File:  [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / pcre32_valid_utf32.c
Revision 1.1.1.1 (vendor branch): download - view: text, annotated - select for diffs - revision graph
Mon Jul 22 08:25:55 2013 UTC (10 years, 10 months ago) by misho
Branches: pcre, MAIN
CVS tags: v8_34, v8_33, HEAD
8.33

    1: /*************************************************
    2: *      Perl-Compatible Regular Expressions       *
    3: *************************************************/
    4: 
    5: /* PCRE is a library of functions to support regular expressions whose syntax
    6: and semantics are as close as possible to those of the Perl 5 language.
    7: 
    8:                        Written by Philip Hazel
    9:            Copyright (c) 1997-2013 University of Cambridge
   10: 
   11: -----------------------------------------------------------------------------
   12: Redistribution and use in source and binary forms, with or without
   13: modification, are permitted provided that the following conditions are met:
   14: 
   15:     * Redistributions of source code must retain the above copyright notice,
   16:       this list of conditions and the following disclaimer.
   17: 
   18:     * Redistributions in binary form must reproduce the above copyright
   19:       notice, this list of conditions and the following disclaimer in the
   20:       documentation and/or other materials provided with the distribution.
   21: 
   22:     * Neither the name of the University of Cambridge nor the names of its
   23:       contributors may be used to endorse or promote products derived from
   24:       this software without specific prior written permission.
   25: 
   26: THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
   27: AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
   28: IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
   29: ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
   30: LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
   31: CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
   32: SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
   33: INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
   34: CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
   35: ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
   36: POSSIBILITY OF SUCH DAMAGE.
   37: -----------------------------------------------------------------------------
   38: */
   39: 
   40: 
   41: /* This module contains an internal function for validating UTF-32 character
   42: strings. */
   43: 
   44: 
   45: #ifdef HAVE_CONFIG_H
   46: #include "config.h"
   47: #endif
   48: 
   49: /* Generate code with 32 bit character support. */
   50: #define COMPILE_PCRE32
   51: 
   52: #include "pcre_internal.h"
   53: 
   54: /*************************************************
   55: *         Validate a UTF-32 string                *
   56: *************************************************/
   57: 
   58: /* This function is called (optionally) at the start of compile or match, to
   59: check that a supposed UTF-32 string is actually valid. The early check means
   60: that subsequent code can assume it is dealing with a valid string. The check
   61: can be turned off for maximum performance, but the consequences of supplying an
   62: invalid string are then undefined.
   63: 
   64: More information about the details of the error are passed
   65: back in the returned value:
   66: 
   67: PCRE_UTF32_ERR0  No error
   68: PCRE_UTF32_ERR1  Surrogate character
   69: PCRE_UTF32_ERR2  Unused (was non-character)
   70: PCRE_UTF32_ERR3  Character > 0x10ffff
   71: 
   72: Arguments:
   73:   string       points to the string
   74:   length       length of string, or -1 if the string is zero-terminated
   75:   errp         pointer to an error position offset variable
   76: 
   77: Returns:       = 0    if the string is a valid UTF-32 string
   78:                > 0    otherwise, setting the offset of the bad character
   79: */
   80: 
   81: int
   82: PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset)
   83: {
   84: #ifdef SUPPORT_UTF
   85: register PCRE_PUCHAR p;
   86: register pcre_uchar c;
   87: 
   88: if (length < 0)
   89:   {
   90:   for (p = string; *p != 0; p++);
   91:   length = p - string;
   92:   }
   93: 
   94: for (p = string; length-- > 0; p++)
   95:   {
   96:   c = *p;
   97: 
   98:   if ((c & 0xfffff800u) != 0xd800u)
   99:     {
  100:     /* Normal UTF-32 code point. Neither high nor low surrogate. */
  101:     if (c > 0x10ffffu)
  102:       {
  103:       *erroroffset = p - string;
  104:       return PCRE_UTF32_ERR3;
  105:       }
  106:     }
  107:   else
  108:     {
  109:     /* A surrogate */
  110:     *erroroffset = p - string;
  111:     return PCRE_UTF32_ERR1;
  112:     }
  113:   }
  114: 
  115: #else  /* SUPPORT_UTF */
  116: (void)(string);  /* Keep picky compilers happy */
  117: (void)(length);
  118: (void)(erroroffset);
  119: #endif /* SUPPORT_UTF */
  120: 
  121: return PCRE_UTF32_ERR0;   /* This indicates success */
  122: }
  123: 
  124: /* End of pcre32_valid_utf32.c */

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>