function __construct( $importdata, $dataformat ) {
global $rdfiogExtraNSPrefixes,
$rdfiogPropertiesToUseAsWikiTitle,
$rdfiogUseNSPrefixInWikiTitleForProperties,
$rdfiogUseNSPrefixInWikiTitleForEntities;
if ( $dataformat == 'triples_array' ) {
$this->m_triples = $importdata;
} else {
$this->m_unparseddata = $importdata;
}
$this->m_dataformat = $dataformat;
$this->m_haserrors = false;
$this->m_delete = false;
if ( $this->m_dataformat == 'rdfxml' ) {
$this->m_unparseddata = $this->cleanupXML( $this->m_unparseddata );
$this->m_parser = ARC2::getRDFXMLParser();
$this->parse();
} elseif ( $this->m_dataformat == 'turtle' ) {
$this->m_unparseddata = $wgRequest->getText( 'importdata' );
$this->m_parser = ARC2::getTurtleParser();
$this->parse();
}
$this->extractTripleIndex();
$this->m_nsprefixes = $this->getNSPrefixMappingFromParser();
if ( $rdfiogExtraNSPrefixes != '' ) {
$this->addNamespacePrefixes( $rdfiogExtraNSPrefixes );
}
$nsprefixes = $this->m_nsprefixes;
$this->setNSPrefixes( $nsprefixes );
$this->setTripleIndex( $this->m_tripleindex );
// Previously in Equiv URI Class
if ( isset($rdfiogUsePseudoNamespacesForProperties) ) { // TODO: Change to check options from import screen
// use parameter set in LocalSettings.php
$this->m_usenspintitles_properties = $rdfiogUsePseudoNamespacesForProperties;
}
if ( isset($rdfiogUsePseudoNamespacesForEntities) ) {
// use parameter set in LocalSettings.php
$this->m_usenspintitles_entities = $rdfiogUsePseudoNamespacesForEntities;
}
if ( !empty( $rdfiogPropertiesToUseAsWikiTitle ) ) {
$this->m_wikititlepropertyuris = $rdfiogPropertiesToUseAsWikiTitle;
} else {
$this->m_wikititlepropertyuris = array(
'http://semantic-mediawiki.org/swivt/1.0#page', // Suggestion for new property
'http://www.w3.org/2000/01/rdf-schema#label',
'http://purl.org/dc/elements/1.1/title',
'http://www.w3.org/2004/02/skos/core#preferredLabel',
'http://xmlns.com/foaf/0.1/name'
);
}
$this->m_store = new RDFIOStore();
}
function parse_to_simple_index($rdfxml)
{
$triples = array();
if (strlen($rdfxml) > 0) {
$parser = ARC2::getRDFXMLParser();
$parser->parse(null, $rdfxml);
$triples = $parser->getSimpleIndex(0);
}
return $triples;
}
/**
* @deprecated triple lists are deprecated
*/
function describe_to_triple_list($uri, $graphs = array())
{
$triples = array();
$response = $this->describe($uri, $graphs);
if ($response->body) {
$parser_args = array("bnode_prefix" => "genid", "base" => $this->uri);
$parser = ARC2::getRDFXMLParser($parser_args);
$parser->parse("", $response->body);
$triples = $parser->getTriples();
}
return $triples;
}
/**
* get_snapshots
*
* @return array
* @author Keith Alexander
**/
public function get_item_uris()
{
$parser = ARC2::getRDFXMLParser();
$parser->parse($this->uri);
$triples = $parser->getTriples();
$this->errors = $parser->getErrors();
$uris = array();
foreach ($triples as $t) {
if ($t['p'] == 'http://schemas.talis.com/2006/bigfoot/configuration#snapshot') {
$uris[] = $t['o'];
}
}
return $uris;
}
function test_put_to_network_includes_body()
{
$fake_request_factory = new FakeRequestFactory();
$fake_request = new FakeHttpRequest(new HttpResponse(200));
$fake_request_factory->register('PUT', "http://example.org/res", $fake_request);
$group = new NetworkResource("http://example.org/res");
$group->add_resource_triple("http://example.org/res", "http://example.org/pred", "http://example.org/obj");
$group->request_factory = $fake_request_factory;
$group->put_to_network();
$parser = ARC2::getRDFXMLParser(array("bnode_prefix" => "genid", "base" => 'http://example.org/'));
$parser->parse('http://example.org/', $fake_request->get_body());
$triples = $parser->getTriples();
$this->assertEquals(1, count($triples));
}
/**
* get_item_uris
*
* @return array
* @author Chris Clarke
**/
public function get_item_uris()
{
$request = $this->request_factory->make('GET', $this->uri, $this->credentials);
$request->set_accept("application/rdf+xml");
$response = $request->execute();
$parser = ARC2::getRDFXMLParser();
$parser->parse('', $response->body);
$triples = $parser->getTriples();
$this->errors = $parser->getErrors();
$uris = array();
foreach ($triples as $t) {
if ($t['p'] == 'http://schemas.talis.com/2006/bigfoot/configuration#snapshot') {
$uris[] = $t['o'];
}
}
return $uris;
}
/**
* Import RDF/XML, e.g. from the RDF Import Special Page.
* @param string $importData
*/
public function importRdfXml($importData)
{
// Parse RDF/XML to triples
$arc2rdfxmlparser = ARC2::getRDFXMLParser();
$arc2rdfxmlparser->parseData($importData);
// Receive the data
$triples = $arc2rdfxmlparser->triples;
$tripleIndex = $arc2rdfxmlparser->getSimpleIndex();
$namespaces = $arc2rdfxmlparser->nsp;
/* DEBUGGING
echo "*** Triples ***";
echo( print_r( $triples, true ));
echo "*** Triple index ***";
echo( print_r( $tripleIndex, true ));
echo "*** Namespaces ***";
echo( print_r( $namespaces, true ));
*/
$this->importFromArc2Data($triples, $tripleIndex, $namespaces);
return $output = array('triples' => $triples, 'tripleIndex' => $tripleIndex, 'namespaces' => $namespaces);
}
/**
* Extrahiert eingebettetes rdfa aus einer beliebigen HTML Seite und
* speichert es im triple store
* @param string $url
* @return Response Ein Responseobjekt
*/
function extractOAI($rdf, $url)
{
global $ep;
// Wenn es die URL im Graph schon gibt, nichts machen
if (graphContainsUrl($url)) {
$res = new Response(null, "URL {$url} already visited, skip indexing");
return $res;
} else {
$parser = ARC2::getRDFXMLParser();
$parser->parse($url, $rdf);
// triple Darstellung
$triples = $parser->getTriples();
// Wenn kein OAI gefunden wurde
if (count($triples) < 1) {
$res = new Response(null, "URL {$url} contains no OAI-RDF");
return $res;
}
// in Datenbank einfuegen
$ep->insert($triples, "");
$res = new Response(null, "URL {$url}: added " . count($triples) . " triples");
return $res;
}
}
function parseRDFXMLResultDoc($url, $type, &$reader)
{
$parser = ARC2::getRDFXMLParser();
$parser->setReader($reader);
$parser->parse($url);
if ($parser->getErrors()) {
$this->errors = $parser->errors;
# @@@ Could do with (improved) addError(s)?
return;
}
$this->result = $parser->getSimpleIndex(false);
}
private function OWL2RDF($abbv)
{
$filename = parent::getReadFile()->getFilename();
$buf = file_get_contents("compress.zlib://" . $filename);
$parser = ARC2::getRDFXMLParser('file://' . $filename);
$parser->parse("http://bio2rdf.org/bioportal#", $buf);
$triples = $parser->getTriples();
foreach ($triples as $i => $a) {
$this->TriplifyMap($a, strtolower($abbv));
parent::writeRDFBufferToWriteFile();
}
parent::clear();
}
/**
* As for addTurtle but load a string of RDF XML
*
* @see addTurtle
*/
function addRDFXML($base, $data)
{
$parser = ARC2::getRDFXMLParser($this->arc2config);
$parser->parse($base, $data);
$errors = $parser->getErrors();
$parser->resetErrors();
if (sizeof($errors)) {
if ($this->debug) {
print "<h3>Error loading RDFXML string</h3>";
print "<ul><li>" . join("</li><li>", $errors) . "</li></ul>";
}
return 0;
}
return $this->addTriples($parser->getTriples());
}
curl_setopt($ch, CURLOPT_URL, $u);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_MAXREDIRS, 10);
curl_setopt($ch, CURLOPT_HTTPHEADER, array("Accept: text/turtle, text/n3; q=0.9, application/turtle; q=0.8, application/n-triples; q=0.7, application/rdf+xml; q=0.6, application/json; q=0.4, */*; q=0.1"));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$data = curl_exec($ch);
$_aux = curl_getinfo($ch, CURLINFO_CONTENT_TYPE);
$_aux2 = explode(";", $_aux);
$content_type = array_shift($_aux2);
curl_close($ch);
$parser = NULL;
$parsers = array();
$parsers[0]['formats'] = array('text/n3', 'application/x-turtle', 'application/turtle', 'text/turtle');
$parsers[0]['parser'] = ARC2::getTurtleParser();
$parsers[1]['formats'] = array('application/rdf+xml');
$parsers[1]['parser'] = ARC2::getRDFXMLParser();
$parsers[2]['formats'] = array('application/json', 'application/x-javascript', 'text/javascript', 'text/x-javascript', 'text/x-json');
$parsers[2]['parser'] = ARC2::getJSONParser();
foreach ($parsers as $v) {
if (in_array($content_type, $v['formats'])) {
$parser = $v['parser'];
}
}
//If nothing fits, pray to your favorite god that this can be detected and parsed correctly by ARC2.
$parser = ARC2::getRDFParser();
//end of workaround
$parser->parse($u, $data);
//Since IDK which namespace the documents contains, lets use the uri requested
$triples = $parser->getTriples();
$first = true;
$c = 0;
/**
* Parse RDF, either from a string or a URL
*/
public function parse($url)
{
$parser = @ARC2::getRDFXMLParser();
if (stristr($url, '<rdf')) {
$parser->parse(confirm_slash(base_url()), $url);
// Parse an existing string
} else {
@$parser->parse($url);
// Go out and get via the URL
}
$index = $parser->getSimpleIndex(0);
return $index;
}
/**
* Add the triples parsed from the supplied RDF/XML to the graph
* @param string $rdfxml the RDF/XML to parse
* @param string $base the base URI against which relative URIs in the RDF/XML document will be resolved
*/
public function add_rdfxml($rdfxml, $base = '')
{
if ($rdfxml) {
/** @var \ARC2_RDFXMLParser $parser */
$parser = \ARC2::getRDFXMLParser();
$parser->parse($base, $rdfxml);
$this->_add_arc2_triple_list($parser->getTriples());
unset($parser);
}
}
/**
* Parse the results of a search on the contentbox.
* @param string uri the URI used to obtain the search
* @param string xml the xml returned from a search request
* @return ResourceList
*/
function parse_results_xml($uri, $xml)
{
// fix up unprefixed rdf:resource in rss 1.0 otherwise ARC gets confused
$xml = preg_replace("~rdf:li resource=~", "rdf:li rdf:resource=", $xml);
$parser_args = array("bnode_prefix" => "genid", "base" => $this->uri);
$resources = new ResourceList();
$resources->items = array();
$parser = ARC2::getRDFXMLParser($parser_args);
$parser->parse($this->uri, $xml);
$triples = $parser->getTriples();
$index = ARC2::getSimpleIndex($triples, true);
$resources->title = $index[$uri][RSS_TITLE][0];
$resources->description = $index[$uri][RSS_DESCRIPTION][0];
$resources->start_index = $index[$uri][OS_STARTINDEX][0];
$resources->items_per_page = $index[$uri][OS_ITEMSPERPAGE][0];
$resources->total_results = $index[$uri][OS_TOTALRESULTS][0];
$items_resource = $index[$uri][RSS_ITEMS][0];
foreach ($index[$items_resource] as $items_property => $items_property_value) {
if (strpos($items_property, 'http://www.w3.org/1999/02/22-rdf-syntax-ns#_') === 0) {
$resources->items[] = $index[$items_property_value[0]];
}
}
return $resources;
}
static function insertRDF($uri, $graph, $endpoint)
{
self::deleteTriples($uri, $graph, $endpoint);
//READ NEW TRIPLES WITH THE SUBJECT $uri
$parser = @ARC2::getRDFXMLParser();
@$parser->parse($uri);
$err = $parser->getErrors();
if ($err) {
throw new Exception(self::buildMessage($err));
}
$newTriples = @$parser->getTriples();
for ($i = 0, $i_max = count($newTriples); $i < $i_max; $i++) {
if ($uri != $newTriples[$i]['s']) {
unset($newTriples[$i]);
}
}
/* Serializer instantiation */
$ser = @new FourStore_NTriplesSerializer();
/* Serialize a triples array */
$doc = @$ser->getSerializedTriples($newTriples, 1);
self::insert($doc, $graph, $endpoint);
}
/**
* Add the triples parsed from the supplied RDF/XML to the graph
* @param string rdfxml the RDF/XML to parse
* @param string base the base URI against which relative URIs in the RDF/XML document will be resolved
*/
function add_rdfxml($rdfxml, $base = '')
{
if ($rdfxml) {
$parser = ARC2::getRDFXMLParser();
$parser->parse($base, $rdfxml);
$this->_add_arc2_triple_list($parser->getTriples());
unset($parser);
}
}
function test_schedule_restore_posts_rdfxml_with_a_snapshot_uri()
{
$fake_request_factory = new FakeRequestFactory();
$fake_request = new FakeHttpRequest(new HttpResponse());
$fake_request_factory->register('POST', "http://example.org/store/jobs", $fake_request);
$queue = new JobQueue("http://example.org/store/jobs");
$queue->request_factory = $fake_request_factory;
$response = $queue->schedule_restore('http://example.org/snapshot');
$parser = ARC2::getRDFXMLParser(array("bnode_prefix" => "genid", "base" => 'http://example.org/'));
$parser->parse('http://example.org/', $fake_request->get_body());
$triples = $parser->getTriples();
$found_triple = false;
foreach ($triples as $triple) {
if ($triple['p'] == 'http://schemas.talis.com/2006/bigfoot/configuration#snapshotUri' && $triple['o_type'] == 'uri' && $triple['o'] == 'http://example.org/snapshot') {
$found_triple = true;
break;
}
}
$this->assertTrue($found_triple);
}
function parse($base, $rdfxml)
{
$parser = ARC2::getRDFXMLParser();
$parser->parse($base, $rdfxml);
return $parser->getTriples();
}
public function load($uri, $aliases = array(), $map = array())
{
$this->forceString($uri);
$uri = $this->expandURI($uri);
if (substr($uri, 0, 5) == "data:") {
$data = urldecode(preg_replace("/^data:[^,]*,/", "", $uri));
$parser = ARC2::getTurtleParser();
$parser->parse($uri, $data);
} else {
if (isset($this->loaded[$uri])) {
return $this->loaded[$uri];
}
if (isset($this->cacheDir)) {
$filename = $this->cacheDir . "/" . md5($uri);
if (!file_exists($filename) || filemtime($filename) + $this->cacheAge < time()) {
# decache if out of date, even if we fail to re cache.
if (file_exists($filename)) {
unlink($filename);
}
$url = $uri;
$ttl = 16;
$mime = "";
$old_user_agent = ini_get('user_agent');
ini_set('user_agent', "PHP\r\nAccept: application/rdf+xml");
while ($ttl > 0) {
# dirty hack to set the accept header without using curl
if (!($rdf_fp = fopen($url, 'r'))) {
break;
}
$meta_data = stream_get_meta_data($rdf_fp);
$redir = 0;
foreach ($meta_data['wrapper_data'] as $response) {
if (substr(strtolower($response), 0, 10) == 'location: ') {
$newurl = substr($response, 10);
if (substr($newurl, 0, 1) == "/") {
$parts = preg_split("/\\//", $url);
$newurl = $parts[0] . "//" . $parts[2] . $newurl;
}
$url = $newurl;
$redir = 1;
}
if (substr(strtolower($response), 0, 14) == 'content-type: ') {
$mime = preg_replace("/\\s*;.*\$/", "", substr($response, 14));
}
}
if (!$redir) {
break;
}
$ttl--;
fclose($rdf_fp);
}
ini_set('user_agent', $old_user_agent);
if ($ttl > 0 && $mime == "application/rdf+xml" && $rdf_fp) {
# candidate for caching!
if (!($cache_fp = fopen($filename, 'w'))) {
echo "Cannot write file ({$filename})";
exit;
}
while (!feof($rdf_fp)) {
fwrite($cache_fp, fread($rdf_fp, 8192));
}
fclose($cache_fp);
}
fclose($rdf_fp);
}
}
if (isset($filename) && file_exists($filename)) {
$parser = ARC2::getRDFXMLParser();
$parser->parse($filename);
} else {
$parser = ARC2::getRDFParser();
# Don't try to load the same URI twice!
if (!isset($this->firstGraphURI)) {
$this->firstGraphURI = $uri;
}
$parser->parse($uri);
}
}
$errors = $parser->getErrors();
$parser->resetErrors();
if (sizeof($errors)) {
if ($this->debug) {
print "<h3>Error loading: {$uri}</h3>";
print "<ul><li>" . join("</li><li>", $errors) . "</li></ul>";
}
return 0;
}
$triples = $parser->getTriples();
foreach ($triples as $t) {
$t["s"] = $this->cleanURI($t["s"]);
if (!isset($map[$t["s"]])) {
continue;
}
$t["p"] = $this->cleanURI($t["p"]);
if ($t["p"] != "http://www.w3.org/2002/07/owl#sameAs") {
continue;
}
$aliases[$t["o"]] = $t["s"];
}
foreach ($triples as $t) {
$t["s"] = $this->cleanURI($t["s"]);
$t["p"] = $this->cleanURI($t["p"]);
/*
if( $t["o_type"]=="literal" )
{
$t["o_dataype"] = $this->cleanURI($t["o_datatype"]);
$this->t["sp"][$t["s"]][$t["p"]][] = array(
"v"=>$t["o"],
"d"=>$t["o_datatype"],
"l"=>$t["o_lang"] );
}
else
{
$t["o"] = $this->cleanURI($t["o"]);
$this->t["sp"][$t["s"]][$t["p"]][] = $t["o"];
}
$this->t["op"][$t["o"]][$t["p"]][] = $t["s"];
if( $alias )
{
*/
$mod = 0;
if (isset($aliases[$t["s"]])) {
$t["s"] = $aliases[$t["s"]];
}
if (isset($aliases[$t["p"]])) {
$t["p"] = $aliases[$t["p"]];
}
if (isset($aliases[$t["o"]])) {
$t["o"] = $aliases[$t["o"]];
}
// if( $mod )
// {
if ($t["o_type"] == "literal") {
$this->t["sp"][$t["s"]][$t["p"]][] = array("v" => $t["o"], "d" => $t["o_datatype"], "l" => $t["o_lang"]);
} else {
$this->t["sp"][$t["s"]][$t["p"]][] = $t["o"];
}
$this->t["op"][$t["o"]][$t["p"]][] = $t["s"];
// }
// }
}
$this->loaded[$uri] = sizeof($triples);
return $this->loaded[$uri];
}
/**
* Get an array of property URIs from the specified ontology,
* to function as a filter
* @return array $vocab_p_uri_filter
*/
function getVocabPropertyUriFilter() {
$vocaburl = $this->m_filtervocaburl;
$RDFXMLParser = ARC2::getRDFXMLParser();
$RDFXMLParser->parse( $vocaburl );
$vocabtriples = $RDFXMLParser->getTriples();
$vocab_p_uri_filter = array();
foreach ( $vocabtriples as $vocabtriple ) {
$p = $vocabtriple['p'];
$o = $vocabtriple['o'];
// For OWL vocabularies:
if ( $p === 'http://www.w3.org/1999/02/22-rdf-syntax-ns#type' &&
$o === 'http://www.w3.org/2002/07/owl#ObjectProperty' ) {
$vocab_p_uri = $vocabtriple['s'];
$vocab_p_uri_filter[] = $vocab_p_uri;
}
}
return $vocab_p_uri_filter;
}
function test_create_store_posts_rdfxml_with_a_single_store_template()
{
$fake_request_factory = new FakeRequestFactory();
$fake_request = new FakeHttpRequest(new HttpResponse());
$fake_request_factory->register('POST', "http://example.org/stores", $fake_request);
$coll = new StoreCollection("http://example.org/stores");
$coll->request_factory = $fake_request_factory;
$response = $coll->create_store("scooby", "http://example.org/template");
$parser = ARC2::getRDFXMLParser(array("bnode_prefix" => "genid", "base" => 'http://example.org/'));
$parser->parse('http://example.org/', $fake_request->get_body());
$triples = $parser->getTriples();
$values = array();
foreach ($triples as $triple) {
if ($triple['p'] == 'http://schemas.talis.com/2006/bigfoot/configuration#storeTemplate') {
$values[] = $triple['o_type'];
}
}
$this->assertEquals(1, count($values));
}
$q = "\r\nPREFIX dbpedia-owl-musicgenre: <http://dbpedia.org/ontology/MusicGenre/>\r\nPREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\r\nSELECT DISTINCT ?genre ?genreuri\r\nWHERE\r\n { <{$uri}> dbpedia-owl-musicgenre:stylisticOrigin ?genreuri .\r\n ?genreuri rdfs:label ?genre . \r\n FILTER ( langMatches(lang(?genre), \"EN\") ) }\r\n";
$stylisticOrigins = $dbpedia->query($q, 'rows');
$q = "\r\nPREFIX dbpedia-owl-musicgenre: <http://dbpedia.org/ontology/MusicGenre/>\r\nPREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\r\nSELECT DISTINCT ?genre ?genreuri\r\nWHERE\r\n { ?genreuri dbpedia-owl-musicgenre:musicSubgenre <{$uri}> ;\r\n rdfs:label ?genre . \r\n FILTER ( langMatches(lang(?genre), \"EN\") ) }\r\n";
$parentGenres = $dbpedia->query($q, 'rows');
$q = "\r\nPREFIX dbpedia-owl-musicgenre: <http://dbpedia.org/ontology/MusicGenre/>\r\nPREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\r\nSELECT DISTINCT ?genre ?genreuri\r\nWHERE\r\n { ?genreuri dbpedia-owl-musicgenre:stylisticOrigin <{$uri}> ;\r\n rdfs:label ?genre . \r\n FILTER ( langMatches(lang(?genre), \"EN\") ) }\r\n";
$stylisticChildren = $dbpedia->query($q, 'rows');
/* Now, we finally grab artists. */
$q = "\r\nPREFIX dbpedia-owl-artist: <http://dbpedia.org/ontology/Artist/>\r\nPREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\r\nPREFIX dbpprop: <http://dbpedia.org/property/>\r\nSELECT DISTINCT ?artist ?artisturi ?yearsActive\r\nWHERE\r\n { ?artisturi dbpedia-owl-artist:genre <{$uri}> ;\r\n rdfs:label ?artist .\r\n OPTIONAL { ?artisturi dbpprop:yearsActive ?yearsActive . }\r\n FILTER ( langMatches(lang(?artist), \"EN\") ) }\r\n\r\n";
$artists = $dbpedia->query($q, 'rows');
/* But we need to do some legwork to get the number of albums, since
we don't have a sameAs link back to DBTune. We use sameAs.org to go
backwards. */
$newArtists = array();
foreach ($artists as $key => $artist) {
$sameAsURI = "http://sameas.org/rdf?uri=" . urlencode($artist['artisturi']);
$parser = ARC2::getRDFXMLParser();
$parser->parse($sameAsURI);
$triples = $parser->getTriples();
$dbturi = '';
foreach ($triples as $triple) {
if (substr($triple['o'], 0, 46) == 'http://dbtune.org/musicbrainz/resource/artist/') {
$dbturi = $triple['o'];
break;
}
}
$newArtists[$key] = $artist;
$newArtists[$key]['artisturi'] = $dbturi;
print_r($newArtists[$key]);
if ($dbturi != '') {
/* Now that we have the DBTune URI, we can query it for the number
of albums. */
