include/unicode.h

   1 /*@
   2  * Copyright (c) 2014 - 2017 Steffen (Daode) Nurpmeso <steffen@sdaoden.eu>.
   3  *
   4  * Copyright (C) 2002, 2003, 2006
   5  *    Free Software Foundation, Inc.
   6  *      Written by Werner Lemberg <wl@gnu.org>
   7  *
   8  * This is free software; you can redistribute it and/or modify it under
   9  * the terms of the GNU General Public License as published by the Free
  10  * Software Foundation; either version 2, or (at your option) any later
  11  * version.
  12  *
  13  * This is distributed in the hope that it will be useful, but WITHOUT ANY
  14  * WARRANTY; without even the implied warranty of MERCHANTABILITY or
  15  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  16  * for more details.
  17  *
  18  * You should have received a copy of the GNU General Public License along
  19  * with groff; see the file COPYING.  If not, write to the Free Software
  20  * Foundation, 51 Franklin St - Fifth Floor, Boston, MA 02110-1301, USA.
  21  */
  22 #ifndef _UNICODE_H
  23 #define _UNICODE_H
  24
  25 #include "config.h"
  26
  27 // Convert a groff glyph name to a string containing an underscore-separated
  28 // list of Unicode code points.  For example,
  29 //
  30 //   `-'   ->  `2010'
  31 //   `,c'  ->  `00E7'
  32 //   `fl'  ->  `0066_006C'
  33 //
  34 // Return NULL if there is no equivalent.
  35 const char *glyph_name_to_unicode(const char *);
  36
  37 // Convert a string containing an underscore-separated list of Unicode code
  38 // points to a groff glyph name.  For example,
  39 //
  40 //   `2010'       ->  `hy'
  41 //   `0066_006C'  ->  `fl'
  42 //
  43 // Return NULL if there is no equivalent.
  44 const char *unicode_to_glyph_name(const char *);
  45
  46 // Convert a string containing a precomposed Unicode character to a string
  47 // containing an underscore-separated list of Unicode code points,
  48 // representing its canonical decomposition.  Also perform compatibility
  49 // equivalent replacement.  For example,
  50 //
  51 //   `1F3A' -> `0399_0313_0300'
  52 //   `FA6A' -> `983B'
  53 //
  54 // Return NULL if there is no equivalent.
  55 const char *decompose_unicode(const char *);
  56
  57 // Test whether the given string denotes a Unicode character.  It must
  58 // be of the form `uNNNN', obeying the following rules.
  59 //
  60 //   - `NNNN' must consist of at least 4 hexadecimal digits in upper case.
  61 //   - If there are more than 4 hexadecimal digits, the leading one must not
  62 //     be zero,
  63 //   - `NNNN' must denote a valid Unicode code point (U+0000..U+10FFFF,
  64 //     excluding surrogate code points.
  65 //
  66 // Return a pointer to `NNNN' (skipping the leading `u' character) in case
  67 // of success, NULL otherwise.
  68 const char *check_unicode_name(const char *);
  69
  70 #endif // _UNICODE_H
  71 // s-it2-mode