diff options
author | Walter Dörwald <walter@livinglogic.de> | 2006-03-15 11:35:15 (GMT) |
---|---|---|
committer | Walter Dörwald <walter@livinglogic.de> | 2006-03-15 11:35:15 (GMT) |
commit | abb02e59946f9ea3076e96e3b03b51d1cebd46b4 (patch) | |
tree | 165444acd89173a8832547078cbc417d4626116e /Lib/encodings/utf_16.py | |
parent | e2ebb2d7f777db2de72cfeb0e3c489ac4cc5c400 (diff) | |
download | cpython-abb02e59946f9ea3076e96e3b03b51d1cebd46b4.zip cpython-abb02e59946f9ea3076e96e3b03b51d1cebd46b4.tar.gz cpython-abb02e59946f9ea3076e96e3b03b51d1cebd46b4.tar.bz2 |
Patch #1436130: codecs.lookup() now returns a CodecInfo object (a subclass
of tuple) that provides incremental decoders and encoders (a way to use
stateful codecs without the stream API). Functions
codecs.getincrementaldecoder() and codecs.getincrementalencoder() have
been added.
Diffstat (limited to 'Lib/encodings/utf_16.py')
-rw-r--r-- | Lib/encodings/utf_16.py | 52 |
1 files changed, 50 insertions, 2 deletions
diff --git a/Lib/encodings/utf_16.py b/Lib/encodings/utf_16.py index 95abb05..eff08f3 100644 --- a/Lib/encodings/utf_16.py +++ b/Lib/encodings/utf_16.py @@ -15,6 +15,47 @@ encode = codecs.utf_16_encode def decode(input, errors='strict'): return codecs.utf_16_decode(input, errors, True) +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + codecs.IncrementalEncoder.__init__(self, errors) + self.encoder = None + + def encode(self, input, final=False): + if self.encoder is None: + result = codecs.utf_16_encode(input, self.errors)[0] + if sys.byteorder == 'little': + self.encoder = codecs.utf_16_le_encode + else: + self.encoder = codecs.utf_16_be_encode + return result + return self.encoder(input, self.errors)[0] + + def reset(self): + codecs.IncrementalEncoder.reset(self) + self.encoder = None + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def __init__(self, errors='strict'): + codecs.BufferedIncrementalDecoder.__init__(self, errors) + self.decoder = None + + def _buffer_decode(self, input, errors, final): + if self.decoder is None: + (output, consumed, byteorder) = \ + codecs.utf_16_ex_decode(input, errors, 0, final) + if byteorder == -1: + self.decoder = codecs.utf_16_le_decode + elif byteorder == 1: + self.decoder = codecs.utf_16_be_decode + elif consumed >= 2: + raise UnicodeError("UTF-16 stream does not start with BOM") + return (output, consumed) + return self.decoder(input, self.errors, final) + + def reset(self): + codecs.BufferedIncrementalDecoder.reset(self) + self.decoder = None + class StreamWriter(codecs.StreamWriter): def __init__(self, stream, errors='strict'): self.bom_written = False @@ -52,5 +93,12 @@ class StreamReader(codecs.StreamReader): ### encodings module API def getregentry(): - - return (encode,decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-16', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) |