From: nobu.nokada@...
Date: 2002-12-14T02:03:31+09:00
Subject: Re: [RCR] Global Regexp Match Mechanism (//g)

Hi,

At Sat, 14 Dec 2002 01:25:21 +0900,
Matt Armstrong wrote:
> >> Freezing the string is inconvenient in my application.  I examine a
> >> string in detail before deciding whether to append more data to it
> >> (String#<<) from a file or start a new string.
> >
> > Modification of target string will cause the character boundary
> > issue even with your String#gpos.  It must be recalculated.
> 
> It is possible to be fancy and avoid recalculation of byte offset B of
> character position C.  E.g. if you insert 10 bytes before B, increment
> B by 10.

It means all destructive String methods must pay that cost.  It
depends on frequencies of index and other methods, but I doubt
if it acceptable.

> But your point about thread safety is good.  String#index together
> with \G is a good solution.  Though Regexp#match with a character
> offset may be handy too, since it returns the MatchData.

I also want this extension.


Index: re.c
===================================================================
RCS file: /cvs/ruby/src/ruby/re.c,v
retrieving revision 1.86
diff -u -2 -p -r1.86 re.c
--- re.c	12 Dec 2002 09:17:32 -0000	1.86
+++ re.c	12 Dec 2002 09:31:57 -0000
@@ -1130,10 +1130,18 @@ rb_reg_match2(re)
 
 static VALUE
-rb_reg_match_m(re, str)
-    VALUE re, str;
+rb_reg_match_m(argc, argv, re)
+    int argc;
+    VALUE *argv;
+    VALUE re;
 {
-    VALUE result = rb_reg_match(re, str);
+    VALUE str, initpos, result;
+    long pos = 0;
 
-    if (NIL_P(result)) return Qnil;
+    if (rb_scan_args(argc, argv, "11", &str, &initpos) == 2) {
+	pos = NUM2LONG(initpos);
+    }
+    if (NIL_P(str)) return Qnil;
+    StringValue(str);
+    if (rb_reg_search(re, str, pos, 0) < 0) return Qnil;
     result = rb_backref_get();
     rb_match_busy(result);
@@ -1586,5 +1683,5 @@ Init_Regexp()
     rb_define_method(rb_cRegexp, "===", rb_reg_match, 1);
     rb_define_method(rb_cRegexp, "~", rb_reg_match2, 0);
-    rb_define_method(rb_cRegexp, "match", rb_reg_match_m, 1);
+    rb_define_method(rb_cRegexp, "match", rb_reg_match_m, -1);
     rb_define_method(rb_cRegexp, "to_s", rb_reg_to_s, 0);
     rb_define_method(rb_cRegexp, "inspect", rb_reg_inspect, 0);


-- 
Nobu Nakada