Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[3284] trunk/components-ext/src/main/java/org/ dllearner/algorithm/tbsl
|
From: <seb...@us...> - 2011-09-23 08:33:51
|
Revision: 3284
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=3284&view=rev
Author: sebastianwtr
Date: 2011-09-23 08:33:44 +0000 (Fri, 23 Sep 2011)
Log Message:
-----------
[tbsl] added some new packetches and function for the QALD Projekt at UNI Bi
Added Paths:
-----------
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/GetRessourcePropertys.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlFilter.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlObject.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Levenshtein.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Parsing.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/exploration_main.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/test_vergleich.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxHandler.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxParser.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/ParseXmlHtml.java
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/GetRessourcePropertys.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/GetRessourcePropertys.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/GetRessourcePropertys.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,84 @@
+package org.dllearner.algorithm.tbsl.exploration.Sparql;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+
+import org.dllearner.algorithm.tbsl.exploration.sax.MySaxParser;
+
+public class GetRessourcePropertys {
+
+ public ArrayList<String> getPropertys(String element) throws IOException{
+ sendServerPropertyRequest(element);
+ return do_parsing("answer_property");
+
+
+ }
+ /**
+ * Get an uri and saves the properties of this resource
+ * @param vergleich
+ * @throws IOException
+ */
+ private void sendServerPropertyRequest(String vergleich) throws IOException{
+
+ String bla123 = vergleich;
+ //to get only the name
+ bla123=bla123.replace("http://dbpedia.org/resource/Category:","");
+ bla123=bla123.replace("http://dbpedia.org/resource/","");
+ vergleich=bla123;
+ String tmp="http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=PREFIX+rdfs%3A+%3Chttp%3A%2F%2Fwww.w3.org%2F2000%2F01%2Frdf-schema%23%3E%0D%0APREFIX+res%3A+%3Chttp%3A%2F%2Fdbpedia.org%2Fresource%2F%3E%0D%0A%0D%0ASELECT+DISTINCT+%3Fp+%3Fl+WHERE++{%0D%0A+{+res%3A"+vergleich+"+%3Fp+%3Fo+.+}%0D%0A+UNION%0D%0A+{+%3Fs+%3Fp+res%3A"+vergleich+"+.+}%0D%0A+{+%3Fp+rdfs%3Alabel+%3Fl+.+}%0D%0A}%0D%0A&format=text%2Fhtml&debug=on&timeout=";
+ URL url;
+ InputStream is;
+ InputStreamReader isr;
+ BufferedReader r;
+ String str;
+ String result="";
+
+ try {
+ url = new URL(tmp);
+ is = url.openStream();
+ isr = new InputStreamReader(is);
+ r = new BufferedReader(isr);
+ do {
+ str = r.readLine();
+ if (str != null)
+ result=result+str;
+ } while (str != null);
+ } catch (MalformedURLException e) {
+ System.out.println("Must enter a valid URL");
+ } catch (IOException e) {
+ System.out.println("Can not connect");
+ }
+
+ FileWriter w = new FileWriter("answer_property");
+ w.write(result);
+ w.close();
+ }
+
+
+ private static ArrayList<String> do_parsing(String datei)
+ {
+ ArrayList<String> indexObject = null;
+
+ File file = new File(datei);
+ try
+ {
+ MySaxParser parser = new MySaxParser(file);
+ parser.parse();
+ indexObject = parser.getIndexObject();
+ }
+ catch (Exception ex)
+ {
+ System.out.println("Another exciting error occured: " + ex.getLocalizedMessage());
+ }
+
+ return indexObject;
+ }
+
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlFilter.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlFilter.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlFilter.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,54 @@
+package org.dllearner.algorithm.tbsl.exploration.Sparql;
+
+import java.util.HashMap;
+
+public class SparqlFilter {
+ public void create_Sparql_who(String string,HashMap<String, String> hm){
+ // string=string.replaceAll("?", "");
+ String[] array= string.split(" ");
+ //schauen ob erstes Wort ein who ist!
+ if(array[0].contains("who")){
+ int position=0;
+ for(int i=0;i<array.length;i++){
+ if (array[i].contains("of")){
+ position=i;
+ break;
+ }
+ }
+ String vor_of=array[position-1];
+ String nach_of="";
+ //wenn nur ein element hinter of kommt
+ if(array.length-position-1==1){
+ nach_of=array[position+1];
+ }
+ else{
+ for(int i=position+1; i<array.length;i++){
+ //nach_of=nach_of+array[i]+" ";
+ nach_of=(nach_of.concat(array[i])).concat(" ");
+ }
+
+ //letztes leerzeichen loeschen
+ nach_of = nach_of.substring(0, nach_of.length()-1);
+ }
+ String uri_vor_of=" ";
+ String uri_nach_of=" ";
+
+ uri_vor_of=hm.get(vor_of);
+ uri_nach_of=hm.get(nach_of);
+ if(uri_vor_of!=null && uri_nach_of!=null){
+ uri_nach_of=uri_nach_of.replace("Category:", "");
+ uri_nach_of=uri_nach_of.replace("category:", "");
+
+
+ String anfrage=null;
+ anfrage="PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>select ?x where { <"+uri_nach_of+"> <"+uri_vor_of+"> ?x.}";
+
+ }
+ else{
+ //System.out.println("Nothing to do");
+ }
+
+ }
+
+ }
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlObject.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlObject.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/Sparql/SparqlObject.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,364 @@
+package org.dllearner.algorithm.tbsl.exploration.Sparql;
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Set;
+
+import net.didion.jwnl.JWNLException;
+
+import org.dllearner.algorithm.tbsl.nlp.WordNet;
+import org.dllearner.algorithm.tbsl.sparql.BasicQueryTemplate;
+import org.dllearner.algorithm.tbsl.templator.BasicTemplator;
+import org.dllearner.algorithm.tbsl.templator.Templator;
+
+
+
+public class SparqlObject {
+ //global Variable dict
+
+ //start counting with 0
+ static int iteration_deept=1;
+ static WordNet wordnet;
+ BasicTemplator btemplator;
+ Templator templator;
+
+ /*Set<BasicQueryTemplate> querytemps = btemplator.buildBasicQueries(line);
+ for (BasicQueryTemplate temp : querytemps) {
+ System.out.println(temp.toString());
+ }
+
+ */
+ //Konstruktor
+ public SparqlObject() throws MalformedURLException{
+ wordnet = new WordNet();
+ System.out.println("Loading SPARQL Templator");
+ btemplator = new BasicTemplator();
+ templator = new Templator();
+ System.out.println("Loading SPARQL Templator Done\n");
+ }
+
+
+ public void create_Sparql_query(String string,HashMap<String, String> hm) throws JWNLException{
+ // string=string.replaceAll("?", "");
+ String[] array= string.split(" ");
+ String teststring="";
+ /*Set<BasicQueryTemplate> querytemps = btemplator.buildBasicQueries("Who is the Mayor of Berlin?");
+ for (BasicQueryTemplate temp : querytemps) {
+ //System.out.println(temp.toString());
+ teststring=teststring.concat(temp.toString());
+ }
+
+ System.out.println("##################");
+ System.out.println(teststring);*/
+
+ /**
+ * Cluster function
+ */
+ /*
+ int length=array.length;
+ int [] result_array= new int[length];
+ for(int p =0;p<length;p++){
+ result_array[p]=0;
+ }
+ int zaehler=1;
+
+ //looking for max 3 word as one index
+ for(int z=length-1;z>=0;z=z-1){
+ if(z-2>=0){
+ String tmp1 = array[z];
+ String tmp2 = array[z-1];
+ String tmp3 = array[z-2];
+
+ String tmpstring3=(((tmp3.concat(" ")).concat(tmp2)).concat(" ")).concat(tmp1);
+ String tmpstring2=(tmp2.concat(" ")).concat(tmp1);
+ String tmpstring1=tmp1;
+
+ //always looking for the "biggest" match
+ if(hm.get(tmpstring3)!=null){
+ result_array[z]=zaehler;
+ result_array[z-1]=zaehler;
+ result_array[z-2]=zaehler;
+ zaehler++;
+ }
+ else{
+ if(hm.get(tmpstring2)!=null){
+ result_array[z]=zaehler;
+ result_array[z-1]=zaehler;
+ zaehler++;
+ }
+ else{
+ if(hm.get(tmpstring1)!=null){
+ result_array[z]=zaehler;
+ zaehler++;
+ }
+ }
+ }
+
+ }
+ else{
+ if(z-1>=0){
+ String tmp1 = array[z];
+ String tmp2 = array[z-1];
+
+ String tmpstring2=(tmp2.concat(" ")).concat(tmp1);
+ String tmpstring1=tmp1;
+
+ //always looking for the "biggest" match
+
+ if(hm.get(tmpstring2)!=null){
+ result_array[z]=zaehler;
+ result_array[z-1]=zaehler;
+ zaehler++;
+ }
+ else{
+ if(hm.get(tmpstring1)!=null){
+ result_array[z]=zaehler;
+ zaehler++;
+ }
+ }
+ }
+ if(z==0){
+ if(hm.get(array[z])!=null){
+ result_array[z]=zaehler;
+ zaehler++;
+ }
+ }
+ }
+ }
+
+ System.out.println("###### Cluster ######");
+ for(int p =0;p<length;p++){
+ System.out.println(result_array[p]);
+ }
+ System.out.println("######");
+ */
+
+ //look, if the first word is a who!
+ if(array[0].contains("who")){
+ int position=0;
+ for(int i=0;i<array.length;i++){
+ if (array[i].contains("of")){
+ position=i;
+ break;
+ }
+ }
+ String vor_of=array[position-1];
+ String nach_of="";
+ //if there is only one element after of
+ if(array.length-position-1==1){
+ nach_of=array[position+1];
+ }
+ else{
+ for(int i=position+1; i<array.length;i++){
+ nach_of=(nach_of.concat(array[i])).concat(" ");
+ }
+
+ //delete last emty space
+ nach_of = nach_of.substring(0, nach_of.length()-1);
+ }
+ String uri_vor_of=" ";
+ String uri_nach_of=" ";
+
+ uri_vor_of=hm.get(vor_of);
+ uri_nach_of=hm.get(nach_of);
+ if(uri_vor_of!=null && uri_nach_of!=null){
+ uri_nach_of=uri_nach_of.replace("Category:", "");
+ uri_nach_of=uri_nach_of.replace("category:", "");
+
+ String anfrage;
+ anfrage="PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>select ?x where { <"+uri_nach_of+"> <"+uri_vor_of+"> ?x.}";
+
+ //if there is no answer from the server, start searching with wordnet
+ String result="";
+ result=sendServerQuestionRequest(anfrage);
+ if(result!="noanswer"){
+ System.out.println(result);
+ }
+ else{
+ long startTime = System.currentTimeMillis();
+
+ System.out.println("Get Propertys of "+nach_of);
+
+ //contains uri AND string, every second is the string
+ ArrayList<String> properties = new ArrayList<String>();
+ GetRessourcePropertys property = new GetRessourcePropertys();
+ try {
+ //using uri now, not the string
+ properties=property.getPropertys(hm.get(nach_of));
+ } catch (IOException e) {
+ // TODO Auto-generated catch block
+ e.printStackTrace();
+ }
+
+ System.out.println("Start Iterating Wordnet with "+vor_of+" and deept of "+iteration_deept);
+ ArrayList<String> semantics=new ArrayList<String>();
+ ArrayList<String> tmp_semantics=new ArrayList<String>();
+ ArrayList<String> result_SemanticsMatchProperties=new ArrayList<String>();
+ semantics.add(vor_of);
+ tmp_semantics=semantics;
+ for(int i=0;i<=iteration_deept;i++){
+
+ try {
+ tmp_semantics=getSemantics(tmp_semantics);
+ } catch (IOException e) {
+ // TODO Auto-generated catch block
+ e.printStackTrace();
+
+ }
+ //each word only one time
+ for(String k : tmp_semantics){
+ if(!semantics.contains(k)) semantics.add(k);
+ }
+
+ }
+ long endTime = System.currentTimeMillis();
+ System.out.println("Getting Properties and Semantics took "+(endTime-startTime) +" ms\n");
+
+ //TODO: Try, if it works, if you use only one loop: (b.lowerCase).contains(properties.get(h))
+ for(int h=1;h<properties.size()-2;h=h+2){
+ for(String b : semantics){
+ //System.out.println(properties.get(h));
+ //System.out.println(b);
+ if(properties.get(h).contains(b.toLowerCase())){
+ if(!result_SemanticsMatchProperties.contains(properties.get(h)))
+ result_SemanticsMatchProperties.add(properties.get(h));
+ }
+ }
+ }
+ for(String b : result_SemanticsMatchProperties){
+ vor_of=b.toLowerCase();
+ uri_vor_of=hm.get(vor_of);
+ if(uri_vor_of!=null){
+ anfrage="PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>select ?x where { <"+uri_nach_of+"> <"+uri_vor_of+"> ?x.}";
+ System.out.println("Answer with the property \" " + b + "\" :\n"+sendServerQuestionRequest(anfrage));
+ }
+ }
+ long endTime2 = System.currentTimeMillis();
+ System.out.println("Getting Properties, Semantics and Answer from server took "+(endTime2-startTime) +" ms");
+ }
+ }
+
+ }
+
+ }
+
+ private static ArrayList<String> getSemantics (ArrayList<String> semantics) throws IOException, JWNLException {
+ ArrayList<String> result = new ArrayList<String>();
+ for(String id :semantics){
+ List<String> array =wordnet.getRelatedNouns(id);
+ for(String i:array){
+ if(!result.contains(i))result.add(i);
+ }
+
+
+ }
+ return result;
+ }
+
+
+
+
+ private String sendServerQuestionRequest(String query){
+ //SPARQL-Endpoint of Semantic Computing Group
+ String tmp="http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query="+createServerRequest(query)+"&format=text%2Fhtml&debug=on&timeout=";
+ URL url;
+ InputStream is;
+ InputStreamReader isr;
+ BufferedReader r;
+ String str="";
+ String result="";
+
+ try {
+ url = new URL(tmp);
+ is = url.openStream();
+ isr = new InputStreamReader(is);
+ r = new BufferedReader(isr);
+ int counter=0;
+ do {
+ str = r.readLine();
+ if (str != null){
+ result=result.concat(str);
+ counter=counter+1;}
+ } while (str != null);
+
+ if(result.isEmpty()) System.out.println("HALOSHSS");
+ //TODO:if counter = 5 or less, there is an empty answer from the Server! Still to Verify!
+ if(counter<=5){
+ System.out.println("Empty Answer from Server");
+ return "noanswer";
+ }
+ } catch (MalformedURLException e) {
+ System.out.println("Must enter a valid URL");
+ } catch (IOException e) {
+ System.out.println("Can not connect");
+ }
+
+
+
+ return createAnswer(result);
+ }
+
+
+ private String createAnswer(String string){
+ string=string.replace("table","");
+ string=string.replace("<tr>", "");
+ string=string.replace("</tr>", "");
+ string=string.replace("</>","");
+ string=string.replace("<th>l</th>","");
+ string=string.replace("<th>x</th>","");
+ string=string.replace("< class=\"sparql\" border=\"1\">","");
+ string=string.replace("\n","");
+ string=string.replace(" ","");
+ string=string.replace("</td>","");
+ string=string.replace("<td>","");
+ return string;
+
+ }
+
+
+ private String createServerRequest(String query){
+ String anfrage=null;
+ anfrage=removeSpecialKeys(query);
+ anfrage=anfrage.replace("<","<");
+ anfrage=anfrage.replace("%gt;",">");
+ anfrage=anfrage.replace("&","&");
+ //anfrage=anfrage.replaceAll("#>","%23%3E%0D%0A%");
+ anfrage=anfrage.replace("#","%23");
+ anfrage=anfrage.replace(" ","+");
+ anfrage=anfrage.replace("/","%2F");
+ anfrage=anfrage.replace(":","%3A");
+ anfrage=anfrage.replace("?","%3F");
+ anfrage=anfrage.replace("$","%24");
+ //anfrage=anfrage.replaceAll("F>+","F%3E%0D%0A");
+ anfrage=anfrage.replace(">","%3E");
+ anfrage=anfrage.replace("<","%3C");
+ anfrage=anfrage.replace("\"","%22");
+ anfrage=anfrage.replace("\n","%0D%0A%09");
+ anfrage=anfrage.replace("%%0D%0A%09","%09");
+ anfrage=anfrage.replace("=","%3D");
+ anfrage=anfrage.replace("@","%40");
+ anfrage=anfrage.replace("&","%26");
+ anfrage=anfrage.replace("(","%28");
+ anfrage=anfrage.replace(")","%29");
+ anfrage=anfrage.replace("%3E%0D%0A%25","%3E");
+ //anfrage=anfrage.replaceAll("\n",".%0D%0A%09");
+ return anfrage;
+ }
+
+ private String removeSpecialKeys(String query){
+ query=query.replace("\\","");
+ //query=query.replaceAll("\a","");
+ query=query.replace("\b","");
+ query=query.replace("\f","");
+ query=query.replace("\r","");
+ query=query.replace("\t","");
+ // query=query.replaceAll("\v","");
+ return query;
+ }
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Levenshtein.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Levenshtein.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Levenshtein.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,60 @@
+package org.dllearner.algorithm.tbsl.exploration.exploration_main;
+
+
+import java.lang.Math;
+import java.math.BigDecimal;
+
+public class Levenshtein {
+
+
+ //http://de.wikipedia.org/wiki/Levenshtein-Distanz
+ public double nld(String orig, String eing){
+ int result = diff(orig,eing);
+ int length=Math.max(orig.length(),eing.length());
+
+
+ //if distance between both is zero, then the NLD must be one
+ if(result==0 ){
+ return 1;
+ }
+ else{
+ BigDecimal m = new BigDecimal(result);
+ BigDecimal n = new BigDecimal(length);
+
+ BigDecimal c = new BigDecimal(0);
+ c=m.divide(n, 5, BigDecimal.ROUND_FLOOR);
+
+ return c.doubleValue();
+ }
+
+ }
+
+ public int diff(String orig, String eing) {
+
+ int matrix[][] = new int[orig.length() + 1][eing.length() + 1];
+ for (int i = 0; i < orig.length() + 1; i++) {
+ matrix[i][0] = i;
+ }
+ for (int i = 0; i < eing.length() + 1; i++) {
+ matrix[0][i] = i;
+ }
+ for (int a = 1; a < orig.length() + 1; a++) {
+ for (int b = 1; b < eing.length() + 1; b++) {
+ int right = 0;
+ if (orig.charAt(a - 1) != eing.charAt(b - 1)) {
+ right = 1;
+ }
+ int mini = matrix[a - 1][b] + 1;
+ if (matrix[a][b - 1] + 1 < mini) {
+ mini = matrix[a][b - 1] + 1;
+ }
+ if (matrix[a - 1][b - 1] + right < mini) {
+ mini = matrix[a - 1][b - 1] + right;
+ }
+ matrix[a][b] = mini;
+ }
+ }
+
+ return matrix[orig.length()][eing.length()];
+ }
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Parsing.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Parsing.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/Parsing.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,19 @@
+package org.dllearner.algorithm.tbsl.exploration.exploration_main;
+import java.util.HashMap;
+
+
+public class Parsing {
+ public static void do_parsing(HashMap<String, String> hm, String string){
+ String [] array = string.split(" ");
+
+ for(String name : hm.values()){
+ //System.err.println(name);
+ for(String inhalt : array){
+ if(name.equals(inhalt)){
+ System.out.println("Super " + inhalt);
+ }
+ }
+ }
+
+ }
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/exploration_main.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/exploration_main.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/exploration_main.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,144 @@
+package org.dllearner.algorithm.tbsl.exploration.exploration_main;
+import java.io.BufferedReader;
+
+import java.io.FileInputStream;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.net.URL;
+import java.nio.channels.Channels;
+import java.nio.channels.ReadableByteChannel;
+import java.util.*;
+
+import net.didion.jwnl.JWNLException;
+
+import org.dllearner.algorithm.tbsl.exploration.Sparql.SparqlObject;
+import org.dllearner.algorithm.tbsl.exploration.sax.ParseXmlHtml;
+
+/*
+ *
+ * As you need more than 512 MB Ram, increase usable RAM for Java
+ * in Eclipse Run -> RunConfigurations -> Arguments -> VM Arguments -> -Xmx1024m
+ */
+
+// Sax example from http://www.bennyn.de/programmierung/java/java-xml-sax-parser.html
+
+/*
+ *
+ * eins:http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=SELECT+DISTINCT+%3Fx+%3Fl++WHERE+{%0D%0A++%3Fx+rdf%3Atype+%3Fc+.%0D%0A++%3Fx+rdfs%3Alabel+%3Fl+.%0D%0A++FILTER+%28lang%28%3Fl%29+%3D+%27en%27%29%0D%0A}&format=text%2Fhtml&debug=on&timeout=
+ * zwei:http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=SELECT+DISTINCT+%3Fc+%3Fl++WHERE+{%0D%0A++%3Fx+rdf%3Atype+%3Fc+.%0D%0A++%3Fc+rdfs%3Alabel+%3Fl+.%0D%0A++FILTER+%28lang%28%3Fl%29+%3D+%27en%27%29%0D%0A}&format=text%2Fhtml&debug=on&timeout=
+ *
+ */
+public class exploration_main {
+
+ private static HashMap<String, String> hm = new HashMap<String, String>();
+ private static String qaldEntity2="http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=SELECT+DISTINCT+%3Fc+%3Fl++WHERE+{%0D%0A++%3Fx+rdf%3Atype+%3Fc+.%0D%0A++%3Fc+rdfs%3Alabel+%3Fl+.%0D%0A++FILTER+%28lang%28%3Fl%29+%3D+%27en%27%29%0D%0A}&format=text%2Fhtml&debug=on&timeout=";
+ private static String qaldEntity1="http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=SELECT+DISTINCT+%3Fx+%3Fl++WHERE+{%0D%0A++%3Fx+rdf%3Atype+%3Fc+.%0D%0A++%3Fx+rdfs%3Alabel+%3Fl+.%0D%0A++FILTER+%28lang%28%3Fl%29+%3D+%27en%27%29%0D%0A}&format=text%2Fhtml&debug=on&timeout=";
+ /**
+ * @param args
+ * @throws IOException
+ * @throws JWNLException
+ * @throws InterruptedException
+ */
+ public static void main(String[] args) throws IOException, JWNLException, InterruptedException {
+
+ /**
+ * Do the starting initializing stuff
+ */
+ long startInitTime = System.currentTimeMillis();
+
+ System.out.println("Start Indexing");
+
+ //For testing!
+ hm=ParseXmlHtml.parse_xml("/home/swalter/workspace/ressource/sparql_zwei",hm);
+ hm=ParseXmlHtml.parse_xml("/home/swalter/workspace/ressource/sparql_eins",hm);
+
+
+ /*
+ * For real use!
+ */
+ /* hm=ParseXmlHtml.parse_xml((getEntity(qaldEntity2,"/tmp/qaldEntity2")),hm);
+ System.out.println("Entity2 done");
+ hm=ParseXmlHtml.parse_xml((getEntity(qaldEntity1,"/tmp/qaldEntity1")),hm);
+ System.out.println("Entity1 done");*/
+ System.out.println("Done with indexing\n");
+ System.out.println("Start generating Wordnet Dictionary");
+ SparqlObject sparql = new SparqlObject();
+ System.out.println("Generating Wordnet Dictionary Done");
+ long stopInitTime = System.currentTimeMillis();
+ System.out.println("Time for Initialising "+(stopInitTime-startInitTime)+" ms");
+
+ boolean schleife=true;
+ while(schleife==true){
+ BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
+ String line;
+ try {
+ System.out.println("\n\n");
+ System.out.println("Please enter a Question:");
+ line = in.readLine();
+ if(line.contains("quit")){
+ schleife=false;
+ System.out.println("Bye!");
+ }
+ if(line.contains("text")&& schleife==true){
+ TimeZone.setDefault(TimeZone.getTimeZone("GMT"));
+
+
+ System.out.println("Please enter Path of txt. File:");
+ line=in.readLine();
+
+ //Start Time measuring
+ long startTime = System.currentTimeMillis();
+ String s="";
+ BufferedReader in_file = new BufferedReader(new InputStreamReader(new FileInputStream(line)));
+ int anzahl=0;
+ while( null != (s = in_file.readLine()) ) {
+ System.out.println(s);
+ anzahl++;
+ //get each line and send it to the parser
+ s=s.replace("?","");
+ sparql.create_Sparql_query(s.toLowerCase(),hm);
+ }
+ long timeNow = System.currentTimeMillis();
+ long diff = timeNow-startTime;
+
+ System.out.println("Time for "+anzahl+" questions = "+diff+" ms.");
+
+ }
+ else if(schleife==true){
+ long startTime = System.currentTimeMillis();
+ line=line.replace("?","");
+ /* Set<BasicQueryTemplate> querytemps = btemplator.buildBasicQueries(line);
+ for (BasicQueryTemplate temp : querytemps) {
+ System.out.println(temp.toString());
+ }*/
+ sparql.create_Sparql_query(line.toLowerCase(),hm);
+ long endTime= System.currentTimeMillis();
+ System.out.println("\n The complete answering of the Question took "+(endTime-startTime)+" ms");
+ }
+
+ } catch (IOException e) {
+ // TODO Auto-generated catch block
+ e.printStackTrace();
+ }
+ }
+
+ }
+
+
+
+ private static String getEntity(String query, String name) throws IOException, InterruptedException{
+
+ // String query_complete="wget "+"\""+query+"\""+" -O "+"\""+name+"\"";
+ URL url = new URL(query);
+ ReadableByteChannel rbc = Channels.newChannel(url.openStream());
+ //System.out.println(rbc.toString());
+ FileOutputStream fos = new FileOutputStream(name);
+ //max 200MB = 209715200 Byte
+ fos.getChannel().transferFrom(rbc, 0, 209715200 );
+
+
+ return name;
+ }
+
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/test_vergleich.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/test_vergleich.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/exploration_main/test_vergleich.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,131 @@
+package org.dllearner.algorithm.tbsl.exploration.exploration_main;
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+
+import org.dllearner.algorithm.tbsl.exploration.sax.MySaxParser;
+
+
+/*
+ *
+ * wget "http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=PREFIX+rdfs%3A+%3Chttp%3A%2F%2Fwww.w3.org%2F2000%2F01%2Frdf-schema%23%3E%0D%0APREFIX+res%3A+%3Chttp%3A%2F%2Fdbpedia.org%2Fresource%2F%3E%0D%0A%0D%0ASELECT+DISTINCT+%3Fp+%3Fl+WHERE++{%0D%0A+{+res%3ABerlin+%3Fp+%3Fo+.+}%0D%0A+UNION%0D%0A+{+%3Fs+%3Fp+res%3ABerlin+.+}%0D%0A+{+%3Fp+rdfs%3Alabel+%3Fl+.+}%0D%0A}&format=text%2Fhtml&debug=on&timeout=" -O bla.txt
+
+ */
+public class test_vergleich {
+
+ public String DoVergleich(String suchbegriff, String vergleich) throws IOException{
+ String ergebnis_string="";
+ //sendServerRequest(vergleich);
+ sendServerRequest_new(vergleich);
+ ergebnis_string=do_parsing("answer",suchbegriff);
+
+ return ergebnis_string;
+
+
+ }
+
+ private void sendServerRequest(String vergleich) throws IOException{
+ String tmp="wget -O answer \"http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=PREFIX+rdfs%3A+%3Chttp%3A%2F%2Fwww.w3.org%2F2000%2F01%2Frdf-schema%23%3E%0D%0APREFIX+res%3A+%3Chttp%3A%2F%2Fdbpedia.org%2Fresource%2F%3E%0D%0A%0D%0ASELECT+DISTINCT+%3Fp+%3Fl+WHERE++{%0D%0A+{+res%3ABerlin+%3Fp+%3Fo+.+}%0D%0A+UNION%0D%0A+{+%3Fs+%3Fp+res%3A"+vergleich+"+.+}%0D%0A+{+%3Fp+rdfs%3Alabel+%3Fl+.+}%0D%0A}%0D%0A&format=text%2Fhtml&debug=on&timeout=\"";
+ //System.out.println(tmp);
+ Process p = Runtime.getRuntime().exec(tmp);
+ try {
+ p.waitFor();
+ } catch (InterruptedException e) {
+ // TODO Auto-generated catch block
+ e.printStackTrace();
+ }
+ }
+
+ private void sendServerRequest_new(String vergleich) throws IOException{
+ String tmp="http://greententacle.techfak.uni-bielefeld.de:5171/sparql?default-graph-uri=&query=PREFIX+rdfs%3A+%3Chttp%3A%2F%2Fwww.w3.org%2F2000%2F01%2Frdf-schema%23%3E%0D%0APREFIX+res%3A+%3Chttp%3A%2F%2Fdbpedia.org%2Fresource%2F%3E%0D%0A%0D%0ASELECT+DISTINCT+%3Fp+%3Fl+WHERE++{%0D%0A+{+res%3ABerlin+%3Fp+%3Fo+.+}%0D%0A+UNION%0D%0A+{+%3Fs+%3Fp+res%3A"+vergleich+"+.+}%0D%0A+{+%3Fp+rdfs%3Alabel+%3Fl+.+}%0D%0A}%0D%0A&format=text%2Fhtml&debug=on&timeout=";
+ URL url;
+ InputStream is;
+ InputStreamReader isr;
+ BufferedReader r;
+ String str;
+ String result="";
+
+ try {
+ url = new URL(tmp);
+ is = url.openStream();
+ isr = new InputStreamReader(is);
+ r = new BufferedReader(isr);
+ do {
+ str = r.readLine();
+ if (str != null)
+ result=result+str;
+ } while (str != null);
+ } catch (MalformedURLException e) {
+ System.out.println("Must enter a valid URL");
+ } catch (IOException e) {
+ System.out.println("Can not connect");
+ }
+
+ FileWriter w = new FileWriter("answer");
+ w.write(result);
+ w.close();
+ }
+
+
+ private static String do_parsing(String datei, String suchbergriff)
+ {
+ ArrayList<String> indexObject = null;
+ String ergebnis_uri="";
+ double zwischenwert=0;
+ double tmp=0;
+ Levenshtein levenshtein = new Levenshtein();
+
+ File file = new File(datei);
+ try
+ {
+ MySaxParser parser = new MySaxParser(file);
+ parser.parse();
+ indexObject = parser.getIndexObject();
+ for (int i = 1; i < indexObject.size(); i=i+2)
+ {
+ System.out.println((indexObject.get(i)).toLowerCase());
+ tmp = levenshtein.nld(suchbergriff.toLowerCase(), (indexObject.get(i)).toLowerCase());
+ System.out.println(tmp);
+ System.out.println("######");
+
+ String ergebnis_string;
+ if(tmp==1.0){
+ zwischenwert=tmp;
+ System.out.println(tmp);
+ System.out.println("YEAH!!!!");
+ ergebnis_string=indexObject.get(i);
+
+ ergebnis_uri=indexObject.get(i-1);
+ System.out.println(ergebnis_uri);
+ i=indexObject.size();
+ break;
+ }
+ if(tmp>zwischenwert){
+ zwischenwert=tmp;
+ System.out.println(tmp);
+ ergebnis_string=indexObject.get(i);
+
+ ergebnis_uri=indexObject.get(i-1);
+ System.out.println(ergebnis_uri);
+ }
+ }
+ indexObject.clear();
+
+ }
+ catch (Exception ex)
+ {
+ System.out.println("Another exciting error occured: " + ex.getLocalizedMessage());
+ }
+
+ return ergebnis_uri;
+ }
+
+
+
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxHandler.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxHandler.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxHandler.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,77 @@
+package org.dllearner.algorithm.tbsl.exploration.sax;
+
+import java.util.ArrayList;
+import org.xml.sax.Attributes;
+import org.xml.sax.SAXException;
+import org.xml.sax.helpers.DefaultHandler;
+
+public class MySaxHandler extends DefaultHandler
+{
+
+ private StringBuffer buffer;
+ private boolean buffering;
+ private ArrayList<String> indexObject;
+
+ public MySaxHandler()
+ {
+ this.buffer = null;
+ this.buffering = false;
+ indexObject = new ArrayList<String>();
+ }
+
+ @Override
+ public void startDocument() throws SAXException
+ {
+ this.buffer = new StringBuffer("");
+ }
+
+ @Override
+ public void startElement(String namespaceURI, String localName, String tagName, Attributes attributes) throws SAXException
+ {
+ String tag = tagName;
+ //name=td
+ if (tag.equals("td"))
+ {
+ this.buffering = true;
+ }
+ }
+
+ @Override
+ public void endElement(String namespaceURI, String localName, String tagName) throws SAXException
+ {
+ String tag = tagName;
+ String tagValue = null;
+
+ //name=td
+ if (tag.equals("td"))
+ {
+ tagValue = this.buffer.toString();
+ this.buffering = false;
+ this.buffer = new StringBuffer();
+ }
+
+ parseValue(tagValue);
+ }
+
+ @Override
+ public void characters(char chars[], int start, int length)
+ {
+ if (this.buffering)
+ {
+ this.buffer = this.buffer.append(chars, start, length);
+ }
+ }
+
+ private void parseValue(String value)
+ {
+ if (value != null)
+ {
+ this.indexObject.add(value);
+ }
+ }
+
+ public ArrayList<String> getIndexObject()
+ {
+ return this.indexObject;
+ }
+}
\ No newline at end of file
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxParser.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxParser.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/MySaxParser.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,51 @@
+package org.dllearner.algorithm.tbsl.exploration.sax;
+
+
+import java.io.File;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+import javax.xml.parsers.ParserConfigurationException;
+import javax.xml.parsers.SAXParser;
+import javax.xml.parsers.SAXParserFactory;
+import org.xml.sax.InputSource;
+import org.xml.sax.SAXException;
+import org.xml.sax.XMLReader;
+
+public class MySaxParser
+{
+ private URL url;
+ private ArrayList<String> indexObject;
+
+ public MySaxParser()
+ {
+ super();
+ }
+
+ public MySaxParser(File file) throws MalformedURLException
+ {
+ this.url = file.toURI().toURL();
+ }
+
+ public void parse() throws ParserConfigurationException, SAXException, IOException
+ {
+ // Initialize SAX Parser:
+ SAXParserFactory factory = SAXParserFactory.newInstance();
+ SAXParser parser = factory.newSAXParser();
+ XMLReader reader = parser.getXMLReader();
+ // Create SAX Handler:
+ MySaxHandler handler = new MySaxHandler();
+ reader.setContentHandler(handler);
+ // Parse XML file:
+ InputSource input = new InputSource(url.openStream());
+ reader.parse(input);
+ // Get the result:
+ this.indexObject = handler.getIndexObject();
+ }
+
+ public ArrayList<String> getIndexObject()
+ {
+ return this.indexObject;
+ }
+}
Added: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/ParseXmlHtml.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/ParseXmlHtml.java (rev 0)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/exploration/sax/ParseXmlHtml.java 2011-09-23 08:33:44 UTC (rev 3284)
@@ -0,0 +1,36 @@
+package org.dllearner.algorithm.tbsl.exploration.sax;
+
+import java.io.File;
+import java.util.ArrayList;
+import java.util.HashMap;
+
+public class ParseXmlHtml {
+ public static HashMap<String, String> parse_xml(String dateiname, HashMap<String, String> hm)
+ {
+ ArrayList<String> indexObject = null;
+ File file = new File(dateiname);
+ try
+ {
+ MySaxParser parser = new MySaxParser(file);
+ parser.parse();
+ indexObject = parser.getIndexObject();
+ /*for (int i = 0; i < indexObject.size(); i++)
+ {
+ hm.put((indexObject.get(i+1)).toLowerCase(), indexObject.get(i));
+ }*/
+ for (int i = 1; i < indexObject.size(); i=i+2)
+ {
+ hm.put((indexObject.get(i)).toLowerCase(), indexObject.get(i-1));
+ }
+ indexObject.clear();
+
+ }
+ catch (Exception ex)
+ {
+ System.out.println("Another exciting error occured: " + ex.getLocalizedMessage());
+ }
+ return hm;
+ }
+
+
+}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
