1
0
mirror of https://github.com/samba-team/samba.git synced 2024-12-23 17:34:34 +03:00
samba-mirror/lib/ldb/common/ldb_utf8.c
Andreas Schneider 24275cd800 lib:ldb: Use ldb_ascii_toupper() for case folding
For example there are at least two locales (tr_TR and az_AZ) in glibc
having dotless i transformation different from Latin scripts and GUID
versus Guid comparison would be different there (attribute name would
not match in the test).

See also
https://en.wikipedia.org/wiki/Dotted_and_dotless_I
https://lists.samba.org/archive/samba-technical/2019-December/134659.html

This fixes: LC_ALL=tr_TR.UTF-8 make test

BUG: https://bugzilla.samba.org/show_bug.cgi?id=15248

Signed-off-by: Andreas Schneider <asn@samba.org>
Reviewed-by: Stefan Metzmacher <metze@samba.org>
2022-12-23 13:23:29 +00:00

141 lines
3.2 KiB
C

/*
ldb database library
Copyright (C) Andrew Tridgell 2004
** NOTE! The following LGPL license applies to the ldb
** library. This does NOT imply that all of Samba is released
** under the LGPL
This library 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 library 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 library; if not, see <http://www.gnu.org/licenses/>.
*/
/*
* Name: ldb
*
* Component: ldb utf8 handling
*
* Description: case folding and case comparison for UTF8 strings
*
* Author: Andrew Tridgell
*/
#include "ldb_private.h"
#include "system/locale.h"
/*
this allow the user to pass in a caseless comparison
function to handle utf8 caseless comparisons
*/
void ldb_set_utf8_fns(struct ldb_context *ldb,
void *context,
char *(*casefold)(void *, void *, const char *, size_t))
{
if (context)
ldb->utf8_fns.context = context;
if (casefold)
ldb->utf8_fns.casefold = casefold;
}
/*
a simple case folding function
NOTE: does not handle UTF8
*/
char *ldb_casefold_default(void *context, TALLOC_CTX *mem_ctx, const char *s, size_t n)
{
size_t i;
char *ret = talloc_strndup(mem_ctx, s, n);
if (!s) {
errno = ENOMEM;
return NULL;
}
for (i=0;ret[i];i++) {
ret[i] = ldb_ascii_toupper((unsigned char)ret[i]);
}
return ret;
}
void ldb_set_utf8_default(struct ldb_context *ldb)
{
ldb_set_utf8_fns(ldb, NULL, ldb_casefold_default);
}
char *ldb_casefold(struct ldb_context *ldb, TALLOC_CTX *mem_ctx, const char *s, size_t n)
{
return ldb->utf8_fns.casefold(ldb->utf8_fns.context, mem_ctx, s, n);
}
/*
check the attribute name is valid according to rfc2251
returns 1 if the name is ok
*/
int ldb_valid_attr_name(const char *s)
{
size_t i;
if (!s || !s[0])
return 0;
/* handle special ldb_tdb wildcard */
if (strcmp(s, "*") == 0) return 1;
for (i = 0; s[i]; i++) {
if (! isascii(s[i])) {
return 0;
}
if (i == 0) { /* first char must be an alpha (or our special '@' identifier) */
if (! (isalpha(s[i]) || (s[i] == '@'))) {
return 0;
}
} else {
if (! (isalnum(s[i]) || (s[i] == '-'))) {
return 0;
}
}
}
return 1;
}
char *ldb_attr_casefold(TALLOC_CTX *mem_ctx, const char *s)
{
size_t i;
char *ret = talloc_strdup(mem_ctx, s);
if (!ret) {
errno = ENOMEM;
return NULL;
}
for (i = 0; ret[i]; i++) {
ret[i] = ldb_ascii_toupper((unsigned char)ret[i]);
}
return ret;
}
/*
we accept either 'dn' or 'distinguishedName' for a distinguishedName
*/
int ldb_attr_dn(const char *attr)
{
if (ldb_attr_cmp(attr, "dn") == 0 ||
ldb_attr_cmp(attr, "distinguishedName") == 0) {
return 0;
}
return -1;
}
_PRIVATE_ char ldb_ascii_toupper(char c) {
return ('a' <= c && c <= 'z') ? c ^ 0x20 : toupper(c);
}