Marc-André Lemburg | a866df8 | 2001-01-03 21:29:14 +0000 | [diff] [blame] | 1 | """ Python Character Mapping Codec generated from 'CP855.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 | 0x0080: 0x0452, # CYRILLIC SMALL LETTER DJE |
| 41 | 0x0081: 0x0402, # CYRILLIC CAPITAL LETTER DJE |
| 42 | 0x0082: 0x0453, # CYRILLIC SMALL LETTER GJE |
| 43 | 0x0083: 0x0403, # CYRILLIC CAPITAL LETTER GJE |
| 44 | 0x0084: 0x0451, # CYRILLIC SMALL LETTER IO |
| 45 | 0x0085: 0x0401, # CYRILLIC CAPITAL LETTER IO |
| 46 | 0x0086: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE |
| 47 | 0x0087: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE |
| 48 | 0x0088: 0x0455, # CYRILLIC SMALL LETTER DZE |
| 49 | 0x0089: 0x0405, # CYRILLIC CAPITAL LETTER DZE |
| 50 | 0x008a: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I |
| 51 | 0x008b: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I |
| 52 | 0x008c: 0x0457, # CYRILLIC SMALL LETTER YI |
| 53 | 0x008d: 0x0407, # CYRILLIC CAPITAL LETTER YI |
| 54 | 0x008e: 0x0458, # CYRILLIC SMALL LETTER JE |
| 55 | 0x008f: 0x0408, # CYRILLIC CAPITAL LETTER JE |
| 56 | 0x0090: 0x0459, # CYRILLIC SMALL LETTER LJE |
| 57 | 0x0091: 0x0409, # CYRILLIC CAPITAL LETTER LJE |
| 58 | 0x0092: 0x045a, # CYRILLIC SMALL LETTER NJE |
| 59 | 0x0093: 0x040a, # CYRILLIC CAPITAL LETTER NJE |
| 60 | 0x0094: 0x045b, # CYRILLIC SMALL LETTER TSHE |
| 61 | 0x0095: 0x040b, # CYRILLIC CAPITAL LETTER TSHE |
| 62 | 0x0096: 0x045c, # CYRILLIC SMALL LETTER KJE |
| 63 | 0x0097: 0x040c, # CYRILLIC CAPITAL LETTER KJE |
| 64 | 0x0098: 0x045e, # CYRILLIC SMALL LETTER SHORT U |
| 65 | 0x0099: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U |
| 66 | 0x009a: 0x045f, # CYRILLIC SMALL LETTER DZHE |
| 67 | 0x009b: 0x040f, # CYRILLIC CAPITAL LETTER DZHE |
| 68 | 0x009c: 0x044e, # CYRILLIC SMALL LETTER YU |
| 69 | 0x009d: 0x042e, # CYRILLIC CAPITAL LETTER YU |
| 70 | 0x009e: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN |
| 71 | 0x009f: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN |
| 72 | 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A |
| 73 | 0x00a1: 0x0410, # CYRILLIC CAPITAL LETTER A |
| 74 | 0x00a2: 0x0431, # CYRILLIC SMALL LETTER BE |
| 75 | 0x00a3: 0x0411, # CYRILLIC CAPITAL LETTER BE |
| 76 | 0x00a4: 0x0446, # CYRILLIC SMALL LETTER TSE |
| 77 | 0x00a5: 0x0426, # CYRILLIC CAPITAL LETTER TSE |
| 78 | 0x00a6: 0x0434, # CYRILLIC SMALL LETTER DE |
| 79 | 0x00a7: 0x0414, # CYRILLIC CAPITAL LETTER DE |
| 80 | 0x00a8: 0x0435, # CYRILLIC SMALL LETTER IE |
| 81 | 0x00a9: 0x0415, # CYRILLIC CAPITAL LETTER IE |
| 82 | 0x00aa: 0x0444, # CYRILLIC SMALL LETTER EF |
| 83 | 0x00ab: 0x0424, # CYRILLIC CAPITAL LETTER EF |
| 84 | 0x00ac: 0x0433, # CYRILLIC SMALL LETTER GHE |
| 85 | 0x00ad: 0x0413, # CYRILLIC CAPITAL LETTER GHE |
| 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: 0x0445, # CYRILLIC SMALL LETTER HA |
| 94 | 0x00b6: 0x0425, # CYRILLIC CAPITAL LETTER HA |
| 95 | 0x00b7: 0x0438, # CYRILLIC SMALL LETTER I |
| 96 | 0x00b8: 0x0418, # CYRILLIC CAPITAL LETTER I |
| 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: 0x0439, # CYRILLIC SMALL LETTER SHORT I |
| 102 | 0x00be: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I |
| 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: 0x043a, # CYRILLIC SMALL LETTER KA |
| 111 | 0x00c7: 0x041a, # CYRILLIC CAPITAL LETTER KA |
| 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: 0x043b, # CYRILLIC SMALL LETTER EL |
| 121 | 0x00d1: 0x041b, # CYRILLIC CAPITAL LETTER EL |
| 122 | 0x00d2: 0x043c, # CYRILLIC SMALL LETTER EM |
| 123 | 0x00d3: 0x041c, # CYRILLIC CAPITAL LETTER EM |
| 124 | 0x00d4: 0x043d, # CYRILLIC SMALL LETTER EN |
| 125 | 0x00d5: 0x041d, # CYRILLIC CAPITAL LETTER EN |
| 126 | 0x00d6: 0x043e, # CYRILLIC SMALL LETTER O |
| 127 | 0x00d7: 0x041e, # CYRILLIC CAPITAL LETTER O |
| 128 | 0x00d8: 0x043f, # CYRILLIC SMALL LETTER PE |
| 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: 0x041f, # CYRILLIC CAPITAL LETTER PE |
| 134 | 0x00de: 0x044f, # CYRILLIC SMALL LETTER YA |
| 135 | 0x00df: 0x2580, # UPPER HALF BLOCK |
| 136 | 0x00e0: 0x042f, # CYRILLIC CAPITAL LETTER YA |
| 137 | 0x00e1: 0x0440, # CYRILLIC SMALL LETTER ER |
| 138 | 0x00e2: 0x0420, # CYRILLIC CAPITAL LETTER ER |
| 139 | 0x00e3: 0x0441, # CYRILLIC SMALL LETTER ES |
| 140 | 0x00e4: 0x0421, # CYRILLIC CAPITAL LETTER ES |
| 141 | 0x00e5: 0x0442, # CYRILLIC SMALL LETTER TE |
| 142 | 0x00e6: 0x0422, # CYRILLIC CAPITAL LETTER TE |
| 143 | 0x00e7: 0x0443, # CYRILLIC SMALL LETTER U |
| 144 | 0x00e8: 0x0423, # CYRILLIC CAPITAL LETTER U |
| 145 | 0x00e9: 0x0436, # CYRILLIC SMALL LETTER ZHE |
| 146 | 0x00ea: 0x0416, # CYRILLIC CAPITAL LETTER ZHE |
| 147 | 0x00eb: 0x0432, # CYRILLIC SMALL LETTER VE |
| 148 | 0x00ec: 0x0412, # CYRILLIC CAPITAL LETTER VE |
| 149 | 0x00ed: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN |
| 150 | 0x00ee: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN |
| 151 | 0x00ef: 0x2116, # NUMERO SIGN |
| 152 | 0x00f0: 0x00ad, # SOFT HYPHEN |
| 153 | 0x00f1: 0x044b, # CYRILLIC SMALL LETTER YERU |
| 154 | 0x00f2: 0x042b, # CYRILLIC CAPITAL LETTER YERU |
| 155 | 0x00f3: 0x0437, # CYRILLIC SMALL LETTER ZE |
| 156 | 0x00f4: 0x0417, # CYRILLIC CAPITAL LETTER ZE |
| 157 | 0x00f5: 0x0448, # CYRILLIC SMALL LETTER SHA |
| 158 | 0x00f6: 0x0428, # CYRILLIC CAPITAL LETTER SHA |
| 159 | 0x00f7: 0x044d, # CYRILLIC SMALL LETTER E |
| 160 | 0x00f8: 0x042d, # CYRILLIC CAPITAL LETTER E |
| 161 | 0x00f9: 0x0449, # CYRILLIC SMALL LETTER SHCHA |
| 162 | 0x00fa: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA |
| 163 | 0x00fb: 0x0447, # CYRILLIC SMALL LETTER CHE |
| 164 | 0x00fc: 0x0427, # CYRILLIC CAPITAL LETTER CHE |
| 165 | 0x00fd: 0x00a7, # SECTION SIGN |
| 166 | 0x00fe: 0x25a0, # BLACK SQUARE |
| 167 | 0x00ff: 0x00a0, # NO-BREAK SPACE |
Marc-André Lemburg | a866df8 | 2001-01-03 21:29:14 +0000 | [diff] [blame] | 168 | }) |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 169 | |
| 170 | ### Encoding Map |
| 171 | |
| 172 | encoding_map = {} |
| 173 | for k,v in decoding_map.items(): |
| 174 | encoding_map[v] = k |