| 1 | """ Python 'utf-16' Codec
|
|---|
| 2 |
|
|---|
| 3 |
|
|---|
| 4 | Written by Marc-Andre Lemburg (mal@lemburg.com).
|
|---|
| 5 |
|
|---|
| 6 | (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|---|
| 7 |
|
|---|
| 8 | """
|
|---|
| 9 | import codecs, sys
|
|---|
| 10 |
|
|---|
| 11 | ### Codec APIs
|
|---|
| 12 |
|
|---|
| 13 | encode = codecs.utf_16_encode
|
|---|
| 14 |
|
|---|
| 15 | def decode(input, errors='strict'):
|
|---|
| 16 | return codecs.utf_16_decode(input, errors, True)
|
|---|
| 17 |
|
|---|
| 18 | class IncrementalEncoder(codecs.IncrementalEncoder):
|
|---|
| 19 | def __init__(self, errors='strict'):
|
|---|
| 20 | codecs.IncrementalEncoder.__init__(self, errors)
|
|---|
| 21 | self.encoder = None
|
|---|
| 22 |
|
|---|
| 23 | def encode(self, input, final=False):
|
|---|
| 24 | if self.encoder is None:
|
|---|
| 25 | result = codecs.utf_16_encode(input, self.errors)[0]
|
|---|
| 26 | if sys.byteorder == 'little':
|
|---|
| 27 | self.encoder = codecs.utf_16_le_encode
|
|---|
| 28 | else:
|
|---|
| 29 | self.encoder = codecs.utf_16_be_encode
|
|---|
| 30 | return result
|
|---|
| 31 | return self.encoder(input, self.errors)[0]
|
|---|
| 32 |
|
|---|
| 33 | def reset(self):
|
|---|
| 34 | codecs.IncrementalEncoder.reset(self)
|
|---|
| 35 | self.encoder = None
|
|---|
| 36 |
|
|---|
| 37 | def getstate(self):
|
|---|
| 38 | # state info we return to the caller:
|
|---|
| 39 | # 0: stream is in natural order for this platform
|
|---|
| 40 | # 2: endianness hasn't been determined yet
|
|---|
| 41 | # (we're never writing in unnatural order)
|
|---|
| 42 | return (2 if self.encoder is None else 0)
|
|---|
| 43 |
|
|---|
| 44 | def setstate(self, state):
|
|---|
| 45 | if state:
|
|---|
| 46 | self.encoder = None
|
|---|
| 47 | else:
|
|---|
| 48 | if sys.byteorder == 'little':
|
|---|
| 49 | self.encoder = codecs.utf_16_le_encode
|
|---|
| 50 | else:
|
|---|
| 51 | self.encoder = codecs.utf_16_be_encode
|
|---|
| 52 |
|
|---|
| 53 | class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
|
|---|
| 54 | def __init__(self, errors='strict'):
|
|---|
| 55 | codecs.BufferedIncrementalDecoder.__init__(self, errors)
|
|---|
| 56 | self.decoder = None
|
|---|
| 57 |
|
|---|
| 58 | def _buffer_decode(self, input, errors, final):
|
|---|
| 59 | if self.decoder is None:
|
|---|
| 60 | (output, consumed, byteorder) = \
|
|---|
| 61 | codecs.utf_16_ex_decode(input, errors, 0, final)
|
|---|
| 62 | if byteorder == -1:
|
|---|
| 63 | self.decoder = codecs.utf_16_le_decode
|
|---|
| 64 | elif byteorder == 1:
|
|---|
| 65 | self.decoder = codecs.utf_16_be_decode
|
|---|
| 66 | elif consumed >= 2:
|
|---|
| 67 | raise UnicodeError("UTF-16 stream does not start with BOM")
|
|---|
| 68 | return (output, consumed)
|
|---|
| 69 | return self.decoder(input, self.errors, final)
|
|---|
| 70 |
|
|---|
| 71 | def reset(self):
|
|---|
| 72 | codecs.BufferedIncrementalDecoder.reset(self)
|
|---|
| 73 | self.decoder = None
|
|---|
| 74 |
|
|---|
| 75 | class StreamWriter(codecs.StreamWriter):
|
|---|
| 76 | def __init__(self, stream, errors='strict'):
|
|---|
| 77 | codecs.StreamWriter.__init__(self, stream, errors)
|
|---|
| 78 | self.encoder = None
|
|---|
| 79 |
|
|---|
| 80 | def reset(self):
|
|---|
| 81 | codecs.StreamWriter.reset(self)
|
|---|
| 82 | self.encoder = None
|
|---|
| 83 |
|
|---|
| 84 | def encode(self, input, errors='strict'):
|
|---|
| 85 | if self.encoder is None:
|
|---|
| 86 | result = codecs.utf_16_encode(input, errors)
|
|---|
| 87 | if sys.byteorder == 'little':
|
|---|
| 88 | self.encoder = codecs.utf_16_le_encode
|
|---|
| 89 | else:
|
|---|
| 90 | self.encoder = codecs.utf_16_be_encode
|
|---|
| 91 | return result
|
|---|
| 92 | else:
|
|---|
| 93 | return self.encoder(input, errors)
|
|---|
| 94 |
|
|---|
| 95 | class StreamReader(codecs.StreamReader):
|
|---|
| 96 |
|
|---|
| 97 | def reset(self):
|
|---|
| 98 | codecs.StreamReader.reset(self)
|
|---|
| 99 | try:
|
|---|
| 100 | del self.decode
|
|---|
| 101 | except AttributeError:
|
|---|
| 102 | pass
|
|---|
| 103 |
|
|---|
| 104 | def decode(self, input, errors='strict'):
|
|---|
| 105 | (object, consumed, byteorder) = \
|
|---|
| 106 | codecs.utf_16_ex_decode(input, errors, 0, False)
|
|---|
| 107 | if byteorder == -1:
|
|---|
| 108 | self.decode = codecs.utf_16_le_decode
|
|---|
| 109 | elif byteorder == 1:
|
|---|
| 110 | self.decode = codecs.utf_16_be_decode
|
|---|
| 111 | elif consumed>=2:
|
|---|
| 112 | raise UnicodeError,"UTF-16 stream does not start with BOM"
|
|---|
| 113 | return (object, consumed)
|
|---|
| 114 |
|
|---|
| 115 | ### encodings module API
|
|---|
| 116 |
|
|---|
| 117 | def getregentry():
|
|---|
| 118 | return codecs.CodecInfo(
|
|---|
| 119 | name='utf-16',
|
|---|
| 120 | encode=encode,
|
|---|
| 121 | decode=decode,
|
|---|
| 122 | incrementalencoder=IncrementalEncoder,
|
|---|
| 123 | incrementaldecoder=IncrementalDecoder,
|
|---|
| 124 | streamreader=StreamReader,
|
|---|
| 125 | streamwriter=StreamWriter,
|
|---|
| 126 | )
|
|---|
