Marc-André Lemburg | 17b6d28 | 2004-07-28 15:37:54 +0000 | [diff] [blame] | 1 | """ Python Character Mapping Codec generated from 'hp_roman8.txt' with gencodec.py. |
| 2 | |
| 3 | Based on data from ftp://dkuug.dk/i18n/charmaps/HP-ROMAN8 (Keld Simonsen) |
| 4 | |
| 5 | Original source: LaserJet IIP Printer User's Manual HP part no |
| 6 | 33471-90901, Hewlet-Packard, June 1989. |
| 7 | |
| 8 | """#" |
| 9 | |
| 10 | import codecs |
| 11 | |
| 12 | ### Codec APIs |
| 13 | |
| 14 | class Codec(codecs.Codec): |
| 15 | |
| 16 | def encode(self,input,errors='strict'): |
Marc-André Lemburg | 17b6d28 | 2004-07-28 15:37:54 +0000 | [diff] [blame] | 17 | return codecs.charmap_encode(input,errors,encoding_map) |
| 18 | |
| 19 | def decode(self,input,errors='strict'): |
Marc-André Lemburg | 17b6d28 | 2004-07-28 15:37:54 +0000 | [diff] [blame] | 20 | return codecs.charmap_decode(input,errors,decoding_map) |
| 21 | |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 22 | class IncrementalEncoder(codecs.IncrementalEncoder): |
| 23 | def encode(self, input, final=False): |
| 24 | return codecs.charmap_encode(input,self.errors,encoding_map)[0] |
| 25 | |
| 26 | class IncrementalDecoder(codecs.IncrementalDecoder): |
| 27 | def decode(self, input, final=False): |
| 28 | return codecs.charmap_decode(input,self.errors,decoding_map)[0] |
| 29 | |
Marc-André Lemburg | 17b6d28 | 2004-07-28 15:37:54 +0000 | [diff] [blame] | 30 | class StreamWriter(Codec,codecs.StreamWriter): |
| 31 | pass |
| 32 | |
| 33 | class StreamReader(Codec,codecs.StreamReader): |
| 34 | pass |
| 35 | |
| 36 | ### encodings module API |
| 37 | |
| 38 | def getregentry(): |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 39 | return codecs.CodecInfo( |
| 40 | name='hp-roman8', |
| 41 | encode=Codec().encode, |
| 42 | decode=Codec().decode, |
| 43 | incrementalencoder=IncrementalEncoder, |
| 44 | incrementaldecoder=IncrementalDecoder, |
| 45 | streamwriter=StreamWriter, |
| 46 | streamreader=StreamReader, |
| 47 | ) |
Marc-André Lemburg | 17b6d28 | 2004-07-28 15:37:54 +0000 | [diff] [blame] | 48 | |
| 49 | ### Decoding Map |
| 50 | |
| 51 | decoding_map = codecs.make_identity_dict(range(256)) |
| 52 | decoding_map.update({ |
Tim Peters | c0cbc86 | 2004-07-31 21:17:37 +0000 | [diff] [blame] | 53 | 0x00a1: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE |
| 54 | 0x00a2: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX |
| 55 | 0x00a3: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE |
| 56 | 0x00a4: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX |
| 57 | 0x00a5: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS |
| 58 | 0x00a6: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX |
| 59 | 0x00a7: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS |
| 60 | 0x00a8: 0x00b4, # ACUTE ACCENT |
| 61 | 0x00a9: 0x02cb, # MODIFIER LETTER GRAVE ACCENT (Mandarin Chinese fourth tone) |
| 62 | 0x00aa: 0x02c6, # MODIFIER LETTER CIRCUMFLEX ACCENT |
| 63 | 0x00ab: 0x00a8, # DIAERESIS |
| 64 | 0x00ac: 0x02dc, # SMALL TILDE |
| 65 | 0x00ad: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE |
| 66 | 0x00ae: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX |
| 67 | 0x00af: 0x20a4, # LIRA SIGN |
| 68 | 0x00b0: 0x00af, # MACRON |
| 69 | 0x00b1: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE |
| 70 | 0x00b2: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE |
| 71 | 0x00b3: 0x00b0, # DEGREE SIGN |
| 72 | 0x00b4: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA |
| 73 | 0x00b5: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA |
| 74 | 0x00b6: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE |
| 75 | 0x00b7: 0x00f1, # LATIN SMALL LETTER N WITH TILDE |
| 76 | 0x00b8: 0x00a1, # INVERTED EXCLAMATION MARK |
| 77 | 0x00b9: 0x00bf, # INVERTED QUESTION MARK |
| 78 | 0x00ba: 0x00a4, # CURRENCY SIGN |
| 79 | 0x00bb: 0x00a3, # POUND SIGN |
| 80 | 0x00bc: 0x00a5, # YEN SIGN |
| 81 | 0x00bd: 0x00a7, # SECTION SIGN |
| 82 | 0x00be: 0x0192, # LATIN SMALL LETTER F WITH HOOK |
| 83 | 0x00bf: 0x00a2, # CENT SIGN |
| 84 | 0x00c0: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX |
| 85 | 0x00c1: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX |
| 86 | 0x00c2: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX |
| 87 | 0x00c3: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX |
| 88 | 0x00c4: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE |
| 89 | 0x00c5: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE |
| 90 | 0x00c6: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE |
| 91 | 0x00c7: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE |
| 92 | 0x00c8: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE |
| 93 | 0x00c9: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE |
| 94 | 0x00ca: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE |
| 95 | 0x00cb: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE |
| 96 | 0x00cc: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS |
| 97 | 0x00cd: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS |
| 98 | 0x00ce: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS |
| 99 | 0x00cf: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS |
| 100 | 0x00d0: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE |
| 101 | 0x00d1: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX |
| 102 | 0x00d2: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE |
| 103 | 0x00d3: 0x00c6, # LATIN CAPITAL LETTER AE |
| 104 | 0x00d4: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE |
| 105 | 0x00d5: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE |
| 106 | 0x00d6: 0x00f8, # LATIN SMALL LETTER O WITH STROKE |
| 107 | 0x00d7: 0x00e6, # LATIN SMALL LETTER AE |
| 108 | 0x00d8: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS |
| 109 | 0x00d9: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE |
| 110 | 0x00da: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS |
| 111 | 0x00db: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS |
| 112 | 0x00dc: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE |
| 113 | 0x00dd: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS |
| 114 | 0x00de: 0x00df, # LATIN SMALL LETTER SHARP S (German) |
| 115 | 0x00df: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX |
| 116 | 0x00e0: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE |
| 117 | 0x00e1: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE |
| 118 | 0x00e2: 0x00e3, # LATIN SMALL LETTER A WITH TILDE |
| 119 | 0x00e3: 0x00d0, # LATIN CAPITAL LETTER ETH (Icelandic) |
| 120 | 0x00e4: 0x00f0, # LATIN SMALL LETTER ETH (Icelandic) |
| 121 | 0x00e5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE |
| 122 | 0x00e6: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE |
| 123 | 0x00e7: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE |
| 124 | 0x00e8: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE |
| 125 | 0x00e9: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE |
| 126 | 0x00ea: 0x00f5, # LATIN SMALL LETTER O WITH TILDE |
| 127 | 0x00eb: 0x0160, # LATIN CAPITAL LETTER S WITH CARON |
| 128 | 0x00ec: 0x0161, # LATIN SMALL LETTER S WITH CARON |
| 129 | 0x00ed: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE |
| 130 | 0x00ee: 0x0178, # LATIN CAPITAL LETTER Y WITH DIAERESIS |
| 131 | 0x00ef: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS |
| 132 | 0x00f0: 0x00de, # LATIN CAPITAL LETTER THORN (Icelandic) |
| 133 | 0x00f1: 0x00fe, # LATIN SMALL LETTER THORN (Icelandic) |
| 134 | 0x00f2: 0x00b7, # MIDDLE DOT |
| 135 | 0x00f3: 0x00b5, # MICRO SIGN |
| 136 | 0x00f4: 0x00b6, # PILCROW SIGN |
| 137 | 0x00f5: 0x00be, # VULGAR FRACTION THREE QUARTERS |
| 138 | 0x00f6: 0x2014, # EM DASH |
| 139 | 0x00f7: 0x00bc, # VULGAR FRACTION ONE QUARTER |
| 140 | 0x00f8: 0x00bd, # VULGAR FRACTION ONE HALF |
| 141 | 0x00f9: 0x00aa, # FEMININE ORDINAL INDICATOR |
| 142 | 0x00fa: 0x00ba, # MASCULINE ORDINAL INDICATOR |
| 143 | 0x00fb: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK |
| 144 | 0x00fc: 0x25a0, # BLACK SQUARE |
| 145 | 0x00fd: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK |
| 146 | 0x00fe: 0x00b1, # PLUS-MINUS SIGN |
| 147 | 0x00ff: None, |
Marc-André Lemburg | 17b6d28 | 2004-07-28 15:37:54 +0000 | [diff] [blame] | 148 | }) |
| 149 | |
| 150 | ### Encoding Map |
| 151 | |
| 152 | encoding_map = codecs.make_encoding_map(decoding_map) |