| 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) 1997-2007 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 |
|
|---|
| 51 |
#include "local_config.h" |
|---|
| 52 |
#include "pcre_internal.h" |
|---|
| 53 |
|
|---|
| 54 |
|
|---|
| 55 |
|
|---|
| 56 |
/************************************************* |
|---|
| 57 |
* Check for newline at given position * |
|---|
| 58 |
*************************************************/ |
|---|
| 59 |
|
|---|
| 60 |
/* It is guaranteed that the initial value of ptr is less than the end of the |
|---|
| 61 |
string that is being processed. |
|---|
| 62 |
|
|---|
| 63 |
Arguments: |
|---|
| 64 |
ptr pointer to possible newline |
|---|
| 65 |
type the newline type |
|---|
| 66 |
endptr pointer to the end of the string |
|---|
| 67 |
lenptr where to return the length |
|---|
| 68 |
utf8 TRUE if in utf8 mode |
|---|
| 69 |
|
|---|
| 70 |
Returns: TRUE or FALSE |
|---|
| 71 |
*/ |
|---|
| 72 |
|
|---|
| 73 |
BOOL |
|---|
| 74 |
_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr, |
|---|
| 75 |
int *lenptr, BOOL utf8) |
|---|
| 76 |
{ |
|---|
| 77 |
int c; |
|---|
| 78 |
if (utf8) { GETCHAR(c, ptr); } else c = *ptr; |
|---|
| 79 |
|
|---|
| 80 |
if (type == NLTYPE_ANYCRLF) switch(c) |
|---|
| 81 |
{ |
|---|
| 82 |
case 0x000a: *lenptr = 1; return TRUE; /* LF */ |
|---|
| 83 |
case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; |
|---|
| 84 |
return TRUE; /* CR */ |
|---|
| 85 |
default: return FALSE; |
|---|
| 86 |
} |
|---|
| 87 |
|
|---|
| 88 |
/* NLTYPE_ANY */ |
|---|
| 89 |
|
|---|
| 90 |
else switch(c) |
|---|
| 91 |
{ |
|---|
| 92 |
case 0x000a: /* LF */ |
|---|
| 93 |
case 0x000b: /* VT */ |
|---|
| 94 |
case 0x000c: *lenptr = 1; return TRUE; /* FF */ |
|---|
| 95 |
case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; |
|---|
| 96 |
return TRUE; /* CR */ |
|---|
| 97 |
case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ |
|---|
| 98 |
case 0x2028: /* LS */ |
|---|
| 99 |
case 0x2029: *lenptr = 3; return TRUE; /* PS */ |
|---|
| 100 |
default: return FALSE; |
|---|
| 101 |
} |
|---|
| 102 |
} |
|---|
| 103 |
|
|---|
| 104 |
|
|---|
| 105 |
|
|---|
| 106 |
/************************************************* |
|---|
| 107 |
* Check for newline at previous position * |
|---|
| 108 |
*************************************************/ |
|---|
| 109 |
|
|---|
| 110 |
/* It is guaranteed that the initial value of ptr is greater than the start of |
|---|
| 111 |
the string that is being processed. |
|---|
| 112 |
|
|---|
| 113 |
Arguments: |
|---|
| 114 |
ptr pointer to possible newline |
|---|
| 115 |
type the newline type |
|---|
| 116 |
startptr pointer to the start of the string |
|---|
| 117 |
lenptr where to return the length |
|---|
| 118 |
utf8 TRUE if in utf8 mode |
|---|
| 119 |
|
|---|
| 120 |
Returns: TRUE or FALSE |
|---|
| 121 |
*/ |
|---|
| 122 |
|
|---|
| 123 |
BOOL |
|---|
| 124 |
_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr, |
|---|
| 125 |
int *lenptr, BOOL utf8) |
|---|
| 126 |
{ |
|---|
| 127 |
int c; |
|---|
| 128 |
ptr--; |
|---|
| 129 |
#ifdef SUPPORT_UTF8 |
|---|
| 130 |
if (utf8) |
|---|
| 131 |
{ |
|---|
| 132 |
BACKCHAR(ptr); |
|---|
| 133 |
GETCHAR(c, ptr); |
|---|
| 134 |
} |
|---|
| 135 |
else c = *ptr; |
|---|
| 136 |
#else /* no UTF-8 support */ |
|---|
| 137 |
c = *ptr; |
|---|
| 138 |
#endif /* SUPPORT_UTF8 */ |
|---|
| 139 |
|
|---|
| 140 |
if (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 |
|
|---|
| 148 |
else 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 */ |
|---|