summaryrefslogtreecommitdiffstats
path: root/lib/sh/mbschr.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 15:38:56 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 15:38:56 +0000
commit6c20c8ed2cb9ab69a1a57ccb2b9b79969a808321 (patch)
treef63ce19d57fad3ac4a15bc26dbfbfa2b834111b5 /lib/sh/mbschr.c
parentInitial commit. (diff)
downloadbash-upstream.tar.xz
bash-upstream.zip
Adding upstream version 5.2.15.upstream/5.2.15upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'lib/sh/mbschr.c')
-rw-r--r--lib/sh/mbschr.c91
1 files changed, 91 insertions, 0 deletions
diff --git a/lib/sh/mbschr.c b/lib/sh/mbschr.c
new file mode 100644
index 0000000..639962d
--- /dev/null
+++ b/lib/sh/mbschr.c
@@ -0,0 +1,91 @@
+/* mbschr.c - strchr(3) that handles multibyte characters. */
+
+/* Copyright (C) 2002 Free Software Foundation, Inc.
+
+ This file is part of GNU Bash, the Bourne Again SHell.
+
+ Bash 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.
+
+ Bash 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 Bash. If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <config.h>
+
+#ifdef HAVE_STDLIB_H
+# include <stdlib.h>
+#endif
+
+#include "bashansi.h"
+#include "shmbutil.h"
+
+extern int locale_mb_cur_max;
+extern int locale_utf8locale;
+
+#undef mbschr
+
+extern char *utf8_mbschr (const char *, int); /* XXX */
+
+/* In some locales, the non-first byte of some multibyte characters have
+ the same value as some ascii character. Faced with these strings, a
+ legacy strchr() might return the wrong value. */
+
+char *
+#if defined (PROTOTYPES)
+mbschr (const char *s, int c)
+#else
+mbschr (s, c)
+ const char *s;
+ int c;
+#endif
+{
+#if HANDLE_MULTIBYTE
+ char *pos;
+ mbstate_t state;
+ size_t strlength, mblength;
+
+ if (locale_utf8locale && c < 0x80)
+ return (utf8_mbschr (s, c)); /* XXX */
+
+ /* The locale encodings with said weird property are BIG5, BIG5-HKSCS,
+ GBK, GB18030, SHIFT_JIS, and JOHAB. They exhibit the problem only
+ when c >= 0x30. We can therefore use the faster bytewise search if
+ c <= 0x30. */
+ if ((unsigned char)c >= '0' && locale_mb_cur_max > 1)
+ {
+ pos = (char *)s;
+ memset (&state, '\0', sizeof(mbstate_t));
+ strlength = strlen (s);
+
+ while (strlength > 0)
+ {
+ if (is_basic (*pos))
+ mblength = 1;
+ else
+ {
+ mblength = mbrlen (pos, strlength, &state);
+ if (mblength == (size_t)-2 || mblength == (size_t)-1 || mblength == (size_t)0)
+ mblength = 1;
+ }
+
+ if (mblength == 1 && c == (unsigned char)*pos)
+ return pos;
+
+ strlength -= mblength;
+ pos += mblength;
+ }
+
+ return ((char *)NULL);
+ }
+ else
+#endif
+ return (strchr (s, c));
+}