Marc-André Lemburg | a866df8 | 2001-01-03 21:29:14 +0000 | [diff] [blame] | 1 | """ Python Character Mapping Codec generated from 'CP500.TXT' with gencodec.py. |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 2 | |
| 3 | Written by Marc-Andre Lemburg (mal@lemburg.com). |
| 4 | |
| 5 | (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. |
Marc-André Lemburg | a866df8 | 2001-01-03 21:29:14 +0000 | [diff] [blame] | 6 | (c) Copyright 2000 Guido van Rossum. |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 7 | |
| 8 | """#" |
| 9 | |
| 10 | import codecs |
| 11 | |
| 12 | ### Codec APIs |
| 13 | |
| 14 | class 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 | |
| 24 | class StreamWriter(Codec,codecs.StreamWriter): |
| 25 | pass |
| 26 | |
| 27 | class StreamReader(Codec,codecs.StreamReader): |
| 28 | pass |
| 29 | |
| 30 | ### encodings module API |
| 31 | |
| 32 | def getregentry(): |
| 33 | |
| 34 | return (Codec().encode,Codec().decode,StreamReader,StreamWriter) |
| 35 | |
| 36 | ### Decoding Map |
| 37 | |
Marc-André Lemburg | a866df8 | 2001-01-03 21:29:14 +0000 | [diff] [blame] | 38 | decoding_map = codecs.make_identity_dict(range(256)) |
| 39 | decoding_map.update({ |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 40 | 0x0004: 0x009c, # CONTROL |
| 41 | 0x0005: 0x0009, # HORIZONTAL TABULATION |
| 42 | 0x0006: 0x0086, # CONTROL |
| 43 | 0x0007: 0x007f, # DELETE |
| 44 | 0x0008: 0x0097, # CONTROL |
| 45 | 0x0009: 0x008d, # CONTROL |
| 46 | 0x000a: 0x008e, # CONTROL |
| 47 | 0x0014: 0x009d, # CONTROL |
| 48 | 0x0015: 0x0085, # CONTROL |
| 49 | 0x0016: 0x0008, # BACKSPACE |
| 50 | 0x0017: 0x0087, # CONTROL |
| 51 | 0x001a: 0x0092, # CONTROL |
| 52 | 0x001b: 0x008f, # CONTROL |
| 53 | 0x0020: 0x0080, # CONTROL |
| 54 | 0x0021: 0x0081, # CONTROL |
| 55 | 0x0022: 0x0082, # CONTROL |
| 56 | 0x0023: 0x0083, # CONTROL |
| 57 | 0x0024: 0x0084, # CONTROL |
| 58 | 0x0025: 0x000a, # LINE FEED |
| 59 | 0x0026: 0x0017, # END OF TRANSMISSION BLOCK |
| 60 | 0x0027: 0x001b, # ESCAPE |
| 61 | 0x0028: 0x0088, # CONTROL |
| 62 | 0x0029: 0x0089, # CONTROL |
| 63 | 0x002a: 0x008a, # CONTROL |
| 64 | 0x002b: 0x008b, # CONTROL |
| 65 | 0x002c: 0x008c, # CONTROL |
| 66 | 0x002d: 0x0005, # ENQUIRY |
| 67 | 0x002e: 0x0006, # ACKNOWLEDGE |
| 68 | 0x002f: 0x0007, # BELL |
| 69 | 0x0030: 0x0090, # CONTROL |
| 70 | 0x0031: 0x0091, # CONTROL |
| 71 | 0x0032: 0x0016, # SYNCHRONOUS IDLE |
| 72 | 0x0033: 0x0093, # CONTROL |
| 73 | 0x0034: 0x0094, # CONTROL |
| 74 | 0x0035: 0x0095, # CONTROL |
| 75 | 0x0036: 0x0096, # CONTROL |
| 76 | 0x0037: 0x0004, # END OF TRANSMISSION |
| 77 | 0x0038: 0x0098, # CONTROL |
| 78 | 0x0039: 0x0099, # CONTROL |
| 79 | 0x003a: 0x009a, # CONTROL |
| 80 | 0x003b: 0x009b, # CONTROL |
| 81 | 0x003c: 0x0014, # DEVICE CONTROL FOUR |
| 82 | 0x003d: 0x0015, # NEGATIVE ACKNOWLEDGE |
| 83 | 0x003e: 0x009e, # CONTROL |
| 84 | 0x003f: 0x001a, # SUBSTITUTE |
| 85 | 0x0040: 0x0020, # SPACE |
| 86 | 0x0041: 0x00a0, # NO-BREAK SPACE |
| 87 | 0x0042: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX |
| 88 | 0x0043: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS |
| 89 | 0x0044: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE |
| 90 | 0x0045: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE |
| 91 | 0x0046: 0x00e3, # LATIN SMALL LETTER A WITH TILDE |
| 92 | 0x0047: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE |
| 93 | 0x0048: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA |
| 94 | 0x0049: 0x00f1, # LATIN SMALL LETTER N WITH TILDE |
| 95 | 0x004a: 0x005b, # LEFT SQUARE BRACKET |
| 96 | 0x004b: 0x002e, # FULL STOP |
| 97 | 0x004c: 0x003c, # LESS-THAN SIGN |
| 98 | 0x004d: 0x0028, # LEFT PARENTHESIS |
| 99 | 0x004e: 0x002b, # PLUS SIGN |
| 100 | 0x004f: 0x0021, # EXCLAMATION MARK |
| 101 | 0x0050: 0x0026, # AMPERSAND |
| 102 | 0x0051: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE |
| 103 | 0x0052: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX |
| 104 | 0x0053: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS |
| 105 | 0x0054: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE |
| 106 | 0x0055: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE |
| 107 | 0x0056: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX |
| 108 | 0x0057: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS |
| 109 | 0x0058: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE |
| 110 | 0x0059: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN) |
| 111 | 0x005a: 0x005d, # RIGHT SQUARE BRACKET |
| 112 | 0x005b: 0x0024, # DOLLAR SIGN |
| 113 | 0x005c: 0x002a, # ASTERISK |
| 114 | 0x005d: 0x0029, # RIGHT PARENTHESIS |
| 115 | 0x005e: 0x003b, # SEMICOLON |
| 116 | 0x005f: 0x005e, # CIRCUMFLEX ACCENT |
| 117 | 0x0060: 0x002d, # HYPHEN-MINUS |
| 118 | 0x0061: 0x002f, # SOLIDUS |
| 119 | 0x0062: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX |
| 120 | 0x0063: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS |
| 121 | 0x0064: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE |
| 122 | 0x0065: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE |
| 123 | 0x0066: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE |
| 124 | 0x0067: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE |
| 125 | 0x0068: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA |
| 126 | 0x0069: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE |
| 127 | 0x006a: 0x00a6, # BROKEN BAR |
| 128 | 0x006b: 0x002c, # COMMA |
| 129 | 0x006c: 0x0025, # PERCENT SIGN |
| 130 | 0x006d: 0x005f, # LOW LINE |
| 131 | 0x006e: 0x003e, # GREATER-THAN SIGN |
| 132 | 0x006f: 0x003f, # QUESTION MARK |
| 133 | 0x0070: 0x00f8, # LATIN SMALL LETTER O WITH STROKE |
| 134 | 0x0071: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE |
| 135 | 0x0072: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX |
| 136 | 0x0073: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS |
| 137 | 0x0074: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE |
| 138 | 0x0075: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE |
| 139 | 0x0076: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX |
| 140 | 0x0077: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS |
| 141 | 0x0078: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE |
| 142 | 0x0079: 0x0060, # GRAVE ACCENT |
| 143 | 0x007a: 0x003a, # COLON |
| 144 | 0x007b: 0x0023, # NUMBER SIGN |
| 145 | 0x007c: 0x0040, # COMMERCIAL AT |
| 146 | 0x007d: 0x0027, # APOSTROPHE |
| 147 | 0x007e: 0x003d, # EQUALS SIGN |
| 148 | 0x007f: 0x0022, # QUOTATION MARK |
| 149 | 0x0080: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE |
| 150 | 0x0081: 0x0061, # LATIN SMALL LETTER A |
| 151 | 0x0082: 0x0062, # LATIN SMALL LETTER B |
| 152 | 0x0083: 0x0063, # LATIN SMALL LETTER C |
| 153 | 0x0084: 0x0064, # LATIN SMALL LETTER D |
| 154 | 0x0085: 0x0065, # LATIN SMALL LETTER E |
| 155 | 0x0086: 0x0066, # LATIN SMALL LETTER F |
| 156 | 0x0087: 0x0067, # LATIN SMALL LETTER G |
| 157 | 0x0088: 0x0068, # LATIN SMALL LETTER H |
| 158 | 0x0089: 0x0069, # LATIN SMALL LETTER I |
| 159 | 0x008a: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK |
| 160 | 0x008b: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK |
| 161 | 0x008c: 0x00f0, # LATIN SMALL LETTER ETH (ICELANDIC) |
| 162 | 0x008d: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE |
| 163 | 0x008e: 0x00fe, # LATIN SMALL LETTER THORN (ICELANDIC) |
| 164 | 0x008f: 0x00b1, # PLUS-MINUS SIGN |
| 165 | 0x0090: 0x00b0, # DEGREE SIGN |
| 166 | 0x0091: 0x006a, # LATIN SMALL LETTER J |
| 167 | 0x0092: 0x006b, # LATIN SMALL LETTER K |
| 168 | 0x0093: 0x006c, # LATIN SMALL LETTER L |
| 169 | 0x0094: 0x006d, # LATIN SMALL LETTER M |
| 170 | 0x0095: 0x006e, # LATIN SMALL LETTER N |
| 171 | 0x0096: 0x006f, # LATIN SMALL LETTER O |
| 172 | 0x0097: 0x0070, # LATIN SMALL LETTER P |
| 173 | 0x0098: 0x0071, # LATIN SMALL LETTER Q |
| 174 | 0x0099: 0x0072, # LATIN SMALL LETTER R |
| 175 | 0x009a: 0x00aa, # FEMININE ORDINAL INDICATOR |
| 176 | 0x009b: 0x00ba, # MASCULINE ORDINAL INDICATOR |
| 177 | 0x009c: 0x00e6, # LATIN SMALL LIGATURE AE |
| 178 | 0x009d: 0x00b8, # CEDILLA |
| 179 | 0x009e: 0x00c6, # LATIN CAPITAL LIGATURE AE |
| 180 | 0x009f: 0x00a4, # CURRENCY SIGN |
| 181 | 0x00a0: 0x00b5, # MICRO SIGN |
| 182 | 0x00a1: 0x007e, # TILDE |
| 183 | 0x00a2: 0x0073, # LATIN SMALL LETTER S |
| 184 | 0x00a3: 0x0074, # LATIN SMALL LETTER T |
| 185 | 0x00a4: 0x0075, # LATIN SMALL LETTER U |
| 186 | 0x00a5: 0x0076, # LATIN SMALL LETTER V |
| 187 | 0x00a6: 0x0077, # LATIN SMALL LETTER W |
| 188 | 0x00a7: 0x0078, # LATIN SMALL LETTER X |
| 189 | 0x00a8: 0x0079, # LATIN SMALL LETTER Y |
| 190 | 0x00a9: 0x007a, # LATIN SMALL LETTER Z |
| 191 | 0x00aa: 0x00a1, # INVERTED EXCLAMATION MARK |
| 192 | 0x00ab: 0x00bf, # INVERTED QUESTION MARK |
| 193 | 0x00ac: 0x00d0, # LATIN CAPITAL LETTER ETH (ICELANDIC) |
| 194 | 0x00ad: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE |
| 195 | 0x00ae: 0x00de, # LATIN CAPITAL LETTER THORN (ICELANDIC) |
| 196 | 0x00af: 0x00ae, # REGISTERED SIGN |
| 197 | 0x00b0: 0x00a2, # CENT SIGN |
| 198 | 0x00b1: 0x00a3, # POUND SIGN |
| 199 | 0x00b2: 0x00a5, # YEN SIGN |
| 200 | 0x00b3: 0x00b7, # MIDDLE DOT |
| 201 | 0x00b4: 0x00a9, # COPYRIGHT SIGN |
| 202 | 0x00b5: 0x00a7, # SECTION SIGN |
| 203 | 0x00b7: 0x00bc, # VULGAR FRACTION ONE QUARTER |
| 204 | 0x00b8: 0x00bd, # VULGAR FRACTION ONE HALF |
| 205 | 0x00b9: 0x00be, # VULGAR FRACTION THREE QUARTERS |
| 206 | 0x00ba: 0x00ac, # NOT SIGN |
| 207 | 0x00bb: 0x007c, # VERTICAL LINE |
| 208 | 0x00bc: 0x00af, # MACRON |
| 209 | 0x00bd: 0x00a8, # DIAERESIS |
| 210 | 0x00be: 0x00b4, # ACUTE ACCENT |
| 211 | 0x00bf: 0x00d7, # MULTIPLICATION SIGN |
| 212 | 0x00c0: 0x007b, # LEFT CURLY BRACKET |
| 213 | 0x00c1: 0x0041, # LATIN CAPITAL LETTER A |
| 214 | 0x00c2: 0x0042, # LATIN CAPITAL LETTER B |
| 215 | 0x00c3: 0x0043, # LATIN CAPITAL LETTER C |
| 216 | 0x00c4: 0x0044, # LATIN CAPITAL LETTER D |
| 217 | 0x00c5: 0x0045, # LATIN CAPITAL LETTER E |
| 218 | 0x00c6: 0x0046, # LATIN CAPITAL LETTER F |
| 219 | 0x00c7: 0x0047, # LATIN CAPITAL LETTER G |
| 220 | 0x00c8: 0x0048, # LATIN CAPITAL LETTER H |
| 221 | 0x00c9: 0x0049, # LATIN CAPITAL LETTER I |
| 222 | 0x00ca: 0x00ad, # SOFT HYPHEN |
| 223 | 0x00cb: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX |
| 224 | 0x00cc: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS |
| 225 | 0x00cd: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE |
| 226 | 0x00ce: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE |
| 227 | 0x00cf: 0x00f5, # LATIN SMALL LETTER O WITH TILDE |
| 228 | 0x00d0: 0x007d, # RIGHT CURLY BRACKET |
| 229 | 0x00d1: 0x004a, # LATIN CAPITAL LETTER J |
| 230 | 0x00d2: 0x004b, # LATIN CAPITAL LETTER K |
| 231 | 0x00d3: 0x004c, # LATIN CAPITAL LETTER L |
| 232 | 0x00d4: 0x004d, # LATIN CAPITAL LETTER M |
| 233 | 0x00d5: 0x004e, # LATIN CAPITAL LETTER N |
| 234 | 0x00d6: 0x004f, # LATIN CAPITAL LETTER O |
| 235 | 0x00d7: 0x0050, # LATIN CAPITAL LETTER P |
| 236 | 0x00d8: 0x0051, # LATIN CAPITAL LETTER Q |
| 237 | 0x00d9: 0x0052, # LATIN CAPITAL LETTER R |
| 238 | 0x00da: 0x00b9, # SUPERSCRIPT ONE |
| 239 | 0x00db: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX |
| 240 | 0x00dc: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS |
| 241 | 0x00dd: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE |
| 242 | 0x00de: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE |
| 243 | 0x00df: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS |
| 244 | 0x00e0: 0x005c, # REVERSE SOLIDUS |
| 245 | 0x00e1: 0x00f7, # DIVISION SIGN |
| 246 | 0x00e2: 0x0053, # LATIN CAPITAL LETTER S |
| 247 | 0x00e3: 0x0054, # LATIN CAPITAL LETTER T |
| 248 | 0x00e4: 0x0055, # LATIN CAPITAL LETTER U |
| 249 | 0x00e5: 0x0056, # LATIN CAPITAL LETTER V |
| 250 | 0x00e6: 0x0057, # LATIN CAPITAL LETTER W |
| 251 | 0x00e7: 0x0058, # LATIN CAPITAL LETTER X |
| 252 | 0x00e8: 0x0059, # LATIN CAPITAL LETTER Y |
| 253 | 0x00e9: 0x005a, # LATIN CAPITAL LETTER Z |
| 254 | 0x00ea: 0x00b2, # SUPERSCRIPT TWO |
| 255 | 0x00eb: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX |
| 256 | 0x00ec: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS |
| 257 | 0x00ed: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE |
| 258 | 0x00ee: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE |
| 259 | 0x00ef: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE |
| 260 | 0x00f0: 0x0030, # DIGIT ZERO |
| 261 | 0x00f1: 0x0031, # DIGIT ONE |
| 262 | 0x00f2: 0x0032, # DIGIT TWO |
| 263 | 0x00f3: 0x0033, # DIGIT THREE |
| 264 | 0x00f4: 0x0034, # DIGIT FOUR |
| 265 | 0x00f5: 0x0035, # DIGIT FIVE |
| 266 | 0x00f6: 0x0036, # DIGIT SIX |
| 267 | 0x00f7: 0x0037, # DIGIT SEVEN |
| 268 | 0x00f8: 0x0038, # DIGIT EIGHT |
| 269 | 0x00f9: 0x0039, # DIGIT NINE |
| 270 | 0x00fa: 0x00b3, # SUPERSCRIPT THREE |
| 271 | 0x00fb: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX |
| 272 | 0x00fc: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS |
| 273 | 0x00fd: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE |
| 274 | 0x00fe: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE |
| 275 | 0x00ff: 0x009f, # CONTROL |
Marc-André Lemburg | a866df8 | 2001-01-03 21:29:14 +0000 | [diff] [blame] | 276 | }) |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 277 | |
| 278 | ### Encoding Map |
| 279 | |
Marc-André Lemburg | 716cf91 | 2001-05-16 09:41:45 +0000 | [diff] [blame] | 280 | encoding_map = codecs.make_encoding_map(decoding_map) |