summaryrefslogtreecommitdiff
path: root/lib/uniwbrk/u8-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 /lib/uniwbrk/u8-wordbreaks.c
Imported Upstream version 0.9.1upstream/0.9.1
Diffstat (limited to 'lib/uniwbrk/u8-wordbreaks.c')
-rw-r--r--lib/uniwbrk/u8-wordbreaks.c124
1 files changed, 124 insertions, 0 deletions
diff --git a/lib/uniwbrk/u8-wordbreaks.c b/lib/uniwbrk/u8-wordbreaks.c
new file mode 100644
index 00000000..59d2076d
--- /dev/null
+++ b/lib/uniwbrk/u8-wordbreaks.c
@@ -0,0 +1,124 @@
+/* Word breaks in UTF-8 strings.
+ Copyright (C) 2009 Free Software Foundation, Inc.
+ Written by Bruno Haible <bruno@clisp.org>, 2009.
+
+ This program is free software: you can redistribute it and/or modify it
+ under the terms of the GNU Lesser 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
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+#include <config.h>
+
+/* Specification. */
+#include "uniwbrk.h"
+
+#include <string.h>
+
+#include "unistr.h"
+#include "uniwbrk/wbrktable.h"
+
+#define FUNC u8_wordbreaks
+#define UNIT uint8_t
+#define U_MBTOUC_UNSAFE u8_mbtouc_unsafe
+#include "u-wordbreaks.h"
+
+
+#ifdef TEST
+
+#include <stdio.h>
+#include <stdlib.h>
+
+/* Read the contents of an input stream, and return it, terminated with a NUL
+ byte. */
+char *
+read_file (FILE *stream)
+{
+#define BUFSIZE 4096
+ char *buf = NULL;
+ int alloc = 0;
+ int size = 0;
+ int count;
+
+ while (! feof (stream))
+ {
+ if (size + BUFSIZE > alloc)
+ {
+ alloc = alloc + alloc / 2;
+ if (alloc < size + BUFSIZE)
+ alloc = size + BUFSIZE;
+ buf = realloc (buf, alloc);
+ if (buf == NULL)
+ {
+ fprintf (stderr, "out of memory\n");
+ exit (1);
+ }
+ }
+ count = fread (buf + size, 1, BUFSIZE, stream);
+ if (count == 0)
+ {
+ if (ferror (stream))
+ {
+ perror ("fread");
+ exit (1);
+ }
+ }
+ else
+ size += count;
+ }
+ buf = realloc (buf, size + 1);
+ if (buf == NULL)
+ {
+ fprintf (stderr, "out of memory\n");
+ exit (1);
+ }
+ buf[size] = '\0';
+ return buf;
+#undef BUFSIZE
+}
+
+int
+main (int argc, char * argv[])
+{
+ if (argc == 1)
+ {
+ /* Display all the word breaks in the input string. */
+ char *input = read_file (stdin);
+ int length = strlen (input);
+ char *breaks = malloc (length);
+ int i;
+
+ u8_wordbreaks ((uint8_t *) input, length, breaks);
+
+ for (i = 0; i < length; i++)
+ {
+ switch (breaks[i])
+ {
+ case 1:
+ /* U+2027 in UTF-8 encoding */
+ putc (0xe2, stdout); putc (0x80, stdout); putc (0xa7, stdout);
+ break;
+ case 0:
+ break;
+ default:
+ abort ();
+ }
+ putc (input[i], stdout);
+ }
+
+ free (breaks);
+
+ return 0;
+ }
+ else
+ return 1;
+}
+
+#endif /* TEST */