summaryrefslogtreecommitdiff
path: root/tests/uniwbrk/test-u16-wordbreaks.c
diff options
context:
space:
mode:
authorAndreas Rottmann <a.rottmann@gmx.at>2009-09-14 12:32:44 +0200
committerAndreas Rottmann <a.rottmann@gmx.at>2009-09-14 12:32:44 +0200
commitfa095a4504cbe668e4244547e2c141597bea4ecf (patch)
tree06135820a286ffec47804e75fbf8a147e92acd2e /tests/uniwbrk/test-u16-wordbreaks.c
Imported Upstream version 0.9.1upstream/0.9.1
Diffstat (limited to 'tests/uniwbrk/test-u16-wordbreaks.c')
-rw-r--r--tests/uniwbrk/test-u16-wordbreaks.c106
1 files changed, 106 insertions, 0 deletions
diff --git a/tests/uniwbrk/test-u16-wordbreaks.c b/tests/uniwbrk/test-u16-wordbreaks.c
new file mode 100644
index 00000000..b5eb26cd
--- /dev/null
+++ b/tests/uniwbrk/test-u16-wordbreaks.c
@@ -0,0 +1,106 @@
+/* Test of word breaks in UTF-16 strings.
+ Copyright (C) 2009 Free Software Foundation, Inc.
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU 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 General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+/* Written by Bruno Haible <bruno@clisp.org>, 2009. */
+
+#include <config.h>
+
+#include "uniwbrk.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
+#define ASSERT(expr) \
+ do \
+ { \
+ if (!(expr)) \
+ { \
+ fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
+ fflush (stderr); \
+ abort (); \
+ } \
+ } \
+ while (0)
+
+int
+main ()
+{
+ /* Test case n = 0. */
+ u16_wordbreaks (NULL, 0, NULL);
+
+ {
+ static const uint16_t input[61] =
+ /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
+ { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
+ 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
+ 0x0439, 0x0442, 0x0435, '!', ' ',
+ 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
+ '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
+ 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
+ };
+ char *p = (char *) malloc (SIZEOF (input));
+ size_t i;
+
+ u16_wordbreaks (input, SIZEOF (input), p);
+
+ for (i = 0; i < 61; i++)
+ {
+ ASSERT (p[i] == ((i >= 4 && i <= 5)
+ || (i >= 9 && i <= 11)
+ || (i >= 23 && i <= 31)
+ || (i >= 35 && i <= 39)
+ || (i >= 42 && i <= 46)
+ || (i >= 48 && i <= 58)
+ || i == 60
+ ? 1 : 0));
+ }
+ free (p);
+ }
+
+ {
+ /* Same input string, decomposed. */
+ static const uint16_t input[67] =
+ /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
+ { 'G', 'r', 0x0075, 0x0308, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
+ 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
+ 0x0438, 0x0306, 0x0442, 0x0435, '!', ' ',
+ 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
+ '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
+ 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',',
+ 0x1112, 0x1161, 0x11AB, 0x1100, 0x1173, 0x11AF, '\n'
+ };
+ char *p = (char *) malloc (SIZEOF (input));
+ size_t i;
+
+ u16_wordbreaks (input, SIZEOF (input), p);
+
+ for (i = 0; i < 67; i++)
+ {
+ ASSERT (p[i] == ((i >= 5 && i <= 6)
+ || (i >= 10 && i <= 12)
+ || (i >= 25 && i <= 33)
+ || (i >= 37 && i <= 41)
+ || (i >= 44 && i <= 48)
+ || (i >= 50 && i <= 60)
+ || i == 66
+ ? 1 : 0));
+ }
+ free (p);
+ }
+
+ return 0;
+}