From 9d53690f0d4e5686e80f034ea584b7a822b356d3 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 25 Apr 2019 13:51:22 -0400 Subject: 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 Signed-off-by: Theodore Ts'o --- include/linux/unicode.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 include/linux/unicode.h (limited to 'include/linux') 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 +#include + +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 */ -- cgit v1.2.3-59-g8ed1b