| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # encodings.pm --
|
|---|
| 4 | # A component of the Greenstone digital library software
|
|---|
| 5 | # from the New Zealand Digital Library Project at the
|
|---|
| 6 | # University of Waikato, New Zealand.
|
|---|
| 7 | #
|
|---|
| 8 | # Copyright (C) 2001 New Zealand Digital Library Project
|
|---|
| 9 | #
|
|---|
| 10 | # This program is free software; you can redistribute it and/or modify
|
|---|
| 11 | # it under the terms of the GNU General Public License as published by
|
|---|
| 12 | # the Free Software Foundation; either version 2 of the License, or
|
|---|
| 13 | # (at your option) any later version.
|
|---|
| 14 | #
|
|---|
| 15 | # This program is distributed in the hope that it will be useful,
|
|---|
| 16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 18 | # GNU General Public License for more details.
|
|---|
| 19 | #
|
|---|
| 20 | # You should have received a copy of the GNU General Public License
|
|---|
| 21 | # along with this program; if not, write to the Free Software
|
|---|
| 22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 23 | #
|
|---|
| 24 | ###########################################################################
|
|---|
| 25 |
|
|---|
| 26 | # Each encoding supported by the Greenstone build-time software should be
|
|---|
| 27 | # specified in the following hash table ($encodings).
|
|---|
| 28 |
|
|---|
| 29 | package encodings;
|
|---|
| 30 |
|
|---|
| 31 | # $encodings takes the form:
|
|---|
| 32 | # --> identifier --> name --> The full display name of the encoding.
|
|---|
| 33 | # --> mapfile --> The ump file associated with the encoding
|
|---|
| 34 | # --> double --> 1 if it's a double byte encoding
|
|---|
| 35 | # --> converter --> If the encoding needs a specialized conversion
|
|---|
| 36 | # routine this is the name of that routine.
|
|---|
| 37 |
|
|---|
| 38 | $encodings = {
|
|---|
| 39 | 'iso_8859_1' => {'name' => 'Latin1 (western languages)', 'mapfile' => '8859_1.ump'},
|
|---|
| 40 |
|
|---|
| 41 | 'iso_8859_2' => {'name' => 'Latin2 (central and eastern european languages)',
|
|---|
| 42 | 'mapfile' => '8859_2.ump'},
|
|---|
| 43 |
|
|---|
| 44 | 'iso_8859_3' => {'name' => 'Latin3', 'mapfile' => '8859_3.ump'},
|
|---|
| 45 |
|
|---|
| 46 | 'iso_8859_4' => {'name' => 'Latin4', 'mapfile' => '8859_4.ump'},
|
|---|
| 47 |
|
|---|
| 48 | 'iso_8859_5' => {'name' => 'Cyrillic', 'mapfile' => '8859_5.ump'},
|
|---|
| 49 |
|
|---|
| 50 | 'iso_8859_6' => {'name' => 'Arabic', 'mapfile' => '8859_6.ump'},
|
|---|
| 51 |
|
|---|
| 52 | 'iso_8859_7' => {'name' => 'Greek', 'mapfile' => '8859_7.ump'},
|
|---|
| 53 |
|
|---|
| 54 | 'iso_8859_8' => {'name' => 'Hebrew', 'mapfile' => '8859_8.ump'},
|
|---|
| 55 |
|
|---|
| 56 | 'iso_8859_9' => {'name' => 'Turkish', 'mapfile' => '8859_9.ump'},
|
|---|
| 57 |
|
|---|
| 58 | 'windows_1250' => {'name' => 'Windows codepage 1250 (WinLatin2)',
|
|---|
| 59 | 'mapfile' => 'win1250.ump'},
|
|---|
| 60 |
|
|---|
| 61 | 'windows_1251' => {'name' => 'Windows codepage 1251 (WinCyrillic)',
|
|---|
| 62 | 'mapfile' => 'win1251.ump'},
|
|---|
| 63 |
|
|---|
| 64 | 'windows_1252' => {'name' => 'Windows codepage 1252 (WinLatin1)',
|
|---|
| 65 | 'mapfile' => 'win1252.ump'},
|
|---|
| 66 |
|
|---|
| 67 | 'windows_1253' => {'name' => 'Windows codepage 1253 (WinGreek)',
|
|---|
| 68 | 'mapfile' => 'win1253.ump'},
|
|---|
| 69 |
|
|---|
| 70 | 'windows_1254' => {'name' => 'Windows codepage 1254 (WinTurkish)',
|
|---|
| 71 | 'mapfile' => 'win1254.ump'},
|
|---|
| 72 |
|
|---|
| 73 | 'windows_1255' => {'name' => 'Windows codepage 1255 (WinHebrew)',
|
|---|
| 74 | 'mapfile' => 'win1255.ump'},
|
|---|
| 75 |
|
|---|
| 76 | 'windows_1256' => {'name' => 'Windows codepage 1256 (WinArabic)',
|
|---|
| 77 | 'mapfile' => 'win1256.ump'},
|
|---|
| 78 |
|
|---|
| 79 | 'windows_1257' => {'name' => 'Windows codepage 1257 (WinBaltic)',
|
|---|
| 80 | 'mapfile' => 'win1257.ump'},
|
|---|
| 81 |
|
|---|
| 82 | 'windows_1258' => {'name' => 'Windows codepage 1258 (Vietnamese)',
|
|---|
| 83 | 'mapfile' => 'win1258.ump'},
|
|---|
| 84 |
|
|---|
| 85 | 'windows_874' => {'name' => 'Windows codepage 874 (Thai)', 'mapfile' => 'win874.ump'},
|
|---|
| 86 |
|
|---|
| 87 | 'dos_866' => {'name' => 'DOS codepage 866 (Cyrillic)', 'mapfile' => 'dos866.ump'},
|
|---|
| 88 |
|
|---|
| 89 | 'koi8_r' => {'name' => 'Cyrillic', 'mapfile' => 'koi8_r.ump'},
|
|---|
| 90 |
|
|---|
| 91 | 'koi8_u' => {'name' => 'Cyrillic (Ukrainian)', 'mapfile' => 'koi8_u.ump'},
|
|---|
| 92 |
|
|---|
| 93 | 'iscii_de' => {'name' => 'ISCII Devanagari', 'mapfile' => 'iscii_de.ump'},
|
|---|
| 94 |
|
|---|
| 95 | 'shift_jis' => {'name' => 'Japanese (Shift-JIS)', 'mapfile' => 'shiftjis.ump',
|
|---|
| 96 | 'converter' => 'shiftjis2unicode'},
|
|---|
| 97 |
|
|---|
| 98 | 'euc_jp' => {'name' => 'Japanese (EUC)', 'mapfile' => 'euc_jp.ump'},
|
|---|
| 99 |
|
|---|
| 100 | 'korean' => {'name' => 'Korean (Unified Hangul Code - i.e. a superset of EUC-KR)',
|
|---|
| 101 | 'mapfile' => 'uhc.ump'},
|
|---|
| 102 |
|
|---|
| 103 | 'gb' => {'name' => 'Chinese Simplified (GB)', 'mapfile' => 'gbk.ump'},
|
|---|
| 104 |
|
|---|
| 105 | 'big5' => {'name' => 'Chinese Traditional (Big5)', 'mapfile' => 'big5.ump'}
|
|---|
| 106 |
|
|---|
| 107 | };
|
|---|
