Gecko [ fernandoquevedodop.com ]

Name	Size	Permission
benchmark	583 B	-rw-r--r--
dump_index	1.4 KB	-rw-r--r--
transform-fdt	1.12 KB	-rw-r--r--

Code Editor : dump_index

#!/usr/bin/perl

=head1 NAME

dump_index - dump the contents of an index

=head1 SYNOPSIS

perl -w dump_index $DIR

=head1 DESCRIPTION

This will dump out an index in human readable form. It can be used when 
debugging to compare indexes create with Plucene to those created with
Lucene.
	
=cut

use strict;
use warnings;

use Plucene::Index::Reader;

my $where = shift @ARGV;
my $r     = Plucene::Index::Reader->open($where);

no strict 'refs';
my @readers = (@{ $r->{readers} } ? @{ $r->{readers} } : $r);
print "We have " . @readers . " readers\n";
if (@readers == 1 and $r->isa("Plucene::Index::SegmentsReader")) {
	die "But no segments\n";
}

print "\n\nDocuments:\n";
for my $reader (@readers) {
	print "Segment "
		. $reader->{segment} . " has "
		. $reader->max_doc
		. " docs\n";
	my @terms = $reader->terms;
	print "Fields:\n";
	for my $field ($reader->field_infos->fields) {
		print "\t" . $field->number . ": " . $field->name;
		print " [indexed]" if $field->is_indexed;
		print "\n";
	}
	print "Terms: \n";
	my $td = $reader->term_docs;
	for my $t (@terms) {
		while ($t->next) {
			my $term = $t->term;
			print $term->field . ": " . $term->text . "\n";
			$td->seek($term);
			my ($docs, $freqs) = $td->read;
			for (0 .. $#$docs) {
				print "\t Doc "
					. $docs->[$_] . " ("
					. $freqs->[$_]
					. " occurrences)\n";
			}
		}
	}

}
print "Total documents: " . $r->max_doc . " in " . @readers . " segments\n";

${this.title}

Code Editor : dump_index