#!/usr/bin/perl
use warnings;
use strict;
use feature qw{ say };

use HTML::Parser;
use WWW::Mechanize;

my ($date,$first_page,$last_page,@toc);
sub get_date {
    my ($self, $tag, $attr) = @_;
    if ('span' eq $tag
        and $attr->{class}
        and 'highwire-cite-metadata-date' eq $attr->{class}
        and not defined $date
       ) {
        $self->handler(text => \&next_text_to_date, 'self, text');

    } elsif ('span' eq $tag
             and $attr->{class}
             and 'highwire-cite-metadata-pages' eq $attr->{class}
            ) {
        if (not defined $first_page) {
            $self->handler(text => \&parse_first_page, 'self, text');
        } else {
            $self->handler(text => \&parse_last_page, 'self, text');
        }

    } elsif ('span' eq $tag
             and $attr->{class}
             and 'highwire-cite-metadata-doi' eq $attr->{class}
            ) {
        $self->handler(text => \&retrieve_doi, 'self, text');

    } elsif ('div' eq $tag
             and $attr->{class}
             and $attr->{class} =~ /\bissue-toc-section\b/
            ) {
        $self->handler(text => \&next_text_to_toc, 'self, text');
    }
}


sub next_text_to_date {
    my ($self, $text) = @_;
    $text =~ s/^\s+|\s+$//g;
    $date = $text;
    $self->handler(text => undef);
}


sub parse_first_page {
    my ($self, $text) = @_;
    if ($text =~ /([A-Z0-9]+)(?:-[0-9A-Z]+)?/) {
        $first_page = $1;
        $self->handler(text => undef);
    }
}


sub parse_last_page {
    my ($self, $text) = @_;
    if ($text =~ /(?:[A-Z0-9]+-)?([0-9A-Z]+)/) {
        $last_page = $1;
        $self->handler(text => undef);
    }
}


sub next_text_to_toc {
    my ($self, $text) = @_;
    push @toc, [$text];
    $self->handler(text => undef);
}


sub retrieve_doi {
    my ($self, $text) = @_;
    if ('DOI:' ne $text) {
        $text =~ s/^\s+|\s+$//g;
        push @{ $toc[-1] }, $text;
        $self->handler(text => undef);
    }
}


print STDERR 'Enter the URL: ';
chomp(my $url = <>);
my ($volume, $issue) = (split m(/), $url)[-2, -1];

my $p = 'HTML::Parser'->new( api_version => 3,
                             start_h => [ \&get_date, 'self, tagname, attr' ],
                           );

my $mech = 'WWW::Mechanize'->new(agent => 'Mozilla');
$mech->get($url);
my $contents = $mech->content;
$p->parse($contents);
$p->eof;

my $toc;
for my $section (@toc) {
    $toc .= "<TocSection>\n";
    $toc .= "<Heading>".shift(@$section)."</Heading>\n";
    $toc .= join q(), map "<DOI>$_</DOI>\n", @$section;
    $toc .= "</TocSection>\n";
}

open (F6, ">meta_issue_$issue.xml");

	 
print F6 <<"__HTML__";
<!DOCTYPE MetaIssue SYSTEM "http://schema.highwire.org/public/toc/MetaIssue.pubids.dtd">
<MetaIssue volume="$volume" issue="$issue">
<Provider>Cadmus</Provider>
<IssueDate>$date</IssueDate>
<PageRange>$first_page-$last_page</PageRange>
<TOC>$toc</TOC>
</MetaIssue>
__HTML__