utf8.c

来自「支持SSL v2/v3, TLS, PKCS #5, PKCS #7, PKCS」· C语言 代码 · 共 760 行 · 第 1/2 页

/* 
 * The contents of this file are subject to the Mozilla Public
 * License Version 1.1 (the "License"); you may not use this file
 * except in compliance with the License. You may obtain a copy of
 * the License at http://www.mozilla.org/MPL/
 * 
 * Software distributed under the License is distributed on an "AS
 * IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
 * implied. See the License for the specific language governing
 * rights and limitations under the License.
 * 
 * The Original Code is the Netscape security libraries.
 * 
 * The Initial Developer of the Original Code is Netscape
 * Communications Corporation.  Portions created by Netscape are 
 * Copyright (C) 1994-2000 Netscape Communications Corporation.  All
 * Rights Reserved.
 * 
 * Contributor(s):
 * 
 * Alternatively, the contents of this file may be used under the
 * terms of the GNU General Public License Version 2 or later (the
 * "GPL"), in which case the provisions of the GPL are applicable 
 * instead of those above.  If you wish to allow use of your 
 * version of this file only under the terms of the GPL and not to
 * allow others to use your version of this file under the MPL,
 * indicate your decision by deleting the provisions above and
 * replace them with the notice and other provisions required by
 * the GPL.  If you do not delete the provisions above, a recipient
 * may use your version of this file under either the MPL or the
 * GPL.
 */

#ifdef DEBUG
static const char CVS_ID[] = "@(#) $RCSfile: utf8.c,v $ $Revision: 1.3 $ $Date: 2000/05/12 18:43:28 $ $Name: NSS_3_1_1_RTM $";
#endif /* DEBUG */

/*
 * utf8.c
 *
 * This file contains some additional utility routines required for
 * handling UTF8 strings.
 */

#ifndef BASE_H
#include "base.h"
#endif /* BASE_H */

#include "plstr.h"

/*
 * NOTES:
 *
 * There's an "is hex string" function in pki1/atav.c.  If we need
 * it in more places, pull that one out.
 */

/*
 * nssUTF8_CaseIgnoreMatch
 * 
 * Returns true if the two UTF8-encoded strings pointed to by the 
 * two specified NSSUTF8 pointers differ only in typcase.
 *
 * The error may be one of the following values:
 *  NSS_ERROR_INVALID_POINTER
 *
 * Return value:
 *  PR_TRUE if the strings match, ignoring case
 *  PR_FALSE if they don't
 *  PR_FALSE upon error
 */

NSS_IMPLEMENT PRBool
nssUTF8_CaseIgnoreMatch
(
  const NSSUTF8 *a,
  const NSSUTF8 *b,
  PRStatus *statusOpt
)
{
#ifdef NSSDEBUG
  if( ((const NSSUTF8 *)NULL == a) ||
      ((const NSSUTF8 *)NULL == b) ) {
    nss_SetError(NSS_ERROR_INVALID_POINTER);
    if( (PRStatus *)NULL != statusOpt ) {
      *statusOpt = PR_FAILURE;
    }
    return PR_FALSE;
  }
#endif /* NSSDEBUG */

  if( (PRStatus *)NULL != statusOpt ) {
    *statusOpt = PR_SUCCESS;
  }

  /*
   * XXX fgmr
   *
   * This is, like, so wrong!
   */
  if( 0 == PL_strcasecmp((const char *)a, (const char *)b) ) {
    return PR_TRUE;
  } else {
    return PR_FALSE;
  }
}

/*
 * nssUTF8_PrintableMatch
 *
 * Returns true if the two Printable strings pointed to by the 
 * two specified NSSUTF8 pointers match when compared with the 
 * rules for Printable String (leading and trailing spaces are 
 * disregarded, extents of whitespace match irregardless of length, 
 * and case is not significant), then PR_TRUE will be returned.
 * Otherwise, PR_FALSE will be returned.  Upon failure, PR_FALSE
 * will be returned.  If the optional statusOpt argument is not
 * NULL, then PR_SUCCESS or PR_FAILURE will be stored in that
 * location.
 *
 * The error may be one of the following values:
 *  NSS_ERROR_INVALID_POINTER
 *
 * Return value:
 *  PR_TRUE if the strings match, ignoring case
 *  PR_FALSE if they don't
 *  PR_FALSE upon error
 */

NSS_IMPLEMENT PRBool
nssUTF8_PrintableMatch
(
  const NSSUTF8 *a,
  const NSSUTF8 *b,
  PRStatus *statusOpt
)
{
  PRUint8 *c;
  PRUint8 *d;

#ifdef NSSDEBUG
  if( ((const NSSUTF8 *)NULL == a) ||
      ((const NSSUTF8 *)NULL == b) ) {
    nss_SetError(NSS_ERROR_INVALID_POINTER);
    if( (PRStatus *)NULL != statusOpt ) {
      *statusOpt = PR_FAILURE;
    }
    return PR_FALSE;
  }
#endif /* NSSDEBUG */

  if( (PRStatus *)NULL != statusOpt ) {
    *statusOpt = PR_SUCCESS;
  }

  c = (PRUint8 *)a;
  d = (PRUint8 *)b;

  while( ' ' == *c ) {
    c++;
  }

  while( ' ' == *d ) {
    d++;
  }

  while( ('\0' != *c) && ('\0' != *d) ) {
    PRUint8 e, f;

    e = *c;
    f = *d;
    
    if( ('a' <= e) && (e <= 'z') ) {
      e -= ('a' - 'A');
    }

    if( ('a' <= f) && (f <= 'z') ) {
      f -= ('a' - 'A');
    }

    if( e != f ) {
      return PR_FALSE;
    }

    c++;
    d++;

    if( ' ' == *c ) {
      while( ' ' == *c ) {
        c++;
      }
      c--;
    }

    if( ' ' == *d ) {
      while( ' ' == *d ) {
        d++;
      }
      d--;
    }
  }

  while( ' ' == *c ) {
    c++;
  }

  while( ' ' == *d ) {
    d++;
  }

  if( *c == *d ) {
    /* And both '\0', btw */
    return PR_TRUE;
  } else {
    return PR_FALSE;
  }
}

/*
 * nssUTF8_Duplicate
 *
 * This routine duplicates the UTF8-encoded string pointed to by the
 * specified NSSUTF8 pointer.  If the optional arenaOpt argument is
 * not null, the memory required will be obtained from that arena;
 * otherwise, the memory required will be obtained from the heap.
 * A pointer to the new string will be returned.  In case of error,
 * an error will be placed on the error stack and NULL will be 
 * returned.
 *
 * The error may be one of the following values:
 *  NSS_ERROR_INVALID_POINTER
 *  NSS_ERROR_INVALID_ARENA
 *  NSS_ERROR_NO_MEMORY
 */

NSS_IMPLEMENT NSSUTF8 *
nssUTF8_Duplicate
(
  const NSSUTF8 *s,
  NSSArena *arenaOpt
)
{
  NSSUTF8 *rv;
  PRUint32 len;

#ifdef NSSDEBUG
  if( (const NSSUTF8 *)NULL == s ) {
    nss_SetError(NSS_ERROR_INVALID_POINTER);
    return (NSSUTF8 *)NULL;
  }

  if( (NSSArena *)NULL != arenaOpt ) {
    if( PR_SUCCESS != nssArena_verifyPointer(arenaOpt) ) {
      return (NSSUTF8 *)NULL;
    }
  }
#endif /* NSSDEBUG */

  len = PL_strlen((const char *)s);
#ifdef PEDANTIC
  if( '\0' != ((const char *)s)[ len ] ) {
    /* must have wrapped, e.g., too big for PRUint32 */
    nss_SetError(NSS_ERROR_NO_MEMORY);
    return (NSSUTF8 *)NULL;
  }
#endif /* PEDANTIC */
  len++; /* zero termination */

  rv = nss_ZAlloc(arenaOpt, len);
  if( (void *)NULL == rv ) {
    return (NSSUTF8 *)NULL;
  }

  (void)nsslibc_memcpy(rv, s, len);
  return rv;
}

/*
 * nssUTF8_Size
 *
 * This routine returns the length in bytes (including the terminating
 * null) of the UTF8-encoded string pointed to by the specified
 * NSSUTF8 pointer.  Zero is returned on error.
 *
 * The error may be one of the following values:
 *  NSS_ERROR_INVALID_POINTER
 *  NSS_ERROR_VALUE_TOO_LARGE
 *
 * Return value:
 *  0 on error
 *  nonzero length of the string.
 */

NSS_IMPLEMENT PRUint32
nssUTF8_Size
(
  const NSSUTF8 *s,
  PRStatus *statusOpt
)
{
  PRUint32 sv;

#ifdef NSSDEBUG
  if( (const NSSUTF8 *)NULL == s ) {
    nss_SetError(NSS_ERROR_INVALID_POINTER);
    if( (PRStatus *)NULL != statusOpt ) {
      *statusOpt = PR_FAILURE;
    }
    return 0;
  }
#endif /* NSSDEBUG */

  sv = PL_strlen((const char *)s) + 1;
#ifdef PEDANTIC
  if( '\0' != ((const char *)s)[ sv-1 ] ) {
    /* wrapped */
    nss_SetError(NSS_ERROR_VALUE_TOO_LARGE);
    if( (PRStatus *)NULL != statusOpt ) {
      *statusOpt = PR_FAILURE;
    }
    return 0;
  }
#endif /* PEDANTIC */

  if( (PRStatus *)NULL != statusOpt ) {
    *statusOpt = PR_SUCCESS;
  }

  return sv;
}

/*
 * nssUTF8_Length
 *
 * This routine returns the length in characters (not including the
 * terminating null) of the UTF8-encoded string pointed to by the
 * specified NSSUTF8 pointer.
 *
 * The error may be one of the following values:
 *  NSS_ERROR_INVALID_POINTER
 *  NSS_ERROR_VALUE_TOO_LARGE
 *  NSS_ERROR_INVALID_STRING
 *
 * Return value:
 *  length of the string (which may be zero)
 *  0 on error
 */

NSS_IMPLEMENT PRUint32
nssUTF8_Length
(
  const NSSUTF8 *s,
  PRStatus *statusOpt
)
{
  PRUint32 l = 0;
  const PRUint8 *c = (const PRUint8 *)s;

#ifdef NSSDEBUG
  if( (const NSSUTF8 *)NULL == s ) {
    nss_SetError(NSS_ERROR_INVALID_POINTER);
    goto loser;
  }
#endif /* NSSDEBUG */

  /*
   * From RFC 2044:
   *
   * UCS-4 range (hex.)           UTF-8 octet sequence (binary)
   * 0000 0000-0000 007F   0xxxxxxx
   * 0000 0080-0000 07FF   110xxxxx 10xxxxxx
   * 0000 0800-0000 FFFF   1110xxxx 10xxxxxx 10xxxxxx
   * 0001 0000-001F FFFF   11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
   * 0020 0000-03FF FFFF   111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
   * 0400 0000-7FFF FFFF   1111110x 10xxxxxx ... 10xxxxxx
   */  

  while( 0 != *c ) {
    PRUint32 incr;
    if( (*c & 0x80) == 0 ) {