cpython-lru_cache-weakref: Lib/test/test

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

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	0cd197f13400
children	21fb1767e185

rev	line source
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	1 """ Test script for the Unicode implementation.
1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	2
1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	3 Written by Marc-Andre Lemburg (mal@lemburg.com).
1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	4
1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	5 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	6
15957 c1a8deb15f0e This patch removes all uses of "assert" in the regression test suite Marc-André Lemburg <mal@egenix.com> parents: 15910 diff changeset	7 """#"
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	8 import sys
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	9 import struct
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	10 import codecs
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	11 import unittest
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	12 from test import test_support, string_tests
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	13
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	14 # decorator to skip tests on narrow builds
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	15 requires_wide_build = unittest.skipIf(sys.maxunicode == 65535,
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	16 'requires wide build')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	17
35938 bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	18 # Error handling (bad decoder return)
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	19 def search_function(encoding):
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	20 def decode1(input, errors="strict"):
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	21 return 42 # not a tuple
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	22 def encode1(input, errors="strict"):
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	23 return 42 # not a tuple
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	24 def encode2(input, errors="strict"):
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	25 return (42, 42) # no unicode
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	26 def decode2(input, errors="strict"):
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	27 return (42, 42) # no unicode
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	28 if encoding=="test.unicode1":
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	29 return (encode1, decode1, None, None)
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	30 elif encoding=="test.unicode2":
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	31 return (encode2, decode2, None, None)
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	32 else:
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	33 return None
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	34 codecs.register(search_function)
bb80b8f393ef Move registration of the codec search function to the module scope Neal Norwitz <nnorwitz@gmail.com> parents: 35331 diff changeset	35
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	36 class UnicodeTest(
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	37 string_tests.CommonTest,
33298 a37ae7dba814 Move test_bug1001011() to string_tests.MixinStrUnicodeTest so that Walter Dörwald <walter@livinglogic.de> parents: 32951 diff changeset	38 string_tests.MixinStrUnicodeUserStringTest,
a37ae7dba814 Move test_bug1001011() to string_tests.MixinStrUnicodeTest so that Walter Dörwald <walter@livinglogic.de> parents: 32951 diff changeset	39 string_tests.MixinStrUnicodeTest,
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	40 ):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	41 type2test = unicode
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	42
64708 44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	43 def assertEqual(self, first, second, msg=None):
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	44 # strict assertEqual method: reject implicit bytes/unicode equality
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	45 super(UnicodeTest, self).assertEqual(first, second, msg)
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	46 if isinstance(first, unicode) or isinstance(second, unicode):
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	47 self.assertIsInstance(first, unicode)
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	48 self.assertIsInstance(second, unicode)
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	49 elif isinstance(first, str) or isinstance(second, str):
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	50 self.assertIsInstance(first, str)
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	51 self.assertIsInstance(second, str)
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	52
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	53 def checkequalnofix(self, result, object, methodname, *args):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	54 method = getattr(object, methodname)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	55 realresult = method(*args)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	56 self.assertEqual(realresult, result)
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	57 self.assertTrue(type(realresult) is type(result))
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	58
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	59 # if the original is returned make sure that
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	60 # this doesn't happen with subclasses
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	61 if realresult is object:
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	62 class usub(unicode):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	63 def __repr__(self):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	64 return 'usub(%r)' % unicode.__repr__(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	65 object = usub(object)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	66 method = getattr(object, methodname)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	67 realresult = method(*args)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	68 self.assertEqual(realresult, result)
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	69 self.assertTrue(object is not realresult)
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	70
30653 3b47d6057151 Fix for SF bug [ 817156 ] invalid \U escape gives 0=length unistr. Jeremy Hylton <jeremy@alum.mit.edu> parents: 30059 diff changeset	71 def test_literals(self):
3b47d6057151 Fix for SF bug [ 817156 ] invalid \U escape gives 0=length unistr. Jeremy Hylton <jeremy@alum.mit.edu> parents: 30059 diff changeset	72 self.assertEqual(u'\xff', u'\u00ff')
3b47d6057151 Fix for SF bug [ 817156 ] invalid \U escape gives 0=length unistr. Jeremy Hylton <jeremy@alum.mit.edu> parents: 30059 diff changeset	73 self.assertEqual(u'\uffff', u'\U0000ffff')
42310 4c658377b908 Fix failing unicode test caused by change to ast.c at r56441 Kurt B. Kaiser <kbk@shore.net> parents: 42023 diff changeset	74 self.assertRaises(SyntaxError, eval, 'u\'\\Ufffffffe\'')
4c658377b908 Fix failing unicode test caused by change to ast.c at r56441 Kurt B. Kaiser <kbk@shore.net> parents: 42023 diff changeset	75 self.assertRaises(SyntaxError, eval, 'u\'\\Uffffffff\'')
4c658377b908 Fix failing unicode test caused by change to ast.c at r56441 Kurt B. Kaiser <kbk@shore.net> parents: 42023 diff changeset	76 self.assertRaises(SyntaxError, eval, 'u\'\\U%08x\'' % 0x110000)
30653 3b47d6057151 Fix for SF bug [ 817156 ] invalid \U escape gives 0=length unistr. Jeremy Hylton <jeremy@alum.mit.edu> parents: 30059 diff changeset	77
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	78 def test_repr(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	79 if not sys.platform.startswith('java'):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	80 # Test basic sanity of repr()
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	81 self.assertEqual(repr(u'abc'), "u'abc'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	82 self.assertEqual(repr(u'ab\\c'), "u'ab\\\\c'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	83 self.assertEqual(repr(u'ab\\'), "u'ab\\\\'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	84 self.assertEqual(repr(u'\\c'), "u'\\\\c'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	85 self.assertEqual(repr(u'\\'), "u'\\\\'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	86 self.assertEqual(repr(u'\n'), "u'\\n'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	87 self.assertEqual(repr(u'\r'), "u'\\r'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	88 self.assertEqual(repr(u'\t'), "u'\\t'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	89 self.assertEqual(repr(u'\b'), "u'\\x08'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	90 self.assertEqual(repr(u"'\""), """u'\\'"'""")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	91 self.assertEqual(repr(u"'\""), """u'\\'"'""")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	92 self.assertEqual(repr(u"'"), '''u"'"''')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	93 self.assertEqual(repr(u'"'), """u'"'""")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	94 latin1repr = (
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	95 "u'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	96 "\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	97 "\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	98 "JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{\|}~\\x7f"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	99 "\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	100 "\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	101 "\\x9c\\x9d\\x9e\\x9f\\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	102 "\\xaa\\xab\\xac\\xad\\xae\\xaf\\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	103 "\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\\xc0\\xc1\\xc2\\xc3\\xc4\\xc5"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	104 "\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\\xd0\\xd1\\xd2\\xd3"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	105 "\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\\xe0\\xe1"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	106 "\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	107 "\\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd"
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	108 "\\xfe\\xff'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	109 testrepr = repr(u''.join(map(unichr, xrange(256))))
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	110 self.assertEqual(testrepr, latin1repr)
39621 e8a65bbd6a29 Patch #1541585: fix buffer overrun when performing repr() on Neal Norwitz <nnorwitz@gmail.com> parents: 38096 diff changeset	111 # Test repr works on wide unicode escapes without overflow.
e8a65bbd6a29 Patch #1541585: fix buffer overrun when performing repr() on Neal Norwitz <nnorwitz@gmail.com> parents: 38096 diff changeset	112 self.assertEqual(repr(u"\U00010000" * 39 + u"\uffff" * 4096),
e8a65bbd6a29 Patch #1541585: fix buffer overrun when performing repr() on Neal Norwitz <nnorwitz@gmail.com> parents: 38096 diff changeset	113 repr(u"\U00010000" * 39 + u"\uffff" * 4096))
e8a65bbd6a29 Patch #1541585: fix buffer overrun when performing repr() on Neal Norwitz <nnorwitz@gmail.com> parents: 38096 diff changeset	114
20017 08446a986a56 Test basic functioning of unicode repr(). (If this breaks Jython, Guido van Rossum <guido@python.org> parents: 19999 diff changeset	115
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	116 def test_count(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	117 string_tests.CommonTest.test_count(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	118 # check mixed argument types
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	119 self.checkequalnofix(3, 'aaa', 'count', u'a')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	120 self.checkequalnofix(0, 'aaa', 'count', u'b')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	121 self.checkequalnofix(3, u'aaa', 'count', 'a')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	122 self.checkequalnofix(0, u'aaa', 'count', 'b')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	123 self.checkequalnofix(0, u'aaa', 'count', 'b')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	124 self.checkequalnofix(1, u'aaa', 'count', 'a', -1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	125 self.checkequalnofix(3, u'aaa', 'count', 'a', -10)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	126 self.checkequalnofix(2, u'aaa', 'count', 'a', 0, -1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	127 self.checkequalnofix(0, u'aaa', 'count', 'a', 0, -10)
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	128
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	129 def test_find(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	130 self.checkequalnofix(0, u'abcdefghiabc', 'find', u'abc')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	131 self.checkequalnofix(9, u'abcdefghiabc', 'find', u'abc', 1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	132 self.checkequalnofix(-1, u'abcdefghiabc', 'find', u'def', 4)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	133
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	134 self.assertRaises(TypeError, u'hello'.find)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	135 self.assertRaises(TypeError, u'hello'.find, 42)
15910 f7f3be3d00b9 Added checks to prevent PyUnicode_Count() from dumping core Marc-André Lemburg <mal@egenix.com> parents: 15706 diff changeset	136
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	137 def test_rfind(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	138 string_tests.CommonTest.test_rfind(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	139 # check mixed argument types
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	140 self.checkequalnofix(9, 'abcdefghiabc', 'rfind', u'abc')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	141 self.checkequalnofix(12, 'abcdefghiabc', 'rfind', u'')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	142 self.checkequalnofix(12, u'abcdefghiabc', 'rfind', '')
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	143
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	144 def test_index(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	145 string_tests.CommonTest.test_index(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	146 # check mixed argument types
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	147 for (t1, t2) in ((str, unicode), (unicode, str)):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	148 self.checkequalnofix(0, t1('abcdefghiabc'), 'index', t2(''))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	149 self.checkequalnofix(3, t1('abcdefghiabc'), 'index', t2('def'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	150 self.checkequalnofix(0, t1('abcdefghiabc'), 'index', t2('abc'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	151 self.checkequalnofix(9, t1('abcdefghiabc'), 'index', t2('abc'), 1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	152 self.assertRaises(ValueError, t1('abcdefghiabc').index, t2('hib'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	153 self.assertRaises(ValueError, t1('abcdefghiab').index, t2('abc'), 1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	154 self.assertRaises(ValueError, t1('abcdefghi').index, t2('ghi'), 8)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	155 self.assertRaises(ValueError, t1('abcdefghi').index, t2('ghi'), -1)
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	156
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	157 def test_rindex(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	158 string_tests.CommonTest.test_rindex(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	159 # check mixed argument types
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	160 for (t1, t2) in ((str, unicode), (unicode, str)):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	161 self.checkequalnofix(12, t1('abcdefghiabc'), 'rindex', t2(''))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	162 self.checkequalnofix(3, t1('abcdefghiabc'), 'rindex', t2('def'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	163 self.checkequalnofix(9, t1('abcdefghiabc'), 'rindex', t2('abc'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	164 self.checkequalnofix(0, t1('abcdefghiabc'), 'rindex', t2('abc'), 0, -1)
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	165
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	166 self.assertRaises(ValueError, t1('abcdefghiabc').rindex, t2('hib'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	167 self.assertRaises(ValueError, t1('defghiabc').rindex, t2('def'), 1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	168 self.assertRaises(ValueError, t1('defghiabc').rindex, t2('abc'), 0, -1)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	169 self.assertRaises(ValueError, t1('abcdefghi').rindex, t2('ghi'), 0, 8)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	170 self.assertRaises(ValueError, t1('abcdefghi').rindex, t2('ghi'), 0, -1)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	171
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	172 def test_translate(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	173 self.checkequalnofix(u'bbbc', u'abababc', 'translate', {ord('a'):None})
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	174 self.checkequalnofix(u'iiic', u'abababc', 'translate', {ord('a'):None, ord('b'):ord('i')})
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	175 self.checkequalnofix(u'iiix', u'abababc', 'translate', {ord('a'):None, ord('b'):ord('i'), ord('c'):u'x'})
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	176 self.checkequalnofix(u'<i><i><i>c', u'abababc', 'translate', {ord('a'):None, ord('b'):u'<i>'})
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	177 self.checkequalnofix(u'c', u'abababc', 'translate', {ord('a'):None, ord('b'):u''})
31455 37d501b9e2d5 Fix reallocation bug in unicode.translate(): The code was comparing Walter Dörwald <walter@livinglogic.de> parents: 30653 diff changeset	178 self.checkequalnofix(u'xyyx', u'xzx', 'translate', {ord('z'):u'yy'})
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	179
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	180 self.assertRaises(TypeError, u'hello'.translate)
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	181 self.assertRaises(TypeError, u'abababc'.translate, {ord('a'):''})
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	182
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	183 def test_split(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	184 string_tests.CommonTest.test_split(self)
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	185
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	186 # Mixed arguments
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	187 self.checkequalnofix([u'a', u'b', u'c', u'd'], u'a//b//c//d', 'split', '//')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	188 self.checkequalnofix([u'a', u'b', u'c', u'd'], 'a//b//c//d', 'split', u'//')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	189 self.checkequalnofix([u'endcase ', u''], u'endcase test', 'split', 'test')
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	190
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	191 def test_join(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	192 string_tests.MixinStrUnicodeUserStringTest.test_join(self)
23225 e639e34ef901 Apply patch diff.txt from SF feature request Walter Dörwald <walter@livinglogic.de> parents: 23115 diff changeset	193
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	194 # mixed arguments
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	195 self.checkequalnofix(u'a b c d', u' ', 'join', ['a', 'b', u'c', u'd'])
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	196 self.checkequalnofix(u'abcd', u'', 'join', (u'a', u'b', u'c', u'd'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	197 self.checkequalnofix(u'w x y z', u' ', 'join', string_tests.Sequence('wxyz'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	198 self.checkequalnofix(u'a b c d', ' ', 'join', [u'a', u'b', u'c', u'd'])
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	199 self.checkequalnofix(u'a b c d', ' ', 'join', ['a', 'b', u'c', u'd'])
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	200 self.checkequalnofix(u'abcd', '', 'join', (u'a', u'b', u'c', u'd'))
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	201 self.checkequalnofix(u'w x y z', ' ', 'join', string_tests.Sequence(u'wxyz'))
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	202
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	203 def test_strip(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	204 string_tests.CommonTest.test_strip(self)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	205 self.assertRaises(UnicodeError, u"hello".strip, "\xff")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	206
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	207 def test_replace(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	208 string_tests.CommonTest.test_replace(self)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	209
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	210 # method call forwarded from str implementation because of unicode argument
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	211 self.checkequalnofix(u'one@two!three!', 'one!two!three!', 'replace', u'!', u'@', 1)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	212 self.assertRaises(TypeError, 'replace'.replace, u"r", 42)
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	213
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	214 def test_comparison(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	215 # Comparisons:
64708 44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	216 self.assertTrue(u'abc' == 'abc')
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	217 self.assertTrue('abc' == u'abc')
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	218 self.assertTrue(u'abc' == u'abc')
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	219 self.assertTrue(u'abcd' > 'abc')
6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	220 self.assertTrue('abcd' > u'abc')
6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	221 self.assertTrue(u'abcd' > u'abc')
6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	222 self.assertTrue(u'abc' < 'abcd')
6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	223 self.assertTrue('abc' < u'abcd')
6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	224 self.assertTrue(u'abc' < u'abcd')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	225
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	226 if 0:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	227 # Move these tests to a Unicode collation module test...
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	228 # Testing UTF-16 code point order comparisons...
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	229
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	230 # No surrogates, no fixup required.
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	231 self.assertTrue(u'\u0061' < u'\u20ac')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	232 # Non surrogate below surrogate value, no fixup required
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	233 self.assertTrue(u'\u0061' < u'\ud800\udc02')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	234
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	235 # Non surrogate above surrogate value, fixup required
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	236 def test_lecmp(s, s2):
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	237 self.assertTrue(s < s2)
13410 5157eb7be20d Tests for new surrogate support in the UTF-8 codec. By Bill Tutt. Marc-André Lemburg <mal@egenix.com> parents: 13400 diff changeset	238
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	239 def test_fixup(s):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	240 s2 = u'\ud800\udc01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	241 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	242 s2 = u'\ud900\udc01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	243 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	244 s2 = u'\uda00\udc01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	245 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	246 s2 = u'\udb00\udc01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	247 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	248 s2 = u'\ud800\udd01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	249 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	250 s2 = u'\ud900\udd01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	251 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	252 s2 = u'\uda00\udd01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	253 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	254 s2 = u'\udb00\udd01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	255 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	256 s2 = u'\ud800\ude01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	257 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	258 s2 = u'\ud900\ude01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	259 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	260 s2 = u'\uda00\ude01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	261 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	262 s2 = u'\udb00\ude01'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	263 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	264 s2 = u'\ud800\udfff'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	265 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	266 s2 = u'\ud900\udfff'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	267 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	268 s2 = u'\uda00\udfff'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	269 test_lecmp(s, s2)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	270 s2 = u'\udb00\udfff'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	271 test_lecmp(s, s2)
13410 5157eb7be20d Tests for new surrogate support in the UTF-8 codec. By Bill Tutt. Marc-André Lemburg <mal@egenix.com> parents: 13400 diff changeset	272
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	273 test_fixup(u'\ue000')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	274 test_fixup(u'\uff61')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	275
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	276 # Surrogates on both sides, no fixup required
55002 6768b2350c57 convert usage of fail* to assert* Benjamin Peterson <benjamin@python.org> parents: 54267 diff changeset	277 self.assertTrue(u'\ud800\udc02' < u'\ud84d\udc56')
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	278
71869 d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	279 def test_capitalize(self):
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	280 string_tests.CommonTest.test_capitalize(self)
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	281 # check that titlecased chars are lowered correctly
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	282 # \u1ffc is the titlecased char
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	283 self.checkequal(u'\u1ffc\u1ff3\u1ff3\u1ff3',
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	284 u'\u1ff3\u1ff3\u1ffc\u1ffc', 'capitalize')
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	285 # check with cased non-letter chars
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	286 self.checkequal(u'\u24c5\u24e8\u24e3\u24d7\u24de\u24dd',
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	287 u'\u24c5\u24ce\u24c9\u24bd\u24c4\u24c3', 'capitalize')
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	288 self.checkequal(u'\u24c5\u24e8\u24e3\u24d7\u24de\u24dd',
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	289 u'\u24df\u24e8\u24e3\u24d7\u24de\u24dd', 'capitalize')
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	290 self.checkequal(u'\u2160\u2171\u2172',
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	291 u'\u2160\u2161\u2162', 'capitalize')
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	292 self.checkequal(u'\u2160\u2171\u2172',
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	293 u'\u2170\u2171\u2172', 'capitalize')
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	294 # check with Ll chars with no upper - nothing changes here
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	295 self.checkequal(u'\u019b\u1d00\u1d86\u0221\u1fb7',
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	296 u'\u019b\u1d00\u1d86\u0221\u1fb7', 'capitalize')
d3816fa1bcdf #12266: move the tests in test_unicode. Ezio Melotti <ezio.melotti@gmail.com> parents: 69562 diff changeset	297
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	298 def test_islower(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	299 string_tests.MixinStrUnicodeUserStringTest.test_islower(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	300 self.checkequalnofix(False, u'\u1FFc', 'islower')
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	301
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	302 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	303 def test_islower_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	304 # non-BMP, uppercase
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	305 self.assertFalse(u'\U00010401'.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	306 self.assertFalse(u'\U00010427'.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	307 # non-BMP, lowercase
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	308 self.assertTrue(u'\U00010429'.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	309 self.assertTrue(u'\U0001044E'.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	310 # non-BMP, non-cased
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	311 self.assertFalse(u'\U0001F40D'.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	312 self.assertFalse(u'\U0001F46F'.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	313
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	314 def test_isupper(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	315 string_tests.MixinStrUnicodeUserStringTest.test_isupper(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	316 if not sys.platform.startswith('java'):
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	317 self.checkequalnofix(False, u'\u1FFc', 'isupper')
13353 0b289e00d52a Added tests for the new .isalpha() and .isalnum() methods. Marc-André Lemburg <mal@egenix.com> parents: 13189 diff changeset	318
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	319 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	320 def test_isupper_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	321 # non-BMP, uppercase
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	322 self.assertTrue(u'\U00010401'.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	323 self.assertTrue(u'\U00010427'.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	324 # non-BMP, lowercase
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	325 self.assertFalse(u'\U00010429'.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	326 self.assertFalse(u'\U0001044E'.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	327 # non-BMP, non-cased
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	328 self.assertFalse(u'\U0001F40D'.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	329 self.assertFalse(u'\U0001F46F'.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	330
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	331 def test_istitle(self):
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	332 string_tests.MixinStrUnicodeUserStringTest.test_istitle(self)
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	333 self.checkequalnofix(True, u'\u1FFc', 'istitle')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	334 self.checkequalnofix(True, u'Greek \u1FFcitlecases ...', 'istitle')
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	335
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	336 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	337 def test_istitle_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	338 # non-BMP, uppercase + lowercase
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	339 self.assertTrue(u'\U00010401\U00010429'.istitle())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	340 self.assertTrue(u'\U00010427\U0001044E'.istitle())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	341 # apparently there are no titlecased (Lt) non-BMP chars in Unicode 6
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	342 for ch in [u'\U00010429', u'\U0001044E', u'\U0001F40D', u'\U0001F46F']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	343 self.assertFalse(ch.istitle(), '{!r} is not title'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	344
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	345 def test_isspace(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	346 string_tests.MixinStrUnicodeUserStringTest.test_isspace(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	347 self.checkequalnofix(True, u'\u2000', 'isspace')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	348 self.checkequalnofix(True, u'\u200a', 'isspace')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	349 self.checkequalnofix(False, u'\u2014', 'isspace')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	350
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	351 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	352 def test_isspace_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	353 # apparently there are no non-BMP spaces chars in Unicode 6
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	354 for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	355 u'\U0001F40D', u'\U0001F46F']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	356 self.assertFalse(ch.isspace(), '{!r} is not space.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	357
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	358 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	359 def test_isalnum_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	360 for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	361 u'\U0001D7F6', u'\U000104A0', u'\U000104A0', u'\U0001F107']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	362 self.assertTrue(ch.isalnum(), '{!r} is alnum.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	363
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	364 def test_isalpha(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	365 string_tests.MixinStrUnicodeUserStringTest.test_isalpha(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	366 self.checkequalnofix(True, u'\u1FFc', 'isalpha')
12001 e362f326048c Marc-Andre Lemburg: Add tests for mixed use of char in string. Guido van Rossum <guido@python.org> parents: 11992 diff changeset	367
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	368 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	369 def test_isalpha_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	370 # non-BMP, cased
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	371 self.assertTrue(u'\U00010401'.isalpha())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	372 self.assertTrue(u'\U00010427'.isalpha())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	373 self.assertTrue(u'\U00010429'.isalpha())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	374 self.assertTrue(u'\U0001044E'.isalpha())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	375 # non-BMP, non-cased
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	376 self.assertFalse(u'\U0001F40D'.isalpha())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	377 self.assertFalse(u'\U0001F46F'.isalpha())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	378
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	379 def test_isdecimal(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	380 self.checkequalnofix(False, u'', 'isdecimal')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	381 self.checkequalnofix(False, u'a', 'isdecimal')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	382 self.checkequalnofix(True, u'0', 'isdecimal')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	383 self.checkequalnofix(False, u'\u2460', 'isdecimal') # CIRCLED DIGIT ONE
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	384 self.checkequalnofix(False, u'\xbc', 'isdecimal') # VULGAR FRACTION ONE QUARTER
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	385 self.checkequalnofix(True, u'\u0660', 'isdecimal') # ARABIC-INDIC DIGIT ZERO
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	386 self.checkequalnofix(True, u'0123456789', 'isdecimal')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	387 self.checkequalnofix(False, u'0123456789a', 'isdecimal')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	388
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	389 self.checkraises(TypeError, 'abc', 'isdecimal', 42)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	390
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	391 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	392 def test_isdecimal_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	393 for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	394 u'\U0001F40D', u'\U0001F46F', u'\U00011065', u'\U0001F107']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	395 self.assertFalse(ch.isdecimal(), '{!r} is not decimal.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	396 for ch in [u'\U0001D7F6', u'\U000104A0', u'\U000104A0']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	397 self.assertTrue(ch.isdecimal(), '{!r} is decimal.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	398
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	399 def test_isdigit(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	400 string_tests.MixinStrUnicodeUserStringTest.test_isdigit(self)
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	401 self.checkequalnofix(True, u'\u2460', 'isdigit')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	402 self.checkequalnofix(False, u'\xbc', 'isdigit')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	403 self.checkequalnofix(True, u'\u0660', 'isdigit')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	404
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	405 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	406 def test_isdigit_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	407 for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	408 u'\U0001F40D', u'\U0001F46F', u'\U00011065']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	409 self.assertFalse(ch.isdigit(), '{!r} is not a digit.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	410 for ch in [u'\U0001D7F6', u'\U000104A0', u'\U000104A0', u'\U0001F107']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	411 self.assertTrue(ch.isdigit(), '{!r} is a digit.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	412
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	413 def test_isnumeric(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	414 self.checkequalnofix(False, u'', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	415 self.checkequalnofix(False, u'a', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	416 self.checkequalnofix(True, u'0', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	417 self.checkequalnofix(True, u'\u2460', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	418 self.checkequalnofix(True, u'\xbc', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	419 self.checkequalnofix(True, u'\u0660', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	420 self.checkequalnofix(True, u'0123456789', 'isnumeric')
fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	421 self.checkequalnofix(False, u'0123456789a', 'isnumeric')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	422
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	423 self.assertRaises(TypeError, u"abc".isnumeric, 42)
12917 2a2caaee6797 Marc-Andre Lemburg <mal@lemburg.com>: Marc-André Lemburg <mal@egenix.com> parents: 12897 diff changeset	424
72038 75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	425 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	426 def test_isnumeric_non_bmp(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	427 for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	428 u'\U0001F40D', u'\U0001F46F']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	429 self.assertFalse(ch.isnumeric(), '{!r} is not numeric.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	430 for ch in [u'\U00010107', u'\U0001D7F6', u'\U00023b1b',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	431 u'\U000104A0', u'\U0001F107']:
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	432 self.assertTrue(ch.isnumeric(), '{!r} is numeric.'.format(ch))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	433
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	434 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	435 def test_surrogates(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	436 # this test actually passes on narrow too, but it's just by accident.
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	437 # Surrogates are seen as non-cased chars, so u'X\uD800X' is as
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	438 # uppercase as 'X X'
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	439 for s in (u'a\uD800b\uDFFF', u'a\uDFFFb\uD800',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	440 u'a\uD800b\uDFFFa', u'a\uDFFFb\uD800a'):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	441 self.assertTrue(s.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	442 self.assertFalse(s.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	443 self.assertFalse(s.istitle())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	444 for s in (u'A\uD800B\uDFFF', u'A\uDFFFB\uD800',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	445 u'A\uD800B\uDFFFA', u'A\uDFFFB\uD800A'):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	446 self.assertFalse(s.islower())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	447 self.assertTrue(s.isupper())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	448 self.assertTrue(s.istitle())
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	449
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	450 for meth_name in ('islower', 'isupper', 'istitle'):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	451 meth = getattr(unicode, meth_name)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	452 for s in (u'\uD800', u'\uDFFF', u'\uD800\uD800', u'\uDFFF\uDFFF'):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	453 self.assertFalse(meth(s), '%r.%s() is False' % (s, meth_name))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	454
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	455 for meth_name in ('isalpha', 'isalnum', 'isdigit', 'isspace',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	456 'isdecimal', 'isnumeric'):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	457 meth = getattr(unicode, meth_name)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	458 for s in (u'\uD800', u'\uDFFF', u'\uD800\uD800', u'\uDFFF\uDFFF',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	459 u'a\uD800b\uDFFF', u'a\uDFFFb\uD800',
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	460 u'a\uD800b\uDFFFa', u'a\uDFFFb\uD800a'):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	461 self.assertFalse(meth(s), '%r.%s() is False' % (s, meth_name))
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	462
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	463
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	464 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	465 def test_lower(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	466 string_tests.CommonTest.test_lower(self)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	467 self.assertEqual(u'\U00010427'.lower(), u'\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	468 self.assertEqual(u'\U00010427\U00010427'.lower(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	469 u'\U0001044F\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	470 self.assertEqual(u'\U00010427\U0001044F'.lower(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	471 u'\U0001044F\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	472 self.assertEqual(u'X\U00010427x\U0001044F'.lower(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	473 u'x\U0001044Fx\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	474
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	475 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	476 def test_upper(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	477 string_tests.CommonTest.test_upper(self)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	478 self.assertEqual(u'\U0001044F'.upper(), u'\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	479 self.assertEqual(u'\U0001044F\U0001044F'.upper(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	480 u'\U00010427\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	481 self.assertEqual(u'\U00010427\U0001044F'.upper(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	482 u'\U00010427\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	483 self.assertEqual(u'X\U00010427x\U0001044F'.upper(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	484 u'X\U00010427X\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	485
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	486 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	487 def test_capitalize(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	488 string_tests.CommonTest.test_capitalize(self)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	489 self.assertEqual(u'\U0001044F'.capitalize(), u'\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	490 self.assertEqual(u'\U0001044F\U0001044F'.capitalize(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	491 u'\U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	492 self.assertEqual(u'\U00010427\U0001044F'.capitalize(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	493 u'\U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	494 self.assertEqual(u'\U0001044F\U00010427'.capitalize(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	495 u'\U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	496 self.assertEqual(u'X\U00010427x\U0001044F'.capitalize(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	497 u'X\U0001044Fx\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	498
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	499 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	500 def test_title(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	501 string_tests.MixinStrUnicodeUserStringTest.test_title(self)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	502 self.assertEqual(u'\U0001044F'.title(), u'\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	503 self.assertEqual(u'\U0001044F\U0001044F'.title(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	504 u'\U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	505 self.assertEqual(u'\U0001044F\U0001044F \U0001044F\U0001044F'.title(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	506 u'\U00010427\U0001044F \U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	507 self.assertEqual(u'\U00010427\U0001044F \U00010427\U0001044F'.title(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	508 u'\U00010427\U0001044F \U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	509 self.assertEqual(u'\U0001044F\U00010427 \U0001044F\U00010427'.title(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	510 u'\U00010427\U0001044F \U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	511 self.assertEqual(u'X\U00010427x\U0001044F X\U00010427x\U0001044F'.title(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	512 u'X\U0001044Fx\U0001044F X\U0001044Fx\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	513
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	514 @requires_wide_build
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	515 def test_swapcase(self):
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	516 string_tests.CommonTest.test_swapcase(self)
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	517 self.assertEqual(u'\U0001044F'.swapcase(), u'\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	518 self.assertEqual(u'\U00010427'.swapcase(), u'\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	519 self.assertEqual(u'\U0001044F\U0001044F'.swapcase(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	520 u'\U00010427\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	521 self.assertEqual(u'\U00010427\U0001044F'.swapcase(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	522 u'\U0001044F\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	523 self.assertEqual(u'\U0001044F\U00010427'.swapcase(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	524 u'\U00010427\U0001044F')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	525 self.assertEqual(u'X\U00010427x\U0001044F'.swapcase(),
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	526 u'x\U0001044FX\U00010427')
75a4941d4d61 #9200: backport tests but run them on wide builds only. Ezio Melotti <ezio.melotti@gmail.com> parents: 71869 diff changeset	527
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	528 def test_contains(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	529 # Testing Unicode contains method
58460 17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	530 self.assertIn('a', u'abdb')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	531 self.assertIn('a', u'bdab')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	532 self.assertIn('a', u'bdaba')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	533 self.assertIn('a', u'bdba')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	534 self.assertIn('a', u'bdba')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	535 self.assertIn(u'a', u'bdba')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	536 self.assertNotIn(u'a', u'bdb')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	537 self.assertNotIn(u'a', 'bdb')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	538 self.assertIn(u'a', 'bdba')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	539 self.assertIn(u'a', ('a',1,None))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	540 self.assertIn(u'a', (1,None,'a'))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	541 self.assertIn(u'a', (1,None,u'a'))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	542 self.assertIn('a', ('a',1,None))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	543 self.assertIn('a', (1,None,'a'))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	544 self.assertIn('a', (1,None,u'a'))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	545 self.assertNotIn('a', ('x',1,u'y'))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	546 self.assertNotIn('a', ('x',1,None))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	547 self.assertNotIn(u'abcd', u'abcxxxx')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	548 self.assertIn(u'ab', u'abcd')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	549 self.assertIn('ab', u'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	550 self.assertIn(u'ab', 'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	551 self.assertIn(u'ab', (1,None,u'ab'))
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	552 self.assertIn(u'', u'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	553 self.assertIn('', u'abc')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	554
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	555 # If the following fails either
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	556 # the contains operator does not propagate UnicodeErrors or
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	557 # someone has changed the default encoding
57729 2b8f485b0d03 Issue #1680159: unicode coercion during an 'in' operation was masking R. David Murray <rdmurray@bitdance.com> parents: 56093 diff changeset	558 self.assertRaises(UnicodeDecodeError, 'g\xe2teau'.__contains__, u'\xe2')
2b8f485b0d03 Issue #1680159: unicode coercion during an 'in' operation was masking R. David Murray <rdmurray@bitdance.com> parents: 56093 diff changeset	559 self.assertRaises(UnicodeDecodeError, u'g\xe2teau'.__contains__, '\xe2')
24737 eaa87632b1e8 Add C API PyUnicode_FromOrdinal() which exposes unichr() at C level. Marc-André Lemburg <mal@egenix.com> parents: 24703 diff changeset	560
58460 17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	561 self.assertIn(u'', '')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	562 self.assertIn('', u'')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	563 self.assertIn(u'', u'')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	564 self.assertIn(u'', 'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	565 self.assertIn('', u'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	566 self.assertIn(u'', u'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	567 self.assertNotIn(u'\0', 'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	568 self.assertNotIn('\0', u'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	569 self.assertNotIn(u'\0', u'abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	570 self.assertIn(u'\0', '\0abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	571 self.assertIn('\0', u'\0abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	572 self.assertIn(u'\0', u'\0abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	573 self.assertIn(u'\0', 'abc\0')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	574 self.assertIn('\0', u'abc\0')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	575 self.assertIn(u'\0', u'abc\0')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	576 self.assertIn(u'a', '\0abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	577 self.assertIn('a', u'\0abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	578 self.assertIn(u'a', u'\0abc')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	579 self.assertIn(u'asdf', 'asdf')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	580 self.assertIn('asdf', u'asdf')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	581 self.assertIn(u'asdf', u'asdf')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	582 self.assertNotIn(u'asdf', 'asd')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	583 self.assertNotIn('asdf', u'asd')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	584 self.assertNotIn(u'asdf', u'asd')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	585 self.assertNotIn(u'asdf', '')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	586 self.assertNotIn('asdf', u'')
17891566a478 use assert[Not]In where appropriate Ezio Melotti <ezio.melotti@gmail.com> parents: 58090 diff changeset	587 self.assertNotIn(u'asdf', u'')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	588
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	589 self.assertRaises(TypeError, u"abc".__contains__)
57729 2b8f485b0d03 Issue #1680159: unicode coercion during an 'in' operation was masking R. David Murray <rdmurray@bitdance.com> parents: 56093 diff changeset	590 self.assertRaises(TypeError, u"abc".__contains__, object())
11992 1789fae5f074 Marc-Andre Lemburg: test script for Unicode implementation. Guido van Rossum <guido@python.org> parents: diff changeset	591
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	592 def test_formatting(self):
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	593 string_tests.MixinStrUnicodeUserStringTest.test_formatting(self)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	594 # Testing Unicode formatting strings...
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	595 self.assertEqual(u"%s, %s" % (u"abc", "abc"), u'abc, abc')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	596 self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, 2, 3), u'abc, abc, 1, 2.000000, 3.00')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	597 self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", 1, -2, 3), u'abc, abc, 1, -2.000000, 3.00')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	598 self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.5), u'abc, abc, -1, -2.000000, 3.50')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	599 self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 3.57), u'abc, abc, -1, -2.000000, 3.57')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	600 self.assertEqual(u"%s, %s, %i, %f, %5.2f" % (u"abc", "abc", -1, -2, 1003.57), u'abc, abc, -1, -2.000000, 1003.57')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	601 if not sys.platform.startswith('java'):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	602 self.assertEqual(u"%r, %r" % (u"abc", "abc"), u"u'abc', 'abc'")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	603 self.assertEqual(u"%(x)s, %(y)s" % {'x':u"abc", 'y':"def"}, u'abc, def')
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	604 self.assertEqual(u"%(x)s, %(\xfc)s" % {'x':u"abc", u'\xfc':"def"}, u'abc, def')
28479 e13a7e1fdb9e Remove duplicate test. Walter Dörwald <walter@livinglogic.de> parents: 28478 diff changeset	605
28478 8802de0da533 Fix PyString_Format() so that '%c' % u'a' returns u'a' Walter Dörwald <walter@livinglogic.de> parents: 28009 diff changeset	606 self.assertEqual(u'%c' % 0x1234, u'\u1234')
28494 32bea41fef68 Change formatchar(), so that u"%c" % 0xffffffff now raises Walter Dörwald <walter@livinglogic.de> parents: 28479 diff changeset	607 self.assertRaises(OverflowError, u"%c".__mod__, (sys.maxunicode+1,))
63106 742fdf7f6540 Merged revisions 82980 via svnmerge from Stefan Krah <stefan@bytereef.org> parents: 62711 diff changeset	608 self.assertRaises(ValueError, u"%.1\u1032f".__mod__, (1.0/3))
20563 9058e49c6c57 Additional test and documentation for the unicode() changes. Marc-André Lemburg <mal@egenix.com> parents: 20240 diff changeset	609
59087 7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	610 for num in range(0x00,0x80):
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	611 char = chr(num)
64708 44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	612 self.assertEqual(u"%c" % char, unicode(char))
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	613 self.assertEqual(u"%c" % num, unicode(char))
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	614 self.assertTrue(char == u"%c" % char)
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	615 self.assertTrue(char == u"%c" % num)
59087 7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	616 # Issue 7649
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	617 for num in range(0x80,0x100):
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	618 uchar = unichr(num)
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	619 self.assertEqual(uchar, u"%c" % num) # works only with ints
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	620 self.assertEqual(uchar, u"%c" % uchar) # and unicode chars
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	621 # the implicit decoding should fail for non-ascii chars
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	622 self.assertRaises(UnicodeDecodeError, u"%c".__mod__, chr(num))
7780482a64da Merged revisions 78392 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 54268 diff changeset	623 self.assertRaises(UnicodeDecodeError, u"%s".__mod__, chr(num))
20563 9058e49c6c57 Additional test and documentation for the unicode() changes. Marc-André Lemburg <mal@egenix.com> parents: 20240 diff changeset	624
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	625 # formatting jobs delegated from the string implementation:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	626 self.assertEqual('...%(foo)s...' % {'foo':u"abc"}, u'...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	627 self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	628 self.assertEqual('...%(foo)s...' % {u'foo':"abc"}, '...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	629 self.assertEqual('...%(foo)s...' % {u'foo':u"abc"}, u'...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	630 self.assertEqual('...%(foo)s...' % {u'foo':u"abc",'def':123}, u'...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	631 self.assertEqual('...%(foo)s...' % {u'foo':u"abc",u'def':123}, u'...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	632 self.assertEqual('...%s...%s...%s...%s...' % (1,2,3,u"abc"), u'...1...2...3...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	633 self.assertEqual('...%%...%%s...%s...%s...%s...%s...' % (1,2,3,u"abc"), u'...%...%s...1...2...3...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	634 self.assertEqual('...%s...' % u"abc", u'...abc...')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	635 self.assertEqual('%*s' % (5,u'abc',), u' abc')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	636 self.assertEqual('%*s' % (-5,u'abc',), u'abc ')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	637 self.assertEqual('%.s' % (5,2,u'abc',), u' ab')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	638 self.assertEqual('%.s' % (5,3,u'abc',), u' abc')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	639 self.assertEqual('%i %.s' % (10, 5,3,u'abc',), u'10 abc')
28009 fe10ece8ba68 Port all string tests to PyUnit and share as much tests Walter Dörwald <walter@livinglogic.de> parents: 27797 diff changeset	640 self.assertEqual('%i%s %.s' % (10, 3, 5, 3, u'abc',), u'103 abc')
28478 8802de0da533 Fix PyString_Format() so that '%c' % u'a' returns u'a' Walter Dörwald <walter@livinglogic.de> parents: 28009 diff changeset	641 self.assertEqual('%c' % u'a', u'a')
35331 ef11cbc08dab Change the %s format specifier for str objects so that it returns a Neil Schemenauer <nascheme@enme.ucalgary.ca> parents: 34931 diff changeset	642 class Wrapper:
ef11cbc08dab Change the %s format specifier for str objects so that it returns a Neil Schemenauer <nascheme@enme.ucalgary.ca> parents: 34931 diff changeset	643 def __str__(self):
ef11cbc08dab Change the %s format specifier for str objects so that it returns a Neil Schemenauer <nascheme@enme.ucalgary.ca> parents: 34931 diff changeset	644 return u'\u1234'
ef11cbc08dab Change the %s format specifier for str objects so that it returns a Neil Schemenauer <nascheme@enme.ucalgary.ca> parents: 34931 diff changeset	645 self.assertEqual('%s' % Wrapper(), u'\u1234')
38096 5457ab9f8599 Whitespace normalization. Tim Peters <tim.peters@gmail.com> parents: 38055 diff changeset	646
69562 3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	647 def test_startswith_endswith_errors(self):
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	648 for meth in (u'foo'.startswith, u'foo'.endswith):
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	649 with self.assertRaises(UnicodeDecodeError):
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	650 meth('\xff')
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	651 with self.assertRaises(TypeError) as cm:
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	652 meth(['f'])
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	653 exc = str(cm.exception)
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	654 self.assertIn('unicode', exc)
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	655 self.assertIn('str', exc)
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	656 self.assertIn('tuple', exc)
3ceeccbc2c3b #6780: fix starts/endswith error message to mention that tuples are accepted too. Ezio Melotti parents: 68256 diff changeset	657
38055 fcc61835c6ac Bug #1473625: stop cPickle making float dumps locale dependent in protocol 0. Georg Brandl <georg@python.org> parents: 37301 diff changeset	658 @test_support.run_with_locale('LC_ALL', 'de_DE', 'fr_FR')
36341 4bcf5fe54d83 Checkin the test of patch #1400181. Georg Brandl <georg@python.org> parents: 36056 diff changeset	659 def test_format_float(self):
38055 fcc61835c6ac Bug #1473625: stop cPickle making float dumps locale dependent in protocol 0. Georg Brandl <georg@python.org> parents: 37301 diff changeset	660 # should not format with a comma, but always with C locale
fcc61835c6ac Bug #1473625: stop cPickle making float dumps locale dependent in protocol 0. Georg Brandl <georg@python.org> parents: 37301 diff changeset	661 self.assertEqual(u'1.0', u'%.1f' % 1.0)
36341 4bcf5fe54d83 Checkin the test of patch #1400181. Georg Brandl <georg@python.org> parents: 36056 diff changeset	662
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	663 def test_constructor(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	664 # unicode(obj) tests (this maps to PyObject_Unicode() at C level)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	665
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	666 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	667 unicode(u'unicode remains unicode'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	668 u'unicode remains unicode'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	669 )
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	670
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	671 class UnicodeSubclass(unicode):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	672 pass
19998 8a0c97453df4 Patch #435971: UTF-7 codec by Brian Quinlan. Marc-André Lemburg <mal@egenix.com> parents: 18828 diff changeset	673
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	674 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	675 unicode(UnicodeSubclass('unicode subclass becomes unicode')),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	676 u'unicode subclass becomes unicode'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	677 )
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	678
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	679 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	680 unicode('strings are converted to unicode'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	681 u'strings are converted to unicode'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	682 )
19998 8a0c97453df4 Patch #435971: UTF-7 codec by Brian Quinlan. Marc-André Lemburg <mal@egenix.com> parents: 18828 diff changeset	683
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	684 class UnicodeCompat:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	685 def __init__(self, x):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	686 self.x = x
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	687 def __unicode__(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	688 return self.x
19998 8a0c97453df4 Patch #435971: UTF-7 codec by Brian Quinlan. Marc-André Lemburg <mal@egenix.com> parents: 18828 diff changeset	689
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	690 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	691 unicode(UnicodeCompat('__unicode__ compatible objects are recognized')),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	692 u'__unicode__ compatible objects are recognized')
19998 8a0c97453df4 Patch #435971: UTF-7 codec by Brian Quinlan. Marc-André Lemburg <mal@egenix.com> parents: 18828 diff changeset	693
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	694 class StringCompat:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	695 def __init__(self, x):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	696 self.x = x
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	697 def __str__(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	698 return self.x
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	699
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	700 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	701 unicode(StringCompat('__str__ compatible objects are recognized')),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	702 u'__str__ compatible objects are recognized'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	703 )
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	704
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	705 # unicode(obj) is compatible to str():
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	706
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	707 o = StringCompat('unicode(obj) is compatible to str()')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	708 self.assertEqual(unicode(o), u'unicode(obj) is compatible to str()')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	709 self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	710
32801 16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	711 # %-formatting and .__unicode__()
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	712 self.assertEqual(u'%s' %
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	713 UnicodeCompat(u"u'%s' % obj uses obj.__unicode__()"),
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	714 u"u'%s' % obj uses obj.__unicode__()")
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	715 self.assertEqual(u'%s' %
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	716 UnicodeCompat(u"u'%s' % obj falls back to obj.__str__()"),
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	717 u"u'%s' % obj falls back to obj.__str__()")
16de4f90ef44 Let u'%s' % obj try obj.__unicode__() first and fallback to obj.__str__(). Marc-André Lemburg <mal@egenix.com> parents: 32240 diff changeset	718
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	719 for obj in (123, 123.45, 123L):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	720 self.assertEqual(unicode(obj), unicode(str(obj)))
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	721
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	722 # unicode(obj, encoding, error) tests (this maps to
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	723 # PyUnicode_FromEncodedObject() at C level)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	724
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	725 if not sys.platform.startswith('java'):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	726 self.assertRaises(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	727 TypeError,
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	728 unicode,
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	729 u'decoding unicode is not supported',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	730 'utf-8',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	731 'strict'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	732 )
21882 94bac88f150f Fix for the UTF-8 memory allocation bug and the UTF-8 encoding Marc-André Lemburg <mal@egenix.com> parents: 21337 diff changeset	733
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	734 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	735 unicode('strings are decoded to unicode', 'utf-8', 'strict'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	736 u'strings are decoded to unicode'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	737 )
13410 5157eb7be20d Tests for new surrogate support in the UTF-8 codec. By Bill Tutt. Marc-André Lemburg <mal@egenix.com> parents: 13400 diff changeset	738
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	739 if not sys.platform.startswith('java'):
59432 e23cba03cc4b Issue #7849: Now the utility ``check_warnings`` verifies if the warnings are Florent Xicluna <florent.xicluna@gmail.com> parents: 59085 diff changeset	740 with test_support.check_py3k_warnings():
63553 7c3b849d181a Merged revisions 78758 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 63106 diff changeset	741 buf = buffer('character buffers are decoded to unicode')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	742 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	743 unicode(
63553 7c3b849d181a Merged revisions 78758 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 63106 diff changeset	744 buf,
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	745 'utf-8',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	746 'strict'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	747 ),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	748 u'character buffers are decoded to unicode'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	749 )
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	750
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	751 self.assertRaises(TypeError, unicode, 42, 42, 42)
13410 5157eb7be20d Tests for new surrogate support in the UTF-8 codec. By Bill Tutt. Marc-André Lemburg <mal@egenix.com> parents: 13400 diff changeset	752
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	753 def test_codecs_utf7(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	754 utfTests = [
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	755 (u'A\u2262\u0391.', 'A+ImIDkQ.'), # RFC2152 example
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	756 (u'Hi Mom -\u263a-!', 'Hi Mom -+Jjo--!'), # RFC2152 example
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	757 (u'\u65E5\u672C\u8A9E', '+ZeVnLIqe-'), # RFC2152 example
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	758 (u'Item 3 is \u00a31.', 'Item 3 is +AKM-1.'), # RFC2152 example
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	759 (u'+', '+-'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	760 (u'+-', '+--'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	761 (u'+?', '+-?'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	762 (u'\?', '+AFw?'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	763 (u'+?', '+-?'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	764 (ur'\\?', '+AFwAXA?'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	765 (ur'\\\?', '+AFwAXABc?'),
53740 12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	766 (ur'++--', '+-+---'),
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	767 (u'\U000abcde', '+2m/c3g-'), # surrogate pairs
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	768 (u'/', '/'),
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	769 ]
12051 d89556c04ef9 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: 12025 diff changeset	770
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	771 for (x, y) in utfTests:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	772 self.assertEqual(x.encode('utf-7'), y)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	773
73554 050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	774 # Unpaired surrogates are passed through
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	775 self.assertEqual(u'\uD801'.encode('utf-7'), '+2AE-')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	776 self.assertEqual(u'\uD801x'.encode('utf-7'), '+2AE-x')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	777 self.assertEqual(u'\uDC01'.encode('utf-7'), '+3AE-')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	778 self.assertEqual(u'\uDC01x'.encode('utf-7'), '+3AE-x')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	779 self.assertEqual('+2AE-'.decode('utf-7'), u'\uD801')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	780 self.assertEqual('+2AE-x'.decode('utf-7'), u'\uD801x')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	781 self.assertEqual('+3AE-'.decode('utf-7'), u'\uDC01')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	782 self.assertEqual('+3AE-x'.decode('utf-7'), u'\uDC01x')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	783
73554 050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	784 self.assertEqual(u'\uD801\U000abcde'.encode('utf-7'), '+2AHab9ze-')
050772822bde Issue #13333: The UTF-7 decoder now accepts lone surrogates Antoine Pitrou <solipsis@pitrou.net> parents: 72038 diff changeset	785 self.assertEqual('+2AHab9ze-'.decode('utf-7'), u'\uD801\U000abcde')
12331 d195f17f2927 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: 12248 diff changeset	786
53740 12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	787 # Direct encoded characters
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	788 set_d = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'(),-./:?"
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	789 # Optional direct characters
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	790 set_o = '!"#$%&*;<=>@[]^_`{\|}'
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	791 for c in set_d:
12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	792 self.assertEqual(c.encode('utf7'), c.encode('ascii'))
64708 44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	793 self.assertEqual(c.encode('ascii').decode('utf7'), unicode(c))
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	794 self.assertTrue(c == c.encode('ascii').decode('utf7'))
53740 12d8fd499722 Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Antoine Pitrou <solipsis@pitrou.net> parents: 52161 diff changeset	795 for c in set_o:
64708 44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	796 self.assertEqual(c.encode('ascii').decode('utf7'), unicode(c))
44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	797 self.assertTrue(c == c.encode('ascii').decode('utf7'))
48072 b71d76bf4506 #2242: utf7 decoding crashes on bogus input on some Windows/MSVC versions Antoine Pitrou <solipsis@pitrou.net> parents: 46060 diff changeset	798
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	799 def test_codecs_utf8(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	800 self.assertEqual(u''.encode('utf-8'), '')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	801 self.assertEqual(u'\u20ac'.encode('utf-8'), '\xe2\x82\xac')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	802 self.assertEqual(u'\ud800\udc02'.encode('utf-8'), '\xf0\x90\x80\x82')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	803 self.assertEqual(u'\ud84d\udc56'.encode('utf-8'), '\xf0\xa3\x91\x96')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	804 self.assertEqual(u'\ud800'.encode('utf-8'), '\xed\xa0\x80')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	805 self.assertEqual(u'\udc00'.encode('utf-8'), '\xed\xb0\x80')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	806 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	807 (u'\ud800\udc02'*1000).encode('utf-8'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	808 '\xf0\x90\x80\x82'*1000
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	809 )
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	810 self.assertEqual(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	811 u'\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	812 u'\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	813 u'\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	814 u'\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	815 u'\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	816 u' Nunstuck git und'.encode('utf-8'),
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	817 '\xe6\xad\xa3\xe7\xa2\xba\xe3\x81\xab\xe8\xa8\x80\xe3\x81'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	818 '\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3\xe3\x81\xaf\xe3'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	819 '\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3\x81\xbe'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	820 '\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	821 '\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	822 '\xaa\x9e\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	823 '\xe3\x81\x82\xe3\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	824 '\x9f\xe3\x82\x89\xe3\x82\x81\xe3\x81\xa7\xe3\x81\x99\xe3'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	825 '\x80\x82\xe5\xae\x9f\xe9\x9a\x9b\xe3\x81\xab\xe3\x81\xaf'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	826 '\xe3\x80\x8cWenn ist das Nunstuck git und'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	827 )
22423 b523a470a0ce Do not insert characters for unicode-escape decoders if the error mode Martin v. Löwis <martin@v.loewis.de> parents: 21886 diff changeset	828
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	829 # UTF-8 specific decoding tests
64701 28e6a41c5ba0 Merged revisions 84470-84471,84566-84567,84759 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 63102 diff changeset	830 self.assertEqual(unicode('\xf0\xa3\x91\x96', 'utf-8'), u'\U00023456')
28e6a41c5ba0 Merged revisions 84470-84471,84566-84567,84759 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 63102 diff changeset	831 self.assertEqual(unicode('\xf0\x90\x80\x82', 'utf-8'), u'\U00010002')
28e6a41c5ba0 Merged revisions 84470-84471,84566-84567,84759 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 63102 diff changeset	832 self.assertEqual(unicode('\xe2\x82\xac', 'utf-8'), u'\u20ac')
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	833
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	834 # Other possible utf-8 test cases:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	835 # * strict decoding testing for all of the
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	836 # UTF8_ERROR cases in PyUnicode_DecodeUTF8
12051 d89556c04ef9 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: 12025 diff changeset	837
62711 4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	838 def test_utf8_decode_valid_sequences(self):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	839 sequences = [
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	840 # single byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	841 ('\x00', u'\x00'), ('a', u'a'), ('\x7f', u'\x7f'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	842 # 2 bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	843 ('\xc2\x80', u'\x80'), ('\xdf\xbf', u'\u07ff'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	844 # 3 bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	845 ('\xe0\xa0\x80', u'\u0800'), ('\xed\x9f\xbf', u'\ud7ff'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	846 ('\xee\x80\x80', u'\uE000'), ('\xef\xbf\xbf', u'\uffff'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	847 # 4 bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	848 ('\xF0\x90\x80\x80', u'\U00010000'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	849 ('\xf4\x8f\xbf\xbf', u'\U0010FFFF')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	850 ]
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	851 for seq, res in sequences:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	852 self.assertEqual(seq.decode('utf-8'), res)
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	853
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	854 for ch in map(unichr, range(0, sys.maxunicode)):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	855 self.assertEqual(ch, ch.encode('utf-8').decode('utf-8'))
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	856
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	857 def test_utf8_decode_invalid_sequences(self):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	858 # continuation bytes in a sequence of 2, 3, or 4 bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	859 continuation_bytes = map(chr, range(0x80, 0xC0))
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	860 # start bytes of a 2-byte sequence equivalent to codepoints < 0x7F
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	861 invalid_2B_seq_start_bytes = map(chr, range(0xC0, 0xC2))
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	862 # start bytes of a 4-byte sequence equivalent to codepoints > 0x10FFFF
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	863 invalid_4B_seq_start_bytes = map(chr, range(0xF5, 0xF8))
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	864 invalid_start_bytes = (
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	865 continuation_bytes + invalid_2B_seq_start_bytes +
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	866 invalid_4B_seq_start_bytes + map(chr, range(0xF7, 0x100))
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	867 )
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	868
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	869 for byte in invalid_start_bytes:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	870 self.assertRaises(UnicodeDecodeError, byte.decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	871
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	872 for sb in invalid_2B_seq_start_bytes:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	873 for cb in continuation_bytes:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	874 self.assertRaises(UnicodeDecodeError, (sb+cb).decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	875
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	876 for sb in invalid_4B_seq_start_bytes:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	877 for cb1 in continuation_bytes[:3]:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	878 for cb3 in continuation_bytes[:3]:
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	879 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	880 (sb+cb1+'\x80'+cb3).decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	881
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	882 for cb in map(chr, range(0x80, 0xA0)):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	883 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	884 ('\xE0'+cb+'\x80').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	885 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	886 ('\xE0'+cb+'\xBF').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	887 # XXX: surrogates shouldn't be valid UTF-8!
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	888 # see http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	889 # (table 3-7) and http://www.rfc-editor.org/rfc/rfc3629.txt
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	890 #for cb in map(chr, range(0xA0, 0xC0)):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	891 #self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	892 #('\xED'+cb+'\x80').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	893 #self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	894 #('\xED'+cb+'\xBF').decode, 'utf-8')
68052 dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	895 # but since they are valid on Python 2 add a test for that:
dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	896 for cb, surrogate in zip(map(chr, range(0xA0, 0xC0)),
dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	897 map(unichr, range(0xd800, 0xe000, 64))):
dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	898 encoded = '\xED'+cb+'\x80'
dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	899 self.assertEqual(encoded.decode('utf-8'), surrogate)
dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	900 self.assertEqual(surrogate.encode('utf-8'), encoded)
dc8626e08577 Python 2 can encode/decode surrogates to utf-8. Add a test for this. Ezio Melotti <ezio.melotti@gmail.com> parents: 65662 diff changeset	901
62711 4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	902 for cb in map(chr, range(0x80, 0x90)):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	903 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	904 ('\xF0'+cb+'\x80\x80').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	905 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	906 ('\xF0'+cb+'\xBF\xBF').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	907 for cb in map(chr, range(0x90, 0xC0)):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	908 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	909 ('\xF4'+cb+'\x80\x80').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	910 self.assertRaises(UnicodeDecodeError,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	911 ('\xF4'+cb+'\xBF\xBF').decode, 'utf-8')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	912
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	913 def test_issue8271(self):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	914 # Issue #8271: during the decoding of an invalid UTF-8 byte sequence,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	915 # only the start byte and the continuation byte(s) are now considered
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	916 # invalid, instead of the number of bytes specified by the start byte.
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	917 # See http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf (page 95,
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	918 # table 3-8, Row 2) for more information about the algorithm used.
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	919 FFFD = u'\ufffd'
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	920 sequences = [
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	921 # invalid start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	922 ('\x80', FFFD), # continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	923 ('\x80\x80', FFFD*2), # 2 continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	924 ('\xc0', FFFD),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	925 ('\xc0\xc0', FFFD*2),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	926 ('\xc1', FFFD),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	927 ('\xc1\xc0', FFFD*2),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	928 ('\xc0\xc1', FFFD*2),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	929 # with start byte of a 2-byte sequence
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	930 ('\xc2', FFFD), # only the start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	931 ('\xc2\xc2', FFFD*2), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	932 ('\xc2\xc2\xc2', FFFD*3), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	933 ('\xc2\x41', FFFD+'A'), # invalid continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	934 # with start byte of a 3-byte sequence
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	935 ('\xe1', FFFD), # only the start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	936 ('\xe1\xe1', FFFD*2), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	937 ('\xe1\xe1\xe1', FFFD*3), # 3 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	938 ('\xe1\xe1\xe1\xe1', FFFD*4), # 4 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	939 ('\xe1\x80', FFFD), # only 1 continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	940 ('\xe1\x41', FFFD+'A'), # invalid continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	941 ('\xe1\x41\x80', FFFD+'A'+FFFD), # invalid cb followed by valid cb
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	942 ('\xe1\x41\x41', FFFD+'AA'), # 2 invalid continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	943 ('\xe1\x80\x41', FFFD+'A'), # only 1 valid continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	944 ('\xe1\x80\xe1\x41', FFFD*2+'A'), # 1 valid and the other invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	945 ('\xe1\x41\xe1\x80', FFFD+'A'+FFFD), # 1 invalid and the other valid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	946 # with start byte of a 4-byte sequence
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	947 ('\xf1', FFFD), # only the start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	948 ('\xf1\xf1', FFFD*2), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	949 ('\xf1\xf1\xf1', FFFD*3), # 3 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	950 ('\xf1\xf1\xf1\xf1', FFFD*4), # 4 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	951 ('\xf1\xf1\xf1\xf1\xf1', FFFD*5), # 5 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	952 ('\xf1\x80', FFFD), # only 1 continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	953 ('\xf1\x80\x80', FFFD), # only 2 continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	954 ('\xf1\x80\x41', FFFD+'A'), # 1 valid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	955 ('\xf1\x80\x41\x41', FFFD+'AA'), # 1 valid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	956 ('\xf1\x80\x80\x41', FFFD+'A'), # 2 valid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	957 ('\xf1\x41\x80', FFFD+'A'+FFFD), # 1 invalid cv and 1 valid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	958 ('\xf1\x41\x80\x80', FFFD+'A'+FFFD*2), # 1 invalid cb and 2 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	959 ('\xf1\x41\x80\x41', FFFD+'A'+FFFD+'A'), # 2 invalid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	960 ('\xf1\x41\x41\x80', FFFD+'AA'+FFFD), # 1 valid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	961 ('\xf1\x41\xf1\x80', FFFD+'A'+FFFD),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	962 ('\xf1\x41\x80\xf1', FFFD+'A'+FFFD*2),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	963 ('\xf1\xf1\x80\x41', FFFD*2+'A'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	964 ('\xf1\x41\xf1\xf1', FFFD+'A'+FFFD*2),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	965 # with invalid start byte of a 4-byte sequence (rfc2279)
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	966 ('\xf5', FFFD), # only the start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	967 ('\xf5\xf5', FFFD*2), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	968 ('\xf5\x80', FFFD*2), # only 1 continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	969 ('\xf5\x80\x80', FFFD*3), # only 2 continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	970 ('\xf5\x80\x80\x80', FFFD*4), # 3 continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	971 ('\xf5\x80\x41', FFFD*2+'A'), # 1 valid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	972 ('\xf5\x80\x41\xf5', FFFD*2+'A'+FFFD),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	973 ('\xf5\x41\x80\x80\x41', FFFD+'A'+FFFD*2+'A'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	974 # with invalid start byte of a 5-byte sequence (rfc2279)
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	975 ('\xf8', FFFD), # only the start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	976 ('\xf8\xf8', FFFD*2), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	977 ('\xf8\x80', FFFD*2), # only one continuation byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	978 ('\xf8\x80\x41', FFFD*2 + 'A'), # 1 valid cb and 1 invalid
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	979 ('\xf8\x80\x80\x80\x80', FFFD*5), # invalid 5 bytes seq with 5 bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	980 # with invalid start byte of a 6-byte sequence (rfc2279)
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	981 ('\xfc', FFFD), # only the start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	982 ('\xfc\xfc', FFFD*2), # 2 start bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	983 ('\xfc\x80\x80', FFFD*3), # only 2 continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	984 ('\xfc\x80\x80\x80\x80\x80', FFFD*6), # 6 continuation bytes
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	985 # invalid start byte
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	986 ('\xfe', FFFD),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	987 ('\xfe\x80\x80', FFFD*3),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	988 # other sequences
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	989 ('\xf1\x80\x41\x42\x43', u'\ufffd\x41\x42\x43'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	990 ('\xf1\x80\xff\x42\x43', u'\ufffd\ufffd\x42\x43'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	991 ('\xf1\x80\xc2\x81\x43', u'\ufffd\x81\x43'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	992 ('\x61\xF1\x80\x80\xE1\x80\xC2\x62\x80\x63\x80\xBF\x64',
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	993 u'\x61\uFFFD\uFFFD\uFFFD\x62\uFFFD\x63\uFFFD\uFFFD\x64'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	994 ]
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	995 for n, (seq, res) in enumerate(sequences):
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	996 self.assertRaises(UnicodeDecodeError, seq.decode, 'utf-8', 'strict')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	997 self.assertEqual(seq.decode('utf-8', 'replace'), res)
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	998 self.assertEqual((seq+'b').decode('utf-8', 'replace'), res+'b')
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	999 self.assertEqual(seq.decode('utf-8', 'ignore'),
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	1000 res.replace(u'\uFFFD', ''))
4de13feaea01 Merged revisions 81758-81759 via svnmerge from Ezio Melotti <ezio.melotti@gmail.com> parents: 62176 diff changeset	1001
30059 200165d11a94 Support trailing dots in DNS names. Fixes #782510. Will backport to 2.3. Martin v. Löwis <martin@v.loewis.de> parents: 29164 diff changeset	1002 def test_codecs_idna(self):
200165d11a94 Support trailing dots in DNS names. Fixes #782510. Will backport to 2.3. Martin v. Löwis <martin@v.loewis.de> parents: 29164 diff changeset	1003 # Test whether trailing dot is preserved
200165d11a94 Support trailing dots in DNS names. Fixes #782510. Will backport to 2.3. Martin v. Löwis <martin@v.loewis.de> parents: 29164 diff changeset	1004 self.assertEqual(u"www.python.org.".encode("idna"), "www.python.org.")
200165d11a94 Support trailing dots in DNS names. Fixes #782510. Will backport to 2.3. Martin v. Löwis <martin@v.loewis.de> parents: 29164 diff changeset	1005
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1006 def test_codecs_errors(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1007 # Error handling (encoding)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1008 self.assertRaises(UnicodeError, u'Andr\202 x'.encode, 'ascii')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1009 self.assertRaises(UnicodeError, u'Andr\202 x'.encode, 'ascii','strict')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1010 self.assertEqual(u'Andr\202 x'.encode('ascii','ignore'), "Andr x")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1011 self.assertEqual(u'Andr\202 x'.encode('ascii','replace'), "Andr? x")
56093 f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1012 self.assertEqual(u'Andr\202 x'.encode('ascii', 'replace'),
f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1013 u'Andr\202 x'.encode('ascii', errors='replace'))
f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1014 self.assertEqual(u'Andr\202 x'.encode('ascii', 'ignore'),
f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1015 u'Andr\202 x'.encode(encoding='ascii', errors='ignore'))
12051 d89556c04ef9 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: 12025 diff changeset	1016
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1017 # Error handling (decoding)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1018 self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1019 self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii','strict')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1020 self.assertEqual(unicode('Andr\202 x','ascii','ignore'), u"Andr x")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1021 self.assertEqual(unicode('Andr\202 x','ascii','replace'), u'Andr\uFFFD x')
56093 f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1022 self.assertEqual(u'abcde'.decode('ascii', 'ignore'),
f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1023 u'abcde'.decode('ascii', errors='ignore'))
f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1024 self.assertEqual(u'abcde'.decode('ascii', 'replace'),
f64c0eb8cc62 add keyword arguments support to str/unicode encode and decode #6300 Benjamin Peterson <benjamin@python.org> parents: 55002 diff changeset	1025 u'abcde'.decode(encoding='ascii', errors='replace'))
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1026
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1027 # Error handling (unknown character names)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1028 self.assertEqual("\\N{foo}xx".decode("unicode-escape", "ignore"), u"xx")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1029
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1030 # Error handling (truncated escape sequence)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1031 self.assertRaises(UnicodeError, "\\".decode, "unicode-escape")
12051 d89556c04ef9 Marc-Andre Lemburg: Guido van Rossum <guido@python.org> parents: 12025 diff changeset	1032
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1033 self.assertRaises(TypeError, "hello".decode, "test.unicode1")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1034 self.assertRaises(TypeError, unicode, "hello", "test.unicode2")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1035 self.assertRaises(TypeError, u"hello".encode, "test.unicode1")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1036 self.assertRaises(TypeError, u"hello".encode, "test.unicode2")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1037 # executes PyUnicode_Encode()
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1038 import imp
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1039 self.assertRaises(
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1040 ImportError,
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1041 imp.find_module,
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1042 "non-existing module",
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1043 [u"non-existing dir"]
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1044 )
21886 abedb2418f62 Fix to the UTF-8 encoder: it failed on 0-length input strings. Marc-André Lemburg <mal@egenix.com> parents: 21882 diff changeset	1045
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1046 # Error handling (wrong arguments)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1047 self.assertRaises(TypeError, u"hello".encode, 42, 42, 42)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1048
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1049 # Error handling (PyUnicode_EncodeDecimal())
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1050 self.assertRaises(UnicodeError, int, u"\u0200")
21886 abedb2418f62 Fix to the UTF-8 encoder: it failed on 0-length input strings. Marc-André Lemburg <mal@egenix.com> parents: 21882 diff changeset	1051
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1052 def test_codecs(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1053 # Encoding
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1054 self.assertEqual(u'hello'.encode('ascii'), 'hello')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1055 self.assertEqual(u'hello'.encode('utf-7'), 'hello')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1056 self.assertEqual(u'hello'.encode('utf-8'), 'hello')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1057 self.assertEqual(u'hello'.encode('utf8'), 'hello')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1058 self.assertEqual(u'hello'.encode('utf-16-le'), 'h\000e\000l\000l\000o\000')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1059 self.assertEqual(u'hello'.encode('utf-16-be'), '\000h\000e\000l\000l\000o')
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1060 self.assertEqual(u'hello'.encode('latin-1'), 'hello')
12248 70154e2e9c89 Marc-Andre's third try at this bulk patch seems to work (except that Guido van Rossum <guido@python.org> parents: 12074 diff changeset	1061
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1062 # Roundtrip safety for BMP (just the first 1024 chars)
36056 f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1063 for c in xrange(1024):
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1064 u = unichr(c)
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1065 for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le',
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1066 'utf-16-be', 'raw_unicode_escape',
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1067 'unicode_escape', 'unicode_internal'):
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1068 self.assertEqual(unicode(u.encode(encoding),encoding), u)
12248 70154e2e9c89 Marc-Andre's third try at this bulk patch seems to work (except that Guido van Rossum <guido@python.org> parents: 12074 diff changeset	1069
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1070 # Roundtrip safety for BMP (just the first 256 chars)
36056 f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1071 for c in xrange(256):
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1072 u = unichr(c)
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1073 for encoding in ('latin-1',):
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1074 self.assertEqual(unicode(u.encode(encoding),encoding), u)
12248 70154e2e9c89 Marc-Andre's third try at this bulk patch seems to work (except that Guido van Rossum <guido@python.org> parents: 12074 diff changeset	1075
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1076 # Roundtrip safety for BMP (just the first 128 chars)
36056 f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1077 for c in xrange(128):
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1078 u = unichr(c)
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1079 for encoding in ('ascii',):
f1ae11457d34 Bug #1379994: Fix unicode_escape codecs to encode r'\' as r'\\' Hye-Shik Chang <hyeshik@gmail.com>* parents: 35938 diff changeset	1080 self.assertEqual(unicode(u.encode(encoding),encoding), u)
15305 07f24261c6e6 Make reindent.py happy (convert everything to 4-space indents!). Fred Drake <fdrake@acm.org> parents: 15081 diff changeset	1081
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1082 # Roundtrip safety for non-BMP (just a few chars)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1083 u = u'\U00010001\U00020002\U00030003\U00040004\U00050005'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1084 for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1085 #'raw_unicode_escape',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1086 'unicode_escape', 'unicode_internal'):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1087 self.assertEqual(unicode(u.encode(encoding),encoding), u)
17815 d6df8d371b67 Get rid of the superstitious "~" in dict hashing's "i = (~hash) & mask". Tim Peters <tim.peters@gmail.com> parents: 17655 diff changeset	1088
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1089 # UTF-8 must be roundtrip safe for all UCS-2 code points
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1090 # This excludes surrogates: in the full range, there would be
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1091 # a surrogate pair (\udbff\udc00), which gets converted back
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1092 # to a non-BMP character (\U0010fc00)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1093 u = u''.join(map(unichr, range(0,0xd800)+range(0xe000,0x10000)))
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1094 for encoding in ('utf-8',):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1095 self.assertEqual(unicode(u.encode(encoding),encoding), u)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1096
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1097 def test_codecs_charmap(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1098 # 0-127
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1099 s = ''.join(map(chr, xrange(128)))
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1100 for encoding in (
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1101 'cp037', 'cp1026',
61884 c56fb63c648f #8016: add the CP858 codec (approved by Benjamin). (Also add CP720 to the tests, it was missing there.) Georg Brandl <georg@python.org> parents: 59897 diff changeset	1102 'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
c56fb63c648f #8016: add the CP858 codec (approved by Benjamin). (Also add CP720 to the tests, it was missing there.) Georg Brandl <georg@python.org> parents: 59897 diff changeset	1103 'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1104 'cp863', 'cp865', 'cp866',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1105 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1106 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1107 'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1108 'mac_cyrillic', 'mac_latin2',
12248 70154e2e9c89 Marc-Andre's third try at this bulk patch seems to work (except that Guido van Rossum <guido@python.org> parents: 12074 diff changeset	1109
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1110 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1111 'cp1256', 'cp1257', 'cp1258',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1112 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1113
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1114 'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1115 'cp1006', 'iso8859_8',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1116
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1117 ### These have undefined mappings:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1118 #'cp424',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1119
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1120 ### These fail the round-trip:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1121 #'cp875'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1122
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1123 ):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1124 self.assertEqual(unicode(s, encoding).encode(encoding), s)
15305 07f24261c6e6 Make reindent.py happy (convert everything to 4-space indents!). Fred Drake <fdrake@acm.org> parents: 15081 diff changeset	1125
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1126 # 128-255
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1127 s = ''.join(map(chr, xrange(128, 256)))
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1128 for encoding in (
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1129 'cp037', 'cp1026',
61884 c56fb63c648f #8016: add the CP858 codec (approved by Benjamin). (Also add CP720 to the tests, it was missing there.) Georg Brandl <georg@python.org> parents: 59897 diff changeset	1130 'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
c56fb63c648f #8016: add the CP858 codec (approved by Benjamin). (Also add CP720 to the tests, it was missing there.) Georg Brandl <georg@python.org> parents: 59897 diff changeset	1131 'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1132 'cp863', 'cp865', 'cp866',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1133 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1134 'iso8859_2', 'iso8859_4', 'iso8859_5',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1135 'iso8859_9', 'koi8_r', 'latin_1',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1136 'mac_cyrillic', 'mac_latin2',
15305 07f24261c6e6 Make reindent.py happy (convert everything to 4-space indents!). Fred Drake <fdrake@acm.org> parents: 15081 diff changeset	1137
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1138 ### These have undefined mappings:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1139 #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1140 #'cp1256', 'cp1257', 'cp1258',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1141 #'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1142 #'iso8859_3', 'iso8859_6', 'iso8859_7',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1143 #'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
12390 6edbae6dbcf5 M.-A. Lemburg <mal@lemburg.com>: Fred Drake <fdrake@acm.org> parents: 12365 diff changeset	1144
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1145 ### These fail the round-trip:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1146 #'cp1006', 'cp875', 'iso8859_8',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1147
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1148 ):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1149 self.assertEqual(unicode(s, encoding).encode(encoding), s)
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1150
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1151 def test_concatenation(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1152 self.assertEqual((u"abc" u"def"), u"abcdef")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1153 self.assertEqual(("abc" u"def"), u"abcdef")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1154 self.assertEqual((u"abc" "def"), u"abcdef")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1155 self.assertEqual((u"abc" u"def" "ghi"), u"abcdefghi")
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1156 self.assertEqual(("abc" "def" u"ghi"), u"abcdefghi")
21027 dee0e866653e Fix for bug #480188: printing unicode objects Marc-André Lemburg <mal@egenix.com> parents: 20563 diff changeset	1157
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1158 def test_printing(self):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1159 class BitBucket:
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1160 def write(self, text):
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1161 pass
24598 12e146171f3d Committing patch #591250 which provides "str1 in str2" when str1 is a Barry Warsaw <barry@python.org> parents: 24538 diff changeset	1162
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1163 out = BitBucket()
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1164 print >>out, u'abc'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1165 print >>out, u'abc', u'def'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1166 print >>out, u'abc', 'def'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1167 print >>out, 'abc', u'def'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1168 print >>out, u'abc\n'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1169 print >>out, u'abc\n',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1170 print >>out, u'abc\n',
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1171 print >>out, u'def\n'
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1172 print >>out, u'def\n'
24598 12e146171f3d Committing patch #591250 which provides "str1 in str2" when str1 is a Barry Warsaw <barry@python.org> parents: 24538 diff changeset	1173
29164 4d9017ef7b5f Consider \U-escapes in raw-unicode-escape. Fixes #444514. Martin v. Löwis <martin@v.loewis.de> parents: 28917 diff changeset	1174 def test_ucs4(self):
4d9017ef7b5f Consider \U-escapes in raw-unicode-escape. Fixes #444514. Martin v. Löwis <martin@v.loewis.de> parents: 28917 diff changeset	1175 x = u'\U00100000'
4d9017ef7b5f Consider \U-escapes in raw-unicode-escape. Fixes #444514. Martin v. Löwis <martin@v.loewis.de> parents: 28917 diff changeset	1176 y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
4d9017ef7b5f Consider \U-escapes in raw-unicode-escape. Fixes #444514. Martin v. Löwis <martin@v.loewis.de> parents: 28917 diff changeset	1177 self.assertEqual(x, y)
4d9017ef7b5f Consider \U-escapes in raw-unicode-escape. Fixes #444514. Martin v. Löwis <martin@v.loewis.de> parents: 28917 diff changeset	1178
46060 42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1179 y = r'\U00100000'
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1180 x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1181 self.assertEqual(x, y)
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1182 y = r'\U00010000'
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1183 x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1184 self.assertEqual(x, y)
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1185
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1186 try:
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1187 '\U11111111'.decode("raw-unicode-escape")
46028 8710ba7fba2b #1477: ur'\U0010FFFF' raised in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 45468 diff changeset	1188 except UnicodeDecodeError as e:
46060 42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1189 self.assertEqual(e.start, 0)
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1190 self.assertEqual(e.end, 10)
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1191 else:
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1192 self.fail("Should have raised UnicodeDecodeError")
42285d63755a #1477: ur'\U0010FFFF' used to raise in narrow unicode builds. Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 42026 diff changeset	1193
34931 9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1194 def test_conversion(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1195 # Make sure __unicode__() works properly
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1196 class Foo0:
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1197 def __str__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1198 return "foo"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1199
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1200 class Foo1:
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1201 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1202 return u"foo"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1203
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1204 class Foo2(object):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1205 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1206 return u"foo"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1207
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1208 class Foo3(object):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1209 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1210 return "foo"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1211
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1212 class Foo4(str):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1213 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1214 return "foo"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1215
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1216 class Foo5(unicode):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1217 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1218 return "foo"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1219
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1220 class Foo6(str):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1221 def __str__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1222 return "foos"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1223
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1224 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1225 return u"foou"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1226
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1227 class Foo7(unicode):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1228 def __str__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1229 return "foos"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1230 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1231 return u"foou"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1232
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1233 class Foo8(unicode):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1234 def __new__(cls, content=""):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1235 return unicode.__new__(cls, 2*content)
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1236 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1237 return self
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1238
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1239 class Foo9(unicode):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1240 def __str__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1241 return "string"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1242 def __unicode__(self):
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1243 return "not unicode"
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1244
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1245 self.assertEqual(unicode(Foo0()), u"foo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1246 self.assertEqual(unicode(Foo1()), u"foo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1247 self.assertEqual(unicode(Foo2()), u"foo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1248 self.assertEqual(unicode(Foo3()), u"foo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1249 self.assertEqual(unicode(Foo4("bar")), u"foo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1250 self.assertEqual(unicode(Foo5("bar")), u"foo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1251 self.assertEqual(unicode(Foo6("bar")), u"foou")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1252 self.assertEqual(unicode(Foo7("bar")), u"foou")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1253 self.assertEqual(unicode(Foo8("foo")), u"foofoo")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1254 self.assertEqual(str(Foo9("foo")), "string")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1255 self.assertEqual(unicode(Foo9("foo")), u"not unicode")
9a1b1e1ae653 Make subclasses of int, long, complex, float, and unicode perform type Brett Cannon <bcannon@gmail.com> parents: 33298 diff changeset	1256
37301 f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1257 def test_unicode_repr(self):
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1258 class s1:
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1259 def __repr__(self):
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1260 return '\\n'
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1261
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1262 class s2:
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1263 def __repr__(self):
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1264 return u'\\n'
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1265
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1266 self.assertEqual(repr(s1()), '\\n')
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1267 self.assertEqual(repr(s2()), '\\n')
f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1268
42005 2bd9417dacd5 Prevent expandtabs() on string and unicode objects from causing a segfault when Neal Norwitz <nnorwitz@gmail.com> parents: 39621 diff changeset	1269 def test_expandtabs_overflows_gracefully(self):
2bd9417dacd5 Prevent expandtabs() on string and unicode objects from causing a segfault when Neal Norwitz <nnorwitz@gmail.com> parents: 39621 diff changeset	1270 # This test only affects 32-bit platforms because expandtabs can only take
2bd9417dacd5 Prevent expandtabs() on string and unicode objects from causing a segfault when Neal Norwitz <nnorwitz@gmail.com> parents: 39621 diff changeset	1271 # an int as the max value, not a 64-bit C long. If expandtabs is changed
2bd9417dacd5 Prevent expandtabs() on string and unicode objects from causing a segfault when Neal Norwitz <nnorwitz@gmail.com> parents: 39621 diff changeset	1272 # to take a 64-bit long, this test should apply to all platforms.
42026 75efe6bf8a3e Backport 55873: Neal Norwitz <nnorwitz@gmail.com> parents: 42005 diff changeset	1273 if sys.maxint > (1 << 32) or struct.calcsize('P') != 4:
42005 2bd9417dacd5 Prevent expandtabs() on string and unicode objects from causing a segfault when Neal Norwitz <nnorwitz@gmail.com> parents: 39621 diff changeset	1274 return
2bd9417dacd5 Prevent expandtabs() on string and unicode objects from causing a segfault when Neal Norwitz <nnorwitz@gmail.com> parents: 39621 diff changeset	1275 self.assertRaises(OverflowError, u't\tt\t'.expandtabs, sys.maxint)
37301 f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1276
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1277 def test__format__(self):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1278 def test(value, format, expected):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1279 # test both with and without the trailing 's'
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1280 self.assertEqual(value.__format__(format), expected)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1281 self.assertEqual(value.__format__(format + u's'), expected)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1282
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1283 test(u'', u'', u'')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1284 test(u'abc', u'', u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1285 test(u'abc', u'.3', u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1286 test(u'ab', u'.3', u'ab')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1287 test(u'abcdef', u'.3', u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1288 test(u'abcdef', u'.0', u'')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1289 test(u'abc', u'3.3', u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1290 test(u'abc', u'2.3', u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1291 test(u'abc', u'2.2', u'ab')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1292 test(u'abc', u'3.2', u'ab ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1293 test(u'result', u'x<0', u'result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1294 test(u'result', u'x<5', u'result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1295 test(u'result', u'x<6', u'result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1296 test(u'result', u'x<7', u'resultx')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1297 test(u'result', u'x<8', u'resultxx')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1298 test(u'result', u' <7', u'result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1299 test(u'result', u'<7', u'result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1300 test(u'result', u'>7', u' result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1301 test(u'result', u'>8', u' result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1302 test(u'result', u'^8', u' result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1303 test(u'result', u'^9', u' result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1304 test(u'result', u'^10', u' result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1305 test(u'a', u'10000', u'a' + u' ' * 9999)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1306 test(u'', u'10000', u' ' * 10000)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1307 test(u'', u'10000000', u' ' * 10000000)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1308
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1309 # test mixing unicode and str
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1310 self.assertEqual(u'abc'.__format__('s'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1311 self.assertEqual(u'abc'.__format__('->10s'), u'-------abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1312
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1313 def test_format(self):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1314 self.assertEqual(u''.format(), u'')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1315 self.assertEqual(u'a'.format(), u'a')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1316 self.assertEqual(u'ab'.format(), u'ab')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1317 self.assertEqual(u'a{{'.format(), u'a{')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1318 self.assertEqual(u'a}}'.format(), u'a}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1319 self.assertEqual(u'{{b'.format(), u'{b')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1320 self.assertEqual(u'}}b'.format(), u'}b')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1321 self.assertEqual(u'a{{b'.format(), u'a{b')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1322
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1323 # examples from the PEP:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1324 import datetime
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1325 self.assertEqual(u"My name is {0}".format(u'Fred'), u"My name is Fred")
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1326 self.assertEqual(u"My name is {0[name]}".format(dict(name=u'Fred')),
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1327 u"My name is Fred")
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1328 self.assertEqual(u"My name is {0} :-{{}}".format(u'Fred'),
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1329 u"My name is Fred :-{}")
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1330
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1331 # datetime.__format__ doesn't work with unicode
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1332 #d = datetime.date(2007, 8, 18)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1333 #self.assertEqual("The year is {0.year}".format(d),
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1334 # "The year is 2007")
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1335
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1336 # classes we'll use for testing
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1337 class C:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1338 def __init__(self, x=100):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1339 self._x = x
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1340 def __format__(self, spec):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1341 return spec
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1342
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1343 class D:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1344 def __init__(self, x):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1345 self.x = x
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1346 def __format__(self, spec):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1347 return str(self.x)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1348
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1349 # class with __str__, but no __format__
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1350 class E:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1351 def __init__(self, x):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1352 self.x = x
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1353 def __str__(self):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1354 return u'E(' + self.x + u')'
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1355
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1356 # class with __repr__, but no __format__ or __str__
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1357 class F:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1358 def __init__(self, x):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1359 self.x = x
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1360 def __repr__(self):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1361 return u'F(' + self.x + u')'
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1362
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1363 # class with __format__ that forwards to string, for some format_spec's
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1364 class G:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1365 def __init__(self, x):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1366 self.x = x
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1367 def __str__(self):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1368 return u"string is " + self.x
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1369 def __format__(self, format_spec):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1370 if format_spec == 'd':
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1371 return u'G(' + self.x + u')'
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1372 return object.__format__(self, format_spec)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1373
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1374 # class that returns a bad type from __format__
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1375 class H:
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1376 def __format__(self, format_spec):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1377 return 1.0
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1378
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1379 class I(datetime.date):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1380 def __format__(self, format_spec):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1381 return self.strftime(format_spec)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1382
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1383 class J(int):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1384 def __format__(self, format_spec):
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1385 return int.__format__(self * 2, format_spec)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1386
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1387
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1388 self.assertEqual(u''.format(), u'')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1389 self.assertEqual(u'abc'.format(), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1390 self.assertEqual(u'{0}'.format(u'abc'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1391 self.assertEqual(u'{0:}'.format(u'abc'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1392 self.assertEqual(u'X{0}'.format(u'abc'), u'Xabc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1393 self.assertEqual(u'{0}X'.format(u'abc'), u'abcX')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1394 self.assertEqual(u'X{0}Y'.format(u'abc'), u'XabcY')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1395 self.assertEqual(u'{1}'.format(1, u'abc'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1396 self.assertEqual(u'X{1}'.format(1, u'abc'), u'Xabc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1397 self.assertEqual(u'{1}X'.format(1, u'abc'), u'abcX')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1398 self.assertEqual(u'X{1}Y'.format(1, u'abc'), u'XabcY')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1399 self.assertEqual(u'{0}'.format(-15), u'-15')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1400 self.assertEqual(u'{0}{1}'.format(-15, u'abc'), u'-15abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1401 self.assertEqual(u'{0}X{1}'.format(-15, u'abc'), u'-15Xabc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1402 self.assertEqual(u'{{'.format(), u'{')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1403 self.assertEqual(u'}}'.format(), u'}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1404 self.assertEqual(u'{{}}'.format(), u'{}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1405 self.assertEqual(u'{{x}}'.format(), u'{x}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1406 self.assertEqual(u'{{{0}}}'.format(123), u'{123}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1407 self.assertEqual(u'{{{{0}}}}'.format(), u'{{0}}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1408 self.assertEqual(u'}}{{'.format(), u'}{')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1409 self.assertEqual(u'}}x{{'.format(), u'}x{')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1410
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1411 # weird field names
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1412 self.assertEqual(u"{0[foo-bar]}".format({u'foo-bar':u'baz'}), u'baz')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1413 self.assertEqual(u"{0[foo bar]}".format({u'foo bar':u'baz'}), u'baz')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1414 self.assertEqual(u"{0[ ]}".format({u' ':3}), u'3')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1415
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1416 self.assertEqual(u'{foo._x}'.format(foo=C(20)), u'20')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1417 self.assertEqual(u'{1}{0}'.format(D(10), D(20)), u'2010')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1418 self.assertEqual(u'{0._x.x}'.format(C(D(u'abc'))), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1419 self.assertEqual(u'{0[0]}'.format([u'abc', u'def']), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1420 self.assertEqual(u'{0[1]}'.format([u'abc', u'def']), u'def')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1421 self.assertEqual(u'{0[1][0]}'.format([u'abc', [u'def']]), u'def')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1422 self.assertEqual(u'{0[1][0].x}'.format(['abc', [D(u'def')]]), u'def')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1423
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1424 # strings
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1425 self.assertEqual(u'{0:.3s}'.format(u'abc'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1426 self.assertEqual(u'{0:.3s}'.format(u'ab'), u'ab')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1427 self.assertEqual(u'{0:.3s}'.format(u'abcdef'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1428 self.assertEqual(u'{0:.0s}'.format(u'abcdef'), u'')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1429 self.assertEqual(u'{0:3.3s}'.format(u'abc'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1430 self.assertEqual(u'{0:2.3s}'.format(u'abc'), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1431 self.assertEqual(u'{0:2.2s}'.format(u'abc'), u'ab')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1432 self.assertEqual(u'{0:3.2s}'.format(u'abc'), u'ab ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1433 self.assertEqual(u'{0:x<0s}'.format(u'result'), u'result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1434 self.assertEqual(u'{0:x<5s}'.format(u'result'), u'result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1435 self.assertEqual(u'{0:x<6s}'.format(u'result'), u'result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1436 self.assertEqual(u'{0:x<7s}'.format(u'result'), u'resultx')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1437 self.assertEqual(u'{0:x<8s}'.format(u'result'), u'resultxx')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1438 self.assertEqual(u'{0: <7s}'.format(u'result'), u'result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1439 self.assertEqual(u'{0:<7s}'.format(u'result'), u'result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1440 self.assertEqual(u'{0:>7s}'.format(u'result'), u' result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1441 self.assertEqual(u'{0:>8s}'.format(u'result'), u' result')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1442 self.assertEqual(u'{0:^8s}'.format(u'result'), u' result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1443 self.assertEqual(u'{0:^9s}'.format(u'result'), u' result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1444 self.assertEqual(u'{0:^10s}'.format(u'result'), u' result ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1445 self.assertEqual(u'{0:10000}'.format(u'a'), u'a' + u' ' * 9999)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1446 self.assertEqual(u'{0:10000}'.format(u''), u' ' * 10000)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1447 self.assertEqual(u'{0:10000000}'.format(u''), u' ' * 10000000)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1448
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1449 # format specifiers for user defined type
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1450 self.assertEqual(u'{0:abc}'.format(C()), u'abc')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1451
64707 274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1452 # !r and !s coercions
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1453 self.assertEqual(u'{0!s}'.format(u'Hello'), u'Hello')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1454 self.assertEqual(u'{0!s:}'.format(u'Hello'), u'Hello')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1455 self.assertEqual(u'{0!s:15}'.format(u'Hello'), u'Hello ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1456 self.assertEqual(u'{0!s:15s}'.format(u'Hello'), u'Hello ')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1457 self.assertEqual(u'{0!r}'.format(u'Hello'), u"u'Hello'")
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1458 self.assertEqual(u'{0!r:}'.format(u'Hello'), u"u'Hello'")
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1459 self.assertEqual(u'{0!r}'.format(F(u'Hello')), u'F(Hello)')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1460
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1461 # test fallback to object.__format__
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1462 self.assertEqual(u'{0}'.format({}), u'{}')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1463 self.assertEqual(u'{0}'.format([]), u'[]')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1464 self.assertEqual(u'{0}'.format([1]), u'[1]')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1465 self.assertEqual(u'{0}'.format(E(u'data')), u'E(data)')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1466 self.assertEqual(u'{0:d}'.format(G(u'data')), u'G(data)')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1467 self.assertEqual(u'{0!s}'.format(G(u'data')), u'string is data')
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1468
64707 274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1469 msg = 'object.__format__ with a non-empty format string is deprecated'
274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1470 with test_support.check_warnings((msg, PendingDeprecationWarning)):
274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1471 self.assertEqual(u'{0:^10}'.format(E(u'data')), u' E(data) ')
274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1472 self.assertEqual(u'{0:^10s}'.format(E(u'data')), u' E(data) ')
274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1473 self.assertEqual(u'{0:>15s}'.format(G(u'data')), u' string is data')
274a0bf46871 Check PendingDeprecationWarning after issue #7994. Florent Xicluna <florent.xicluna@gmail.com> parents: 64701 diff changeset	1474
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1475 self.assertEqual(u"{0:date: %Y-%m-%d}".format(I(year=2007,
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1476 month=8,
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1477 day=27)),
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1478 u"date: 2007-08-27")
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1479
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1480 # test deriving from a builtin type and overriding __format__
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1481 self.assertEqual(u"{0}".format(J(10)), u"20")
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1482
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1483
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1484 # string format specifiers
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1485 self.assertEqual(u'{0:}'.format('a'), u'a')
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1486
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1487 # computed format specifiers
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1488 self.assertEqual(u"{0:.{1}}".format(u'hello world', 5), u'hello')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1489 self.assertEqual(u"{0:.{1}s}".format(u'hello world', 5), u'hello')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1490 self.assertEqual(u"{0:.{precision}s}".format('hello world', precision=5), u'hello')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1491 self.assertEqual(u"{0:{width}.{precision}s}".format('hello world', width=10, precision=5), u'hello ')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1492 self.assertEqual(u"{0:{width}.{precision}s}".format('hello world', width='10', precision='5'), u'hello ')
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1493
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1494 # test various errors
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1495 self.assertRaises(ValueError, u'{'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1496 self.assertRaises(ValueError, u'}'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1497 self.assertRaises(ValueError, u'a{'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1498 self.assertRaises(ValueError, u'a}'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1499 self.assertRaises(ValueError, u'{a'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1500 self.assertRaises(ValueError, u'}a'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1501 self.assertRaises(IndexError, u'{0}'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1502 self.assertRaises(IndexError, u'{1}'.format, u'abc')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1503 self.assertRaises(KeyError, u'{x}'.format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1504 self.assertRaises(ValueError, u"}{".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1505 self.assertRaises(ValueError, u"{".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1506 self.assertRaises(ValueError, u"}".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1507 self.assertRaises(ValueError, u"abc{0:{}".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1508 self.assertRaises(ValueError, u"{0".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1509 self.assertRaises(IndexError, u"{0.}".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1510 self.assertRaises(ValueError, u"{0.}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1511 self.assertRaises(IndexError, u"{0[}".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1512 self.assertRaises(ValueError, u"{0[}".format, [])
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1513 self.assertRaises(KeyError, u"{0]}".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1514 self.assertRaises(ValueError, u"{0.[]}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1515 self.assertRaises(ValueError, u"{0..foo}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1516 self.assertRaises(ValueError, u"{0[0}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1517 self.assertRaises(ValueError, u"{0[0:foo}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1518 self.assertRaises(KeyError, u"{c]}".format)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1519 self.assertRaises(ValueError, u"{{ {{{0}}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1520 self.assertRaises(ValueError, u"{0}}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1521 self.assertRaises(KeyError, u"{foo}".format, bar=3)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1522 self.assertRaises(ValueError, u"{0!x}".format, 3)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1523 self.assertRaises(ValueError, u"{0!}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1524 self.assertRaises(ValueError, u"{0!rs}".format, 0)
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1525 self.assertRaises(ValueError, u"{!}".format)
52161 1f96d733a743 Unicode format tests weren't actually testing unicode. This was probably due to the original backport from py3k. Eric Smith <eric@trueblade.com> parents: 52157 diff changeset	1526 self.assertRaises(IndexError, u"{:}".format)
1f96d733a743 Unicode format tests weren't actually testing unicode. This was probably due to the original backport from py3k. Eric Smith <eric@trueblade.com> parents: 52157 diff changeset	1527 self.assertRaises(IndexError, u"{:s}".format)
1f96d733a743 Unicode format tests weren't actually testing unicode. This was probably due to the original backport from py3k. Eric Smith <eric@trueblade.com> parents: 52157 diff changeset	1528 self.assertRaises(IndexError, u"{}".format)
62176 3e86254039b9 Merged revisions 81825 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 62170 diff changeset	1529 big = u"23098475029384702983476098230754973209482573"
3e86254039b9 Merged revisions 81825 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 62170 diff changeset	1530 self.assertRaises(ValueError, (u"{" + big + u"}").format)
3e86254039b9 Merged revisions 81825 via svnmerge from Benjamin Peterson <benjamin@python.org> parents: 62170 diff changeset	1531 self.assertRaises(ValueError, (u"{[" + big + u"]}").format, [0])
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1532
54268 d2d028f65c7c Merged revisions 72848 via svnmerge from Eric Smith <eric@trueblade.com> parents: 52162 diff changeset	1533 # issue 6089
d2d028f65c7c Merged revisions 72848 via svnmerge from Eric Smith <eric@trueblade.com> parents: 52162 diff changeset	1534 self.assertRaises(ValueError, u"{0[0]x}".format, [None])
d2d028f65c7c Merged revisions 72848 via svnmerge from Eric Smith <eric@trueblade.com> parents: 52162 diff changeset	1535 self.assertRaises(ValueError, u"{0[0](10)}".format, [None])
d2d028f65c7c Merged revisions 72848 via svnmerge from Eric Smith <eric@trueblade.com> parents: 52162 diff changeset	1536
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1537 # can't have a replacement on the field name portion
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1538 self.assertRaises(TypeError, u'{0[{1}]}'.format, u'abcdefg', 4)
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1539
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1540 # exceed maximum recursion depth
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1541 self.assertRaises(ValueError, u"{0:{1:{2}}}".format, u'abc', u's', u'')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1542 self.assertRaises(ValueError, u"{0:{1:{2:{3:{4:{5:{6}}}}}}}".format,
45381 b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1543 0, 1, 2, 3, 4, 5, 6, 7)
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1544
b7231bf6bfb7 Backport of PEP 3101, Advanced String Formatting, from py3k. Eric Smith <eric@trueblade.com> parents: 42310 diff changeset	1545 # string format spec errors
52162 4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1546 self.assertRaises(ValueError, u"{0:-s}".format, u'')
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1547 self.assertRaises(ValueError, format, u"", u"-")
4e1a1576f1e5 Merged revisions 70368 via svnmerge from Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1548 self.assertRaises(ValueError, u"{0:=s}".format, u'')
37301 f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1549
45391 3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1550 # test combining string and unicode
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1551 self.assertEqual(u"foo{0}".format('bar'), u'foobar')
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1552 # This will try to convert the argument from unicode to str, which
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1553 # will succeed
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1554 self.assertEqual("foo{0}".format(u'bar'), 'foobar')
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1555 # This will try to convert the argument from unicode to str, which
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1556 # will fail
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1557 self.assertRaises(UnicodeEncodeError, "foo{0}".format, u'\u1000bar')
3fc586307d66 Added code to correct combining str and unicode in ''.format(). Added test case. Eric Smith <eric@trueblade.com> parents: 45381 diff changeset	1558
52157 3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1559 def test_format_auto_numbering(self):
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1560 class C:
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1561 def __init__(self, x=100):
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1562 self._x = x
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1563 def __format__(self, spec):
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1564 return spec
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1565
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1566 self.assertEqual(u'{}'.format(10), u'10')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1567 self.assertEqual(u'{:5}'.format('s'), u's ')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1568 self.assertEqual(u'{!r}'.format('s'), u"'s'")
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1569 self.assertEqual(u'{._x}'.format(C(10)), u'10')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1570 self.assertEqual(u'{[1]}'.format([1, 2]), u'2')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1571 self.assertEqual(u'{[a]}'.format({'a':4, 'b':2}), u'4')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1572 self.assertEqual(u'a{}b{}c'.format(0, 1), u'a0b1c')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1573
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1574 self.assertEqual(u'a{:{}}b'.format('x', '^10'), u'a x b')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1575 self.assertEqual(u'a{:{}x}b'.format(20, '#'), u'a0x14b')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1576
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1577 # can't mix and match numbering and auto-numbering
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1578 self.assertRaises(ValueError, u'{}{1}'.format, 1, 2)
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1579 self.assertRaises(ValueError, u'{1}{}'.format, 1, 2)
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1580 self.assertRaises(ValueError, u'{:{1}}'.format, 1, 2)
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1581 self.assertRaises(ValueError, u'{0:{}}'.format, 1, 2)
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1582
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1583 # can mix and match auto-numbering and named
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1584 self.assertEqual(u'{f}{}'.format(4, f='test'), u'test4')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1585 self.assertEqual(u'{}{f}'.format(4, f='test'), u'4test')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1586 self.assertEqual(u'{:{f}}{g}{}'.format(1, 3, g='g', f=2), u' 1g3')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1587 self.assertEqual(u'{f:{}}{}{g}'.format(2, 4, f=1, g='g'), u' 14g')
3f18d609ac1b Issue 5237, Allow auto-numbered replacement fields in str.format() strings. Eric Smith <eric@trueblade.com> parents: 49031 diff changeset	1588
48117 a94f136b5283 Correct a crash when two successive unicode allocations fail with a MemoryError: Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 48070 diff changeset	1589 def test_raiseMemError(self):
a94f136b5283 Correct a crash when two successive unicode allocations fail with a MemoryError: Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 48070 diff changeset	1590 # Ensure that the freelist contains a consistent object, even
a94f136b5283 Correct a crash when two successive unicode allocations fail with a MemoryError: Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 48070 diff changeset	1591 # when a string allocation fails with a MemoryError.
a94f136b5283 Correct a crash when two successive unicode allocations fail with a MemoryError: Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 48070 diff changeset	1592 # This used to crash the interpreter,
a94f136b5283 Correct a crash when two successive unicode allocations fail with a MemoryError: Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 48070 diff changeset	1593 # or leak references when the number was smaller.
49031 433220a60a8d #3601: test_unicode.test_raiseMemError fails in UCS4 Antoine Pitrou <solipsis@pitrou.net> parents: 48268 diff changeset	1594 charwidth = 4 if sys.maxunicode >= 0x10000 else 2
433220a60a8d #3601: test_unicode.test_raiseMemError fails in UCS4 Antoine Pitrou <solipsis@pitrou.net> parents: 48268 diff changeset	1595 # Note: sys.maxsize is half of the actual max allocation because of
433220a60a8d #3601: test_unicode.test_raiseMemError fails in UCS4 Antoine Pitrou <solipsis@pitrou.net> parents: 48268 diff changeset	1596 # the signedness of Py_ssize_t.
433220a60a8d #3601: test_unicode.test_raiseMemError fails in UCS4 Antoine Pitrou <solipsis@pitrou.net> parents: 48268 diff changeset	1597 alloc = lambda: u"a" * (sys.maxsize // charwidth * 2)
48268 d7d7139d5840 #3556: test_raiseMemError consumes an insane amount of memory Antoine Pitrou <solipsis@pitrou.net> parents: 48117 diff changeset	1598 self.assertRaises(MemoryError, alloc)
d7d7139d5840 #3556: test_raiseMemError consumes an insane amount of memory Antoine Pitrou <solipsis@pitrou.net> parents: 48117 diff changeset	1599 self.assertRaises(MemoryError, alloc)
48117 a94f136b5283 Correct a crash when two successive unicode allocations fail with a MemoryError: Amaury Forgeot d'Arc <amauryfa@gmail.com> parents: 48070 diff changeset	1600
59900 6151d09ce039 Merged revisions 79278,79280 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 59087 diff changeset	1601 def test_format_subclass(self):
6151d09ce039 Merged revisions 79278,79280 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 59087 diff changeset	1602 class U(unicode):
6151d09ce039 Merged revisions 79278,79280 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 59087 diff changeset	1603 def __unicode__(self):
6151d09ce039 Merged revisions 79278,79280 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 59087 diff changeset	1604 return u'__unicode__ overridden'
6151d09ce039 Merged revisions 79278,79280 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 59087 diff changeset	1605 u = U(u'xxx')
64701 28e6a41c5ba0 Merged revisions 84470-84471,84566-84567,84759 via svnmerge from Florent Xicluna <florent.xicluna@gmail.com> parents: 63102 diff changeset	1606 self.assertEqual("%s" % u, u'__unicode__ overridden')
64708 44199aa8932b Strengthen test_unicode with explicit type checking for assertEqual tests. Florent Xicluna <florent.xicluna@gmail.com> parents: 64707 diff changeset	1607 self.assertEqual("{}".format(u), '__unicode__ overridden')
59900 6151d09ce039 Merged revisions 79278,79280 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 59087 diff changeset	1608
73682 0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1609 def test_encode_decimal(self):
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1610 from _testcapi import unicode_encodedecimal
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1611 self.assertEqual(unicode_encodedecimal(u'123'),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1612 b'123')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1613 self.assertEqual(unicode_encodedecimal(u'\u0663.\u0661\u0664'),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1614 b'3.14')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1615 self.assertEqual(unicode_encodedecimal(u"\N{EM SPACE}3.14\N{EN SPACE}"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1616 b' 3.14 ')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1617 self.assertRaises(UnicodeEncodeError,
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1618 unicode_encodedecimal, u"123\u20ac", "strict")
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1619 self.assertEqual(unicode_encodedecimal(u"123\u20ac", "replace"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1620 b'123?')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1621 self.assertEqual(unicode_encodedecimal(u"123\u20ac", "ignore"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1622 b'123')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1623 self.assertEqual(unicode_encodedecimal(u"123\u20ac", "xmlcharrefreplace"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1624 b'123€')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1625 self.assertEqual(unicode_encodedecimal(u"123\u20ac", "backslashreplace"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1626 b'123\\u20ac')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1627 self.assertEqual(unicode_encodedecimal(u"123\u20ac\N{EM SPACE}", "replace"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1628 b'123? ')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1629 self.assertEqual(unicode_encodedecimal(u"123\u20ac\u20ac", "replace"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1630 b'123??')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1631 self.assertEqual(unicode_encodedecimal(u"123\u20ac\u0660", "replace"),
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1632 b'123?0')
0cd197f13400 Issue #13093: Fix error handling on PyUnicode_EncodeDecimal() Victor Stinner <victor.stinner@haypocalc.com> parents: 73554 diff changeset	1633
37301 f284e854fe72 Fixed bug #1459029 - unicode reprs were double-escaped. Anthony Baxter <anthonybaxter@gmail.com> parents: 36341 diff changeset	1634
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1635 def test_main():
41534 6c4d7678af5e Standardize on test.test_support.run_unittest() (as opposed to a mix of run_unittest() and run_suite()). Also, add functionality to run_unittest() that admits usage of unittest.TestLoader.loadTestsFromModule(). Collin Winter <collinw@gmail.com> parents: 39621 diff changeset	1636 test_support.run_unittest(__name__)
27304 a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1637
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1638 if __name__ == "__main__":
a555230be3cb Port test_unicode.py to PyUnit and add tests for error Walter Dörwald <walter@livinglogic.de> parents: 27176 diff changeset	1639 test_main()

Mercurial > cpython-lru_cache-weakref

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