Branch
Hash :
c63a0c67
Author :
Date :
2025-09-24T23:28:18
Update to Unicode 17.0.0. * lib/gen-uni-tables.c (is_property_alphabetic): Add three YANGQIN SIGNs. (UC_JOINING_GROUP_THIN_NOON): New enum item. (fill_arabicshaping, joining_group_as_c_identifier): Handle UC_JOINING_GROUP_THIN_NOON. (LBP_*): Split LBP_SA into LBP_SA1 and LBP_SA2. (LBP_HH, LBP_SA): New enum items. (get_lbp): Use them. Update such that unilbrk/lbrkprop.txt comes out as expected. (debug_output_lbp): Handle LBP_HH. Print either LBP_SA1, LBP_SA2 as LBP_SA. (fill_org_lbp, debug_output_org_lbp): Handle LBP_HH. (lbp_value_to_string): Handle LBP_HH. Handle LBP_SA1, LBP_SA2 instead of LBP_SA. (output_lbrk_rules_as_tables): Update for LBP_HH change. Update rules LBP12a, LB21 as specified by https://www.unicode.org/reports/tr14/tr14-55.html. (get_wbp): Update such that uniwbrk/wbrkprop.txt comes out as expected. * lib/unictype.in.h (UC_JOINING_GROUP_THIN_NOON): New enum item. * lib/unictype/joininggroup_byname.gperf: Handle it. * lib/unictype/joininggroup_name.h: Likewise. * lib/unilbrk/lbrktables.h (LBP_*): Split LBP_SA into LBP_SA1 and LBP_SA2. (LBP_HH): New enum item. (unilbrk_table): Update bounds. * lib/unilbrk/u8-possible-linebreaks.c (u8_possible_linebreaks_loop): Use LBP_HL_HY instead of LBP_HL_BA. Use LBP_SA1 instead of LBP_SA. Treat LBP_SA2 like LBP_CM. Update rules LB20a and LB21a, as specified by https://www.unicode.org/reports/tr14/tr14-55.html. * lib/unilbrk/u16-possible-linebreaks.c (u16_possible_linebreaks_loop): Likewise. * lib/unilbrk/u32-possible-linebreaks.c (u32_possible_linebreaks_loop): Likewise. * tests/unigbrk/test-u8-grapheme-breaks.c (main): Use U+2B50 instead of U+2605, because U+2605 no longer is an Extended_Pictographic character. * tests/unigbrk/test-u16-grapheme-breaks.c (main): Likewise. * tests/unigbrk/test-u32-grapheme-breaks.c (main): Likewise. * tests/unigbrk/test-u8-grapheme-next.c (main): Likewise. * tests/unigbrk/test-u16-grapheme-next.c (main): Likewise. * tests/unigbrk/test-u32-grapheme-next.c (main): Likewise. * tests/unigbrk/test-u8-grapheme-prev.c (main): Likewise. * tests/unigbrk/test-u16-grapheme-prev.c (main): Likewise. * tests/unigbrk/test-u32-grapheme-prev.c (main): Likewise. * tests/uniwidth/test-uc_width2.sh: Update expected test result. * All generated files under lib/uni* and tests/uni*: Regenerate. * tests/uniname/NameAliases.txt: Update. * tests/uniname/UnicodeData.txt: Update. * tests/uninorm/NormalizationTest.txt: Update. * tests/unigbrk/GraphemeBreakTest.txt: Update. * tests/uniwbrk/WordBreakTest.txt: Update. * tests/unilbrk/LineBreakTest.txt: Update. * All the affected modules: Bump required libunistring version.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
/* Grapheme cluster breaks test.
Copyright (C) 2010-2025 Free Software Foundation, Inc.
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/>. */
/* Written by Ben Pfaff <blp@cs.stanford.edu>, 2010. */
#include <config.h>
/* Specification. */
#include <unigbrk.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "macros.h"
static void
test_u16_grapheme_breaks (const char *expected, ...)
{
size_t n = strlen (expected);
uint16_t s[16];
va_list args;
char breaks[16];
size_t i;
ASSERT (n <= 16);
memset (breaks, 0xcc, n);
va_start (args, expected);
for (i = 0; i < n; i++)
{
int unit = va_arg (args, int);
ASSERT (unit >= 0);
s[i] = unit;
}
ASSERT (va_arg (args, int) == -1);
va_end (args);
u16_grapheme_breaks (s, n, breaks);
for (i = 0; i < n; i++)
if (breaks[i] != (expected[i] == '#'))
{
size_t j;
fprintf (stderr, "wrong grapheme breaks:\n");
fprintf (stderr, " input:");
for (j = 0; j < n; j++)
fprintf (stderr, " %04X", s[j]);
putc ('\n', stderr);
fprintf (stderr, "expected:");
for (j = 0; j < n; j++)
fprintf (stderr, " %d", expected[j] == '#');
putc ('\n', stderr);
fprintf (stderr, " actual:");
for (j = 0; j < n; j++)
fprintf (stderr, " %d", breaks[j]);
putc ('\n', stderr);
fflush (stderr);
abort ();
}
}
int
main (void)
{
/* Standalone 1-unit graphemes. */
test_u16_grapheme_breaks ("#", 'a', -1);
test_u16_grapheme_breaks ("##", 'a', 'b', -1);
test_u16_grapheme_breaks ("###", 'a', 'b', 'c', -1);
#define HIRAGANA_A 0x3042 /* あ: Hiragana letter 'a'. */
test_u16_grapheme_breaks ("#", HIRAGANA_A, -1);
test_u16_grapheme_breaks ("##", HIRAGANA_A, 'x', -1);
test_u16_grapheme_breaks ("##", HIRAGANA_A, HIRAGANA_A, -1);
/* Combining accents. */
#define GRAVE 0x0300 /* Combining grave accent. */
#define ACUTE 0x0301 /* Combining acute accent. */
test_u16_grapheme_breaks ("#_", 'e', ACUTE, -1);
test_u16_grapheme_breaks ("#__", 'e', ACUTE, GRAVE, -1);
test_u16_grapheme_breaks ("#_#", 'e', ACUTE, 'x', -1);
test_u16_grapheme_breaks ("#_#_", 'e', ACUTE, 'e', GRAVE, -1);
/* CR LF handling. */
test_u16_grapheme_breaks ("######_#",
'a', '\n', 'b', '\r', 'c', '\r', '\n', 'd',
-1);
/* Emoji modifier / ZWJ sequence. */
test_u16_grapheme_breaks ("#____",
0x2B50, 0x0305, 0x0347, 0x200D, 0x2600,
-1);
/* Regional indicators. */
test_u16_grapheme_breaks ("##___#___#",
'.', 0xD83C, 0xDDE9, 0xD83C, 0xDDEA, 0xD83C, 0xDDEB, 0xD83C, 0xDDF7, '.',
-1);
return test_exit_status;
}