blob: c0e8088ea829ffed5adf6aff2442f4b310efb77b [file] [log] [blame]
Thomas Woutersa9773292006-04-21 09:43:23 +00001""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py.
Guido van Rossum0229bf62000-03-10 23:17:24 +00002
3"""#"
4
5import codecs
6
7### Codec APIs
8
9class Codec(codecs.Codec):
10
11 def encode(self,input,errors='strict'):
Thomas Wouters73e5a5b2006-06-08 15:35:45 +000012 return codecs.charmap_encode(input,errors,encoding_table)
Tim Peters469cdad2002-08-08 20:19:19 +000013
Guido van Rossum0229bf62000-03-10 23:17:24 +000014 def decode(self,input,errors='strict'):
Marc-André Lemburga1129f42005-10-21 13:49:12 +000015 return codecs.charmap_decode(input,errors,decoding_table)
Tim Peters536cf992005-12-25 23:18:31 +000016
Thomas Woutersa9773292006-04-21 09:43:23 +000017class IncrementalEncoder(codecs.IncrementalEncoder):
18 def encode(self, input, final=False):
Thomas Wouters73e5a5b2006-06-08 15:35:45 +000019 return codecs.charmap_encode(input,self.errors,encoding_table)[0]
Thomas Woutersa9773292006-04-21 09:43:23 +000020
21class IncrementalDecoder(codecs.IncrementalDecoder):
22 def decode(self, input, final=False):
23 return codecs.charmap_decode(input,self.errors,decoding_table)[0]
24
Guido van Rossum0229bf62000-03-10 23:17:24 +000025class StreamWriter(Codec,codecs.StreamWriter):
26 pass
Tim Peters469cdad2002-08-08 20:19:19 +000027
Guido van Rossum0229bf62000-03-10 23:17:24 +000028class StreamReader(Codec,codecs.StreamReader):
29 pass
30
31### encodings module API
32
33def getregentry():
Thomas Woutersa9773292006-04-21 09:43:23 +000034 return codecs.CodecInfo(
35 name='cp1252',
36 encode=Codec().encode,
37 decode=Codec().decode,
38 incrementalencoder=IncrementalEncoder,
39 incrementaldecoder=IncrementalDecoder,
40 streamreader=StreamReader,
41 streamwriter=StreamWriter,
42 )
Guido van Rossum0229bf62000-03-10 23:17:24 +000043
Guido van Rossum0229bf62000-03-10 23:17:24 +000044
Marc-André Lemburga1129f42005-10-21 13:49:12 +000045### Decoding Table
46
47decoding_table = (
Guido van Rossumef87d6e2007-05-02 19:09:54 +000048 '\x00' # 0x00 -> NULL
49 '\x01' # 0x01 -> START OF HEADING
50 '\x02' # 0x02 -> START OF TEXT
51 '\x03' # 0x03 -> END OF TEXT
52 '\x04' # 0x04 -> END OF TRANSMISSION
53 '\x05' # 0x05 -> ENQUIRY
54 '\x06' # 0x06 -> ACKNOWLEDGE
55 '\x07' # 0x07 -> BELL
56 '\x08' # 0x08 -> BACKSPACE
57 '\t' # 0x09 -> HORIZONTAL TABULATION
58 '\n' # 0x0A -> LINE FEED
59 '\x0b' # 0x0B -> VERTICAL TABULATION
60 '\x0c' # 0x0C -> FORM FEED
61 '\r' # 0x0D -> CARRIAGE RETURN
62 '\x0e' # 0x0E -> SHIFT OUT
63 '\x0f' # 0x0F -> SHIFT IN
64 '\x10' # 0x10 -> DATA LINK ESCAPE
65 '\x11' # 0x11 -> DEVICE CONTROL ONE
66 '\x12' # 0x12 -> DEVICE CONTROL TWO
67 '\x13' # 0x13 -> DEVICE CONTROL THREE
68 '\x14' # 0x14 -> DEVICE CONTROL FOUR
69 '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
70 '\x16' # 0x16 -> SYNCHRONOUS IDLE
71 '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
72 '\x18' # 0x18 -> CANCEL
73 '\x19' # 0x19 -> END OF MEDIUM
74 '\x1a' # 0x1A -> SUBSTITUTE
75 '\x1b' # 0x1B -> ESCAPE
76 '\x1c' # 0x1C -> FILE SEPARATOR
77 '\x1d' # 0x1D -> GROUP SEPARATOR
78 '\x1e' # 0x1E -> RECORD SEPARATOR
79 '\x1f' # 0x1F -> UNIT SEPARATOR
80 ' ' # 0x20 -> SPACE
81 '!' # 0x21 -> EXCLAMATION MARK
82 '"' # 0x22 -> QUOTATION MARK
83 '#' # 0x23 -> NUMBER SIGN
84 '$' # 0x24 -> DOLLAR SIGN
85 '%' # 0x25 -> PERCENT SIGN
86 '&' # 0x26 -> AMPERSAND
87 "'" # 0x27 -> APOSTROPHE
88 '(' # 0x28 -> LEFT PARENTHESIS
89 ')' # 0x29 -> RIGHT PARENTHESIS
90 '*' # 0x2A -> ASTERISK
91 '+' # 0x2B -> PLUS SIGN
92 ',' # 0x2C -> COMMA
93 '-' # 0x2D -> HYPHEN-MINUS
94 '.' # 0x2E -> FULL STOP
95 '/' # 0x2F -> SOLIDUS
96 '0' # 0x30 -> DIGIT ZERO
97 '1' # 0x31 -> DIGIT ONE
98 '2' # 0x32 -> DIGIT TWO
99 '3' # 0x33 -> DIGIT THREE
100 '4' # 0x34 -> DIGIT FOUR
101 '5' # 0x35 -> DIGIT FIVE
102 '6' # 0x36 -> DIGIT SIX
103 '7' # 0x37 -> DIGIT SEVEN
104 '8' # 0x38 -> DIGIT EIGHT
105 '9' # 0x39 -> DIGIT NINE
106 ':' # 0x3A -> COLON
107 ';' # 0x3B -> SEMICOLON
108 '<' # 0x3C -> LESS-THAN SIGN
109 '=' # 0x3D -> EQUALS SIGN
110 '>' # 0x3E -> GREATER-THAN SIGN
111 '?' # 0x3F -> QUESTION MARK
112 '@' # 0x40 -> COMMERCIAL AT
113 'A' # 0x41 -> LATIN CAPITAL LETTER A
114 'B' # 0x42 -> LATIN CAPITAL LETTER B
115 'C' # 0x43 -> LATIN CAPITAL LETTER C
116 'D' # 0x44 -> LATIN CAPITAL LETTER D
117 'E' # 0x45 -> LATIN CAPITAL LETTER E
118 'F' # 0x46 -> LATIN CAPITAL LETTER F
119 'G' # 0x47 -> LATIN CAPITAL LETTER G
120 'H' # 0x48 -> LATIN CAPITAL LETTER H
121 'I' # 0x49 -> LATIN CAPITAL LETTER I
122 'J' # 0x4A -> LATIN CAPITAL LETTER J
123 'K' # 0x4B -> LATIN CAPITAL LETTER K
124 'L' # 0x4C -> LATIN CAPITAL LETTER L
125 'M' # 0x4D -> LATIN CAPITAL LETTER M
126 'N' # 0x4E -> LATIN CAPITAL LETTER N
127 'O' # 0x4F -> LATIN CAPITAL LETTER O
128 'P' # 0x50 -> LATIN CAPITAL LETTER P
129 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
130 'R' # 0x52 -> LATIN CAPITAL LETTER R
131 'S' # 0x53 -> LATIN CAPITAL LETTER S
132 'T' # 0x54 -> LATIN CAPITAL LETTER T
133 'U' # 0x55 -> LATIN CAPITAL LETTER U
134 'V' # 0x56 -> LATIN CAPITAL LETTER V
135 'W' # 0x57 -> LATIN CAPITAL LETTER W
136 'X' # 0x58 -> LATIN CAPITAL LETTER X
137 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
138 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
139 '[' # 0x5B -> LEFT SQUARE BRACKET
140 '\\' # 0x5C -> REVERSE SOLIDUS
141 ']' # 0x5D -> RIGHT SQUARE BRACKET
142 '^' # 0x5E -> CIRCUMFLEX ACCENT
143 '_' # 0x5F -> LOW LINE
144 '`' # 0x60 -> GRAVE ACCENT
145 'a' # 0x61 -> LATIN SMALL LETTER A
146 'b' # 0x62 -> LATIN SMALL LETTER B
147 'c' # 0x63 -> LATIN SMALL LETTER C
148 'd' # 0x64 -> LATIN SMALL LETTER D
149 'e' # 0x65 -> LATIN SMALL LETTER E
150 'f' # 0x66 -> LATIN SMALL LETTER F
151 'g' # 0x67 -> LATIN SMALL LETTER G
152 'h' # 0x68 -> LATIN SMALL LETTER H
153 'i' # 0x69 -> LATIN SMALL LETTER I
154 'j' # 0x6A -> LATIN SMALL LETTER J
155 'k' # 0x6B -> LATIN SMALL LETTER K
156 'l' # 0x6C -> LATIN SMALL LETTER L
157 'm' # 0x6D -> LATIN SMALL LETTER M
158 'n' # 0x6E -> LATIN SMALL LETTER N
159 'o' # 0x6F -> LATIN SMALL LETTER O
160 'p' # 0x70 -> LATIN SMALL LETTER P
161 'q' # 0x71 -> LATIN SMALL LETTER Q
162 'r' # 0x72 -> LATIN SMALL LETTER R
163 's' # 0x73 -> LATIN SMALL LETTER S
164 't' # 0x74 -> LATIN SMALL LETTER T
165 'u' # 0x75 -> LATIN SMALL LETTER U
166 'v' # 0x76 -> LATIN SMALL LETTER V
167 'w' # 0x77 -> LATIN SMALL LETTER W
168 'x' # 0x78 -> LATIN SMALL LETTER X
169 'y' # 0x79 -> LATIN SMALL LETTER Y
170 'z' # 0x7A -> LATIN SMALL LETTER Z
171 '{' # 0x7B -> LEFT CURLY BRACKET
172 '|' # 0x7C -> VERTICAL LINE
173 '}' # 0x7D -> RIGHT CURLY BRACKET
174 '~' # 0x7E -> TILDE
175 '\x7f' # 0x7F -> DELETE
176 '\u20ac' # 0x80 -> EURO SIGN
177 '\ufffe' # 0x81 -> UNDEFINED
178 '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
179 '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
180 '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
181 '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
182 '\u2020' # 0x86 -> DAGGER
183 '\u2021' # 0x87 -> DOUBLE DAGGER
184 '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
185 '\u2030' # 0x89 -> PER MILLE SIGN
186 '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
187 '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
188 '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
189 '\ufffe' # 0x8D -> UNDEFINED
190 '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
191 '\ufffe' # 0x8F -> UNDEFINED
192 '\ufffe' # 0x90 -> UNDEFINED
193 '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
194 '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
195 '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
196 '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
197 '\u2022' # 0x95 -> BULLET
198 '\u2013' # 0x96 -> EN DASH
199 '\u2014' # 0x97 -> EM DASH
200 '\u02dc' # 0x98 -> SMALL TILDE
201 '\u2122' # 0x99 -> TRADE MARK SIGN
202 '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
203 '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
204 '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
205 '\ufffe' # 0x9D -> UNDEFINED
206 '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
207 '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
208 '\xa0' # 0xA0 -> NO-BREAK SPACE
209 '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
210 '\xa2' # 0xA2 -> CENT SIGN
211 '\xa3' # 0xA3 -> POUND SIGN
212 '\xa4' # 0xA4 -> CURRENCY SIGN
213 '\xa5' # 0xA5 -> YEN SIGN
214 '\xa6' # 0xA6 -> BROKEN BAR
215 '\xa7' # 0xA7 -> SECTION SIGN
216 '\xa8' # 0xA8 -> DIAERESIS
217 '\xa9' # 0xA9 -> COPYRIGHT SIGN
218 '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
219 '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
220 '\xac' # 0xAC -> NOT SIGN
221 '\xad' # 0xAD -> SOFT HYPHEN
222 '\xae' # 0xAE -> REGISTERED SIGN
223 '\xaf' # 0xAF -> MACRON
224 '\xb0' # 0xB0 -> DEGREE SIGN
225 '\xb1' # 0xB1 -> PLUS-MINUS SIGN
226 '\xb2' # 0xB2 -> SUPERSCRIPT TWO
227 '\xb3' # 0xB3 -> SUPERSCRIPT THREE
228 '\xb4' # 0xB4 -> ACUTE ACCENT
229 '\xb5' # 0xB5 -> MICRO SIGN
230 '\xb6' # 0xB6 -> PILCROW SIGN
231 '\xb7' # 0xB7 -> MIDDLE DOT
232 '\xb8' # 0xB8 -> CEDILLA
233 '\xb9' # 0xB9 -> SUPERSCRIPT ONE
234 '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
235 '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
236 '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
237 '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
238 '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
239 '\xbf' # 0xBF -> INVERTED QUESTION MARK
240 '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
241 '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
242 '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
243 '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
244 '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
245 '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
246 '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
247 '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
248 '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
249 '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
250 '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
251 '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
252 '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
253 '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
254 '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
255 '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
256 '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH
257 '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
258 '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
259 '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
260 '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
261 '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
262 '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
263 '\xd7' # 0xD7 -> MULTIPLICATION SIGN
264 '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
265 '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
266 '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
267 '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
268 '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
269 '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
270 '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN
271 '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
272 '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
273 '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
274 '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
275 '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
276 '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
277 '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
278 '\xe6' # 0xE6 -> LATIN SMALL LETTER AE
279 '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
280 '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
281 '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
282 '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
283 '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
284 '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
285 '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
286 '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
287 '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
288 '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH
289 '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
290 '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
291 '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
292 '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
293 '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
294 '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
295 '\xf7' # 0xF7 -> DIVISION SIGN
296 '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
297 '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
298 '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
299 '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
300 '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
301 '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
302 '\xfe' # 0xFE -> LATIN SMALL LETTER THORN
303 '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000304)
305
Thomas Wouters73e5a5b2006-06-08 15:35:45 +0000306### Encoding table
307encoding_table=codecs.charmap_build(decoding_table)