File:  [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / pcre_newline.c
Revision 1.1.1.2 (vendor branch): download - view: text, annotated - select for diffs - revision graph
Tue Feb 21 23:50:25 2012 UTC (12 years, 4 months ago) by misho
Branches: pcre, MAIN
CVS tags: v8_31, v8_30, HEAD
pcre

    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) 1997-2012 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 internal functions for testing newlines when more than
   42: one kind of newline is to be recognized. When a newline is found, its length is
   43: returned. In principle, we could implement several newline "types", each
   44: referring to a different set of newline characters. At present, PCRE supports
   45: only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF,
   46: and NLTYPE_ANY. The full list of Unicode newline characters is taken from
   47: http://unicode.org/unicode/reports/tr18/. */
   48: 
   49: 
   50: #ifdef HAVE_CONFIG_H
   51: #include "config.h"
   52: #endif
   53: 
   54: #include "pcre_internal.h"
   55: 
   56: 
   57: 
   58: /*************************************************
   59: *      Check for newline at given position       *
   60: *************************************************/
   61: 
   62: /* It is guaranteed that the initial value of ptr is less than the end of the
   63: string that is being processed.
   64: 
   65: Arguments:
   66:   ptr          pointer to possible newline
   67:   type         the newline type
   68:   endptr       pointer to the end of the string
   69:   lenptr       where to return the length
   70:   utf          TRUE if in utf mode
   71: 
   72: Returns:       TRUE or FALSE
   73: */
   74: 
   75: BOOL
   76: PRIV(is_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR endptr, int *lenptr,
   77:   BOOL utf)
   78: {
   79: int c;
   80: (void)utf;
   81: #ifdef SUPPORT_UTF
   82: if (utf)
   83:   {
   84:   GETCHAR(c, ptr);
   85:   }
   86: else
   87: #endif  /* SUPPORT_UTF */
   88:   c = *ptr;
   89: 
   90: if (type == NLTYPE_ANYCRLF) switch(c)
   91:   {
   92:   case 0x000a: *lenptr = 1; return TRUE;             /* LF */
   93:   case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
   94:                return TRUE;                          /* CR */
   95:   default: return FALSE;
   96:   }
   97: 
   98: /* NLTYPE_ANY */
   99: 
  100: else switch(c)
  101:   {
  102:   case 0x000a:                                       /* LF */
  103:   case 0x000b:                                       /* VT */
  104:   case 0x000c: *lenptr = 1; return TRUE;             /* FF */
  105:   case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
  106:                return TRUE;                          /* CR */
  107: #ifdef COMPILE_PCRE8
  108:   case 0x0085: *lenptr = utf? 2 : 1; return TRUE;    /* NEL */
  109:   case 0x2028:                                       /* LS */
  110:   case 0x2029: *lenptr = 3; return TRUE;             /* PS */
  111: #else
  112:   case 0x0085:                                       /* NEL */
  113:   case 0x2028:                                       /* LS */
  114:   case 0x2029: *lenptr = 1; return TRUE;             /* PS */
  115: #endif /* COMPILE_PCRE8 */
  116:   default: return FALSE;
  117:   }
  118: }
  119: 
  120: 
  121: 
  122: /*************************************************
  123: *     Check for newline at previous position     *
  124: *************************************************/
  125: 
  126: /* It is guaranteed that the initial value of ptr is greater than the start of
  127: the string that is being processed.
  128: 
  129: Arguments:
  130:   ptr          pointer to possible newline
  131:   type         the newline type
  132:   startptr     pointer to the start of the string
  133:   lenptr       where to return the length
  134:   utf          TRUE if in utf mode
  135: 
  136: Returns:       TRUE or FALSE
  137: */
  138: 
  139: BOOL
  140: PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr,
  141:   BOOL utf)
  142: {
  143: int c;
  144: (void)utf;
  145: ptr--;
  146: #ifdef SUPPORT_UTF
  147: if (utf)
  148:   {
  149:   BACKCHAR(ptr);
  150:   GETCHAR(c, ptr);
  151:   }
  152: else
  153: #endif  /* SUPPORT_UTF */
  154:   c = *ptr;
  155: 
  156: if (type == NLTYPE_ANYCRLF) switch(c)
  157:   {
  158:   case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
  159:                return TRUE;                         /* LF */
  160:   case 0x000d: *lenptr = 1; return TRUE;            /* CR */
  161:   default: return FALSE;
  162:   }
  163: 
  164: else switch(c)
  165:   {
  166:   case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
  167:                return TRUE;                         /* LF */
  168:   case 0x000b:                                      /* VT */
  169:   case 0x000c:                                      /* FF */
  170:   case 0x000d: *lenptr = 1; return TRUE;            /* CR */
  171: #ifdef COMPILE_PCRE8
  172:   case 0x0085: *lenptr = utf? 2 : 1; return TRUE;   /* NEL */
  173:   case 0x2028:                                      /* LS */
  174:   case 0x2029: *lenptr = 3; return TRUE;            /* PS */
  175: #else
  176:   case 0x0085:                                       /* NEL */
  177:   case 0x2028:                                       /* LS */
  178:   case 0x2029: *lenptr = 1; return TRUE;             /* PS */
  179: #endif /* COMPILE_PCRE8 */
  180:   default: return FALSE;
  181:   }
  182: }
  183: 
  184: /* End of pcre_newline.c */

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