2009-03-08 Bruno Haible <bruno@clisp.org>
+ New module 'unicase/u8-casecmp'.
+ * lib/unicase/u8-casecmp.c: New file.
+ * lib/unicase/u-casecmp.h: New file.
+ * modules/unicase/u8-casecmp: New file.
+
Tests for module 'unicase/u32-casefold'.
* modules/unicase/u32-casefold-tests: New file.
* tests/unicase/test-u32-casefold.c: New file.
--- /dev/null
+/* Case and normalization insensitive comparison of Unicode 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/>. */
+
+int
+FUNC (const UNIT *s1, size_t n1, const UNIT *s2, size_t n2,
+ const char *iso639_language, uninorm_t nf, int *resultp)
+{
+ UNIT buf1[2048 / sizeof (UNIT)];
+ UNIT buf2[2048 / sizeof (UNIT)];
+ UNIT *norms1;
+ size_t norms1_length;
+ UNIT *norms2;
+ size_t norms2_length;
+ int cmp;
+
+ /* Optimization: There is no need to do canonical composition of each string.
+ Decomposition is enough. */
+ if (nf != NULL)
+ nf = uninorm_decomposing_form (nf);
+
+ /* Case-fold and normalize S1. */
+ norms1_length = sizeof (buf1) / sizeof (UNIT);
+ norms1 = U_CASEFOLD (s1, n1, iso639_language, nf, buf1, &norms1_length);
+ if (norms1 == NULL)
+ /* errno is set here. */
+ return -1;
+
+ /* Case-fold and normalize S2. */
+ norms2_length = sizeof (buf2) / sizeof (UNIT);
+ norms2 = U_CASEFOLD (s2, n2, iso639_language, nf, buf2, &norms2_length);
+ if (norms2 == NULL)
+ {
+ if (norms1 != buf1)
+ {
+ int saved_errno = errno;
+ free (norms1);
+ errno = saved_errno;
+ }
+ return -1;
+ }
+
+ /* Compare the normalized strings. */
+ cmp = U_CMP (norms1, norms2, MIN (norms1_length, norms2_length));
+ if (cmp == 0)
+ {
+ if (norms1_length < norms2_length)
+ cmp = -1;
+ else if (norms1_length > norms2_length)
+ cmp = 1;
+ }
+ else if (cmp > 0)
+ cmp = 1;
+ else if (cmp < 0)
+ cmp = -1;
+
+ if (norms2 != buf2)
+ free (norms2);
+ if (norms1 != buf1)
+ free (norms1);
+ *resultp = cmp;
+ return 0;
+}
--- /dev/null
+/* Case and normalization insensitive comparison of 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 "unicase.h"
+
+#include <errno.h>
+#include <stdlib.h>
+
+#include "minmax.h"
+#include "uninorm.h"
+#include "unistr.h"
+
+#define FUNC u8_casecmp
+#define UNIT uint8_t
+#define U_CASEFOLD u8_casefold
+#define U_CMP u8_cmp
+#include "u-casecmp.h"