(.*) # what's between tags, even newline

##</code><code>##


#!/usr/bin/env perl5.10.0
use strict;
use warnings;
use re 'eval';
use Test::More qw(no_plan);
use 5.010;
use Data::Dumper;


my $xml;
my $nested_tags;

my $cdata = qr{ (?> 
	   [^<>&"]+     # any amount of "normal" text
	 | \&\w+;       # named chars
     | \&\#\d+;     # numbered codepoints
)}x;

$xml = qr{
    (?> (??{$nested_tags}) | $cdata)+
}x;

#$xml = qr/ $single_xml+/;


my $name = qr{
    (?>\w+(?: [:-]\w+)*)
}x;
my $attribute = qr{
    (?>$name="$cdata*+")
}x;

{
    $nested_tags = qr{
        (?<nested_tags>
        <   
            ($name) 
#            (?{print "after <$^N: \n"})
#            (?{print "match: [$&] (\$2:$2) \n"})
            (?>\s+$attribute)*\s*
            (?:
                /\s*>                # either an empty tag end ...
    
            | >                      # or end-of-tag and
            (?> (?&nested_tags) | $cdata)*+ # arbitrary XML
                </\s* (??{$2})\s*> # and a closing tag containing
                                    # the current name
            )
        )
    }x;
}


like   "foo bar baz",       qr/^$cdata$/, "cdata";
unlike "<bla>",             qr/^$cdata$/, "cdata";
like   'blerk="foo"',       qr/^$attribute$/, "simple attribute";
unlike 'blerk=bar',         qr/^$attribute$/, "non-quoted attribute";
like   '<bla />',           qr/^$nested_tags$/, "single, empty XML tag";
unlike '<bla>',             qr/^$nested_tags$/, "single, non-empty XML tag";
like '<bla></bla>',         qr/^$nested_tags$/, "single, closed XML tag";
like '<bla><blubb/></bla>', qr/^$nested_tags$/, "nested tags 1";
like '<bla>foo</bla>',      qr/^$nested_tags$/, "nested tags 2";
unlike '<bla><blubb></bla>',qr/^$nested_tags$/, "nested tags 3";
like '<bla><blubb></blubb></bla>',
                            qr/^$nested_tags$/, "nested tags 4";
like '<moep><blubb></blubb></moep><foo/><bar></bar>',
                            qr/^$xml+$/, 'multiple nested tags';
unlike '<bla><blubb></foo></bla>',
                            qr/^$xml+$/, "wrongly nested tags";
like '<bla>foo</bla>',      qr/^$xml+$/, "nested tags with cdata";
like '<bla foo="bar" />',   qr/^$nested_tags$/, 'Tag with attribute';
like '<bla>foo &auml;blubb</bla>',
                            qr/^$nested_tags$/, 'Tags with named entities';
unlike '<bla>foo &aumlblubb</bla>',
                            qr/^$nested_tags$/, 'Tags with malformed named entities';

#print Dumper \@names;