self.assertEqual("\u01c4".title(), "\u01c5")
self.assertEqual("\u01c5".title(), "\u01c5")
self.assertEqual("\u01c6".title(), "\u01c5")
def test_linebreak_7643(self):
for i in range(0x10000):
lines = (chr(i) + 'A').splitlines()
if i in (0x0a, 0x0b, 0x0c, 0x0d, 0x85,
0x1c, 0x1d, 0x1e, 0x2028, 0x2029):
self.assertEqual(len(lines), 2,
r"\u%.4x should be a linebreak" % i)
else:
self.assertEqual(len(lines), 1,
r"\u%.4x should not be a linebreak" % i)
if __name__ == "__main__":
unittest.main()
|
