#!/usr/bin/perl

use strict;
use XML::LibXML;
use Getopt::Long;
binmode STDOUT,":utf8";

my $Usage = "Usage:  $0 [-x] [-r] -p xpath_spec file.xml\n";
my %opt;
die $Usage unless ( GetOptions( \%opt, 'x', 'r', 'p=s' ) and
                    @ARGV == 1 and -f $ARGV[0] and $opt{p} =~ /\w/ );
my $xmlfile = shift;

my $xml = XML::LibXML->new;
my $doc;
if ( ! $opt{r} ) {
    $doc = $xml->parse_file( $xmlfile );
}
else {
    my $xmlstr = "<EXP_ROOT_$$>";
    $opt{p} = "/EXP_ROOT_$$" . $opt{p};
    {
        local $/;
        open( X, '<:utf8', $xmlfile ) or die "Unable to read $xmlfile: $!\n";
        $xmlstr .= <X>;
        close X;
    }
    $xmlstr .= "</EXP_ROOT_$$>";
    $doc = $xml->parse_string( $xmlstr );
}
my $pth = XML::LibXML::XPathContext->new( $doc );
for my $n ( $pth->findnodes( $opt{p} )) {
    if ( $opt{x} ) {
        print $n->toString, "\n";
    } else {
        print $n->textContent, "\n";
    }
}

=head1 NAME

exp -- extract XPath matches from XML data

=head1 SYNOPSIS

 exp [-r] [-x] -p xpath_spec file.xml

  -r : supply a root node for the xml stream
  -x : output the matching content as xml elements

=head1 DESCRIPTION

This program will print portions (if any) from an XML file that match
a given XPath specifier.  

=head1 AUTHOR

David Graff <graff@ldc.upenn.edu>

=cut