[703] in Zephyr_Bugs
regex handling in zwgc
daemon@ATHENA.MIT.EDU (Derrick J. Brashear)
Wed Sep 13 10:44:31 1995
Date: Wed, 13 Sep 1995 10:43:55 -0400 (EDT)
From: "Derrick J. Brashear" <shadow@DEMENTIA.ORG>
Reply-To: "Derrick J. Brashear" <shadow@DEMENTIA.ORG>
To: bug-zephyr@MIT.EDU
---2143855796-143302914-811003436=:14990
Content-Type: TEXT/PLAIN; CHARSET=US-ASCII
Hi,
I had some trouble with regex handling in zwgc. Specifically, under Solaris
regcomp is not implemented, and re_comp only exists in libucb, which I'm
striving not to use. The compatibility code provided did "the wrong thing" for
something like $recipient =~ "*, where I define "the wrong thing" as "not what
the older zephyr we have currently does". In this case, I wanted to check and
see if what i got was a broadcast message in some realm that I'm subscribed in.
I applied the attached patch, which is essentially re_comp and re_exec from 4.3
BSD.
-D
---2143855796-143302914-811003436=:14990
Content-Type: TEXT/plain; CHARSET=US-ASCII
Content-Description: zwgc-regex.diff
*** regexp.c.orig Wed Sep 13 10:21:50 1995
--- regexp.c Wed Sep 13 10:34:28 1995
***************
*** 81,111 ****
#endif
#if !defined(HAVE_RE_COMP) && !defined(HAVE_REGCOMP)
! #ifdef HAVE_LIBGEN_H
! #include <libgen.h>
! #endif
! static char *re;
! char *re_comp(s)
! char *s;
{
! if(!s)
! return 0;
! if(re)
! free(re);
! if(!(re = regcmp(s, (char *)0)))
! return "Bad argument to re_comp";
! return 0;
}
! int re_exec(s)
! char *s;
{
! return regex(re, s) != 0;
}
#endif
--- 81,406 ----
#endif
#if !defined(HAVE_RE_COMP) && !defined(HAVE_REGCOMP)
+ #define CBRA 1
+ #define CCHR 2
+ #define CDOT 4
+ #define CCL 6
+ #define NCCL 8
+ #define CDOL 10
+ #define CEOFS 11
+ #define CKET 12
+ #define CBACK 18
! #define CSTAR 01
! #define ESIZE 512
! #define NBRA 9
! static char expbuf[ESIZE], *braslist[NBRA], *braelist[NBRA];
! static char circf;
!
! /*
! * compile the regular expression argument into a dfa
! */
! char *
! re_comp(sp)
! register char *sp;
{
! register int c;
! register char *ep = expbuf;
! int cclcnt, numbra = 0;
! char *lastep = 0;
! char bracket[NBRA];
! char *bracketp = &bracket[0];
! static char *retoolong = "Regular expression too long";
! #define comerr(msg) {expbuf[0] = 0; numbra = 0; return(msg); }
! if (sp == 0 || *sp == '\0') {
! if (*ep == 0)
! return("No previous regular expression");
! return(0);
! }
! if (*sp == '^') {
! circf = 1;
! sp++;
! }
! else
! circf = 0;
! for (;;) {
! if (ep >= &expbuf[ESIZE])
! comerr(retoolong);
! if ((c = *sp++) == '\0') {
! if (bracketp != bracket)
! comerr("unmatched \\(");
! *ep++ = CEOFS;
! *ep++ = 0;
! return(0);
! }
! if (c != '*')
! lastep = ep;
! switch (c) {
!
! case '.':
! *ep++ = CDOT;
! continue;
!
! case '*':
! if (lastep == 0 || *lastep == CBRA || *lastep == CKET)
! goto defchar;
! *lastep |= CSTAR;
! continue;
!
! case '$':
! if (*sp != '\0')
! goto defchar;
! *ep++ = CDOL;
! continue;
!
! case '[':
! *ep++ = CCL;
! *ep++ = 0;
! cclcnt = 1;
! if ((c = *sp++) == '^') {
! c = *sp++;
! ep[-2] = NCCL;
! }
! do {
! if (c == '\0')
! comerr("missing ]");
! if (c == '-' && ep [-1] != 0) {
! if ((c = *sp++) == ']') {
! *ep++ = '-';
! cclcnt++;
! break;
! }
! while (ep[-1] < c) {
! *ep = ep[-1] + 1;
! ep++;
! cclcnt++;
! if (ep >= &expbuf[ESIZE])
! comerr(retoolong);
! }
! }
! *ep++ = c;
! cclcnt++;
! if (ep >= &expbuf[ESIZE])
! comerr(retoolong);
! } while ((c = *sp++) != ']');
! lastep[1] = cclcnt;
! continue;
!
! case '\\':
! if ((c = *sp++) == '(') {
! if (numbra >= NBRA)
! comerr("too many \\(\\) pairs");
! *bracketp++ = numbra;
! *ep++ = CBRA;
! *ep++ = numbra++;
! continue;
! }
! if (c == ')') {
! if (bracketp <= bracket)
! comerr("unmatched \\)");
! *ep++ = CKET;
! *ep++ = *--bracketp;
! continue;
! }
! if (c >= '1' && c < ('1' + NBRA)) {
! *ep++ = CBACK;
! *ep++ = c - '1';
! continue;
! }
! *ep++ = CCHR;
! *ep++ = c;
! continue;
!
! defchar:
! default:
! *ep++ = CCHR;
! *ep++ = c;
! }
! }
}
! /*
! * match the argument string against the compiled re
! */
! int
! re_exec(p1)
! register char *p1;
{
! register char *p2 = expbuf;
! register int c;
! int rv;
!
! for (c = 0; c < NBRA; c++) {
! braslist[c] = 0;
! braelist[c] = 0;
! }
! if (circf)
! return((advance(p1, p2)));
! /*
! * fast check for first character
! */
! if (*p2 == CCHR) {
! c = p2[1];
! do {
! if (*p1 != c)
! continue;
! if (rv = advance(p1, p2))
! return(rv);
! } while (*p1++);
! return(0);
! }
! /*
! * regular algorithm
! */
! do
! if (rv = advance(p1, p2))
! return(rv);
! while (*p1++);
! return(0);
! }
!
! /*
! * try to match the next thing in the dfa
! */
! static int
! advance(lp, ep)
! register char *lp, *ep;
! {
! register char *curlp;
! int ct, i;
! int rv;
!
! for (;;)
! switch (*ep++) {
!
! case CCHR:
! if (*ep++ == *lp++)
! continue;
! return(0);
!
! case CDOT:
! if (*lp++)
! continue;
! return(0);
!
! case CDOL:
! if (*lp == '\0')
! continue;
! return(0);
!
! case CEOFS:
! return(1);
!
! case CCL:
! if (cclass(ep, *lp++, 1)) {
! ep += *ep;
! continue;
! }
! return(0);
!
! case NCCL:
! if (cclass(ep, *lp++, 0)) {
! ep += *ep;
! continue;
! }
! return(0);
!
! case CBRA:
! braslist[*ep++] = lp;
! continue;
!
! case CKET:
! braelist[*ep++] = lp;
! continue;
!
! case CBACK:
! if (braelist[i = *ep++] == 0)
! return(-1);
! if (backref(i, lp)) {
! lp += braelist[i] - braslist[i];
! continue;
! }
! return(0);
!
! case CBACK|CSTAR:
! if (braelist[i = *ep++] == 0)
! return(-1);
! curlp = lp;
! ct = braelist[i] - braslist[i];
! while (backref(i, lp))
! lp += ct;
! while (lp >= curlp) {
! if (rv = advance(lp, ep))
! return(rv);
! lp -= ct;
! }
! continue;
!
! case CDOT|CSTAR:
! curlp = lp;
! while (*lp++)
! ;
! goto star;
!
! case CCHR|CSTAR:
! curlp = lp;
! while (*lp++ == *ep)
! ;
! ep++;
! goto star;
!
! case CCL|CSTAR:
! case NCCL|CSTAR:
! curlp = lp;
! while (cclass(ep, *lp++, ep[-1] == (CCL|CSTAR)))
! ;
! ep += *ep;
! goto star;
!
! star:
! do {
! lp--;
! if (rv = advance(lp, ep))
! return(rv);
! } while (lp > curlp);
! return(0);
!
! default:
! return(-1);
! }
! }
!
! backref(i, lp)
! register int i;
! register char *lp;
! {
! register char *bp;
!
! bp = braslist[i];
! while (*bp++ == *lp++)
! if (bp >= braelist[i])
! return(1);
! return(0);
! }
!
! int
! cclass(set, c, af)
! register char *set, c;
! int af;
! {
! register int n;
!
! if (c == 0)
! return(0);
! n = *set++;
! while (--n)
! if (*set++ == c)
! return(af);
! return(! af);
}
#endif
---2143855796-143302914-811003436=:14990--
