001/** 002 * Copyright (C) 2007 - 2016, Jens Lehmann 003 * 004 * This file is part of DL-Learner. 005 * 006 * DL-Learner is free software; you can redistribute it and/or modify 007 * it under the terms of the GNU General Public License as published by 008 * the Free Software Foundation; either version 3 of the License, or 009 * (at your option) any later version. 010 * 011 * DL-Learner is distributed in the hope that it will be useful, 012 * but WITHOUT ANY WARRANTY; without even the implied warranty of 013 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 014 * GNU General Public License for more details. 015 * 016 * You should have received a copy of the GNU General Public License 017 * along with this program. If not, see <http://www.gnu.org/licenses/>. 018 */ 019package org.dllearner.algorithms.qtl.util.filters; 020 021import com.google.common.base.Charsets; 022import com.google.common.io.Files; 023import org.apache.jena.graph.Node; 024import org.apache.jena.graph.NodeFactory; 025import org.apache.jena.query.QueryExecution; 026import org.apache.jena.query.QuerySolution; 027import org.apache.jena.query.ResultSet; 028import org.apache.jena.rdf.model.Resource; 029import org.apache.jena.sparql.util.NodeComparator; 030import org.dllearner.kb.SparqlEndpointKS; 031 032import java.io.File; 033import java.io.IOException; 034import java.net.URISyntaxException; 035import java.util.List; 036import java.util.Set; 037import java.util.TreeSet; 038 039/** 040 * @author Lorenz Buehmann 041 * 042 */ 043public class PredicateExistenceFilterDBpedia extends PredicateExistenceFilter{ 044 045 private String PATH = "org/dllearner/algorithms/qtl/dbpedia_meaningless_properties.txt"; 046 private SparqlEndpointKS ks; 047 048 public PredicateExistenceFilterDBpedia(SparqlEndpointKS ks) { 049 this.ks = ks; 050 Set<Node> existentialMeaninglessProperties = new TreeSet<>(new NodeComparator()); 051 052 try { 053 List<String> lines = Files.readLines(new File(this.getClass().getClassLoader().getResource(PATH).toURI()), Charsets.UTF_8); 054 for (String line : lines) { 055 if(!line.trim().isEmpty() && !line.startsWith("#")) { 056 existentialMeaninglessProperties.add(NodeFactory.createURI(line.trim())); 057 } 058 } 059 } catch (IOException | URISyntaxException e) { 060 e.printStackTrace(); 061 } 062 setExistentialMeaninglessProperties(existentialMeaninglessProperties); 063 } 064 065 private void analyze() { 066 Set<Node> existentialMeaninglessProperties = new TreeSet<>(new NodeComparator()); 067 068 StringBuilder sb = new StringBuilder(); 069 // check data properties 070 String query = "SELECT ?p ?range WHERE {?p a owl:DatatypeProperty . ?p rdfs:range ?range .}"; 071 072 QueryExecution qe = ks.getQueryExecutionFactory().createQueryExecution(query); 073 ResultSet rs = qe.execSelect(); 074 while (rs.hasNext()) { 075 QuerySolution qs = rs.next(); 076 077 Resource property = qs.getResource("p"); 078 Resource range = qs.getResource("range"); 079 080// if(range.equals(XSD.xdouble)) { 081 existentialMeaninglessProperties.add(property.asNode()); 082// } 083 } 084 qe.close(); 085 for (Node p : existentialMeaninglessProperties) { 086 sb.append(p).append("\n"); 087 } 088 existentialMeaninglessProperties.clear(); 089 sb.append("\n\n"); 090 091 // check object properties 092 query = "SELECT ?p WHERE {?p a owl:ObjectProperty .}"; 093 094 qe = ks.getQueryExecutionFactory().createQueryExecution(query); 095 rs = qe.execSelect(); 096 while (rs.hasNext()) { 097 QuerySolution qs = rs.next(); 098 099 Resource property = qs.getResource("p"); 100 existentialMeaninglessProperties.add(property.asNode()); 101 102 } 103 qe.close(); 104 105 for (Node p : existentialMeaninglessProperties) { 106 sb.append(p).append("\n"); 107 } 108 try { 109 Files.asCharSink(new File("dbpedia_meaningless_properties.txt"), Charsets.UTF_8).write(sb.toString()); 110 } catch (IOException e) { 111 e.printStackTrace(); 112 } 113 } 114 115}