about summary refs log tree commit diff
diff options
context:
space:
mode:
-rw-r--r--ChangeLog7
-rw-r--r--Doc/Zsh/expn.yo60
-rw-r--r--Src/subst.c11
-rw-r--r--Test/D04parameter.ztst14
4 files changed, 56 insertions, 36 deletions
diff --git a/ChangeLog b/ChangeLog
index 3ba0a6b1d..a68c01534 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2010-11-25  Peter Stephenson  <pws@csr.com>
+
+	* 28434: Doc/Zsh/expn.yo, Src/subst.c, Test/D04parameter.ztst:
+	Make ${NAME:OFFSET} always use zero-offset.
+
 2010-11-22  Peter Stephenson  <pws@csr.com>
 
 	* 28424: Doc/Zsh/options.yo, Src/options.c, Src/utils.c,
@@ -13838,5 +13843,5 @@
 
 *****************************************************
 * This is used by the shell to define $ZSH_PATCHLEVEL
-* $Revision: 1.5125 $
+* $Revision: 1.5126 $
 *****************************************************
diff --git a/Doc/Zsh/expn.yo b/Doc/Zsh/expn.yo
index 416d46407..0c26a7ca5 100644
--- a/Doc/Zsh/expn.yo
+++ b/Doc/Zsh/expn.yo
@@ -588,23 +588,29 @@ remove the non-matched elements).
 xitem(tt(${)var(name)tt(:)var(offset)tt(}))
 item(tt(${)var(name)tt(:)var(offset)tt(:)var(length)tt(}))(
 This syntax gives effects similar to parameter subscripting
-in the form tt($)var(name)tt({)var(offset)tt(,)var(end)tt(}) but in
-a form compatible with other shells.
-
-If the variable var(name) is a scalar, substitute the contents
-starting from offset var(offset); if var(name) is an array,
-substitute elements from element var(offset).  If var(length) is
-given, substitute that many characters or elements, otherwise the
-entire rest of the scalar or array.
-
-var(offset) is treated similarly to a parameter subscript:
-the offset of the first character or element in var(name)
-is 0 if the option tt(KSH_ARRAYS) is set, else 1; a negative
-subscript counts backwards so that -1 corresponds to the last
-character or element.
+in the form tt($)var(name)tt({)var(start)tt(,)var(end)tt(}), but is
+compatible with other shells; note that both var(offset) and var(length)
+are interpreted differently from the components of a subscript.
+
+If var(offset) is non-negative, then if the variable var(name) is a
+scalar substitute the contents starting var(offset) characters from the
+first character of the string, and if var(name) is an array substitute
+elements starting var(offset) elements from the first element.  If
+var(length) is given, substitute that many characters or elements,
+otherwise the entire rest of the scalar or array.
+
+A positive var(offset) is always treated as the offset of a character or
+element in var(name) from the first character or element of the array
+(this is different from native zsh subscript notation).  Hence 0
+refers to the first character or element regardless of the setting of
+the option tt(KSH_ARRAYS).
+
+A negative offset counts backwards from the end of the scalar or array,
+so that -1 corresponds to the last character or element, and so on.
 
 var(length) is always treated directly as a length and hence may not be
-negative.
+negative.  The option tt(MULTIBYTE) is obeyed, i.e. the offset and length
+count multibyte characters where appropriate.
 
 var(offset) and var(length) undergo the same set of shell substitutions
 as for scalar assignment; in addition, they are then subject to arithmetic
@@ -615,19 +621,29 @@ print ${foo: 1 + 2}
 print ${foo:$(( 1 + 2))}
 print ${foo:$(echo 1 + 2)})
 
-all have the same effect.
+all have the same effect, extracting the string starting at the fourth
+character of tt($foo) if the substution would otherwise return a scalar,
+or the array starting at the fourth element if tt($foo) would return an
+array.  Note that with the option tt(KSH_ARRAYS) tt($foo) always returns
+a scalar (regardless of the use of the offset syntax) and a form
+such as tt($foo[*]:3) is required to extract elements of an array named
+tt(foo).
 
-Note that if var(offset) is negative, the tt(-) may not appear immediately
+If var(offset) is negative, the tt(-) may not appear immediately
 after the tt(:) as this indicates the
-tt(${)var(name)tt(:-)var(word)tt(}) form of substitution; a space
+tt(${)var(name)tt(:-)var(word)tt(}) form of substitution.  Instead, a space
 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.
+used to indicate history-style modifiers.  To substitute a value from a
+variable, the recommended approach is to proceed it with a tt($) as this
+signifies the intention (parameter substitution can easily be rendered
+unreadable); however, as arithmetic substitution is performed, the
+expression tt(${var: offs}) does work, retrieving the offset from
+tt($offs).
 
 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
+for array offset 0.  This usually accesses to the
+first element of the array.  However, if the substitution refers 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
diff --git a/Src/subst.c b/Src/subst.c
index 12825ff93..031a1affd 100644
--- a/Src/subst.c
+++ b/Src/subst.c
@@ -1640,7 +1640,7 @@ paramsubst(LinkList l, LinkNode n, char **str, int qt, int ssub)
     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.
+     * e.g ${*:1:1} refers to $1.
      * This is for compatibility.
      */
     int horrible_offset_hack = 0;
@@ -2768,16 +2768,15 @@ paramsubst(LinkList l, LinkNode n, char **str, int qt, int ssub)
 			return NULL;
 		    }
 		}
-		if (!isset(KSHARRAYS) || horrible_offset_hack) {
+		if (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.
+		     * style positional parameter array which includes
+		     * offset 0, we use $0.
 		     */
-		    if (isset(KSHARRAYS) && horrible_offset_hack &&
-			offset == 0 && isarr) {
+		    if (offset == 0 && isarr) {
 			offset_hack_argzero = 1;
 		    } else if (offset > 0) {
 			offset--;
diff --git a/Test/D04parameter.ztst b/Test/D04parameter.ztst
index 46565a121..4bd911e5f 100644
--- a/Test/D04parameter.ztst
+++ b/Test/D04parameter.ztst
@@ -1268,15 +1268,15 @@
    print ${foo:$(echo 3 + 3):`echo 4 - 3`}
    print ${foo: -1}
    print ${foo: -10}
-0:Bash-style subscripts, scalar
->3456789
+0:Bash-style offsets, scalar
 >456789
 >56789
 >6789
->3
+>789
 >4
 >5
 >6
+>7
 >9
 >123456789
 
@@ -1291,15 +1291,15 @@
    print ${foo:$(echo 3 + 3):`echo 4 - 3`}
    print ${foo: -1}
    print ${foo: -10}
-0:Bash-style subscripts, array
->3 4 5 6 7 8 9
+0:Bash-style offsets, array
 >4 5 6 7 8 9
 >5 6 7 8 9
 >6 7 8 9
->3
+>7 8 9
 >4
 >5
 >6
+>7
 >9
 >1 2 3 4 5 6 7 8 9
 
@@ -1321,7 +1321,7 @@
      echo ${str: -1:1}
    }
    testfn
-0:Bash-style subscripts, Bourne-style indexing
+0:Bash-style offsets, Bourne-style indexing
 >1
 >2
 >3