lib/uniwbrk.in.h

   1 /* Word breaks in Unicode strings.
   2    Copyright (C) 2001-2003, 2005-2021 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2009.
   4
   5    This program is free software: you can redistribute it and/or modify it
   6    under the terms of the GNU Lesser General Public License as published
   7    by the Free Software Foundation; either version 3 of the License, or
   8    (at your option) any later version.
   9
  10    This program is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public License
  16    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  17
  18 #ifndef _UNIWBRK_H
  19 #define _UNIWBRK_H
  20
  21 /* Get size_t.  */
  22 #include <stddef.h>
  23
  24 #include "unitypes.h"
  25
  26
  27 #ifdef __cplusplus
  28 extern "C" {
  29 #endif
  30
  31 /* ========================================================================= */
  32
  33 /* Property defined in Unicode Standard Annex #29, section "Word Boundaries"
  34    <https://www.unicode.org/reports/tr29/#Word_Boundaries>  */
  35
  36 /* Possible values of the Word_Break property.
  37    This enumeration may be extended in the future.  */
  38 enum
  39 {
  40   WBP_OTHER        = 0,
  41   WBP_CR           = 11,
  42   WBP_LF           = 12,
  43   WBP_NEWLINE      = 10,
  44   WBP_EXTEND       = 8,
  45   WBP_FORMAT       = 9,
  46   WBP_KATAKANA     = 1,
  47   WBP_ALETTER      = 2,
  48   WBP_MIDNUMLET    = 3,
  49   WBP_MIDLETTER    = 4,
  50   WBP_MIDNUM       = 5,
  51   WBP_NUMERIC      = 6,
  52   WBP_EXTENDNUMLET = 7,
  53   WBP_RI           = 13,
  54   WBP_DQ           = 14,
  55   WBP_SQ           = 15,
  56   WBP_HL           = 16,
  57   WBP_ZWJ          = 17,
  58   WBP_EB           = 18,
  59   WBP_EM           = 19,
  60   WBP_GAZ          = 20,
  61   WBP_EBG          = 21
  62 };
  63
  64 /* Return the Word_Break property of a Unicode character.  */
  65 extern int
  66        uc_wordbreak_property (ucs4_t uc)
  67        _UC_ATTRIBUTE_CONST;
  68
  69 /* ========================================================================= */
  70
  71 /* Word breaks.  */
  72
  73 /* Determine the word break points in S, and store the result at p[0..n-1].
  74    p[i] = 1 means that there is a word boundary between s[i-1] and s[i].
  75    p[i] = 0 means that s[i-1] and s[i] must not be separated.
  76  */
  77 extern void
  78        u8_wordbreaks (const uint8_t *s, size_t n, char *p);
  79 extern void
  80        u16_wordbreaks (const uint16_t *s, size_t n, char *p);
  81 extern void
  82        u32_wordbreaks (const uint32_t *s, size_t n, char *p);
  83 extern void
  84        ulc_wordbreaks (const char *s, size_t n, char *_UC_RESTRICT p);
  85
  86 /* ========================================================================= */
  87
  88 #ifdef __cplusplus
  89 }
  90 #endif
  91
  92
  93 #endif /* _UNIWBRK_H */