1/************************************************* 2* Perl-Compatible Regular Expressions * 3*************************************************/ 4 5/* PCRE is a library of functions to support regular expressions whose syntax 6and semantics are as close as possible to those of the Perl 5 language. 7 8 Written by Philip Hazel 9 Copyright (c) 1997-2009 University of Cambridge 10 11----------------------------------------------------------------------------- 12Redistribution and use in source and binary forms, with or without 13modification, 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 26THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 27AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 28IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 29ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE 30LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 31CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 32SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS 33INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN 34CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 35ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 36POSSIBILITY OF SUCH DAMAGE. 37----------------------------------------------------------------------------- 38*/ 39 40 41/* This module contains internal functions for testing newlines when more than 42one kind of newline is to be recognized. When a newline is found, its length is 43returned. In principle, we could implement several newline "types", each 44referring to a different set of newline characters. At present, PCRE supports 45only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, 46and NLTYPE_ANY. The full list of Unicode newline characters is taken from 47http://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 63string that is being processed. 64 65Arguments: 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 utf8 TRUE if in utf8 mode 71 72Returns: TRUE or FALSE 73*/ 74 75BOOL 76_pcre_is_newline(USPTR ptr, int type, USPTR endptr, int *lenptr, BOOL utf8) 77{ 78int c; 79if (utf8) { GETCHAR(c, ptr); } else c = *ptr; 80 81if (type == NLTYPE_ANYCRLF) switch(c) 82 { 83 case 0x000a: *lenptr = 1; return TRUE; /* LF */ 84 case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; 85 return TRUE; /* CR */ 86 default: return FALSE; 87 } 88 89/* NLTYPE_ANY */ 90 91else switch(c) 92 { 93 case 0x000a: /* LF */ 94 case 0x000b: /* VT */ 95 case 0x000c: *lenptr = 1; return TRUE; /* FF */ 96 case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; 97 return TRUE; /* CR */ 98 case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ 99 case 0x2028: /* LS */ 100 case 0x2029: *lenptr = 3; return TRUE; /* PS */ 101 default: return FALSE; 102 } 103} 104 105 106 107/************************************************* 108* Check for newline at previous position * 109*************************************************/ 110 111/* It is guaranteed that the initial value of ptr is greater than the start of 112the string that is being processed. 113 114Arguments: 115 ptr pointer to possible newline 116 type the newline type 117 startptr pointer to the start of the string 118 lenptr where to return the length 119 utf8 TRUE if in utf8 mode 120 121Returns: TRUE or FALSE 122*/ 123 124BOOL 125_pcre_was_newline(USPTR ptr, int type, USPTR startptr, int *lenptr, BOOL utf8) 126{ 127int c; 128ptr--; 129#ifdef SUPPORT_UTF8 130if (utf8) 131 { 132 BACKCHAR(ptr); 133 GETCHAR(c, ptr); 134 } 135else c = *ptr; 136#else /* no UTF-8 support */ 137c = *ptr; 138#endif /* SUPPORT_UTF8 */ 139 140if (type == NLTYPE_ANYCRLF) switch(c) 141 { 142 case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; 143 return TRUE; /* LF */ 144 case 0x000d: *lenptr = 1; return TRUE; /* CR */ 145 default: return FALSE; 146 } 147 148else switch(c) 149 { 150 case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; 151 return TRUE; /* LF */ 152 case 0x000b: /* VT */ 153 case 0x000c: /* FF */ 154 case 0x000d: *lenptr = 1; return TRUE; /* CR */ 155 case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ 156 case 0x2028: /* LS */ 157 case 0x2029: *lenptr = 3; return TRUE; /* PS */ 158 default: return FALSE; 159 } 160} 161 162/* End of pcre_newline.c */ 163