1 /* Test of word breaks in UTF-32 strings.
2 Copyright (C) 2009 Free Software Foundation, Inc.
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation; either version 3 of the License, or
7 (at your option) any later version.
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <http://www.gnu.org/licenses/>. */
17 /* Written by Bruno Haible <bruno@clisp.org>, 2009. */
26 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
27 #define ASSERT(expr) \
32 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
42 /* Test case n = 0. */
43 u32_wordbreaks (NULL, 0, NULL);
46 static const uint32_t input[61] =
47 /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
48 { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
49 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
50 0x0439, 0x0442, 0x0435, '!', ' ',
51 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
52 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
53 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
55 char *p = (char *) malloc (SIZEOF (input));
58 u32_wordbreaks (input, SIZEOF (input), p);
60 for (i = 0; i < 61; i++)
62 ASSERT (p[i] == ((i >= 4 && i <= 5)
63 || (i >= 9 && i <= 11)
64 || (i >= 23 && i <= 31)
65 || (i >= 35 && i <= 39)
66 || (i >= 42 && i <= 46)
67 || (i >= 48 && i <= 58)
75 /* Same input string, decomposed. */
76 static const uint32_t input[67] =
77 /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
78 { 'G', 'r', 0x0075, 0x0308, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
79 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
80 0x0438, 0x0306, 0x0442, 0x0435, '!', ' ',
81 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
82 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
83 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',',
84 0x1112, 0x1161, 0x11AB, 0x1100, 0x1173, 0x11AF, '\n'
86 char *p = (char *) malloc (SIZEOF (input));
89 u32_wordbreaks (input, SIZEOF (input), p);
91 for (i = 0; i < 67; i++)
93 ASSERT (p[i] == ((i >= 5 && i <= 6)
94 || (i >= 10 && i <= 12)
95 || (i >= 25 && i <= 33)
96 || (i >= 37 && i <= 41)
97 || (i >= 44 && i <= 48)
98 || (i >= 50 && i <= 60)