Mercurial > gnulib
view lib/unilbrk/lbrktables.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
/* Line breaking auxiliary tables. Copyright (C) 2001-2003, 2006-2017 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. 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/>. */ #include "unitypes.h" /* Line breaking classification. */ enum { /* Values >= 30 are resolved at run time. */ LBP_BK = 30, /* mandatory break */ /*LBP_CR, carriage return - not used here because it's a DOSism */ /*LBP_LF, line feed - not used here because it's a DOSism */ LBP_CM = 31, /* attached characters and combining marks */ /*LBP_NL, next line - not used here because it's equivalent to LBP_BK */ /*LBP_SG, surrogates - not used here because they are not characters */ LBP_WJ = 0, /* word joiner */ LBP_ZW = 32, /* zero width space */ LBP_GL = 1, /* non-breaking (glue) */ LBP_SP = 33, /* space */ LBP_B2 = 2, /* break opportunity before and after */ LBP_BA = 3, /* break opportunity after */ LBP_BB = 4, /* break opportunity before */ LBP_HY = 5, /* hyphen */ LBP_CB = 34, /* contingent break opportunity */ LBP_CL = 6, /* closing punctuation */ LBP_CP = 7, /* closing parenthesis */ LBP_EX = 8, /* exclamation/interrogation */ LBP_IN = 9, /* inseparable */ LBP_NS = 10, /* non starter */ LBP_OP = 11, /* opening punctuation */ LBP_QU = 12, /* ambiguous quotation */ LBP_IS = 13, /* infix separator (numeric) */ LBP_NU = 14, /* numeric */ LBP_PO = 15, /* postfix (numeric) */ LBP_PR = 16, /* prefix (numeric) */ LBP_SY = 17, /* symbols allowing breaks */ LBP_AI = 35, /* ambiguous (alphabetic or ideograph) */ LBP_AL = 18, /* ordinary alphabetic and symbol characters */ /*LBP_CJ, conditional Japanese starters, resolved to NS */ LBP_H2 = 19, /* Hangul LV syllable */ LBP_H3 = 20, /* Hangul LVT syllable */ LBP_HL = 25, /* Hebrew letter */ LBP_ID = 21, /* ideographic */ LBP_JL = 22, /* Hangul L Jamo */ LBP_JV = 23, /* Hangul V Jamo */ LBP_JT = 24, /* Hangul T Jamo */ LBP_RI = 26, /* regional indicator */ LBP_SA = 36, /* complex context (South East Asian) */ LBP_ZWJ = 27, /* zero width joiner */ LBP_EB = 28, /* emoji base */ LBP_EM = 29, /* emoji modifier */ LBP_XX = 37 /* unknown */ }; #include "lbrkprop1.h" static inline unsigned char unilbrkprop_lookup (ucs4_t uc) { unsigned int index1 = uc >> lbrkprop_header_0; if (index1 < lbrkprop_header_1) { int lookup1 = unilbrkprop.level1[index1]; if (lookup1 >= 0) { unsigned int index2 = (uc >> lbrkprop_header_2) & lbrkprop_header_3; int lookup2 = unilbrkprop.level2[lookup1 + index2]; if (lookup2 >= 0) { unsigned int index3 = uc & lbrkprop_header_4; return unilbrkprop.level3[lookup2 + index3]; } } } return LBP_XX; } /* Table indexed by two line breaking classifications. */ #define D 1 /* direct break opportunity, empty in table 7.3 of UTR #14 */ #define I 2 /* indirect break opportunity, '%' in table 7.3 of UTR #14 */ #define P 3 /* prohibited break, '^' in table 7.3 of UTR #14 */ extern const unsigned char unilbrk_table[30][30]; /* We don't support line breaking of complex-context dependent characters (Thai, Lao, Myanmar, Khmer) yet, because it requires dictionary lookup. */