D:\Temp\file.ext.bak
E:\Code\junk.stuff.ext

##</code><code>##

           # not all of these are valid urls
           # nor do I want all of them to match
           # For instance some invalids I DO want to match
           # but handle their invalidity later
my @url=qw(
           http://www.foobar.com
           http://www.foobar.com/foo
           http://www.foobar.com/foo/
           http://www.foobar.com/foo.pl
           http://www.foobar.com/.extension
           http://www.foobar.com?test
           http://www.foobar.com/foo?test
           http://www.foobar.com/foo/?test
           http://www.foobar.com/foo.pl?
           http://www.foobar.com/.extension?
           http://www.foobar.com/foo/bar/foobar.html
           http://www.foobar.com/foo/bar/foo.bar.html
           http://perlmonks.com/index.pl?node_id=68135
           http://perlmonks.com/index.pl??node_id=68135
           http:///file.ext?
           http:///.ext?
           http:///file.ext
           http:///.ext
           );


##</code><code>##

 
foreach (@url) {
	if (my @parts=m!^http://   #must begin http://
	              (            #capture the site
	                 [^/?]+    #  site has no / or ? in it
	              )            #its mandatory

	              (            #capture the path
	                 /         #  starts with a /
	                 (?:       #  group but dont capture
	                    [^/?]+ #    anything but / or ?
	                    /      #    followed by a /
	                 )*        #  zero or more times (opt)
	              )?           #all optional

	              (            #capture the filename
	                  [^./?]   #  doesnt start with a . or ? or /
	                  [^/?]+?  #  all chars not / or ? , (ctd.)
	                           #    --leave stuff for rest of rex
	               )?          #we dont have to have a filename

	              (            #capture the extension
	                  \.       #  they start with dots you know
	                  [^.?]*   #  any letter that arent a . or ?
	               )?          #we dont need an extension really

	              (            #capture a parameter string
	                  \?       #  it starts with a ?
	                  .*       #  and has any char following
	              )?           #but its optional too..
	              $            #and thats the end folks...
	            !x) {          #ignore comments and whitespace in rex
		print "$_\t".join(',',@parts)."\n"; # weve matched now print
	} else {
		print "NOMATCH:$_\n"; #oops, is this ok?
	}
} #lets try the next URL and see if we do better....
# :)