Re: PATCH: bash-style substrings & subarrays

[Peter Stephenson <Peter.Stephenson@xxxxxxx>]

On Wed, 17 Nov 2010 16:54:17 +0000
Peter Stephenson <pws@xxxxxxx> wrote:
> One thing I have not yet tried to do is the fact that the offset is
> offset by 1 when the variable is * or @ in bash (i.e. corresponding to
> having KSH_ARRAYS set, except it doesn't this time), i.e. ${*:1:1}
> gives you $1 not $2.

I refer honourable members to the answer I gave on a previous occasion.

> Yech.

Index: Doc/Zsh/expn.yo
===================================================================
RCS file: /cvsroot/zsh/zsh/Doc/Zsh/expn.yo,v
retrieving revision 1.122
diff -p -u -r1.122 expn.yo
--- Doc/Zsh/expn.yo	18 Nov 2010 10:07:56 -0000	1.122
+++ Doc/Zsh/expn.yo	18 Nov 2010 12:38:42 -0000
@@ -623,6 +623,16 @@ tt(${)var(name)tt(:-)var(word)tt(}) form
 may be inserted before the tt(-).  Furthermore, neither var(offset) nor
 var(length) may begin with an alphabetic character or tt(&) as these are
 used to indicate history-style modifiers.
+
+For further compatibility with other shells there is a special case
+when the tt(KSH_ARRAYS) option is active, as in emulation of
+Bourne-style shells.  In this case array subscript 0 usually refers to the
+first element of the array.  However, if the substitution refers to the
+positional parameter array, e.g. tt($@) or tt($*), then offset 0
+instead refers to tt($0), offset 1 refers to tt($1), and so on.  In
+other words, the positional parameter array is effectively extended by
+prepending tt($0).  Hence tt(${*:0:1}) substitutes tt($0) and
+tt(${*:1:1}) substitutes tt($1).
 )
 xitem(tt(${)var(name)tt(/)var(pattern)tt(/)var(repl)tt(}))
 item(tt(${)var(name)tt(//)var(pattern)tt(/)var(repl)tt(}))(
Index: Src/subst.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/subst.c,v
retrieving revision 1.109
diff -p -u -r1.109 subst.c
--- Src/subst.c	18 Nov 2010 10:07:56 -0000	1.109
+++ Src/subst.c	18 Nov 2010 12:38:42 -0000
@@ -1636,6 +1636,12 @@ paramsubst(LinkList l, LinkNode n, char 
      * and the argument passing to fetchvalue has another kludge.
      */
     int subexp;
+    /*
+     * If we're referring to the positional parameters, then
+     * e.g ${*:1:1} refers to $1 even if KSH_ARRAYS is in effect.
+     * This is for compatibility.
+     */
+    int horrible_offset_hack = 0;
 
     *s++ = '\0';
     /*
@@ -2281,6 +2287,12 @@ paramsubst(LinkList l, LinkNode n, char 
 		val = getstrvalue(v);
 	    }
 	}
+	/* See if this is a reference to the positional parameters. */
+	if (v && v->pm && v->pm->gsu.a == &vararray_gsu &&
+	    (char ***)v->pm->u.data == &pparams)
+	    horrible_offset_hack = 1;
+	else
+	    horrible_offset_hack = 0;
 	/*
 	 * Finished with the original parameter and its indices;
 	 * carry on looping to see if we need to do more indexing.
@@ -2732,6 +2744,7 @@ paramsubst(LinkList l, LinkNode n, char 
 	    if (check_offset) {
 		zlong offset = mathevali(check_offset);
 		zlong length = (zlong)-1;
+		int offset_hack_argzero = 0;
 		if (errflag)
 		    return NULL;
 		if ((*check_offset2 && *check_offset2 != ':')) {
@@ -2753,8 +2766,21 @@ paramsubst(LinkList l, LinkNode n, char 
 			return NULL;
 		    }
 		}
-		if (!isset(KSHARRAYS) && offset > 0)
-		    offset--;
+		if (!isset(KSHARRAYS) || horrible_offset_hack) {
+		    /*
+		     * As part of the 'orrible hoffset 'ack,
+		     * (what hare you? Han 'orrible hoffset 'ack,
+		     * sergeant major), if we are given a ksh/bash/POSIX
+		     * style array which includes offset 0, we use
+		     * $0.
+		     */
+		    if (isset(KSHARRAYS) && horrible_offset_hack &&
+			offset == 0 && isarr) {
+			offset_hack_argzero = 1;
+		    } else if (offset > 0) {
+			offset--;
+		    }
+		}
 		if (isarr) {
 		    int alen = arrlen(aval), count;
 		    char **srcptr, **dstptr, **newarr;
@@ -2764,6 +2790,8 @@ paramsubst(LinkList l, LinkNode n, char 
 			if (offset < 0)
 			    offset = 0;
 		    }
+		    if (offset_hack_argzero)
+			alen++;
 		    if (length < 0)
 		      length = alen;
 		    if (offset > alen)
@@ -2774,6 +2802,10 @@ paramsubst(LinkList l, LinkNode n, char 
 		    srcptr = aval + offset;
 		    newarr = dstptr = (char **)
 			zhalloc((length+1)*sizeof(char *));
+		    if (count && offset_hack_argzero) {
+			*dstptr++ = dupstring(argzero);
+			count--;
+		    }
 		    while (count--)
 			*dstptr++ = dupstring(*srcptr++);
 		    *dstptr = (char *)NULL;
Index: Test/D04parameter.ztst
===================================================================
RCS file: /cvsroot/zsh/zsh/Test/D04parameter.ztst,v
retrieving revision 1.45
diff -p -u -r1.45 D04parameter.ztst
--- Test/D04parameter.ztst	18 Nov 2010 10:07:56 -0000	1.45
+++ Test/D04parameter.ztst	18 Nov 2010 12:38:42 -0000
@@ -1302,3 +1302,32 @@
 >6
 >9
 >1 2 3 4 5 6 7 8 9
+
+   testfn() {
+     emulate -L sh
+     set -A foo 1 2 3
+     set -- 1 2 3
+     str=abc
+     echo ${foo[*]:0:1}
+     echo ${foo[*]:1:1}
+     echo ${foo[*]: -1:1}
+     :
+     echo ${*:0:1}
+     echo ${*:1:1}
+     echo ${*: -1:1}
+     :
+     echo ${str:0:1}
+     echo ${str:1:1}
+     echo ${str: -1:1}
+   }
+   testfn
+0:Bash-style subscripts, Bourne-style indexing
+>1
+>2
+>3
+>testfn
+>1
+>3
+>a
+>b
+>c

-- 
Peter Stephenson <pws@xxxxxxx>            Software Engineer
Tel: +44 (0)1223 692070                   Cambridge Silicon Radio Limited
Churchill House, Cambridge Business Park, Cowley Road, Cambridge, CB4 0WZ, UK


Member of the CSR plc group of companies. CSR plc registered in England and Wales, registered number 4187346, registered office Churchill House, Cambridge Business Park, Cowley Road, Cambridge, CB4 0WZ, United Kingdom