use 5.014;
use strictures;
use Lucy;

my $index = "./lucy.index";
my $schema = Lucy::Plan::Schema->new;
my $easyanalyzer = Lucy::Analysis::EasyAnalyzer
    ->new( language => 'en' );
my $text_type = Lucy::Plan::FullTextType
    ->new( analyzer => $easyanalyzer, );
my $string_type = Lucy::Plan::StringType->new();

$schema->spec_field( name => 'id',   type => $string_type );
$schema->spec_field( name => 'content', type => $text_type );

open my $db, "<", "/tmp/PM.db" or die $!;

my $indexer = get_indexer();
my $counter = 1;
while (<$db>)
{
    chomp;
    my ( $id, $text ) = split /;/, $_, 2;
    $indexer->add_doc({ id => $id,
                        content => $text });

    unless ( $counter++ % 100_000 )
    {
        print "committing a batch...\n";
        $indexer->commit;
        $indexer = get_indexer();
    }
}
print "optimizing and committing...\n";
$indexer->optimize;
$indexer->commit;

sub get_indexer {
    Lucy::Index::Indexer
        ->new( schema => $schema,
               index  => $index,
               create => 1 );
}