note
Samy_rio
<p>Hi [Anonymous Monk], try like this using Regular Expression,</p>
<code>
use strict;
use warnings;
my $input = do{local $/; <DATA>};
$input =~ s/(<(h\d+>)[^\n]+)/$1<\/$2/gsi;
$input =~ s/(<h(\d+)[^>]*>)(.*?)(?=(<h(\d+)[^>]*>))/"$1".§ion_close($2,$3,$5)/egsi;
$input =~ s/(<(h\d+>)){2,}/$1/gsi;
######Last level
if ($input =~/<h./si)
{
if ($input =~/(<h\d+[^>]*>)(.*)(<h(\d+)[^>]*>)(.*)$/si)
{
$input =~s/(<h\d+[^>]*>)(.*)(<h(\d+)[^>]*>)(.*)$/"$1$2$3".§ion_close($4,$5,1)/egsi;
}
else
{
$input =~s/(.*)(<h(\d+)[^>]*>)(.*)$/"$1$2".§ion_close($3,$4,1)/egsi;
}
}
############Heading replacement
$input =~ s/(<h(\d+)>)((?:(?!<\/h\2>).)*)<\/h\2>/$1<head>$3<\/head>/gsi;
$input =~ s/(<\/?)h(\d+>)/$1section$2/gsi;
print $input;
sub section_close
{
my ($csect_no,$aft_txt,$asect_no)=@_;
my $tag_close;
if ($csect_no == $asect_no)
{
$tag_close="$aft_txt<\/h$csect_no>\n"
}
if ($csect_no < $asect_no)
{
my $j = $asect_no - $csect_no;
my $i = $csect_no;
my $temp = "";
while ($j > 1)
{
my $k = $i + 1;
$temp = $temp."<h$k>\n";
$i++;
$j--;
}
$tag_close = "<h$csect_no>".$aft_txt.$temp;
}
if ($csect_no > $asect_no) #head separation
{
my $temp = "";
my $i = $asect_no;
for ($i = $asect_no; $i <= $csect_no; $i++)
{
$temp = "<\/h$i>\n".$temp;
}
$tag_close = $aft_txt.$temp;
}
return $tag_close;
}
__DATA__
<h1>Heading level 1
<h2>Heading level 2
<h3>Heading level 3
<h2>Heading level 2
<h1>Heading level 1
paragraph here
paragraph here
Output:
-------
<section1><head>Heading level 1</head>
<section2><head>Heading level 2</head>
<section3><head>Heading level 3</head>
</section3>
</section2>
<section2><head>Heading level 2</head>
</section2>
</section1>
<section1><head>Heading level 1</head>
paragraph here
paragraph here
</section1>
</code>
<!-- Node text goes above. Div tags should contain sig only -->
<div class="pmsig"><div class="pmsig-460657">
<p>Regards,<br>Velusamy R.<hr><c>eval"print uc\"\\c$_\""for split'','j)@,/6%@0%2,`e@3!-9v2)/@|6%,53!-9@2~j';</c></p>
</div></div>
604767
604767