Home | History | Annotate | Download | only in dist
      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 pcre_uint32 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 /* Note that this function is called only for ANY or ANYCRLF. */
     91 
     92 if (type == NLTYPE_ANYCRLF) switch(c)
     93   {
     94   case CHAR_LF: *lenptr = 1; return TRUE;
     95   case CHAR_CR: *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
     96                return TRUE;
     97   default: return FALSE;
     98   }
     99 
    100 /* NLTYPE_ANY */
    101 
    102 else switch(c)
    103   {
    104 #ifdef EBCDIC
    105   case CHAR_NEL:
    106 #endif
    107   case CHAR_LF:
    108   case CHAR_VT:
    109   case CHAR_FF: *lenptr = 1; return TRUE;
    110 
    111   case CHAR_CR:
    112   *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
    113   return TRUE;
    114 
    115 #ifndef EBCDIC
    116 #ifdef COMPILE_PCRE8
    117   case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE;
    118   case 0x2028:                                       /* LS */
    119   case 0x2029: *lenptr = 3; return TRUE;             /* PS */
    120 #else /* COMPILE_PCRE16 || COMPILE_PCRE32 */
    121   case CHAR_NEL:
    122   case 0x2028:                                       /* LS */
    123   case 0x2029: *lenptr = 1; return TRUE;             /* PS */
    124 #endif  /* COMPILE_PCRE8 */
    125 #endif  /* Not EBCDIC */
    126 
    127   default: return FALSE;
    128   }
    129 }
    130 
    131 
    132 
    133 /*************************************************
    134 *     Check for newline at previous position     *
    135 *************************************************/
    136 
    137 /* It is guaranteed that the initial value of ptr is greater than the start of
    138 the string that is being processed.
    139 
    140 Arguments:
    141   ptr          pointer to possible newline
    142   type         the newline type
    143   startptr     pointer to the start of the string
    144   lenptr       where to return the length
    145   utf          TRUE if in utf mode
    146 
    147 Returns:       TRUE or FALSE
    148 */
    149 
    150 BOOL
    151 PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr,
    152   BOOL utf)
    153 {
    154 pcre_uint32 c;
    155 (void)utf;
    156 ptr--;
    157 #ifdef SUPPORT_UTF
    158 if (utf)
    159   {
    160   BACKCHAR(ptr);
    161   GETCHAR(c, ptr);
    162   }
    163 else
    164 #endif  /* SUPPORT_UTF */
    165   c = *ptr;
    166 
    167 /* Note that this function is called only for ANY or ANYCRLF. */
    168 
    169 if (type == NLTYPE_ANYCRLF) switch(c)
    170   {
    171   case CHAR_LF:
    172   *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
    173   return TRUE;
    174 
    175   case CHAR_CR: *lenptr = 1; return TRUE;
    176   default: return FALSE;
    177   }
    178 
    179 /* NLTYPE_ANY */
    180 
    181 else switch(c)
    182   {
    183   case CHAR_LF:
    184   *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
    185   return TRUE;
    186 
    187 #ifdef EBCDIC
    188   case CHAR_NEL:
    189 #endif
    190   case CHAR_VT:
    191   case CHAR_FF:
    192   case CHAR_CR: *lenptr = 1; return TRUE;
    193 
    194 #ifndef EBCDIC
    195 #ifdef COMPILE_PCRE8
    196   case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE;
    197   case 0x2028:                                       /* LS */
    198   case 0x2029: *lenptr = 3; return TRUE;             /* PS */
    199 #else /* COMPILE_PCRE16 || COMPILE_PCRE32 */
    200   case CHAR_NEL:
    201   case 0x2028:                                       /* LS */
    202   case 0x2029: *lenptr = 1; return TRUE;             /* PS */
    203 #endif  /* COMPILE_PCRE8 */
    204 #endif  /* NotEBCDIC */
    205 
    206   default: return FALSE;
    207   }
    208 }
    209 
    210 /* End of pcre_newline.c */
    211