
Parse::MediaWikiDump::Links - Object capable of processing link dump files

This object is used to access content of the SQL based category dump files by providing an iterative interface for extracting the indidivual article links to the same. Objects returned are an instance of Parse::MediaWikiDump::link.

$pmwd = Parse::MediaWikiDump->new;
$links = $pmwd->links('pagelinks.sql');
$links = $pmwd->links(\*FILEHANDLE);
#print the links between articles
while(defined($link = $links->next)) {
print 'from ', $link->from, ' to ', $link->namespace, ':', $link->to, "\n";
}

Create a new instance of a page links dump file parser
Return the next available Parse::MediaWikiDump::link object or undef if there is no more data left

#!/usr/bin/perl
use strict;
use warnings;
use Parse::MediaWikiDump;
my $pmwd = Parse::MediaWikiDump->new;
my $links = $pmwd->links(shift) or die "must specify a pagelinks dump file";
my $dump = $pmwd->pages(shift) or die "must specify an article dump file";
my %id_to_namespace;
my %id_to_pagename;
binmode(STDOUT, ':utf8');
#build a map between namespace ids to namespace names
foreach (@{$dump->namespaces}) {
my $id = $_->[0];
my $name = $_->[1];
$id_to_namespace{$id} = $name;
}
#build a map between article ids and article titles
while(my $page = $dump->next) {
my $id = $page->id;
my $title = $page->title;
$id_to_pagename{$id} = $title;
}
$dump = undef; #cleanup since we don't need it anymore
while(my $link = $links->next) {
my $namespace = $link->namespace;
my $from = $link->from;
my $to = $link->to;
my $namespace_name = $id_to_namespace{$namespace};
my $fully_qualified;
my $from_name = $id_to_pagename{$from};
if ($namespace_name eq '') {
#default namespace
$fully_qualified = $to;
} else {
$fully_qualified = "$namespace_name:$to";
}
print "Article \"$from_name\" links to \"$fully_qualified\"\n";
}