cpython-lru_cache-weakref: Lib/test/test

annotate Lib/test/test_unicodedata.py @ 78069:a8aa77458e12 3.2

Add c_size_t and c_ssize_t to the ctypes summary table.

author	Antoine Pitrou <solipsis@pitrou.net>
date	Thu, 12 Jul 2012 20:31:50 +0200
parents	3c9232a684ae
children	9f41acdb3150

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
49797 f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	7 """
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	8
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	9 import sys
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	10 import unittest
38453 29ae5e0fc348 Much-needed merge (using svnmerge.py this time) of trunk changes into p3yk. Thomas Wouters <thomas@python.org> parents: 36924 diff changeset	11 import hashlib
49797 f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	12 import subprocess
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	13 import 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'
53967 41c09e142bd0 Rename the surrogates handler to surrogatepass. Martin v. Löwis <martin@v.loewis.de> parents: 53681 diff changeset	16 errors = 'surrogatepass'
14896 ad98c136475e Fixed encoding to use an endianness independent format. Marc-André Lemburg <mal@egenix.com> parents: 14875 diff changeset	17
14875 17b5c43c08a6 Added test suite for the complete Unicode database. The test previously Marc-André Lemburg <mal@egenix.com> parents: 12074 diff changeset	18
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously Marc-André Lemburg <mal@egenix.com> parents: 12074 diff changeset	19 ### Run tests
17b5c43c08a6 Added test suite for the complete Unicode database. The test previously Marc-André Lemburg <mal@egenix.com> parents: 12074 diff changeset	20
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	21 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	22
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error Walter Dörwald <walter@livinglogic.de> parents: 24364 diff changeset	23 # update this, if the database changes
65217 cbde81ef4af7 Upgrade to Unicode 6.0.0. Martin v. Löwis <martin@v.loewis.de> parents: 64153 diff changeset	24 expectedchecksum = '21b90f1aed00081b81ca7942b22196af090015a0'
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	25
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error Walter Dörwald <walter@livinglogic.de> parents: 24364 diff changeset	26 def test_method_checksum(self):
38453 29ae5e0fc348 Much-needed merge (using svnmerge.py this time) of trunk changes into p3yk. Thomas Wouters <thomas@python.org> parents: 36924 diff changeset	27 h = hashlib.sha1()
60086 bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	28 for i in range(0x10000):
41585 825d966338ea Rename 'unicode' to 'str' in its tp_name field. Rename 'str' to 'str8'. Guido van Rossum <guido@python.org> parents: 41575 diff changeset	29 char = chr(i)
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	30 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	31 # Predicates (single char)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	32 "01"[char.isalnum()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	33 "01"[char.isalpha()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	34 "01"[char.isdecimal()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	35 "01"[char.isdigit()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	36 "01"[char.islower()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	37 "01"[char.isnumeric()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	38 "01"[char.isspace()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	39 "01"[char.istitle()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	40 "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	41
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	42 # Predicates (multiple chars)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	43 "01"[(char + 'abc').isalnum()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	44 "01"[(char + 'abc').isalpha()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	45 "01"[(char + '123').isdecimal()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	46 "01"[(char + '123').isdigit()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	47 "01"[(char + 'abc').islower()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	48 "01"[(char + '123').isnumeric()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	49 "01"[(char + ' \t').isspace()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	50 "01"[(char + 'abc').istitle()],
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	51 "01"[(char + 'ABC').isupper()],
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	52
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 # 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	54 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	55 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	56 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	57
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 # Mappings (multiple chars)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	59 (char + 'abc').lower(),
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	60 (char + 'ABC').upper(),
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	61 (char + 'abc').title(),
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	62 (char + 'ABC').title(),
12074 65f35b73e350 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: diff changeset	63
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	64 ]
53681 52a77ef069cd Issue #3672: Reject surrogates in utf-8 codec; add surrogates error Martin v. Löwis <martin@v.loewis.de> parents: 53476 diff changeset	65 h.update(''.join(data).encode(encoding, errors))
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	66 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	67 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	68
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 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	70
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 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	72 # 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	73 # 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	74 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	75 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	76
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 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	78 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	79
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 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	81
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error Walter Dörwald <walter@livinglogic.de> parents: 24364 diff changeset	82 # update this, if the database changes
65217 cbde81ef4af7 Upgrade to Unicode 6.0.0. Martin v. Löwis <martin@v.loewis.de> parents: 64153 diff changeset	83 expectedchecksum = 'c23dfc0b5eaf3ca2aad32d733de96bb182ccda50'
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	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 = []
38453 29ae5e0fc348 Much-needed merge (using svnmerge.py this time) of trunk changes into p3yk. Thomas Wouters <thomas@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):
41585 825d966338ea Rename 'unicode' to 'str' in its tp_name field. Rename 'str' to 'str8'. Guido van Rossum <guido@python.org> parents: 41575 diff changeset	89 char = chr(i)
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	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
63750 eafe07d40eb7 Issue #9337: Make float.__str__ identical to float.__repr__. Mark Dickinson <dickinsm@gmail.com> parents: 60086 diff changeset	92 format(self.db.digit(char, -1), '.12g'),
eafe07d40eb7 Issue #9337: Make float.__str__ identical to float.__repr__. Mark Dickinson <dickinsm@gmail.com> parents: 60086 diff changeset	93 format(self.db.numeric(char, -1), '.12g'),
eafe07d40eb7 Issue #9337: Make float.__str__ identical to float.__repr__. Mark Dickinson <dickinsm@gmail.com> parents: 60086 diff changeset	94 format(self.db.decimal(char, -1), '.12g'),
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	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 ]
42907 0170418dadea Changes in anticipation of stricter str vs. bytes enforcement. Guido van Rossum <guido@python.org> parents: 42466 diff changeset	101 h.update(''.join(data).encode("ascii"))
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	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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	106 self.assertEqual(self.db.digit('A', None), None)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	107 self.assertEqual(self.db.digit('9'), 9)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	108 self.assertEqual(self.db.digit('\u215b', None), None)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	109 self.assertEqual(self.db.digit('\u2468'), 9)
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	110 self.assertEqual(self.db.digit('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	113 self.assertRaises(TypeError, self.db.digit, 'xx')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	114 self.assertRaises(ValueError, self.db.digit, '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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	117 self.assertEqual(self.db.numeric('A',None), None)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	118 self.assertEqual(self.db.numeric('9'), 9)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	119 self.assertEqual(self.db.numeric('\u215b'), 0.125)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	120 self.assertEqual(self.db.numeric('\u2468'), 9.0)
56408 6c91d1803182 Merged revisions 75272-75273 via svnmerge from Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 55593 diff changeset	121 self.assertEqual(self.db.numeric('\ua627'), 7.0)
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	122 self.assertEqual(self.db.numeric('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	125 self.assertRaises(TypeError, self.db.numeric, 'xx')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	126 self.assertRaises(ValueError, self.db.numeric, 'x')
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	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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	129 self.assertEqual(self.db.decimal('A',None), None)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	130 self.assertEqual(self.db.decimal('9'), 9)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	131 self.assertEqual(self.db.decimal('\u215b', None), None)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	132 self.assertEqual(self.db.decimal('\u2468', None), None)
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	133 self.assertEqual(self.db.decimal('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	136 self.assertRaises(TypeError, self.db.decimal, 'xx')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	137 self.assertRaises(ValueError, self.db.decimal, 'x')
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	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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	140 self.assertEqual(self.db.category('\uFFFE'), 'Cn')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	141 self.assertEqual(self.db.category('a'), 'Ll')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	142 self.assertEqual(self.db.category('A'), 'Lu')
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	143 self.assertEqual(self.db.category('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	146 self.assertRaises(TypeError, self.db.category, 'xx')
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	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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	149 self.assertEqual(self.db.bidirectional('\uFFFE'), '')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	150 self.assertEqual(self.db.bidirectional(' '), 'WS')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	151 self.assertEqual(self.db.bidirectional('A'), 'L')
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	152 self.assertEqual(self.db.bidirectional('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	155 self.assertRaises(TypeError, self.db.bidirectional, '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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	158 self.assertEqual(self.db.decomposition('\uFFFE'),'')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	159 self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034')
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	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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	162 self.assertRaises(TypeError, self.db.decomposition, 'xx')
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	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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	165 self.assertEqual(self.db.mirrored('\uFFFE'), 0)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	166 self.assertEqual(self.db.mirrored('a'), 0)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	167 self.assertEqual(self.db.mirrored('\u2201'), 1)
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	168 self.assertEqual(self.db.mirrored('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	171 self.assertRaises(TypeError, self.db.mirrored, '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):
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	174 self.assertEqual(self.db.combining('\uFFFE'), 0)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	175 self.assertEqual(self.db.combining('a'), 0)
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	176 self.assertEqual(self.db.combining('\u20e1'), 230)
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	177 self.assertEqual(self.db.combining('\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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	180 self.assertRaises(TypeError, self.db.combining, 'xx')
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	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)
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	184 self.assertRaises(ValueError, self.db.normalize, 'unknown', 'xx')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	185 self.assertEqual(self.db.normalize('NFKC', ''), '')
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
59325 fd8fdd388963 Merged revisions 78647 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 55593 diff changeset	189 def test_pr29(self):
fd8fdd388963 Merged revisions 78647 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 55593 diff changeset	190 # http://www.unicode.org/review/pr-29.html
67184 a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	191 # See issues #1054943 and #10254.
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	192 composed = ("\u0b47\u0300\u0b3e", "\u1100\u0300\u1161",
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	193 'Li\u030dt-s\u1e73\u0301',
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	194 '\u092e\u093e\u0930\u094d\u0915 \u091c\u093c'
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	195 + '\u0941\u0915\u0947\u0930\u092c\u0930\u094d\u0917',
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	196 '\u0915\u093f\u0930\u094d\u0917\u093f\u091c\u093c'
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	197 + '\u0938\u094d\u0924\u093e\u0928')
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	198 for text in composed:
59325 fd8fdd388963 Merged revisions 78647 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 55593 diff changeset	199 self.assertEqual(self.db.normalize('NFC', text), text)
fd8fdd388963 Merged revisions 78647 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 55593 diff changeset	200
67184 a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	201 def test_issue10254(self):
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	202 # Crash reported in #10254
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	203 a = 'C\u0338' * 20 + 'C\u0327'
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	204 b = 'C\u0338' * 20 + '\xC7'
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 diff changeset	205 self.assertEqual(self.db.normalize('NFC', a), b)
a4ec20cc9066 Merged revisions 87442 via svnmerge from Alexander Belopolsky <alexander.belopolsky@gmail.com> parents: 66340 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
43777 0d462d789b18 Merging the py3k-pep3137 branch back into the py3k branch. Guido van Rossum <guido@python.org> parents: 43664 diff changeset	209 self.assertRaises(TypeError, eaw, b'a')
43947 cbc8b3bd3157 Rename buffer -> bytearray. Guido van Rossum <guido@python.org> parents: 43777 diff changeset	210 self.assertRaises(TypeError, eaw, bytearray())
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	211 self.assertRaises(TypeError, eaw, '')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	212 self.assertRaises(TypeError, eaw, 'ra')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	213 self.assertEqual(eaw('\x1e'), 'N')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	214 self.assertEqual(eaw('\x20'), 'Na')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	215 self.assertEqual(eaw('\uC894'), 'W')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	216 self.assertEqual(eaw('\uFF66'), 'H')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	217 self.assertEqual(eaw('\uFF1F'), 'F')
beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 38453 diff changeset	218 self.assertEqual(eaw('\u2010'), 'A')
47458 e4a186437440 Change all functions that expect one unicode character to accept a pair of Walter Dörwald <walter@livinglogic.de> parents: 47201 diff changeset	219 self.assertEqual(eaw('\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	220
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error Walter Dörwald <walter@livinglogic.de> parents: 24364 diff changeset	221 class UnicodeMiscTest(UnicodeDatabaseTest):
12074 65f35b73e350 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: diff changeset	222
49797 f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	223 def test_failed_import_during_compiling(self):
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	224 # Issue 4367
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	225 # Decoding \N escapes requires the unicodedata module. If it can't be
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	226 # imported, we shouldn't segfault.
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	227
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	228 # This program should raise a SyntaxError in the eval.
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	229 code = "import sys;" \
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	230 "sys.modules['unicodedata'] = None;" \
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	231 """eval("'\\\\N{SOFT HYPHEN}'")"""
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	232 args = [sys.executable, "-c", code]
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	233 # We use a subprocess because the unicodedata module may already have
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	234 # been loaded in this process.
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	235 popen = subprocess.Popen(args, stderr=subprocess.PIPE)
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	236 popen.wait()
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	237 self.assertEqual(popen.returncode, 1)
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	238 error = "SyntaxError: (unicode error) \\N escapes not supported " \
f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	239 "(can't load unicodedata module)"
58415 f6a626f34840 use assert[Not]In where appropriate Benjamin Peterson <benjamin@python.org> parents: 56408 diff changeset	240 self.assertIn(error, popen.stderr.read().decode("ascii"))
65760 ef6dad7517c5 Fix resource warning in test_unicodedata. Patch by Brian Brazil. Antoine Pitrou <solipsis@pitrou.net> parents: 65217 diff changeset	241 popen.stderr.close()
49797 f403d94157b2 Merged revisions 67320 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 49125 diff changeset	242
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	243 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	244 # 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	245 # 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	246 # 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	247 count = 0
41642 a6eb6acfe04a Merged revisions 55007-55179 via svnmerge from Guido van Rossum <guido@python.org> parents: 41585 diff changeset	248 for i in range(0x10000):
41585 825d966338ea Rename 'unicode' to 'str' in its tp_name field. Rename 'str' to 'str8'. Guido van Rossum <guido@python.org> parents: 41575 diff changeset	249 c = chr(i)
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	250 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	251 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	252 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	253 count += 1
55593 0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	254 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	255
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	256 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	257 # Test that digit and numeric are consistent,
28231 4cafa5141012 Whitespace normalization. Tim Peters <tim.peters@gmail.com> parents: 28075 diff changeset	258 # 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	259 # 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	260 count = 0
41642 a6eb6acfe04a Merged revisions 55007-55179 via svnmerge from Guido van Rossum <guido@python.org> parents: 41585 diff changeset	261 for i in range(0x10000):
41585 825d966338ea Rename 'unicode' to 'str' in its tp_name field. Rename 'str' to 'str8'. Guido van Rossum <guido@python.org> parents: 41575 diff changeset	262 c = chr(i)
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	263 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	264 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	265 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	266 count += 1
55593 0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	267 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	268
42466 3fc3cedc49ca Merged revisions 56753-56781 via svnmerge from Guido van Rossum <guido@python.org> parents: 41837 diff changeset	269 def test_bug_1704793(self):
66340 2beb25369289 Merged revisions 86596 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 59327 diff changeset	270 self.assertEqual(self.db.lookup("GOTHIC LETTER FAIHU"), '\U00010346')
42466 3fc3cedc49ca Merged revisions 56753-56781 via svnmerge from Guido van Rossum <guido@python.org> parents: 41837 diff changeset	271
49125 dc60293b29d5 Merged revisions 66362 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 47458 diff changeset	272 def test_ucd_510(self):
dc60293b29d5 Merged revisions 66362 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 47458 diff changeset	273 import unicodedata
dc60293b29d5 Merged revisions 66362 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 47458 diff changeset	274 # In UCD 5.1.0, a mirrored property changed wrt. UCD 3.2.0
55593 0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	275 self.assertTrue(unicodedata.mirrored("\u0f3a"))
0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	276 self.assertTrue(not unicodedata.ucd_3_2_0.mirrored("\u0f3a"))
49125 dc60293b29d5 Merged revisions 66362 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 47458 diff changeset	277 # Also, we now have two ways of representing
dc60293b29d5 Merged revisions 66362 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 47458 diff changeset	278 # the upper-case mapping: as delta, or as absolute value
55593 0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	279 self.assertTrue("a".upper()=='A')
0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	280 self.assertTrue("\u1d79".upper()=='\ua77d')
0bb232078b8c Merged revisions 73715 via svnmerge from Georg Brandl <georg@python.org> parents: 53967 diff changeset	281 self.assertTrue(".".upper()=='.')
53402 2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	282
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	283 def test_bug_5828(self):
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	284 self.assertEqual("\u1d79".lower(), "\u1d79")
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	285 # Only U+0000 should have U+0000 as its upper/lower/titlecase variant
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	286 self.assertEqual(
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	287 [
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	288 c for c in range(sys.maxunicode+1)
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	289 if "\x00" in chr(c).lower()+chr(c).upper()+chr(c).title()
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	290 ],
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	291 [0]
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	292 )
2f8e535f9a9b Merged revisions 71896 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 49797 diff changeset	293
53476 951a62b86de8 Merged revisions 71974 via svnmerge from Walter Dörwald <walter@livinglogic.de> parents: 53452 diff changeset	294 def test_bug_4971(self):
53452 912438655f93 Merged revisions 71949 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 53402 diff changeset	295 # LETTER DZ WITH CARON: DZ, Dz, dz
912438655f93 Merged revisions 71949 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 53402 diff changeset	296 self.assertEqual("\u01c4".title(), "\u01c5")
912438655f93 Merged revisions 71949 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 53402 diff changeset	297 self.assertEqual("\u01c5".title(), "\u01c5")
912438655f93 Merged revisions 71949 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 53402 diff changeset	298 self.assertEqual("\u01c6".title(), "\u01c5")
49125 dc60293b29d5 Merged revisions 66362 via svnmerge from Martin v. Löwis <martin@v.loewis.de> parents: 47458 diff changeset	299
60086 bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	300 def test_linebreak_7643(self):
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	301 for i in range(0x10000):
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	302 lines = (chr(i) + 'A').splitlines()
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	303 if i in (0x0a, 0x0b, 0x0c, 0x0d, 0x85,
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	304 0x1c, 0x1d, 0x1e, 0x2028, 0x2029):
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	305 self.assertEqual(len(lines), 2,
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	306 r"\u%.4x should be a linebreak" % i)
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	307 else:
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	308 self.assertEqual(len(lines), 1,
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	309 r"\u%.4x should not be a linebreak" % i)
bf3c48f2417c Merged revisions 79494,79496 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 59719 diff changeset	310
64146 8f97c64b2333 #5127: Even on narrow unicode builds, the C functions that access the Unicode Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 63750 diff changeset	311 def test_UCS4(self):
8f97c64b2333 #5127: Even on narrow unicode builds, the C functions that access the Unicode Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 63750 diff changeset	312 # unicodedata should work with code points outside the BMP
8f97c64b2333 #5127: Even on narrow unicode builds, the C functions that access the Unicode Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 63750 diff changeset	313 # even on a narrow Unicode build
64150 23a598c01911 Fix stupid typo in test. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 64146 diff changeset	314 self.assertEqual(self.db.category("\U0001012A"), "No")
23a598c01911 Fix stupid typo in test. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 64146 diff changeset	315 self.assertEqual(self.db.numeric("\U0001012A"), 9000)
64153 05a3dfda04ff Add more tests to unicodedata with large code points Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 64150 diff changeset	316 self.assertEqual(self.db.decimal("\U0001D7FD"), 7)
05a3dfda04ff Add more tests to unicodedata with large code points Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 64150 diff changeset	317 self.assertEqual(self.db.digit("\U0001D7FD"), 7)
64146 8f97c64b2333 #5127: Even on narrow unicode builds, the C functions that access the Unicode Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 63750 diff changeset	318
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	319 def test_main():
47201 9c930a32cebb #2621 rename test.test_support to test.support Benjamin Peterson <benjamin@python.org> parents: 43947 diff changeset	320 test.support.run_unittest(
28917 1741af48fd9f Combine the functionality of test_support.run_unittest() Walter Dörwald <walter@livinglogic.de> parents: 28231 diff changeset	321 UnicodeMiscTest,
1741af48fd9f Combine the functionality of test_support.run_unittest() Walter Dörwald <walter@livinglogic.de> parents: 28231 diff changeset	322 UnicodeMethodsTest,
1741af48fd9f Combine the functionality of test_support.run_unittest() Walter Dörwald <walter@livinglogic.de> parents: 28231 diff changeset	323 UnicodeFunctionsTest
1741af48fd9f Combine the functionality of test_support.run_unittest() Walter Dörwald <walter@livinglogic.de> parents: 28231 diff changeset	324 )
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	325
7fdcc4cfc759 Port test_ucn and test_unicodedata to PyUnit. Add a few tests for error Walter Dörwald <walter@livinglogic.de> parents: 24364 diff changeset	326 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	327 test_main()

Mercurial > cpython-lru_cache-weakref

annotate Lib/test/test_unicodedata.py @ 78069:a8aa77458e12 3.2