PATCH: fix for (#s) and (#e) in param substs

[Peter Stephenson <pws@xxxxxxxxxxxxxxxxxxxxxxxxx>]

This wasn't as bad as it could have been.  Things like

${foo//(#s)d*time(#e)/d fight/}

are all now supposed to work.  One thing I like about this is it allows you
to forget about not only anchor characters in / and //, but even ## and %%,
and with the (S) parameter flag # and % too --- the /-forms together with
the start and end assertions present a single consistent interface for
pattern substitutions.

It's amazing what I can get excited about nowadays.

By the way, I inserted a hostage to fortune in the manual by claiming that
`(^(#s))' etc. also work, i.e. you can assert that you are not at the start
of the string.  I believe this to be the case, but it is a good deal more
hairy as it relies on the exclusion code, which is a bit stomach-turning.
I've caught another potential bug that exclusions in groups pretend the
string ends at the end of the group, which could have made (#e) match
erroneously.  I don't claim that's the end of the matter.

Index: Doc/Zsh/expn.yo
===================================================================
RCS file: /cvsroot/zsh/zsh/Doc/Zsh/expn.yo,v
retrieving revision 1.4
diff -u -r1.4 expn.yo
--- Doc/Zsh/expn.yo	2000/04/06 18:44:01	1.4
+++ Doc/Zsh/expn.yo	2000/04/14 11:26:05
@@ -1309,6 +1309,16 @@
 `tt(*((#s)|/)test((#e)|/)*)' matches a path segment `tt(test)' in any of
 the following strings: tt(test), tt(test/at/start), tt(at/end/test),
 tt(in/test/middle).
+
+Another use is in parameter substitution; for example
+`tt(${array/(#s)A*Z(#e)})' will remove only elements of an array which
+match the complete pattern `tt(A*Z)'.  There are other ways of performing
+many operations of this type, however the combination of the substitution
+operations `tt(/)' and `tt(//)' with the `tt((#s))' and `tt((#e))' flags
+provides a single simple and memorable method.
+
+Note that assertions of the form `tt((^(#s)))' also work, i.e. match
+anywhere except at the start of the string.
 )
 enditem()
 
Index: Src/glob.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/glob.c,v
retrieving revision 1.3
diff -u -r1.3 glob.c
--- Src/glob.c	2000/04/07 02:27:44	1.3
+++ Src/glob.c	2000/04/14 11:26:05
@@ -2056,6 +2056,39 @@
 }
 
 /**/
+static void
+set_pat_start(Patprog p, int offs)
+{
+    /*
+     * If we are messing around with the test string by advancing up
+     * it from the start, we need to tell the pattern matcher that
+     * a start-of-string assertion, i.e. (#s), should fail.  Hence
+     * we test whether the offset of the real start of string from
+     * the actual start, passed as offs, is zero.
+     */
+    if (offs)
+	p->flags |= PAT_NOTSTART;
+    else
+	p->flags &= ~PAT_NOTSTART;
+}
+
+/**/
+static void
+set_pat_end(Patprog p, char null_me)
+{
+    /*
+     * If we are messing around with the string by shortening it at the
+     * tail, we need to tell the pattern matcher that an end-of-string
+     * assertion, i.e. (#e), should fail.  Hence we test whether
+     * the character null_me about to be zapped is or is not already a null.
+     */
+    if (null_me)
+	p->flags |= PAT_NOTEND;
+    else
+	p->flags &= ~PAT_NOTEND;
+}
+
+/**/
 static int
 igetmatch(char **sp, Patprog p, int fl, int n, char *replstr)
 {
@@ -2068,6 +2101,9 @@
     if (p->mustoff && !strstr((char *)s, (char *)p + p->mustoff))
 	matched = 0;
 
+    /* in case we used the prog before... */
+    p->flags &= ~(PAT_NOTSTART|PAT_NOTEND);
+
     if (fl & SUB_ALL) {
 	i = matched && pattry(p, s);
 	*sp = get_match_ret(*sp, 0, i ? l : 0, fl, i ? replstr : 0);
@@ -2092,6 +2128,7 @@
 		     */
 		    for (t = s; t < mpos; METAINC(t)) {
 			sav = *t;
+			set_pat_end(p, sav);
 			*t = '\0';
 			if (pattry(p, s)) {
 			    mpos = patinput;
@@ -2112,6 +2149,7 @@
 	     * There's no optimization here.               */
 	    patoffset = ml;
 	    for (t = s + l; t >= s; t--, patoffset--) {
+		set_pat_start(p, t-s);
 		if (pattry(p, t)) {
 		    *sp = get_match_ret(*sp, t - s, l, fl, replstr);
 		    patoffset = 0;
@@ -2128,6 +2166,7 @@
 	     * move forward along string until we get a match. *
 	     * Again there's no optimisation.                  */
 	    for (i = 0, t = s; i < l; i++, t++, patoffset++) {
+		set_pat_start(p, t-s);
 		if (pattry(p, t)) {
 		    *sp = get_match_ret(*sp, i, l, fl, replstr);
 		    patoffset = 0;
@@ -2141,6 +2180,7 @@
 
 	case SUB_SUBSTR:
 	    /* Smallest at start, but matching substrings. */
+	    set_pat_start(p, l);
 	    if (!(fl & SUB_GLOBAL) && pattry(p, s + l) && !--n) {
 		*sp = get_match_ret(*sp, 0, 0, fl, replstr);
 		return 1;
@@ -2155,12 +2195,14 @@
 		matched = 0;
 		for (; t < s + l; t++, patoffset++) {
 		    /* Find the longest match from this position. */
+		    set_pat_start(p, t-s);
 		    if (pattry(p, t) && patinput > t) {
 			char *mpos = patinput;
 			if (!(fl & SUB_LONG) && !(p->flags & PAT_PURES)) {
 			    char *ptr;
 			    for (ptr = t; ptr < mpos; METAINC(ptr)) {
 				sav = *ptr;
+				set_pat_end(p, sav);
 				*ptr = '\0';
 				if (pattry(p, t)) {
 				    mpos = patinput;
@@ -2209,6 +2251,7 @@
 	     * at the start.  Goodness knows if this is a good idea
 	     * with global substitution, so it doesn't happen.
 	     */
+	    set_pat_start(p, l);
 	    if ((fl & (SUB_LONG|SUB_GLOBAL)) == SUB_LONG &&
 		pattry(p, s + l) && !--n) {
 		*sp = get_match_ret(*sp, 0, 0, fl, replstr);
@@ -2219,6 +2262,7 @@
 	case (SUB_END|SUB_SUBSTR):
 	    /* Shortest at end with substrings */
 	    patoffset = ml;
+	    set_pat_start(p, l);
 	    if (pattry(p, s + l) && !--n) {
 		*sp = get_match_ret(*sp, l, l, fl, replstr);
 		patoffset = 0;
@@ -2230,6 +2274,7 @@
 	    for (t = s + l - 1; t >= s; t--, patoffset--) {
 		if (t > s && t[-1] == Meta)
 		    t--;
+		set_pat_start(p, t-s);
 		if (pattry(p, t) && patinput > t && !--n) {
 		    /* Found the longest match */
 		    char *mpos = patinput;
@@ -2237,6 +2282,7 @@
 			char *ptr;
 			for (ptr = t; ptr < mpos; METAINC(ptr)) {
 			    sav = *ptr;
+			    set_pat_end(p, sav);
 			    *ptr = '\0';
 			    if (pattry(p, t)) {
 				mpos = patinput;
@@ -2252,6 +2298,7 @@
 		}
 	    }
 	    patoffset = ml;
+	    set_pat_start(p, l);
 	    if ((fl & SUB_LONG) && pattry(p, s + l) && !--n) {
 		*sp = get_match_ret(*sp, l, l, fl, replstr);
 		patoffset = 0;
Index: Src/pattern.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/pattern.c,v
retrieving revision 1.4
diff -u -r1.4 pattern.c
--- Src/pattern.c	2000/04/06 18:44:01	1.4
+++ Src/pattern.c	2000/04/14 11:26:05
@@ -1757,6 +1757,9 @@
 			 * over, that doesn't matter:  we should fail anyway.
 			 * The pointer also tells us where the asserted
 			 * pattern matched for use by the exclusion.
+			 *
+			 * P.S. in case you were wondering, this code
+			 * is horrible.
 			 */
 			Upat syncstrp;
 			unsigned char *oldsyncstr;
@@ -1782,6 +1785,7 @@
 			    char savchar, *testptr;
 			    char *savpatinstart = patinstart;
 			    int savforce = forceerrs, savpatinlen = patinlen;
+			    int savpatflags = patflags;
 			    forceerrs = -1;
 			    savglobdots = globdots;
 			    matchederrs = errsfound;
@@ -1800,6 +1804,12 @@
 			    testptr = patinstart + (syncpt - syncstrp->p);
 			    DPUTS(testptr > matchpt, "BUG: EXCSYNC failed");
 			    savchar = *testptr;
+			    /*
+			     * If this isn't really the end of the string,
+			     * remember this for the (#e) assertion.
+			     */
+			    if (savchar)
+				patflags |= PAT_NOTEND;
 			    *testptr = '\0';
 			    next = PATNEXT(scan);
 			    while (next && P_ISEXCLUDE(next)) {
@@ -1848,6 +1858,7 @@
 				next = PATNEXT(next);
 			    }
 			    *testptr = savchar;
+			    patflags = savpatflags;
 			    globdots = savglobdots;
 			    forceerrs = savforce;
 			    if (ret)
@@ -2015,11 +2026,11 @@
 	     */
 	    return 0;
 	case P_ISSTART:
-	    if (patinput != patinstart)
+	    if (patinput != patinstart || (patflags & PAT_NOTSTART))
 		fail = 1;
 	    break;
 	case P_ISEND:
-	    if (*patinput)
+	    if (*patinput || (patflags & PAT_NOTEND))
 		fail = 1;
 	    break;
 	case P_END:
Index: Src/zsh.h
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/zsh.h,v
retrieving revision 1.5
diff -u -r1.5 zsh.h
--- Src/zsh.h	2000/04/13 22:25:04	1.5
+++ Src/zsh.h	2000/04/14 11:26:05
@@ -1024,6 +1024,8 @@
 #define PAT_STATIC	0x0040	/* Don't copy pattern to heap as per default */
 #define PAT_SCAN	0x0080	/* Scanning, so don't try must-match test */
 #define PAT_ZDUP        0x0100  /* Copy pattern in real memory */
+#define PAT_NOTSTART	0x0200	/* Start of string is not real start */
+#define PAT_NOTEND	0x0400	/* End of string is not real end */
 
 /* Globbing flags: lower 8 bits gives approx count */
 #define GF_LCMATCHUC	0x0100

-- 
Peter Stephenson <pws@xxxxxxxxxxxxxxxxxxxxxxxxx>
Cambridge Silicon Radio, Unit 300, Science Park, Milton Road,
Cambridge, CB4 0XL, UK                          Tel: +44 (0)1223 392070