Re: histsubstpattern in zmv

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

> On 02/06/2023 09:40 Peter Stephenson <p.w.stephenson@xxxxxxxxxxxx> wrote:
> On 01/06/2023 19:35 Stephane Chazelas <stephane@xxxxxxxxxxxx> wrote:
> > The csh-style ${var:s/foo/bar} is often more legible and easy
> > to cumulate than the Korn-style equivalent ${var/foo/bar}
> >..
> > But that needs set -o histsubstpattern and in zmv, emulate -LR
> > zsh resets options.
> > 
> > Would it be possibe to enable it in zmv along with extendedglob
> > which is already enabled there, or if not allow the user to enable it,
> > or maybe even better introduced some :+s/pattern/repl/
> > :-s/string/repl/ or :S/pattern/replacement/ so we can use both
> > at the same time, like ${f:gs/***/3-stars/:gS/???/any-3-chars} ?
> 
> I can't see any good reason not to enable it.

Having said that, adding an :S variant isn't particularly difficult
and is more widely useful.

pws

diff --git a/Doc/Zsh/expn.yo b/Doc/Zsh/expn.yo
index 6f86d0c54..7bc736470 100644
--- a/Doc/Zsh/expn.yo
+++ b/Doc/Zsh/expn.yo
@@ -312,7 +312,8 @@ zero) that are neither `tt(.)' nor `tt(/)' and that continue to the end
 of the string.  For example, the extension of
 `tt(foo.orig.c)' is `tt(.c)', and `tt(dir.c/foo)' has no extension.
 )
-item(tt(s/)var(l)tt(/)var(r)[tt(/)])(
+xitem(tt(s/)var(l)tt(/)var(r)[tt(/)])
+item(tt(S/)var(l)tt(/)var(r)[tt(/)])(
 Substitute var(r) for var(l) as described below.
 The substitution is done only for the
 first string that matches var(l).  For arrays and for filename
@@ -324,13 +325,17 @@ perform global substitution, i.e. substitute every occurrence of var(r)
 for var(l).  Note that the tt(g) or tt(:G) must appear in exactly the
 position shown.
 
+The use of tt(S) instead of tt(s) is identical except that
+the source is treated as a pattern, just as if the option
+tt(HIST_SUBST_PATTERN) were set.
+
 See further notes on this form of substitution below.
 )
 item(tt(&))(
-Repeat the previous tt(s) substitution.  Like tt(s), may be preceded
-immediately by a tt(g).  In parameter expansion the tt(&) must appear
-inside braces, and in filename generation it must be quoted with a
-backslash.
+Repeat the previous tt(s) or tt(S) substitution, whichever was most
+recent.  Like tt(s) and tt(S), may be preceded immediately by a tt(g).
+In parameter expansion the tt(&) must appear inside braces, and in
+filename generation it must be quoted with a backslash.
 )
 item(tt(t) [ var(digits) ])(
 Remove all leading pathname components, leaving the final component (tail).
@@ -377,7 +382,8 @@ substitutions or expansions are performed once at the time the qualifier
 is parsed, even before the `tt(:s)' expression itself is divided into
 var(l) and var(r) sides.
 
-If the option tt(HIST_SUBST_PATTERN) is set, var(l) is treated as
+If the option tt(HIST_SUBST_PATTERN) is set or the original substitution
+was started with a capital tt(S), var(l) is treated as
 a pattern of the usual form described in
 ifzman(the section FILENAME GENERATION below)\
 ifnzman(noderef(Filename Generation)).  This can be used in
diff --git a/Src/hist.c b/Src/hist.c
index 7e6394406..b4dc53d90 100644
--- a/Src/hist.c
+++ b/Src/hist.c
@@ -163,6 +163,11 @@ char *hsubl;
 /**/
 char *hsubr;
  
+/* state of histsubstpattern at last substitution */
+
+/**/
+int hsubpatopt;
+
 /* pointer into the history line */
  
 /**/
@@ -624,7 +629,7 @@ histsubchar(int c)
 	    return substfailed();
 	if (!hsubl)
 	    return -1;
-	if (subst(&sline, hsubl, hsubr, gbal))
+	if (subst(&sline, hsubl, hsubr, gbal, 0))
 	    return substfailed();
     } else {
 	/* Line doesn't begin ^foo^bar */
@@ -831,7 +836,7 @@ histsubchar(int c)
 	    if ((c = ingetc()) == 'g') {
 		gbal = 1;
 		c = ingetc();
-		if (c != 's' && c != '&') {
+		if (c != 's' && c != 'S' && c != '&') {
 		    zerr("'s' or '&' modifier expected after 'g'");
 		    return -1;
 		}
@@ -891,11 +896,13 @@ histsubchar(int c)
 		}
 		break;
 	    case 's':
+	    case 'S':
+		hsubpatopt = (c == 'S');
 		if (getsubsargs(sline, &gbal, &cflag))
 		    return -1; /* fall through */
 	    case '&':
 		if (hsubl && hsubr) {
-		    if (subst(&sline, hsubl, hsubr, gbal))
+		    if (subst(&sline, hsubl, hsubr, gbal, hsubpatopt))
 			return substfailed();
 		} else {
 		    herrflush();
@@ -2315,7 +2322,7 @@ casemodify(char *str, int how)
 
 /**/
 int
-subst(char **strptr, char *in, char *out, int gbal)
+subst(char **strptr, char *in, char *out, int gbal, int forcepat)
 {
     char *str = *strptr, *substcut, *sptr;
     int off, inlen, outlen;
@@ -2323,7 +2330,7 @@ subst(char **strptr, char *in, char *out, int gbal)
     if (!*in)
 	in = str, gbal = 0;
 
-    if (isset(HISTSUBSTPATTERN)) {
+    if (isset(HISTSUBSTPATTERN) || forcepat) {
 	int fl = SUB_LONG|SUB_REST|SUB_RETFAIL;
 	char *oldin = in;
 	if (gbal)
diff --git a/Src/subst.c b/Src/subst.c
index 974d6171e..14947ae36 100644
--- a/Src/subst.c
+++ b/Src/subst.c
@@ -4351,6 +4351,8 @@ modify(char **str, char **ptr, int inbrace)
 		break;
 
 	    case 's':
+	    case 'S':
+		hsubpatopt = (**ptr == 'S');
 		c = **ptr;
 		(*ptr)++;
 		ptr1 = *ptr;
@@ -4445,7 +4447,7 @@ modify(char **str, char **ptr, int inbrace)
 		break;
 
 	    case '&':
-		c = 's';
+		c = hsubpatopt ? 'S' : 's';
 		break;
 
 	    case 'g':
@@ -4534,8 +4536,10 @@ modify(char **str, char **ptr, int inbrace)
 			copy = casemodify(tt, CASMOD_UPPER);
 			break;
 		    case 's':
+		    case 'S':
+			hsubpatopt = (c == 'S');
 			if (hsubl && hsubr)
-			    subst(&copy, hsubl, hsubr, gbal);
+			    subst(&copy, hsubl, hsubr, gbal, hsubpatopt);
 			break;
 		    case 'q':
 			copy = quotestring(copy, QT_BACKSLASH_SHOWNULL);
@@ -4620,8 +4624,10 @@ modify(char **str, char **ptr, int inbrace)
 		    *str = casemodify(*str, CASMOD_UPPER);
 		    break;
 		case 's':
+		case 'S':
+		    hsubpatopt = (c == 'S');
 		    if (hsubl && hsubr)
-			subst(str, hsubl, hsubr, gbal);
+			subst(str, hsubl, hsubr, gbal, hsubpatopt);
 		    break;
 		case 'q':
 		    *str = quotestring(*str, QT_BACKSLASH);
diff --git a/Test/D04parameter.ztst b/Test/D04parameter.ztst
index 7990c2958..2fd2f975f 100644
--- a/Test/D04parameter.ztst
+++ b/Test/D04parameter.ztst
@@ -2754,3 +2754,13 @@ F:behavior, see http://austingroupbugs.net/view.php?id=888
 0:(users/28784 inspired this) substituting a single-quoted backslash, part #3: control
 >xfooy
 
+ spacestring="string with spaces"
+ print ${spacestring:gs/[[:space:]]/ /}
+ print ${spacestring:g&}
+ print ${spacestring:gS/[[:space:]]//}
+ print ${spacestring:g&}
+0:Different behaviour of :s and :S modifiers
+>string with spaces
+>string with spaces
+>stringwithspaces
+>stringwithspaces