DRC | 2ff39b8 | 2011-07-28 08:38:59 +0000 | [diff] [blame^] | 1 | // |
| 2 | // "$Id: fl_encoding_latin1.cxx 7903 2010-11-28 21:06:39Z matt $" |
| 3 | // |
| 4 | // Convert MSWindows-1252 (Latin-1) encoded text to the local encoding. |
| 5 | // |
| 6 | // Copyright 1998-2010 by Bill Spitzak and others. |
| 7 | // |
| 8 | // This library is free software; you can redistribute it and/or |
| 9 | // modify it under the terms of the GNU Library General Public |
| 10 | // License as published by the Free Software Foundation; either |
| 11 | // version 2 of the License, or (at your option) any later version. |
| 12 | // |
| 13 | // This library is distributed in the hope that it will be useful, |
| 14 | // but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 15 | // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 16 | // Library General Public License for more details. |
| 17 | // |
| 18 | // You should have received a copy of the GNU Library General Public |
| 19 | // License along with this library; if not, write to the Free Software |
| 20 | // Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 |
| 21 | // USA. |
| 22 | // |
| 23 | // Please report all bugs and problems on the following page: |
| 24 | // |
| 25 | // http://www.fltk.org/str.php |
| 26 | // |
| 27 | |
| 28 | #include <FL/fl_draw.H> |
| 29 | #include <FL/Enumerations.H> |
| 30 | #include <stdlib.h> |
| 31 | #include "flstring.h" |
| 32 | |
| 33 | #ifdef __APPLE__ |
| 34 | |
| 35 | // These function assume a western code page. If you need to support |
| 36 | // scripts that are not part of this code page, you might want to |
| 37 | // take a look at FLTK2, which uses utf8 for text encoding. |
| 38 | // |
| 39 | // By keeping these conversion tables in their own module, they will not |
| 40 | // be statically linked (by a smart linker) unless actually used. |
| 41 | // |
| 42 | // On MS-Windows, nothing need to be converted. We simply return the |
| 43 | // original pointer. |
| 44 | // |
| 45 | // Most X11 implementations seem to default to Latin-1 as a code since it |
| 46 | // is a superset of ISO 8859-1, the original wetsern codepage on X11. |
| 47 | // |
| 48 | // Apple's OS X however renders text in MacRoman for western settings. The |
| 49 | // lookup tables below will convert all common character codes and replace |
| 50 | // unknown characters with an upsidedown question mark. |
| 51 | |
| 52 | // This table converts MSWindows-1252/Latin 1 into MacRoman encoding |
| 53 | static uchar latin2roman[128] = { |
| 54 | 0xdb, 0xc0, 0xe2, 0xc4, 0xe3, 0xc9, 0xa0, 0xe0, 0xf6, 0xe4, 0xc0, 0xdc, 0xce, 0xc0, 0xc0, 0xc0, |
| 55 | 0xc0, 0xd4, 0xd5, 0xd2, 0xd3, 0xa5, 0xd0, 0xd1, 0xf7, 0xaa, 0xc0, 0xdd, 0xcf, 0xc0, 0xc0, 0xd9, |
| 56 | 0xca, 0xc1, 0xa2, 0xa3, 0xc0, 0xb4, 0xc0, 0xa4, 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0xc0, 0xa8, 0xf8, |
| 57 | 0xa1, 0xb1, 0xc0, 0xc0, 0xab, 0xb5, 0xa6, 0xe1, 0xfc, 0xc0, 0xbc, 0xc8, 0xc0, 0xc0, 0xc0, 0xc0, |
| 58 | 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, |
| 59 | 0xc0, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0xc0, 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0xc0, 0xc0, 0xa7, |
| 60 | 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, |
| 61 | 0xc0, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0xc0, 0xc0, 0xd8 |
| 62 | }; |
| 63 | |
| 64 | // This table converts MacRoman into MSWindows-1252/Latin 1 |
| 65 | static uchar roman2latin[128] = { |
| 66 | 0xc4, 0xc5, 0xc7, 0xc9, 0xd1, 0xd6, 0xdc, 0xe1, 0xe0, 0xe2, 0xe4, 0xe3, 0xe5, 0xe7, 0xe9, 0xe8, |
| 67 | 0xea, 0xeb, 0xed, 0xec, 0xee, 0xef, 0xf1, 0xf3, 0xf2, 0xf4, 0xf6, 0xf5, 0xfa, 0xf9, 0xfb, 0xfc, |
| 68 | 0x86, 0xb0, 0xa2, 0xa3, 0xa7, 0x95, 0xb6, 0xdf, 0xae, 0xa9, 0x99, 0xb4, 0xa8, 0xbf, 0xc6, 0xd8, |
| 69 | 0xbf, 0xb1, 0xbf, 0xbf, 0xa5, 0xb5, 0xbf, 0xbf, 0xbf, 0xbf, 0xbf, 0xaa, 0xba, 0xbf, 0xe6, 0xf8, |
| 70 | 0xbf, 0xa1, 0xac, 0xbf, 0x83, 0xbf, 0xbf, 0xab, 0xbb, 0x85, 0xa0, 0xc0, 0xc3, 0xd5, 0x8c, 0x9c, |
| 71 | 0x96, 0x97, 0x93, 0x94, 0x91, 0x92, 0xf7, 0xbf, 0xff, 0x9f, 0xbf, 0x80, 0x8b, 0x9b, 0xbf, 0xbf, |
| 72 | 0x87, 0xb7, 0x82, 0x84, 0x89, 0xc2, 0xca, 0xc1, 0xcb, 0xc8, 0xcd, 0xce, 0xcf, 0xcc, 0xd3, 0xd4, |
| 73 | 0xbf, 0xd2, 0xda, 0xdb, 0xd9, 0xbf, 0x88, 0x98, 0xaf, 0xbf, 0xbf, 0xbf, 0xb8, 0xbf, 0xbf, 0xbf |
| 74 | }; |
| 75 | |
| 76 | static char *buf = 0; |
| 77 | static int n_buf = 0; |
| 78 | |
| 79 | const char *fl_latin1_to_local(const char *t, int n) |
| 80 | { |
| 81 | if (n==-1) n = strlen(t); |
| 82 | if (n<=n_buf) { |
| 83 | n_buf = (n + 257) & 0x7fffff00; |
| 84 | if (buf) free(buf); |
| 85 | buf = (char*)malloc(n_buf); |
| 86 | } |
| 87 | const uchar *src = (const uchar*)t; |
| 88 | uchar *dst = (uchar*)buf; |
| 89 | for ( ; n>0; n--) { |
| 90 | uchar c = *src++; |
| 91 | if (c>127) |
| 92 | *dst = latin2roman[c-128]; |
| 93 | else |
| 94 | *dst = c; |
| 95 | } |
| 96 | //*dst = 0; // this would be wrong! |
| 97 | return buf; |
| 98 | } |
| 99 | |
| 100 | const char *fl_local_to_latin1(const char *t, int n) |
| 101 | { |
| 102 | if (n==-1) n = strlen(t); |
| 103 | if (n<=n_buf) { |
| 104 | n_buf = (n + 257) & 0x7fffff00; |
| 105 | if (buf) free(buf); |
| 106 | buf = (char*)malloc(n_buf); |
| 107 | } |
| 108 | const uchar *src = (const uchar*)t; |
| 109 | uchar *dst = (uchar*)buf; |
| 110 | for ( ; n>0; n--) { |
| 111 | uchar c = *src++; |
| 112 | if (c>127) |
| 113 | *dst++ = roman2latin[c-128]; |
| 114 | else |
| 115 | *dst++ = c; |
| 116 | } |
| 117 | //*dst = 0; // this would be wrong |
| 118 | return buf; |
| 119 | } |
| 120 | |
| 121 | #else |
| 122 | |
| 123 | const char *fl_latin1_to_local(const char *t, int) |
| 124 | { |
| 125 | return t; |
| 126 | } |
| 127 | |
| 128 | const char *fl_local_to_latin1(const char *t, int) |
| 129 | { |
| 130 | return t; |
| 131 | } |
| 132 | |
| 133 | #endif |
| 134 | |
| 135 | // |
| 136 | // End of "$Id: fl_encoding_latin1.cxx 7903 2010-11-28 21:06:39Z matt $". |
| 137 | // |