| 1 | /* lang.h -- declarations for language codes etc.
|
|---|
| 2 | $Id: lang.h,v 1.6 2004/04/11 17:56:47 karl Exp $
|
|---|
| 3 |
|
|---|
| 4 | Copyright (C) 1999, 2001, 2002, 2003 Free Software Foundation, Inc.
|
|---|
| 5 |
|
|---|
| 6 | This program is free software; you can redistribute it and/or modify
|
|---|
| 7 | it under the terms of the GNU General Public License as published by
|
|---|
| 8 | the Free Software Foundation; either version 2, or (at your option)
|
|---|
| 9 | any later version.
|
|---|
| 10 |
|
|---|
| 11 | This program is distributed in the hope that it will be useful,
|
|---|
| 12 | but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 13 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 14 | GNU General Public License for more details.
|
|---|
| 15 |
|
|---|
| 16 | You should have received a copy of the GNU General Public License
|
|---|
| 17 | along with this program; if not, write to the Free Software
|
|---|
| 18 | Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|---|
| 19 |
|
|---|
| 20 | Originally written by Karl Heinz Marbaise <kama@hippo.fido.de>. */
|
|---|
| 21 |
|
|---|
| 22 | #ifndef LANG_H
|
|---|
| 23 | #define LANG_H
|
|---|
| 24 |
|
|---|
| 25 | /* The language code which can be changed through @documentlanguage
|
|---|
| 26 | * Actually we don't currently support this (may be in the future) ;-)
|
|---|
| 27 | * These code are the ISO-639 two letter codes.
|
|---|
| 28 | */
|
|---|
| 29 | typedef enum
|
|---|
| 30 | {
|
|---|
| 31 | aa, ab, af, am, ar, as, ay, az,
|
|---|
| 32 | ba, be, bg, bh, bi, bn, bo, br,
|
|---|
| 33 | ca, co, cs, cy,
|
|---|
| 34 | da, de, dz,
|
|---|
| 35 | el, en, eo, es, et, eu,
|
|---|
| 36 | fa, fi, fj, fo, fr, fy,
|
|---|
| 37 | ga, gd, gl, gn, gu,
|
|---|
| 38 | ha, he, hi, hr, hu, hy,
|
|---|
| 39 | ia, id, ie, ik, is, it, iu,
|
|---|
| 40 | ja, jw,
|
|---|
| 41 | ka, kk, kl, km, kn, ko, ks, ku, ky,
|
|---|
| 42 | la, ln, lo, lt, lv,
|
|---|
| 43 | mg, mi, mk, ml, mn, mo, mr, ms, mt, my,
|
|---|
| 44 | na, ne, nl, no,
|
|---|
| 45 | oc, om, or,
|
|---|
| 46 | pa, pl, ps, pt,
|
|---|
| 47 | qu,
|
|---|
| 48 | rm, rn, ro, ru, rw,
|
|---|
| 49 | sa, sd, sg, sh, si, sk, sl, sm, sn, so, sq, sr, ss, st, su, sv, sw,
|
|---|
| 50 | ta, te, tg, th, ti, tk, tl, tn, to, tr, ts, tt, tw,
|
|---|
| 51 | ug, uk, ur, uz,
|
|---|
| 52 | vi, vo,
|
|---|
| 53 | wo,
|
|---|
| 54 | xh,
|
|---|
| 55 | yi, yo,
|
|---|
| 56 | za, zh, zu,
|
|---|
| 57 | last_language_code
|
|---|
| 58 | } language_code_type;
|
|---|
| 59 |
|
|---|
| 60 | /* The current language code. */
|
|---|
| 61 | extern language_code_type language_code;
|
|---|
| 62 |
|
|---|
| 63 |
|
|---|
| 64 | /* Information for each language. */
|
|---|
| 65 | typedef struct
|
|---|
| 66 | {
|
|---|
| 67 | language_code_type lc; /* language code as enum type */
|
|---|
| 68 | char *abbrev; /* two letter language code */
|
|---|
| 69 | char *desc; /* full name for language code */
|
|---|
| 70 | } language_type;
|
|---|
| 71 |
|
|---|
| 72 | extern language_type language_table[];
|
|---|
| 73 |
|
|---|
| 74 |
|
|---|
| 75 | |
|---|
| 76 |
|
|---|
| 77 | /* The document encoding. This is useful to produce true 8-bit
|
|---|
| 78 | characters according to the @documentencoding. */
|
|---|
| 79 |
|
|---|
| 80 | typedef enum {
|
|---|
| 81 | no_encoding,
|
|---|
| 82 | US_ASCII,
|
|---|
| 83 | ISO_8859_1,
|
|---|
| 84 | ISO_8859_2,
|
|---|
| 85 | ISO_8859_3, /* this and none of the rest are supported. */
|
|---|
| 86 | ISO_8859_4,
|
|---|
| 87 | ISO_8859_5,
|
|---|
| 88 | ISO_8859_6,
|
|---|
| 89 | ISO_8859_7,
|
|---|
| 90 | ISO_8859_8,
|
|---|
| 91 | ISO_8859_9,
|
|---|
| 92 | ISO_8859_10,
|
|---|
| 93 | ISO_8859_11,
|
|---|
| 94 | ISO_8859_12,
|
|---|
| 95 | ISO_8859_13,
|
|---|
| 96 | ISO_8859_14,
|
|---|
| 97 | ISO_8859_15,
|
|---|
| 98 | last_encoding_code
|
|---|
| 99 | } encoding_code_type;
|
|---|
| 100 |
|
|---|
| 101 | /* The current document encoding, or null if not set. */
|
|---|
| 102 | extern encoding_code_type document_encoding_code;
|
|---|
| 103 |
|
|---|
| 104 | /* If an encoding is not supported, just keep it as a string. */
|
|---|
| 105 | extern char *unknown_encoding;
|
|---|
| 106 |
|
|---|
| 107 | /* Maps an HTML abbreviation to ISO and Unicode codes for a given code. */
|
|---|
| 108 |
|
|---|
| 109 | typedef unsigned short int unicode_t; /* should be 16 bits */
|
|---|
| 110 | typedef unsigned char byte_t;
|
|---|
| 111 |
|
|---|
| 112 | typedef struct
|
|---|
| 113 | {
|
|---|
| 114 | char *html; /* HTML equivalent like umlaut auml => ä */
|
|---|
| 115 | byte_t bytecode; /* 8-Bit Code (ISO 8859-1,...) */
|
|---|
| 116 | unicode_t unicode; /* Unicode in U+ convention */
|
|---|
| 117 | } iso_map_type;
|
|---|
| 118 |
|
|---|
| 119 | /* Information about the document encoding. */
|
|---|
| 120 | typedef struct
|
|---|
| 121 | {
|
|---|
| 122 | encoding_code_type ec; /* document encoding type (see above enum) */
|
|---|
| 123 | char *encname; /* encoding name like "iso-8859-1", valid in
|
|---|
| 124 | HTML and Emacs */
|
|---|
| 125 | iso_map_type *isotab; /* address of ISO translation table */
|
|---|
| 126 | } encoding_type;
|
|---|
| 127 |
|
|---|
| 128 | /* Table with all the encoding codes that we recognize. */
|
|---|
| 129 | extern encoding_type encoding_table[];
|
|---|
| 130 |
|
|---|
| 131 | |
|---|
| 132 |
|
|---|
| 133 | /* The commands. */
|
|---|
| 134 | extern void cm_documentlanguage (void),
|
|---|
| 135 | cm_documentencoding (void);
|
|---|
| 136 |
|
|---|
| 137 | /* Accents, other non-English characters. */
|
|---|
| 138 | void cm_accent (int arg), cm_special_char (int arg),
|
|---|
| 139 | cm_dotless (int arg, int start, int end);
|
|---|
| 140 |
|
|---|
| 141 | extern void cm_accent_umlaut (int arg, int start, int end),
|
|---|
| 142 | cm_accent_acute (int arg, int start, int end),
|
|---|
| 143 | cm_accent_cedilla (int arg, int start, int end),
|
|---|
| 144 | cm_accent_hat (int arg, int start, int end),
|
|---|
| 145 | cm_accent_grave (int arg, int start, int end),
|
|---|
| 146 | cm_accent_tilde (int arg, int start, int end);
|
|---|
| 147 |
|
|---|
| 148 | extern char *current_document_encoding (void);
|
|---|
| 149 |
|
|---|
| 150 | #endif /* not LANG_H */
|
|---|
