-
-
Notifications
You must be signed in to change notification settings - Fork 34.2k
Expand file tree
/
Copy pathcodecs.py
More file actions
1115 lines (849 loc) · 35.3 KB
/
codecs.py
File metadata and controls
1115 lines (849 loc) · 35.3 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
""" codecs -- Python Codec Registry, API and helpers.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
import __builtin__, sys
### Registry and builtin stateless codec functions
try:
from _codecs import *
except ImportError, why:
raise SystemError('Failed to load the builtin codecs: %s' % why)
__all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE",
"BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",
"BOM_UTF8", "BOM_UTF16", "BOM_UTF16_LE", "BOM_UTF16_BE",
"BOM_UTF32", "BOM_UTF32_LE", "BOM_UTF32_BE",
"CodecInfo", "Codec", "IncrementalEncoder", "IncrementalDecoder",
"StreamReader", "StreamWriter",
"StreamReaderWriter", "StreamRecoder",
"getencoder", "getdecoder", "getincrementalencoder",
"getincrementaldecoder", "getreader", "getwriter",
"encode", "decode", "iterencode", "iterdecode",
"strict_errors", "ignore_errors", "replace_errors",
"xmlcharrefreplace_errors", "backslashreplace_errors",
"register_error", "lookup_error"]
### Constants
#
# Byte Order Mark (BOM = ZERO WIDTH NO-BREAK SPACE = U+FEFF)
# and its possible byte string values
# for UTF8/UTF16/UTF32 output and little/big endian machines
#
# UTF-8
BOM_UTF8 = '\xef\xbb\xbf'
# UTF-16, little endian
BOM_LE = BOM_UTF16_LE = '\xff\xfe'
# UTF-16, big endian
BOM_BE = BOM_UTF16_BE = '\xfe\xff'
# UTF-32, little endian
BOM_UTF32_LE = '\xff\xfe\x00\x00'
# UTF-32, big endian
BOM_UTF32_BE = '\x00\x00\xfe\xff'
if sys.byteorder == 'little':
# UTF-16, native endianness
BOM = BOM_UTF16 = BOM_UTF16_LE
# UTF-32, native endianness
BOM_UTF32 = BOM_UTF32_LE
else:
# UTF-16, native endianness
BOM = BOM_UTF16 = BOM_UTF16_BE
# UTF-32, native endianness
BOM_UTF32 = BOM_UTF32_BE
# Old broken names (don't use in new code)
BOM32_LE = BOM_UTF16_LE
BOM32_BE = BOM_UTF16_BE
BOM64_LE = BOM_UTF32_LE
BOM64_BE = BOM_UTF32_BE
### Codec base classes (defining the API)
class CodecInfo(tuple):
"""Codec details when looking up the codec registry"""
# Private API to allow Python to blacklist the known non-Unicode
# codecs in the standard library. A more general mechanism to
# reliably distinguish test encodings from other codecs will hopefully
# be defined for Python 3.5
#
# See http://bugs.python.org/issue19619
_is_text_encoding = True # Assume codecs are text encodings by default
def __new__(cls, encode, decode, streamreader=None, streamwriter=None,
incrementalencoder=None, incrementaldecoder=None, name=None,
_is_text_encoding=None):
self = tuple.__new__(cls, (encode, decode, streamreader, streamwriter))
self.name = name
self.encode = encode
self.decode = decode
self.incrementalencoder = incrementalencoder
self.incrementaldecoder = incrementaldecoder
self.streamwriter = streamwriter
self.streamreader = streamreader
if _is_text_encoding is not None:
self._is_text_encoding = _is_text_encoding
return self
def __repr__(self):
return "<%s.%s object for encoding %s at 0x%x>" % (self.__class__.__module__, self.__class__.__name__, self.name, id(self))
class Codec:
""" Defines the interface for stateless encoders/decoders.
The .encode()/.decode() methods may use different error
handling schemes by providing the errors argument. These
string values are predefined:
'strict' - raise a ValueError error (or a subclass)
'ignore' - ignore the character and continue with the next
'replace' - replace with a suitable replacement character;
Python will use the official U+FFFD REPLACEMENT
CHARACTER for the builtin Unicode codecs on
decoding and '?' on encoding.
'xmlcharrefreplace' - Replace with the appropriate XML
character reference (only for encoding).
'backslashreplace' - Replace with backslashed escape sequences
(only for encoding).
The set of allowed values can be extended via register_error.
"""
def encode(self, input, errors='strict'):
""" Encodes the object input and returns a tuple (output
object, length consumed).
errors defines the error handling to apply. It defaults to
'strict' handling.
The method may not store state in the Codec instance. Use
StreamWriter for codecs which have to keep state in order to
make encoding efficient.
The encoder must be able to handle zero length input and
return an empty object of the output object type in this
situation.
"""
raise NotImplementedError
def decode(self, input, errors='strict'):
""" Decodes the object input and returns a tuple (output
object, length consumed).
input must be an object which provides the bf_getreadbuf
buffer slot. Python strings, buffer objects and memory
mapped files are examples of objects providing this slot.
errors defines the error handling to apply. It defaults to
'strict' handling.
The method may not store state in the Codec instance. Use
StreamReader for codecs which have to keep state in order to
make decoding efficient.
The decoder must be able to handle zero length input and
return an empty object of the output object type in this
situation.
"""
raise NotImplementedError
class IncrementalEncoder(object):
"""
An IncrementalEncoder encodes an input in multiple steps. The input can be
passed piece by piece to the encode() method. The IncrementalEncoder remembers
the state of the Encoding process between calls to encode().
"""
def __init__(self, errors='strict'):
"""
Creates an IncrementalEncoder instance.
The IncrementalEncoder may use different error handling schemes by
providing the errors keyword argument. See the module docstring
for a list of possible values.
"""
self.errors = errors
self.buffer = ""
def encode(self, input, final=False):
"""
Encodes input and returns the resulting object.
"""
raise NotImplementedError
def reset(self):
"""
Resets the encoder to the initial state.
"""
def getstate(self):
"""
Return the current state of the encoder.
"""
return 0
def setstate(self, state):
"""
Set the current state of the encoder. state must have been
returned by getstate().
"""
class BufferedIncrementalEncoder(IncrementalEncoder):
"""
This subclass of IncrementalEncoder can be used as the baseclass for an
incremental encoder if the encoder must keep some of the output in a
buffer between calls to encode().
"""
def __init__(self, errors='strict'):
IncrementalEncoder.__init__(self, errors)
self.buffer = "" # unencoded input that is kept between calls to encode()
def _buffer_encode(self, input, errors, final):
# Overwrite this method in subclasses: It must encode input
# and return an (output, length consumed) tuple
raise NotImplementedError
def encode(self, input, final=False):
# encode input (taking the buffer into account)
data = self.buffer + input
(result, consumed) = self._buffer_encode(data, self.errors, final)
# keep unencoded input until the next call
self.buffer = data[consumed:]
return result
def reset(self):
IncrementalEncoder.reset(self)
self.buffer = ""
def getstate(self):
return self.buffer or 0
def setstate(self, state):
self.buffer = state or ""
class IncrementalDecoder(object):
"""
An IncrementalDecoder decodes an input in multiple steps. The input can be
passed piece by piece to the decode() method. The IncrementalDecoder
remembers the state of the decoding process between calls to decode().
"""
def __init__(self, errors='strict'):
"""
Creates an IncrementalDecoder instance.
The IncrementalDecoder may use different error handling schemes by
providing the errors keyword argument. See the module docstring
for a list of possible values.
"""
self.errors = errors
def decode(self, input, final=False):
"""
Decodes input and returns the resulting object.
"""
raise NotImplementedError
def reset(self):
"""
Resets the decoder to the initial state.
"""
def getstate(self):
"""
Return the current state of the decoder.
This must be a (buffered_input, additional_state_info) tuple.
buffered_input must be a bytes object containing bytes that
were passed to decode() that have not yet been converted.
additional_state_info must be a non-negative integer
representing the state of the decoder WITHOUT yet having
processed the contents of buffered_input. In the initial state
and after reset(), getstate() must return (b"", 0).
"""
return (b"", 0)
def setstate(self, state):
"""
Set the current state of the decoder.
state must have been returned by getstate(). The effect of
setstate((b"", 0)) must be equivalent to reset().
"""
class BufferedIncrementalDecoder(IncrementalDecoder):
"""
This subclass of IncrementalDecoder can be used as the baseclass for an
incremental decoder if the decoder must be able to handle incomplete byte
sequences.
"""
def __init__(self, errors='strict'):
IncrementalDecoder.__init__(self, errors)
self.buffer = "" # undecoded input that is kept between calls to decode()
def _buffer_decode(self, input, errors, final):
# Overwrite this method in subclasses: It must decode input
# and return an (output, length consumed) tuple
raise NotImplementedError
def decode(self, input, final=False):
# decode input (taking the buffer into account)
data = self.buffer + input
(result, consumed) = self._buffer_decode(data, self.errors, final)
# keep undecoded input until the next call
self.buffer = data[consumed:]
return result
def reset(self):
IncrementalDecoder.reset(self)
self.buffer = ""
def getstate(self):
# additional state info is always 0
return (self.buffer, 0)
def setstate(self, state):
# ignore additional state info
self.buffer = state[0]
#
# The StreamWriter and StreamReader class provide generic working
# interfaces which can be used to implement new encoding submodules
# very easily. See encodings/utf_8.py for an example on how this is
# done.
#
class StreamWriter(Codec):
def __init__(self, stream, errors='strict'):
""" Creates a StreamWriter instance.
stream must be a file-like object open for writing
(binary) data.
The StreamWriter may use different error handling
schemes by providing the errors keyword argument. These
parameters are predefined:
'strict' - raise a ValueError (or a subclass)
'ignore' - ignore the character and continue with the next
'replace'- replace with a suitable replacement character
'xmlcharrefreplace' - Replace with the appropriate XML
character reference.
'backslashreplace' - Replace with backslashed escape
sequences (only for encoding).
The set of allowed parameter values can be extended via
register_error.
"""
self.stream = stream
self.errors = errors
def write(self, object):
""" Writes the object's contents encoded to self.stream.
"""
data, consumed = self.encode(object, self.errors)
self.stream.write(data)
def writelines(self, list):
""" Writes the concatenated list of strings to the stream
using .write().
"""
self.write(''.join(list))
def reset(self):
""" Flushes and resets the codec buffers used for keeping state.
Calling this method should ensure that the data on the
output is put into a clean state, that allows appending
of new fresh data without having to rescan the whole
stream to recover state.
"""
pass
def seek(self, offset, whence=0):
self.stream.seek(offset, whence)
if whence == 0 and offset == 0:
self.reset()
def __getattr__(self, name,
getattr=getattr):
""" Inherit all other methods from the underlying stream.
"""
return getattr(self.stream, name)
def __enter__(self):
return self
def __exit__(self, type, value, tb):
self.stream.close()
###
class StreamReader(Codec):
def __init__(self, stream, errors='strict'):
""" Creates a StreamReader instance.
stream must be a file-like object open for reading
(binary) data.
The StreamReader may use different error handling
schemes by providing the errors keyword argument. These
parameters are predefined:
'strict' - raise a ValueError (or a subclass)
'ignore' - ignore the character and continue with the next
'replace'- replace with a suitable replacement character;
The set of allowed parameter values can be extended via
register_error.
"""
self.stream = stream
self.errors = errors
self.bytebuffer = ""
# For str->str decoding this will stay a str
# For str->unicode decoding the first read will promote it to unicode
self.charbuffer = ""
self.linebuffer = None
def decode(self, input, errors='strict'):
raise NotImplementedError
def read(self, size=-1, chars=-1, firstline=False):
""" Decodes data from the stream self.stream and returns the
resulting object.
chars indicates the number of characters to read from the
stream. read() will never return more than chars
characters, but it might return less, if there are not enough
characters available.
size indicates the approximate maximum number of bytes to
read from the stream for decoding purposes. The decoder
can modify this setting as appropriate. The default value
-1 indicates to read and decode as much as possible. size
is intended to prevent having to decode huge files in one
step.
If firstline is true, and a UnicodeDecodeError happens
after the first line terminator in the input only the first line
will be returned, the rest of the input will be kept until the
next call to read().
The method should use a greedy read strategy meaning that
it should read as much data as is allowed within the
definition of the encoding and the given size, e.g. if
optional encoding endings or state markers are available
on the stream, these should be read too.
"""
# If we have lines cached, first merge them back into characters
if self.linebuffer:
self.charbuffer = "".join(self.linebuffer)
self.linebuffer = None
if chars < 0:
# For compatibility with other read() methods that take a
# single argument
chars = size
# read until we get the required number of characters (if available)
while True:
# can the request be satisfied from the character buffer?
if chars >= 0:
if len(self.charbuffer) >= chars:
break
# we need more data
if size < 0:
newdata = self.stream.read()
else:
newdata = self.stream.read(size)
# decode bytes (those remaining from the last call included)
data = self.bytebuffer + newdata
try:
newchars, decodedbytes = self.decode(data, self.errors)
except UnicodeDecodeError, exc:
if firstline:
newchars, decodedbytes = self.decode(data[:exc.start], self.errors)
lines = newchars.splitlines(True)
if len(lines)<=1:
raise
else:
raise
# keep undecoded bytes until the next call
self.bytebuffer = data[decodedbytes:]
# put new characters in the character buffer
self.charbuffer += newchars
# there was no data available
if not newdata:
break
if chars < 0:
# Return everything we've got
result = self.charbuffer
self.charbuffer = ""
else:
# Return the first chars characters
result = self.charbuffer[:chars]
self.charbuffer = self.charbuffer[chars:]
return result
def readline(self, size=None, keepends=True):
""" Read one line from the input stream and return the
decoded data.
size, if given, is passed as size argument to the
read() method.
"""
# If we have lines cached from an earlier read, return
# them unconditionally
if self.linebuffer:
line = self.linebuffer[0]
del self.linebuffer[0]
if len(self.linebuffer) == 1:
# revert to charbuffer mode; we might need more data
# next time
self.charbuffer = self.linebuffer[0]
self.linebuffer = None
if not keepends:
line = line.splitlines(False)[0]
return line
readsize = size or 72
line = ""
# If size is given, we call read() only once
while True:
data = self.read(readsize, firstline=True)
if data:
# If we're at a "\r" read one extra character (which might
# be a "\n") to get a proper line ending. If the stream is
# temporarily exhausted we return the wrong line ending.
if data.endswith("\r"):
data += self.read(size=1, chars=1)
line += data
lines = line.splitlines(True)
if lines:
if len(lines) > 1:
# More than one line result; the first line is a full line
# to return
line = lines[0]
del lines[0]
if len(lines) > 1:
# cache the remaining lines
lines[-1] += self.charbuffer
self.linebuffer = lines
self.charbuffer = None
else:
# only one remaining line, put it back into charbuffer
self.charbuffer = lines[0] + self.charbuffer
if not keepends:
line = line.splitlines(False)[0]
break
line0withend = lines[0]
line0withoutend = lines[0].splitlines(False)[0]
if line0withend != line0withoutend: # We really have a line end
# Put the rest back together and keep it until the next call
self.charbuffer = "".join(lines[1:]) + self.charbuffer
if keepends:
line = line0withend
else:
line = line0withoutend
break
# we didn't get anything or this was our only try
if not data or size is not None:
if line and not keepends:
line = line.splitlines(False)[0]
break
if readsize<8000:
readsize *= 2
return line
def readlines(self, sizehint=None, keepends=True):
""" Read all lines available on the input stream
and return them as list of lines.
Line breaks are implemented using the codec's decoder
method and are included in the list entries.
sizehint, if given, is ignored since there is no efficient
way to finding the true end-of-line.
"""
data = self.read()
return data.splitlines(keepends)
def reset(self):
""" Resets the codec buffers used for keeping state.
Note that no stream repositioning should take place.
This method is primarily intended to be able to recover
from decoding errors.
"""
self.bytebuffer = ""
self.charbuffer = u""
self.linebuffer = None
def seek(self, offset, whence=0):
""" Set the input stream's current position.
Resets the codec buffers used for keeping state.
"""
self.stream.seek(offset, whence)
self.reset()
def next(self):
""" Return the next decoded line from the input stream."""
line = self.readline()
if line:
return line
raise StopIteration
def __iter__(self):
return self
def __getattr__(self, name,
getattr=getattr):
""" Inherit all other methods from the underlying stream.
"""
return getattr(self.stream, name)
def __enter__(self):
return self
def __exit__(self, type, value, tb):
self.stream.close()
###
class StreamReaderWriter:
""" StreamReaderWriter instances allow wrapping streams which
work in both read and write modes.
The design is such that one can use the factory functions
returned by the codec.lookup() function to construct the
instance.
"""
# Optional attributes set by the file wrappers below
encoding = 'unknown'
def __init__(self, stream, Reader, Writer, errors='strict'):
""" Creates a StreamReaderWriter instance.
stream must be a Stream-like object.
Reader, Writer must be factory functions or classes
providing the StreamReader, StreamWriter interface resp.
Error handling is done in the same way as defined for the
StreamWriter/Readers.
"""
self.stream = stream
self.reader = Reader(stream, errors)
self.writer = Writer(stream, errors)
self.errors = errors
def read(self, size=-1):
return self.reader.read(size)
def readline(self, size=None):
return self.reader.readline(size)
def readlines(self, sizehint=None):
return self.reader.readlines(sizehint)
def next(self):
""" Return the next decoded line from the input stream."""
return self.reader.next()
def __iter__(self):
return self
def write(self, data):
return self.writer.write(data)
def writelines(self, list):
return self.writer.writelines(list)
def reset(self):
self.reader.reset()
self.writer.reset()
def seek(self, offset, whence=0):
self.stream.seek(offset, whence)
self.reader.reset()
if whence == 0 and offset == 0:
self.writer.reset()
def __getattr__(self, name,
getattr=getattr):
""" Inherit all other methods from the underlying stream.
"""
return getattr(self.stream, name)
# these are needed to make "with codecs.open(...)" work properly
def __enter__(self):
return self
def __exit__(self, type, value, tb):
self.stream.close()
###
class StreamRecoder:
""" StreamRecoder instances provide a frontend - backend
view of encoding data.
They use the complete set of APIs returned by the
codecs.lookup() function to implement their task.
Data written to the stream is first decoded into an
35B2
intermediate format (which is dependent on the given codec
combination) and then written to the stream using an instance
of the provided Writer class.
In the other direction, data is read from the stream using a
Reader instance and then return encoded data to the caller.
"""
# Optional attributes set by the file wrappers below
data_encoding = 'unknown'
file_encoding = 'unknown'
def __init__(self, stream, encode, decode, Reader, Writer,
errors='strict'):
""" Creates a StreamRecoder instance which implements a two-way
conversion: encode and decode work on the frontend (the
input to .read() and output of .write()) while
Reader and Writer work on the backend (reading and
writing to the stream).
You can use these objects to do transparent direct
recodings from e.g. latin-1 to utf-8 and back.
stream must be a file-like object.
encode, decode must adhere to the Codec interface, Reader,
Writer must be factory functions or classes providing the
StreamReader, StreamWriter interface resp.
encode and decode are needed for the frontend translation,
Reader and Writer for the backend translation. Unicode is
used as intermediate encoding.
Error handling is done in the same way as defined for the
StreamWriter/Readers.
"""
self.stream = stream
self.encode = encode
self.decode = decode
self.reader = Reader(stream, errors)
self.writer = Writer(stream, errors)
self.errors = errors
def read(self, size=-1):
data = self.reader.read(size)
data, bytesencoded = self.encode(data, self.errors)
return data
def readline(self, size=None):
if size is None:
data = self.reader.readline()
else:
data = self.reader.readline(size)
data, bytesencoded = self.encode(data, self.errors)
return data
def readlines(self, sizehint=None):
data = self.reader.read()
data, bytesencoded = self.encode(data, self.errors)
return data.splitlines(1)
def next(self):
""" Return the next decoded line from the input stream."""
data = self.reader.next()
data, bytesencoded = self.encode(data, self.errors)
return data
def __iter__(self):
return self
def write(self, data):
data, bytesdecoded = self.decode(data, self.errors)
return self.writer.write(data)
def writelines(self, list):
data = ''.join(list)
data, bytesdecoded = self.decode(data, self.errors)
return self.writer.write(data)
def reset(self):
self.reader.reset()
self.writer.reset()
def __getattr__(self, name,
getattr=getattr):
""" Inherit all other methods from the underlying stream.
"""
return getattr(self.stream, name)
def __enter__(self):
return self
def __exit__(self, type, value, tb):
self.stream.close()
### Shortcuts
def open(filename, mode='rb', encoding=None, errors='strict', buffering=1):
""" Open an encoded file using the given mode and return
a wrapped version providing transparent encoding/decoding.
Note: The wrapped version will only accept the object format
defined by the codecs, i.e. Unicode objects for most builtin
codecs. Output is also codec dependent and will usually be
Unicode as well.
Files are always opened in binary mode, even if no binary mode
was specified. This is done to avoid data loss due to encodings
using 8-bit values. The default file mode is 'rb' meaning to
open the file in binary read mode.
encoding specifies the encoding which is to be used for the
file.
errors may be given to define the error handling. It defaults
to 'strict' which causes ValueErrors to be raised in case an
encoding error occurs.
buffering has the same meaning as for the builtin open() API.
It defaults to line buffered.
The returned wrapped file object provides an extra attribute
.encoding which allows querying the used encoding. This
attribute is only available if an encoding was specified as
parameter.
"""
if encoding is not None:
if 'U' in mode:
# No automatic conversion of '\n' is done on reading and writing
mode = mode.strip().replace('U', '')
if mode[:1] not in set('rwa'):
mode = 'r' + mode
if 'b' not in mode:
# Force opening of the file in binary mode
mode = mode + 'b'
file = __builtin__.open(filename, mode, buffering)
if encoding is None:
return file
info = lookup(encoding)
srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, errors)
# Add attributes to simplify introspection
srw.encoding = encoding
return srw
def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'):
""" Return a wrapped version of file which provides transparent
encoding translation.
Strings written to the wrapped file are interpreted according
to the given data_encoding and then written to the original
file as string using file_encoding. The intermediate encoding
will usually be Unicode but depends on the specified codecs.
Strings are read from the file using file_encoding and then
passed back to the caller as string using data_encoding.
If file_encoding is not given, it defaults to data_encoding.
errors may be given to define the error handling. It defaults
to 'strict' which causes ValueErrors to be raised in case an
encoding error occurs.
The returned wrapped file object provides two extra attributes
.data_encoding and .file_encoding which reflect the given
parameters of the same name. The attributes can be used for
introspection by Python programs.
"""
if file_encoding is None:
file_encoding = data_encoding
data_info = lookup(data_encoding)
file_info = lookup(file_encoding)
sr = StreamRecoder(file, data_info.encode, data_info.decode,
file_info.streamreader, file_info.streamwriter, errors)
# Add attributes to simplify introspection
sr.data_encoding = data_encoding
sr.file_encoding = file_encoding
return sr
### Helpers for codec lookup
def getencoder(encoding):
""" Lookup up the codec for the given encoding and return
its encoder function.
Raises a LookupError in case the encoding cannot be found.
"""
return lookup(encoding).encode
def getdecoder(encoding):
""" Lookup up the codec for the given encoding and return
its decoder function.
Raises a LookupError in case the encoding cannot be found.
"""
return lookup(encoding).decode
def getincrementalencoder(encoding):
""" Lookup up the codec for the given encoding and return
its IncrementalEncoder class or factory function.
Raises a LookupError in case the encoding cannot be found
or the codecs doesn't provide an incremental encoder.
"""
encoder = lookup(encoding).incrementalencoder
if encoder is None:
raise LookupError(encoding)
return encoder
def getincrementaldecoder(encoding):
""" Lookup up the codec for the given encoding and return
its IncrementalDecoder class or factory function.
Raises a LookupError in case the encoding cannot be found
or the codecs doesn't provide an incremental decoder.
"""
decoder = lookup(encoding).incrementaldecoder
if decoder is None:
raise LookupError(encoding)
return decoder
def getreader(encoding):
""" Lookup up the codec for the given encoding and return
its StreamReader class or factory function.
Raises a LookupError in case the encoding cannot be found.
"""