Re: Bug#501851: zsh: Completion fails if a directory name contains '(', ')' and 'Ä '.

[Peter Stephenson <p.w.stephenson@xxxxxxxxxxxx>]

On Wed, 15 Oct 2008 13:34:47 +0900
Morita Sho <morita-pub-en-debian@xxxxxxxxxxxxxxxx> wrote:
> Thanks for detailed explanation! But I'm still confusing. Even with the old
> syntax, the completion Ä/[TAB] won't work.

You're right.  My explanation wasn't correct; it doesn't matter if you
use the m:{[lower]}={[upper]} syntax or the older one, so I've restored
the advice that the newer one is preferable.

> BTW, to find out why replacing _path_files with the old one solves the problem
> for me, I put a debug output into _path_files as below to watch the value of
> $tmp1 before the $~tmp1 expansion.
>     print "DEBUG: LINENO=$LINENO tmp1=$tmp1" > /dev/stderr
>     tmp1=( $~tmp1 ) 2> /dev/null
> 
> When I type Ä/[TAB], I got this debug output.
> DEBUG: LINENO=400 tmp1=Äï*(-/)
> DEBUG: LINENO=400 tmp1=Äï*(-/)

Thanks, this tells me that the compfiles utility isn't handling Meta
characters properly when performing matching.  Luckily this seems to be
a local problem within that command that I think the patch addresses.

Index: Doc/Zsh/compwid.yo
===================================================================
RCS file: /cvsroot/zsh/zsh/Doc/Zsh/compwid.yo,v
retrieving revision 1.44
diff -u -r1.44 compwid.yo
--- Doc/Zsh/compwid.yo	14 Oct 2008 12:59:04 -0000	1.44
+++ Doc/Zsh/compwid.yo	18 Oct 2008 18:44:08 -0000
@@ -942,16 +942,14 @@
 completion you can use `tt(m:{[:lower:]}={[:upper:]})'.  Although the
 matching system does not yet handle multibyte characters, this is likely
 to be a future extension, at which point this syntax will handle
-arbitrary alphabets; until then it is safer to use the older syntax
-that only handles ASCII characters, `tt(m:{a-z}={A-Z}) as this does
-not have side effects in the case of multibyte characters.
-
-In other cases `tt([:)var(name)tt(:])' forms are allowed.  If the two forms
-on the left and right are the same, the characters must match exactly.  In
-remaining cases, the corresponding tests are applied to both characters,
-but they are not otherwise constrained; any matching character in one set
-goes with any matching character in the other set:  this is equivalent to
-the behaviour of ordinary character classes.
+arbitrary alphabets; hence this form, rather than the use of explicit
+ranges, is the recommended form.  In other cases
+`tt([:)var(name)tt(:])' forms are allowed.  If the two forms on the left
+and right are the same, the characters must match exactly.  In remaining
+cases, the corresponding tests are applied to both characters, but they
+are not otherwise constrained; any matching character in one set goes
+with any matching character in the other set:  this is equivalent to the
+behaviour of ordinary character classes.
 
 The pattern var(tpat) may also be one or two stars, `tt(*)' or
 `tt(**)'. This means that the pattern on the command line can match
Index: Src/Zle/computil.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/Zle/computil.c,v
retrieving revision 1.110
diff -u -r1.110 computil.c
--- Src/Zle/computil.c	14 Oct 2008 22:09:11 -0000	1.110
+++ Src/Zle/computil.c	18 Oct 2008 18:44:09 -0000
@@ -4024,7 +4024,7 @@
      * management is difficult.
      */
     for (;;) {
-	for (mp = ms; *add; add++, mp++) {
+	for (mp = ms; *add; ) {
 	    if (!(m = *mp)) {
 		/*
 		 * No matcher, so just match the character
@@ -4034,13 +4034,13 @@
 		 * metacharacter?
 		 */
 		if (ret) {
-		    if (imeta(*add)) {
+		    if (*add == Meta) {
 			*p++ = Meta;
-			*p++ = *add ^ 32;
+			*p++ = add[1];
 		    } else
 			*p++ = *add;
 		} else
-		    len += imeta(*add) ? 2 : 1;
+		    len += (*add == Meta) ? 2 : 1;
 	    } else if (m->flags & CMF_RIGHT) {
 		/*
 		 * Right-anchored:  match anything followed
@@ -4049,15 +4049,16 @@
 		if (ret) {
 		    *p++ = '*';
 		    /* TODO: quote again? */
-		    if (imeta(*add)) {
+		    if (*add == Meta) {
 			*p++ = Meta;
-			*p++ = *add ^ 32;
+			*p++ = add[1];
 		    } else
 			*p++ = *add;
 		} else
-		    len += imeta(*add) ? 3 : 2;
+		    len += (*add == Meta) ? 3 : 2;
 	    } else {
 		/* The usual set of matcher possibilities. */
+		int chr = (*add == Meta) ? add[1] ^ 32 : *add;
 		int ind;
 		if (m->line->tp == CPAT_EQUIV &&
 		    m->word->tp == CPAT_EQUIV) {
@@ -4072,21 +4073,21 @@
 		     */
 		    if (ret) {
 			*p++ = '[';
-			if (imeta(*add)) {
+			if (*add == Meta) {
 			    *p++ = Meta;
-			    *p++ = *add ^ 32;
+			    *p++ = add[1];
 			} else
 			    *p++ = *add;
 		    } else
-			len += imeta(*add) ? 3 : 2;
-		    if (PATMATCHRANGE(m->line->u.str, CONVCAST(*add),
+			len += (*add == Meta) ? 3 : 2;
+		    if (PATMATCHRANGE(m->line->u.str, CONVCAST(chr),
 				      &ind, &mt)) {
 			/*
 			 * Find the equivalent match for ind in the
 			 * word pattern.
 			 */
 			if ((ind = pattern_match_equivalence
-			     (m->word, ind, mt, CONVCAST(*add))) != -1) {
+			     (m->word, ind, mt, CONVCAST(chr))) != -1) {
 			    if (ret) {
 				if (imeta(ind)) {
 				    *p++ = Meta;
@@ -4158,7 +4159,7 @@
 			 * if *add is ] and ] is also the first
 			 * character in the range.
 			 */
-			addadd = !pattern_match1(m->word, CONVCAST(*add), &mt);
+			addadd = !pattern_match1(m->word, CONVCAST(chr), &mt);
 			if (addadd && *add == ']') {
 			    if (ret)
 				*p++ = *add;
@@ -4218,6 +4219,13 @@
 		    }
 		}
 	    }
+	    if (*add == Meta) {
+		add += 2;
+		mp += 2;
+	    } else {
+		add++;
+		mp++;
+	    }
 	}
 	if (ret) {
 	    *p = '\0';
@@ -4236,19 +4244,19 @@
 
     if (m && m != pcm_err) {
 	char *tmp;
-	int al = strlen(add), tl;
-	VARARR(Cmatcher, ms, al);
+	int al = strlen(add), zl = ztrlen(add), tl, cl;
+	VARARR(Cmatcher, ms, zl);
 	Cmatcher *mp;
 	Cpattern stopp;
 	int stopl = 0;
 
-	memset(ms, 0, al * sizeof(Cmatcher));
+	memset(ms, 0, zl * sizeof(Cmatcher));
 
 	for (; m && *add; m = m->next) {
 	    stopp = NULL;
 	    if (!(m->flags & (CMF_LEFT|CMF_RIGHT))) {
 		if (m->llen == 1 && m->wlen == 1) {
-		    for (tmp = add, tl = al, mp = ms; tl; tl--, tmp++, mp++) {
+		    for (tmp = add, tl = al, mp = ms; tl; ) {
 			if (pattern_match(m->line, tmp, NULL, NULL)) {
 			    if (*mp) {
 				*tmp = '\0';
@@ -4257,6 +4265,10 @@
 			    } else
 				*mp = m;
 			}
+			cl = (*tmp == Meta) ? 2 : 1;
+			tl -= cl;
+			tmp += cl;
+			mp += cl;
 		    }
 		} else {
 		    stopp = m->line;
@@ -4264,7 +4276,7 @@
 		}
 	    } else if (m->flags & CMF_RIGHT) {
 		if (m->wlen < 0 && !m->llen && m->ralen == 1) {
-		    for (tmp = add, tl = al, mp = ms; tl; tl--, tmp++, mp++) {
+		    for (tmp = add, tl = al, mp = ms; tl; ) {
 			if (pattern_match(m->right, tmp, NULL, NULL)) {
 			    if (*mp || (tmp == add && *tmp == '.')) {
 				*tmp = '\0';
@@ -4273,6 +4285,10 @@
 			    } else
 				*mp = m;
 			}
+			cl = (*tmp == Meta) ? 2 : 1;
+			tl -= cl;
+			tmp += cl;
+			mp += cl;
 		    }
 		} else if (m->llen) {
 		    stopp = m->line;
@@ -4289,12 +4305,16 @@
 		stopl = m->lalen;
 	    }
 	    if (stopp)
-		for (tmp = add, tl = al; tl >= stopl; tl--, tmp++)
+		for (tmp = add, tl = al; tl >= stopl; ) {
 		    if (pattern_match(stopp, tmp, NULL, NULL)) {
 			*tmp = '\0';
 			al = tmp - add;
 			break;
 		    }
+		    cl = (*tmp == Meta) ? 2 : 1;
+		    tl -= cl;
+		    tmp += cl;
+		}
 	}
 	if (*add)
 	    return cfp_matcher_range(ms, add);


-- 
Peter Stephenson <p.w.stephenson@xxxxxxxxxxxx>
Web page now at http://homepage.ntlworld.com/p.w.stephenson/