unigbrk.h (5526B)
1 /* DO NOT EDIT! GENERATED AUTOMATICALLY! */ 2 /* Grapheme cluster breaks in Unicode strings. 3 Copyright (C) 2010-2024 Free Software Foundation, Inc. 4 Written by Ben Pfaff <blp@cs.stanford.edu>, 2010. 5 6 This file is free software. 7 It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+". 8 You can redistribute it and/or modify it under either 9 - the terms of the GNU Lesser General Public License as published 10 by the Free Software Foundation, either version 3, or (at your 11 option) any later version, or 12 - the terms of the GNU General Public License as published by the 13 Free Software Foundation; either version 2, or (at your option) 14 any later version, or 15 - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+". 16 17 This file is distributed in the hope that it will be useful, 18 but WITHOUT ANY WARRANTY; without even the implied warranty of 19 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 20 Lesser General Public License and the GNU General Public License 21 for more details. 22 23 You should have received a copy of the GNU Lesser General Public 24 License and of the GNU General Public License along with this 25 program. If not, see <https://www.gnu.org/licenses/>. */ 26 27 #ifndef _UNIGBRK_H 28 #define _UNIGBRK_H 29 30 /* Get bool. */ 31 #include <unistring/stdbool.h> 32 33 /* Get size_t. */ 34 #include <stddef.h> 35 36 #include "unitypes.h" 37 38 #ifdef __cplusplus 39 extern "C" { 40 #endif 41 42 /* ========================================================================= */ 43 44 /* Property defined in Unicode Standard Annex #29, section "Grapheme Cluster 45 Boundaries" 46 <https://unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries> */ 47 48 /* Possible values of the Grapheme_Cluster_Break property. 49 This enumeration may be extended in the future. */ 50 enum 51 { 52 GBP_OTHER = 0, 53 GBP_CR = 1, 54 GBP_LF = 2, 55 GBP_CONTROL = 3, 56 GBP_EXTEND = 4, 57 GBP_PREPEND = 5, 58 GBP_SPACINGMARK = 6, 59 GBP_L = 7, 60 GBP_V = 8, 61 GBP_T = 9, 62 GBP_LV = 10, 63 GBP_LVT = 11, 64 GBP_RI = 12, 65 GBP_ZWJ = 13, 66 GBP_EB = 14, /* obsolete */ 67 GBP_EM = 15, /* obsolete */ 68 GBP_GAZ = 16, /* obsolete */ 69 GBP_EBG = 17 /* obsolete */ 70 }; 71 72 /* Return the Grapheme_Cluster_Break property of a Unicode character. */ 73 extern int 74 uc_graphemeclusterbreak_property (ucs4_t uc) 75 _UC_ATTRIBUTE_CONST; 76 77 /* ========================================================================= */ 78 79 /* Grapheme cluster breaks. */ 80 81 /* Returns true if there is a grapheme cluster boundary between Unicode code 82 points A and B. A "grapheme cluster" is an approximation to a 83 user-perceived character, which sometimes corresponds to multiple code 84 points. For example, an English letter followed by an acute accent can be 85 expressed as two consecutive Unicode code points, but it is perceived by the 86 user as only a single character and therefore constitutes a single grapheme 87 cluster. 88 89 Implements extended (not legacy) grapheme cluster rules, because UAX #29 90 indicates that they are preferred. 91 92 Note: This function does not work right with syllables in Indic scripts or 93 emojis, because it does not look at the characters before A and after B. 94 95 Use A == 0 or B == 0 to indicate start of text or end of text, 96 respectively. */ 97 extern bool 98 uc_is_grapheme_break (ucs4_t a, ucs4_t b) 99 _UC_ATTRIBUTE_CONST; 100 101 /* Returns the start of the next grapheme cluster following S, or NULL if the 102 end of the string has been reached. 103 Note: These functions do not work right with syllables in Indic scripts or 104 emojis, because they do not consider the characters before S. */ 105 extern const uint8_t * 106 u8_grapheme_next (const uint8_t *s, const uint8_t *end) 107 _UC_ATTRIBUTE_PURE; 108 extern const uint16_t * 109 u16_grapheme_next (const uint16_t *s, const uint16_t *end) 110 _UC_ATTRIBUTE_PURE; 111 extern const uint32_t * 112 u32_grapheme_next (const uint32_t *s, const uint32_t *end) 113 _UC_ATTRIBUTE_PURE; 114 115 /* Returns the start of the previous grapheme cluster before S, or NULL if the 116 start of the string has been reached. 117 Note: These functions do not work right with syllables in Indic scripts or 118 emojis, because they do not consider the characters at or after S. */ 119 extern const uint8_t * 120 u8_grapheme_prev (const uint8_t *s, const uint8_t *start) 121 _UC_ATTRIBUTE_PURE; 122 extern const uint16_t * 123 u16_grapheme_prev (const uint16_t *s, const uint16_t *start) 124 _UC_ATTRIBUTE_PURE; 125 extern const uint32_t * 126 u32_grapheme_prev (const uint32_t *s, const uint32_t *start) 127 _UC_ATTRIBUTE_PURE; 128 129 /* Determine the grapheme cluster boundaries in S, and store the result at 130 p[0..n-1]. p[i] = 1 means that a new grapheme cluster begins at s[i]. p[i] 131 = 0 means that s[i-1] and s[i] are part of the same grapheme cluster. p[0] 132 will always be 1. 133 */ 134 extern void 135 u8_grapheme_breaks (const uint8_t *s, size_t n, char *p); 136 extern void 137 u16_grapheme_breaks (const uint16_t *s, size_t n, char *p); 138 extern void 139 u32_grapheme_breaks (const uint32_t *s, size_t n, char *p); 140 extern void 141 ulc_grapheme_breaks (const char *s, size_t n, char *p); 142 extern void 143 uc_grapheme_breaks (const ucs4_t *s, size_t n, char *p); 144 145 /* ========================================================================= */ 146 147 #ifdef __cplusplus 148 } 149 #endif 150 151 152 #endif /* _UNIGBRK_H */