[sm130futures] Moving pcre now.
This commit is contained in:
Jason Felds
@@ -1,45 +0,0 @@
|
||||
PCRE LICENCE
|
||||
------------
|
||||
|
||||
PCRE is a library of functions to support regular expressions whose syntax
|
||||
and semantics are as close as possible to those of the Perl 5 language.
|
||||
|
||||
This release of PCRE is distributed under the terms of the "BSD" licence,
|
||||
as specified below. The documentation for PCRE, supplied in the "doc"
|
||||
directory, is distributed under the same terms as the software itself.
|
||||
|
||||
Written by: Philip Hazel <[email protected]>
|
||||
|
||||
University of Cambridge Computing Service,
|
||||
Cambridge, England. Phone: +44 1223 334714.
|
||||
|
||||
Copyright (c) 1997-2003 University of Cambridge
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the University of Cambridge nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
End
|
||||
@@ -1,183 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
/* This file is automatically written by the dftables auxiliary
|
||||
program. If you edit it by hand, you might like to edit the Makefile to
|
||||
prevent its ever being regenerated.
|
||||
|
||||
This file is #included in the compilation of pcre.c to build the default
|
||||
character tables which are used when no tables are passed to the compile
|
||||
function. */
|
||||
|
||||
static unsigned char pcre_default_tables[] = {
|
||||
|
||||
/* This table is a lower casing table. */
|
||||
|
||||
0, 1, 2, 3, 4, 5, 6, 7,
|
||||
8, 9, 10, 11, 12, 13, 14, 15,
|
||||
16, 17, 18, 19, 20, 21, 22, 23,
|
||||
24, 25, 26, 27, 28, 29, 30, 31,
|
||||
32, 33, 34, 35, 36, 37, 38, 39,
|
||||
40, 41, 42, 43, 44, 45, 46, 47,
|
||||
48, 49, 50, 51, 52, 53, 54, 55,
|
||||
56, 57, 58, 59, 60, 61, 62, 63,
|
||||
64, 97, 98, 99,100,101,102,103,
|
||||
104,105,106,107,108,109,110,111,
|
||||
112,113,114,115,116,117,118,119,
|
||||
120,121,122, 91, 92, 93, 94, 95,
|
||||
96, 97, 98, 99,100,101,102,103,
|
||||
104,105,106,107,108,109,110,111,
|
||||
112,113,114,115,116,117,118,119,
|
||||
120,121,122,123,124,125,126,127,
|
||||
128,129,130,131,132,133,134,135,
|
||||
136,137,138,139,140,141,142,143,
|
||||
144,145,146,147,148,149,150,151,
|
||||
152,153,154,155,156,157,158,159,
|
||||
160,161,162,163,164,165,166,167,
|
||||
168,169,170,171,172,173,174,175,
|
||||
176,177,178,179,180,181,182,183,
|
||||
184,185,186,187,188,189,190,191,
|
||||
192,193,194,195,196,197,198,199,
|
||||
200,201,202,203,204,205,206,207,
|
||||
208,209,210,211,212,213,214,215,
|
||||
216,217,218,219,220,221,222,223,
|
||||
224,225,226,227,228,229,230,231,
|
||||
232,233,234,235,236,237,238,239,
|
||||
240,241,242,243,244,245,246,247,
|
||||
248,249,250,251,252,253,254,255,
|
||||
|
||||
/* This table is a case flipping table. */
|
||||
|
||||
0, 1, 2, 3, 4, 5, 6, 7,
|
||||
8, 9, 10, 11, 12, 13, 14, 15,
|
||||
16, 17, 18, 19, 20, 21, 22, 23,
|
||||
24, 25, 26, 27, 28, 29, 30, 31,
|
||||
32, 33, 34, 35, 36, 37, 38, 39,
|
||||
40, 41, 42, 43, 44, 45, 46, 47,
|
||||
48, 49, 50, 51, 52, 53, 54, 55,
|
||||
56, 57, 58, 59, 60, 61, 62, 63,
|
||||
64, 97, 98, 99,100,101,102,103,
|
||||
104,105,106,107,108,109,110,111,
|
||||
112,113,114,115,116,117,118,119,
|
||||
120,121,122, 91, 92, 93, 94, 95,
|
||||
96, 65, 66, 67, 68, 69, 70, 71,
|
||||
72, 73, 74, 75, 76, 77, 78, 79,
|
||||
80, 81, 82, 83, 84, 85, 86, 87,
|
||||
88, 89, 90,123,124,125,126,127,
|
||||
128,129,130,131,132,133,134,135,
|
||||
136,137,138,139,140,141,142,143,
|
||||
144,145,146,147,148,149,150,151,
|
||||
152,153,154,155,156,157,158,159,
|
||||
160,161,162,163,164,165,166,167,
|
||||
168,169,170,171,172,173,174,175,
|
||||
176,177,178,179,180,181,182,183,
|
||||
184,185,186,187,188,189,190,191,
|
||||
192,193,194,195,196,197,198,199,
|
||||
200,201,202,203,204,205,206,207,
|
||||
208,209,210,211,212,213,214,215,
|
||||
216,217,218,219,220,221,222,223,
|
||||
224,225,226,227,228,229,230,231,
|
||||
232,233,234,235,236,237,238,239,
|
||||
240,241,242,243,244,245,246,247,
|
||||
248,249,250,251,252,253,254,255,
|
||||
|
||||
/* This table contains bit maps for various character classes.
|
||||
Each map is 32 bytes long and the bits run from the least
|
||||
significant end of each byte. The classes that have their own
|
||||
maps are: space, xdigit, digit, upper, lower, word, graph
|
||||
print, punct, and cntrl. Other classes are built from combinations. */
|
||||
|
||||
0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
|
||||
0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
|
||||
0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,
|
||||
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,
|
||||
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,
|
||||
0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
|
||||
|
||||
/* This table identifies various classes of character by individual bits:
|
||||
0x01 white space character
|
||||
0x02 letter
|
||||
0x04 decimal digit
|
||||
0x08 hexadecimal digit
|
||||
0x10 alphanumeric or '_'
|
||||
0x80 regular expression metacharacter or binary zero
|
||||
*/
|
||||
|
||||
0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
|
||||
0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
|
||||
0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */
|
||||
0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */
|
||||
0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */
|
||||
0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */
|
||||
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */
|
||||
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */
|
||||
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */
|
||||
0x12,0x12,0x12,0x80,0x00,0x00,0x80,0x10, /* X - _ */
|
||||
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */
|
||||
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */
|
||||
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */
|
||||
0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
|
||||
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
|
||||
|
||||
/* End of chartables.c */
|
||||
-357
@@ -1,357 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
/*
|
||||
This is a library of functions to support regular expressions whose syntax
|
||||
and semantics are as close as possible to those of the Perl 5 language. See
|
||||
the file Tech.Notes for some information on the internals.
|
||||
|
||||
Written by: Philip Hazel <[email protected]>
|
||||
|
||||
Copyright (c) 1997-2003 University of Cambridge
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the University of Cambridge nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
-----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
/* This module contains some convenience functions for extracting substrings
|
||||
from the subject string after a regex match has succeeded. The original idea
|
||||
for these functions came from Scott Wimer <[email protected]>. */
|
||||
|
||||
|
||||
/* Include the internals header, which itself includes Standard C headers plus
|
||||
the external pcre header. */
|
||||
|
||||
#include "internal.h"
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Find number for named string *
|
||||
*************************************************/
|
||||
|
||||
/* This function is used by the two extraction functions below, as well
|
||||
as being generally available.
|
||||
|
||||
Arguments:
|
||||
code the compiled regex
|
||||
stringname the name whose number is required
|
||||
|
||||
Returns: the number of the named parentheses, or a negative number
|
||||
(PCRE_ERROR_NOSUBSTRING) if not found
|
||||
*/
|
||||
|
||||
int
|
||||
pcre_get_stringnumber(const pcre *code, const char *stringname)
|
||||
{
|
||||
int rc;
|
||||
int entrysize;
|
||||
int top, bot;
|
||||
uschar *nametable;
|
||||
|
||||
if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
|
||||
return rc;
|
||||
if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
|
||||
|
||||
if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
|
||||
return rc;
|
||||
if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
|
||||
return rc;
|
||||
|
||||
bot = 0;
|
||||
while (top > bot)
|
||||
{
|
||||
int mid = (top + bot) / 2;
|
||||
uschar *entry = nametable + entrysize*mid;
|
||||
int c = strcmp(stringname, (char *)(entry + 2));
|
||||
if (c == 0) return (entry[0] << 8) + entry[1];
|
||||
if (c > 0) bot = mid + 1; else top = mid;
|
||||
}
|
||||
|
||||
return PCRE_ERROR_NOSUBSTRING;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Copy captured string to given buffer *
|
||||
*************************************************/
|
||||
|
||||
/* This function copies a single captured substring into a given buffer.
|
||||
Note that we use memcpy() rather than strncpy() in case there are binary zeros
|
||||
in the string.
|
||||
|
||||
Arguments:
|
||||
subject the subject string that was matched
|
||||
ovector pointer to the offsets table
|
||||
stringcount the number of substrings that were captured
|
||||
(i.e. the yield of the pcre_exec call, unless
|
||||
that was zero, in which case it should be 1/3
|
||||
of the offset table size)
|
||||
stringnumber the number of the required substring
|
||||
buffer where to put the substring
|
||||
size the size of the buffer
|
||||
|
||||
Returns: if successful:
|
||||
the length of the copied string, not including the zero
|
||||
that is put on the end; can be zero
|
||||
if not successful:
|
||||
PCRE_ERROR_NOMEMORY (-6) buffer too small
|
||||
PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
|
||||
*/
|
||||
|
||||
int
|
||||
pcre_copy_substring(const char *subject, int *ovector, int stringcount,
|
||||
int stringnumber, char *buffer, int size)
|
||||
{
|
||||
int yield;
|
||||
if (stringnumber < 0 || stringnumber >= stringcount)
|
||||
return PCRE_ERROR_NOSUBSTRING;
|
||||
stringnumber *= 2;
|
||||
yield = ovector[stringnumber+1] - ovector[stringnumber];
|
||||
if (size < yield + 1) return PCRE_ERROR_NOMEMORY;
|
||||
memcpy(buffer, subject + ovector[stringnumber], yield);
|
||||
buffer[yield] = 0;
|
||||
return yield;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Copy named captured string to given buffer *
|
||||
*************************************************/
|
||||
|
||||
/* This function copies a single captured substring into a given buffer,
|
||||
identifying it by name.
|
||||
|
||||
Arguments:
|
||||
code the compiled regex
|
||||
subject the subject string that was matched
|
||||
ovector pointer to the offsets table
|
||||
stringcount the number of substrings that were captured
|
||||
(i.e. the yield of the pcre_exec call, unless
|
||||
that was zero, in which case it should be 1/3
|
||||
of the offset table size)
|
||||
stringname the name of the required substring
|
||||
buffer where to put the substring
|
||||
size the size of the buffer
|
||||
|
||||
Returns: if successful:
|
||||
the length of the copied string, not including the zero
|
||||
that is put on the end; can be zero
|
||||
if not successful:
|
||||
PCRE_ERROR_NOMEMORY (-6) buffer too small
|
||||
PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
|
||||
*/
|
||||
|
||||
int
|
||||
pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector,
|
||||
int stringcount, const char *stringname, char *buffer, int size)
|
||||
{
|
||||
int n = pcre_get_stringnumber(code, stringname);
|
||||
if (n <= 0) return n;
|
||||
return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size);
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Copy all captured strings to new store *
|
||||
*************************************************/
|
||||
|
||||
/* This function gets one chunk of store and builds a list of pointers and all
|
||||
of the captured substrings in it. A NULL pointer is put on the end of the list.
|
||||
|
||||
Arguments:
|
||||
subject the subject string that was matched
|
||||
ovector pointer to the offsets table
|
||||
stringcount the number of substrings that were captured
|
||||
(i.e. the yield of the pcre_exec call, unless
|
||||
that was zero, in which case it should be 1/3
|
||||
of the offset table size)
|
||||
listptr set to point to the list of pointers
|
||||
|
||||
Returns: if successful: 0
|
||||
if not successful:
|
||||
PCRE_ERROR_NOMEMORY (-6) failed to get store
|
||||
*/
|
||||
|
||||
int
|
||||
pcre_get_substring_list(const char *subject, int *ovector, int stringcount,
|
||||
const char ***listptr)
|
||||
{
|
||||
int i;
|
||||
int size = sizeof(char *);
|
||||
int double_count = stringcount * 2;
|
||||
char **stringlist;
|
||||
char *p;
|
||||
|
||||
for (i = 0; i < double_count; i += 2)
|
||||
size += sizeof(char *) + ovector[i+1] - ovector[i] + 1;
|
||||
|
||||
stringlist = (char **)(pcre_malloc)(size);
|
||||
if (stringlist == NULL) return PCRE_ERROR_NOMEMORY;
|
||||
|
||||
*listptr = (const char **)stringlist;
|
||||
p = (char *)(stringlist + stringcount + 1);
|
||||
|
||||
for (i = 0; i < double_count; i += 2)
|
||||
{
|
||||
int len = ovector[i+1] - ovector[i];
|
||||
memcpy(p, subject + ovector[i], len);
|
||||
*stringlist++ = p;
|
||||
p += len;
|
||||
*p++ = 0;
|
||||
}
|
||||
|
||||
*stringlist = NULL;
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Free store obtained by get_substring_list *
|
||||
*************************************************/
|
||||
|
||||
/* This function exists for the benefit of people calling PCRE from non-C
|
||||
programs that can call its functions, but not free() or (pcre_free)() directly.
|
||||
|
||||
Argument: the result of a previous pcre_get_substring_list()
|
||||
Returns: nothing
|
||||
*/
|
||||
|
||||
void
|
||||
pcre_free_substring_list(const char **pointer)
|
||||
{
|
||||
(pcre_free)((void *)pointer);
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Copy captured string to new store *
|
||||
*************************************************/
|
||||
|
||||
/* This function copies a single captured substring into a piece of new
|
||||
store
|
||||
|
||||
Arguments:
|
||||
subject the subject string that was matched
|
||||
ovector pointer to the offsets table
|
||||
stringcount the number of substrings that were captured
|
||||
(i.e. the yield of the pcre_exec call, unless
|
||||
that was zero, in which case it should be 1/3
|
||||
of the offset table size)
|
||||
stringnumber the number of the required substring
|
||||
stringptr where to put a pointer to the substring
|
||||
|
||||
Returns: if successful:
|
||||
the length of the string, not including the zero that
|
||||
is put on the end; can be zero
|
||||
if not successful:
|
||||
PCRE_ERROR_NOMEMORY (-6) failed to get store
|
||||
PCRE_ERROR_NOSUBSTRING (-7) substring not present
|
||||
*/
|
||||
|
||||
int
|
||||
pcre_get_substring(const char *subject, int *ovector, int stringcount,
|
||||
int stringnumber, const char **stringptr)
|
||||
{
|
||||
int yield;
|
||||
char *substring;
|
||||
if (stringnumber < 0 || stringnumber >= stringcount)
|
||||
return PCRE_ERROR_NOSUBSTRING;
|
||||
stringnumber *= 2;
|
||||
yield = ovector[stringnumber+1] - ovector[stringnumber];
|
||||
substring = (char *)(pcre_malloc)(yield + 1);
|
||||
if (substring == NULL) return PCRE_ERROR_NOMEMORY;
|
||||
memcpy(substring, subject + ovector[stringnumber], yield);
|
||||
substring[yield] = 0;
|
||||
*stringptr = substring;
|
||||
return yield;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Copy named captured string to new store *
|
||||
*************************************************/
|
||||
|
||||
/* This function copies a single captured substring, identified by name, into
|
||||
new store.
|
||||
|
||||
Arguments:
|
||||
code the compiled regex
|
||||
subject the subject string that was matched
|
||||
ovector pointer to the offsets table
|
||||
stringcount the number of substrings that were captured
|
||||
(i.e. the yield of the pcre_exec call, unless
|
||||
that was zero, in which case it should be 1/3
|
||||
of the offset table size)
|
||||
stringname the name of the required substring
|
||||
stringptr where to put the pointer
|
||||
|
||||
Returns: if successful:
|
||||
the length of the copied string, not including the zero
|
||||
that is put on the end; can be zero
|
||||
if not successful:
|
||||
PCRE_ERROR_NOMEMORY (-6) couldn't get memory
|
||||
PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
|
||||
*/
|
||||
|
||||
int
|
||||
pcre_get_named_substring(const pcre *code, const char *subject, int *ovector,
|
||||
int stringcount, const char *stringname, const char **stringptr)
|
||||
{
|
||||
int n = pcre_get_stringnumber(code, stringname);
|
||||
if (n <= 0) return n;
|
||||
return pcre_get_substring(subject, ovector, stringcount, n, stringptr);
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Free store obtained by get_substring *
|
||||
*************************************************/
|
||||
|
||||
/* This function exists for the benefit of people calling PCRE from non-C
|
||||
programs that can call its functions, but not free() or (pcre_free)() directly.
|
||||
|
||||
Argument: the result of a previous pcre_get_substring()
|
||||
Returns: nothing
|
||||
*/
|
||||
|
||||
void
|
||||
pcre_free_substring(const char *pointer)
|
||||
{
|
||||
(pcre_free)((void *)pointer);
|
||||
}
|
||||
|
||||
/* End of get.c */
|
||||
@@ -1,697 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
|
||||
/* This is a library of functions to support regular expressions whose syntax
|
||||
and semantics are as close as possible to those of the Perl 5 language. See
|
||||
the file Tech.Notes for some information on the internals.
|
||||
|
||||
Written by: Philip Hazel <[email protected]>
|
||||
|
||||
Copyright (c) 1997-2003 University of Cambridge
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the University of Cambridge nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
-----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
/* This header contains definitions that are shared between the different
|
||||
modules, but which are not relevant to the outside. */
|
||||
|
||||
/* Get the definitions provided by running "configure" */
|
||||
|
||||
//#include "config.h"
|
||||
#define HAVE_MEMMOVE 1
|
||||
#define NEWLINE '\n'
|
||||
#define LINK_SIZE 2
|
||||
#define HAVE_STRERROR 1
|
||||
#define EBCDIC 0
|
||||
#define MATCH_LIMIT 10000000
|
||||
#define POSIX_MALLOC_THRESHOLD 10
|
||||
#define EXPORT
|
||||
|
||||
#if defined(_MSC_VER)
|
||||
#pragma warning( disable : 4244 )
|
||||
#endif
|
||||
|
||||
/* Standard C headers plus the external interface definition. The only time
|
||||
setjmp and stdarg are used is when NO_RECURSE is set. */
|
||||
|
||||
#include <ctype.h>
|
||||
#include <limits.h>
|
||||
#include <setjmp.h>
|
||||
#include <stdarg.h>
|
||||
#include <stddef.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#ifndef PCRE_SPY
|
||||
#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */
|
||||
#endif
|
||||
|
||||
#include "pcre.h"
|
||||
|
||||
/* When compiling for use with the Virtual Pascal compiler, these functions
|
||||
need to have their names changed. PCRE must be compiled with the -DVPCOMPAT
|
||||
option on the command line. */
|
||||
|
||||
#ifdef VPCOMPAT
|
||||
#define strncmp(s1,s2,m) _strncmp(s1,s2,m)
|
||||
#define memcpy(d,s,n) _memcpy(d,s,n)
|
||||
#define memmove(d,s,n) _memmove(d,s,n)
|
||||
#define memset(s,c,n) _memset(s,c,n)
|
||||
#else /* VPCOMPAT */
|
||||
|
||||
/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(),
|
||||
define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY
|
||||
is set. Otherwise, include an emulating function for those systems that have
|
||||
neither (there some non-Unix environments where this is the case). This assumes
|
||||
that all calls to memmove are moving strings upwards in store, which is the
|
||||
case in PCRE. */
|
||||
|
||||
#if ! HAVE_MEMMOVE
|
||||
#undef memmove /* some systems may have a macro */
|
||||
#if HAVE_BCOPY
|
||||
#define memmove(a, b, c) bcopy(b, a, c)
|
||||
#else /* HAVE_BCOPY */
|
||||
void *
|
||||
pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n)
|
||||
{
|
||||
int i;
|
||||
dest += n;
|
||||
src += n;
|
||||
for (i = 0; i < n; ++i) *(--dest) = *(--src);
|
||||
}
|
||||
#define memmove(a, b, c) pcre_memmove(a, b, c)
|
||||
#endif /* not HAVE_BCOPY */
|
||||
#endif /* not HAVE_MEMMOVE */
|
||||
#endif /* not VPCOMPAT */
|
||||
|
||||
|
||||
/* PCRE keeps offsets in its compiled code as 2-byte quantities by default.
|
||||
These are used, for example, to link from the start of a subpattern to its
|
||||
alternatives and its end. The use of 2 bytes per offset limits the size of the
|
||||
compiled regex to around 64K, which is big enough for almost everybody.
|
||||
However, I received a request for an even bigger limit. For this reason, and
|
||||
also to make the code easier to maintain, the storing and loading of offsets
|
||||
from the byte string is now handled by the macros that are defined here.
|
||||
|
||||
The macros are controlled by the value of LINK_SIZE. This defaults to 2 in
|
||||
the config.h file, but can be overridden by using -D on the command line. This
|
||||
is automated on Unix systems via the "configure" command. */
|
||||
|
||||
#if LINK_SIZE == 2
|
||||
|
||||
#define PUT(a,n,d) \
|
||||
(a[n] = (d) >> 8), \
|
||||
(a[(n)+1] = (d) & 255)
|
||||
|
||||
#define GET(a,n) \
|
||||
(((a)[n] << 8) | (a)[(n)+1])
|
||||
|
||||
#define MAX_PATTERN_SIZE (1 << 16)
|
||||
|
||||
|
||||
#elif LINK_SIZE == 3
|
||||
|
||||
#define PUT(a,n,d) \
|
||||
(a[n] = (d) >> 16), \
|
||||
(a[(n)+1] = (d) >> 8), \
|
||||
(a[(n)+2] = (d) & 255)
|
||||
|
||||
#define GET(a,n) \
|
||||
(((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2])
|
||||
|
||||
#define MAX_PATTERN_SIZE (1 << 24)
|
||||
|
||||
|
||||
#elif LINK_SIZE == 4
|
||||
|
||||
#define PUT(a,n,d) \
|
||||
(a[n] = (d) >> 24), \
|
||||
(a[(n)+1] = (d) >> 16), \
|
||||
(a[(n)+2] = (d) >> 8), \
|
||||
(a[(n)+3] = (d) & 255)
|
||||
|
||||
#define GET(a,n) \
|
||||
(((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3])
|
||||
|
||||
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
|
||||
|
||||
|
||||
#else
|
||||
#error LINK_SIZE must be either 2, 3, or 4
|
||||
#endif
|
||||
|
||||
|
||||
/* Convenience macro defined in terms of the others */
|
||||
|
||||
#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE
|
||||
|
||||
|
||||
/* PCRE uses some other 2-byte quantities that do not change when the size of
|
||||
offsets changes. There are used for repeat counts and for other things such as
|
||||
capturing parenthesis numbers in back references. */
|
||||
|
||||
#define PUT2(a,n,d) \
|
||||
a[n] = (d) >> 8; \
|
||||
a[(n)+1] = (d) & 255
|
||||
|
||||
#define GET2(a,n) \
|
||||
(((a)[n] << 8) | (a)[(n)+1])
|
||||
|
||||
#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2
|
||||
|
||||
|
||||
/* In case there is no definition of offsetof() provided - though any proper
|
||||
Standard C system should have one. */
|
||||
|
||||
#ifndef offsetof
|
||||
#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field))
|
||||
#endif
|
||||
|
||||
/* These are the public options that can change during matching. */
|
||||
|
||||
#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
|
||||
|
||||
/* Private options flags start at the most significant end of the four bytes,
|
||||
but skip the top bit so we can use ints for convenience without getting tangled
|
||||
with negative values. The public options defined in pcre.h start at the least
|
||||
significant end. Make sure they don't overlap, though now that we have expanded
|
||||
to four bytes there is plenty of space. */
|
||||
|
||||
#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */
|
||||
#define PCRE_REQCHSET 0x20000000 /* req_byte is set */
|
||||
#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */
|
||||
#define PCRE_ICHANGED 0x08000000 /* i option changes within regex */
|
||||
|
||||
/* Options for the "extra" block produced by pcre_study(). */
|
||||
|
||||
#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */
|
||||
|
||||
/* Masks for identifying the public options which are permitted at compile
|
||||
time, run time or study time, respectively. */
|
||||
|
||||
#define PUBLIC_OPTIONS \
|
||||
(PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
|
||||
PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
|
||||
PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK)
|
||||
|
||||
#define PUBLIC_EXEC_OPTIONS \
|
||||
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK)
|
||||
|
||||
#define PUBLIC_STUDY_OPTIONS 0 /* None defined */
|
||||
|
||||
/* Magic number to provide a small check against being handed junk. */
|
||||
|
||||
#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */
|
||||
|
||||
/* Negative values for the firstchar and reqchar variables */
|
||||
|
||||
#define REQ_UNSET (-2)
|
||||
#define REQ_NONE (-1)
|
||||
|
||||
/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a
|
||||
variable-length repeat, or a anything other than literal characters. */
|
||||
|
||||
#define REQ_CASELESS 0x0100 /* indicates caselessness */
|
||||
#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */
|
||||
|
||||
/* Miscellaneous definitions */
|
||||
|
||||
typedef int BOOL;
|
||||
|
||||
#define FALSE 0
|
||||
#define TRUE 1
|
||||
|
||||
/* Escape items that are just an encoding of a particular data value. Note that
|
||||
ESC_n is defined as yet another macro, which is set in config.h to either \n
|
||||
(the default) or \r (which some people want). */
|
||||
|
||||
#ifndef ESC_e
|
||||
#define ESC_e 27
|
||||
#endif
|
||||
|
||||
#ifndef ESC_f
|
||||
#define ESC_f '\f'
|
||||
#endif
|
||||
|
||||
#ifndef ESC_n
|
||||
#define ESC_n NEWLINE
|
||||
#endif
|
||||
|
||||
#ifndef ESC_r
|
||||
#define ESC_r '\r'
|
||||
#endif
|
||||
|
||||
/* We can't officially use ESC_t because it is a POSIX reserved identifier
|
||||
(presumably because of all the others like size_t). */
|
||||
|
||||
#ifndef ESC_tee
|
||||
#define ESC_tee '\t'
|
||||
#endif
|
||||
|
||||
/* These are escaped items that aren't just an encoding of a particular data
|
||||
value such as \n. They must have non-zero values, as check_escape() returns
|
||||
their negation. Also, they must appear in the same order as in the opcode
|
||||
definitions below, up to ESC_z. There's a dummy for OP_ANY because it
|
||||
corresponds to "." rather than an escape sequence. The final one must be
|
||||
ESC_REF as subsequent values are used for \1, \2, \3, etc. There is are two
|
||||
tests in the code for an escape greater than ESC_b and less than ESC_Z to
|
||||
detect the types that may be repeated. These are the types that consume a
|
||||
character. If any new escapes are put in between that don't consume a
|
||||
character, that code will have to change. */
|
||||
|
||||
enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W,
|
||||
ESC_w, ESC_dum1, ESC_C, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_REF };
|
||||
|
||||
/* Flag bits and data types for the extended class (OP_XCLASS) for classes that
|
||||
contain UTF-8 characters with values greater than 255. */
|
||||
|
||||
#define XCL_NOT 0x01 /* Flag: this is a negative class */
|
||||
#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */
|
||||
|
||||
#define XCL_END 0 /* Marks end of individual items */
|
||||
#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */
|
||||
#define XCL_RANGE 2 /* A range (two multibyte chars) follows */
|
||||
|
||||
|
||||
/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets
|
||||
that extract substrings. Starting from 1 (i.e. after OP_END), the values up to
|
||||
OP_EOD must correspond in order to the list of escapes immediately above.
|
||||
Note that whenever this list is updated, the two macro definitions that follow
|
||||
must also be updated to match. */
|
||||
|
||||
enum {
|
||||
OP_END, /* 0 End of pattern */
|
||||
|
||||
/* Values corresponding to backslashed metacharacters */
|
||||
|
||||
OP_SOD, /* 1 Start of data: \A */
|
||||
OP_SOM, /* 2 Start of match (subject + offset): \G */
|
||||
OP_NOT_WORD_BOUNDARY, /* 3 \B */
|
||||
OP_WORD_BOUNDARY, /* 4 \b */
|
||||
OP_NOT_DIGIT, /* 5 \D */
|
||||
OP_DIGIT, /* 6 \d */
|
||||
OP_NOT_WHITESPACE, /* 7 \S */
|
||||
OP_WHITESPACE, /* 8 \s */
|
||||
OP_NOT_WORDCHAR, /* 9 \W */
|
||||
OP_WORDCHAR, /* 10 \w */
|
||||
OP_ANY, /* 11 Match any character */
|
||||
OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */
|
||||
OP_EODN, /* 13 End of data or \n at end of data: \Z. */
|
||||
OP_EOD, /* 14 End of data: \z */
|
||||
|
||||
OP_OPT, /* 15 Set runtime options */
|
||||
OP_CIRC, /* 16 Start of line - varies with multiline switch */
|
||||
OP_DOLL, /* 17 End of line - varies with multiline switch */
|
||||
OP_CHARS, /* 18 Match string of characters */
|
||||
OP_NOT, /* 19 Match anything but the following char */
|
||||
|
||||
OP_STAR, /* 20 The maximizing and minimizing versions of */
|
||||
OP_MINSTAR, /* 21 all these opcodes must come in pairs, with */
|
||||
OP_PLUS, /* 22 the minimizing one second. */
|
||||
OP_MINPLUS, /* 23 This first set applies to single characters */
|
||||
OP_QUERY, /* 24 */
|
||||
OP_MINQUERY, /* 25 */
|
||||
OP_UPTO, /* 26 From 0 to n matches */
|
||||
OP_MINUPTO, /* 27 */
|
||||
OP_EXACT, /* 28 Exactly n matches */
|
||||
|
||||
OP_NOTSTAR, /* 29 The maximizing and minimizing versions of */
|
||||
OP_NOTMINSTAR, /* 30 all these opcodes must come in pairs, with */
|
||||
OP_NOTPLUS, /* 31 the minimizing one second. */
|
||||
OP_NOTMINPLUS, /* 32 This set applies to "not" single characters */
|
||||
OP_NOTQUERY, /* 33 */
|
||||
OP_NOTMINQUERY, /* 34 */
|
||||
OP_NOTUPTO, /* 35 From 0 to n matches */
|
||||
OP_NOTMINUPTO, /* 36 */
|
||||
OP_NOTEXACT, /* 37 Exactly n matches */
|
||||
|
||||
OP_TYPESTAR, /* 38 The maximizing and minimizing versions of */
|
||||
OP_TYPEMINSTAR, /* 39 all these opcodes must come in pairs, with */
|
||||
OP_TYPEPLUS, /* 40 the minimizing one second. These codes must */
|
||||
OP_TYPEMINPLUS, /* 41 be in exactly the same order as those above. */
|
||||
OP_TYPEQUERY, /* 42 This set applies to character types such as \d */
|
||||
OP_TYPEMINQUERY, /* 43 */
|
||||
OP_TYPEUPTO, /* 44 From 0 to n matches */
|
||||
OP_TYPEMINUPTO, /* 45 */
|
||||
OP_TYPEEXACT, /* 46 Exactly n matches */
|
||||
|
||||
OP_CRSTAR, /* 47 The maximizing and minimizing versions of */
|
||||
OP_CRMINSTAR, /* 48 all these opcodes must come in pairs, with */
|
||||
OP_CRPLUS, /* 49 the minimizing one second. These codes must */
|
||||
OP_CRMINPLUS, /* 50 be in exactly the same order as those above. */
|
||||
OP_CRQUERY, /* 51 These are for character classes and back refs */
|
||||
OP_CRMINQUERY, /* 52 */
|
||||
OP_CRRANGE, /* 53 These are different to the three seta above. */
|
||||
OP_CRMINRANGE, /* 54 */
|
||||
|
||||
OP_CLASS, /* 55 Match a character class, chars < 256 only */
|
||||
OP_NCLASS, /* 56 Same, but the bitmap was created from a negative
|
||||
class - the difference is relevant only when a UTF-8
|
||||
character > 255 is encountered. */
|
||||
|
||||
OP_XCLASS, /* 57 Extended class for handling UTF-8 chars within the
|
||||
class. This does both positive and negative. */
|
||||
|
||||
OP_REF, /* 58 Match a back reference */
|
||||
OP_RECURSE, /* 59 Match a numbered subpattern (possibly recursive) */
|
||||
OP_CALLOUT, /* 60 Call out to external function if provided */
|
||||
|
||||
OP_ALT, /* 61 Start of alternation */
|
||||
OP_KET, /* 62 End of group that doesn't have an unbounded repeat */
|
||||
OP_KETRMAX, /* 63 These two must remain together and in this */
|
||||
OP_KETRMIN, /* 64 order. They are for groups the repeat for ever. */
|
||||
|
||||
/* The assertions must come before ONCE and COND */
|
||||
|
||||
OP_ASSERT, /* 65 Positive lookahead */
|
||||
OP_ASSERT_NOT, /* 66 Negative lookahead */
|
||||
OP_ASSERTBACK, /* 67 Positive lookbehind */
|
||||
OP_ASSERTBACK_NOT, /* 68 Negative lookbehind */
|
||||
OP_REVERSE, /* 69 Move pointer back - used in lookbehind assertions */
|
||||
|
||||
/* ONCE and COND must come after the assertions, with ONCE first, as there's
|
||||
a test for >= ONCE for a subpattern that isn't an assertion. */
|
||||
|
||||
OP_ONCE, /* 70 Once matched, don't back up into the subpattern */
|
||||
OP_COND, /* 71 Conditional group */
|
||||
OP_CREF, /* 72 Used to hold an extraction string number (cond ref) */
|
||||
|
||||
OP_BRAZERO, /* 73 These two must remain together and in this */
|
||||
OP_BRAMINZERO, /* 74 order. */
|
||||
|
||||
OP_BRANUMBER, /* 75 Used for extracting brackets whose number is greater
|
||||
than can fit into an opcode. */
|
||||
|
||||
OP_BRA /* 76 This and greater values are used for brackets that
|
||||
extract substrings up to a basic limit. After that,
|
||||
use is made of OP_BRANUMBER. */
|
||||
};
|
||||
|
||||
/* WARNING: There is an implicit assumption in study.c that all opcodes are
|
||||
less than 128 in value. This makes handling UTF-8 character sequences easier.
|
||||
*/
|
||||
|
||||
|
||||
/* This macro defines textual names for all the opcodes. There are used only
|
||||
for debugging, in pcre.c when DEBUG is defined, and also in pcretest.c. The
|
||||
macro is referenced only in printint.c. */
|
||||
|
||||
#define OP_NAME_LIST \
|
||||
"End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \
|
||||
"\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", "\\Z", "\\z", \
|
||||
"Opt", "^", "$", "chars", "not", \
|
||||
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
|
||||
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
|
||||
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
|
||||
"*", "*?", "+", "+?", "?", "??", "{", "{", \
|
||||
"class", "nclass", "xclass", "Ref", "Recurse", "Callout", \
|
||||
"Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \
|
||||
"AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\
|
||||
"Brazero", "Braminzero", "Branumber", "Bra"
|
||||
|
||||
|
||||
/* This macro defines the length of fixed length operations in the compiled
|
||||
regex. The lengths are used when searching for specific things, and also in the
|
||||
debugging printing of a compiled regex. We use a macro so that it can be
|
||||
incorporated both into pcre.c and pcretest.c without being publicly exposed.
|
||||
|
||||
As things have been extended, some of these are no longer fixed lenths, but are
|
||||
minima instead. For example, the length of a single-character repeat may vary
|
||||
in UTF-8 mode. The code that uses this table must know about such things. */
|
||||
|
||||
#define OP_LENGTHS \
|
||||
1, /* End */ \
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \
|
||||
1, 1, 1, 1, 2, 1, 1, /* Any, Anybyte, \Z, \z, Opt, ^, $ */ \
|
||||
2, /* Chars - the minimum length */ \
|
||||
2, /* not */ \
|
||||
/* Positive single-char repeats ** These are */ \
|
||||
2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \
|
||||
4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \
|
||||
/* Negative single-char repeats - only for chars < 256 */ \
|
||||
2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \
|
||||
4, 4, 4, /* NOT upto, minupto, exact */ \
|
||||
/* Positive type repeats */ \
|
||||
2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \
|
||||
4, 4, 4, /* Type upto, minupto, exact */ \
|
||||
/* Character class & ref repeats */ \
|
||||
1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \
|
||||
5, 5, /* CRRANGE, CRMINRANGE */ \
|
||||
33, /* CLASS */ \
|
||||
33, /* NCLASS */ \
|
||||
0, /* XCLASS - variable length */ \
|
||||
3, /* REF */ \
|
||||
1+LINK_SIZE, /* RECURSE */ \
|
||||
2, /* CALLOUT */ \
|
||||
1+LINK_SIZE, /* Alt */ \
|
||||
1+LINK_SIZE, /* Ket */ \
|
||||
1+LINK_SIZE, /* KetRmax */ \
|
||||
1+LINK_SIZE, /* KetRmin */ \
|
||||
1+LINK_SIZE, /* Assert */ \
|
||||
1+LINK_SIZE, /* Assert not */ \
|
||||
1+LINK_SIZE, /* Assert behind */ \
|
||||
1+LINK_SIZE, /* Assert behind not */ \
|
||||
1+LINK_SIZE, /* Reverse */ \
|
||||
1+LINK_SIZE, /* Once */ \
|
||||
1+LINK_SIZE, /* COND */ \
|
||||
3, /* CREF */ \
|
||||
1, 1, /* BRAZERO, BRAMINZERO */ \
|
||||
3, /* BRANUMBER */ \
|
||||
1+LINK_SIZE /* BRA */ \
|
||||
|
||||
|
||||
/* The highest extraction number before we have to start using additional
|
||||
bytes. (Originally PCRE didn't have support for extraction counts highter than
|
||||
this number.) The value is limited by the number of opcodes left after OP_BRA,
|
||||
i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional
|
||||
opcodes. */
|
||||
|
||||
#define EXTRACT_BASIC_MAX 150
|
||||
|
||||
/* A magic value for OP_CREF to indicate the "in recursion" condition. */
|
||||
|
||||
#define CREF_RECURSE 0xffff
|
||||
|
||||
/* The texts of compile-time error messages are defined as macros here so that
|
||||
they can be accessed by the POSIX wrapper and converted into error codes. Yes,
|
||||
I could have used error codes in the first place, but didn't feel like changing
|
||||
just to accommodate the POSIX wrapper. */
|
||||
|
||||
#define ERR1 "\\ at end of pattern"
|
||||
#define ERR2 "\\c at end of pattern"
|
||||
#define ERR3 "unrecognized character follows \\"
|
||||
#define ERR4 "numbers out of order in {} quantifier"
|
||||
#define ERR5 "number too big in {} quantifier"
|
||||
#define ERR6 "missing terminating ] for character class"
|
||||
#define ERR7 "invalid escape sequence in character class"
|
||||
#define ERR8 "range out of order in character class"
|
||||
#define ERR9 "nothing to repeat"
|
||||
#define ERR10 "operand of unlimited repeat could match the empty string"
|
||||
#define ERR11 "internal error: unexpected repeat"
|
||||
#define ERR12 "unrecognized character after (?"
|
||||
#define ERR13 "POSIX named classes are supported only within a class"
|
||||
#define ERR14 "missing )"
|
||||
#define ERR15 "reference to non-existent subpattern"
|
||||
#define ERR16 "erroffset passed as NULL"
|
||||
#define ERR17 "unknown option bit(s) set"
|
||||
#define ERR18 "missing ) after comment"
|
||||
#define ERR19 "parentheses nested too deeply"
|
||||
#define ERR20 "regular expression too large"
|
||||
#define ERR21 "failed to get memory"
|
||||
#define ERR22 "unmatched parentheses"
|
||||
#define ERR23 "internal error: code overflow"
|
||||
#define ERR24 "unrecognized character after (?<"
|
||||
#define ERR25 "lookbehind assertion is not fixed length"
|
||||
#define ERR26 "malformed number after (?("
|
||||
#define ERR27 "conditional group contains more than two branches"
|
||||
#define ERR28 "assertion expected after (?("
|
||||
#define ERR29 "(?R or (?digits must be followed by )"
|
||||
#define ERR30 "unknown POSIX class name"
|
||||
#define ERR31 "POSIX collating elements are not supported"
|
||||
#define ERR32 "this version of PCRE is not compiled with PCRE_UTF8 support"
|
||||
#define ERR33 "spare error"
|
||||
#define ERR34 "character value in \\x{...} sequence is too large"
|
||||
#define ERR35 "invalid condition (?(0)"
|
||||
#define ERR36 "\\C not allowed in lookbehind assertion"
|
||||
#define ERR37 "PCRE does not support \\L, \\l, \\N, \\P, \\p, \\U, \\u, or \\X"
|
||||
#define ERR38 "number after (?C is > 255"
|
||||
#define ERR39 "closing ) for (?C expected"
|
||||
#define ERR40 "recursive call could loop indefinitely"
|
||||
#define ERR41 "unrecognized character after (?P"
|
||||
#define ERR42 "syntax error after (?P"
|
||||
#define ERR43 "two named groups have the same name"
|
||||
#define ERR44 "invalid UTF-8 string"
|
||||
|
||||
/* All character handling must be done as unsigned characters. Otherwise there
|
||||
are problems with top-bit-set characters and functions such as isspace().
|
||||
However, we leave the interface to the outside world as char *, because that
|
||||
should make things easier for callers. We define a short type for unsigned char
|
||||
to save lots of typing. I tried "uchar", but it causes problems on Digital
|
||||
Unix, where it is defined in sys/types, so use "uschar" instead. */
|
||||
|
||||
typedef unsigned char uschar;
|
||||
|
||||
/* The real format of the start of the pcre block; the index of names and the
|
||||
code vector run on as long as necessary after the end. */
|
||||
|
||||
typedef struct real_pcre {
|
||||
unsigned long int magic_number;
|
||||
size_t size; /* Total that was malloced */
|
||||
const unsigned char *tables; /* Pointer to tables */
|
||||
unsigned long int options;
|
||||
unsigned short int top_bracket;
|
||||
unsigned short int top_backref;
|
||||
unsigned short int first_byte;
|
||||
unsigned short int req_byte;
|
||||
unsigned short int name_entry_size; /* Size of any name items; 0 => none */
|
||||
unsigned short int name_count; /* Number of name items */
|
||||
} real_pcre;
|
||||
|
||||
/* The format of the block used to store data from pcre_study(). */
|
||||
|
||||
typedef struct pcre_study_data {
|
||||
size_t size; /* Total that was malloced */
|
||||
uschar options;
|
||||
uschar start_bits[32];
|
||||
} pcre_study_data;
|
||||
|
||||
/* Structure for passing "static" information around between the functions
|
||||
doing the compiling, so that they are thread-safe. */
|
||||
|
||||
typedef struct compile_data {
|
||||
const uschar *lcc; /* Points to lower casing table */
|
||||
const uschar *fcc; /* Points to case-flipping table */
|
||||
const uschar *cbits; /* Points to character type table */
|
||||
const uschar *ctypes; /* Points to table of type maps */
|
||||
const uschar *start_code; /* The start of the compiled code */
|
||||
uschar *name_table; /* The name/number table */
|
||||
int names_found; /* Number of entries so far */
|
||||
int name_entry_size; /* Size of each entry */
|
||||
int top_backref; /* Maximum back reference */
|
||||
unsigned int backref_map; /* Bitmap of low back refs */
|
||||
int req_varyopt; /* "After variable item" flag for reqbyte */
|
||||
} compile_data;
|
||||
|
||||
/* Structure for maintaining a chain of pointers to the currently incomplete
|
||||
branches, for testing for left recursion. */
|
||||
|
||||
typedef struct branch_chain {
|
||||
struct branch_chain *outer;
|
||||
uschar *current;
|
||||
} branch_chain;
|
||||
|
||||
/* Structure for items in a linked list that represents an explicit recursive
|
||||
call within the pattern. */
|
||||
|
||||
typedef struct recursion_info {
|
||||
struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
|
||||
int group_num; /* Number of group that was called */
|
||||
const uschar *after_call; /* "Return value": points after the call in the expr */
|
||||
const uschar *save_start; /* Old value of md->start_match */
|
||||
int *offset_save; /* Pointer to start of saved offsets */
|
||||
int saved_max; /* Number of saved offsets */
|
||||
} recursion_info;
|
||||
|
||||
/* When compiling in a mode that doesn't use recursive calls to match(),
|
||||
a structure is used to remember local variables on the heap. It is defined in
|
||||
pcre.c, close to the match() function, so that it is easy to keep it in step
|
||||
with any changes of local variable. However, the pointer to the current frame
|
||||
must be saved in some "static" place over a longjmp(). We declare the
|
||||
structure here so that we can put a pointer in the match_data structure.
|
||||
NOTE: This isn't used for a "normal" compilation of pcre. */
|
||||
|
||||
struct heapframe;
|
||||
|
||||
/* Structure for passing "static" information around between the functions
|
||||
doing the matching, so that they are thread-safe. */
|
||||
|
||||
typedef struct match_data {
|
||||
unsigned long int match_call_count; /* As it says */
|
||||
unsigned long int match_limit;/* As it says */
|
||||
int *offset_vector; /* Offset vector */
|
||||
int offset_end; /* One past the end */
|
||||
int offset_max; /* The maximum usable for return data */
|
||||
const uschar *lcc; /* Points to lower casing table */
|
||||
const uschar *ctypes; /* Points to table of type maps */
|
||||
BOOL offset_overflow; /* Set if too many extractions */
|
||||
BOOL notbol; /* NOTBOL flag */
|
||||
BOOL noteol; /* NOTEOL flag */
|
||||
BOOL utf8; /* UTF8 flag */
|
||||
BOOL endonly; /* Dollar not before final \n */
|
||||
BOOL notempty; /* Empty string match not wanted */
|
||||
const uschar *start_code; /* For use when recursing */
|
||||
const uschar *start_subject; /* Start of the subject string */
|
||||
const uschar *end_subject; /* End of the subject string */
|
||||
const uschar *start_match; /* Start of this match attempt */
|
||||
const uschar *end_match_ptr; /* Subject position at end match */
|
||||
int end_offset_top; /* Highwater mark at end of match */
|
||||
int capture_last; /* Most recent capture number */
|
||||
int start_offset; /* The start offset value */
|
||||
recursion_info *recursive; /* Linked list of recursion data */
|
||||
void *callout_data; /* To pass back to callouts */
|
||||
struct heapframe *thisframe; /* Used only when compiling for no recursion */
|
||||
} match_data;
|
||||
|
||||
/* Bit definitions for entries in the pcre_ctypes table. */
|
||||
|
||||
#define ctype_space 0x01
|
||||
#define ctype_letter 0x02
|
||||
#define ctype_digit 0x04
|
||||
#define ctype_xdigit 0x08
|
||||
#define ctype_word 0x10 /* alphameric or '_' */
|
||||
#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */
|
||||
|
||||
/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set
|
||||
of bits for a class map. Some classes are built by combining these tables. */
|
||||
|
||||
#define cbit_space 0 /* [:space:] or \s */
|
||||
#define cbit_xdigit 32 /* [:xdigit:] */
|
||||
#define cbit_digit 64 /* [:digit:] or \d */
|
||||
#define cbit_upper 96 /* [:upper:] */
|
||||
#define cbit_lower 128 /* [:lower:] */
|
||||
#define cbit_word 160 /* [:word:] or \w */
|
||||
#define cbit_graph 192 /* [:graph:] */
|
||||
#define cbit_print 224 /* [:print:] */
|
||||
#define cbit_punct 256 /* [:punct:] */
|
||||
#define cbit_cntrl 288 /* [:cntrl:] */
|
||||
#define cbit_length 320 /* Length of the cbits table */
|
||||
|
||||
/* Offsets of the various tables from the base tables pointer, and
|
||||
total length. */
|
||||
|
||||
#define lcc_offset 0
|
||||
#define fcc_offset 256
|
||||
#define cbits_offset 512
|
||||
#define ctypes_offset (cbits_offset + cbit_length)
|
||||
#define tables_length (ctypes_offset + 256)
|
||||
|
||||
/* End of internal.h */
|
||||
@@ -1,148 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
/*
|
||||
PCRE is a library of functions to support regular expressions whose syntax
|
||||
and semantics are as close as possible to those of the Perl 5 language.
|
||||
|
||||
Written by: Philip Hazel <[email protected]>
|
||||
|
||||
Copyright (c) 1997-2003 University of Cambridge
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the University of Cambridge nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
See the file Tech.Notes for some information on the internals.
|
||||
*/
|
||||
|
||||
|
||||
/* This file is compiled on its own as part of the PCRE library. However,
|
||||
it is also included in the compilation of dftables.c, in which case the macro
|
||||
DFTABLES is defined. */
|
||||
|
||||
#ifndef DFTABLES
|
||||
#include "internal.h"
|
||||
#endif
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Create PCRE character tables *
|
||||
*************************************************/
|
||||
|
||||
/* This function builds a set of character tables for use by PCRE and returns
|
||||
a pointer to them. They are build using the ctype functions, and consequently
|
||||
their contents will depend upon the current locale setting. When compiled as
|
||||
part of the library, the store is obtained via pcre_malloc(), but when compiled
|
||||
inside dftables, use malloc().
|
||||
|
||||
Arguments: none
|
||||
Returns: pointer to the contiguous block of data
|
||||
*/
|
||||
|
||||
const unsigned char *
|
||||
pcre_maketables(void)
|
||||
{
|
||||
unsigned char *yield, *p;
|
||||
int i;
|
||||
|
||||
#ifndef DFTABLES
|
||||
yield = (unsigned char*)(pcre_malloc)(tables_length);
|
||||
#else
|
||||
yield = (unsigned char*)malloc(tables_length);
|
||||
#endif
|
||||
|
||||
if (yield == NULL) return NULL;
|
||||
p = yield;
|
||||
|
||||
/* First comes the lower casing table */
|
||||
|
||||
for (i = 0; i < 256; i++) *p++ = tolower(i);
|
||||
|
||||
/* Next the case-flipping table */
|
||||
|
||||
for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i);
|
||||
|
||||
/* Then the character class tables. Don't try to be clever and save effort
|
||||
on exclusive ones - in some locales things may be different. Note that the
|
||||
table for "space" includes everything "isspace" gives, including VT in the
|
||||
default locale. This makes it work for the POSIX class [:space:]. */
|
||||
|
||||
memset(p, 0, cbit_length);
|
||||
for (i = 0; i < 256; i++)
|
||||
{
|
||||
if (isdigit(i))
|
||||
{
|
||||
p[cbit_digit + i/8] |= 1 << (i&7);
|
||||
p[cbit_word + i/8] |= 1 << (i&7);
|
||||
}
|
||||
if (isupper(i))
|
||||
{
|
||||
p[cbit_upper + i/8] |= 1 << (i&7);
|
||||
p[cbit_word + i/8] |= 1 << (i&7);
|
||||
}
|
||||
if (islower(i))
|
||||
{
|
||||
p[cbit_lower + i/8] |= 1 << (i&7);
|
||||
p[cbit_word + i/8] |= 1 << (i&7);
|
||||
}
|
||||
if (i == '_') p[cbit_word + i/8] |= 1 << (i&7);
|
||||
if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7);
|
||||
if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7);
|
||||
if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7);
|
||||
if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7);
|
||||
if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7);
|
||||
if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7);
|
||||
}
|
||||
p += cbit_length;
|
||||
|
||||
/* Finally, the character type table. In this, we exclude VT from the white
|
||||
space chars, because Perl doesn't recognize it as such for \s and for comments
|
||||
within regexes. */
|
||||
|
||||
for (i = 0; i < 256; i++)
|
||||
{
|
||||
int x = 0;
|
||||
if (i != 0x0b && isspace(i)) x += ctype_space;
|
||||
if (isalpha(i)) x += ctype_letter;
|
||||
if (isdigit(i)) x += ctype_digit;
|
||||
if (isxdigit(i)) x += ctype_xdigit;
|
||||
if (isalnum(i) || i == '_') x += ctype_word;
|
||||
|
||||
/* Note: strchr includes the terminating zero in the characters it considers.
|
||||
In this instance, that is ok because we want binary zero to be flagged as a
|
||||
meta-character, which in this sense is any character that terminates a run
|
||||
of data characters. */
|
||||
|
||||
if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; *p++ = x; }
|
||||
|
||||
return yield;
|
||||
}
|
||||
|
||||
/* End of maketables.c */
|
||||
-8319
File diff suppressed because it is too large
Load Diff
-193
@@ -1,193 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
/* Copyright (c) 1997-2003 University of Cambridge */
|
||||
|
||||
#ifndef _PCRE_H
|
||||
#define _PCRE_H
|
||||
|
||||
/* The file pcre.h is build by "configure". Do not edit it; instead
|
||||
make changes to pcre.in. */
|
||||
|
||||
#define PCRE_MAJOR 4
|
||||
#define PCRE_MINOR 5
|
||||
#define PCRE_DATE 01-December-2003
|
||||
|
||||
/* Win32 uses DLL by default */
|
||||
|
||||
/* #ifdef _WIN32
|
||||
# ifdef PCRE_DEFINITION
|
||||
# ifdef DLL_EXPORT
|
||||
# define PCRE_DATA_SCOPE __declspec(dllexport)
|
||||
# endif
|
||||
# else
|
||||
# ifndef PCRE_STATIC
|
||||
# define PCRE_DATA_SCOPE extern __declspec(dllimport)
|
||||
# endif
|
||||
# endif
|
||||
#endif */
|
||||
#ifndef PCRE_DATA_SCOPE
|
||||
# define PCRE_DATA_SCOPE extern
|
||||
#endif
|
||||
|
||||
/* Have to include stdlib.h in order to ensure that size_t is defined;
|
||||
it is needed here for malloc. */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
/* Allow for C++ users */
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* Options */
|
||||
|
||||
#define PCRE_CASELESS 0x0001
|
||||
#define PCRE_MULTILINE 0x0002
|
||||
#define PCRE_DOTALL 0x0004
|
||||
#define PCRE_EXTENDED 0x0008
|
||||
#define PCRE_ANCHORED 0x0010
|
||||
#define PCRE_DOLLAR_ENDONLY 0x0020
|
||||
#define PCRE_EXTRA 0x0040
|
||||
#define PCRE_NOTBOL 0x0080
|
||||
#define PCRE_NOTEOL 0x0100
|
||||
#define PCRE_UNGREEDY 0x0200
|
||||
#define PCRE_NOTEMPTY 0x0400
|
||||
#define PCRE_UTF8 0x0800
|
||||
#define PCRE_NO_AUTO_CAPTURE 0x1000
|
||||
#define PCRE_NO_UTF8_CHECK 0x2000
|
||||
|
||||
/* Exec-time and get/set-time error codes */
|
||||
|
||||
#define PCRE_ERROR_NOMATCH (-1)
|
||||
#define PCRE_ERROR_NULL (-2)
|
||||
#define PCRE_ERROR_BADOPTION (-3)
|
||||
#define PCRE_ERROR_BADMAGIC (-4)
|
||||
#define PCRE_ERROR_UNKNOWN_NODE (-5)
|
||||
#define PCRE_ERROR_NOMEMORY (-6)
|
||||
#define PCRE_ERROR_NOSUBSTRING (-7)
|
||||
#define PCRE_ERROR_MATCHLIMIT (-8)
|
||||
#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */
|
||||
#define PCRE_ERROR_BADUTF8 (-10)
|
||||
#define PCRE_ERROR_BADUTF8_OFFSET (-11)
|
||||
|
||||
/* Request types for pcre_fullinfo() */
|
||||
|
||||
#define PCRE_INFO_OPTIONS 0
|
||||
#define PCRE_INFO_SIZE 1
|
||||
#define PCRE_INFO_CAPTURECOUNT 2
|
||||
#define PCRE_INFO_BACKREFMAX 3
|
||||
#define PCRE_INFO_FIRSTBYTE 4
|
||||
#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */
|
||||
#define PCRE_INFO_FIRSTTABLE 5
|
||||
#define PCRE_INFO_LASTLITERAL 6
|
||||
#define PCRE_INFO_NAMEENTRYSIZE 7
|
||||
#define PCRE_INFO_NAMECOUNT 8
|
||||
#define PCRE_INFO_NAMETABLE 9
|
||||
#define PCRE_INFO_STUDYSIZE 10
|
||||
|
||||
/* Request types for pcre_config() */
|
||||
|
||||
#define PCRE_CONFIG_UTF8 0
|
||||
#define PCRE_CONFIG_NEWLINE 1
|
||||
#define PCRE_CONFIG_LINK_SIZE 2
|
||||
#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3
|
||||
#define PCRE_CONFIG_MATCH_LIMIT 4
|
||||
#define PCRE_CONFIG_STACKRECURSE 5
|
||||
|
||||
/* Bit flags for the pcre_extra structure */
|
||||
|
||||
#define PCRE_EXTRA_STUDY_DATA 0x0001
|
||||
#define PCRE_EXTRA_MATCH_LIMIT 0x0002
|
||||
#define PCRE_EXTRA_CALLOUT_DATA 0x0004
|
||||
|
||||
/* Types */
|
||||
|
||||
struct real_pcre; /* declaration; the definition is private */
|
||||
typedef struct real_pcre pcre;
|
||||
|
||||
/* The structure for passing additional data to pcre_exec(). This is defined in
|
||||
such as way as to be extensible. */
|
||||
|
||||
typedef struct pcre_extra {
|
||||
unsigned long int flags; /* Bits for which fields are set */
|
||||
void *study_data; /* Opaque data from pcre_study() */
|
||||
unsigned long int match_limit; /* Maximum number of calls to match() */
|
||||
void *callout_data; /* Data passed back in callouts */
|
||||
} pcre_extra;
|
||||
|
||||
/* The structure for passing out data via the pcre_callout_function. We use a
|
||||
structure so that new fields can be added on the end in future versions,
|
||||
without changing the API of the function, thereby allowing old clients to work
|
||||
without modification. */
|
||||
|
||||
typedef struct pcre_callout_block {
|
||||
int version; /* Identifies version of block */
|
||||
/* ------------------------ Version 0 ------------------------------- */
|
||||
int callout_number; /* Number compiled into pattern */
|
||||
int *offset_vector; /* The offset vector */
|
||||
const char *subject; /* The subject being matched */
|
||||
int subject_length; /* The length of the subject */
|
||||
int start_match; /* Offset to start of this match attempt */
|
||||
int current_position; /* Where we currently are */
|
||||
int capture_top; /* Max current capture */
|
||||
int capture_last; /* Most recently closed capture */
|
||||
void *callout_data; /* Data passed in with the call */
|
||||
/* ------------------------------------------------------------------ */
|
||||
} pcre_callout_block;
|
||||
|
||||
/* Indirection for store get and free functions. These can be set to
|
||||
alternative malloc/free functions if required. Special ones are used in the
|
||||
non-recursive case for "frames". There is also an optional callout function
|
||||
that is triggered by the (?) regex item. Some magic is required for Win32 DLL;
|
||||
it is null on other OS. For Virtual Pascal, these have to be different again.
|
||||
*/
|
||||
|
||||
#ifndef VPCOMPAT
|
||||
#define pcre_malloc malloc
|
||||
#define pcre_free free
|
||||
#define pcre_stack_malloc malloc
|
||||
#define pcre_stack_free free
|
||||
#define pcre_callout NULL
|
||||
#else /* VPCOMPAT */
|
||||
extern void *pcre_malloc(size_t);
|
||||
extern void pcre_free(void *);
|
||||
extern void *pcre_stack_malloc(size_t);
|
||||
extern void pcre_stack_free(void *);
|
||||
extern int pcre_callout(pcre_callout_block *);
|
||||
#endif /* VPCOMPAT */
|
||||
|
||||
/* Exported PCRE functions */
|
||||
|
||||
extern pcre *pcre_compile(const char *, int, const char **,
|
||||
int *, const unsigned char *);
|
||||
extern int pcre_config(int, void *);
|
||||
extern int pcre_copy_named_substring(const pcre *, const char *,
|
||||
int *, int, const char *, char *, int);
|
||||
extern int pcre_copy_substring(const char *, int *, int, int,
|
||||
char *, int);
|
||||
extern int pcre_exec(const pcre *, const pcre_extra *,
|
||||
const char *, int, int, int, int *, int);
|
||||
extern void pcre_free_substring(const char *);
|
||||
extern void pcre_free_substring_list(const char **);
|
||||
extern int pcre_fullinfo(const pcre *, const pcre_extra *, int,
|
||||
void *);
|
||||
extern int pcre_get_named_substring(const pcre *, const char *,
|
||||
int *, int, const char *, const char **);
|
||||
extern int pcre_get_stringnumber(const pcre *, const char *);
|
||||
extern int pcre_get_substring(const char *, int *, int, int,
|
||||
const char **);
|
||||
extern int pcre_get_substring_list(const char *, int *, int,
|
||||
const char ***);
|
||||
extern int pcre_info(const pcre *, int *, int *);
|
||||
extern const unsigned char *pcre_maketables(void);
|
||||
extern pcre_extra *pcre_study(const pcre *, int, const char **);
|
||||
extern const char *pcre_version(void);
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* extern "C" */
|
||||
#endif
|
||||
|
||||
#endif /* End of pcre.h */
|
||||
@@ -1,368 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
/*
|
||||
This is a library of functions to support regular expressions whose syntax
|
||||
and semantics are as close as possible to those of the Perl 5 language. See
|
||||
the file Tech.Notes for some information on the internals.
|
||||
|
||||
Written by: Philip Hazel <[email protected]>
|
||||
|
||||
Copyright (c) 1997-2003 University of Cambridge
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the University of Cambridge nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
-----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
|
||||
/* This module contains a debugging function for printing out the internal form
|
||||
of a compiled regular expression. It is kept in a separate file so that it can
|
||||
be #included both in the pcretest program, and in the library itself when
|
||||
compiled with the debugging switch. */
|
||||
|
||||
|
||||
static const char *OP_names[] = { OP_NAME_LIST };
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Print single- or multi-byte character *
|
||||
*************************************************/
|
||||
|
||||
/* These tables are actually copies of ones in pcre.c. If we compile the
|
||||
library with debugging, they are included twice, but that isn't really a
|
||||
problem - compiling with debugging is pretty rare and these are very small. */
|
||||
|
||||
static const int utf8_t3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
|
||||
|
||||
static const uschar utf8_t4[] = {
|
||||
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
||||
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
||||
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
|
||||
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
|
||||
|
||||
static int
|
||||
print_char(FILE *f, uschar *ptr, BOOL utf8)
|
||||
{
|
||||
int c = *ptr;
|
||||
|
||||
if (!utf8 || (c & 0xc0) != 0xc0)
|
||||
{
|
||||
if (isprint(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
|
||||
return 0;
|
||||
}
|
||||
else
|
||||
{
|
||||
int i;
|
||||
int a = utf8_t4[c & 0x3f]; /* Number of additional bytes */
|
||||
int s = 6*a;
|
||||
c = (c & utf8_t3[a]) << s;
|
||||
for (i = 1; i <= a; i++)
|
||||
{
|
||||
s -= 6;
|
||||
c |= (ptr[i] & 0x3f) << s;
|
||||
}
|
||||
if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c);
|
||||
return a;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Print compiled regex *
|
||||
*************************************************/
|
||||
|
||||
static void
|
||||
print_internals(pcre *external_re, FILE *f)
|
||||
{
|
||||
real_pcre *re = (real_pcre *)external_re;
|
||||
uschar *codestart =
|
||||
(uschar *)re + sizeof(real_pcre) + re->name_count * re->name_entry_size;
|
||||
uschar *code = codestart;
|
||||
BOOL utf8 = (re->options & PCRE_UTF8) != 0;
|
||||
|
||||
for(;;)
|
||||
{
|
||||
uschar *ccode;
|
||||
int c;
|
||||
int extra = 0;
|
||||
|
||||
fprintf(f, "%3d ", code - codestart);
|
||||
|
||||
if (*code >= OP_BRA)
|
||||
{
|
||||
if (*code - OP_BRA > EXTRACT_BASIC_MAX)
|
||||
fprintf(f, "%3d Bra extra\n", GET(code, 1));
|
||||
else
|
||||
fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA);
|
||||
code += OP_lengths[OP_BRA];
|
||||
continue;
|
||||
}
|
||||
|
||||
switch(*code)
|
||||
{
|
||||
case OP_END:
|
||||
fprintf(f, " %s\n", OP_names[*code]);
|
||||
fprintf(f, "------------------------------------------------------------------\n");
|
||||
return;
|
||||
|
||||
case OP_OPT:
|
||||
fprintf(f, " %.2x %s", code[1], OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_CHARS:
|
||||
{
|
||||
int charlength = code[1];
|
||||
ccode = code + 2;
|
||||
extra = charlength;
|
||||
fprintf(f, "%3d ", charlength);
|
||||
while (charlength > 0)
|
||||
{
|
||||
int extrabytes = print_char(f, ccode, utf8);
|
||||
ccode += 1 + extrabytes;
|
||||
charlength -= 1 + extrabytes;
|
||||
}
|
||||
}
|
||||
break;
|
||||
|
||||
case OP_KETRMAX:
|
||||
case OP_KETRMIN:
|
||||
case OP_ALT:
|
||||
case OP_KET:
|
||||
case OP_ASSERT:
|
||||
case OP_ASSERT_NOT:
|
||||
case OP_ASSERTBACK:
|
||||
case OP_ASSERTBACK_NOT:
|
||||
case OP_ONCE:
|
||||
case OP_COND:
|
||||
case OP_REVERSE:
|
||||
fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_BRANUMBER:
|
||||
printf("%3d %s", GET2(code, 1), OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_CREF:
|
||||
if (GET2(code, 1) == CREF_RECURSE)
|
||||
fprintf(f, " Cond recurse");
|
||||
else
|
||||
fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_STAR:
|
||||
case OP_MINSTAR:
|
||||
case OP_PLUS:
|
||||
case OP_MINPLUS:
|
||||
case OP_QUERY:
|
||||
case OP_MINQUERY:
|
||||
case OP_TYPESTAR:
|
||||
case OP_TYPEMINSTAR:
|
||||
case OP_TYPEPLUS:
|
||||
case OP_TYPEMINPLUS:
|
||||
case OP_TYPEQUERY:
|
||||
case OP_TYPEMINQUERY:
|
||||
fprintf(f, " ");
|
||||
if (*code >= OP_TYPESTAR) fprintf(f, "%s", OP_names[code[1]]);
|
||||
else extra = print_char(f, code+1, utf8);
|
||||
fprintf(f, "%s", OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_EXACT:
|
||||
case OP_UPTO:
|
||||
case OP_MINUPTO:
|
||||
fprintf(f, " ");
|
||||
extra = print_char(f, code+3, utf8);
|
||||
fprintf(f, "{");
|
||||
if (*code != OP_EXACT) fprintf(f, ",");
|
||||
fprintf(f, "%d}", GET2(code,1));
|
||||
if (*code == OP_MINUPTO) fprintf(f, "?");
|
||||
break;
|
||||
|
||||
case OP_TYPEEXACT:
|
||||
case OP_TYPEUPTO:
|
||||
case OP_TYPEMINUPTO:
|
||||
fprintf(f, " %s{", OP_names[code[3]]);
|
||||
if (*code != OP_TYPEEXACT) fprintf(f, "0,");
|
||||
fprintf(f, "%d}", GET2(code,1));
|
||||
if (*code == OP_TYPEMINUPTO) fprintf(f, "?");
|
||||
break;
|
||||
|
||||
case OP_NOT:
|
||||
if (isprint(c = code[1])) fprintf(f, " [^%c]", c);
|
||||
else fprintf(f, " [^\\x%02x]", c);
|
||||
break;
|
||||
|
||||
case OP_NOTSTAR:
|
||||
case OP_NOTMINSTAR:
|
||||
case OP_NOTPLUS:
|
||||
case OP_NOTMINPLUS:
|
||||
case OP_NOTQUERY:
|
||||
case OP_NOTMINQUERY:
|
||||
if (isprint(c = code[1])) fprintf(f, " [^%c]", c);
|
||||
else fprintf(f, " [^\\x%02x]", c);
|
||||
fprintf(f, "%s", OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_NOTEXACT:
|
||||
case OP_NOTUPTO:
|
||||
case OP_NOTMINUPTO:
|
||||
if (isprint(c = code[3])) fprintf(f, " [^%c]{", c);
|
||||
else fprintf(f, " [^\\x%02x]{", c);
|
||||
if (*code != OP_NOTEXACT) fprintf(f, ",");
|
||||
fprintf(f, "%d}", GET2(code,1));
|
||||
if (*code == OP_NOTMINUPTO) fprintf(f, "?");
|
||||
break;
|
||||
|
||||
case OP_RECURSE:
|
||||
fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
|
||||
break;
|
||||
|
||||
case OP_REF:
|
||||
fprintf(f, " \\%d", GET2(code,1));
|
||||
ccode = code + OP_lengths[*code];
|
||||
goto CLASS_REF_REPEAT;
|
||||
|
||||
case OP_CALLOUT:
|
||||
fprintf(f, " %s %d", OP_names[*code], code[1]);
|
||||
break;
|
||||
|
||||
/* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in
|
||||
having this code always here, and it makes it less messy without all those
|
||||
#ifdefs. */
|
||||
|
||||
case OP_CLASS:
|
||||
case OP_NCLASS:
|
||||
case OP_XCLASS:
|
||||
{
|
||||
int i, min, max;
|
||||
BOOL printmap;
|
||||
|
||||
fprintf(f, " [");
|
||||
|
||||
if (*code == OP_XCLASS)
|
||||
{
|
||||
extra = GET(code, 1);
|
||||
ccode = code + LINK_SIZE + 1;
|
||||
printmap = (*ccode & XCL_MAP) != 0;
|
||||
if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^");
|
||||
}
|
||||
else
|
||||
{
|
||||
printmap = TRUE;
|
||||
ccode = code + 1;
|
||||
}
|
||||
|
||||
/* Print a bit map */
|
||||
|
||||
if (printmap)
|
||||
{
|
||||
for (i = 0; i < 256; i++)
|
||||
{
|
||||
if ((ccode[i/8] & (1 << (i&7))) != 0)
|
||||
{
|
||||
int j;
|
||||
for (j = i+1; j < 256; j++)
|
||||
if ((ccode[j/8] & (1 << (j&7))) == 0) break;
|
||||
if (i == '-' || i == ']') fprintf(f, "\\");
|
||||
if (isprint(i)) fprintf(f, "%c", i); else fprintf(f, "\\x%02x", i);
|
||||
if (--j > i)
|
||||
{
|
||||
fprintf(f, "-");
|
||||
if (j == '-' || j == ']') fprintf(f, "\\");
|
||||
if (isprint(j)) fprintf(f, "%c", j); else fprintf(f, "\\x%02x", j);
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
}
|
||||
ccode += 32;
|
||||
}
|
||||
|
||||
/* For an XCLASS there is always some additional data */
|
||||
|
||||
if (*code == OP_XCLASS)
|
||||
{
|
||||
int ch;
|
||||
while ((ch = *ccode++) != XCL_END)
|
||||
{
|
||||
ccode += 1 + print_char(f, ccode, TRUE);
|
||||
if (ch == XCL_RANGE)
|
||||
{
|
||||
fprintf(f, "-");
|
||||
ccode += 1 + print_char(f, ccode, TRUE);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* Indicate a non-UTF8 class which was created by negation */
|
||||
|
||||
fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : "");
|
||||
|
||||
/* Handle repeats after a class or a back reference */
|
||||
|
||||
CLASS_REF_REPEAT:
|
||||
switch(*ccode)
|
||||
{
|
||||
case OP_CRSTAR:
|
||||
case OP_CRMINSTAR:
|
||||
case OP_CRPLUS:
|
||||
case OP_CRMINPLUS:
|
||||
case OP_CRQUERY:
|
||||
case OP_CRMINQUERY:
|
||||
fprintf(f, "%s", OP_names[*ccode]);
|
||||
extra = OP_lengths[*ccode];
|
||||
break;
|
||||
|
||||
case OP_CRRANGE:
|
||||
case OP_CRMINRANGE:
|
||||
min = GET2(ccode,1);
|
||||
max = GET2(ccode,3);
|
||||
if (max == 0) fprintf(f, "{%d,}", min);
|
||||
else fprintf(f, "{%d,%d}", min, max);
|
||||
if (*ccode == OP_CRMINRANGE) fprintf(f, "?");
|
||||
extra = OP_lengths[*ccode];
|
||||
break;
|
||||
}
|
||||
}
|
||||
break;
|
||||
|
||||
/* Anything else is just an item with no data*/
|
||||
|
||||
default:
|
||||
fprintf(f, " %s", OP_names[*code]);
|
||||
break;
|
||||
}
|
||||
|
||||
code += OP_lengths[*code] + extra;
|
||||
fprintf(f, "\n");
|
||||
}
|
||||
}
|
||||
|
||||
/* End of printint.c */
|
||||
@@ -1,480 +0,0 @@
|
||||
/*************************************************
|
||||
* Perl-Compatible Regular Expressions *
|
||||
*************************************************/
|
||||
|
||||
/*
|
||||
This is a library of functions to support regular expressions whose syntax
|
||||
and semantics are as close as possible to those of the Perl 5 language. See
|
||||
the file Tech.Notes for some information on the internals.
|
||||
|
||||
Written by: Philip Hazel <[email protected]>
|
||||
|
||||
Copyright (c) 1997-2003 University of Cambridge
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the University of Cambridge nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
-----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
|
||||
/* Include the internals header, which itself includes Standard C headers plus
|
||||
the external pcre header. */
|
||||
|
||||
#include "internal.h"
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Set a bit and maybe its alternate case *
|
||||
*************************************************/
|
||||
|
||||
/* Given a character, set its bit in the table, and also the bit for the other
|
||||
version of a letter if we are caseless.
|
||||
|
||||
Arguments:
|
||||
start_bits points to the bit map
|
||||
c is the character
|
||||
caseless the caseless flag
|
||||
cd the block with char table pointers
|
||||
|
||||
Returns: nothing
|
||||
*/
|
||||
|
||||
static void
|
||||
set_bit(uschar *start_bits, int c, BOOL caseless, compile_data *cd)
|
||||
{
|
||||
start_bits[c/8] |= (1 << (c&7));
|
||||
if (caseless && (cd->ctypes[c] & ctype_letter) != 0)
|
||||
start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7));
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Create bitmap of starting chars *
|
||||
*************************************************/
|
||||
|
||||
/* This function scans a compiled unanchored expression and attempts to build a
|
||||
bitmap of the set of initial characters. If it can't, it returns FALSE. As time
|
||||
goes by, we may be able to get more clever at doing this.
|
||||
|
||||
Arguments:
|
||||
code points to an expression
|
||||
start_bits points to a 32-byte table, initialized to 0
|
||||
caseless the current state of the caseless flag
|
||||
utf8 TRUE if in UTF-8 mode
|
||||
cd the block with char table pointers
|
||||
|
||||
Returns: TRUE if table built, FALSE otherwise
|
||||
*/
|
||||
|
||||
static BOOL
|
||||
set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless,
|
||||
BOOL utf8, compile_data *cd)
|
||||
{
|
||||
register int c;
|
||||
|
||||
/* This next statement and the later reference to dummy are here in order to
|
||||
trick the optimizer of the IBM C compiler for OS/2 into generating correct
|
||||
code. Apparently IBM isn't going to fix the problem, and we would rather not
|
||||
disable optimization (in this module it actually makes a big difference, and
|
||||
the pcre module can use all the optimization it can get). */
|
||||
|
||||
volatile int dummy;
|
||||
|
||||
do
|
||||
{
|
||||
const uschar *tcode = code + 1 + LINK_SIZE;
|
||||
BOOL try_next = TRUE;
|
||||
|
||||
while (try_next)
|
||||
{
|
||||
/* If a branch starts with a bracket or a positive lookahead assertion,
|
||||
recurse to set bits from within them. That's all for this branch. */
|
||||
|
||||
if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT)
|
||||
{
|
||||
if (!set_start_bits(tcode, start_bits, caseless, utf8, cd))
|
||||
return FALSE;
|
||||
try_next = FALSE;
|
||||
}
|
||||
|
||||
else switch(*tcode)
|
||||
{
|
||||
default:
|
||||
return FALSE;
|
||||
|
||||
/* Skip over callout */
|
||||
|
||||
case OP_CALLOUT:
|
||||
tcode += 2;
|
||||
break;
|
||||
|
||||
/* Skip over extended extraction bracket number */
|
||||
|
||||
case OP_BRANUMBER:
|
||||
tcode += 3;
|
||||
break;
|
||||
|
||||
/* Skip over lookbehind and negative lookahead assertions */
|
||||
|
||||
case OP_ASSERT_NOT:
|
||||
case OP_ASSERTBACK:
|
||||
case OP_ASSERTBACK_NOT:
|
||||
do tcode += GET(tcode, 1); while (*tcode == OP_ALT);
|
||||
tcode += 1+LINK_SIZE;
|
||||
break;
|
||||
|
||||
/* Skip over an option setting, changing the caseless flag */
|
||||
|
||||
case OP_OPT:
|
||||
caseless = (tcode[1] & PCRE_CASELESS) != 0;
|
||||
tcode += 2;
|
||||
break;
|
||||
|
||||
/* BRAZERO does the bracket, but carries on. */
|
||||
|
||||
case OP_BRAZERO:
|
||||
case OP_BRAMINZERO:
|
||||
if (!set_start_bits(++tcode, start_bits, caseless, utf8, cd))
|
||||
return FALSE;
|
||||
dummy = 1;
|
||||
do tcode += GET(tcode,1); while (*tcode == OP_ALT);
|
||||
tcode += 1+LINK_SIZE;
|
||||
break;
|
||||
|
||||
/* Single-char * or ? sets the bit and tries the next item */
|
||||
|
||||
case OP_STAR:
|
||||
case OP_MINSTAR:
|
||||
case OP_QUERY:
|
||||
case OP_MINQUERY:
|
||||
set_bit(start_bits, tcode[1], caseless, cd);
|
||||
tcode += 2;
|
||||
#ifdef SUPPORT_UTF8
|
||||
if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++;
|
||||
#endif
|
||||
break;
|
||||
|
||||
/* Single-char upto sets the bit and tries the next */
|
||||
|
||||
case OP_UPTO:
|
||||
case OP_MINUPTO:
|
||||
set_bit(start_bits, tcode[3], caseless, cd);
|
||||
tcode += 4;
|
||||
#ifdef SUPPORT_UTF8
|
||||
if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++;
|
||||
#endif
|
||||
break;
|
||||
|
||||
/* At least one single char sets the bit and stops */
|
||||
|
||||
case OP_EXACT: /* Fall through */
|
||||
tcode++;
|
||||
|
||||
case OP_CHARS: /* Fall through */
|
||||
tcode++;
|
||||
|
||||
case OP_PLUS:
|
||||
case OP_MINPLUS:
|
||||
set_bit(start_bits, tcode[1], caseless, cd);
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
/* Single character type sets the bits and stops */
|
||||
|
||||
case OP_NOT_DIGIT:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= ~cd->cbits[c+cbit_digit];
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
case OP_DIGIT:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= cd->cbits[c+cbit_digit];
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
case OP_NOT_WHITESPACE:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= ~cd->cbits[c+cbit_space];
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
case OP_WHITESPACE:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= cd->cbits[c+cbit_space];
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
case OP_NOT_WORDCHAR:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= ~cd->cbits[c+cbit_word];
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
case OP_WORDCHAR:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= cd->cbits[c+cbit_word];
|
||||
try_next = FALSE;
|
||||
break;
|
||||
|
||||
/* One or more character type fudges the pointer and restarts, knowing
|
||||
it will hit a single character type and stop there. */
|
||||
|
||||
case OP_TYPEPLUS:
|
||||
case OP_TYPEMINPLUS:
|
||||
tcode++;
|
||||
break;
|
||||
|
||||
case OP_TYPEEXACT:
|
||||
tcode += 3;
|
||||
break;
|
||||
|
||||
/* Zero or more repeats of character types set the bits and then
|
||||
try again. */
|
||||
|
||||
case OP_TYPEUPTO:
|
||||
case OP_TYPEMINUPTO:
|
||||
tcode += 2; /* Fall through */
|
||||
|
||||
case OP_TYPESTAR:
|
||||
case OP_TYPEMINSTAR:
|
||||
case OP_TYPEQUERY:
|
||||
case OP_TYPEMINQUERY:
|
||||
switch(tcode[1])
|
||||
{
|
||||
case OP_ANY:
|
||||
return FALSE;
|
||||
|
||||
case OP_NOT_DIGIT:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= ~cd->cbits[c+cbit_digit];
|
||||
break;
|
||||
|
||||
case OP_DIGIT:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= cd->cbits[c+cbit_digit];
|
||||
break;
|
||||
|
||||
case OP_NOT_WHITESPACE:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= ~cd->cbits[c+cbit_space];
|
||||
break;
|
||||
|
||||
case OP_WHITESPACE:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= cd->cbits[c+cbit_space];
|
||||
break;
|
||||
|
||||
case OP_NOT_WORDCHAR:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= ~cd->cbits[c+cbit_word];
|
||||
break;
|
||||
|
||||
case OP_WORDCHAR:
|
||||
for (c = 0; c < 32; c++)
|
||||
start_bits[c] |= cd->cbits[c+cbit_word];
|
||||
break;
|
||||
}
|
||||
|
||||
tcode += 2;
|
||||
break;
|
||||
|
||||
/* Character class where all the information is in a bit map: set the
|
||||
bits and either carry on or not, according to the repeat count. If it was
|
||||
a negative class, and we are operating with UTF-8 characters, any byte
|
||||
with a value >= 0xc4 is a potentially valid starter because it starts a
|
||||
character with a value > 255. */
|
||||
|
||||
case OP_NCLASS:
|
||||
if (utf8)
|
||||
{
|
||||
start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */
|
||||
memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */
|
||||
}
|
||||
/* Fall through */
|
||||
|
||||
case OP_CLASS:
|
||||
{
|
||||
tcode++;
|
||||
|
||||
/* In UTF-8 mode, the bits in a bit map correspond to character
|
||||
values, not to byte values. However, the bit map we are constructing is
|
||||
for byte values. So we have to do a conversion for characters whose
|
||||
value is > 127. In fact, there are only two possible starting bytes for
|
||||
characters in the range 128 - 255. */
|
||||
|
||||
if (utf8)
|
||||
{
|
||||
for (c = 0; c < 16; c++) start_bits[c] |= tcode[c];
|
||||
for (c = 128; c < 256; c++)
|
||||
{
|
||||
if ((tcode[c/8] && (1 << (c&7))) != 0)
|
||||
{
|
||||
int d = (c >> 6) | 0xc0; /* Set bit for this starter */
|
||||
start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */
|
||||
c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* In non-UTF-8 mode, the two bit maps are completely compatible. */
|
||||
|
||||
else
|
||||
{
|
||||
for (c = 0; c < 32; c++) start_bits[c] |= tcode[c];
|
||||
}
|
||||
|
||||
/* Advance past the bit map, and act on what follows */
|
||||
|
||||
tcode += 32;
|
||||
switch (*tcode)
|
||||
{
|
||||
case OP_CRSTAR:
|
||||
case OP_CRMINSTAR:
|
||||
case OP_CRQUERY:
|
||||
case OP_CRMINQUERY:
|
||||
tcode++;
|
||||
break;
|
||||
|
||||
case OP_CRRANGE:
|
||||
case OP_CRMINRANGE:
|
||||
if (((tcode[1] << 8) + tcode[2]) == 0) tcode += 5;
|
||||
else try_next = FALSE;
|
||||
break;
|
||||
|
||||
default:
|
||||
try_next = FALSE;
|
||||
break;
|
||||
}
|
||||
}
|
||||
break; /* End of bitmap class handling */
|
||||
|
||||
} /* End of switch */
|
||||
} /* End of try_next loop */
|
||||
|
||||
code += GET(code, 1); /* Advance to next branch */
|
||||
}
|
||||
while (*code == OP_ALT);
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************
|
||||
* Study a compiled expression *
|
||||
*************************************************/
|
||||
|
||||
/* This function is handed a compiled expression that it must study to produce
|
||||
information that will speed up the matching. It returns a pcre_extra block
|
||||
which then gets handed back to pcre_exec().
|
||||
|
||||
Arguments:
|
||||
re points to the compiled expression
|
||||
options contains option bits
|
||||
errorptr points to where to place error messages;
|
||||
set NULL unless error
|
||||
|
||||
Returns: pointer to a pcre_extra block, with study_data filled in and the
|
||||
appropriate flag set;
|
||||
NULL on error or if no optimization possible
|
||||
*/
|
||||
|
||||
EXPORT pcre_extra *
|
||||
pcre_study(const pcre *external_re, int options, const char **errorptr)
|
||||
{
|
||||
uschar start_bits[32];
|
||||
pcre_extra *extra;
|
||||
pcre_study_data *study;
|
||||
const real_pcre *re = (const real_pcre *)external_re;
|
||||
uschar *code = (uschar *)re + sizeof(real_pcre) +
|
||||
(re->name_count * re->name_entry_size);
|
||||
compile_data compile_block;
|
||||
|
||||
*errorptr = NULL;
|
||||
|
||||
if (re == NULL || re->magic_number != MAGIC_NUMBER)
|
||||
{
|
||||
*errorptr = "argument is not a compiled regular expression";
|
||||
return NULL;
|
||||
}
|
||||
|
||||
if ((options & ~PUBLIC_STUDY_OPTIONS) != 0)
|
||||
{
|
||||
*errorptr = "unknown or incorrect option bit(s) set";
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/* For an anchored pattern, or an unanchored pattern that has a first char, or
|
||||
a multiline pattern that matches only at "line starts", no further processing
|
||||
at present. */
|
||||
|
||||
if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
|
||||
return NULL;
|
||||
|
||||
/* Set the character tables in the block which is passed around */
|
||||
|
||||
compile_block.lcc = re->tables + lcc_offset;
|
||||
compile_block.fcc = re->tables + fcc_offset;
|
||||
compile_block.cbits = re->tables + cbits_offset;
|
||||
compile_block.ctypes = re->tables + ctypes_offset;
|
||||
|
||||
/* See if we can find a fixed set of initial characters for the pattern. */
|
||||
|
||||
memset(start_bits, 0, 32 * sizeof(uschar));
|
||||
if (!set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0,
|
||||
(re->options & PCRE_UTF8) != 0, &compile_block)) return NULL;
|
||||
|
||||
/* Get a pcre_extra block and a pcre_study_data block. The study data is put in
|
||||
the latter, which is pointed to by the former, which may also get additional
|
||||
data set later by the calling program. At the moment, the size of
|
||||
pcre_study_data is fixed. We nevertheless save it in a field for returning via
|
||||
the pcre_fullinfo() function so that if it becomes variable in the future, we
|
||||
don't have to change that code. */
|
||||
|
||||
extra = (pcre_extra *)(pcre_malloc)
|
||||
(sizeof(pcre_extra) + sizeof(pcre_study_data));
|
||||
|
||||
if (extra == NULL)
|
||||
{
|
||||
*errorptr = "failed to get memory";
|
||||
return NULL;
|
||||
}
|
||||
|
||||
study = (pcre_study_data *)((char *)extra + sizeof(pcre_extra));
|
||||
extra->flags = PCRE_EXTRA_STUDY_DATA;
|
||||
extra->study_data = study;
|
||||
|
||||
study->size = sizeof(pcre_study_data);
|
||||
study->options = PCRE_STUDY_MAPPED;
|
||||
memcpy(study->start_bits, start_bits, sizeof(start_bits));
|
||||
|
||||
return extra;
|
||||
}
|
||||
|
||||
/* End of study.c */
|
||||
Reference in New Issue
Block a user