Mercurial > gnulib

comparison lib/unigbrk/u-grapheme-breaks.h @ 19273:638b6d1fdf36 ueno/unicode-9.0.0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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
children c1cbd8206d4b
comparison
equal deleted inserted replaced
19272:c20fd8143023 19273:638b6d1fdf36
1 /* Grapheme cluster break function.
2 Copyright (C) 2010-2017 Free Software Foundation, Inc.
3 Written by Ben Pfaff <blp@cs.stanford.edu>, 2010.
4
5 This program is free software: you can redistribute it and/or modify it
6 under the terms of the GNU Lesser General Public License as published
7 by the Free Software Foundation; either version 3 of the License, or
8 (at your option) 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 GNU
13 Lesser General Public License for more details.
14
15 You should have received a copy of the GNU Lesser General Public License
16 along with this program. If not, see <http://www.gnu.org/licenses/>. */
17
18 void
19 FUNC (const UNIT *s, size_t n, char *p)
20 {
21 if (n > 0)
22 {
23 const UNIT *s_end = s + n;
24
25 /* Grapheme Cluster break property of the last character.
26 -1 at the very beginning of the string. */
27 int last_char_prop = -1;
28
29 /* Grapheme Cluster break property of the last complex character.
30 -1 at the very beginning of the string. */
31 int last_compchar_prop = -1;
32
33 size_t ri_count = 0;
34
35 /* Don't break inside multibyte characters. */
36 memset (p, 0, n);
37
38 while (s < s_end)
39 {
40 ucs4_t uc;
41 int count = U_MBTOUC (&uc, s, s_end - s);
42 int prop = uc_graphemeclusterbreak_property (uc);
43
44 /* Break at the start of the string (GB1). */
45 if (last_char_prop < 0)
46 *p = 1;
47 else
48 {
49 /* No break between CR and LF (GB3). */
50 if (last_char_prop == GBP_CR && prop == GBP_LF)
51 /* *p = 0 */;
52 /* Break before and after newlines (GB4, GB5). */
53 else if ((last_char_prop == GBP_CR
54 || last_char_prop == GBP_LF
55 || last_char_prop == GBP_CONTROL)
56 || (prop == GBP_CR
57 || prop == GBP_LF
58 || prop == GBP_CONTROL))
59 *p = 1;
60 /* No break between Hangul syllable sequences (GB6, GB7, GB8). */
61 else if ((last_char_prop == GBP_L
62 && (prop == GBP_L
63 || prop == GBP_V
64 || prop == GBP_LV
65 || prop == GBP_LVT))
66 || ((last_char_prop == GBP_LV
67 || last_char_prop == GBP_V)
68 && (prop == GBP_V
69 || prop == GBP_T))
70 || ((last_char_prop == GBP_LVT
71 || last_char_prop == GBP_T)
72 && prop == GBP_T))
73 /* *p = 0 */;
74 /* No break before extending characters or ZWJ (GB9). */
75 else if (prop == GBP_EXTEND || prop == GBP_ZWJ)
76 /* *p = 0 */;
77 /* No break before SpacingMarks (GB9a). */
78 else if (prop == GBP_SPACINGMARK)
79 /* *p = 0 */;
80 /* No break after Prepend characters (GB9b). */
81 else if (last_char_prop == GBP_PREPEND)
82 /* *p = 0 */;
83 /* No break within emoji modifier sequences (GB10). */
84 else if ((last_compchar_prop == GBP_EB
85 || last_compchar_prop == GBP_EBG)
86 && prop == GBP_EM)
87 /* *p = 0 */;
88 /* No break within emoji zwj sequences (GB11). */
89 else if (last_char_prop == GBP_ZWJ
90 && (prop == GBP_GAZ
91 || prop == GBP_EBG))
92 /* *p = 0 */;
93 /* No break between RI if there is an odd number of RI
94 characters before (GB12, GB13). */
95 else if (prop == GBP_RI)
96 {
97 if (ri_count % 2 == 0)
98 *p = 1;
99 /* else *p = 0; */
100 }
101 /* Break everywhere (GBP999). */
102 else
103 *p = 1;
104 }
105
106 last_char_prop = prop;
107
108 if (!(prop == GBP_EXTEND
109 && (last_compchar_prop == GBP_EB
110 || last_compchar_prop == GBP_EBG)))
111 last_compchar_prop = prop;
112
113 if (prop == GBP_RI)
114 ri_count++;
115 else
116 ri_count = 0;
117
118 s += count;
119 p += count;
120 }
121 }
122 }