1 /* DO NOT EDIT! GENERATED AUTOMATICALLY! */ 2 /* Word breaks in Unicode strings. 3 Copyright (C) 2001-2003, 2005-2018 Free Software Foundation, Inc. 4 Written by Bruno Haible <bruno@clisp.org>, 2009. 5 6 This program is free software: you can redistribute it and/or 7 modify it under the terms of either: 8 9 * the GNU Lesser General Public License as published by the Free 10 Software Foundation; either version 3 of the License, or (at your 11 option) any later version. 12 13 or 14 15 * the GNU General Public License as published by the Free 16 Software Foundation; either version 2 of the License, or (at your 17 option) any later version. 18 19 or both in parallel, as here. 20 This program is distributed in the hope that it will be useful, 21 but WITHOUT ANY WARRANTY; without even the implied warranty of 22 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 23 Lesser General Public License for more details. 24 25 You should have received a copy of the GNU Lesser General Public License 26 along with this program. If not, see <https://www.gnu.org/licenses/>. */ 27 28 #ifndef _UNIWBRK_H 29 #define _UNIWBRK_H 30 31 /* Get size_t. */ 32 #include <stddef.h> 33 34 #include "unitypes.h" 35 36 37 #ifdef __cplusplus 38 extern "C" { 39 #endif 40 41 /* ========================================================================= */ 42 43 /* Property defined in Unicode Standard Annex #29, section "Word Boundaries" 44 <http://www.unicode.org/reports/tr29/#Word_Boundaries> */ 45 46 /* Possible values of the Word_Break property. 47 This enumeration may be extended in the future. */ 48 enum 49 { 50 WBP_OTHER = 0, 51 WBP_CR = 11, 52 WBP_LF = 12, 53 WBP_NEWLINE = 10, 54 WBP_EXTEND = 8, 55 WBP_FORMAT = 9, 56 WBP_KATAKANA = 1, 57 WBP_ALETTER = 2, 58 WBP_MIDNUMLET = 3, 59 WBP_MIDLETTER = 4, 60 WBP_MIDNUM = 5, 61 WBP_NUMERIC = 6, 62 WBP_EXTENDNUMLET = 7, 63 WBP_RI = 13, 64 WBP_DQ = 14, 65 WBP_SQ = 15, 66 WBP_HL = 16, 67 WBP_ZWJ = 17, 68 WBP_EB = 18, 69 WBP_EM = 19, 70 WBP_GAZ = 20, 71 WBP_EBG = 21 72 }; 73 74 /* Return the Word_Break property of a Unicode character. */ 75 extern int 76 uc_wordbreak_property (ucs4_t uc) 77 _UC_ATTRIBUTE_CONST; 78 79 /* ========================================================================= */ 80 81 /* Word breaks. */ 82 83 /* Determine the word break points in S, and store the result at p[0..n-1]. 84 p[i] = 1 means that there is a word boundary between s[i-1] and s[i]. 85 p[i] = 0 means that s[i-1] and s[i] must not be separated. 86 */ 87 extern void 88 u8_wordbreaks (const uint8_t *s, size_t n, char *p); 89 extern void 90 u16_wordbreaks (const uint16_t *s, size_t n, char *p); 91 extern void 92 u32_wordbreaks (const uint32_t *s, size_t n, char *p); 93 extern void 94 ulc_wordbreaks (const char *s, size_t n, char *p); 95 96 /* ========================================================================= */ 97 98 #ifdef __cplusplus 99 } 100 #endif 101 102 103 #endif /* _UNIWBRK_H */ 104