1 """ codecs -- Python Codec Registry, API and helpers.
4 Written by Marc-Andre Lemburg (mal@lemburg.com).
38 # Byte Order Mark (BOM = ZERO WIDTH NO-BREAK SPACE = U+FEFF)
43 # UTF-8
46 # UTF-16, little endian
49 # UTF-16, big endian
52 # UTF-32, little endian
55 # UTF-32, big endian
60     # UTF-16, native endianness
63     # UTF-32, native endianness
68     # UTF-16, native endianness
71     # UTF-32, native endianness
86     # Private API to allow Python 3.4 to denylist the known non-Unicode
119         handling schemes by providing the errors argument. These
122          'strict' - raise a ValueError error (or a subclass)
123          'ignore' - ignore the character and continue with the next
124          'replace' - replace with a suitable replacement character;
128          'surrogateescape' - replace with private code points U+DCnn.
129          'xmlcharrefreplace' - Replace with the appropriate XML
131          'backslashreplace'  - Replace with backslashed escape sequences.
132          'namereplace'       - Replace with \\N{...} escape sequences
138     def encode(self, input, errors='strict'):  argument
143             errors defines the error handling to apply. It defaults to
157     def decode(self, input, errors='strict'):  argument
166             errors defines the error handling to apply. It defaults to
186     def __init__(self, errors='strict'):  argument
191         providing the errors keyword argument. See the module docstring
194         self.errors = errors
226     def __init__(self, errors='strict'):  argument
227         IncrementalEncoder.__init__(self, errors)
231     def _buffer_encode(self, input, errors, final):  argument
239         (result, consumed) = self._buffer_encode(data, self.errors, final)
260     def __init__(self, errors='strict'):  argument
265         providing the errors keyword argument. See the module docstring
268         self.errors = errors
288         additional_state_info must be a non-negative integer
309     def __init__(self, errors='strict'):  argument
310         IncrementalDecoder.__init__(self, errors)
314     def _buffer_decode(self, input, errors, final):  argument
322         (result, consumed) = self._buffer_decode(data, self.errors, final)
336         # ignore additional state info
348     def __init__(self, stream, errors='strict'):  argument
352             stream must be a file-like object open for writing.
355             schemes by providing the errors keyword argument. These
358              'strict' - raise a ValueError (or a subclass)
359              'ignore' - ignore the character and continue with the next
360              'replace'- replace with a suitable replacement character
361              'xmlcharrefreplace' - Replace with the appropriate XML
363              'backslashreplace'  - Replace with backslashed escape
365              'namereplace'       - Replace with \\N{...} escape sequences.
371         self.errors = errors
377         data, consumed = self.encode(object, self.errors)
423     def __init__(self, stream, errors='strict'):  argument
427             stream must be a file-like object open for reading.
430             schemes by providing the errors keyword argument. These
433              'strict' - raise a ValueError (or a subclass)
434              'ignore' - ignore the character and continue with the next
435              'replace'- replace with a suitable replacement character
436              'backslashreplace' - Replace with backslashed escape sequences;
442         self.errors = errors
448     def decode(self, input, errors='strict'):  argument
451     def read(self, size=-1, chars=-1, firstline=False):
463             -1 indicates to read and decode as much as possible.  size
504                 newchars, decodedbytes = self.decode(data, self.errors)
508                         self.decode(data[:exc.start], self.errors)
577                         lines[-1] += self.charbuffer
615             way to finding the true end-of-line.
627             from decoding errors.
681     def __init__(self, stream, Reader, Writer, errors='strict'):  argument
685             stream must be a Stream-like object.
695         self.reader = Reader(stream, errors)
696         self.writer = Writer(stream, errors)
697         self.errors = errors
699     def read(self, size=-1):
776                  errors='strict'):  argument
778         """ Creates a StreamRecoder instance which implements a two-way
784             transcodings from e.g. latin-1 to utf-8 and back.
786             stream must be a file-like object.
799         self.reader = Reader(stream, errors)
800         self.writer = Writer(stream, errors)
801         self.errors = errors
803     def read(self, size=-1):
806         data, bytesencoded = self.encode(data, self.errors)
815         data, bytesencoded = self.encode(data, self.errors)
821         data, bytesencoded = self.encode(data, self.errors)
828         data, bytesencoded = self.encode(data, self.errors)
836         data, bytesdecoded = self.decode(data, self.errors)
842         data, bytesdecoded = self.decode(data, self.errors)
871 def open(filename, mode='r', encoding=None, errors='strict', buffering=-1):  argument
888         errors may be given to define the error handling. It defaults
893         It defaults to -1 which means that the default buffer size will
912         srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, errors)
920 def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'):  argument
935         errors may be given to define the error handling. It defaults
950                        file_info.streamreader, file_info.streamwriter, errors)
1026 def iterencode(iterator, encoding, errors='strict', **kwargs):  argument
1032     errors and kwargs are passed through to the IncrementalEncoder
1035     encoder = getincrementalencoder(encoding)(errors, **kwargs)
1044 def iterdecode(iterator, encoding, errors='strict', **kwargs):  argument
1050     errors and kwargs are passed through to the IncrementalDecoder
1053     decoder = getincrementaldecoder(encoding)(errors, **kwargs)
1062 ### Helpers for charmap-based codecs
1066     """ make_identity_dict(rng) -> dict
1099     ignore_errors = lookup_error("ignore")
1105     # In --disable-unicode builds, these error handler are missing
1123     # Make stdout translate Latin-1 output into UTF-8 output
1124     sys.stdout = EncodedFile(sys.stdout, 'latin-1', 'utf-8')
1126     # Have stdin translate Latin-1 input into UTF-8 input
1127     sys.stdin = EncodedFile(sys.stdin, 'utf-8', 'latin-1')