cifs_unicode.c | Explore in Territory

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *
 *   Copyright (c) International Business Machines  Corp., 2000,2009
 *   Modified by Steve French ([email protected])
 */
#include <linux/fs.h>
#include <linux/slab.h>
#include "cifs_fs_sb.h"
#include "cifs_unicode.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifs_debug.h"

int cifs_remap(struct cifs_sb_info *cifs_sb)
{ … }

/* Convert character using the SFU - "Services for Unix" remapping range */
static bool
convert_sfu_char(const __u16 src_char, char *target)
{ … }

/* Convert character using the SFM - "Services for Mac" remapping range */
static bool
convert_sfm_char(const __u16 src_char, char *target)
{ … }


/*
 * cifs_mapchar - convert a host-endian char to proper char in codepage
 * @target - where converted character should be copied
 * @src_char - 2 byte host-endian source character
 * @cp - codepage to which character should be converted
 * @map_type - How should the 7 NTFS/SMB reserved characters be mapped to UCS2?
 *
 * 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 __u16 *from, const struct nls_table *cp,
	     int maptype)
{ … }

/*
 * cifs_from_utf16 - 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 utf16le 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 UTF16-2. 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_utf16(char *to, const __le16 *from, int tolen, int fromlen,
		const struct nls_table *codepage, int map_type)
{ … }

/*
 * NAME:	cifs_strtoUTF16()
 *
 * FUNCTION:	Convert character string to unicode string
 *
 */
int
cifs_strtoUTF16(__le16 *to, const char *from, int len,
	      const struct nls_table *codepage)
{ … }

/*
 * cifs_utf16_bytes - how long will a string be after conversion?
 * @utf16 - pointer to input string
 * @maxbytes - don't go past this many bytes of input string
 * @codepage - destination codepage
 *
 * Walk a utf16le string and return the number of bytes that the string will
 * be after being converted to the given charset, not including any null
 * termination required. Don't walk past maxbytes in the source buffer.
 */
int
cifs_utf16_bytes(const __le16 *from, int maxbytes,
		const struct nls_table *codepage)
{ … }

/*
 * cifs_strndup_from_utf16 - copy a string from wire format to the local
 * codepage
 * @src - source string
 * @maxlen - don't walk past this many bytes in the source string
 * @is_unicode - is this a unicode string?
 * @codepage - destination codepage
 *
 * Take a string given by the server, convert it to the local codepage and
 * put it in a new buffer. Returns a pointer to the new string or NULL on
 * error.
 */
char *
cifs_strndup_from_utf16(const char *src, const int maxlen,
			const bool is_unicode, const struct nls_table *codepage)
{ … }

static __le16 convert_to_sfu_char(char src_char)
{ … }

static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
{ … }

/*
 * Convert 16 bit Unicode pathname to wire format from string in current code
 * page. Conversion may involve remapping up the six characters that are
 * only legal in POSIX-like OS (if they are present in the string). Path
 * names are little endian 16 bit Unicode on the wire
 */
int
cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
		 const struct nls_table *cp, int map_chars)
{ … }

/*
 * cifs_local_to_utf16_bytes - how long will a string be after conversion?
 * @from - pointer to input string
 * @maxbytes - don't go past this many bytes of input string
 * @codepage - source codepage
 *
 * Walk a string and return the number of bytes that the string will
 * be after being converted to the given charset, not including any null
 * termination required. Don't walk past maxbytes in the source buffer.
 */

static int
cifs_local_to_utf16_bytes(const char *from, int len,
			  const struct nls_table *codepage)
{ … }

/*
 * cifs_strndup_to_utf16 - copy a string to wire format from the local codepage
 * @src - source string
 * @maxlen - don't walk past this many bytes in the source string
 * @utf16_len - the length of the allocated string in bytes (including null)
 * @cp - source codepage
 * @remap - map special chars
 *
 * Take a string convert it from the local codepage to UTF16 and
 * put it in a new buffer. Returns a pointer to the new string or NULL on
 * error.
 */
__le16 *
cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len,
		      const struct nls_table *cp, int remap)
{ … }
linux/fs/smb/client/cifs_unicode.c
