Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 1 | """ Python Character Mapping Codec generated from '8859-3.TXT'. |
| 2 | |
| 3 | |
| 4 | Written by Marc-Andre Lemburg (mal@lemburg.com). |
| 5 | |
| 6 | (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. |
| 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 | |
| 38 | decoding_map = { |
| 39 | |
| 40 | 0x00a1: 0x0126, # LATIN CAPITAL LETTER H WITH STROKE |
| 41 | 0x00a2: 0x02d8, # BREVE |
| 42 | 0x00a6: 0x0124, # LATIN CAPITAL LETTER H WITH CIRCUMFLEX |
| 43 | 0x00a9: 0x0130, # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 44 | 0x00aa: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA |
| 45 | 0x00ab: 0x011e, # LATIN CAPITAL LETTER G WITH BREVE |
| 46 | 0x00ac: 0x0134, # LATIN CAPITAL LETTER J WITH CIRCUMFLEX |
| 47 | 0x00af: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE |
| 48 | 0x00b1: 0x0127, # LATIN SMALL LETTER H WITH STROKE |
| 49 | 0x00b6: 0x0125, # LATIN SMALL LETTER H WITH CIRCUMFLEX |
| 50 | 0x00b9: 0x0131, # LATIN SMALL LETTER DOTLESS I |
| 51 | 0x00ba: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA |
| 52 | 0x00bb: 0x011f, # LATIN SMALL LETTER G WITH BREVE |
| 53 | 0x00bc: 0x0135, # LATIN SMALL LETTER J WITH CIRCUMFLEX |
| 54 | 0x00bf: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE |
| 55 | 0x00c5: 0x010a, # LATIN CAPITAL LETTER C WITH DOT ABOVE |
| 56 | 0x00c6: 0x0108, # LATIN CAPITAL LETTER C WITH CIRCUMFLEX |
| 57 | 0x00d5: 0x0120, # LATIN CAPITAL LETTER G WITH DOT ABOVE |
| 58 | 0x00d8: 0x011c, # LATIN CAPITAL LETTER G WITH CIRCUMFLEX |
| 59 | 0x00dd: 0x016c, # LATIN CAPITAL LETTER U WITH BREVE |
| 60 | 0x00de: 0x015c, # LATIN CAPITAL LETTER S WITH CIRCUMFLEX |
| 61 | 0x00e5: 0x010b, # LATIN SMALL LETTER C WITH DOT ABOVE |
| 62 | 0x00e6: 0x0109, # LATIN SMALL LETTER C WITH CIRCUMFLEX |
| 63 | 0x00f5: 0x0121, # LATIN SMALL LETTER G WITH DOT ABOVE |
| 64 | 0x00f8: 0x011d, # LATIN SMALL LETTER G WITH CIRCUMFLEX |
| 65 | 0x00fd: 0x016d, # LATIN SMALL LETTER U WITH BREVE |
| 66 | 0x00fe: 0x015d, # LATIN SMALL LETTER S WITH CIRCUMFLEX |
| 67 | 0x00ff: 0x02d9, # DOT ABOVE |
| 68 | } |
| 69 | |
| 70 | ### Encoding Map |
| 71 | |
| 72 | encoding_map = {} |
| 73 | for k,v in decoding_map.items(): |
| 74 | encoding_map[v] = k |