Mercurial > gnulib
view lib/uniwbrk.in.h @ 19273:638b6d1fdf36 ueno/unicode-9.0.0
libunistring: update to Unicode 9.0.0
* lib/gen-uni-tables.c (fill_properties): Recognize Sentence_Terminal
and Prepended_Concatenation_Mark.
(is_property_default_ignorable_code_point): Exclude U+08E2.
(fill_arabicshaping): Allow missing whitespace when parsing;
recognize "AFRICAN FEH", "AFRICAN QAF", and "AFRICAN MOON".
(output_blocks): Increase the element size of the level1 table to
accommodate more blocks.
(get_lbp): Recognize ZWJ, E_Base, and E_Modifier characters;
Update each class according to the standard.
(get_wbp): Recognize ZWJ, E_Base, E_Modifier, Glue_After_Zwj, and
E_Base_GAZ characters.
(output_gbp_table): Recognize ZWJ, E_Base, E_Modifier, Glue_After_Zwj,
and E_Base_GAZ characters.
* lib/unictype.in.h (UC_JOINING_GROUP_AFRICAN_FEH,
UC_JOINING_GROUP_AFRICAN_QAF, UC_JOINING_GROUP_AFRICAN_MOON): New enum value.
* lib/unilbrk/lbrktables.h (LBP_ZWJ, LBP_EB, LBP_EM): New enum value.
* lib/unilbrk/lbrktables.c (unilbrk_table): Extend the table with
LBP_ZWJ, LBP_EB, and LBP_EM.
* lib/uniwbrk.in.h (WBP_ZWJ, WBP_EB, WBP_EM, WBP_GAZ, WBP_EBG): New
enum value.
* lib/uniwbrk/u-wordbreaks.h: Implement WB3c, WB15, and WB16.
* lib/uniwbrk/wbrktable.h (uniwbrk_prop_index): New variable declaration.
* lib/uniwbrk/wbrktable.c (uniwbrk_prop_index): New variable.
(uniwbrk_table): Implement WB14.
* tests/uniwbrk/test-uc-wordbreaks.c (wordbreakproperty_to_string):
Check WBP_ZWJ, WBP_EB, WBP_EM, WBP_GAZ, and WBP_EBG.
* modules/unigbrk/u{32,16,8}-grapheme-breaks: No longer depend on
uc-is-grapheme-break.
* modules/unigbrk/uc-grapheme-breaks: New module.
* modules/unigbrk/uc-grapheme-breaks-tests: New module.
* lib/unigbrk.in.h (GBP_ZWJ, GBP_EB, GBP_EM, GBP_GAZ, GBP_EBG): New
enum value.
(uc_grapheme_breaks): New function, replacing uc_is_grapheme_break.
* lib/unigbrk/u-grapheme-breaks.h: New file.
* lib/unigbrk/u{32,16,8}-grapheme-breaks.c: Rewrite using
u-grapheme-breaks.h instead of uc_is_grapheme_break.
* lib/unigbrk/uc-grapheme-breaks.c: New file.
* lib/unigbrk/uc-is-grapheme-break.c: Partially update to TR29 rev 29.
* tests/unigbrk/test-uc-gbrk-prop.c (graphemebreakproperty_to_string):
Check GBP_ZWJ, GBP_EB, GBP_EM, GBP_GAZ, and GBP_EBG.
* tests/unigbrk/test-uc-grapheme-breaks.c: New test.
* tests/unigbrk/test-uc-is-grapheme-break.c (graphemebreakproperty_to_string):
Check GBP_ZWJ, GBP_EB, GBP_EM, GBP_GAZ, and GBP_EBG.
(main): Skip unsupported rules involving 3 or more characters, namely
GB10, GB12, and GB13.
* lib/uniwidth/width.c (nonspacing_table_data): Update.
author | Daiki Ueno <ueno@gnu.org> |
---|---|
date | Wed, 12 Oct 2016 17:40:37 +0200 |
parents | 9759915b2aca |
children | 10eb9086bea0 |
line wrap: on
line source
/* Word breaks in Unicode strings. Copyright (C) 2001-2003, 2005-2017 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 <https://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, WBP_RI = 13, WBP_DQ = 14, WBP_SQ = 15, WBP_HL = 16, WBP_ZWJ = 17, WBP_EB = 18, WBP_EM = 19, WBP_GAZ = 20, WBP_EBG = 21 }; /* Return the Word_Break property of a Unicode character. */ extern int uc_wordbreak_property (ucs4_t uc) _UC_ATTRIBUTE_CONST; /* ========================================================================= */ /* 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 */