| 1 | """ codecs -- Python Codec Registry, API and helpers.
|
|---|
| 2 |
|
|---|
| 3 |
|
|---|
| 4 | Written by Marc-Andre Lemburg ([email protected]).
|
|---|
| 5 |
|
|---|
| 6 | (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|---|
| 7 |
|
|---|
| 8 | """#"
|
|---|
| 9 |
|
|---|
| 10 | import __builtin__, sys
|
|---|
| 11 |
|
|---|
| 12 | ### Registry and builtin stateless codec functions
|
|---|
| 13 |
|
|---|
| 14 | try:
|
|---|
| 15 | from _codecs import *
|
|---|
| 16 | except ImportError, why:
|
|---|
| 17 | raise SystemError('Failed to load the builtin codecs: %s' % why)
|
|---|
| 18 |
|
|---|
| 19 | __all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE",
|
|---|
| 20 | "BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",
|
|---|
| 21 | "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_LE", "BOM_UTF16_BE",
|
|---|
| 22 | "BOM_UTF32", "BOM_UTF32_LE", "BOM_UTF32_BE",
|
|---|
| 23 | "strict_errors", "ignore_errors", "replace_errors",
|
|---|
| 24 | "xmlcharrefreplace_errors",
|
|---|
| 25 | "register_error", "lookup_error"]
|
|---|
| 26 |
|
|---|
| 27 | ### Constants
|
|---|
| 28 |
|
|---|
| 29 | #
|
|---|
| 30 | # Byte Order Mark (BOM = ZERO WIDTH NO-BREAK SPACE = U+FEFF)
|
|---|
| 31 | # and its possible byte string values
|
|---|
| 32 | # for UTF8/UTF16/UTF32 output and little/big endian machines
|
|---|
| 33 | #
|
|---|
| 34 |
|
|---|
| 35 | # UTF-8
|
|---|
| 36 | BOM_UTF8 = '\xef\xbb\xbf'
|
|---|
| 37 |
|
|---|
| 38 | # UTF-16, little endian
|
|---|
| 39 | BOM_LE = BOM_UTF16_LE = '\xff\xfe'
|
|---|
| 40 |
|
|---|
| 41 | # UTF-16, big endian
|
|---|
| 42 | BOM_BE = BOM_UTF16_BE = '\xfe\xff'
|
|---|
| 43 |
|
|---|
| 44 | # UTF-32, little endian
|
|---|
| 45 | BOM_UTF32_LE = '\xff\xfe\x00\x00'
|
|---|
| 46 |
|
|---|
| 47 | # UTF-32, big endian
|
|---|
| 48 | BOM_UTF32_BE = '\x00\x00\xfe\xff'
|
|---|
| 49 |
|
|---|
| 50 | if sys.byteorder == 'little':
|
|---|
| 51 |
|
|---|
| 52 | # UTF-16, native endianness
|
|---|
| 53 | BOM = BOM_UTF16 = BOM_UTF16_LE
|
|---|
| 54 |
|
|---|
| 55 | # UTF-32, native endianness
|
|---|
| 56 | BOM_UTF32 = BOM_UTF32_LE
|
|---|
| 57 |
|
|---|
| 58 | else:
|
|---|
| 59 |
|
|---|
| 60 | # UTF-16, native endianness
|
|---|
| 61 | BOM = BOM_UTF16 = BOM_UTF16_BE
|
|---|
| 62 |
|
|---|
| 63 | # UTF-32, native endianness
|
|---|
| 64 | BOM_UTF32 = BOM_UTF32_BE
|
|---|
| 65 |
|
|---|
| 66 | # Old broken names (don't use in new code)
|
|---|
| 67 | BOM32_LE = BOM_UTF16_LE
|
|---|
| 68 | BOM32_BE = BOM_UTF16_BE
|
|---|
| 69 | BOM64_LE = BOM_UTF32_LE
|
|---|
| 70 | BOM64_BE = BOM_UTF32_BE
|
|---|
| 71 |
|
|---|
| 72 |
|
|---|
| 73 | ### Codec base classes (defining the API)
|
|---|
| 74 |
|
|---|
| 75 | class CodecInfo(tuple):
|
|---|
| 76 |
|
|---|
| 77 | def __new__(cls, encode, decode, streamreader=None, streamwriter=None,
|
|---|
| 78 | incrementalencoder=None, incrementaldecoder=None, name=None):
|
|---|
| 79 | self = tuple.__new__(cls, (encode, decode, streamreader, streamwriter))
|
|---|
| 80 | self.name = name
|
|---|
| 81 | self.encode = encode
|
|---|
| 82 | self.decode = decode
|
|---|
| 83 | self.incrementalencoder = incrementalencoder
|
|---|
| 84 | self.incrementaldecoder = incrementaldecoder
|
|---|
| 85 | self.streamwriter = streamwriter
|
|---|
| 86 | self.streamreader = streamreader
|
|---|
| 87 | return self
|
|---|
| 88 |
|
|---|
| 89 | def __repr__(self):
|
|---|
| 90 | return "<%s.%s object for encoding %s at 0x%x>" % (self.__class__.__module__, self.__class__.__name__, self.name, id(self))
|
|---|
| 91 |
|
|---|
|
|---|
