mirror of
https://github.com/python/cpython.git
synced 2025-11-25 04:34:37 +00:00
Rip out all the u"..." literals and calls to unicode().
This commit is contained in:
Guido van Rossum
parent
572dbf8f13
commit
ef87d6ed94
200 changed files with 18074 additions and 18074 deletions
|
|
@ -30,9 +30,9 @@ class Test_MultibyteCodec(unittest.TestCase):
|
|||
|
||||
def test_nullcoding(self):
|
||||
for enc in ALL_CJKENCODINGS:
|
||||
self.assertEqual(''.decode(enc), u'')
|
||||
self.assertEqual(unicode('', enc), u'')
|
||||
self.assertEqual(u''.encode(enc), '')
|
||||
self.assertEqual(''.decode(enc), '')
|
||||
self.assertEqual(str('', enc), '')
|
||||
self.assertEqual(''.encode(enc), '')
|
||||
|
||||
def test_str_decode(self):
|
||||
for enc in ALL_CJKENCODINGS:
|
||||
|
|
@ -40,7 +40,7 @@ class Test_MultibyteCodec(unittest.TestCase):
|
|||
|
||||
def test_errorcallback_longindex(self):
|
||||
dec = codecs.getdecoder('euc-kr')
|
||||
myreplace = lambda exc: (u'', sys.maxint+1)
|
||||
myreplace = lambda exc: ('', sys.maxint+1)
|
||||
codecs.register_error('test.cjktest', myreplace)
|
||||
self.assertRaises(IndexError, dec,
|
||||
'apple\x92ham\x93spam', 'test.cjktest')
|
||||
|
|
@ -58,14 +58,14 @@ class Test_IncrementalEncoder(unittest.TestCase):
|
|||
def test_stateless(self):
|
||||
# cp949 encoder isn't stateful at all.
|
||||
encoder = codecs.getincrementalencoder('cp949')()
|
||||
self.assertEqual(encoder.encode(u'\ud30c\uc774\uc36c \ub9c8\uc744'),
|
||||
self.assertEqual(encoder.encode('\ud30c\uc774\uc36c \ub9c8\uc744'),
|
||||
'\xc6\xc4\xc0\xcc\xbd\xe3 \xb8\xb6\xc0\xbb')
|
||||
self.assertEqual(encoder.reset(), None)
|
||||
self.assertEqual(encoder.encode(u'\u2606\u223c\u2606', True),
|
||||
self.assertEqual(encoder.encode('\u2606\u223c\u2606', True),
|
||||
'\xa1\xd9\xa1\xad\xa1\xd9')
|
||||
self.assertEqual(encoder.reset(), None)
|
||||
self.assertEqual(encoder.encode(u'', True), '')
|
||||
self.assertEqual(encoder.encode(u'', False), '')
|
||||
self.assertEqual(encoder.encode('', True), '')
|
||||
self.assertEqual(encoder.encode('', False), '')
|
||||
self.assertEqual(encoder.reset(), None)
|
||||
|
||||
def test_stateful(self):
|
||||
|
|
@ -75,29 +75,29 @@ class Test_IncrementalEncoder(unittest.TestCase):
|
|||
# U+0300 => ABDC
|
||||
|
||||
encoder = codecs.getincrementalencoder('jisx0213')()
|
||||
self.assertEqual(encoder.encode(u'\u00e6\u0300'), '\xab\xc4')
|
||||
self.assertEqual(encoder.encode(u'\u00e6'), '')
|
||||
self.assertEqual(encoder.encode(u'\u0300'), '\xab\xc4')
|
||||
self.assertEqual(encoder.encode(u'\u00e6', True), '\xa9\xdc')
|
||||
self.assertEqual(encoder.encode('\u00e6\u0300'), '\xab\xc4')
|
||||
self.assertEqual(encoder.encode('\u00e6'), '')
|
||||
self.assertEqual(encoder.encode('\u0300'), '\xab\xc4')
|
||||
self.assertEqual(encoder.encode('\u00e6', True), '\xa9\xdc')
|
||||
|
||||
self.assertEqual(encoder.reset(), None)
|
||||
self.assertEqual(encoder.encode(u'\u0300'), '\xab\xdc')
|
||||
self.assertEqual(encoder.encode('\u0300'), '\xab\xdc')
|
||||
|
||||
self.assertEqual(encoder.encode(u'\u00e6'), '')
|
||||
self.assertEqual(encoder.encode('\u00e6'), '')
|
||||
self.assertEqual(encoder.encode('', True), '\xa9\xdc')
|
||||
self.assertEqual(encoder.encode('', True), '')
|
||||
|
||||
def test_stateful_keep_buffer(self):
|
||||
encoder = codecs.getincrementalencoder('jisx0213')()
|
||||
self.assertEqual(encoder.encode(u'\u00e6'), '')
|
||||
self.assertRaises(UnicodeEncodeError, encoder.encode, u'\u0123')
|
||||
self.assertEqual(encoder.encode(u'\u0300\u00e6'), '\xab\xc4')
|
||||
self.assertRaises(UnicodeEncodeError, encoder.encode, u'\u0123')
|
||||
self.assertEqual(encoder.encode('\u00e6'), '')
|
||||
self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
|
||||
self.assertEqual(encoder.encode('\u0300\u00e6'), '\xab\xc4')
|
||||
self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
|
||||
self.assertEqual(encoder.reset(), None)
|
||||
self.assertEqual(encoder.encode(u'\u0300'), '\xab\xdc')
|
||||
self.assertEqual(encoder.encode(u'\u00e6'), '')
|
||||
self.assertRaises(UnicodeEncodeError, encoder.encode, u'\u0123')
|
||||
self.assertEqual(encoder.encode(u'', True), '\xa9\xdc')
|
||||
self.assertEqual(encoder.encode('\u0300'), '\xab\xdc')
|
||||
self.assertEqual(encoder.encode('\u00e6'), '')
|
||||
self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
|
||||
self.assertEqual(encoder.encode('', True), '\xa9\xdc')
|
||||
|
||||
|
||||
class Test_IncrementalDecoder(unittest.TestCase):
|
||||
|
|
@ -106,52 +106,52 @@ class Test_IncrementalDecoder(unittest.TestCase):
|
|||
# cp949 decoder is simple with only 1 or 2 bytes sequences.
|
||||
decoder = codecs.getincrementaldecoder('cp949')()
|
||||
self.assertEqual(decoder.decode('\xc6\xc4\xc0\xcc\xbd'),
|
||||
u'\ud30c\uc774')
|
||||
'\ud30c\uc774')
|
||||
self.assertEqual(decoder.decode('\xe3 \xb8\xb6\xc0\xbb'),
|
||||
u'\uc36c \ub9c8\uc744')
|
||||
self.assertEqual(decoder.decode(''), u'')
|
||||
'\uc36c \ub9c8\uc744')
|
||||
self.assertEqual(decoder.decode(''), '')
|
||||
|
||||
def test_dbcs_keep_buffer(self):
|
||||
decoder = codecs.getincrementaldecoder('cp949')()
|
||||
self.assertEqual(decoder.decode('\xc6\xc4\xc0'), u'\ud30c')
|
||||
self.assertEqual(decoder.decode('\xc6\xc4\xc0'), '\ud30c')
|
||||
self.assertRaises(UnicodeDecodeError, decoder.decode, '', True)
|
||||
self.assertEqual(decoder.decode('\xcc'), u'\uc774')
|
||||
self.assertEqual(decoder.decode('\xcc'), '\uc774')
|
||||
|
||||
self.assertEqual(decoder.decode('\xc6\xc4\xc0'), u'\ud30c')
|
||||
self.assertEqual(decoder.decode('\xc6\xc4\xc0'), '\ud30c')
|
||||
self.assertRaises(UnicodeDecodeError, decoder.decode, '\xcc\xbd', True)
|
||||
self.assertEqual(decoder.decode('\xcc'), u'\uc774')
|
||||
self.assertEqual(decoder.decode('\xcc'), '\uc774')
|
||||
|
||||
def test_iso2022(self):
|
||||
decoder = codecs.getincrementaldecoder('iso2022-jp')()
|
||||
ESC = '\x1b'
|
||||
self.assertEqual(decoder.decode(ESC + '('), u'')
|
||||
self.assertEqual(decoder.decode('B', True), u'')
|
||||
self.assertEqual(decoder.decode(ESC + '$'), u'')
|
||||
self.assertEqual(decoder.decode('B@$'), u'\u4e16')
|
||||
self.assertEqual(decoder.decode('@$@'), u'\u4e16')
|
||||
self.assertEqual(decoder.decode('$', True), u'\u4e16')
|
||||
self.assertEqual(decoder.decode(ESC + '('), '')
|
||||
self.assertEqual(decoder.decode('B', True), '')
|
||||
self.assertEqual(decoder.decode(ESC + '$'), '')
|
||||
self.assertEqual(decoder.decode('B@$'), '\u4e16')
|
||||
self.assertEqual(decoder.decode('@$@'), '\u4e16')
|
||||
self.assertEqual(decoder.decode('$', True), '\u4e16')
|
||||
self.assertEqual(decoder.reset(), None)
|
||||
self.assertEqual(decoder.decode('@$'), u'@$')
|
||||
self.assertEqual(decoder.decode(ESC + '$'), u'')
|
||||
self.assertEqual(decoder.decode('@$'), '@$')
|
||||
self.assertEqual(decoder.decode(ESC + '$'), '')
|
||||
self.assertRaises(UnicodeDecodeError, decoder.decode, '', True)
|
||||
self.assertEqual(decoder.decode('B@$'), u'\u4e16')
|
||||
self.assertEqual(decoder.decode('B@$'), '\u4e16')
|
||||
|
||||
|
||||
class Test_StreamWriter(unittest.TestCase):
|
||||
if len(u'\U00012345') == 2: # UCS2
|
||||
if len('\U00012345') == 2: # UCS2
|
||||
def test_gb18030(self):
|
||||
s= StringIO.StringIO()
|
||||
c = codecs.getwriter('gb18030')(s)
|
||||
c.write(u'123')
|
||||
c.write('123')
|
||||
self.assertEqual(s.getvalue(), '123')
|
||||
c.write(u'\U00012345')
|
||||
c.write('\U00012345')
|
||||
self.assertEqual(s.getvalue(), '123\x907\x959')
|
||||
c.write(u'\U00012345'[0])
|
||||
c.write('\U00012345'[0])
|
||||
self.assertEqual(s.getvalue(), '123\x907\x959')
|
||||
c.write(u'\U00012345'[1] + u'\U00012345' + u'\uac00\u00ac')
|
||||
c.write('\U00012345'[1] + '\U00012345' + '\uac00\u00ac')
|
||||
self.assertEqual(s.getvalue(),
|
||||
'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
|
||||
c.write(u'\U00012345'[0])
|
||||
c.write('\U00012345'[0])
|
||||
self.assertEqual(s.getvalue(),
|
||||
'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
|
||||
self.assertRaises(UnicodeError, c.reset)
|
||||
|
|
@ -161,20 +161,20 @@ class Test_StreamWriter(unittest.TestCase):
|
|||
def test_utf_8(self):
|
||||
s= StringIO.StringIO()
|
||||
c = codecs.getwriter('utf-8')(s)
|
||||
c.write(u'123')
|
||||
c.write('123')
|
||||
self.assertEqual(s.getvalue(), '123')
|
||||
c.write(u'\U00012345')
|
||||
c.write('\U00012345')
|
||||
self.assertEqual(s.getvalue(), '123\xf0\x92\x8d\x85')
|
||||
|
||||
# Python utf-8 codec can't buffer surrogate pairs yet.
|
||||
if 0:
|
||||
c.write(u'\U00012345'[0])
|
||||
c.write('\U00012345'[0])
|
||||
self.assertEqual(s.getvalue(), '123\xf0\x92\x8d\x85')
|
||||
c.write(u'\U00012345'[1] + u'\U00012345' + u'\uac00\u00ac')
|
||||
c.write('\U00012345'[1] + '\U00012345' + '\uac00\u00ac')
|
||||
self.assertEqual(s.getvalue(),
|
||||
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
|
||||
'\xea\xb0\x80\xc2\xac')
|
||||
c.write(u'\U00012345'[0])
|
||||
c.write('\U00012345'[0])
|
||||
self.assertEqual(s.getvalue(),
|
||||
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
|
||||
'\xea\xb0\x80\xc2\xac')
|
||||
|
|
@ -182,7 +182,7 @@ class Test_StreamWriter(unittest.TestCase):
|
|||
self.assertEqual(s.getvalue(),
|
||||
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
|
||||
'\xea\xb0\x80\xc2\xac\xed\xa0\x88')
|
||||
c.write(u'\U00012345'[1])
|
||||
c.write('\U00012345'[1])
|
||||
self.assertEqual(s.getvalue(),
|
||||
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
|
||||
'\xea\xb0\x80\xc2\xac\xed\xa0\x88\xed\xbd\x85')
|
||||
|
|
@ -199,13 +199,13 @@ class Test_StreamWriter(unittest.TestCase):
|
|||
class Test_ISO2022(unittest.TestCase):
|
||||
def test_g2(self):
|
||||
iso2022jp2 = '\x1b(B:hu4:unit\x1b.A\x1bNi de famille'
|
||||
uni = u':hu4:unit\xe9 de famille'
|
||||
uni = ':hu4:unit\xe9 de famille'
|
||||
self.assertEqual(iso2022jp2.decode('iso2022-jp-2'), uni)
|
||||
|
||||
def test_iso2022_jp_g0(self):
|
||||
self.failIf('\x0e' in u'\N{SOFT HYPHEN}'.encode('iso-2022-jp-2'))
|
||||
self.failIf('\x0e' in '\N{SOFT HYPHEN}'.encode('iso-2022-jp-2'))
|
||||
for encoding in ('iso-2022-jp-2004', 'iso-2022-jp-3'):
|
||||
e = u'\u3406'.encode(encoding)
|
||||
e = '\u3406'.encode(encoding)
|
||||
self.failIf(filter(lambda x: x >= '\x80', e))
|
||||
|
||||
def test_bug1572832(self):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue