blob: dd2318721e968633f9e4ca6ea63f944206df9674 [file] [log] [blame]
Marc-André Lemburga866df82001-01-03 21:29:14 +00001""" Python Character Mapping Codec generated from 'CP850.TXT' with gencodec.py.
Guido van Rossum0229bf62000-03-10 23:17:24 +00002
3Written by Marc-Andre Lemburg (mal@lemburg.com).
4
5(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
Marc-André Lemburga866df82001-01-03 21:29:14 +00006(c) Copyright 2000 Guido van Rossum.
Guido van Rossum0229bf62000-03-10 23:17:24 +00007
8"""#"
9
10import codecs
11
12### Codec APIs
13
14class Codec(codecs.Codec):
15
16 def encode(self,input,errors='strict'):
17
18 return codecs.charmap_encode(input,errors,encoding_map)
19
20 def decode(self,input,errors='strict'):
21
22 return codecs.charmap_decode(input,errors,decoding_map)
23
24class StreamWriter(Codec,codecs.StreamWriter):
25 pass
26
27class StreamReader(Codec,codecs.StreamReader):
28 pass
29
30### encodings module API
31
32def getregentry():
33
34 return (Codec().encode,Codec().decode,StreamReader,StreamWriter)
35
36### Decoding Map
37
Marc-André Lemburga866df82001-01-03 21:29:14 +000038decoding_map = codecs.make_identity_dict(range(256))
39decoding_map.update({
Guido van Rossum0229bf62000-03-10 23:17:24 +000040 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
41 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
42 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
43 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
44 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
45 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
46 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
47 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
48 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
49 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
50 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
51 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
52 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
53 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
54 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
55 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
56 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
57 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
58 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
59 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
60 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
61 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
62 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
63 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
64 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
65 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
66 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
67 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
68 0x009c: 0x00a3, # POUND SIGN
69 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
70 0x009e: 0x00d7, # MULTIPLICATION SIGN
71 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
72 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
73 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
74 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
75 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
76 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
77 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
78 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
79 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
80 0x00a8: 0x00bf, # INVERTED QUESTION MARK
81 0x00a9: 0x00ae, # REGISTERED SIGN
82 0x00aa: 0x00ac, # NOT SIGN
83 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
84 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
85 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
86 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
87 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
88 0x00b0: 0x2591, # LIGHT SHADE
89 0x00b1: 0x2592, # MEDIUM SHADE
90 0x00b2: 0x2593, # DARK SHADE
91 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
92 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
93 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
94 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
95 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
96 0x00b8: 0x00a9, # COPYRIGHT SIGN
97 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
98 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
99 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
100 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
101 0x00bd: 0x00a2, # CENT SIGN
102 0x00be: 0x00a5, # YEN SIGN
103 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
104 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
105 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
106 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
107 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
108 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
109 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
110 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
111 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
112 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
113 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
114 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
115 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
116 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
117 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
118 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
119 0x00cf: 0x00a4, # CURRENCY SIGN
120 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH
121 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH
122 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
123 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
124 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
125 0x00d5: 0x0131, # LATIN SMALL LETTER DOTLESS I
126 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
127 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
128 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
129 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
130 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
131 0x00db: 0x2588, # FULL BLOCK
132 0x00dc: 0x2584, # LOWER HALF BLOCK
133 0x00dd: 0x00a6, # BROKEN BAR
134 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
135 0x00df: 0x2580, # UPPER HALF BLOCK
136 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
137 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
138 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
139 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
140 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
141 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
142 0x00e6: 0x00b5, # MICRO SIGN
143 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN
144 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN
145 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
146 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
147 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
148 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
149 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
150 0x00ee: 0x00af, # MACRON
151 0x00ef: 0x00b4, # ACUTE ACCENT
152 0x00f0: 0x00ad, # SOFT HYPHEN
153 0x00f1: 0x00b1, # PLUS-MINUS SIGN
154 0x00f2: 0x2017, # DOUBLE LOW LINE
155 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
156 0x00f4: 0x00b6, # PILCROW SIGN
157 0x00f5: 0x00a7, # SECTION SIGN
158 0x00f6: 0x00f7, # DIVISION SIGN
159 0x00f7: 0x00b8, # CEDILLA
160 0x00f8: 0x00b0, # DEGREE SIGN
161 0x00f9: 0x00a8, # DIAERESIS
162 0x00fa: 0x00b7, # MIDDLE DOT
163 0x00fb: 0x00b9, # SUPERSCRIPT ONE
164 0x00fc: 0x00b3, # SUPERSCRIPT THREE
165 0x00fd: 0x00b2, # SUPERSCRIPT TWO
166 0x00fe: 0x25a0, # BLACK SQUARE
167 0x00ff: 0x00a0, # NO-BREAK SPACE
Marc-André Lemburga866df82001-01-03 21:29:14 +0000168})
Guido van Rossum0229bf62000-03-10 23:17:24 +0000169
170### Encoding Map
171
Marc-André Lemburg716cf912001-05-16 09:41:45 +0000172encoding_map = codecs.make_encoding_map(decoding_map)