#!/usr/bin/perl

use warnings;
use strict;

use XML::Compile::Schema ();
use XML::Compile::Util   qw/type_of_node/;
use Getopt::Long         qw/GetOptions :config gnu_compat bundling/;
use YAML                 qw/Dump/;

my ($xml_input, $root_type, @schemas, $bigints, $bigfloats, $yaml_out);

GetOptions
   "bigints|bi|b!" => \$bigints
 , "bigfloats|bf"  => \$bigfloats
 , "output|o=s"    => \$yaml_out
 , "schema|s=s"    => \@schemas
 , "type|t=s"      => \$root_type
 , "xml|x=s"       => \$xml_input
   or exit 1;

$xml_input = '-' if @schemas && !defined $xml_input;
$yaml_out  = '-' unless defined $yaml_out;

if(@ARGV)
{   die "ERROR: either use options or no options, not mixed\n"
        if defined $xml_input && @ARGV;
    ($xml_input, @schemas) = @ARGV;
}

defined $xml_input
    or die "ERROR: no input message specified\n";

@schemas
    or die "ERROR: no schema's specified\n";

@schemas   = map { split /\,/ } @schemas;

my $parser = XML::LibXML->new;

my $msg    = $xml_input eq '-'
           ? $parser->parse_fh(\*STDIN)
           : $parser->parse_file($xml_input);

my $top = $msg->documentElement;
$root_type ||= type_of_node $top;

my $schema = XML::Compile::Schema->new( \@schemas );

my $read = $schema->compile
  ( READER => $root_type
  , sloppy_integers => !$bigints
  , sloppy_floats   => !$bigfloats
  );

my $data = Dump $read->($top);

if($yaml_out eq '-')
{   print $data;
}
else
{   open OUT, ">:utf8", $yaml_out
        or die "ERROR: cannot write yaml to $yaml_out: $!\n";

    print OUT $data;
    close OUT
        or die "ERROR: write error for $yaml_out: $!\n";
}

exit 0;

__END__

=head1 NAME

xml2yaml - convert an XML message with a schema into YAML

=head1 SYNOPSIS

 xml2yaml xml-file schema-file(s)  >yaml-file

 xml2yaml -x xml-file -s schema-files -o yaml-file

=head1 DESCRIPTION

Convert an XML message into YAML with the same structure.  A schema
is required to enforce the correct syntax, especially for optionally
repeated elements.

=head2 Options

You can either specify an XML message filename and one or more
schema filenames as arguments, or use the options.

=over 4

=item --xml|-x filename

The file which contains the xml message.  A single dash means "stdin".

=item --schema|-s filename(s)

This option can be repeated, or the filenames separated by comma's, if
you have more than one schema file to parse.  All imported and included
schema components have to be provided explicitly.

=item --bigints|-b  (boolean)

By default, the translation is a little sloppy: Integer types are defined
to support at least 18 digits in XML.  However, this is usually unneccesary
large and unreadible in YAML.

=item --type|-t TYPE

The type of the root element, required if the XML is not namespaceo
qualified, although the schema is.  If not specified, the root element
is automatically inspected.

The TYPE notation is C<{namespace}localname>.  Be warned to use quoting
on the UNIX command-line, because curly braces have a special meaning
for the shell.

=item --output|-o filename

By default (or when the filename is a dash), the output is printed to stdout.

=back

=head1 SEE ALSO

This module is part of Perl's XML-Compile distribution.
Website: F<http://perl.overmeer.net/xml-compile/>

=head1 LICENSE

Copyrights 2008 by Slaven Rezic and Mark Overmeer. For other contributors
see ChangeLog.

This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.
See F<http://www.perl.com/perl/misc/Artistic.html>