Mercurial > hg > octave-kai > gnulib-hg
changeset 11131:b52a93576921
New module 'uniwbrk/base'.
author | Bruno Haible <bruno@clisp.org> |
---|---|
date | Sun, 08 Feb 2009 20:42:32 +0100 |
parents | 5dc843b6cd61 |
children | b21747aefd8a |
files | ChangeLog lib/uniwbrk.h modules/uniwbrk/base |
diffstat | 3 files changed, 111 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +2009-02-08 Bruno Haible <bruno@clisp.org> + + New module 'uniwbrk/base'. + * modules/uniwbrk/base: New file. + * lib/uniwbrk.h: New file. + 2009-02-08 Bruno Haible <bruno@clisp.org> Update to Unicode 5.1.0.
new file mode 100644 --- /dev/null +++ b/lib/uniwbrk.h @@ -0,0 +1,83 @@ +/* Word breaks in Unicode strings. + Copyright (C) 2001-2003, 2005-2009 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2009. + + This program is free software: you can redistribute it and/or modify it + under the terms of the GNU Lesser General Public License as published + by the Free Software Foundation; either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. */ + +#ifndef _UNIWBRK_H +#define _UNIWBRK_H + +/* Get size_t. */ +#include <stddef.h> + +#include "unitypes.h" + + +#ifdef __cplusplus +extern "C" { +#endif + +/* ========================================================================= */ + +/* Property defined in Unicode Standard Annex #29, section "Word Boundaries" + <http://www.unicode.org/reports/tr29/#Word_Boundaries> */ + +/* Possible values of the Word_Break property. + This enumeration may be extended in the future. */ +enum +{ + WBP_OTHER = 0, + WBP_CR = 11, + WBP_LF = 12, + WBP_NEWLINE = 10, + WBP_EXTEND = 8, + WBP_FORMAT = 9, + WBP_KATAKANA = 1, + WBP_ALETTER = 2, + WBP_MIDNUMLET = 3, + WBP_MIDLETTER = 4, + WBP_MIDNUM = 5, + WBP_NUMERIC = 6, + WBP_EXTENDNUMLET = 7 +}; + +/* Return the Word_Break property of a Unicode character. */ +extern int + uc_wordbreak_property (ucs4_t uc); + +/* ========================================================================= */ + +/* Word breaks. */ + +/* Determine the word break points in S, and store the result at p[0..n-1]. + p[i] = 1 means that there is a word boundary between s[i-1] and s[i]. + p[i] = 0 means that s[i-1] and s[i] must not be separated. + */ +extern void + u8_wordbreaks (const uint8_t *s, size_t n, char *p); +extern void + u16_wordbreaks (const uint16_t *s, size_t n, char *p); +extern void + u32_wordbreaks (const uint32_t *s, size_t n, char *p); +extern void + ulc_wordbreaks (const char *s, size_t n, char *p); + +/* ========================================================================= */ + +#ifdef __cplusplus +} +#endif + + +#endif /* _UNIWBRK_H */