#!/usr/bin/perl #-*-perl-*- # use strict; use FindBin; use lib $FindBin::Bin.'/../lib'; use Lingua::Align::Corpus::Parallel; use Lingua::Align::Corpus::Parallel; my $infile = shift(@ARGV); my $informat = shift(@ARGV); my $outformat = shift(@ARGV); my $corpus = new Lingua::Align::Corpus::Parallel(-file => $infile, -type => $informat); my $output = new Lingua::Align::Corpus::Parallel(-type => $outformat, -skip_node_ids => 1); my %src=(); my %trg=(); my $links={}; my %sent=(); print $output->print_header(); while ($corpus->next_alignment(\%src,\%trg,\$links)){ print $output->print_alignments(\%src,\%trg,$links); # print "\n"; } print $output->print_tail(); __END__ =head1 NAME convert_bitext - a script for converting bitexts =head1 SYNOPSIS convert_bitext input-file input-format output-format =head1 DESCRIPTION Convert bitexts from one format to another. There are several formats supported by Lingua::Align. Check L<Lingua::Align::Corpus>, L<Lingua::Align::Corpus::Treebank> for more information. =head1 AUTHOR Joerg Tiedemann =head1 COPYRIGHT AND LICENSE Copyright (C) 2009 by Joerg Tiedemann This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.8.8 or, at your option, any later version of Perl 5 you may have available. =cut