ba0a3b9abb
Part of https://github.com/behdad/fonttools/issues/236 Now we fallback to ASCII for unknown encodings. Not sure if this might be a bad idea. The main user-visible difference is that if there's an ASCII-only text in an unknown encoding, we still "decode" it and use unicode="True" instead of unicode="False". Or is assuming that any unsupported encoding is ASCII-compatible too intrusive?
82 lines
1.5 KiB
Python
82 lines
1.5 KiB
Python
"""Python 2/3 compat layer."""
|
|
|
|
from __future__ import print_function, division, absolute_import
|
|
|
|
try:
|
|
basestring
|
|
except NameError:
|
|
basestring = str
|
|
|
|
try:
|
|
unicode
|
|
except NameError:
|
|
unicode = str
|
|
|
|
try:
|
|
unichr
|
|
bytechr = chr
|
|
byteord = ord
|
|
except:
|
|
unichr = chr
|
|
def bytechr(n):
|
|
return bytes([n])
|
|
def byteord(c):
|
|
return c if isinstance(c, int) else ord(c)
|
|
|
|
try:
|
|
from StringIO import StringIO
|
|
except ImportError:
|
|
from io import BytesIO as StringIO
|
|
|
|
def strjoin(iterable, joiner=''):
|
|
return tostr(joiner).join(iterable)
|
|
|
|
def tobytes(s, encoding='ascii', errors='strict'):
|
|
if not isinstance(s, bytes):
|
|
return s.encode(encoding, errors)
|
|
else:
|
|
return s
|
|
def tounicode(s, encoding='ascii', errors='strict'):
|
|
if not isinstance(s, unicode):
|
|
return s.decode(encoding, errors)
|
|
else:
|
|
return s
|
|
|
|
if str == bytes:
|
|
class Tag(str):
|
|
def tobytes(self):
|
|
if isinstance(self, bytes):
|
|
return self
|
|
else:
|
|
return self.encode('latin1')
|
|
|
|
tostr = tobytes
|
|
|
|
bytesjoin = strjoin
|
|
else:
|
|
class Tag(str):
|
|
|
|
@staticmethod
|
|
def transcode(blob):
|
|
if not isinstance(blob, str):
|
|
blob = blob.decode('latin-1')
|
|
return blob
|
|
|
|
def __new__(self, content):
|
|
return str.__new__(self, self.transcode(content))
|
|
def __ne__(self, other):
|
|
return not self.__eq__(other)
|
|
def __eq__(self, other):
|
|
return str.__eq__(self, self.transcode(other))
|
|
|
|
def __hash__(self):
|
|
return str.__hash__(self)
|
|
|
|
def tobytes(self):
|
|
return self.encode('latin-1')
|
|
|
|
tostr = tounicode
|
|
|
|
def bytesjoin(iterable, joiner=b''):
|
|
return tobytes(joiner).join(tobytes(item) for item in iterable)
|