Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[4013] trunk/components-core
|
From: <lor...@us...> - 2013-07-01 19:05:53
|
Revision: 4013
http://sourceforge.net/p/dl-learner/code/4013
Author: lorenz_b
Date: 2013-07-01 19:05:50 +0000 (Mon, 01 Jul 2013)
Log Message:
-----------
Minor changes in SPARQL reasonr. Updated LUCENE libs for ISLE:
Modified Paths:
--------------
trunk/components-core/pom.xml
trunk/components-core/src/main/java/org/dllearner/algorithms/isle/EntityTextRetriever.java
trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneIndexer.java
trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneSearcher.java
trunk/components-core/src/main/java/org/dllearner/algorithms/pattern/OWLAxiomPatternFinder.java
trunk/components-core/src/main/java/org/dllearner/algorithms/properties/DisjointObjectPropertyAxiomLearner.java
trunk/components-core/src/main/java/org/dllearner/kb/repository/oxford/OxfordRepository.java
trunk/components-core/src/main/java/org/dllearner/kb/sparql/QueryEngineHTTP.java
trunk/components-core/src/main/java/org/dllearner/kb/sparql/simple/SparqlSimpleExtractor.java
trunk/components-core/src/main/java/org/dllearner/reasoning/SPARQLReasoner.java
Modified: trunk/components-core/pom.xml
===================================================================
--- trunk/components-core/pom.xml 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/pom.xml 2013-07-01 19:05:50 UTC (rev 4013)
@@ -215,6 +215,14 @@
<artifactId>lucene-core</artifactId>
</dependency>
<dependency>
+ <groupId>org.apache.lucene</groupId>
+ <artifactId>lucene-analyzers-common</artifactId>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.lucene</groupId>
+ <artifactId>lucene-queryparser</artifactId>
+ </dependency>
+ <dependency>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
</dependency>
@@ -272,7 +280,7 @@
<dependency>
<groupId>org.aksw.jena-sparql-api</groupId>
<artifactId>jena-sparql-api-core</artifactId>
- <version>2.10.0-4-SNAPSHOT</version>
+ <version>2.10.0-5-SNAPSHOT</version>
</dependency>
</dependencies>
<dependencyManagement>
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/isle/EntityTextRetriever.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/EntityTextRetriever.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/isle/EntityTextRetriever.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -43,6 +43,6 @@
* @param entity The entity to handle.
* @return A weighted set of strings. For a value x, we need to have 0 <= x <= 1.
*/
- public Map<String, Integer> getRelevantText(Entity entity);
+ public Map<String, Double> getRelevantText(Entity entity);
}
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneIndexer.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneIndexer.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneIndexer.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -25,8 +25,10 @@
import java.io.IOException;
import java.util.Date;
+import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
@@ -51,12 +53,12 @@
Date start = new Date();
try {
- IndexWriter writer = new IndexWriter( FSDirectory.open( INDEX ),
- new StandardAnalyzer( Version.LUCENE_CURRENT ), true, IndexWriter.MaxFieldLength.LIMITED );
+ Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_43);
+ IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_43, analyzer);
+ IndexWriter writer = new IndexWriter( FSDirectory.open( INDEX ), indexWriterConfig);
System.out.println( "Creating index ..." );
index( writer, docDir );
System.out.println( "Optimizing index ..." );
- writer.optimize();
writer.close();
Date end = new Date();
System.out.println( end.getTime() - start.getTime() + " total milliseconds" );
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneSearcher.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneSearcher.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/isle/LuceneSearcher.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -32,13 +32,14 @@
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
+import org.apache.lucene.index.AtomicReaderContext;
+import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
-import org.apache.lucene.queryParser.QueryParser;
+import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Scorer;
-import org.apache.lucene.search.Searcher;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
@@ -48,7 +49,7 @@
private String FIELD = "contents";
private IndexReader m_reader = null;
- private Searcher m_searcher = null;
+ private IndexSearcher m_searcher = null;
private Analyzer m_analyzer = null;
private QueryParser m_parser = null;
@@ -70,10 +71,10 @@
@SuppressWarnings("deprecation")
public LuceneSearcher() throws Exception {
- m_reader = IndexReader.open( FSDirectory.open( new File( INDEX ) ), true );
+ m_reader = DirectoryReader.open( FSDirectory.open( new File( INDEX ) ));
m_searcher = new IndexSearcher( m_reader );
- m_analyzer = new StandardAnalyzer( Version.LUCENE_CURRENT );
- m_parser = new QueryParser( Version.LUCENE_CURRENT, FIELD, m_analyzer );
+ m_analyzer = new StandardAnalyzer( Version.LUCENE_43);
+ m_parser = new QueryParser( Version.LUCENE_43, FIELD, m_analyzer );
}
public void close() throws Exception {
@@ -139,13 +140,13 @@
return true;
}
@Override
- public void setNextReader( IndexReader reader, int docBase ) throws IOException {
- this.docBase = docBase;
- }
- @Override
public void setScorer(Scorer scorer) throws IOException {
this.scorer = scorer;
}
+ @Override
+ public void setNextReader(AtomicReaderContext context) throws IOException {
+ this.docBase = context.docBase;
+ }
};
m_searcher.search( query, collector );
}
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/pattern/OWLAxiomPatternFinder.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/pattern/OWLAxiomPatternFinder.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/pattern/OWLAxiomPatternFinder.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -364,7 +364,7 @@
System.out.print(i++ + ": ");
URI uri = entry.getPhysicalURI();
// if(uri.toString().startsWith("http://rest.bioontology.org/bioportal/ontologies/download/42764")){
- if (!ontologyProcessed(uri)) {
+ if (!ontologyProcessed(uri)) {//if(entry.getOntologyShortName().equals("00698"))continue;
System.out.print("Loading \"" + entry.getOntologyShortName() + "\" from "+ uri);
try {
manager = OWLManager.createOWLOntologyManager();
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/properties/DisjointObjectPropertyAxiomLearner.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/properties/DisjointObjectPropertyAxiomLearner.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/properties/DisjointObjectPropertyAxiomLearner.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -116,7 +116,7 @@
//compute the overlap if exist
Map<ObjectProperty, Integer> property2Overlap = new HashMap<ObjectProperty, Integer>();
String query = String.format("SELECT ?p (COUNT(*) AS ?cnt) WHERE {?s <%s> ?o. ?s ?p ?o.} GROUP BY ?p", propertyToDescribe.getName());
- System.out.println(query);ResultSet rs = executeSelectQuery(query);
+ ResultSet rs = executeSelectQuery(query);
QuerySolution qs;
while(rs.hasNext()){
qs = rs.next();
Modified: trunk/components-core/src/main/java/org/dllearner/kb/repository/oxford/OxfordRepository.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/kb/repository/oxford/OxfordRepository.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/kb/repository/oxford/OxfordRepository.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -90,7 +90,7 @@
private URI physicalURI;
public RepositoryEntry(URI ontologyIRI) {
- this.ontologyURI = ontologyIRI;System.out.println(ontologyIRI);
+ this.ontologyURI = ontologyIRI;
OntologyIRIShortFormProvider sfp = new OntologyIRIShortFormProvider();
shortName = sfp.getShortForm(IRI.create(ontologyIRI));
physicalURI = ontologyIRI;
Modified: trunk/components-core/src/main/java/org/dllearner/kb/sparql/QueryEngineHTTP.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/kb/sparql/QueryEngineHTTP.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/kb/sparql/QueryEngineHTTP.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -268,7 +268,7 @@
private Model execModel(Model model)
{
HttpQuery httpQuery = makeHttpQuery() ;
- httpQuery.setAccept(WebContent.contentTypeNTriplesAlt) ;
+ httpQuery.setAccept(WebContent.contentTypeTurtleAlt1) ;
InputStream in = httpQuery.exec() ;
//Don't assume the endpoint actually gives back the content type we asked for
@@ -284,7 +284,7 @@
//Try to select language appropriately here based on the model content type
Lang lang = WebContent.contentTypeToLang(actualContentType);
if (! RDFLanguages.isTriples(lang)) throw new QueryException("Endpoint returned Content Type: " + actualContentType + " which is not a valid RDF Graph syntax");
- model.read(in, null, "N-TRIPLES") ;
+ model.read(in, null, "TURTLE") ;
return model ;
}
Modified: trunk/components-core/src/main/java/org/dllearner/kb/sparql/simple/SparqlSimpleExtractor.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/kb/sparql/simple/SparqlSimpleExtractor.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/kb/sparql/simple/SparqlSimpleExtractor.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -11,7 +11,6 @@
import org.dllearner.core.AbstractKnowledgeSource;
import org.dllearner.core.ComponentAnn;
import org.dllearner.core.ComponentInitException;
-import org.dllearner.core.KnowledgeSource;
import org.dllearner.core.OntologyFormat;
import org.dllearner.core.OntologyFormatUnsupportedException;
import org.dllearner.core.config.ConfigOption;
@@ -36,7 +35,6 @@
import com.jamonapi.MonitorFactory;
@ComponentAnn(name = "efficient SPARQL fragment extractor", shortName = "sparqls", version = 0.1)
-
public class SparqlSimpleExtractor extends AbstractKnowledgeSource implements OWLOntologyKnowledgeSource{
@@ -334,5 +332,10 @@
JenaToOwlapiConverter converter = new JenaToOwlapiConverter();
return converter.convert(this.model,manager);
}
+
+ public static String getName(){
+ return "efficient SPARQL fragment extractor";
+ }
+
}
Modified: trunk/components-core/src/main/java/org/dllearner/reasoning/SPARQLReasoner.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/reasoning/SPARQLReasoner.java 2013-07-01 18:51:19 UTC (rev 4012)
+++ trunk/components-core/src/main/java/org/dllearner/reasoning/SPARQLReasoner.java 2013-07-01 19:05:50 UTC (rev 4013)
@@ -22,10 +22,12 @@
import java.net.URL;
import java.sql.SQLException;
import java.util.ArrayList;
+import java.util.Collection;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
+import java.util.Map.Entry;
import java.util.Set;
import java.util.SortedSet;
import java.util.TreeMap;
@@ -73,6 +75,8 @@
import org.slf4j.LoggerFactory;
import com.clarkparsia.owlapiv3.XSD;
+import com.google.common.collect.HashMultimap;
+import com.google.common.collect.Multimap;
import com.hp.hpl.jena.ontology.OntClass;
import com.hp.hpl.jena.ontology.OntModel;
import com.hp.hpl.jena.query.QueryExecution;
@@ -80,6 +84,7 @@
import com.hp.hpl.jena.query.ResultSet;
import com.hp.hpl.jena.rdf.model.Model;
import com.hp.hpl.jena.rdf.model.ModelFactory;
+import com.hp.hpl.jena.rdf.model.RDFNode;
import com.hp.hpl.jena.rdf.model.Resource;
import com.hp.hpl.jena.vocabulary.OWL;
import com.hp.hpl.jena.vocabulary.OWL2;
@@ -134,7 +139,7 @@
e.printStackTrace();
}
}
- qef = new QueryExecutionFactoryPaginated(qef, 10000);
+// qef = new QueryExecutionFactoryPaginated(qef, 10000);
} else {
qef = new QueryExecutionFactoryModel(((LocalModelBasedSparqlEndpointKS)ks).getModel());
@@ -518,6 +523,100 @@
}
return types;
}
+
+ public Set<Property> getProperties(boolean inferType, String namespace) {
+ Set<Property> properties = new HashSet<Property>();
+ String query = "SELECT DISTINCT ?p ?type WHERE {?s ?p ?o."
+ + (namespace != null ? ("FILTER(REGEX(?p,'^" + namespace + "'))") : "")
+ + "OPTIONAL{?p a ?type.}}";
+ ResultSet rs = executeSelectQuery(query);
+ Multimap<String, String> uri2Types = HashMultimap.create();
+ QuerySolution qs;
+ while(rs.hasNext()){
+ qs = rs.next();
+ String uri = qs.getResource("p").getURI();
+ String type = "";
+ if(qs.getResource("type") != null){
+ type = qs.getResource("type").getURI();
+ }
+ uri2Types.put(uri, type);
+ }
+ for (Entry<String, Collection<String>> entry : uri2Types.asMap().entrySet()) {
+ String uri = entry.getKey();
+ Collection<String> types = entry.getValue();
+ if(types.contains(OWL.ObjectProperty.getURI()) && !types.contains(OWL.DatatypeProperty.getURI())){
+ properties.add(new ObjectProperty(uri));
+ } else if(!types.contains(OWL.ObjectProperty.getURI()) && types.contains(OWL.DatatypeProperty.getURI())){
+ properties.add(new DatatypeProperty(uri));
+ } else {
+ //infer the type by values
+ query = "SELECT ?o WHERE {?s <" + uri + "> ?o. } LIMIT 100";
+ rs = executeSelectQuery(query);
+ boolean op = true;
+ boolean dp = true;
+ RDFNode node;
+ while(rs.hasNext()){
+ node = rs.next().get("o");
+ op = node.isResource();
+ dp = node.isLiteral();
+ }
+ if(op && !dp){
+ properties.add(new ObjectProperty(uri));
+ } else if(!op && dp){
+ properties.add(new DatatypeProperty(uri));
+ } else {
+ //not possible to decide
+ }
+ }
+ }
+ return properties;
+ }
+
+ public Set<Property> getProperties(boolean inferType) {
+ Set<Property> properties = new TreeSet<Property>();
+ String query = "SELECT DISTINCT ?p ?type WHERE {?s ?p ?o. OPTIONAL{?p a ?type.}}";
+ ResultSet rs = executeSelectQuery(query);
+ Multimap<String, String> uri2Types = HashMultimap.create();
+ QuerySolution qs;
+ while(rs.hasNext()){
+ qs = rs.next();
+ String uri = qs.getResource("p").getURI();
+ String type = "";
+ if(qs.getResource("type") != null){
+ type = qs.getResource("type").getURI();
+ }
+ uri2Types.put(uri, type);
+ }
+ for (Entry<String, Collection<String>> entry : uri2Types.asMap().entrySet()) {
+ String uri = entry.getKey();
+ Collection<String> types = entry.getValue();
+ if(types.contains(OWL.ObjectProperty.getURI()) && !types.contains(OWL.DatatypeProperty.getURI())){
+ properties.add(new ObjectProperty(uri));
+ } else if(!types.contains(OWL.ObjectProperty.getURI()) && types.contains(OWL.DatatypeProperty.getURI())){
+ properties.add(new DatatypeProperty(uri));
+ } else {
+ //infer the type by values
+ query = "SELECT ?o WHERE {?s <" + uri + "> ?o. } LIMIT 100";
+ rs = executeSelectQuery(query);
+ boolean op = true;
+ boolean dp = true;
+ RDFNode node;
+ while(rs.hasNext()){
+ node = rs.next().get("o");
+ op = node.isResource();
+ dp = node.isLiteral();
+ }
+ if(op && !dp){
+ properties.add(new ObjectProperty(uri));
+ } else if(!op && dp){
+ properties.add(new DatatypeProperty(uri));
+ } else {
+ //not possible to decide
+ }
+ }
+ }
+ return properties;
+ }
public Set<NamedClass> getOWLClasses() {
Set<NamedClass> types = new HashSet<NamedClass>();
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
