lib/uniwbrk.in.h

   1 /* Word breaks in Unicode strings.
   2    Copyright (C) 2001-2003, 2005-2024 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2009.
   4
   5    This file is free software.
   6    It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
   7    You can redistribute it and/or modify it under either
   8      - the terms of the GNU Lesser General Public License as published
   9        by the Free Software Foundation, either version 3, or (at your
  10        option) any later version, or
  11      - the terms of the GNU General Public License as published by the
  12        Free Software Foundation; either version 2, or (at your option)
  13        any later version, or
  14      - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".
  15
  16    This file is distributed in the hope that it will be useful,
  17    but WITHOUT ANY WARRANTY; without even the implied warranty of
  18    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  19    Lesser General Public License and the GNU General Public License
  20    for more details.
  21
  22    You should have received a copy of the GNU Lesser General Public
  23    License and of the GNU General Public License along with this
  24    program.  If not, see <https://www.gnu.org/licenses/>.  */
  25
  26 #ifndef _UNIWBRK_H
  27 #define _UNIWBRK_H
  28
  29 /* Get size_t.  */
  30 #include <stddef.h>
  31
  32 #include "unitypes.h"
  33
  34
  35 #ifdef __cplusplus
  36 extern "C" {
  37 #endif
  38
  39 /* ========================================================================= */
  40
  41 /* Property defined in Unicode Standard Annex #29, section "Word Boundaries"
  42    <https://www.unicode.org/reports/tr29/#Word_Boundaries>  */
  43
  44 /* Possible values of the Word_Break property.
  45    This enumeration may be extended in the future.  */
  46 enum
  47 {
  48   WBP_OTHER        = 0,
  49   WBP_CR           = 11,
  50   WBP_LF           = 12,
  51   WBP_NEWLINE      = 10,
  52   WBP_EXTEND       = 8,
  53   WBP_FORMAT       = 9,
  54   WBP_KATAKANA     = 1,
  55   WBP_ALETTER      = 2,
  56   WBP_MIDNUMLET    = 3,
  57   WBP_MIDLETTER    = 4,
  58   WBP_MIDNUM       = 5,
  59   WBP_NUMERIC      = 6,
  60   WBP_EXTENDNUMLET = 7,
  61   WBP_RI           = 13,
  62   WBP_DQ           = 14,
  63   WBP_SQ           = 15,
  64   WBP_HL           = 16,
  65   WBP_ZWJ          = 17,
  66   WBP_EB           = 18, /* obsolete */
  67   WBP_EM           = 19, /* obsolete */
  68   WBP_GAZ          = 20, /* obsolete */
  69   WBP_EBG          = 21, /* obsolete */
  70   WBP_WSS          = 22
  71 };
  72
  73 /* Return the Word_Break property of a Unicode character.  */
  74 extern int
  75        uc_wordbreak_property (ucs4_t uc)
  76        _UC_ATTRIBUTE_CONST;
  77
  78 /* ========================================================================= */
  79
  80 /* Word breaks.  */
  81
  82 /* Determine the word break points in S, and store the result at p[0..n-1].
  83    p[i] = 1 means that there is a word boundary between s[i-1] and s[i].
  84    p[i] = 0 means that s[i-1] and s[i] must not be separated.
  85  */
  86 extern void
  87        u8_wordbreaks (const uint8_t *s, size_t n, char *p);
  88 extern void
  89        u16_wordbreaks (const uint16_t *s, size_t n, char *p);
  90 extern void
  91        u32_wordbreaks (const uint32_t *s, size_t n, char *p);
  92 extern void
  93        ulc_wordbreaks (const char *s, size_t n, char *_UC_RESTRICT p);
  94
  95 /* ========================================================================= */
  96
  97 #ifdef __cplusplus
  98 }
  99 #endif
 100
 101
 102 #endif /* _UNIWBRK_H */