Re: PATCH: Array subscript documentation

["Bart Schaefer" <schaefer@candle.brasslantern.com>]

On Apr 22, 11:40pm, Peter Stephenson wrote:
} Subject: Re: PATCH: Array subscript documentation
}
} > +example(typeset -A aa
} > +typeset "aa[one\"two\"three\"quotes]"=QQQ
} > +print "$aa[one\"two\"three\"quotes]")
} 
} Unless there's something remaining uncommitted, the last line still
} doesn't work. The assignment strips the backslashes, but the expansion
} doesn't.

Oh, dear.  When I tested this, I forgot to do the `typeset -A' first, so
naturally it appeared to work because both strings evaluate to zero as
arithmetic on an ordinary array.

} I suppose that's because the Bnull's don't get stripped till after the
} end of the parameter expansion. But I don't really understand.

Dnulls, actually, and yes, that's exactly it.  Turns out getindex() needs
to know whether it's being called from inside double quotes.  I'm going
to commit the following patch, which fixes the bug above, and then look
at ways to eliminate the extra strchr(), as the caller of getindex()
ought to be equipped to supply this information.

I was distracted for quite a while trying to fix this bug:

% typeset -A aa
% typeset "aa[one\"two\"three\"quotes]"=QQQ
% print $aa[one"two"three"quotes]"
QQQ

Note in the print line, that the quotes are balanced but that the fourth
quote is outside the brackets.  This should be a parse error.  However,
this bug is present in 4.0.1-pre-2 and other earlier versions of zsh, so
I eventually gave up on it.

Incidentally, an extra thank you goes to everyone who contributed to the 
test suite, especially PWS and Sven.  I wouldn't have been willing/able
to fiddle with this whole subscripting issue if there hadn't been a way
to thoroughly check that I wasn't breaking a vital bit of shell parsing.

diff -ru -x CVS zsh-forge/current/Src/lex.c zsh-4.0/Src/lex.c
--- zsh-forge/current/Src/lex.c	Sat Apr 21 11:40:35 2001
+++ zsh-4.0/Src/lex.c	Sun Apr 22 20:58:02 2001
@@ -1305,7 +1305,8 @@
 		    c == endchar || c == '`' ||
 		    (endchar == ']' && (c == '[' || c == ']' ||
 					c == '(' || c == ')' ||
-					c == '{' || c == '}')))
+					c == '{' || c == '}' ||
+					(c == '"' && sub))))
 		    add(Bnull);
 		else {
 		    /* lexstop is implicitly handled here */
@@ -1390,7 +1391,7 @@
 		err = (!brct-- && math);
 	    break;
 	case '"':
-	    if (intick || endchar == ']' || (!endchar && !bct))
+	    if (intick || ((endchar == ']' || !endchar) && !bct))
 		break;
 	    if (bct) {
 		add(Dnull);
@@ -1463,7 +1464,7 @@
 
 /**/
 mod_export char *
-parse_subscript(char *s)
+parse_subscript(char *s, int sub)
 {
     int l = strlen(s), err;
     char *t;
@@ -1477,7 +1478,7 @@
     len = 0;
     bptr = tokstr = s;
     bsiz = l + 1;
-    err = dquote_parse(']', 1);
+    err = dquote_parse(']', sub);
     if (err) {
 	err = *bptr;
 	*bptr = 0;
diff -ru -x CVS zsh-forge/current/Src/params.c zsh-4.0/Src/params.c
--- zsh-forge/current/Src/params.c	Sun Apr 22 11:43:22 2001
+++ zsh-4.0/Src/params.c	Mon Apr 23 07:46:42 2001
@@ -785,7 +785,7 @@
 	return 0;
 
     /* Require balanced [ ] pairs with something between */
-    if (!(ss = parse_subscript(++ss)))
+    if (!(ss = parse_subscript(++ss, 1)))
 	return 0;
     untokenize(s);
     return !ss[1];
@@ -922,18 +922,18 @@
     for (t = s, i = 0;
 	 (c = *t) && ((c != Outbrack &&
 		       (ishash || c != ',')) || i); t++) {
-	/* Untokenize INULL() except before brackets, for parsestr() */
+	/* Untokenize INULL() except before brackets and double-quotes */
 	if (INULL(c)) {
 	    c = t[1];
 	    if (c == '[' || c == ']' ||
 		c == '(' || c == ')' ||
 		c == '{' || c == '}') {
 		/* This test handles nested subscripts in hash keys */
-		if (ishash && i)
+		if (ishash && i)
 		    *t = ztokens[*t - Pound];
 		needtok = 1;
 		++t;
-	    } else
+	    } else if (c != '"')
 		*t = ztokens[*t - Pound];
 	    continue;
 	}
@@ -1181,16 +1181,17 @@
 {
     int start, end, inv = 0;
     char *s = *pptr, *tbrack;
+    int dq = !!strchr(s, Dnull);
 
     *s++ = '[';
-    s = parse_subscript(s);	/* Error handled after untokenizing */
+    s = parse_subscript(s, dq);	/* Error handled after untokenizing */
     /* Now we untokenize everthing except INULL() markers so we can check *
      * for the '*' and '@' special subscripts.  The INULL()s are removed  *
      * in getarg() after we know whether we're doing reverse indexing.    */
     for (tbrack = *pptr + 1; *tbrack && tbrack != s; tbrack++) {
 	if (INULL(*tbrack) && !*++tbrack)
 	    break;
-	if (itok(*tbrack))
+	if (itok(*tbrack))	/* Need to check for Nularg here? */
 	    *tbrack = ztokens[*tbrack - Pound];
     }
     /* If we reached the end of the string (s == NULL) we have an error */
diff -ru -x CVS zsh-forge/current/Test/D06subscript.ztst zsh-4.0/Test/D06subscript.ztst
--- zsh-forge/current/Test/D06subscript.ztst	Sun Apr 22 11:43:22 2001
+++ zsh-4.0/Test/D06subscript.ztst	Sun Apr 22 21:44:07 2001
@@ -145,3 +145,18 @@
 0:Associative array keys interpreted as patterns
 >\2 backcbrack cbrack star
 >\\\4 \\\? star zounds
+
+  typeset "A[one\"two\"three\"quotes]"=QQQ
+  typeset 'A[one\"two\"three\"quotes]'=qqq
+  print -R "$A[one\"two\"three\"quotes]"
+  print -R $A[one\"two\"three\"quotes]
+  A[one"two"three"four"quotes]=QqQq
+  print -R $A[one"two"three"four"quotes]
+  print -R $A[$A[(i)one\"two\"three\"quotes]]
+  print -R "$A[$A[(i)one\"two\"three\"quotes]]"
+0:Associative array keys with double quotes
+>QQQ
+>qqq
+>QqQq
+>qqq
+>QQQ

-- 
Bart Schaefer                                 Brass Lantern Enterprises
http://www.well.com/user/barts              http://www.brasslantern.com

Zsh: http://www.zsh.org | PHPerl Project: http://phperl.sourceforge.net