Lines Matching refs:unicode
1 """ Test script for the Unicode implementation.
25 return (42, 42) # no unicode
27 return (42, 42) # no unicode
41 type2test = unicode
44 # strict assertEqual method: reject implicit bytes/unicode equality
46 if isinstance(first, unicode) or isinstance(second, unicode):
47 self.assertIsInstance(first, unicode)
48 self.assertIsInstance(second, unicode)
62 class usub(unicode):
64 return 'usub(%r)' % unicode.__repr__(self)
111 # Test repr works on wide unicode escapes without overflow.
147 for (t1, t2) in ((str, unicode), (unicode, str)):
160 for (t1, t2) in ((str, unicode), (unicode, str)):
210 # method call forwarded from str implementation because of unicode argument
227 # Move these tests to a Unicode collation module test...
341 # apparently there are no titlecased (Lt) non-BMP chars in Unicode 6
353 # apparently there are no non-BMP spaces chars in Unicode 6
451 meth = getattr(unicode, meth_name)
457 meth = getattr(unicode, meth_name)
529 # Testing Unicode contains method
594 # Testing Unicode formatting strings...
612 self.assertEqual(u"%c" % char, unicode(char))
613 self.assertEqual(u"%c" % num, unicode(char))
620 self.assertEqual(uchar, u"%c" % uchar) # and unicode chars
666 self.assertIn('unicode', exc)
676 # unicode(obj) tests (this maps to PyObject_Unicode() at C level)
679 unicode(u'unicode remains unicode'),
680 u'unicode remains unicode'
683 class UnicodeSubclass(unicode):
687 unicode(UnicodeSubclass('unicode subclass becomes unicode')),
688 u'unicode subclass becomes unicode'
692 unicode('strings are converted to unicode'),
693 u'strings are converted to unicode'
703 unicode(UnicodeCompat('__unicode__ compatible objects are recognized')),
713 unicode(StringCompat('__str__ compatible objects are recognized')),
717 unicode(obj) is compatible to str():
719 o = StringCompat('unicode(obj) is compatible to str()')
720 self.assertEqual(unicode(o), u'unicode(obj) is compatible to str()')
721 self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
732 self.assertEqual(unicode(obj), unicode(str(obj)))
734 # unicode(obj, encoding, error) tests (this maps to
740 unicode,
741 u'decoding unicode is not supported',
747 unicode('strings are decoded to unicode', 'utf-8', 'strict'),
748 u'strings are decoded to unicode'
753 buf = buffer('character buffers are decoded to unicode')
755 unicode(
760 u'character buffers are decoded to unicode'
763 self.assertRaises(TypeError, unicode, 42, 42, 42)
805 self.assertEqual(c.encode('ascii').decode('utf7'), unicode(c))
808 self.assertEqual(c.encode('ascii').decode('utf7'), unicode(c))
842 self.assertEqual(unicode('\xf0\xa3\x91\x96', 'utf-8'), u'\U00023456')
843 self.assertEqual(unicode('\xf0\x90\x80\x82', 'utf-8'), u'\U00010002')
844 self.assertEqual(unicode('\xe2\x82\xac', 'utf-8'), u'\u20ac')
900 # see http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
929 # See http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf (page 95,
1030 self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii')
1031 self.assertRaises(UnicodeError, unicode, 'Andr\202 x', 'ascii','strict')
1032 self.assertEqual(unicode('Andr\202 x','ascii','ignore'), u"Andr x")
1033 self.assertEqual(unicode('Andr\202 x','ascii','replace'), u'Andr\uFFFD x')
1040 self.assertEqual("\\N{foo}xx".decode("unicode-escape", "ignore"), u"xx")
1043 self.assertRaises(UnicodeError, "\\".decode, "unicode-escape")
1046 self.assertRaises(TypeError, unicode, "hello", "test.unicode2")
1080 self.assertEqual(unicode(u.encode(encoding),encoding), u)
1086 self.assertEqual(unicode(u.encode(encoding),encoding), u)
1092 self.assertEqual(unicode(u.encode(encoding),encoding), u)
1099 self.assertEqual(unicode(u.encode(encoding),encoding), u)
1107 self.assertEqual(unicode(u.encode(encoding),encoding), u)
1136 self.assertEqual(unicode(s, encoding).encode(encoding), s)
1161 self.assertEqual(unicode(s, encoding).encode(encoding), s)
1188 y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
1192 x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
1195 x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
1199 '\U11111111'.decode("raw-unicode-escape")
1228 class Foo5(unicode):
1239 class Foo7(unicode):
1245 class Foo8(unicode):
1247 return unicode.__new__(cls, 2*content)
1251 class Foo9(unicode):
1255 return "not unicode"
1257 self.assertEqual(unicode(Foo0()), u"foo")
1258 self.assertEqual(unicode(Foo1()), u"foo")
1259 self.assertEqual(unicode(Foo2()), u"foo")
1260 self.assertEqual(unicode(Foo3()), u"foo")
1261 self.assertEqual(unicode(Foo4("bar")), u"foo")
1262 self.assertEqual(unicode(Foo5("bar")), u"foo")
1263 self.assertEqual(unicode(Foo6("bar")), u"foou")
1264 self.assertEqual(unicode(Foo7("bar")), u"foou")
1265 self.assertEqual(unicode(Foo8("foo")), u"foofoo")
1267 self.assertEqual(unicode(Foo9("foo")), u"not unicode")
1321 # test mixing unicode and str
1343 # datetime.__format__ doesn't work with unicode
1562 # test combining string and unicode
1564 # This will try to convert the argument from unicode to str, which
1567 # This will try to convert the argument from unicode to str, which
1629 class U(unicode):
