Tests for module 'uniwbrk/u8-wordbreaks'.

diff --git a/ChangeLog b/ChangeLog
index d7bc11a..8ff09b5 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,11 @@
 2009-02-10  Bruno Haible  <bruno@clisp.org>
 
+       Tests for module 'uniwbrk/u8-wordbreaks'.
+       * modules/uniwbrk/u8-wordbreaks-tests: New file.
+       * tests/uniwbrk/test-u8-wordbreaks.c: New file.
+
+2009-02-10  Bruno Haible  <bruno@clisp.org>
+
        * modules/uniwbrk/u8-wordbreaks (Depends-on): Add uniwbrk/wordbreak
        property.
        * modules/uniwbrk/u16-wordbreaks (Depends-on): Likewise.

diff --git a/modules/uniwbrk/u8-wordbreaks-tests b/modules/uniwbrk/u8-wordbreaks-tests
new file mode 100644 (file)
index 0000000..8d14157
--- /dev/null
+++ b/modules/uniwbrk/u8-wordbreaks-tests
@@ -0,0 +1,12 @@
+Files:
+tests/uniwbrk/test-u8-wordbreaks.c
+
+Depends-on:
+
+configure.ac:
+
+Makefile.am:
+TESTS += test-u8-wordbreaks
+check_PROGRAMS += test-u8-wordbreaks
+test_u8_wordbreaks_SOURCES = uniwbrk/test-u8-wordbreaks.c
+

diff --git a/tests/uniwbrk/test-u8-wordbreaks.c b/tests/uniwbrk/test-u8-wordbreaks.c
new file mode 100644 (file)
index 0000000..c263302
--- /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;
+}