1 /* Test of word breaks in UTF-8 strings.
2 Copyright (C) 2009-2012 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. */
30 /* Test case n = 0. */
31 u8_wordbreaks (NULL, 0, NULL);
34 static const uint8_t input[91] =
35 /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
36 "Gr\303\274\303\237 Gott. \320\227\320\264\321\200\320\260\320\262\321\201\321\202\320\262\321\203\320\271\321\202\320\265! x=(-b\302\261sqrt(b\302\262-4ac))/(2a) \346\227\245\346\234\254\350\252\236,\344\270\255\346\226\207,\355\225\234\352\270\200\n";
37 char *p = (char *) malloc (SIZEOF (input));
40 u8_wordbreaks (input, SIZEOF (input), p);
42 for (i = 0; i < 91; i++)
44 ASSERT (p[i] == ((i >= 6 && i <= 7)
45 || (i >= 11 && i <= 13)
46 || (i >= 37 && i <= 44)
47 || i == 46 || (i >= 50 && i <= 52)
48 || (i >= 54 && i <= 55)
49 || (i >= 58 && i <= 62) || (i >= 64 && i <= 67)
50 || i == 70 || i == 73 || i == 76
51 || i == 77 || i == 80 || i == 83
59 /* Same input string, decomposed. */
60 static const uint8_t input[106] =
61 /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
62 "Gru\314\210\303\237 Gott. \320\227\320\264\321\200\320\260\320\262\321\201\321\202\320\262\321\203\320\270\314\206\321\202\320\265! x=(-b\302\261sqrt(b\302\262-4ac))/(2a) \346\227\245\346\234\254\350\252\236,\344\270\255\346\226\207,\341\204\222\341\205\241\341\206\253\341\204\200\341\205\263\341\206\257\n";
63 char *p = (char *) malloc (SIZEOF (input));
66 u8_wordbreaks (input, SIZEOF (input), p);
68 for (i = 0; i < 106; i++)
70 ASSERT (p[i] == ((i >= 7 && i <= 8)
71 || (i >= 12 && i <= 14)
72 || (i >= 40 && i <= 47)
73 || i == 49 || (i >= 53 && i <= 55)
74 || (i >= 57 && i <= 58)
75 || (i >= 61 && i <= 65) || (i >= 67 && i <= 70)
76 || i == 73 || i == 76 || i == 79
77 || i == 80 || i == 83 || i == 86
78 || i == 87 || i == 105