1 /* Test of word breaks in UTF-8 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 u8_wordbreaks (NULL, 0, NULL);
46 static const uint8_t input[91] =
47 /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
48 "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";
49 char *p = (char *) malloc (SIZEOF (input));
52 u8_wordbreaks (input, SIZEOF (input), p);
54 for (i = 0; i < 91; i++)
56 ASSERT (p[i] == ((i >= 6 && i <= 7)
57 || (i >= 11 && i <= 13)
58 || (i >= 37 && i <= 44)
59 || i == 46 || (i >= 50 && i <= 52)
60 || (i >= 54 && i <= 55)
61 || (i >= 58 && i <= 62) || (i >= 64 && i <= 67)
62 || i == 70 || i == 73 || i == 76
63 || i == 77 || i == 80 || i == 83
71 /* Same input string, decomposed. */
72 static const uint8_t input[106] =
73 /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
74 "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";
75 char *p = (char *) malloc (SIZEOF (input));
78 u8_wordbreaks (input, SIZEOF (input), p);
80 for (i = 0; i < 106; i++)
82 ASSERT (p[i] == ((i >= 7 && i <= 8)
83 || (i >= 12 && i <= 14)
84 || (i >= 40 && i <= 47)
85 || i == 49 || (i >= 53 && i <= 55)
86 || (i >= 57 && i <= 58)
87 || (i >= 61 && i <= 65) || (i >= 67 && i <= 70)
88 || i == 73 || i == 76 || i == 79
89 || i == 80 || i == 83 || i == 86
90 || i == 87 || i == 105