summaryrefslogtreecommitdiff
path: root/include/linux/unicode.h
diff options
context:
space:
mode:
authorGabriel Krisman Bertazi <krisman@collabora.co.uk>2019-04-25 20:51:22 +0300
committerTheodore Ts'o <tytso@mit.edu>2019-04-25 20:51:22 +0300
commit9d53690f0d4e5686e80f034ea584b7a822b356d3 (patch)
treec123dcc3f2e193f584acc2560a1358d546e66810 /include/linux/unicode.h
parenta8384c68797ee022f5fd7bcef5f4cc57863d4042 (diff)
downloadlinux-9d53690f0d4e5686e80f034ea584b7a822b356d3.tar.xz
unicode: implement higher level API for string handling
This patch integrates the utf8n patches with some higher level API to perform UTF-8 string comparison, normalization and casefolding operations. Implemented is a variation of NFD, and casefold is performed by doing full casefold on top of NFD. These algorithms are based on the core implemented by Olaf Weber from SGI. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Diffstat (limited to 'include/linux/unicode.h')
-rw-r--r--include/linux/unicode.h30
1 files changed, 30 insertions, 0 deletions
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
new file mode 100644
index 000000000000..aec2c6d800aa
--- /dev/null
+++ b/include/linux/unicode.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNICODE_H
+#define _LINUX_UNICODE_H
+
+#include <linux/init.h>
+#include <linux/dcache.h>
+
+struct unicode_map {
+ const char *charset;
+ int version;
+};
+
+int utf8_validate(const struct unicode_map *um, const struct qstr *str);
+
+int utf8_strncmp(const struct unicode_map *um,
+ const struct qstr *s1, const struct qstr *s2);
+
+int utf8_strncasecmp(const struct unicode_map *um,
+ const struct qstr *s1, const struct qstr *s2);
+
+int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
+ unsigned char *dest, size_t dlen);
+
+int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
+ unsigned char *dest, size_t dlen);
+
+struct unicode_map *utf8_load(const char *version);
+void utf8_unload(struct unicode_map *um);
+
+#endif /* _LINUX_UNICODE_H */