#!/usr/bin/perl -w

use strict;

use Algorithm::Diff qw(diff LCS);
use HTML::TokeParser;
use LWP::Simple;

sub tokenize_url
{
    my $url = shift;

    my $content = get $url or die $!;

    my $p = new HTML::TokeParser(\$content);

    my (@tokens, $token);

    push @tokens, $token
        while (defined ($token = $p->get_token));

    \@tokens;
}

my @content = map { tokenize_url($_) } qw{
http://perlmonks.org/index.pl?node_id=32285
http://perlmonks.org/index.pl?node_id=32286
};

# hash tokens based on their text content
sub hash_token {$_[0][$_[0][0] eq 'T' ? 1 : -1]}

my @diffs = diff $content[0], $content[1], \&hash_token;
my @LCS = LCS $content[0], $content[1], \&hash_token;

my $largest = 0;

for my $hunk (@diffs)
{
    my (@deletions, @additions);

    for (@$hunk)
    {
        push @deletions, $_ if $_->[0] eq '-';
        push @additions, $_ if $_->[0] eq '+';
    }

    my $size = @deletions > @additions ? @deletions : @additions;

    $largest = $size if $size > $largest;
}

print scalar(@{$content[0]}), " line",
    (@{$content[0]} == 1 ? '' : 's'), " in original", $/;
print scalar(@{$content[1]}), " line",
    (@{$content[1]} == 1 ? '' : 's'), " in revision", $/;

print scalar(@diffs), " hunk", (@diffs == 1 ? '' : 's'),
    " differ", $/;
print $largest, " line", ($largest == 1 ? '' : 's'),
    " in largest hunk", $/;

printf "Revision %0.2f%% similar to original$/",
    100 * @LCS / @{$content[0]};
[download]

updated 2001-Aug-01: small code changes; renamed from "RE: Re: HTML Document Comparison"