1 /* linebreak.h - line breaking of Unicode strings 2 Copyright (C) 2001-2003 Free Software Foundation, Inc. 3 Written by Bruno Haible <haible@clisp.cons.org>, 2001. 4 5 This program is free software; you can redistribute it and/or modify 6 it under the terms of the GNU General Public License as published by 7 the Free Software Foundation; either version 2, or (at your option) 8 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 13 GNU General Public License for more details. 14 15 You should have received a copy of the GNU General Public License 16 along with this program; if not, write to the Free Software Foundation, 17 Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ 18 19 #ifndef _LINEBREAK_H 20 #define _LINEBREAK_H 21 22 /* Get size_t. */ 23 #include <stddef.h> 24 25 26 /* Display width. */ 27 28 /* These functions are locale dependent. The encoding argument identifies 29 the encoding (e.g. "ISO-8859-2" for Polish). */ 30 31 /* Return the encoding of the current locale. */ 32 extern const char * locale_charset (void); 33 34 /* Determine number of column positions required for UC. */ 35 extern int uc_width (unsigned int uc, const char *encoding); 36 37 /* Determine number of column positions required for first N units 38 (or fewer if S ends before this) in S. */ 39 extern int u8_width (const unsigned char *s, size_t n, const char *encoding); 40 extern int u16_width (const unsigned short *s, size_t n, const char *encoding); 41 extern int u32_width (const unsigned int *s, size_t n, const char *encoding); 42 43 44 /* Line breaking. */ 45 46 enum { 47 UC_BREAK_UNDEFINED, 48 UC_BREAK_PROHIBITED, 49 UC_BREAK_POSSIBLE, 50 UC_BREAK_MANDATORY, 51 UC_BREAK_HYPHENATION 52 }; 53 54 /* Determine the line break points in S, and store the result at p[0..n-1]. 55 p[i] = UC_BREAK_MANDATORY means that s[i] is a line break character. 56 p[i] = UC_BREAK_POSSIBLE means that a line break may be inserted between 57 s[i-1] and s[i]. 58 p[i] = UC_BREAK_HYPHENATION means that a hyphen and a line break may be 59 inserted between s[i-1] and s[i]. But beware of language dependent 60 hyphenation rules. 61 p[i] = UC_BREAK_PROHIBITED means that s[i-1] and s[i] must not be separated. 62 */ 63 extern void u8_possible_linebreaks (const unsigned char *s, size_t n, 64 const char *encoding, 65 char *p); 66 extern void u16_possible_linebreaks (const unsigned short *s, size_t n, 67 const char *encoding, 68 char *p); 69 extern void u32_possible_linebreaks (const unsigned int *s, size_t n, 70 const char *encoding, 71 char *p); 72 extern void mbs_possible_linebreaks (const char *s, size_t n, 73 const char *encoding, 74 char *p); 75 76 /* Choose the best line breaks, assuming the uc_width function. 77 Return the column after the end of the string. 78 o is an optional override; if o[i] != UC_BREAK_UNDEFINED, o[i] takes 79 precedence over p[i] as returned by the *_possible_linebreaks function. 80 */ 81 extern int 82 u8_width_linebreaks (const unsigned char *s, size_t n, 83 int width, int start_column, int at_end_columns, 84 const char *o, const char *encoding, 85 char *p); 86 extern int 87 u16_width_linebreaks (const unsigned short *s, size_t n, 88 int width, int start_column, int at_end_columns, 89 const char *o, const char *encoding, 90 char *p); 91 extern int 92 u32_width_linebreaks (const unsigned int *s, size_t n, 93 int width, int start_column, int at_end_columns, 94 const char *o, const char *encoding, 95 char *p); 96 extern int 97 mbs_width_linebreaks (const char *s, size_t n, 98 int width, int start_column, int at_end_columns, 99 const char *o, const char *encoding, 100 char *p); 101 102 103 #endif /* _LINEBREAK_H */ 104