summaryrefslogtreecommitdiff
path: root/tests/uniwbrk
diff options
context:
space:
mode:
Diffstat (limited to 'tests/uniwbrk')
-rw-r--r--tests/uniwbrk/test-u16-wordbreaks.c106
-rw-r--r--tests/uniwbrk/test-u32-wordbreaks.c106
-rw-r--r--tests/uniwbrk/test-u8-wordbreaks.c97
-rw-r--r--tests/uniwbrk/test-ulc-wordbreaks.c74
-rwxr-xr-xtests/uniwbrk/test-ulc-wordbreaks.sh15
5 files changed, 398 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;
+}
diff --git a/tests/uniwbrk/test-u32-wordbreaks.c b/tests/uniwbrk/test-u32-wordbreaks.c
new file mode 100644
index 00000000..c6feb84f
--- /dev/null
+++ b/tests/uniwbrk/test-u32-wordbreaks.c
@@ -0,0 +1,106 @@
+/* Test of word breaks in UTF-32 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. */
+ u32_wordbreaks (NULL, 0, NULL);
+
+ {
+ static const uint32_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;
+
+ u32_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 uint32_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;
+
+ u32_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;
+}
diff --git a/tests/uniwbrk/test-u8-wordbreaks.c b/tests/uniwbrk/test-u8-wordbreaks.c
new file mode 100644
index 00000000..c2633025
--- /dev/null
+++ b/tests/uniwbrk/test-u8-wordbreaks.c
@@ -0,0 +1,97 @@
+/* Test of word breaks in UTF-8 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. */
+ u8_wordbreaks (NULL, 0, NULL);
+
+ {
+ static const uint8_t input[91] =
+ /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
+ "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";
+ char *p = (char *) malloc (SIZEOF (input));
+ size_t i;
+
+ u8_wordbreaks (input, SIZEOF (input), p);
+
+ for (i = 0; i < 91; i++)
+ {
+ ASSERT (p[i] == ((i >= 6 && i <= 7)
+ || (i >= 11 && i <= 13)
+ || (i >= 37 && i <= 44)
+ || i == 46 || (i >= 50 && i <= 52)
+ || (i >= 54 && i <= 55)
+ || (i >= 58 && i <= 62) || (i >= 64 && i <= 67)
+ || i == 70 || i == 73 || i == 76
+ || i == 77 || i == 80 || i == 83
+ || i == 84 || i == 90
+ ? 1 : 0));
+ }
+ free (p);
+ }
+
+ {
+ /* Same input string, decomposed. */
+ static const uint8_t input[106] =
+ /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
+ "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";
+ char *p = (char *) malloc (SIZEOF (input));
+ size_t i;
+
+ u8_wordbreaks (input, SIZEOF (input), p);
+
+ for (i = 0; i < 106; i++)
+ {
+ ASSERT (p[i] == ((i >= 7 && i <= 8)
+ || (i >= 12 && i <= 14)
+ || (i >= 40 && i <= 47)
+ || i == 49 || (i >= 53 && i <= 55)
+ || (i >= 57 && i <= 58)
+ || (i >= 61 && i <= 65) || (i >= 67 && i <= 70)
+ || i == 73 || i == 76 || i == 79
+ || i == 80 || i == 83 || i == 86
+ || i == 87 || i == 105
+ ? 1 : 0));
+ }
+ free (p);
+ }
+
+ return 0;
+}
diff --git a/tests/uniwbrk/test-ulc-wordbreaks.c b/tests/uniwbrk/test-ulc-wordbreaks.c
new file mode 100644
index 00000000..80284ab2
--- /dev/null
+++ b/tests/uniwbrk/test-ulc-wordbreaks.c
@@ -0,0 +1,74 @@
+/* Test of word breaks in 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 <locale.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 ()
+{
+ /* configure should already have checked that the locale is supported. */
+ if (setlocale (LC_ALL, "") == NULL)
+ return 1;
+
+ /* Test case n = 0. */
+ ulc_wordbreaks (NULL, 0, NULL);
+
+#if HAVE_ICONV
+ {
+ static const char input[36] =
+ /* "Grüß Gott. x=(-b±sqrt(b²-4ac))/(2a)" */
+ "Gr\374\337 Gott. x=(-b\261sqrt(b\262-4ac))/(2a)\n";
+ char *p = (char *) malloc (SIZEOF (input));
+ size_t i;
+
+ ulc_wordbreaks (input, SIZEOF (input), p);
+
+ for (i = 0; i < 36; i++)
+ {
+ ASSERT (p[i] == ((i >= 4 && i <= 5)
+ || (i >= 9 && i <= 17)
+ || (i >= 21 && i <= 25)
+ || (i >= 28 && i <= 32)
+ || (i >= 34 && i <= 35)
+ ? 1 : 0));
+ }
+ free (p);
+ }
+#endif
+
+ return 0;
+}
diff --git a/tests/uniwbrk/test-ulc-wordbreaks.sh b/tests/uniwbrk/test-ulc-wordbreaks.sh
new file mode 100755
index 00000000..96bae501
--- /dev/null
+++ b/tests/uniwbrk/test-ulc-wordbreaks.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+
+# Test in an ISO-8859-1 or ISO-8859-15 locale.
+: ${LOCALE_FR=fr_FR}
+if test $LOCALE_FR = none; then
+ if test -f /usr/bin/localedef; then
+ echo "Skipping test: no traditional french locale is installed"
+ else
+ echo "Skipping test: no traditional french locale is supported"
+ fi
+ exit 77
+fi
+
+LC_ALL=$LOCALE_FR \
+./test-ulc-wordbreaks${EXEEXT}