2005-04-16 15:20:36 -07:00
|
|
|
/*
|
|
|
|
* fs/cifs/cifs_unicode.c
|
|
|
|
*
|
2005-11-11 16:18:19 -07:00
|
|
|
* Copyright (c) International Business Machines Corp., 2000,2005
|
2005-04-16 15:20:36 -07:00
|
|
|
* Modified by Steve French (sfrench@us.ibm.com)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
2007-06-05 13:35:06 -07:00
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
2005-04-16 15:20:36 -07:00
|
|
|
* (at your option) any later version.
|
2007-06-05 13:35:06 -07:00
|
|
|
*
|
2005-04-16 15:20:36 -07:00
|
|
|
* 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 General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
2007-06-05 13:35:06 -07:00
|
|
|
* along with this program; if not, write to the Free Software
|
2005-04-16 15:20:36 -07:00
|
|
|
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include "cifs_unicode.h"
|
|
|
|
#include "cifs_uniupr.h"
|
|
|
|
#include "cifspdu.h"
|
2006-05-31 15:40:51 -07:00
|
|
|
#include "cifsglob.h"
|
2005-04-16 15:20:36 -07:00
|
|
|
#include "cifs_debug.h"
|
|
|
|
|
2009-04-30 03:46:15 -07:00
|
|
|
/*
|
|
|
|
* cifs_mapchar - convert a little-endian char to proper char in codepage
|
|
|
|
* @target - where converted character should be copied
|
|
|
|
* @src_char - 2 byte little-endian source character
|
|
|
|
* @cp - codepage to which character should be converted
|
|
|
|
* @mapchar - should character be mapped according to mapchars mount option?
|
|
|
|
*
|
|
|
|
* This function handles the conversion of a single character. It is the
|
|
|
|
* responsibility of the caller to ensure that the target buffer is large
|
|
|
|
* enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
|
|
|
|
*/
|
|
|
|
static int
|
|
|
|
cifs_mapchar(char *target, const __le16 src_char, const struct nls_table *cp,
|
|
|
|
bool mapchar)
|
|
|
|
{
|
|
|
|
int len = 1;
|
|
|
|
|
|
|
|
if (!mapchar)
|
|
|
|
goto cp_convert;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* BB: Cannot handle remapping UNI_SLASH until all the calls to
|
|
|
|
* build_path_from_dentry are modified, as they use slash as
|
|
|
|
* separator.
|
|
|
|
*/
|
|
|
|
switch (le16_to_cpu(src_char)) {
|
|
|
|
case UNI_COLON:
|
|
|
|
*target = ':';
|
|
|
|
break;
|
|
|
|
case UNI_ASTERIK:
|
|
|
|
*target = '*';
|
|
|
|
break;
|
|
|
|
case UNI_QUESTION:
|
|
|
|
*target = '?';
|
|
|
|
break;
|
|
|
|
case UNI_PIPE:
|
|
|
|
*target = '|';
|
|
|
|
break;
|
|
|
|
case UNI_GRTRTHAN:
|
|
|
|
*target = '>';
|
|
|
|
break;
|
|
|
|
case UNI_LESSTHAN:
|
|
|
|
*target = '<';
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
goto cp_convert;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
return len;
|
|
|
|
|
|
|
|
cp_convert:
|
|
|
|
len = cp->uni2char(le16_to_cpu(src_char), target,
|
|
|
|
NLS_MAX_CHARSET_SIZE);
|
|
|
|
if (len <= 0) {
|
|
|
|
*target = '?';
|
|
|
|
len = 1;
|
|
|
|
}
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* cifs_from_ucs2 - convert utf16le string to local charset
|
|
|
|
* @to - destination buffer
|
|
|
|
* @from - source buffer
|
|
|
|
* @tolen - destination buffer size (in bytes)
|
|
|
|
* @fromlen - source buffer size (in bytes)
|
|
|
|
* @codepage - codepage to which characters should be converted
|
|
|
|
* @mapchar - should characters be remapped according to the mapchars option?
|
|
|
|
*
|
|
|
|
* Convert a little-endian ucs2le string (as sent by the server) to a string
|
|
|
|
* in the provided codepage. The tolen and fromlen parameters are to ensure
|
|
|
|
* that the code doesn't walk off of the end of the buffer (which is always
|
|
|
|
* a danger if the alignment of the source buffer is off). The destination
|
|
|
|
* string is always properly null terminated and fits in the destination
|
|
|
|
* buffer. Returns the length of the destination string in bytes (including
|
|
|
|
* null terminator).
|
|
|
|
*
|
|
|
|
* Note that some windows versions actually send multiword UTF-16 characters
|
|
|
|
* instead of straight UCS-2. The linux nls routines however aren't able to
|
|
|
|
* deal with those characters properly. In the event that we get some of
|
|
|
|
* those characters, they won't be translated properly.
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
|
|
|
|
const struct nls_table *codepage, bool mapchar)
|
|
|
|
{
|
|
|
|
int i, charlen, safelen;
|
|
|
|
int outlen = 0;
|
|
|
|
int nullsize = nls_nullsize(codepage);
|
|
|
|
int fromwords = fromlen / 2;
|
|
|
|
char tmp[NLS_MAX_CHARSET_SIZE];
|
|
|
|
|
|
|
|
/*
|
|
|
|
* because the chars can be of varying widths, we need to take care
|
|
|
|
* not to overflow the destination buffer when we get close to the
|
|
|
|
* end of it. Until we get to this offset, we don't need to check
|
|
|
|
* for overflow however.
|
|
|
|
*/
|
|
|
|
safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);
|
|
|
|
|
|
|
|
for (i = 0; i < fromwords && from[i]; i++) {
|
|
|
|
/*
|
|
|
|
* check to see if converting this character might make the
|
|
|
|
* conversion bleed into the null terminator
|
|
|
|
*/
|
|
|
|
if (outlen >= safelen) {
|
|
|
|
charlen = cifs_mapchar(tmp, from[i], codepage, mapchar);
|
|
|
|
if ((outlen + charlen) > (tolen - nullsize))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* put converted char into 'to' buffer */
|
|
|
|
charlen = cifs_mapchar(&to[outlen], from[i], codepage, mapchar);
|
|
|
|
outlen += charlen;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* properly null-terminate string */
|
|
|
|
for (i = 0; i < nullsize; i++)
|
|
|
|
to[outlen++] = 0;
|
|
|
|
|
|
|
|
return outlen;
|
|
|
|
}
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
/*
|
|
|
|
* NAME: cifs_strfromUCS()
|
|
|
|
*
|
|
|
|
* FUNCTION: Convert little-endian unicode string to character string
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
int
|
2008-02-07 16:25:02 -07:00
|
|
|
cifs_strfromUCS_le(char *to, const __le16 *from,
|
2005-04-16 15:20:36 -07:00
|
|
|
int len, const struct nls_table *codepage)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
int outlen = 0;
|
|
|
|
|
|
|
|
for (i = 0; (i < len) && from[i]; i++) {
|
|
|
|
int charlen;
|
|
|
|
/* 2.4.0 kernel or greater */
|
|
|
|
charlen =
|
|
|
|
codepage->uni2char(le16_to_cpu(from[i]), &to[outlen],
|
|
|
|
NLS_MAX_CHARSET_SIZE);
|
|
|
|
if (charlen > 0) {
|
|
|
|
outlen += charlen;
|
|
|
|
} else {
|
|
|
|
to[outlen++] = '?';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
to[outlen] = 0;
|
|
|
|
return outlen;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* NAME: cifs_strtoUCS()
|
|
|
|
*
|
|
|
|
* FUNCTION: Convert character string to unicode string
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
int
|
2008-02-07 16:25:02 -07:00
|
|
|
cifs_strtoUCS(__le16 *to, const char *from, int len,
|
2005-04-16 15:20:36 -07:00
|
|
|
const struct nls_table *codepage)
|
|
|
|
{
|
|
|
|
int charlen;
|
|
|
|
int i;
|
2007-07-12 17:33:32 -07:00
|
|
|
wchar_t *wchar_to = (wchar_t *)to; /* needed to quiet sparse */
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
|
|
|
|
|
|
|
|
/* works for 2.4.0 kernel or later */
|
2005-11-11 16:18:19 -07:00
|
|
|
charlen = codepage->char2uni(from, len, &wchar_to[i]);
|
2005-04-16 15:20:36 -07:00
|
|
|
if (charlen < 1) {
|
|
|
|
cERROR(1,
|
2007-04-04 10:10:24 -07:00
|
|
|
("strtoUCS: char2uni of %d returned %d",
|
|
|
|
(int)*from, charlen));
|
2005-11-10 20:28:44 -07:00
|
|
|
/* A question mark */
|
2005-11-11 16:18:19 -07:00
|
|
|
to[i] = cpu_to_le16(0x003f);
|
2005-04-16 15:20:36 -07:00
|
|
|
charlen = 1;
|
2007-06-05 13:35:06 -07:00
|
|
|
} else
|
2005-11-11 16:18:19 -07:00
|
|
|
to[i] = cpu_to_le16(wchar_to[i]);
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
to[i] = 0;
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
|