#!/usr/bin/perl -w
use v5.14;
use strict;
use warnings;
die "please provide a database name" unless $ARGV[0];
my $rootname = $ARGV[0] =~ s/\.xml\.bz2\E//r =~ s,.*/,,r;

use Encode;
use XML::Parser;
use IO::Uncompress::Bunzip2;
use IO::Compress::Bzip2 qw(bzip2 $Bzip2Error);

use Digest::MD5 qw(md5);
use Storable qw(freeze thaw);
open my $db, "> $rootname.db";
END { close $db }

open my $t, "> $rootname.titles";
END { close $t }

my ($title, @block, $char);

my %debug;

use DB_File;
tie my %index, 'DB_File', "$rootname.index";
END { untie %index }

$SIG{INT} = sub { die "caught INT signal" };
END { printf "%d entries made\n", scalar keys %index }

sub store {
    my $freeze = freeze shift;
    bzip2 \($freeze, my $z);
    my $start = tell $db;
    print $db pack('L', length $z), $z;
    printf "block %d -> %d, compressed ratio is %2.2f%%\n",
    $start, tell($db), 100*length($z)/length($freeze),
    ;
}

my $parser = new XML::Parser Handlers => {
    Char => sub { shift; $char .= shift },
    Start => sub { undef $char },
    End => sub {
	shift;
	given( $_[0] ) {
	    when( 'title' ) { $title = encode 'utf8', $char; say $t $title }
	    when( 'text' )  {
		push @block, $char;
		$index{length($title) > 16 ? md5 $title : $title} =
		    pack 'LC', tell($db), scalar(@block) - 1;
		if (@block == 256) {
		    store \@block;
		    undef @block;
		}
	    }
	}
    },
};

$parser->parse( new IO::Uncompress::Bunzip2 $ARGV[0] );
END { store \@block if @block }