Mercurial > cpython-lru_cache-weakref
annotate Lib/codecs.py @ 16413:8819867f14ef legacy-trunk
Patch derived from Trent's 101162: a Python/C API testing framework.
STILL NEEDS UNIX BUILD CHANGES.
| author | Tim Peters <tim.peters@gmail.com> |
|---|---|
| date | Fri, 02 Feb 2001 05:57:15 +0000 |
| parents | b5345e99596b |
| children | c872fdf10130 |
| rev | line source |
|---|---|
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
1 """ codecs -- Python Codec Registry, API and helpers. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
2 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
3 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
4 Written by Marc-Andre Lemburg (mal@lemburg.com). |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
5 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
6 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
7 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
8 """#" |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
9 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
10 import struct,types,__builtin__ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
11 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
12 ### Registry and builtin stateless codec functions |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
13 |
|
12195
bc861add5d71
Marc-Andre Lemburg: Error reporting in the codec registry and lookup
Guido van Rossum <guido@python.org>
parents:
12051
diff
changeset
|
14 try: |
|
bc861add5d71
Marc-Andre Lemburg: Error reporting in the codec registry and lookup
Guido van Rossum <guido@python.org>
parents:
12051
diff
changeset
|
15 from _codecs import * |
|
bc861add5d71
Marc-Andre Lemburg: Error reporting in the codec registry and lookup
Guido van Rossum <guido@python.org>
parents:
12051
diff
changeset
|
16 except ImportError,why: |
|
bc861add5d71
Marc-Andre Lemburg: Error reporting in the codec registry and lookup
Guido van Rossum <guido@python.org>
parents:
12051
diff
changeset
|
17 raise SystemError,\ |
|
bc861add5d71
Marc-Andre Lemburg: Error reporting in the codec registry and lookup
Guido van Rossum <guido@python.org>
parents:
12051
diff
changeset
|
18 'Failed to load the builtin codecs: %s' % why |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
19 |
|
16070
b5345e99596b
added __all__ lists to a number of Python modules
Skip Montanaro <skip@pobox.com>
parents:
15867
diff
changeset
|
20 __all__ = ["register","lookup","open","EncodedFile","BOM","BOM_BE", |
|
b5345e99596b
added __all__ lists to a number of Python modules
Skip Montanaro <skip@pobox.com>
parents:
15867
diff
changeset
|
21 "BOM_LE","BOM32_BE","BOM32_LE","BOM64_BE","BOM64_LE"] |
|
b5345e99596b
added __all__ lists to a number of Python modules
Skip Montanaro <skip@pobox.com>
parents:
15867
diff
changeset
|
22 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
23 ### Constants |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
24 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
25 # |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
26 # Byte Order Mark (BOM) and its possible values (BOM_BE, BOM_LE) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
27 # |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
28 BOM = struct.pack('=H',0xFEFF) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
29 # |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
30 BOM_BE = BOM32_BE = '\376\377' |
|
15867
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
31 # corresponds to Unicode U+FEFF in UTF-16 on big endian |
|
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
32 # platforms == ZERO WIDTH NO-BREAK SPACE |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
33 BOM_LE = BOM32_LE = '\377\376' |
|
15867
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
34 # corresponds to Unicode U+FFFE in UTF-16 on little endian |
|
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
35 # platforms == defined as being an illegal Unicode character |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
36 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
37 # |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
38 # 64-bit Byte Order Marks |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
39 # |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
40 BOM64_BE = '\000\000\376\377' |
|
15867
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
41 # corresponds to Unicode U+0000FEFF in UCS-4 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
42 BOM64_LE = '\377\376\000\000' |
|
15867
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
43 # corresponds to Unicode U+0000FFFE in UCS-4 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
44 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
45 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
46 ### Codec base classes (defining the API) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
47 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
48 class Codec: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
49 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
50 """ Defines the interface for stateless encoders/decoders. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
51 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
52 The .encode()/.decode() methods may implement different error |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
53 handling schemes by providing the errors argument. These |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
54 string values are defined: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
55 |
| 12051 | 56 'strict' - raise a ValueError error (or a subclass) |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
57 'ignore' - ignore the character and continue with the next |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
58 'replace' - replace with a suitable replacement character; |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
59 Python will use the official U+FFFD REPLACEMENT |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
60 CHARACTER for the builtin Unicode codecs. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
61 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
62 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
63 def encode(self,input,errors='strict'): |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
64 |
|
12010
bd1014215f62
"intput" --> "input" (in docstring); noted by Detlef Lannert
Fred Drake <fdrake@acm.org>
parents:
11990
diff
changeset
|
65 """ Encodes the object input and returns a tuple (output |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
66 object, length consumed). |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
67 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
68 errors defines the error handling to apply. It defaults to |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
69 'strict' handling. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
70 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
71 The method may not store state in the Codec instance. Use |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
72 StreamCodec for codecs which have to keep state in order to |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
73 make encoding/decoding efficient. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
74 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
75 The encoder must be able to handle zero length input and |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
76 return an empty object of the output object type in this |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
77 situation. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
78 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
79 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
80 raise NotImplementedError |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
81 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
82 def decode(self,input,errors='strict'): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
83 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
84 """ Decodes the object input and returns a tuple (output |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
85 object, length consumed). |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
86 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
87 input must be an object which provides the bf_getreadbuf |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
88 buffer slot. Python strings, buffer objects and memory |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
89 mapped files are examples of objects providing this slot. |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
90 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
91 errors defines the error handling to apply. It defaults to |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
92 'strict' handling. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
93 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
94 The method may not store state in the Codec instance. Use |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
95 StreamCodec for codecs which have to keep state in order to |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
96 make encoding/decoding efficient. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
97 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
98 The decoder must be able to handle zero length input and |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
99 return an empty object of the output object type in this |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
100 situation. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
101 |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
102 """ |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
103 raise NotImplementedError |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
104 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
105 # |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
106 # The StreamWriter and StreamReader class provide generic working |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
107 # interfaces which can be used to implement new encodings submodules |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
108 # very easily. See encodings/utf_8.py for an example on how this is |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
109 # done. |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
110 # |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
111 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
112 class StreamWriter(Codec): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
113 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
114 def __init__(self,stream,errors='strict'): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
115 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
116 """ Creates a StreamWriter instance. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
117 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
118 stream must be a file-like object open for writing |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
119 (binary) data. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
120 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
121 The StreamWriter may implement different error handling |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
122 schemes by providing the errors keyword argument. These |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
123 parameters are defined: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
124 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
125 'strict' - raise a ValueError (or a subclass) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
126 'ignore' - ignore the character and continue with the next |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
127 'replace'- replace with a suitable replacement character |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
128 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
129 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
130 self.stream = stream |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
131 self.errors = errors |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
132 |
| 12367 | 133 def write(self, object): |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
134 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
135 """ Writes the object's contents encoded to self.stream. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
136 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
137 data, consumed = self.encode(object,self.errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
138 self.stream.write(data) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
139 |
| 12367 | 140 def writelines(self, list): |
| 141 | |
| 142 """ Writes the concatenated list of strings to the stream | |
| 143 using .write(). | |
| 144 """ | |
| 145 self.write(''.join(list)) | |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
146 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
147 def reset(self): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
148 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
149 """ Flushes and resets the codec buffers used for keeping state. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
150 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
151 Calling this method should ensure that the data on the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
152 output is put into a clean state, that allows appending |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
153 of new fresh data without having to rescan the whole |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
154 stream to recover state. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
155 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
156 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
157 pass |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
158 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
159 def __getattr__(self,name, |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
160 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
161 getattr=getattr): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
162 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
163 """ Inherit all other methods from the underlying stream. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
164 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
165 return getattr(self.stream,name) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
166 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
167 ### |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
168 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
169 class StreamReader(Codec): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
170 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
171 def __init__(self,stream,errors='strict'): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
172 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
173 """ Creates a StreamReader instance. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
174 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
175 stream must be a file-like object open for reading |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
176 (binary) data. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
177 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
178 The StreamReader may implement different error handling |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
179 schemes by providing the errors keyword argument. These |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
180 parameters are defined: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
181 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
182 'strict' - raise a ValueError (or a subclass) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
183 'ignore' - ignore the character and continue with the next |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
184 'replace'- replace with a suitable replacement character; |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
185 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
186 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
187 self.stream = stream |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
188 self.errors = errors |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
189 |
| 12367 | 190 def read(self, size=-1): |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
191 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
192 """ Decodes data from the stream self.stream and returns the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
193 resulting object. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
194 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
195 size indicates the approximate maximum number of bytes to |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
196 read from the stream for decoding purposes. The decoder |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
197 can modify this setting as appropriate. The default value |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
198 -1 indicates to read and decode as much as possible. size |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
199 is intended to prevent having to decode huge files in one |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
200 step. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
201 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
202 The method should use a greedy read strategy meaning that |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
203 it should read as much data as is allowed within the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
204 definition of the encoding and the given size, e.g. if |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
205 optional encoding endings or state markers are available |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
206 on the stream, these should be read too. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
207 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
208 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
209 # Unsliced reading: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
210 if size < 0: |
|
15498
46275611cd59
(Patch #102698) Fix for a bug reported by Wade Leftwich:
Andrew M. Kuchling <amk@amk.ca>
parents:
14978
diff
changeset
|
211 return self.decode(self.stream.read(), self.errors)[0] |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
212 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
213 # Sliced reading: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
214 read = self.stream.read |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
215 decode = self.decode |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
216 data = read(size) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
217 i = 0 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
218 while 1: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
219 try: |
|
15498
46275611cd59
(Patch #102698) Fix for a bug reported by Wade Leftwich:
Andrew M. Kuchling <amk@amk.ca>
parents:
14978
diff
changeset
|
220 object, decodedbytes = decode(data, self.errors) |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
221 except ValueError,why: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
222 # This method is slow but should work under pretty much |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
223 # all conditions; at most 10 tries are made |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
224 i = i + 1 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
225 newdata = read(1) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
226 if not newdata or i > 10: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
227 raise |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
228 data = data + newdata |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
229 else: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
230 return object |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
231 |
| 12367 | 232 def readline(self, size=None): |
| 233 | |
| 234 """ Read one line from the input stream and return the | |
| 235 decoded data. | |
| 236 | |
|
12389
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
237 Note: Unlike the .readlines() method, this method inherits |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
238 the line breaking knowledge from the underlying stream's |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
239 .readline() method -- there is currently no support for |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
240 line breaking using the codec decoder due to lack of line |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
241 buffering. Sublcasses should however, if possible, try to |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
242 implement this method using their own knowledge of line |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
243 breaking. |
| 12367 | 244 |
| 245 size, if given, is passed as size argument to the stream's | |
| 246 .readline() method. | |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
247 |
| 12367 | 248 """ |
| 249 if size is None: | |
| 250 line = self.stream.readline() | |
| 251 else: | |
| 252 line = self.stream.readline(size) | |
|
15498
46275611cd59
(Patch #102698) Fix for a bug reported by Wade Leftwich:
Andrew M. Kuchling <amk@amk.ca>
parents:
14978
diff
changeset
|
253 return self.decode(line,self.errors)[0] |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
254 |
| 12367 | 255 |
| 256 def readlines(self, sizehint=0): | |
| 257 | |
| 258 """ Read all lines available on the input stream | |
| 259 and return them as list of lines. | |
| 260 | |
| 261 Line breaks are implemented using the codec's decoder | |
| 262 method and are included in the list entries. | |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
263 |
| 12367 | 264 sizehint, if given, is passed as size argument to the |
| 265 stream's .read() method. | |
| 266 | |
| 267 """ | |
| 268 if sizehint is None: | |
| 269 data = self.stream.read() | |
| 270 else: | |
| 271 data = self.stream.read(sizehint) | |
|
15498
46275611cd59
(Patch #102698) Fix for a bug reported by Wade Leftwich:
Andrew M. Kuchling <amk@amk.ca>
parents:
14978
diff
changeset
|
272 return self.decode(data,self.errors)[0].splitlines(1) |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
273 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
274 def reset(self): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
275 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
276 """ Resets the codec buffers used for keeping state. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
277 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
278 Note that no stream repositioning should take place. |
|
13620
5b727ab37092
Spelling fixes supplied by Rob W. W. Hooft. All these are fixes in either
Thomas Wouters <thomas@python.org>
parents:
12986
diff
changeset
|
279 This method is primarily intended to be able to recover |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
280 from decoding errors. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
281 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
282 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
283 pass |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
284 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
285 def __getattr__(self,name, |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
286 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
287 getattr=getattr): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
288 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
289 """ Inherit all other methods from the underlying stream. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
290 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
291 return getattr(self.stream,name) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
292 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
293 ### |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
294 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
295 class StreamReaderWriter: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
296 |
|
12389
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
297 """ StreamReaderWriter instances allow wrapping streams which |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
298 work in both read and write modes. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
299 |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
300 The design is such that one can use the factory functions |
|
13620
5b727ab37092
Spelling fixes supplied by Rob W. W. Hooft. All these are fixes in either
Thomas Wouters <thomas@python.org>
parents:
12986
diff
changeset
|
301 returned by the codec.lookup() function to construct the |
|
12389
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
302 instance. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
303 |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
304 """ |
| 12367 | 305 # Optional attributes set by the file wrappers below |
| 306 encoding = 'unknown' | |
| 307 | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
308 def __init__(self,stream,Reader,Writer,errors='strict'): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
309 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
310 """ Creates a StreamReaderWriter instance. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
311 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
312 stream must be a Stream-like object. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
313 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
314 Reader, Writer must be factory functions or classes |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
315 providing the StreamReader, StreamWriter interface resp. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
316 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
317 Error handling is done in the same way as defined for the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
318 StreamWriter/Readers. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
319 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
320 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
321 self.stream = stream |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
322 self.reader = Reader(stream, errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
323 self.writer = Writer(stream, errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
324 self.errors = errors |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
325 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
326 def read(self,size=-1): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
327 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
328 return self.reader.read(size) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
329 |
| 12534 | 330 def readline(self, size=None): |
| 12367 | 331 |
| 332 return self.reader.readline(size) | |
| 333 | |
| 12534 | 334 def readlines(self, sizehint=None): |
| 12367 | 335 |
| 336 return self.reader.readlines(sizehint) | |
| 337 | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
338 def write(self,data): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
339 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
340 return self.writer.write(data) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
341 |
| 12367 | 342 def writelines(self,list): |
| 343 | |
| 344 return self.writer.writelines(list) | |
| 345 | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
346 def reset(self): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
347 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
348 self.reader.reset() |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
349 self.writer.reset() |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
350 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
351 def __getattr__(self,name, |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
352 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
353 getattr=getattr): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
354 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
355 """ Inherit all other methods from the underlying stream. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
356 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
357 return getattr(self.stream,name) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
358 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
359 ### |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
360 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
361 class StreamRecoder: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
362 |
|
12389
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
363 """ StreamRecoder instances provide a frontend - backend |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
364 view of encoding data. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
365 |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
366 They use the complete set of APIs returned by the |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
367 codecs.lookup() function to implement their task. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
368 |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
369 Data written to the stream is first decoded into an |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
370 intermediate format (which is dependent on the given codec |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
371 combination) and then written to the stream using an instance |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
372 of the provided Writer class. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
373 |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
374 In the other direction, data is read from the stream using a |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
375 Reader instance and then return encoded data to the caller. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
376 |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
377 """ |
| 12367 | 378 # Optional attributes set by the file wrappers below |
| 379 data_encoding = 'unknown' | |
| 380 file_encoding = 'unknown' | |
| 381 | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
382 def __init__(self,stream,encode,decode,Reader,Writer,errors='strict'): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
383 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
384 """ Creates a StreamRecoder instance which implements a two-way |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
385 conversion: encode and decode work on the frontend (the |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
386 input to .read() and output of .write()) while |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
387 Reader and Writer work on the backend (reading and |
|
12011
4fa25a292273
Oops, another in the same file; I should read the mail fully before
Fred Drake <fdrake@acm.org>
parents:
12010
diff
changeset
|
388 writing to the stream). |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
389 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
390 You can use these objects to do transparent direct |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
391 recodings from e.g. latin-1 to utf-8 and back. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
392 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
393 stream must be a file-like object. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
394 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
395 encode, decode must adhere to the Codec interface, Reader, |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
396 Writer must be factory functions or classes providing the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
397 StreamReader, StreamWriter interface resp. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
398 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
399 encode and decode are needed for the frontend translation, |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
400 Reader and Writer for the backend translation. Unicode is |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
401 used as intermediate encoding. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
402 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
403 Error handling is done in the same way as defined for the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
404 StreamWriter/Readers. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
405 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
406 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
407 self.stream = stream |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
408 self.encode = encode |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
409 self.decode = decode |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
410 self.reader = Reader(stream, errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
411 self.writer = Writer(stream, errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
412 self.errors = errors |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
413 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
414 def read(self,size=-1): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
415 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
416 data = self.reader.read(size) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
417 data, bytesencoded = self.encode(data, self.errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
418 return data |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
419 |
| 12367 | 420 def readline(self,size=None): |
| 421 | |
| 422 if size is None: | |
| 423 data = self.reader.readline() | |
| 424 else: | |
| 425 data = self.reader.readline(size) | |
| 426 data, bytesencoded = self.encode(data, self.errors) | |
| 427 return data | |
| 428 | |
| 429 def readlines(self,sizehint=None): | |
| 430 | |
| 431 if sizehint is None: | |
| 432 data = self.reader.read() | |
| 433 else: | |
| 434 data = self.reader.read(sizehint) | |
| 435 data, bytesencoded = self.encode(data, self.errors) | |
| 436 return data.splitlines(1) | |
| 437 | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
438 def write(self,data): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
439 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
440 data, bytesdecoded = self.decode(data, self.errors) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
441 return self.writer.write(data) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
442 |
| 12367 | 443 def writelines(self,list): |
| 444 | |
| 445 data = ''.join(list) | |
| 446 data, bytesdecoded = self.decode(data, self.errors) | |
| 447 return self.writer.write(data) | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
448 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
449 def reset(self): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
450 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
451 self.reader.reset() |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
452 self.writer.reset() |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
453 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
454 def __getattr__(self,name, |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
455 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
456 getattr=getattr): |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
457 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
458 """ Inherit all other methods from the underlying stream. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
459 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
460 return getattr(self.stream,name) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
461 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
462 ### Shortcuts |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
463 |
|
12986
5279a6e00d36
Marc-Andre Lemburg <mal@lemburg.com>:
Marc-André Lemburg <mal@egenix.com>
parents:
12534
diff
changeset
|
464 def open(filename, mode='rb', encoding=None, errors='strict', buffering=1): |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
465 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
466 """ Open an encoded file using the given mode and return |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
467 a wrapped version providing transparent encoding/decoding. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
468 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
469 Note: The wrapped version will only accept the object format |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
470 defined by the codecs, i.e. Unicode objects for most builtin |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
471 codecs. Output is also codec dependent and will usually by |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
472 Unicode as well. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
473 |
|
12986
5279a6e00d36
Marc-Andre Lemburg <mal@lemburg.com>:
Marc-André Lemburg <mal@egenix.com>
parents:
12534
diff
changeset
|
474 Files are always opened in binary mode, even if no binary mode |
|
5279a6e00d36
Marc-Andre Lemburg <mal@lemburg.com>:
Marc-André Lemburg <mal@egenix.com>
parents:
12534
diff
changeset
|
475 was specified. Thisis done to avoid data loss due to encodings |
|
5279a6e00d36
Marc-Andre Lemburg <mal@lemburg.com>:
Marc-André Lemburg <mal@egenix.com>
parents:
12534
diff
changeset
|
476 using 8-bit values. The default file mode is 'rb' meaning to |
|
5279a6e00d36
Marc-Andre Lemburg <mal@lemburg.com>:
Marc-André Lemburg <mal@egenix.com>
parents:
12534
diff
changeset
|
477 open the file in binary read mode. |
|
5279a6e00d36
Marc-Andre Lemburg <mal@lemburg.com>:
Marc-André Lemburg <mal@egenix.com>
parents:
12534
diff
changeset
|
478 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
479 encoding specifies the encoding which is to be used for the |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
480 the file. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
481 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
482 errors may be given to define the error handling. It defaults |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
483 to 'strict' which causes ValueErrors to be raised in case an |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
484 encoding error occurs. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
485 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
486 buffering has the same meaning as for the builtin open() API. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
487 It defaults to line buffered. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
488 |
|
12389
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
489 The returned wrapped file object provides an extra attribute |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
490 .encoding which allows querying the used encoding. This |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
491 attribute is only available if an encoding was specified as |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
492 parameter. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
493 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
494 """ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
495 if encoding is not None and \ |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
496 'b' not in mode: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
497 # Force opening of the file in binary mode |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
498 mode = mode + 'b' |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
499 file = __builtin__.open(filename, mode, buffering) |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
500 if encoding is None: |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
501 return file |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
502 (e,d,sr,sw) = lookup(encoding) |
| 12367 | 503 srw = StreamReaderWriter(file, sr, sw, errors) |
| 504 # Add attributes to simplify introspection | |
| 505 srw.encoding = encoding | |
| 506 return srw | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
507 |
| 12367 | 508 def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'): |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
509 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
510 """ Return a wrapped version of file which provides transparent |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
511 encoding translation. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
512 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
513 Strings written to the wrapped file are interpreted according |
| 12367 | 514 to the given data_encoding and then written to the original |
| 515 file as string using file_encoding. The intermediate encoding | |
| 516 will usually be Unicode but depends on the specified codecs. | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
517 |
| 12367 | 518 Strings are read from the file using file_encoding and then |
| 519 passed back to the caller as string using data_encoding. | |
| 520 | |
| 521 If file_encoding is not given, it defaults to data_encoding. | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
522 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
523 errors may be given to define the error handling. It defaults |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
524 to 'strict' which causes ValueErrors to be raised in case an |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
525 encoding error occurs. |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
526 |
|
12389
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
527 The returned wrapped file object provides two extra attributes |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
528 .data_encoding and .file_encoding which reflect the given |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
529 parameters of the same name. The attributes can be used for |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
530 introspection by Python programs. |
|
e5b0bea03cfa
M.-A. Lemburg <mal@lemburg.com>:
Fred Drake <fdrake@acm.org>
parents:
12373
diff
changeset
|
531 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
532 """ |
| 12367 | 533 if file_encoding is None: |
| 534 file_encoding = data_encoding | |
| 535 encode, decode = lookup(data_encoding)[:2] | |
| 536 Reader, Writer = lookup(file_encoding)[2:] | |
| 537 sr = StreamRecoder(file, | |
| 538 encode,decode,Reader,Writer, | |
| 539 errors) | |
| 540 # Add attributes to simplify introspection | |
| 541 sr.data_encoding = data_encoding | |
| 542 sr.file_encoding = file_encoding | |
| 543 return sr | |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
544 |
|
15706
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
545 ### Helpers for charmap-based codecs |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
546 |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
547 def make_identity_dict(rng): |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
548 |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
549 """ make_identity_dict(rng) -> dict |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
550 |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
551 Return a dictionary where elements of the rng sequence are |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
552 mapped to themselves. |
|
15867
f5a3d98a35bc
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
15706
diff
changeset
|
553 |
|
15706
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
554 """ |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
555 res = {} |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
556 for i in rng: |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
557 res[i]=i |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
558 return res |
|
bf9bb0e3dd34
This patch changes the default behaviour of the builtin charmap
Marc-André Lemburg <mal@egenix.com>
parents:
15498
diff
changeset
|
559 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
560 ### Tests |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
561 |
|
11990
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
562 if __name__ == '__main__': |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
563 |
|
f104251b6f8f
Module codecs -- Python Codec Registry, API and helpers. Written by
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
564 import sys |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
565 |
| 12367 | 566 # Make stdout translate Latin-1 output into UTF-8 output |
| 567 sys.stdout = EncodedFile(sys.stdout, 'latin-1', 'utf-8') | |
|
12373
d63b57ac617d
Deleted trailing whitespace. This is really a way to be able to add
Guido van Rossum <guido@python.org>
parents:
12367
diff
changeset
|
568 |
| 12367 | 569 # Have stdin translate Latin-1 input into UTF-8 input |
| 570 sys.stdin = EncodedFile(sys.stdin, 'utf-8', 'latin-1') |