2013-08-24 22:11:19 +02:00
|
|
|
/* $NetBSD: str.c,v 1.19 2011/09/08 12:00:26 christos Exp $ */
|
2010-04-08 17:04:57 +02:00
|
|
|
|
|
|
|
/*-
|
|
|
|
* Copyright (c) 1991, 1993
|
|
|
|
* The Regents of the University of California. All rights reserved.
|
|
|
|
*
|
|
|
|
* 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. 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.
|
|
|
|
*/
|
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
#include <sys/cdefs.h>
|
|
|
|
#ifndef lint
|
|
|
|
#if 0
|
|
|
|
static char sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95";
|
|
|
|
#endif
|
|
|
|
__RCSID("$NetBSD: str.c,v 1.19 2011/09/08 12:00:26 christos Exp $");
|
|
|
|
#endif /* not lint */
|
|
|
|
|
2010-04-08 17:04:57 +02:00
|
|
|
#include <sys/types.h>
|
|
|
|
|
|
|
|
#include <err.h>
|
|
|
|
#include <errno.h>
|
|
|
|
#include <stddef.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <ctype.h>
|
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
#include "extern.h"
|
2010-04-08 17:04:57 +02:00
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
static int backslash(STR *);
|
|
|
|
static int bracket(STR *);
|
|
|
|
static int c_class(const void *, const void *);
|
|
|
|
static void genclass(STR *);
|
|
|
|
static void genequiv(STR *);
|
|
|
|
static int genrange(STR *);
|
|
|
|
static void genseq(STR *);
|
2010-04-08 17:04:57 +02:00
|
|
|
|
|
|
|
int
|
2013-08-24 22:11:19 +02:00
|
|
|
next(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
|
|
|
int ch;
|
|
|
|
|
|
|
|
switch (s->state) {
|
|
|
|
case EOS:
|
2013-08-24 22:11:19 +02:00
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
case INFINITE:
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
case NORMAL:
|
|
|
|
switch (ch = *s->str) {
|
|
|
|
case '\0':
|
|
|
|
s->state = EOS;
|
2013-08-24 22:11:19 +02:00
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
case '\\':
|
|
|
|
s->lastch = backslash(s);
|
|
|
|
break;
|
|
|
|
case '[':
|
|
|
|
if (bracket(s))
|
2013-08-24 22:11:19 +02:00
|
|
|
return next(s);
|
2010-04-08 17:04:57 +02:00
|
|
|
/* FALLTHROUGH */
|
|
|
|
default:
|
|
|
|
++s->str;
|
|
|
|
s->lastch = ch;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* We can start a range at any time. */
|
|
|
|
if (s->str[0] == '-' && genrange(s))
|
2013-08-24 22:11:19 +02:00
|
|
|
return next(s);
|
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
case RANGE:
|
|
|
|
if (s->cnt-- == 0) {
|
|
|
|
s->state = NORMAL;
|
2013-08-24 22:11:19 +02:00
|
|
|
return next(s);
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
++s->lastch;
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
case SEQUENCE:
|
|
|
|
if (s->cnt-- == 0) {
|
|
|
|
s->state = NORMAL;
|
2013-08-24 22:11:19 +02:00
|
|
|
return next(s);
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
case SET:
|
|
|
|
if ((s->lastch = s->set[s->cnt++]) == OOBCH) {
|
|
|
|
s->state = NORMAL;
|
2013-08-24 22:11:19 +02:00
|
|
|
return next(s);
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
/* NOTREACHED */
|
2013-08-24 22:11:19 +02:00
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2013-08-24 22:11:19 +02:00
|
|
|
bracket(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
|
|
|
char *p;
|
|
|
|
|
|
|
|
switch (s->str[1]) {
|
|
|
|
case ':': /* "[:class:]" */
|
2013-08-24 22:11:19 +02:00
|
|
|
if ((p = strstr(s->str + 2, ":]")) == NULL)
|
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
*p = '\0';
|
|
|
|
s->str += 2;
|
|
|
|
genclass(s);
|
2013-08-24 22:11:19 +02:00
|
|
|
s->str = p + 2;
|
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
case '=': /* "[=equiv=]" */
|
2013-08-24 22:11:19 +02:00
|
|
|
if ((p = strstr(s->str + 2, "=]")) == NULL)
|
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
s->str += 2;
|
|
|
|
genequiv(s);
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
default: /* "[\###*n]" or "[#*n]" */
|
2013-08-24 22:11:19 +02:00
|
|
|
if ((p = strpbrk(s->str + 2, "*]")) == NULL)
|
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
if (p[0] != '*' || strchr(p, ']') == NULL)
|
2013-08-24 22:11:19 +02:00
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
s->str += 1;
|
|
|
|
genseq(s);
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
/* NOTREACHED */
|
|
|
|
}
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
const char *name;
|
2013-08-24 22:11:19 +02:00
|
|
|
int (*func)(int);
|
2010-04-08 17:04:57 +02:00
|
|
|
} CLASS;
|
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
static const CLASS classes[] = {
|
|
|
|
{ "alnum", isalnum },
|
|
|
|
{ "alpha", isalpha },
|
|
|
|
{ "blank", isblank },
|
|
|
|
{ "cntrl", iscntrl },
|
|
|
|
{ "digit", isdigit },
|
|
|
|
{ "graph", isgraph },
|
|
|
|
{ "lower", islower },
|
|
|
|
{ "print", isprint },
|
|
|
|
{ "punct", ispunct },
|
|
|
|
{ "space", isspace },
|
|
|
|
{ "upper", isupper },
|
|
|
|
{ "xdigit", isxdigit },
|
2010-04-08 17:04:57 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
static void
|
2013-08-24 22:11:19 +02:00
|
|
|
genclass(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
2013-08-24 22:11:19 +02:00
|
|
|
int cnt;
|
|
|
|
const CLASS *cp;
|
|
|
|
CLASS tmp;
|
2010-04-08 17:04:57 +02:00
|
|
|
int *p;
|
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
tmp.name = s->str;
|
|
|
|
if ((cp = bsearch(&tmp, classes, sizeof(classes) /
|
|
|
|
sizeof(*cp), sizeof(*cp), c_class)) == NULL)
|
|
|
|
errx(1, "unknown class %s", s->str);
|
2010-04-08 17:04:57 +02:00
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
if ((s->set = p = malloc((NCHARS + 1) * sizeof(*p))) == NULL)
|
|
|
|
err(1, "malloc");
|
|
|
|
|
|
|
|
for (cnt = 0; cnt < NCHARS; ++cnt)
|
|
|
|
if ((*cp->func)(cnt))
|
2010-04-08 17:04:57 +02:00
|
|
|
*p++ = cnt;
|
2013-08-24 22:11:19 +02:00
|
|
|
*p++ = OOBCH;
|
|
|
|
memset(p, 0, NCHARS + 1 - (p - s->set));
|
2010-04-08 17:04:57 +02:00
|
|
|
|
|
|
|
s->cnt = 0;
|
|
|
|
s->state = SET;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2013-08-24 22:11:19 +02:00
|
|
|
c_class(const void *a, const void *b)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
2013-08-24 22:11:19 +02:00
|
|
|
return strcmp(((const CLASS *)a)->name, ((const CLASS *)b)->name);
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* English doesn't have any equivalence classes, so for now
|
|
|
|
* we just syntax check and grab the character.
|
|
|
|
*/
|
|
|
|
static void
|
2013-08-24 22:11:19 +02:00
|
|
|
genequiv(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
|
|
|
if (*s->str == '\\') {
|
|
|
|
s->equiv[0] = backslash(s);
|
2013-08-24 22:11:19 +02:00
|
|
|
if (*s->str != '=')
|
|
|
|
errx(1, "misplaced equivalence equals sign");
|
2010-04-08 17:04:57 +02:00
|
|
|
} else {
|
|
|
|
s->equiv[0] = s->str[0];
|
2013-08-24 22:11:19 +02:00
|
|
|
if (s->str[1] != '=')
|
|
|
|
errx(1, "misplaced equivalence equals sign");
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
s->str += 2;
|
|
|
|
s->cnt = 0;
|
|
|
|
s->state = SET;
|
|
|
|
s->set = s->equiv;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2013-08-24 22:11:19 +02:00
|
|
|
genrange(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
|
|
|
int stopval;
|
2013-08-24 22:11:19 +02:00
|
|
|
char *savestart;
|
2010-04-08 17:04:57 +02:00
|
|
|
|
|
|
|
savestart = s->str;
|
|
|
|
stopval = *++s->str == '\\' ? backslash(s) : *s->str++;
|
|
|
|
if (stopval < (u_char)s->lastch) {
|
|
|
|
s->str = savestart;
|
2013-08-24 22:11:19 +02:00
|
|
|
return 0;
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
s->cnt = stopval - s->lastch + 1;
|
|
|
|
s->state = RANGE;
|
|
|
|
--s->lastch;
|
2013-08-24 22:11:19 +02:00
|
|
|
return 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2013-08-24 22:11:19 +02:00
|
|
|
genseq(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
|
|
|
char *ep;
|
|
|
|
|
2013-08-24 22:11:19 +02:00
|
|
|
if (s->which == STRING1)
|
|
|
|
errx(1, "sequences only valid in string2");
|
2010-04-08 17:04:57 +02:00
|
|
|
|
|
|
|
if (*s->str == '\\')
|
|
|
|
s->lastch = backslash(s);
|
|
|
|
else
|
|
|
|
s->lastch = *s->str++;
|
2013-08-24 22:11:19 +02:00
|
|
|
if (*s->str != '*')
|
|
|
|
errx(1, "misplaced sequence asterisk");
|
2010-04-08 17:04:57 +02:00
|
|
|
|
|
|
|
switch (*++s->str) {
|
|
|
|
case '\\':
|
|
|
|
s->cnt = backslash(s);
|
|
|
|
break;
|
|
|
|
case ']':
|
|
|
|
s->cnt = 0;
|
|
|
|
++s->str;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
if (isdigit(*s->str)) {
|
2013-08-24 22:11:19 +02:00
|
|
|
s->cnt = strtol(s->str, &ep, 0);
|
2010-04-08 17:04:57 +02:00
|
|
|
if (*ep == ']') {
|
2013-08-24 22:11:19 +02:00
|
|
|
s->str = ep + 1;
|
2010-04-08 17:04:57 +02:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2013-08-24 22:11:19 +02:00
|
|
|
errx(1, "illegal sequence count");
|
2010-04-08 17:04:57 +02:00
|
|
|
/* NOTREACHED */
|
|
|
|
}
|
|
|
|
|
|
|
|
s->state = s->cnt ? SEQUENCE : INFINITE;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Translate \??? into a character. Up to 3 octal digits, if no digits either
|
|
|
|
* an escape code or a literal character.
|
|
|
|
*/
|
|
|
|
static int
|
2013-08-24 22:11:19 +02:00
|
|
|
backslash(STR *s)
|
2010-04-08 17:04:57 +02:00
|
|
|
{
|
|
|
|
int ch, cnt, val;
|
|
|
|
|
|
|
|
for (cnt = val = 0;;) {
|
|
|
|
ch = *++s->str;
|
|
|
|
if (!isascii(ch) || !isdigit(ch))
|
|
|
|
break;
|
|
|
|
val = val * 8 + ch - '0';
|
|
|
|
if (++cnt == 3) {
|
|
|
|
++s->str;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (cnt)
|
2013-08-24 22:11:19 +02:00
|
|
|
return val;
|
2010-04-08 17:04:57 +02:00
|
|
|
if (ch != '\0')
|
|
|
|
++s->str;
|
|
|
|
switch (ch) {
|
2013-08-24 22:11:19 +02:00
|
|
|
case 'a': /* escape characters */
|
|
|
|
return '\7';
|
|
|
|
case 'b':
|
|
|
|
return '\b';
|
|
|
|
case 'e':
|
|
|
|
return '\033';
|
|
|
|
case 'f':
|
|
|
|
return '\f';
|
|
|
|
case 'n':
|
|
|
|
return '\n';
|
|
|
|
case 'r':
|
|
|
|
return '\r';
|
|
|
|
case 't':
|
|
|
|
return '\t';
|
|
|
|
case 'v':
|
|
|
|
return '\13';
|
|
|
|
case '\0': /* \" -> \ */
|
|
|
|
s->state = EOS;
|
|
|
|
return '\\';
|
|
|
|
default: /* \x" -> x */
|
|
|
|
return ch;
|
2010-04-08 17:04:57 +02:00
|
|
|
}
|
|
|
|
}
|