350 lines
11 KiB
C
350 lines
11 KiB
C
/*************************************************
|
|
* 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 <ph10@cam.ac.uk>
|
|
|
|
Copyright (c) 1997-2003 University of Cambridge
|
|
|
|
-----------------------------------------------------------------------------
|
|
Permission is granted to anyone to use this software for any purpose on any
|
|
computer system, and to redistribute it freely, subject to the following
|
|
restrictions:
|
|
|
|
1. This software is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
|
|
2. The origin of this software must not be misrepresented, either by
|
|
explicit claim or by omission.
|
|
|
|
3. Altered versions must be plainly marked as such, and must not be
|
|
misrepresented as being the original software.
|
|
|
|
4. If PCRE is embedded in any software that is released under the GNU
|
|
General Purpose Licence (GPL), then the terms of that licence shall
|
|
supersede any condition above with which it is incompatible.
|
|
-----------------------------------------------------------------------------
|
|
*/
|
|
|
|
/* 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 <scottw@cgibuilder.com>. */
|
|
|
|
|
|
/* 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 **)(g_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
|
|
g_free_substring_list(const char **pointer)
|
|
{
|
|
(g_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 *)(g_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
|
|
g_free_substring(const char *pointer)
|
|
{
|
|
(g_free)((void *)pointer);
|
|
}
|
|
|
|
/* End of get.c */
|