Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner: [369] trunk
|
From: <jen...@us...> - 2008-01-14 08:56:23
|
Revision: 369
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=369&view=rev
Author: jenslehmann
Date: 2008-01-14 00:56:17 -0800 (Mon, 14 Jan 2008)
Log Message:
-----------
started to merge the two SPARQL components
Modified Paths:
--------------
trunk/lib/components.ini
trunk/src/dl-learner/org/dllearner/cli/Start.java
trunk/src/dl-learner/org/dllearner/kb/sparql/SparqlQueryMaker.java
trunk/src/dl-learner/org/dllearner/server/DLLearnerWS.java
Added Paths:
-----------
trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java
trunk/src/dl-learner/org/dllearner/kb/sparql/SparqlCache.java
trunk/src/dl-learner/org/dllearner/kb/sparql/SparqlFilter.java
trunk/src/dl-learner/org/dllearner/kb/sparql/SparqlOntologyCollector.java
Removed Paths:
-------------
trunk/src/dl-learner/org/dllearner/kb/SparqlCache.java
trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java
trunk/src/dl-learner/org/dllearner/kb/SparqlEndpointRestructured.java
trunk/src/dl-learner/org/dllearner/kb/SparqlFilter.java
trunk/src/dl-learner/org/dllearner/kb/SparqlOntologyCollector.java
trunk/src/dl-learner/org/dllearner/kb/SparqlQueryMaker.java
Modified: trunk/lib/components.ini
===================================================================
--- trunk/lib/components.ini 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/lib/components.ini 2008-01-14 08:56:17 UTC (rev 369)
@@ -3,8 +3,7 @@
# knowledge sources
org.dllearner.kb.OWLFile
org.dllearner.kb.KBFile
-org.dllearner.kb.SparqlEndpoint
-org.dllearner.kb.SparqlEndpointRestructured
+org.dllearner.kb.sparql.SparqlEndpoint
# reasoners
org.dllearner.reasoning.OWLAPIReasoner
org.dllearner.reasoning.DIGReasoner
Modified: trunk/src/dl-learner/org/dllearner/cli/Start.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/cli/Start.java 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/src/dl-learner/org/dllearner/cli/Start.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -61,7 +61,6 @@
import org.dllearner.kb.KBFile;
import org.dllearner.kb.OWLFile;
import org.dllearner.kb.SparqlEndpoint;
-import org.dllearner.kb.SparqlEndpointRestructured;
import org.dllearner.learningproblems.PosNegDefinitionLP;
import org.dllearner.learningproblems.PosNegInclusionLP;
import org.dllearner.learningproblems.PosOnlyDefinitionLP;
@@ -231,7 +230,6 @@
Map<Class<? extends Component>, String> componentPrefixMapping = new HashMap<Class<? extends Component>, String>();
// knowledge sources
componentPrefixMapping.put(SparqlEndpoint.class, "sparql");
- componentPrefixMapping.put(SparqlEndpointRestructured.class, "sparql2");
// reasoners
componentPrefixMapping.put(DIGReasoner.class, "digReasoner");
componentPrefixMapping.put(OWLAPIReasoner.class, "owlAPIReasoner");
@@ -386,8 +384,6 @@
ksClass = KBFile.class;
else if (formatString.equals("SPARQL"))
ksClass = SparqlEndpoint.class;
- else if (formatString.equals("SPARQL2"))
- ksClass = SparqlEndpointRestructured.class;
else if (formatString.equals("NT"))
ksClass = OWLFile.class;
else {
Deleted: trunk/src/dl-learner/org/dllearner/kb/SparqlCache.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/kb/SparqlCache.java 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/src/dl-learner/org/dllearner/kb/SparqlCache.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -1,202 +0,0 @@
-/**
- * Copyright (C) 2007, Sebastian Hellmann
- *
- * This file is part of DL-Learner.
- *
- * DL-Learner is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * (at your option) any later version.
- *
- * DL-Learner is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- */
-package org.dllearner.kb;
-
-import java.io.File;
-import java.io.FileInputStream;
-import java.io.FileOutputStream;
-import java.io.ObjectInputStream;
-import java.io.ObjectOutputStream;
-import java.io.Serializable;
-import java.net.URLEncoder;
-/**
- *
- * This is a primitive cache.
- * The objects of this class can be either the cache itself or just on entry in the cache
- *
- * the cache remembers: a timestamp, the original sparql-query, the result
- * key is the subject http://dbpedia.org/resource/Angela_Merkel which is first urlencoded
- * and so serves as the hash for the filename.
- * Cache validates if timestamp too old and Sparql-Query the same
- * before returning the SPARQL xml-result
- *
- * @author Sebastian Hellmann
- * @author Sebastian Knappe
- */
-public class SparqlCache implements Serializable{
-
- final static long serialVersionUID=104;
- transient String basedir="";
- transient String fileending=".cache";
- long timestamp;
- String content="";
- long daysoffreshness=15;
- long multiplier=24*60*60*1000;//h m s ms
- String sparqlquery="";
-
-
- /**
- * Constructor for the cache itself.
- * Called once at the beginning
- *
- * @param path Where the base path to the cache is
- */
- public SparqlCache(String path){
- this.basedir=path+File.separator;
- if(!new File(path).exists())
- {System.out.println(new File(path).mkdir());;}
-
- }
-
-//
- /**
- * Constructor for single cache object(one entry)
- *
- * @param content the sparql xml result
- * @param sparql the sparql query
- */
- public SparqlCache(String content, String sparql){
- this.content=content;
- this.sparqlquery=sparql;
- this.timestamp=System.currentTimeMillis();
- }
-
-
-
- /**
- * use only on the cache object describing the cache itself
- *
- * @param key the individual
- * @param sparql the sparql query
- * @return the cached sparql result or null
- */
- public String get(String key, String sparql){
- String ret=null;
- try{
- SparqlCache c =readFromFile(makeFilename(key));
- if(c==null)return null;
- if(!c.checkFreshness())return null;
- if(!c.validate(sparql))return null;
-
- ret=c.content;
- }catch (Exception e) {e.printStackTrace();}
- return ret;
- }
-
- /**
- *
- * constructor for single cache object(one entry)
- *
- * @param key the individual
- * @param content the sparql result
- * @param sparql the sparql query
- */
- public void put(String key, String content, String sparql){
- SparqlCache c=new SparqlCache(content,sparql);
- putIntoFile(makeFilename(key), c);
- }
-
-
- /**
- * to normalize the filenames
- *
- * @param key
- * @return
- */
- String makeFilename(String key){
- String ret="";
- try{
- ret=basedir+URLEncoder.encode(key, "UTF-8")+fileending;
- }catch (Exception e) {e.printStackTrace();}
- return ret;
- }
-
- /**
- * how old is the result
- * @return
- */
- boolean checkFreshness(){
- if((System.currentTimeMillis()-this.timestamp)<=(daysoffreshness*multiplier))
- //fresh
- return true;
- else return false;
- }
-
-
- /**
- * some sparql query
- * @param sparql
- * @return
- */
- boolean validate(String sparql){
- if(this.sparqlquery.equals(sparql))
- //valid
- return true;
- else return false;
- }
-
- /**
- * makes a new file if none exists
- * @param Filename
- */
- public void checkFile(String Filename){
- if(!new File(Filename).exists()){
- try{
- new File(Filename).createNewFile();
- }catch (Exception e) {e.printStackTrace();}
-
- }
-
- }
-
- /**
- * internal saving function
- * puts a cache object into a file
- *
- * @param Filename
- * @param content
- */
- public void putIntoFile(String Filename,SparqlCache content){
- try{
- FileOutputStream fos = new FileOutputStream( Filename , false );
- ObjectOutputStream o = new ObjectOutputStream( fos );
- o.writeObject( content );
- fos.flush();
- fos.close();
- }catch (Exception e) {System.out.println("Not in cache creating: "+Filename);}
- }
-
- /**
- * internal retrieval function
- *
- * @param Filename
- * @return one entry object
- */
- public SparqlCache readFromFile(String Filename){
- SparqlCache content=null;
- try{
- FileInputStream fos = new FileInputStream( Filename );
- ObjectInputStream o = new ObjectInputStream( fos );
- content=(SparqlCache)o.readObject();
- }catch (Exception e) {}
- return content;
-
- }
-}
Deleted: trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -1,342 +0,0 @@
-/**
- * Copyright (C) 2007, Jens Lehmann
- *
- * This file is part of DL-Learner.
- *
- * DL-Learner is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * (at your option) any later version.
- *
- * DL-Learner is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- */
-package org.dllearner.kb;
-
-import java.io.File;
-import java.io.FileWriter;
-import java.io.IOException;
-import java.net.MalformedURLException;
-import java.net.URI;
-import java.net.URL;
-import java.util.Collection;
-import java.util.LinkedList;
-import java.util.Set;
-
-import org.dllearner.core.KnowledgeSource;
-import org.dllearner.core.OntologyFormat;
-import org.dllearner.core.OntologyFormatUnsupportedException;
-import org.dllearner.core.config.BooleanConfigOption;
-import org.dllearner.core.config.ConfigEntry;
-import org.dllearner.core.config.ConfigOption;
-import org.dllearner.core.config.IntegerConfigOption;
-import org.dllearner.core.config.InvalidConfigOptionValueException;
-import org.dllearner.core.config.StringConfigOption;
-import org.dllearner.core.config.StringSetConfigOption;
-import org.dllearner.core.dl.KB;
-import org.dllearner.parser.KBParser;
-import org.dllearner.reasoning.DIGConverter;
-import org.dllearner.reasoning.JenaOWLDIGConverter;
-import org.dllearner.utilities.Datastructures;
-
-/**
- * Represents a SPARQL Endpoint.
- * TODO: Is it necessary to create a class DBpediaSparqlEndpoint?
- *
- * @author Jens Lehmann
- * @author Sebastian Knappe
- */
-public class SparqlEndpoint extends KnowledgeSource {
-
- //ConfigOptions
- private URL url;
- private Set<String> instances;
- private URL dumpFile;
- private int numberOfRecursions;
- private int filterMode;
- private Set<String> predList;
- private Set<String> objList;
- private Set<String> classList;
- private String format;
- private boolean dumpToFile;
- private boolean useLits=false;
-
- /**
- * Holds the results of the calculateSubjects method
- */
- private String[] subjects;
-
- /**
- * Holds the results of the calculateTriples method
- */
- private String[] triples;
-
- /**
- * Holds the results of the calculateConceptSubjects method
- */
- private String[] conceptSubjects;
-
- /**
- * if a method is running this becomes true
- */
- private boolean subjectThreadRunning=false;
-
- private boolean triplesThreadRunning=false;
-
- private boolean conceptThreadRunning=false;
-
- /**
- * the Thread that is running a method
- */
- private Thread subjectThread;
-
- private Thread triplesThread;
-
- private Thread conceptThread;
-
- //received ontology as array, used if format=Array(an element of the
- //array consists of the subject, predicate and object separated by '<'
- private String[] ontArray;
-
- //received ontology as KB, the internal format
- private KB kb;
-
- public static String getName() {
- return "SPARQL Endpoint";
- }
-
- /**
- * sets the ConfigOptions for this KnowledgeSource
- * @return
- */
- public static Collection<ConfigOption<?>> createConfigOptions() {
- Collection<ConfigOption<?>> options = new LinkedList<ConfigOption<?>>();
- options.add(new StringConfigOption("url", "URL of SPARQL Endpoint"));
- options.add(new StringSetConfigOption("instances","relevant instances e.g. positive and negative examples in a learning problem"));
- options.add(new IntegerConfigOption("numberOfRecursions","number of Recursions, the Sparql-Endpoint is asked"));
- options.add(new IntegerConfigOption("filterMode","the mode of the SPARQL Filter"));
- options.add(new StringSetConfigOption("predList","a predicate list"));
- options.add(new StringSetConfigOption("objList","an object list"));
- options.add(new StringSetConfigOption("classList","a class list"));
- options.add(new StringConfigOption("format", "N-TRIPLES or KB format"));
- options.add(new BooleanConfigOption("dumpToFile", "wether Ontology from DBPedia is written to a file or not"));
- options.add(new BooleanConfigOption("useLits","use Literals in SPARQL query"));
- return options;
- }
-
- /*
- * @see org.dllearner.core.Component#applyConfigEntry(org.dllearner.core.ConfigEntry)
- */
- @Override
- @SuppressWarnings({"unchecked"})
- public <T> void applyConfigEntry(ConfigEntry<T> entry) throws InvalidConfigOptionValueException {
- String option = entry.getOptionName();
- if (option.equals("url")) {
- String s = (String) entry.getValue();
- try {
- url = new URL(s);
- } catch (MalformedURLException e) {
- throw new InvalidConfigOptionValueException(entry.getOption(), entry.getValue(),"malformed URL " + s);
- }
- } else if(option.equals("instances")) {
- instances = (Set<String>) entry.getValue();
- } else if(option.equals("numberOfRecursions")){
- numberOfRecursions=(Integer)entry.getValue();
- } else if(option.equals("predList")) {
- predList = (Set<String>) entry.getValue();
- } else if(option.equals("objList")) {
- objList = (Set<String>) entry.getValue();
- } else if(option.equals("classList")) {
- classList = (Set<String>) entry.getValue();
- } else if(option.equals("filterMode")){
- filterMode=(Integer)entry.getValue();
- } else if(option.equals("format")){
- format=(String)entry.getValue();
- } else if(option.equals("dumpToFile")){
- dumpToFile=(Boolean)entry.getValue();
- } else if(option.equals("useLits")){
- useLits=(Boolean)entry.getValue();
- }
- }
-
- /* (non-Javadoc)
- * @see org.dllearner.core.Component#init()
- */
- @Override
- public void init() {
- System.out.println("SparqlModul: Collecting Ontology");
- SparqlOntologyCollector oc=new SparqlOntologyCollector(Datastructures.setToArray(instances), numberOfRecursions, filterMode,
- Datastructures.setToArray(predList),Datastructures.setToArray( objList),Datastructures.setToArray(classList),format,url,useLits);
-
- try
- {
- String ont=oc.collectOntology();
-
- if (dumpToFile){
- String filename=System.currentTimeMillis()+".nt";
- String basedir="cache"+File.separator;
- try{
- if(!new File(basedir).exists())
- new File(basedir).mkdir();
-
- FileWriter fw=new FileWriter(new File(basedir+filename),true);
- fw.write(ont);
- fw.flush();
- fw.close();
-
- dumpFile=(new File(basedir+filename)).toURI().toURL();
- }catch (Exception e) {e.printStackTrace();}
- }
- if (format.equals("KB")) {
- try{
- // kb=KBParser.parseKBFile(new StringReader(ont));
- kb=KBParser.parseKBFile(dumpFile);
- } catch(Exception e) {e.printStackTrace();}
- }
- }catch(IOException e) {
- e.printStackTrace();
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- /*
- * (non-Javadoc)
- *
- * @see org.dllearner.core.KnowledgeSource#toDIG()
- */
- @Override
- public String toDIG(URI kbURI) {
- if (format.equals("N-TRIPLES")) return JenaOWLDIGConverter.getTellsString(dumpFile, OntologyFormat.N_TRIPLES, kbURI);
- else return DIGConverter.getDIGString(kb, kbURI).toString();
- }
-
- /* (non-Javadoc)
- * @see org.dllearner.core.KnowledgeSource#export(java.io.File, org.dllearner.core.OntologyFormat)
- */
- @Override
- public void export(File file, OntologyFormat format) throws OntologyFormatUnsupportedException {
- // currently no export functions implemented, so we just throw an exception
- throw new OntologyFormatUnsupportedException("export", format);
- }
-
- public URL getURL() {
- return url;
- }
-
- public String[] getOntArray() {
- return ontArray;
- }
-
- public void calculateSubjects(String label,int limit)
- {
- System.out.println("SparqlModul: Collecting Subjects");
- SparqlOntologyCollector oc=new SparqlOntologyCollector(url);
- try{
- subjects=oc.getSubjectsFromLabel(label,limit);
- }catch (IOException e){
- subjects=new String[1];
- subjects[0]="[Error]Sparql Endpoint could not be reached.";
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- public void calculateTriples(String subject) {
- System.out.println("SparqlModul: Collecting Triples");
- SparqlOntologyCollector oc=new SparqlOntologyCollector(url);
- try{
- triples=oc.collectTriples(subject);
- }catch (IOException e){
- triples=new String[1];
- triples[0]="[Error]Sparql Endpoint could not be reached.";
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- public void calculateConceptSubjects(String concept)
- {
- System.out.println("SparqlModul: Collecting Subjects");
- SparqlOntologyCollector oc=new SparqlOntologyCollector(url);
- try{
- conceptSubjects=oc.getSubjectsFromConcept(concept);
- }catch (IOException e){
- conceptSubjects=new String[1];
- conceptSubjects[0]="[Error]Sparql Endpoint could not be reached.";
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- public boolean subjectThreadIsRunning()
- {
- return subjectThreadRunning;
- }
-
- public void setSubjectThreadRunning(boolean bool)
- {
- subjectThreadRunning=bool;
- }
-
- public boolean triplesThreadIsRunning()
- {
- return triplesThreadRunning;
- }
-
- public void setTriplesThreadRunning(boolean bool)
- {
- triplesThreadRunning=bool;
- }
-
- public boolean conceptThreadIsRunning()
- {
- return conceptThreadRunning;
- }
-
- public void setConceptThreadRunning(boolean bool)
- {
- conceptThreadRunning=bool;
- }
-
- public String[] getSubjects()
- {
- return subjects;
- }
-
- public Thread getSubjectThread() {
- return subjectThread;
- }
-
- public void setSubjectThread(Thread subjectThread) {
- this.subjectThread = subjectThread;
- }
-
- public Thread getTriplesThread() {
- return triplesThread;
- }
-
- public void setTriplesThread(Thread triplesThread) {
- this.triplesThread = triplesThread;
- }
-
- public Thread getConceptThread() {
- return conceptThread;
- }
-
- public void setConceptThread(Thread conceptThread) {
- this.conceptThread = conceptThread;
- }
-
- public String[] getTriples()
- {
- return triples;
- }
-
- public String[] getConceptSubjects()
- {
- return conceptSubjects;
- }
-}
Copied: trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java (from rev 367, trunk/src/dl-learner/org/dllearner/kb/SparqlEndpointRestructured.java)
===================================================================
--- trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java (rev 0)
+++ trunk/src/dl-learner/org/dllearner/kb/SparqlEndpoint.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -0,0 +1,510 @@
+/**
+ * Copyright (C) 2007, Jens Lehmann
+ *
+ * This file is part of DL-Learner.
+ *
+ * DL-Learner is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * DL-Learner is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+package org.dllearner.kb;
+
+import java.io.File;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URI;
+import java.net.URL;
+import java.util.Collection;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.LinkedList;
+import java.util.Set;
+
+import org.dllearner.core.KnowledgeSource;
+import org.dllearner.core.OntologyFormat;
+import org.dllearner.core.OntologyFormatUnsupportedException;
+import org.dllearner.core.config.BooleanConfigOption;
+import org.dllearner.core.config.ConfigEntry;
+import org.dllearner.core.config.ConfigOption;
+import org.dllearner.core.config.IntegerConfigOption;
+import org.dllearner.core.config.InvalidConfigOptionValueException;
+import org.dllearner.core.config.StringConfigOption;
+import org.dllearner.core.config.StringSetConfigOption;
+import org.dllearner.core.config.StringTupleListConfigOption;
+import org.dllearner.core.dl.KB;
+import org.dllearner.kb.sparql.Manager;
+import org.dllearner.kb.sparql.Manipulator;
+import org.dllearner.kb.sparql.PredefinedEndpoint;
+import org.dllearner.kb.sparql.PredefinedFilter;
+import org.dllearner.kb.sparql.SparqlOntologyCollector;
+import org.dllearner.kb.sparql.SparqlQueryType;
+import org.dllearner.kb.sparql.SpecificSparqlEndpoint;
+import org.dllearner.parser.KBParser;
+import org.dllearner.reasoning.DIGConverter;
+import org.dllearner.reasoning.JenaOWLDIGConverter;
+import org.dllearner.utilities.StringTuple;
+
+/**
+ * Represents a SPARQL Endpoint.
+ *
+ * @author Jens Lehmann
+ * @author Sebastian Knappe
+ * @author Sebastian Hellmann
+ */
+public class SparqlEndpoint extends KnowledgeSource {
+
+ // ConfigOptions
+ private URL url;
+ String host;
+ private Set<String> instances=new HashSet<String>();;
+ private URL dumpFile;
+ private int recursionDepth = 1;
+ private int predefinedFilter = 0;
+ private int predefinedEndpoint = 0;
+ private Set<String> predList=new HashSet<String>();
+ private Set<String> objList=new HashSet<String>();
+ // private Set<String> classList;
+ private String format = "N-TRIPLES";
+ private boolean dumpToFile = true;
+ private boolean useLits = false;
+ private boolean getAllSuperClasses = true;
+ private boolean closeAfterRecursion = true;
+ private int breakSuperClassRetrievalAfter = 200;
+
+ private boolean learnDomain = false;
+ private boolean learnRange = false;
+ private int numberOfInstancesUsedForRoleLearning=40;
+ private String role="";
+ private String blankNodeIdentifier = "bnode";
+
+ LinkedList<StringTuple> URIParameters = new LinkedList<StringTuple>();
+ LinkedList<StringTuple> replacePredicate = new LinkedList<StringTuple>();
+ LinkedList<StringTuple> replaceObject = new LinkedList<StringTuple>();
+
+ /**
+ * Holds the results of the calculateSubjects method
+ */
+ private String[] subjects;
+
+ /**
+ * Holds the results of the calculateTriples method
+ */
+ private String[] triples;
+
+ /**
+ * Holds the results of the calculateConceptSubjects method
+ */
+ private String[] conceptSubjects;
+
+ /**
+ * if a method is running this becomes true
+ */
+ private boolean subjectThreadRunning = false;
+
+ private boolean triplesThreadRunning = false;
+
+ private boolean conceptThreadRunning = false;
+
+ /**
+ * the Thread that is running a method
+ */
+ private Thread subjectThread;
+
+ private Thread triplesThread;
+
+ private Thread conceptThread;
+
+ // received ontology as array, used if format=Array(an element of the
+ // array consists of the subject, predicate and object separated by '<'
+ private String[] ontArray;
+
+ // received ontology as KB, the internal format
+ private KB kb;
+
+ public static String getName() {
+ return "SPARQL Endpoint Restructured";
+ }
+
+ /**
+ * sets the ConfigOptions for this KnowledgeSource
+ *
+ * @return
+ */
+ public static Collection<ConfigOption<?>> createConfigOptions() {
+ Collection<ConfigOption<?>> options = new LinkedList<ConfigOption<?>>();
+ options.add(new StringConfigOption("url", "URL of SPARQL Endpoint"));
+ options.add(new StringConfigOption("host", "host of SPARQL Endpoint"));
+ options.add(new StringSetConfigOption("instances",
+ "relevant instances e.g. positive and negative examples in a learning problem"));
+ options.add(new IntegerConfigOption("recursionDepth",
+ "recursion depth of KB fragment selection", 2));
+ options.add(new IntegerConfigOption("predefinedFilter", "the mode of the SPARQL Filter"));
+ options.add(new IntegerConfigOption("predefinedEndpoint", "the mode of the SPARQL Filter"));
+
+ options.add(new StringSetConfigOption("predList", "list of all ignored roles"));
+ options.add(new StringSetConfigOption("objList", "list of all ignored objects"));
+ options.add(new StringSetConfigOption("classList", "list of all ignored classes"));
+ options.add(new StringConfigOption("format", "N-TRIPLES or KB format", "N-TRIPLES"));
+ options.add(new BooleanConfigOption("dumpToFile",
+ "Specifies whether the extracted ontology is written to a file or not.", true));
+ options.add(new BooleanConfigOption("useLits", "use Literals in SPARQL query"));
+ options.add(new BooleanConfigOption("getAllSuperClasses", "If true then all superclasses are retrieved until the most general class (owl:Thing) is reached.", true));
+
+ options.add(new BooleanConfigOption("learnDomain", "learns the Domain for a Role"));
+ options.add(new BooleanConfigOption("learnRange", "learns the Range for a Role"));
+ options.add(new StringConfigOption("role", "role to learn Domain/Range from"));
+ options.add(new StringConfigOption("blankNodeIdentifier",
+ "used to identify blanknodes in Tripels"));
+
+ options.add(new StringTupleListConfigOption("example", "example"));
+ options.add(new StringTupleListConfigOption("replacePredicate", "rule for replacing predicates"));
+ options.add(new StringTupleListConfigOption("replaceObject", "rule for replacing predicates"));
+ options.add(new IntegerConfigOption("breakSuperClassRetrievalAfter", "stops a cyclic hierarchy after specified number of classes"));
+ options.add(new IntegerConfigOption("numberOfInstancesUsedForRoleLearning", ""));
+ options.add(new BooleanConfigOption("closeAfterRecursion", "gets all classes for all instances"));
+
+
+
+ return options;
+ }
+
+ /*
+ * @see org.dllearner.core.Component#applyConfigEntry(org.dllearner.core.ConfigEntry)
+ */
+ @Override
+ @SuppressWarnings( { "unchecked" })
+ public <T> void applyConfigEntry(ConfigEntry<T> entry) throws InvalidConfigOptionValueException {
+ String option = entry.getOptionName();
+ if (option.equals("url")) {
+ String s = (String) entry.getValue();
+ try {
+ url = new URL(s);
+ } catch (MalformedURLException e) {
+ throw new InvalidConfigOptionValueException(entry.getOption(), entry.getValue(),
+ "malformed URL " + s);
+ }
+ } else if (option.equals("host")) {
+ host = (String) entry.getValue();
+ } else if (option.equals("instances")) {
+ instances = (Set<String>) entry.getValue();
+ } else if (option.equals("recursionDepth")) {
+ recursionDepth = (Integer) entry.getValue();
+ } else if (option.equals("predList")) {
+ predList = (Set<String>) entry.getValue();
+ } else if (option.equals("objList")) {
+ objList = (Set<String>) entry.getValue();
+ //} else if (option.equals("classList")) {
+ // classList = (Set<String>) entry.getValue();
+ } else if (option.equals("predefinedEndpoint")) {
+ predefinedEndpoint = (Integer) entry.getValue();
+ } else if (option.equals("predefinedFilter")) {
+ predefinedFilter = (Integer) entry.getValue();
+ } else if (option.equals("format")) {
+ format = (String) entry.getValue();
+ } else if (option.equals("dumpToFile")) {
+ dumpToFile = (Boolean) entry.getValue();
+ } else if (option.equals("useLits")) {
+ useLits = (Boolean) entry.getValue();
+ } else if (option.equals("getAllSuperClasses")) {
+ getAllSuperClasses = (Boolean) entry.getValue();
+ } else if (option.equals("learnDomain")) {
+ learnDomain = (Boolean) entry.getValue();
+ }else if (option.equals("learnRange")) {
+ learnRange = (Boolean) entry.getValue();
+ } else if (option.equals("role")) {
+ role = (String) entry.getValue();
+ } else if (option.equals("blankNodeIdentifier")) {
+ blankNodeIdentifier = (String) entry.getValue();
+ } else if (option.equals("example")) {
+ //System.out.println(entry.getValue());
+ }else if (option.equals("replacePredicate")) {
+ replacePredicate = (LinkedList)entry.getValue();
+ }else if (option.equals("replaceObject")) {
+ replaceObject = (LinkedList)entry.getValue();
+ }else if (option.equals("breakSuperClassRetrievalAfter")) {
+ breakSuperClassRetrievalAfter = (Integer) entry.getValue();
+ }else if (option.equals("numberOfInstancesUsedForRoleLearning")) {
+ numberOfInstancesUsedForRoleLearning = (Integer) entry.getValue();
+ }else if (option.equals("closeAfterRecursion")) {
+ closeAfterRecursion = (Boolean) entry.getValue();
+ }
+
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see org.dllearner.core.Component#init()
+ */
+ @Override
+ public void init() {
+ System.out.println("SparqlModul: Collecting Ontology");
+ // SparqlOntologyCollector oc=
+ // new SparqlOntologyCollector(Datastructures.setToArray(instances),
+ // numberOfRecursions, filterMode,
+ // Datastructures.setToArray(predList),Datastructures.setToArray(
+ // objList),Datastructures.setToArray(classList),format,url,useLits);
+ Manager m = new Manager();
+ SpecificSparqlEndpoint sse = null;
+ SparqlQueryType sqt = null;
+ // get Options for Manipulator
+ Manipulator man = new Manipulator(blankNodeIdentifier,breakSuperClassRetrievalAfter,replacePredicate,replaceObject);
+ HashMap<String, String> parameters = new HashMap<String, String>();
+ parameters.put("default-graph-uri", "http://dbpedia.org");
+ parameters.put("format", "application/sparql-results.xml");
+
+ // get Options for endpoints
+ if (predefinedEndpoint >= 1) {
+ sse = PredefinedEndpoint.getEndpoint(predefinedEndpoint);
+ } else {
+ sse = new SpecificSparqlEndpoint(url, host, parameters);
+ }
+
+ // get Options for Filters
+
+ if (predefinedFilter >= 1) {
+ sqt = PredefinedFilter.getFilter(predefinedFilter);
+
+ } else {
+ sqt = new SparqlQueryType("forbid", objList, predList, useLits + "");
+
+ }
+ // give everything to the manager
+ m.useConfiguration(sqt, sse, man, recursionDepth, getAllSuperClasses,closeAfterRecursion);
+ try {
+ String ont = "";
+ //System.out.println(learnDomain);
+ // used to learn a domain of a role
+ if (learnDomain || learnRange) {
+ Set<String> pos=new HashSet<String>();
+ Set<String> neg=new HashSet<String>();
+ if(learnDomain){
+ pos = m.getDomainInstancesForRole(role);
+ neg = m.getRangeInstancesForRole(role);
+ }else if(learnRange){
+ neg = m.getDomainInstancesForRole(role);
+ pos = m.getRangeInstancesForRole(role);
+ }
+ //choose 30
+
+
+ Set<String> tmp=new HashSet<String>();
+ for(String one:pos){
+ tmp.add(one);
+ if(tmp.size()>=numberOfInstancesUsedForRoleLearning)break;
+ }
+ pos=tmp;
+ System.out.println("Instances used: "+pos.size());
+
+ tmp=new HashSet<String>();
+ for(String one:neg){
+ tmp.add(one);
+ if(tmp.size()>=numberOfInstancesUsedForRoleLearning)break;
+ }
+ neg=tmp;
+
+ instances=new HashSet<String>();
+ instances.addAll(pos);
+
+ instances.addAll(neg);
+
+ for(String one:pos){
+ System.out.println("+\""+one+"\"");
+ }
+ for(String one:neg){
+ System.out.println("-\""+one+"\"");
+ }
+
+ /*Random r= new Random();
+
+
+ Object[] arr=instances.toArray();
+ while(instances.size()>=30){
+
+ }*/
+ // add the role to the filter(a solution is always EXISTS
+ // role.TOP)
+ m.addPredicateFilter(role);
+ //System.out.println(instances);
+ // THIS is a workaround
+
+ }
+ // the actual extraction is started here
+ ont = m.extract(instances);
+ System.out.println("Number of cached SPARQL queries: "+m.getConfiguration().numberOfCachedSparqlQueries);
+ System.out.println("Number of uncached SPARQL queries: "+m.getConfiguration().numberOfUncachedSparqlQueries);
+
+ System.out.println("Finished collecting Fragment");
+
+ if (dumpToFile) {
+ String filename = System.currentTimeMillis() + ".nt";
+ String basedir = "cache" + File.separator;
+ try {
+ if (!new File(basedir).exists())
+ new File(basedir).mkdir();
+
+ FileWriter fw = new FileWriter(new File(basedir + filename), true);
+ fw.write(ont);
+ fw.flush();
+ fw.close();
+
+ dumpFile = (new File(basedir + filename)).toURI().toURL();
+ } catch (Exception e) {
+ e.printStackTrace();
+ }
+ }
+ if (format.equals("KB")) {
+ try {
+ //kb = KBParser.parseKBFile(new StringReader(ont));
+ kb=KBParser.parseKBFile(dumpFile);
+ } catch (Exception e) {
+ e.printStackTrace();
+ }
+ }
+ } catch (Exception e) {
+ e.printStackTrace();
+ }
+ System.out.println("SparqlModul: ****Finished");
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see org.dllearner.core.KnowledgeSource#toDIG()
+ */
+ @Override
+ public String toDIG(URI kbURI) {
+ if (format.equals("N-TRIPLES"))
+ return JenaOWLDIGConverter.getTellsString(dumpFile, OntologyFormat.N_TRIPLES, kbURI);
+ else
+ return DIGConverter.getDIGString(kb, kbURI).toString();
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see org.dllearner.core.KnowledgeSource#export(java.io.File,
+ * org.dllearner.core.OntologyFormat)
+ */
+ @Override
+ public void export(File file, OntologyFormat format) throws OntologyFormatUnsupportedException {
+ // currently no export functions implemented, so we just throw an
+ // exception
+ throw new OntologyFormatUnsupportedException("export", format);
+ }
+
+ public URL getURL() {
+ return url;
+ }
+
+ public String[] getOntArray() {
+ return ontArray;
+ }
+
+ public void calculateSubjects(String label, int limit) {
+ System.out.println("SparqlModul: Collecting Subjects");
+ SparqlOntologyCollector oc = new SparqlOntologyCollector(url);
+ try {
+ subjects = oc.getSubjectsFromLabel(label, limit);
+ } catch (IOException e) {
+ subjects = new String[1];
+ subjects[0] = "[Error]Sparql Endpoint could not be reached.";
+ }
+ System.out.println("SparqlModul: ****Finished");
+ }
+
+ public void calculateTriples(String subject) {
+ System.out.println("SparqlModul: Collecting Triples");
+ SparqlOntologyCollector oc = new SparqlOntologyCollector(url);
+ try {
+ triples = oc.collectTriples(subject);
+ } catch (IOException e) {
+ triples = new String[1];
+ triples[0] = "[Error]Sparql Endpoint could not be reached.";
+ }
+ System.out.println("SparqlModul: ****Finished");
+ }
+
+ public void calculateConceptSubjects(String concept) {
+ System.out.println("SparqlModul: Collecting Subjects");
+ SparqlOntologyCollector oc = new SparqlOntologyCollector(url);
+ try {
+ conceptSubjects = oc.getSubjectsFromConcept(concept);
+ } catch (IOException e) {
+ conceptSubjects = new String[1];
+ conceptSubjects[0] = "[Error]Sparql Endpoint could not be reached.";
+ }
+ System.out.println("SparqlModul: ****Finished");
+ }
+
+ public boolean subjectThreadIsRunning() {
+ return subjectThreadRunning;
+ }
+
+ public void setSubjectThreadRunning(boolean bool) {
+ subjectThreadRunning = bool;
+ }
+
+ public boolean triplesThreadIsRunning() {
+ return triplesThreadRunning;
+ }
+
+ public void setTriplesThreadRunning(boolean bool) {
+ triplesThreadRunning = bool;
+ }
+
+ public boolean conceptThreadIsRunning() {
+ return conceptThreadRunning;
+ }
+
+ public void setConceptThreadRunning(boolean bool) {
+ conceptThreadRunning = bool;
+ }
+
+ public String[] getSubjects() {
+ return subjects;
+ }
+
+ public Thread getSubjectThread() {
+ return subjectThread;
+ }
+
+ public void setSubjectThread(Thread subjectThread) {
+ this.subjectThread = subjectThread;
+ }
+
+ public Thread getTriplesThread() {
+ return triplesThread;
+ }
+
+ public void setTriplesThread(Thread triplesThread) {
+ this.triplesThread = triplesThread;
+ }
+
+ public Thread getConceptThread() {
+ return conceptThread;
+ }
+
+ public void setConceptThread(Thread conceptThread) {
+ this.conceptThread = conceptThread;
+ }
+
+ public String[] getTriples() {
+ return triples;
+ }
+
+ public String[] getConceptSubjects() {
+ return conceptSubjects;
+ }
+}
Deleted: trunk/src/dl-learner/org/dllearner/kb/SparqlEndpointRestructured.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/kb/SparqlEndpointRestructured.java 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/src/dl-learner/org/dllearner/kb/SparqlEndpointRestructured.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -1,509 +0,0 @@
-/**
- * Copyright (C) 2007, Jens Lehmann
- *
- * This file is part of DL-Learner.
- *
- * DL-Learner is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * (at your option) any later version.
- *
- * DL-Learner is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- */
-package org.dllearner.kb;
-
-import java.io.File;
-import java.io.FileWriter;
-import java.io.IOException;
-import java.net.MalformedURLException;
-import java.net.URI;
-import java.net.URL;
-import java.util.Collection;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.LinkedList;
-import java.util.Set;
-
-import org.dllearner.core.KnowledgeSource;
-import org.dllearner.core.OntologyFormat;
-import org.dllearner.core.OntologyFormatUnsupportedException;
-import org.dllearner.core.config.BooleanConfigOption;
-import org.dllearner.core.config.ConfigEntry;
-import org.dllearner.core.config.ConfigOption;
-import org.dllearner.core.config.IntegerConfigOption;
-import org.dllearner.core.config.InvalidConfigOptionValueException;
-import org.dllearner.core.config.StringConfigOption;
-import org.dllearner.core.config.StringSetConfigOption;
-import org.dllearner.core.config.StringTupleListConfigOption;
-import org.dllearner.core.dl.KB;
-import org.dllearner.kb.sparql.Manager;
-import org.dllearner.kb.sparql.Manipulator;
-import org.dllearner.kb.sparql.PredefinedEndpoint;
-import org.dllearner.kb.sparql.PredefinedFilter;
-import org.dllearner.kb.sparql.SparqlQueryType;
-import org.dllearner.kb.sparql.SpecificSparqlEndpoint;
-import org.dllearner.parser.KBParser;
-import org.dllearner.reasoning.DIGConverter;
-import org.dllearner.reasoning.JenaOWLDIGConverter;
-import org.dllearner.utilities.StringTuple;
-
-/**
- * Represents a SPARQL Endpoint.
- *
- * @author Jens Lehmann
- * @author Sebastian Knappe
- * @author Sebastian Hellmann
- */
-public class SparqlEndpointRestructured extends KnowledgeSource {
-
- // ConfigOptions
- private URL url;
- String host;
- private Set<String> instances=new HashSet<String>();;
- private URL dumpFile;
- private int recursionDepth = 1;
- private int predefinedFilter = 0;
- private int predefinedEndpoint = 0;
- private Set<String> predList=new HashSet<String>();
- private Set<String> objList=new HashSet<String>();
- private Set<String> classList;
- private String format = "N-TRIPLES";
- private boolean dumpToFile = true;
- private boolean useLits = false;
- private boolean getAllSuperClasses = true;
- private boolean closeAfterRecursion = true;
- private int breakSuperClassRetrievalAfter = 200;
-
- private boolean learnDomain = false;
- private boolean learnRange = false;
- private int numberOfInstancesUsedForRoleLearning=40;
- private String role="";
- private String blankNodeIdentifier = "bnode";
-
- LinkedList<StringTuple> URIParameters = new LinkedList<StringTuple>();
- LinkedList<StringTuple> replacePredicate = new LinkedList<StringTuple>();
- LinkedList<StringTuple> replaceObject = new LinkedList<StringTuple>();
-
- /**
- * Holds the results of the calculateSubjects method
- */
- private String[] subjects;
-
- /**
- * Holds the results of the calculateTriples method
- */
- private String[] triples;
-
- /**
- * Holds the results of the calculateConceptSubjects method
- */
- private String[] conceptSubjects;
-
- /**
- * if a method is running this becomes true
- */
- private boolean subjectThreadRunning = false;
-
- private boolean triplesThreadRunning = false;
-
- private boolean conceptThreadRunning = false;
-
- /**
- * the Thread that is running a method
- */
- private Thread subjectThread;
-
- private Thread triplesThread;
-
- private Thread conceptThread;
-
- // received ontology as array, used if format=Array(an element of the
- // array consists of the subject, predicate and object separated by '<'
- private String[] ontArray;
-
- // received ontology as KB, the internal format
- private KB kb;
-
- public static String getName() {
- return "SPARQL Endpoint Restructured";
- }
-
- /**
- * sets the ConfigOptions for this KnowledgeSource
- *
- * @return
- */
- public static Collection<ConfigOption<?>> createConfigOptions() {
- Collection<ConfigOption<?>> options = new LinkedList<ConfigOption<?>>();
- options.add(new StringConfigOption("url", "URL of SPARQL Endpoint"));
- options.add(new StringConfigOption("host", "host of SPARQL Endpoint"));
- options.add(new StringSetConfigOption("instances",
- "relevant instances e.g. positive and negative examples in a learning problem"));
- options.add(new IntegerConfigOption("recursionDepth",
- "recursion depth of KB fragment selection", 2));
- options.add(new IntegerConfigOption("predefinedFilter", "the mode of the SPARQL Filter"));
- options.add(new IntegerConfigOption("predefinedEndpoint", "the mode of the SPARQL Filter"));
-
- options.add(new StringSetConfigOption("predList", "list of all ignored roles"));
- options.add(new StringSetConfigOption("objList", "list of all ignored objects"));
- options.add(new StringSetConfigOption("classList", "list of all ignored classes"));
- options.add(new StringConfigOption("format", "N-TRIPLES or KB format", "N-TRIPLES"));
- options.add(new BooleanConfigOption("dumpToFile",
- "Specifies whether the extracted ontology is written to a file or not.", true));
- options.add(new BooleanConfigOption("useLits", "use Literals in SPARQL query"));
- options.add(new BooleanConfigOption("getAllSuperClasses", "If true then all superclasses are retrieved until the most general class (owl:Thing) is reached.", true));
-
- options.add(new BooleanConfigOption("learnDomain", "learns the Domain for a Role"));
- options.add(new BooleanConfigOption("learnRange", "learns the Range for a Role"));
- options.add(new StringConfigOption("role", "role to learn Domain/Range from"));
- options.add(new StringConfigOption("blankNodeIdentifier",
- "used to identify blanknodes in Tripels"));
-
- options.add(new StringTupleListConfigOption("example", "example"));
- options.add(new StringTupleListConfigOption("replacePredicate", "rule for replacing predicates"));
- options.add(new StringTupleListConfigOption("replaceObject", "rule for replacing predicates"));
- options.add(new IntegerConfigOption("breakSuperClassRetrievalAfter", "stops a cyclic hierarchy after specified number of classes"));
- options.add(new IntegerConfigOption("numberOfInstancesUsedForRoleLearning", ""));
- options.add(new BooleanConfigOption("closeAfterRecursion", "gets all classes for all instances"));
-
-
-
- return options;
- }
-
- /*
- * @see org.dllearner.core.Component#applyConfigEntry(org.dllearner.core.ConfigEntry)
- */
- @Override
- @SuppressWarnings( { "unchecked" })
- public <T> void applyConfigEntry(ConfigEntry<T> entry) throws InvalidConfigOptionValueException {
- String option = entry.getOptionName();
- if (option.equals("url")) {
- String s = (String) entry.getValue();
- try {
- url = new URL(s);
- } catch (MalformedURLException e) {
- throw new InvalidConfigOptionValueException(entry.getOption(), entry.getValue(),
- "malformed URL " + s);
- }
- } else if (option.equals("host")) {
- host = (String) entry.getValue();
- } else if (option.equals("instances")) {
- instances = (Set<String>) entry.getValue();
- } else if (option.equals("recursionDepth")) {
- recursionDepth = (Integer) entry.getValue();
- } else if (option.equals("predList")) {
- predList = (Set<String>) entry.getValue();
- } else if (option.equals("objList")) {
- objList = (Set<String>) entry.getValue();
- } else if (option.equals("classList")) {
- classList = (Set<String>) entry.getValue();
- } else if (option.equals("predefinedEndpoint")) {
- predefinedEndpoint = (Integer) entry.getValue();
- } else if (option.equals("predefinedFilter")) {
- predefinedFilter = (Integer) entry.getValue();
- } else if (option.equals("format")) {
- format = (String) entry.getValue();
- } else if (option.equals("dumpToFile")) {
- dumpToFile = (Boolean) entry.getValue();
- } else if (option.equals("useLits")) {
- useLits = (Boolean) entry.getValue();
- } else if (option.equals("getAllSuperClasses")) {
- getAllSuperClasses = (Boolean) entry.getValue();
- } else if (option.equals("learnDomain")) {
- learnDomain = (Boolean) entry.getValue();
- }else if (option.equals("learnRange")) {
- learnRange = (Boolean) entry.getValue();
- } else if (option.equals("role")) {
- role = (String) entry.getValue();
- } else if (option.equals("blankNodeIdentifier")) {
- blankNodeIdentifier = (String) entry.getValue();
- } else if (option.equals("example")) {
- //System.out.println(entry.getValue());
- }else if (option.equals("replacePredicate")) {
- replacePredicate = (LinkedList)entry.getValue();
- }else if (option.equals("replaceObject")) {
- replaceObject = (LinkedList)entry.getValue();
- }else if (option.equals("breakSuperClassRetrievalAfter")) {
- breakSuperClassRetrievalAfter = (Integer) entry.getValue();
- }else if (option.equals("numberOfInstancesUsedForRoleLearning")) {
- numberOfInstancesUsedForRoleLearning = (Integer) entry.getValue();
- }else if (option.equals("closeAfterRecursion")) {
- closeAfterRecursion = (Boolean) entry.getValue();
- }
-
- }
-
- /*
- * (non-Javadoc)
- *
- * @see org.dllearner.core.Component#init()
- */
- @Override
- public void init() {
- System.out.println("SparqlModul: Collecting Ontology");
- // SparqlOntologyCollector oc=
- // new SparqlOntologyCollector(Datastructures.setToArray(instances),
- // numberOfRecursions, filterMode,
- // Datastructures.setToArray(predList),Datastructures.setToArray(
- // objList),Datastructures.setToArray(classList),format,url,useLits);
- Manager m = new Manager();
- SpecificSparqlEndpoint sse = null;
- SparqlQueryType sqt = null;
- // get Options for Manipulator
- Manipulator man = new Manipulator(blankNodeIdentifier,breakSuperClassRetrievalAfter,replacePredicate,replaceObject);
- HashMap<String, String> parameters = new HashMap<String, String>();
- parameters.put("default-graph-uri", "http://dbpedia.org");
- parameters.put("format", "application/sparql-results.xml");
-
- // get Options for endpoints
- if (predefinedEndpoint >= 1) {
- sse = PredefinedEndpoint.getEndpoint(predefinedEndpoint);
- } else {
- sse = new SpecificSparqlEndpoint(url, host, parameters);
- }
-
- // get Options for Filters
-
- if (predefinedFilter >= 1) {
- sqt = PredefinedFilter.getFilter(predefinedFilter);
-
- } else {
- sqt = new SparqlQueryType("forbid", objList, predList, useLits + "");
-
- }
- // give everything to the manager
- m.useConfiguration(sqt, sse, man, recursionDepth, getAllSuperClasses,closeAfterRecursion);
- try {
- String ont = "";
- //System.out.println(learnDomain);
- // used to learn a domain of a role
- if (learnDomain || learnRange) {
- Set<String> pos=new HashSet<String>();
- Set<String> neg=new HashSet<String>();
- if(learnDomain){
- pos = m.getDomainInstancesForRole(role);
- neg = m.getRangeInstancesForRole(role);
- }else if(learnRange){
- neg = m.getDomainInstancesForRole(role);
- pos = m.getRangeInstancesForRole(role);
- }
- //choose 30
-
-
- Set<String> tmp=new HashSet<String>();
- for(String one:pos){
- tmp.add(one);
- if(tmp.size()>=numberOfInstancesUsedForRoleLearning)break;
- }
- pos=tmp;
- System.out.println("Instances used: "+pos.size());
-
- tmp=new HashSet<String>();
- for(String one:neg){
- tmp.add(one);
- if(tmp.size()>=numberOfInstancesUsedForRoleLearning)break;
- }
- neg=tmp;
-
- instances=new HashSet<String>();
- instances.addAll(pos);
-
- instances.addAll(neg);
-
- for(String one:pos){
- System.out.println("+\""+one+"\"");
- }
- for(String one:neg){
- System.out.println("-\""+one+"\"");
- }
-
- /*Random r= new Random();
-
-
- Object[] arr=instances.toArray();
- while(instances.size()>=30){
-
- }*/
- // add the role to the filter(a solution is always EXISTS
- // role.TOP)
- m.addPredicateFilter(role);
- //System.out.println(instances);
- // THIS is a workaround
-
- }
- // the actual extraction is started here
- ont = m.extract(instances);
- System.out.println("Number of cached SPARQL queries: "+m.getConfiguration().numberOfCachedSparqlQueries);
- System.out.println("Number of uncached SPARQL queries: "+m.getConfiguration().numberOfUncachedSparqlQueries);
-
- System.out.println("Finished collecting Fragment");
-
- if (dumpToFile) {
- String filename = System.currentTimeMillis() + ".nt";
- String basedir = "cache" + File.separator;
- try {
- if (!new File(basedir).exists())
- new File(basedir).mkdir();
-
- FileWriter fw = new FileWriter(new File(basedir + filename), true);
- fw.write(ont);
- fw.flush();
- fw.close();
-
- dumpFile = (new File(basedir + filename)).toURI().toURL();
- } catch (Exception e) {
- e.printStackTrace();
- }
- }
- if (format.equals("KB")) {
- try {
- //kb = KBParser.parseKBFile(new StringReader(ont));
- kb=KBParser.parseKBFile(dumpFile);
- } catch (Exception e) {
- e.printStackTrace();
- }
- }
- } catch (Exception e) {
- e.printStackTrace();
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- /*
- * (non-Javadoc)
- *
- * @see org.dllearner.core.KnowledgeSource#toDIG()
- */
- @Override
- public String toDIG(URI kbURI) {
- if (format.equals("N-TRIPLES"))
- return JenaOWLDIGConverter.getTellsString(dumpFile, OntologyFormat.N_TRIPLES, kbURI);
- else
- return DIGConverter.getDIGString(kb, kbURI).toString();
- }
-
- /*
- * (non-Javadoc)
- *
- * @see org.dllearner.core.KnowledgeSource#export(java.io.File,
- * org.dllearner.core.OntologyFormat)
- */
- @Override
- public void export(File file, OntologyFormat format) throws OntologyFormatUnsupportedException {
- // currently no export functions implemented, so we just throw an
- // exception
- throw new OntologyFormatUnsupportedException("export", format);
- }
-
- public URL getURL() {
- return url;
- }
-
- public String[] getOntArray() {
- return ontArray;
- }
-
- public void calculateSubjects(String label, int limit) {
- System.out.println("SparqlModul: Collecting Subjects");
- SparqlOntologyCollector oc = new SparqlOntologyCollector(url);
- try {
- subjects = oc.getSubjectsFromLabel(label, limit);
- } catch (IOException e) {
- subjects = new String[1];
- subjects[0] = "[Error]Sparql Endpoint could not be reached.";
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- public void calculateTriples(String subject) {
- System.out.println("SparqlModul: Collecting Triples");
- SparqlOntologyCollector oc = new SparqlOntologyCollector(url);
- try {
- triples = oc.collectTriples(subject);
- } catch (IOException e) {
- triples = new String[1];
- triples[0] = "[Error]Sparql Endpoint could not be reached.";
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- public void calculateConceptSubjects(String concept) {
- System.out.println("SparqlModul: Collecting Subjects");
- SparqlOntologyCollector oc = new SparqlOntologyCollector(url);
- try {
- conceptSubjects = oc.getSubjectsFromConcept(concept);
- } catch (IOException e) {
- conceptSubjects = new String[1];
- conceptSubjects[0] = "[Error]Sparql Endpoint could not be reached.";
- }
- System.out.println("SparqlModul: ****Finished");
- }
-
- public boolean subjectThreadIsRunning() {
- return subjectThreadRunning;
- }
-
- public void setSubjectThreadRunning(boolean bool) {
- subjectThreadRunning = bool;
- }
-
- public boolean triplesThreadIsRunning() {
- return triplesThreadRunning;
- }
-
- public void setTriplesThreadRunning(boolean bool) {
- triplesThreadRunning = bool;
- }
-
- public boolean conceptThreadIsRunning() {
- return conceptThreadRunning;
- }
-
- public void setConceptThreadRunning(boolean bool) {
- conceptThreadRunning = bool;
- }
-
- public String[] getSubjects() {
- return subjects;
- }
-
- public Thread getSubjectThread() {
- return subjectThread;
- }
-
- public void setSubjectThread(Thread subjectThread) {
- this.subjectThread = subjectThread;
- }
-
- public Thread getTriplesThread() {
- return triplesThread;
- }
-
- public void setTriplesThread(Thread triplesThread) {
- this.triplesThread = triplesThread;
- }
-
- public Thread getConceptThread() {
- return conceptThread;
- }
-
- public void setConceptThread(Thread conceptThread) {
- this.conceptThread = conceptThread;
- }
-
- public String[] getTriples() {
- return triples;
- }
-
- public String[] getConceptSubjects() {
- return conceptSubjects;
- }
-}
Deleted: trunk/src/dl-learner/org/dllearner/kb/SparqlFilter.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/kb/SparqlFilter.java 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/src/dl-learner/org/dllearner/kb/SparqlFilter.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -1,119 +0,0 @@
-/**
- * Copyright (C) 2007, Sebastian Hellmann
- *
- * This file is part of DL-Learner.
- *
- * DL-Learner is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * (at your option) any later version.
- *
- * DL-Learner is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- */
-package org.dllearner.kb;
-
-/**
- *
- *
- * encapsulates all the options
- * see the documentation for more help
- *
- * @author Sebastian Hellmann
- * @author Sebastian Knappe
- *
- */
-public class SparqlFilter {
- public int mode=0;
- // 0 yago, 1 only cat, 2 skos+cat
- String[] PredFilter=null;
- String[] ObjFilter=null;
- boolean useLiterals=false;
-
-
- String[] yagoPredFilterDefault={
- "http://www.w3.org/2004/02/skos/core",
- "http://xmlns.com/foaf/0.1/",
- "http://dbpedia.org/property/wikipage-",
- "http://www.w3.org/2002/07/owl#sameAs",
- "http://dbpedia.org/property/reference" };
- String[] yagoObjFilterDefault={
- "http://dbpedia.org/resource/Category:Articles_",
- "http://dbpedia.org/resource/Category:Wikipedia_",
- "http://xmlns.com/foaf/0.1/",
- "http://dbpedia.org/resource/Category",
- "http://dbpedia.org/resource/Template",
- "http://upload.wikimedia.org/wikipedia/commons"};
-
- String[] onlyCatPredFilterDefault={
- "http://www.w3.org/2004/02/skos/core",
- "http://xmlns.com/foaf/0.1/",
- "http://dbpedia.org/property/wikipage-",
- "http://www.w3.org/2002/07/owl#sameAs",
- "http://dbpedia.org/property/reference" };
- String[] onlyCatObjFilterDefault={
- "http://dbpedia.org/resource/Category:Articles_",
- "http://dbpedia.org/resource/Category:Wikipedia_",
- "http://xmlns.com/foaf/0.1/",
- "http://dbpedia.org/class/yago",
- "http://dbpedia.org/resource/Template",
- "http://upload.wikimedia.org/wikipedia/commons"};
-
- String[] skosPredFilterDefault={
- "http://www.w3.org/2004/02/skos/core#narrower",
- "http://xmlns.com/foaf/0.1/",
- "http://dbpedia.org/property/wikipage-",
- "http://www.w3.org/2002/07/owl#sameAs",
- "http://dbpedia.org/property/reference" };
- String[] skosObjFilterDefault={
- "http://dbpedia.org/resource/Category:Articles_",
- "http://dbpedia.org/resource/Category:Wikipedia_",
- "http://xmlns.com/foaf/0.1/",
- "http://dbpedia.org/class/yago",
- "http://dbpedia.org/resource/Template",
- "http://upload.wikimedia.org/wikipedia/commons"};
-
- public SparqlFilter(int mode, String[] pred, String[] obj) {
- if (mode==-1 && (pred==null || obj==null))
- {mode=0;}
- this.mode=mode;
-
- switch (mode){
- case 0: //yago
- ObjFilter=yagoObjFilterDefault;
- PredFilter=yagoPredFilterDefault;
- break;
- case 1: // only Categories
- ObjFilter=onlyCatObjFilterDefault;
- PredFilter=onlyCatPredFilterDefault;
- break;
- case 2: // there are some other changes to, which are made directly in other functions
- ObjFilter=skosObjFilterDefault;
- PredFilter=skosPredFilterDefault;
- break;
- default:
- ObjFilter=obj;
- PredFilter=pred;
- break;
- }
- }
-
- public SparqlFilter(int mode, String[] pred, String[] obj,boolean uselits) throws Exception{
- this(mode,pred,obj);
- this.useLiterals=uselits;
- }
-
- public String[] getObjFilter(){
- return this.ObjFilter;
- }
-
- public String[] getPredFilter(){
- return this.PredFilter;
- }
-}
\ No newline at end of file
Deleted: trunk/src/dl-learner/org/dllearner/kb/SparqlOntologyCollector.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/kb/SparqlOntologyCollector.java 2008-01-13 10:22:16 UTC (rev 368)
+++ trunk/src/dl-learner/org/dllearner/kb/SparqlOntologyCollector.java 2008-01-14 08:56:17 UTC (rev 369)
@@ -1,509 +0,0 @@
-/**
- * Copyright (C) 2007, Sebastian Hellmann
- *
- * This file is part of DL-Learner.
- *
- * DL-Learner is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * (at your option) any later version.
- *
- * DL-Learner is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- */
-package org.dllearner.kb;
-
-import java.io.BufferedReader;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.InputStreamReader;
-import java.io.OutputStream;
-import java.io.OutputStreamWriter;
-import java.net.HttpURLConnection;
-import java.net.URL;
-import java.net.URLEncoder;
-import java.util.ArrayList;
-import java.util.HashSet;
-import java.util.Iterator;
-import java.util.Vector;
-
-
-/**
- * This class collects the ontology from dbpedia,
- * everything is saved in hashsets, so the doublettes are taken care of
- *
- *
- * @author Sebastia...
[truncated message content] |
