Mercurial > cpython-lru_cache-weakref

annotate Lib/test/test_unicodedata.py @ 79675:c0a2294de787 2.7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Issue #16199: Backport 2to3 typo fix from 3.2.
author Chris Jerdonek <chris.jerdonek@gmail.com>
date Thu, 11 Oct 2012 16:15:46 -0700
parents b36cb4602e21
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
1 """ Test script for the unicodedata module.
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
2
14875
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
3 Written by Marc-Andre Lemburg (mal@lemburg.com).
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
4
14875
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
5 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
6
49796
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
7 """
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
8
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
9 import sys
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
10 import unittest
38052
32a187f3d5ba In stdlib, use hashlib instead of deprecated md5 and sha modules.
Georg Brandl <georg@python.org>
parents: 36924
diff changeset
11 import hashlib
49796
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
12 import subprocess
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
13 import test.test_support
14875
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
14
14896
ad98c136475e Fixed encoding to use an endianness independent format.
Marc-André Lemburg <mal@egenix.com>
parents: 14875
diff changeset
15 encoding = 'utf-8'
ad98c136475e Fixed encoding to use an endianness independent format.
Marc-André Lemburg <mal@egenix.com>
parents: 14875
diff changeset
16
14875
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
17
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
18 ### Run tests
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
19
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
20 class UnicodeMethodsTest(unittest.TestCase):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
21
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
22 # update this, if the database changes
59693
344cb6a4ef7d Issue #8024: Update the Unicode database to 5.2
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59323
diff changeset
23 expectedchecksum = '4504dffd035baea02c5b9de82bebc3d65e0e0baf'
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
24
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
25 def test_method_checksum(self):
38052
32a187f3d5ba In stdlib, use hashlib instead of deprecated md5 and sha modules.
Georg Brandl <georg@python.org>
parents: 36924
diff changeset
26 h = hashlib.sha1()
60074
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
27 for i in range(0x10000):
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
28 char = unichr(i)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
29 data = [
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
30 # Predicates (single char)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
31 u"01"[char.isalnum()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
32 u"01"[char.isalpha()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
33 u"01"[char.isdecimal()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
34 u"01"[char.isdigit()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
35 u"01"[char.islower()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
36 u"01"[char.isnumeric()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
37 u"01"[char.isspace()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
38 u"01"[char.istitle()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
39 u"01"[char.isupper()],
14875
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously
Marc-André Lemburg <mal@egenix.com>
parents: 12074
diff changeset
40
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
41 # Predicates (multiple chars)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
42 u"01"[(char + u'abc').isalnum()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
43 u"01"[(char + u'abc').isalpha()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
44 u"01"[(char + u'123').isdecimal()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
45 u"01"[(char + u'123').isdigit()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
46 u"01"[(char + u'abc').islower()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
47 u"01"[(char + u'123').isnumeric()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
48 u"01"[(char + u' \t').isspace()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
49 u"01"[(char + u'abc').istitle()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
50 u"01"[(char + u'ABC').isupper()],
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
51
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
52 # Mappings (single char)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
53 char.lower(),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
54 char.upper(),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
55 char.title(),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
56
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
57 # Mappings (multiple chars)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
58 (char + u'abc').lower(),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
59 (char + u'ABC').upper(),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
60 (char + u'abc').title(),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
61 (char + u'ABC').title(),
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
62
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
63 ]
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
64 h.update(u''.join(data).encode(encoding))
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
65 result = h.hexdigest()
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
66 self.assertEqual(result, self.expectedchecksum)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
67
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
68 class UnicodeDatabaseTest(unittest.TestCase):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
69
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
70 def setUp(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
71 # In case unicodedata is not available, this will raise an ImportError,
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
72 # but the other test cases will still be run
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
73 import unicodedata
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
74 self.db = unicodedata
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
75
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
76 def tearDown(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
77 del self.db
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
78
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
79 class UnicodeFunctionsTest(UnicodeDatabaseTest):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
80
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
81 # update this, if the database changes
59693
344cb6a4ef7d Issue #8024: Update the Unicode database to 5.2
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59323
diff changeset
82 expectedchecksum = '6ccf1b1a36460d2694f9b0b0f0324942fe70ede6'
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
83
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
84 def test_function_checksum(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
85 data = []
38052
32a187f3d5ba In stdlib, use hashlib instead of deprecated md5 and sha modules.
Georg Brandl <georg@python.org>
parents: 36924
diff changeset
86 h = hashlib.sha1()
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
87
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
88 for i in range(0x10000):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
89 char = unichr(i)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
90 data = [
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
91 # Properties
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
92 str(self.db.digit(char, -1)),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
93 str(self.db.numeric(char, -1)),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
94 str(self.db.decimal(char, -1)),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
95 self.db.category(char),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
96 self.db.bidirectional(char),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
97 self.db.decomposition(char),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
98 str(self.db.mirrored(char)),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
99 str(self.db.combining(char)),
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
100 ]
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
101 h.update(''.join(data))
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
102 result = h.hexdigest()
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
103 self.assertEqual(result, self.expectedchecksum)
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
104
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
105 def test_digit(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
106 self.assertEqual(self.db.digit(u'A', None), None)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
107 self.assertEqual(self.db.digit(u'9'), 9)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
108 self.assertEqual(self.db.digit(u'\u215b', None), None)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
109 self.assertEqual(self.db.digit(u'\u2468'), 9)
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
110 self.assertEqual(self.db.digit(u'\U00020000', None), None)
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
111
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
112 self.assertRaises(TypeError, self.db.digit)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
113 self.assertRaises(TypeError, self.db.digit, u'xx')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
114 self.assertRaises(ValueError, self.db.digit, u'x')
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
115
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
116 def test_numeric(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
117 self.assertEqual(self.db.numeric(u'A',None), None)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
118 self.assertEqual(self.db.numeric(u'9'), 9)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
119 self.assertEqual(self.db.numeric(u'\u215b'), 0.125)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
120 self.assertEqual(self.db.numeric(u'\u2468'), 9.0)
56406
a9864417286b #1571184: makeunicodedata.py now generates the functions _PyUnicode_ToNumeric,
Amaury Forgeot d'Arc <amauryfa@gmail.com>
parents: 55002
diff changeset
121 self.assertEqual(self.db.numeric(u'\ua627'), 7.0)
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
122 self.assertEqual(self.db.numeric(u'\U00020000', None), None)
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
123
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
124 self.assertRaises(TypeError, self.db.numeric)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
125 self.assertRaises(TypeError, self.db.numeric, u'xx')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
126 self.assertRaises(ValueError, self.db.numeric, u'x')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
127
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
128 def test_decimal(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
129 self.assertEqual(self.db.decimal(u'A',None), None)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
130 self.assertEqual(self.db.decimal(u'9'), 9)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
131 self.assertEqual(self.db.decimal(u'\u215b', None), None)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
132 self.assertEqual(self.db.decimal(u'\u2468', None), None)
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
133 self.assertEqual(self.db.decimal(u'\U00020000', None), None)
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
134
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
135 self.assertRaises(TypeError, self.db.decimal)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
136 self.assertRaises(TypeError, self.db.decimal, u'xx')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
137 self.assertRaises(ValueError, self.db.decimal, u'x')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
138
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
139 def test_category(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
140 self.assertEqual(self.db.category(u'\uFFFE'), 'Cn')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
141 self.assertEqual(self.db.category(u'a'), 'Ll')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
142 self.assertEqual(self.db.category(u'A'), 'Lu')
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
143 self.assertEqual(self.db.category(u'\U00020000'), 'Lo')
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
144
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
145 self.assertRaises(TypeError, self.db.category)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
146 self.assertRaises(TypeError, self.db.category, u'xx')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
147
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
148 def test_bidirectional(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
149 self.assertEqual(self.db.bidirectional(u'\uFFFE'), '')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
150 self.assertEqual(self.db.bidirectional(u' '), 'WS')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
151 self.assertEqual(self.db.bidirectional(u'A'), 'L')
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
152 self.assertEqual(self.db.bidirectional(u'\U00020000'), 'L')
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
153
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
154 self.assertRaises(TypeError, self.db.bidirectional)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
155 self.assertRaises(TypeError, self.db.bidirectional, u'xx')
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
156
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
157 def test_decomposition(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
158 self.assertEqual(self.db.decomposition(u'\uFFFE'),'')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
159 self.assertEqual(self.db.decomposition(u'\u00bc'), '<fraction> 0031 2044 0034')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
160
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
161 self.assertRaises(TypeError, self.db.decomposition)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
162 self.assertRaises(TypeError, self.db.decomposition, u'xx')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
163
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
164 def test_mirrored(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
165 self.assertEqual(self.db.mirrored(u'\uFFFE'), 0)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
166 self.assertEqual(self.db.mirrored(u'a'), 0)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
167 self.assertEqual(self.db.mirrored(u'\u2201'), 1)
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
168 self.assertEqual(self.db.mirrored(u'\U00020000'), 0)
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
169
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
170 self.assertRaises(TypeError, self.db.mirrored)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
171 self.assertRaises(TypeError, self.db.mirrored, u'xx')
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
172
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
173 def test_combining(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
174 self.assertEqual(self.db.combining(u'\uFFFE'), 0)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
175 self.assertEqual(self.db.combining(u'a'), 0)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
176 self.assertEqual(self.db.combining(u'\u20e1'), 230)
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
177 self.assertEqual(self.db.combining(u'\U00020000'), 0)
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
178
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
179 self.assertRaises(TypeError, self.db.combining)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
180 self.assertRaises(TypeError, self.db.combining, u'xx')
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
181
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
182 def test_normalize(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
183 self.assertRaises(TypeError, self.db.normalize)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
184 self.assertRaises(ValueError, self.db.normalize, 'unknown', u'xx')
31930
f8c0ac5bef02 Special case normalization of empty strings. Fixes #924361.
Martin v. Löwis <martin@v.loewis.de>
parents: 28917
diff changeset
185 self.assertEqual(self.db.normalize('NFKC', u''), u'')
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
186 # The rest can be found in test_normalization.py
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
187 # which requires an external file.
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
188
59819
8f1202ca888e Merged revisions 78646 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 53474
diff changeset
189 def test_pr29(self):
8f1202ca888e Merged revisions 78646 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 53474
diff changeset
190 # http://www.unicode.org/review/pr-29.html
67190
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
191 # See issues #1054943 and #10254.
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
192 composed = (u"\u0b47\u0300\u0b3e", u"\u1100\u0300\u1161",
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
193 u'Li\u030dt-s\u1e73\u0301',
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
194 u'\u092e\u093e\u0930\u094d\u0915 \u091c\u093c'
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
195 + u'\u0941\u0915\u0947\u0930\u092c\u0930\u094d\u0917',
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
196 u'\u0915\u093f\u0930\u094d\u0917\u093f\u091c\u093c'
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
197 + 'u\u0938\u094d\u0924\u093e\u0928')
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
198 for text in composed:
59819
8f1202ca888e Merged revisions 78646 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 53474
diff changeset
199 self.assertEqual(self.db.normalize('NFC', text), text)
8f1202ca888e Merged revisions 78646 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 53474
diff changeset
200
67190
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
201 def test_issue10254(self):
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
202 # Crash reported in #10254
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
203 a = u'C\u0338' * 20 + u'C\u0327'
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
204 b = u'C\u0338' * 20 + u'\xC7'
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
205 self.assertEqual(self.db.normalize('NFC', a), b)
52a861746129 Merged revisions 87541,87543 via svnmerge from
Alexander Belopolsky <alexander.belopolsky@gmail.com>
parents: 59819
diff changeset
206
32951
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
207 def test_east_asian_width(self):
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
208 eaw = self.db.east_asian_width
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
209 self.assertRaises(TypeError, eaw, 'a')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
210 self.assertRaises(TypeError, eaw, u'')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
211 self.assertRaises(TypeError, eaw, u'ra')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
212 self.assertEqual(eaw(u'\x1e'), 'N')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
213 self.assertEqual(eaw(u'\x20'), 'Na')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
214 self.assertEqual(eaw(u'\uC894'), 'W')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
215 self.assertEqual(eaw(u'\uFF66'), 'H')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
216 self.assertEqual(eaw(u'\uFF1F'), 'F')
024ff0ab4588 SF #989185: Drop unicode.iswide() and unicode.width() and add
Hye-Shik Chang <hyeshik@gmail.com>
parents: 31930
diff changeset
217 self.assertEqual(eaw(u'\u2010'), 'A')
47451
ed471a8009a6 Change all functions that expect one unicode character to accept a pair of
Walter Dörwald <walter@livinglogic.de>
parents: 42387
diff changeset
218 self.assertEqual(eaw(u'\U00020000'), 'W')
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
219
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
220 class UnicodeMiscTest(UnicodeDatabaseTest):
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
221
49796
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
222 def test_failed_import_during_compiling(self):
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
223 # Issue 4367
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
224 # Decoding \N escapes requires the unicodedata module. If it can't be
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
225 # imported, we shouldn't segfault.
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
226
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
227 # This program should raise a SyntaxError in the eval.
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
228 code = "import sys;" \
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
229 "sys.modules['unicodedata'] = None;" \
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
230 """eval("u'\N{SOFT HYPHEN}'")"""
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
231 args = [sys.executable, "-c", code]
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
232 # We use a subprocess because the unicodedata module may already have
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
233 # been loaded in this process.
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
234 popen = subprocess.Popen(args, stderr=subprocess.PIPE)
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
235 popen.wait()
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
236 self.assertEqual(popen.returncode, 1)
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
237 error = "SyntaxError: (unicode error) \N escapes not supported " \
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
238 "(can't load unicodedata module)"
58460
17891566a478 use assert[Not]In where appropriate
Ezio Melotti <ezio.melotti@gmail.com>
parents: 56406
diff changeset
239 self.assertIn(error, popen.stderr.read())
49796
0bcafa64eccb Merged revisions 67320 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents: 49124
diff changeset
240
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
241 def test_decimal_numeric_consistent(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
242 # Test that decimal and numeric are consistent,
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
243 # i.e. if a character has a decimal value,
35276
4adbd331d335 Fix all wrong instances of "it's".
Georg Brandl <georg@python.org>
parents: 32951
diff changeset
244 # its numeric value should be the same.
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
245 count = 0
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
246 for i in xrange(0x10000):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
247 c = unichr(i)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
248 dec = self.db.decimal(c, -1)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
249 if dec != -1:
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
250 self.assertEqual(dec, self.db.numeric(c))
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
251 count += 1
55002
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
252 self.assertTrue(count >= 10) # should have tested at least the ASCII digits
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
253
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
254 def test_digit_numeric_consistent(self):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
255 # Test that digit and numeric are consistent,
28231
4cafa5141012 Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 28075
diff changeset
256 # i.e. if a character has a digit value,
35276
4adbd331d335 Fix all wrong instances of "it's".
Georg Brandl <georg@python.org>
parents: 32951
diff changeset
257 # its numeric value should be the same.
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
258 count = 0
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
259 for i in xrange(0x10000):
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
260 c = unichr(i)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
261 dec = self.db.digit(c, -1)
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
262 if dec != -1:
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
263 self.assertEqual(dec, self.db.numeric(c))
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
264 count += 1
55002
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
265 self.assertTrue(count >= 10) # should have tested at least the ASCII digits
12074
65f35b73e350 Marc-Andre Lemburg:
Guido van Rossum <guido@python.org>
parents:
diff changeset
266
42386
7e7dce3089e3 Bug #1704793: Raise KeyError if unicodedata.lookup cannot
Martin v. Löwis <martin@v.loewis.de>
parents: 38422
diff changeset
267 def test_bug_1704793(self):
66348
614c84670c63 Merged revisions 86596 via svnmerge from
Ezio Melotti <ezio.melotti@gmail.com>
parents: 60074
diff changeset
268 self.assertEqual(self.db.lookup("GOTHIC LETTER FAIHU"), u'\U00010346')
42387
85b7f40e1c1c Bug #1704793: Return UTF-16 pair if unicodedata.lookup cannot
Martin v. Löwis <martin@v.loewis.de>
parents: 38422
diff changeset
269
49124
c37c7dbd7880 Issue #3811: The Unicode database was updated to 5.1.
Martin v. Löwis <martin@v.loewis.de>
parents: 47451
diff changeset
270 def test_ucd_510(self):
c37c7dbd7880 Issue #3811: The Unicode database was updated to 5.1.
Martin v. Löwis <martin@v.loewis.de>
parents: 47451
diff changeset
271 import unicodedata
c37c7dbd7880 Issue #3811: The Unicode database was updated to 5.1.
Martin v. Löwis <martin@v.loewis.de>
parents: 47451
diff changeset
272 # In UCD 5.1.0, a mirrored property changed wrt. UCD 3.2.0
55002
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
273 self.assertTrue(unicodedata.mirrored(u"\u0f3a"))
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
274 self.assertTrue(not unicodedata.ucd_3_2_0.mirrored(u"\u0f3a"))
49124
c37c7dbd7880 Issue #3811: The Unicode database was updated to 5.1.
Martin v. Löwis <martin@v.loewis.de>
parents: 47451
diff changeset
275 # Also, we now have two ways of representing
c37c7dbd7880 Issue #3811: The Unicode database was updated to 5.1.
Martin v. Löwis <martin@v.loewis.de>
parents: 47451
diff changeset
276 # the upper-case mapping: as delta, or as absolute value
55002
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
277 self.assertTrue(u"a".upper()==u'A')
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
278 self.assertTrue(u"\u1d79".upper()==u'\ua77d')
6768b2350c57 convert usage of fail* to assert*
Benjamin Peterson <benjamin@python.org>
parents: 53474
diff changeset
279 self.assertTrue(u".".upper()==u".")
53400
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
280
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
281 def test_bug_5828(self):
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
282 self.assertEqual(u"\u1d79".lower(), u"\u1d79")
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
283 # Only U+0000 should have U+0000 as its upper/lower/titlecase variant
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
284 self.assertEqual(
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
285 [
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
286 c for c in range(sys.maxunicode+1)
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
287 if u"\x00" in unichr(c).lower()+unichr(c).upper()+unichr(c).title()
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
288 ],
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
289 [0]
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
290 )
f08f776082ec Merged revisions 71894 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 49796
diff changeset
291
53474
355beb0bd02b Merged revisions 71972 via svnmerge from
Walter Dörwald <walter@livinglogic.de>
parents: 53450
diff changeset
292 def test_bug_4971(self):
53450
c92e93a54298 Merged revisions 71947 via svnmerge from
Martin v. Löwis <martin@v.loewis.de>
parents: 53400
diff changeset
293 # LETTER DZ WITH CARON: DZ, Dz, dz
c92e93a54298 Merged revisions 71947 via svnmerge from
Martin v. Löwis <martin@v.loewis.de>
parents: 53400
diff changeset
294 self.assertEqual(u"\u01c4".title(), u"\u01c5")
c92e93a54298 Merged revisions 71947 via svnmerge from
Martin v. Löwis <martin@v.loewis.de>
parents: 53400
diff changeset
295 self.assertEqual(u"\u01c5".title(), u"\u01c5")
c92e93a54298 Merged revisions 71947 via svnmerge from
Martin v. Löwis <martin@v.loewis.de>
parents: 53400
diff changeset
296 self.assertEqual(u"\u01c6".title(), u"\u01c5")
42386
7e7dce3089e3 Bug #1704793: Raise KeyError if unicodedata.lookup cannot
Martin v. Löwis <martin@v.loewis.de>
parents: 38422
diff changeset
297
60074
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
298 def test_linebreak_7643(self):
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
299 for i in range(0x10000):
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
300 lines = (unichr(i) + u'A').splitlines()
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
301 if i in (0x0a, 0x0b, 0x0c, 0x0d, 0x85,
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
302 0x1c, 0x1d, 0x1e, 0x2028, 0x2029):
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
303 self.assertEqual(len(lines), 2,
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
304 r"\u%.4x should be a linebreak" % i)
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
305 else:
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
306 self.assertEqual(len(lines), 1,
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
307 r"\u%.4x should not be a linebreak" % i)
66e757d8ea93 #7643: Unicode codepoints VT (0x0B) and FF (0x0C) are linebreaks according to Unicode Standard Annex #14.
Florent Xicluna <florent.xicluna@gmail.com>
parents: 59693
diff changeset
308
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
309 def test_main():
28917
1741af48fd9f Combine the functionality of test_support.run_unittest()
Walter Dörwald <walter@livinglogic.de>
parents: 28231
diff changeset
310 test.test_support.run_unittest(
1741af48fd9f Combine the functionality of test_support.run_unittest()
Walter Dörwald <walter@livinglogic.de>
parents: 28231
diff changeset
311 UnicodeMiscTest,
1741af48fd9f Combine the functionality of test_support.run_unittest()
Walter Dörwald <walter@livinglogic.de>
parents: 28231
diff changeset
312 UnicodeMethodsTest,
1741af48fd9f Combine the functionality of test_support.run_unittest()
Walter Dörwald <walter@livinglogic.de>
parents: 28231
diff changeset
313 UnicodeFunctionsTest
1741af48fd9f Combine the functionality of test_support.run_unittest()
Walter Dörwald <walter@livinglogic.de>
parents: 28231
diff changeset
314 )
28075
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
315
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
316 if __name__ == "__main__":
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error
Walter Dörwald <walter@livinglogic.de>
parents: 24364
diff changeset
317 test_main()