mirror of
https://github.com/python/cpython.git
synced 2025-10-31 05:31:20 +00:00
69652035bc
decoding incomplete input (when the input stream is temporarily exhausted). codecs.StreamReader now implements buffering, which enables proper readline support for the UTF-16 decoders. codecs.StreamReader.read() has a new argument chars which specifies the number of characters to return. codecs.StreamReader.readline() and codecs.StreamReader.readlines() have a new argument keepends. Trailing "\n"s will be stripped from the lines if keepends is false. Added C APIs PyUnicode_DecodeUTF8Stateful and PyUnicode_DecodeUTF16Stateful.
49 lines
1.3 KiB
Python
49 lines
1.3 KiB
Python
""" Python 'utf-16' Codec
|
|
|
|
|
|
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
|
|
|
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|
|
|
"""
|
|
import codecs, sys
|
|
|
|
### Codec APIs
|
|
|
|
encode = codecs.utf_16_encode
|
|
|
|
def decode(input, errors='strict'):
|
|
return codecs.utf_16_decode(input, errors, True)
|
|
|
|
class StreamWriter(codecs.StreamWriter):
|
|
def __init__(self, stream, errors='strict'):
|
|
self.bom_written = False
|
|
codecs.StreamWriter.__init__(self, stream, errors)
|
|
|
|
def encode(self, input, errors='strict'):
|
|
self.bom_written = True
|
|
result = codecs.utf_16_encode(input, errors)
|
|
if sys.byteorder == 'little':
|
|
self.encode = codecs.utf_16_le_encode
|
|
else:
|
|
self.encode = codecs.utf_16_be_encode
|
|
return result
|
|
|
|
class StreamReader(codecs.StreamReader):
|
|
|
|
def decode(self, input, errors='strict'):
|
|
(object, consumed, byteorder) = \
|
|
codecs.utf_16_ex_decode(input, errors, 0, False)
|
|
if byteorder == -1:
|
|
self.decode = codecs.utf_16_le_decode
|
|
elif byteorder == 1:
|
|
self.decode = codecs.utf_16_be_decode
|
|
elif consumed>=2:
|
|
raise UnicodeError,"UTF-16 stream does not start with BOM"
|
|
return (object, consumed)
|
|
|
|
### encodings module API
|
|
|
|
def getregentry():
|
|
|
|
return (encode,decode,StreamReader,StreamWriter)
|