util_unistr.c

samba-3.0.22.tar.gz 编译smb服务器的源码

/* 
   Unix SMB/CIFS implementation.
   Samba utility functions
   Copyright (C) Andrew Tridgell 1992-2001
   Copyright (C) Simo Sorce 2001
   Copyright (C) Jeremy Allison 2005
   
   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
   the Free Software Foundation; either version 2 of the License, or
   (at your option) any later version.
   
   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
   along with this program; if not, write to the Free Software
   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

#include "includes.h"

#ifndef MAXUNI
#define MAXUNI 1024
#endif

/* these 3 tables define the unicode case handling.  They are loaded
   at startup either via mmap() or read() from the lib directory */
static smb_ucs2_t *upcase_table;
static smb_ucs2_t *lowcase_table;
static uint8 *valid_table;

/**
 * This table says which Unicode characters are valid dos
 * characters.
 *
 * Each value is just a single bit.
 **/
static uint8 doschar_table[8192]; /* 65536 characters / 8 bits/byte */


/**
 * Load or generate the case handling tables.
 *
 * The case tables are defined in UCS2 and don't depend on any
 * configured parameters, so they never need to be reloaded.
 **/

void load_case_tables(void)
{
	static int initialised;
	int i;

	if (initialised) {
		return;
	}
	initialised = 1;

	upcase_table = map_file(lib_path("upcase.dat"), 0x20000);
	lowcase_table = map_file(lib_path("lowcase.dat"), 0x20000);

	/* we would like Samba to limp along even if these tables are
	   not available */
	if (!upcase_table) {
		DEBUG(1,("creating lame upcase table\n"));
		upcase_table = SMB_MALLOC(0x20000);
		for (i=0;i<0x10000;i++) {
			smb_ucs2_t v;
			SSVAL(&v, 0, i);
			upcase_table[v] = i;
		}
		for (i=0;i<256;i++) {
			smb_ucs2_t v;
			SSVAL(&v, 0, UCS2_CHAR(i));
			upcase_table[v] = UCS2_CHAR(islower(i)?toupper(i):i);
		}
	}

	if (!lowcase_table) {
		DEBUG(1,("creating lame lowcase table\n"));
		lowcase_table = SMB_MALLOC(0x20000);
		for (i=0;i<0x10000;i++) {
			smb_ucs2_t v;
			SSVAL(&v, 0, i);
			lowcase_table[v] = i;
		}
		for (i=0;i<256;i++) {
			smb_ucs2_t v;
			SSVAL(&v, 0, UCS2_CHAR(i));
			lowcase_table[v] = UCS2_CHAR(isupper(i)?tolower(i):i);
		}
	}
}

/*
  see if a ucs2 character can be mapped correctly to a dos character
  and mapped back to the same character in ucs2
*/

int check_dos_char(smb_ucs2_t c)
{
	lazy_initialize_conv();
	
	/* Find the right byte, and right bit within the byte; return
	 * 1 or 0 */
	return (doschar_table[(c & 0xffff) / 8] & (1 << (c & 7))) != 0;
}


static int check_dos_char_slowly(smb_ucs2_t c)
{
	char buf[10];
	smb_ucs2_t c2 = 0;
	int len1, len2;

	len1 = convert_string(CH_UCS2, CH_DOS, &c, 2, buf, sizeof(buf),False);
	if (len1 == 0) {
		return 0;
	}
	len2 = convert_string(CH_DOS, CH_UCS2, buf, len1, &c2, 2,False);
	if (len2 != 2) {
		return 0;
	}
	return (c == c2);
}


/**
 * Fill out doschar table the hard way, by examining each character
 **/

void init_doschar_table(void)
{
	int i, j, byteval;

	/* For each byte of packed table */
	
	for (i = 0; i <= 0xffff; i += 8) {
		byteval = 0;
		for (j = 0; j <= 7; j++) {
			smb_ucs2_t c;

			c = i + j;
			
			if (check_dos_char_slowly(c)) {
				byteval |= 1 << j;
			}
		}
		doschar_table[i/8] = byteval;
	}
}


/**
 * Load the valid character map table from <tt>valid.dat</tt> or
 * create from the configured codepage.
 *
 * This function is called whenever the configuration is reloaded.
 * However, the valid character table is not changed if it's loaded
 * from a file, because we can't unmap files.
 **/

void init_valid_table(void)
{
	static int mapped_file;
	int i;
	const char *allowed = ".!#$%&'()_-@^`~";
	uint8 *valid_file;

	if (mapped_file) {
		/* Can't unmap files, so stick with what we have */
		return;
	}

	valid_file = map_file(lib_path("valid.dat"), 0x10000);
	if (valid_file) {
		valid_table = valid_file;
		mapped_file = 1;
		return;
	}

	/* Otherwise, we're using a dynamically created valid_table.
	 * It might need to be regenerated if the code page changed.
	 * We know that we're not using a mapped file, so we can
	 * free() the old one. */
	if (valid_table) free(valid_table);

	DEBUG(2,("creating default valid table\n"));
	valid_table = SMB_MALLOC(0x10000);
	for (i=0;i<128;i++) {
		valid_table[i] = isalnum(i) || strchr(allowed,i);
	}
	
	for (;i<0x10000;i++) {
		smb_ucs2_t c;
		SSVAL(&c, 0, i);
		valid_table[i] = check_dos_char(c);
	}
}

/*******************************************************************
 Write a string in (little-endian) unicode format. src is in
 the current DOS codepage. len is the length in bytes of the
 string pointed to by dst.

 if null_terminate is True then null terminate the packet (adds 2 bytes)

 the return value is the length in bytes consumed by the string, including the
 null termination if applied
********************************************************************/

size_t dos_PutUniCode(char *dst,const char *src, ssize_t len, BOOL null_terminate)
{
	int flags = null_terminate ? STR_UNICODE|STR_NOALIGN|STR_TERMINATE
				   : STR_UNICODE|STR_NOALIGN;
	return push_ucs2(NULL, dst, src, len, flags);
}


/*******************************************************************
 Skip past a unicode string, but not more than len. Always move
 past a terminating zero if found.
********************************************************************/

char *skip_unibuf(char *src, size_t len)
{
	char *srcend = src + len;

	while (src < srcend && SVAL(src,0)) {
		src += 2;
	}

	if(!SVAL(src,0)) {
		src += 2;
	}

	return src;
}

/* Copy a string from little-endian or big-endian unicode source (depending
 * on flags) to internal samba format destination
 */ 

int rpcstr_pull(char* dest, void *src, int dest_len, int src_len, int flags)
{
	if (!src) {
		dest[0] = 0;
		return 0;
	}
	if(dest_len==-1) {
		dest_len=MAXUNI-3;
	}
	return pull_ucs2(NULL, dest, src, dest_len, src_len, flags|STR_UNICODE|STR_NOALIGN);
}

/* Copy a string from a unistr2 source to internal samba format
   destination.  Use this instead of direct calls to rpcstr_pull() to avoid
   having to determine whether the source string is null terminated. */

int rpcstr_pull_unistr2_fstring(char *dest, UNISTR2 *src)
{
        return pull_ucs2(NULL, dest, src->buffer, sizeof(fstring),
                         src->uni_str_len * 2, 0);
}

/* Helper function to return a talloc'ed string. I have implemented it with a
 * copy because I don't really know how pull_ucs2 and friends calculate the
 * target size. If this turns out to be a major bottleneck someone with deeper
 * multi-byte knowledge needs to revisit this.
 * My (VL) use is dsr_getdcname, which returns 6 strings, the alternative would
 * have been to manually talloc_strdup them in rpc_client/cli_netlogon.c.
 */

size_t rpcstr_pull_unistr2_talloc(TALLOC_CTX *mem_ctx, char **dest,
				  UNISTR2 *src)
{
	pstring tmp;
	size_t result;

	result = pull_ucs2(NULL, tmp, src->buffer, sizeof(tmp),
			   src->uni_str_len * 2, 0);
	if (result < 0) {
		return result;
	}

	*dest = talloc_strdup(mem_ctx, tmp);
	if (*dest == NULL) {
		return -1;
	}

	return result;
}

/* Converts a string from internal samba format to unicode
 */ 

int rpcstr_push(void* dest, const char *src, int dest_len, int flags)
{
	return push_ucs2(NULL, dest, src, dest_len, flags|STR_UNICODE|STR_NOALIGN);
}

/*******************************************************************
 Convert a (little-endian) UNISTR2 structure to an ASCII string.
********************************************************************/

void unistr2_to_ascii(char *dest, const UNISTR2 *str, size_t maxlen)
{
	if (str == NULL) {
		*dest='\0';
		return;
	}
	pull_ucs2(NULL, dest, str->buffer, maxlen, str->uni_str_len*2, STR_NOALIGN);
}

/*******************************************************************
 Convert a (little-endian) UNISTR3 structure to an ASCII string.
********************************************************************/

void unistr3_to_ascii(char *dest, const UNISTR3 *str, size_t maxlen)
{
	if (str == NULL) {
		*dest='\0';
		return;
	}
	pull_ucs2(NULL, dest, str->str.buffer, maxlen, str->uni_str_len*2,
	          STR_NOALIGN);
}
	
/*******************************************************************
 Give a static string for displaying a UNISTR2.
********************************************************************/

const char *unistr2_static(const UNISTR2 *str)
{
	static pstring ret;
	unistr2_to_ascii(ret, str, sizeof(ret));
	return ret;
}

/*******************************************************************
 Duplicate a UNISTR2 string into a null terminated char*
 using a talloc context.
********************************************************************/

char *unistr2_tdup(TALLOC_CTX *ctx, const UNISTR2 *str)
{
	char *s;
	int maxlen = (str->uni_str_len+1)*4;
	if (!str->buffer) {
		return NULL;
	}
	s = (char *)TALLOC(ctx, maxlen); /* convervative */
	if (!s) {
		return NULL;
	}
	pull_ucs2(NULL, s, str->buffer, maxlen, str->uni_str_len*2, STR_NOALIGN);
	return s;
}

/*******************************************************************
 Convert a wchar to upper case.
********************************************************************/

smb_ucs2_t toupper_w(smb_ucs2_t val)
{
	return upcase_table[SVAL(&val,0)];
}

/*******************************************************************
 Convert a wchar to lower case.
********************************************************************/

smb_ucs2_t tolower_w( smb_ucs2_t val )
{
	return lowcase_table[SVAL(&val,0)];
}

/*******************************************************************
 Determine if a character is lowercase.
********************************************************************/

BOOL islower_w(smb_ucs2_t c)
{
	return upcase_table[SVAL(&c,0)] != c;
}

/*******************************************************************
 Determine if a character is uppercase.
********************************************************************/

BOOL isupper_w(smb_ucs2_t c)
{
	return lowcase_table[SVAL(&c,0)] != c;
}

/*******************************************************************
 Determine if a character is valid in a 8.3 name.
********************************************************************/

BOOL isvalid83_w(smb_ucs2_t c)
{
	return valid_table[SVAL(&c,0)] != 0;
}

/*******************************************************************
 Count the number of characters in a smb_ucs2_t string.
********************************************************************/

size_t strlen_w(const smb_ucs2_t *src)
{
	size_t len;
	smb_ucs2_t c;

	for(len = 0; *(COPY_UCS2_CHAR(&c,src)); src++, len++) {
		;
	}

	return len;
}

/*******************************************************************
 Count up to max number of characters in a smb_ucs2_t string.
********************************************************************/

size_t strnlen_w(const smb_ucs2_t *src, size_t max)
{
	size_t len;
	smb_ucs2_t c;

	for(len = 0; *(COPY_UCS2_CHAR(&c,src)) && (len < max); src++, len++) {
		;
	}

	return len;
}

/*******************************************************************
 Wide strchr().
********************************************************************/

smb_ucs2_t *strchr_w(const smb_ucs2_t *s, smb_ucs2_t c)
{
	smb_ucs2_t cp;
	while (*(COPY_UCS2_CHAR(&cp,s))) {
		if (c == cp) {
			return (smb_ucs2_t *)s;
		}
		s++;
	}
	if (c == cp) {
		return (smb_ucs2_t *)s;
	}

	return NULL;
}

smb_ucs2_t *strchr_wa(const smb_ucs2_t *s, char c)
{
	return strchr_w(s, UCS2_CHAR(c));
}

/*******************************************************************
 Wide strrchr().
********************************************************************/

smb_ucs2_t *strrchr_w(const smb_ucs2_t *s, smb_ucs2_t c)
{
	smb_ucs2_t cp;
	const smb_ucs2_t *p = s;
	int len = strlen_w(s);

	if (len == 0) {
		return NULL;
	}
	p += (len - 1);
	do {
		if (c == *(COPY_UCS2_CHAR(&cp,p))) {
			return (smb_ucs2_t *)p;
		}
	} while (p-- != s);
	return NULL;
}

/*******************************************************************
 Wide version of strrchr that returns after doing strrchr 'n' times.
********************************************************************/

smb_ucs2_t *strnrchr_w(const smb_ucs2_t *s, smb_ucs2_t c, unsigned int n)
{
	smb_ucs2_t cp;
	const smb_ucs2_t *p = s;
	int len = strlen_w(s);

	if (len == 0 || !n) {
		return NULL;
	}
	p += (len - 1);
	do {