Re: Backreference problem

[Peter Stephenson <pws@ibmth.df.unipi.it>]

Tanaka Akira wrote:
> Z:akr@is27e1u11% Src/zsh -f
> is27e1u11% setopt extendedglob
> is27e1u11% [[ $'\0' = (#b)($'\0') ]] && echo $mend
> 2
> is27e1u11% 
> 
> I think it should be 1.

Yes, indeed.  Indexes of metafied string elements weren't counted
properly.  The nasty part is getting this right for offsets when using
parameter substitutions, particular global substitutions.  The patch below
seems to work, but be warned that this makes my brain hurt.

--- Src/glob.c.moff	Fri Sep 17 16:33:47 1999
+++ Src/glob.c	Mon Sep 20 11:59:03 1999
@@ -2002,7 +2002,7 @@
 igetmatch(char **sp, Patprog p, int fl, int n, char *replstr)
 {
     char *s = *sp, *t, *start, sav;
-    int i, l = strlen(*sp), matched = 1;
+    int i, l = strlen(*sp), ml = ztrlen(*sp), matched = 1;
 
     MUSTUSEHEAP("igetmatch");	/* presumably covered by prefork() test */
     repllist = NULL;
@@ -2053,8 +2053,8 @@
 	    /* Smallest possible match at tail of string:  *
 	     * move back down string until we get a match. *
 	     * There's no optimization here.               */
-	    for (t = s + l; t >= s; t--) {
-		patoffset = t - s;
+	    patoffset = ml;
+	    for (t = s + l; t >= s; t--, patoffset--) {
 		if (pattry(p, t)) {
 		    *sp = get_match_ret(*sp, t - s, l, fl, replstr);
 		    patoffset = 0;
@@ -2070,8 +2070,7 @@
 	    /* Largest possible match at tail of string:       *
 	     * move forward along string until we get a match. *
 	     * Again there's no optimisation.                  */
-	    for (i = 0, t = s; i < l; i++, t++) {
-		patoffset = i;
+	    for (i = 0, t = s; i < l; i++, t++, patoffset++) {
 		if (pattry(p, t)) {
 		    *sp = get_match_ret(*sp, i, l, fl, replstr);
 		    patoffset = 0;
@@ -2091,15 +2090,14 @@
 	    } /* fall through */
 	case (SUB_SUBSTR|SUB_LONG):
 	    /* longest or smallest at start with substrings */
-	    start = s;
+	    t = s;
 	    if (fl & SUB_GLOBAL)
 		repllist = newlinklist();
 	    do {
 		/* loop over all matches for global substitution */
 		matched = 0;
-		for (t = start; t < s + l; t++) {
+		for (; t < s + l; t++, patoffset++) {
 		    /* Find the longest match from this position. */
-		    patoffset = t - start;
 		    if (pattry(p, t) && patinput > t) {
 			char *mpos = patinput;
 			if (!(fl & SUB_LONG) && !(p->flags & PAT_PURES)) {
@@ -2117,8 +2115,8 @@
 			}
 			if (!--n || (n <= 0 && (fl & SUB_GLOBAL))) {
 			    *sp = get_match_ret(*sp, t-s, mpos-s, fl, replstr);
-			    if (mpos == start)
-				mpos++;
+			    if (mpos == t)
+				METAINC(mpos);
 			}
 			if (!(fl & SUB_GLOBAL)) {
 			    if (n) {
@@ -2139,7 +2137,9 @@
 			 * which is already marked for replacement.
 			 */
 			matched = 1;
-			start = mpos;
+			for ( ; t < mpos; t++, patoffset++)
+			    if (*t == Meta)
+				t++;
 			break;
 		    }
 		    if (*t == Meta)
@@ -2161,17 +2161,16 @@
 
 	case (SUB_END|SUB_SUBSTR):
 	    /* Shortest at end with substrings */
-	    patoffset = l;
+	    patoffset = ml;
 	    if (pattry(p, s + l) && !--n) {
 		*sp = get_match_ret(*sp, l, l, fl, replstr);
 		patoffset = 0;
 		return 1;
 	    } /* fall through */
-	    patoffset = 0;
 	case (SUB_END|SUB_LONG|SUB_SUBSTR):
 	    /* Longest/shortest at end, matching substrings.       */
-	    for (t = s + l - 1; t >= s; t--) {
-		patoffset = t - s;
+	    patoffset--;
+	    for (t = s + l - 1; t >= s; t--, patoffset--) {
 		if (t > s && t[-1] == Meta)
 		    t--;
 		if (pattry(p, t) && patinput > t && !--n) {
@@ -2195,7 +2194,7 @@
 		    return 1;
 		}
 	    }
-	    patoffset = l;
+	    patoffset = ml;
 	    if ((fl & SUB_LONG) && pattry(p, s + l) && !--n) {
 		*sp = get_match_ret(*sp, l, l, fl, replstr);
 		patoffset = 0;
--- Src/pattern.c.moff	Mon Sep 20 12:11:45 1999
+++ Src/pattern.c	Mon Sep 20 12:04:48 1999
@@ -1335,15 +1335,15 @@
 		 * in the pattern matching part.
 		 */
 		char *str;
-		int len = patinput - patinstart;
+		int mlen = ztrsub(patinput, patinstart);
 
 		PERMALLOC {
-		    str = dupstrpfx(patinstart, len);
+		    str = dupstrpfx(patinstart, patinput - patinstart);
 		} LASTALLOC;
 		setsparam("MATCH", str);
 		setiparam("MBEGIN", (zlong)(patoffset + !isset(KSHARRAYS)));
 		setiparam("MEND",
-			  (zlong)(len + patoffset + !isset(KSHARRAYS) - 1));
+			  (zlong)(mlen + patoffset + !isset(KSHARRAYS) - 1));
 	    }
 	    if (prog->patnpar && !(patflags & PAT_FILE)) {
 		/*
@@ -1374,11 +1374,11 @@
 			 * corresponds to indexing as ${foo[1,1]}.
 			 */
 			sprintf(numbuf, "%ld",
-				(long)((*sp - patinstart) + patoffset +
+				(long)(ztrsub(*sp, patinstart) + patoffset +
 				       !isset(KSHARRAYS)));
 			mbeginarr[i] = ztrdup(numbuf);
 			sprintf(numbuf, "%ld",
-				(long)((*ep - patinstart) + patoffset +
+				(long)(ztrsub(*ep, patinstart) + patoffset +
 				       !isset(KSHARRAYS) - 1));
 			mendarr[i] = ztrdup(numbuf);
 			sp++;


-- 
Peter Stephenson <pws@ibmth.df.unipi.it>       Tel: +39 050 844536
WWW:  http://www.ifh.de/~pws/
Dipartimento di Fisica, Via Buonarroti 2, 56127 Pisa, Italy