e5996857ad
idea is that we perform multibyte->wide character conversion while parsing and compiling, then convert byte sequences to wide characters when they're needed for comparison and stepping through the string during execution. As with tr(1), the main complication is to efficiently represent sets of characters in bracket expressions. The old bitmap representation is replaced by a bitmap for the first 256 characters combined with a vector of individual wide characters, a vector of character ranges (for [A-Z] etc.), and a vector of character classes (for [[:alpha:]] etc.). One other point of interest is that although the Boyer-Moore algorithm had to be disabled in the general multibyte case, it is still enabled for UTF-8 because of its self-synchronizing nature. This greatly speeds up matching by reducing the number of multibyte conversions that need to be done.
95 lines
3.1 KiB
C
95 lines
3.1 KiB
C
/*-
|
|
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
|
|
* Copyright (c) 1992, 1993, 1994
|
|
* The Regents of the University of California. All rights reserved.
|
|
*
|
|
* This code is derived from software contributed to Berkeley by
|
|
* Henry Spencer.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. 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.
|
|
* 3. All advertising materials mentioning features or use of this software
|
|
* must display the following acknowledgement:
|
|
* This product includes software developed by the University of
|
|
* California, Berkeley and its contributors.
|
|
* 4. Neither the name of the University 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 REGENTS 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 REGENTS 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.
|
|
*
|
|
* @(#)regfree.c 8.3 (Berkeley) 3/20/94
|
|
*/
|
|
|
|
#if defined(LIBC_SCCS) && !defined(lint)
|
|
static char sccsid[] = "@(#)regfree.c 8.3 (Berkeley) 3/20/94";
|
|
#endif /* LIBC_SCCS and not lint */
|
|
#include <sys/cdefs.h>
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
#include <sys/types.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <limits.h>
|
|
#include <regex.h>
|
|
#include <wchar.h>
|
|
#include <wctype.h>
|
|
|
|
#include "utils.h"
|
|
#include "regex2.h"
|
|
|
|
/*
|
|
- regfree - free everything
|
|
= extern void regfree(regex_t *);
|
|
*/
|
|
void
|
|
regfree(preg)
|
|
regex_t *preg;
|
|
{
|
|
struct re_guts *g;
|
|
int i;
|
|
|
|
if (preg->re_magic != MAGIC1) /* oops */
|
|
return; /* nice to complain, but hard */
|
|
|
|
g = preg->re_g;
|
|
if (g == NULL || g->magic != MAGIC2) /* oops again */
|
|
return;
|
|
preg->re_magic = 0; /* mark it invalid */
|
|
g->magic = 0; /* mark it invalid */
|
|
|
|
if (g->strip != NULL)
|
|
free((char *)g->strip);
|
|
if (g->sets != NULL) {
|
|
for (i = 0; i < g->ncsets; i++) {
|
|
free(g->sets[i].ranges);
|
|
free(g->sets[i].wides);
|
|
free(g->sets[i].types);
|
|
}
|
|
free((char *)g->sets);
|
|
}
|
|
if (g->must != NULL)
|
|
free(g->must);
|
|
if (g->charjump != NULL)
|
|
free(&g->charjump[CHAR_MIN]);
|
|
if (g->matchjump != NULL)
|
|
free(g->matchjump);
|
|
free((char *)g);
|
|
}
|