Mercurial > hg > duomoOWLProject

comparison src/de/mpiwg/dwinter/duomo/stanford/AnalyseWithEvents.java @ 9:4392a6adf85a default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
new version der label mit language tag
author dwinter
date Thu, 16 Aug 2012 11:40:17 +0200
parents 919e9f3b5efd
children
comparison
equal deleted inserted replaced
8:919e9f3b5efd 9:4392a6adf85a
10 import java.io.FileInputStream; 10 import java.io.FileInputStream;
11 import java.io.FileWriter; 11 import java.io.FileWriter;
12 import java.io.IOException; 12 import java.io.IOException;
13 import java.io.InputStreamReader; 13 import java.io.InputStreamReader;
14 import java.io.Reader; 14 import java.io.Reader;
15 import java.net.URLEncoder;
15 import java.util.ArrayList; 16 import java.util.ArrayList;
16 import java.util.Collection; 17 import java.util.Collection;
17 import java.util.HashMap; 18 import java.util.HashMap;
18 import java.util.HashSet; 19 import java.util.HashSet;
19 import java.util.List; 20 import java.util.List;
32 import edu.stanford.nlp.trees.GrammaticalStructureFactory; 33 import edu.stanford.nlp.trees.GrammaticalStructureFactory;
33 import edu.stanford.nlp.trees.PennTreebankLanguagePack; 34 import edu.stanford.nlp.trees.PennTreebankLanguagePack;
34 import edu.stanford.nlp.trees.Tree; 35 import edu.stanford.nlp.trees.Tree;
35 import edu.stanford.nlp.trees.TreebankLanguagePack; 36 import edu.stanford.nlp.trees.TreebankLanguagePack;
36 import edu.stanford.nlp.trees.TypedDependency; 37 import edu.stanford.nlp.trees.TypedDependency;
37
38 public class AnalyseWithEvents { 38 public class AnalyseWithEvents {
39 39
40 private int prepcount = 0;
41 private String prep_ent="http://entities.mpiwg-berlin.mpg.de/research/duomo/prep/";
42 private String prep_ont="http://ontologies.mpiwg-berlin.mpg.de/research/duomo/prep/";
40 public void analyse(String filename) throws IOException { 43 public void analyse(String filename) throws IOException {
41 44
42 LexicalizedParser lp = LexicalizedParser.loadModel("edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz"); 45 LexicalizedParser lp = LexicalizedParser.loadModel("edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz");
43 // This option shows loading and sentence-segment and tokenizing 46 // This option shows loading and sentence-segment and tokenizing
44 // a file using DocumentPreprocessor 47 // a file using DocumentPreprocessor
156 count++; 159 count++;
157 System.out.println(count); 160 System.out.println(count);
158 161
159 162
160 } 163 }
161 //if (count > 5) 164 // if (count > 100)
162 // break; 165 // break;
163 } 166 }
164 System.out.println(tuple); 167 System.out.println(tuple);
165 System.out.println(tupleLong); 168 System.out.println(tupleLong);
166 169
167 FileWriter fw = new FileWriter("/tmp/tuple"); 170 FileWriter fw = new FileWriter("/tmp/tuple");
173 } 176 }
174 fw.close(); 177 fw.close();
175 178
176 179
177 fw = new FileWriter("/tmp/tupleLong"); 180 fw = new FileWriter("/tmp/tupleLong");
178 181
182 FileWriter fw2 = new FileWriter("/tmp/tupleLong.nt3.rdf");
183
179 for (String key : tupleLong.keySet()){ 184 for (String key : tupleLong.keySet()){
180 List<String> val = tupleLong.get(key); 185 List<String> val = tupleLong.get(key);
181 186
182 fw.write(key+"\t"+String.valueOf(val.size())+"\t"+val.toString()+"\n"); 187 fw.write(key+"\t"+String.valueOf(val.size())+"\t"+val.toString()+"\n");
188 String res = writePrepAsTriple(fw2,key);
189 writeEventsToRes(fw2,res,val);
190
191
183 } 192 }
184 fw.close(); 193 fw.close();
185 194 fw2.close();
195
186 fw = new FileWriter("/tmp/words"); 196 fw = new FileWriter("/tmp/words");
187 197
188 for (String key : words.keySet()){ 198 for (String key : words.keySet()){
189 199
190 List<String> val = words.get(key); 200 List<String> val = words.get(key);
191 fw.write(key+"\t"+String.valueOf(val.size())+"\t"+val.toString()+"\n"); 201 fw.write(key+"\t"+String.valueOf(val.size())+"\t"+val.toString()+"\n");
192 } 202 }
193 fw.close(); 203 fw.close();
194 204
205 }
206 private void writeEventsToRes(FileWriter fw2, String prepUri, List<String> val) throws IOException {
207 for (String res :val){
208 fw2.write("<"+res.replace("\"", "")+"><"+prep_ont+"contains> <"+prepUri+">.\n");
209 }
210 fw2.flush();
211
212 }
213 private String writePrepAsTriple(FileWriter fw2, String prep) throws IOException {
214
215 String[] splitted = prep.split("\t");
216 prepcount+=1;
217 String resUri=String.format(prep_ent+"prep_%s",prepcount);
218 fw2.write("<"+resUri+ "> rdf:type "+"<"+prep_ont+"Preposition>.\n");
219
220 if (!splitted[2].equals("")){
221 String wd = URLEncoder.encode(splitted[2],"utf-8");
222 fw2.write("<"+resUri+ "> "+"<"+prep_ont+"main> <"+prep_ent+"Word_"+wd+">.\n");
223 fw2.write("<"+prep_ent+"Word_"+wd+"> rdfs:label \""+splitted[2]+"\"@en .\n");
224 fw2.write("<"+prep_ent+"Word_"+wd+"> rdf:type "+"<"+prep_ont+"Word>.\n");
225 }
226
227 if (!splitted[3].equals("")){
228 String wd = URLEncoder.encode(splitted[3],"utf-8");
229 fw2.write("<"+resUri+ "> "+"<"+prep_ont+"specification> <"+prep_ent+"Word_"+wd+">.\n");
230 fw2.write("<"+prep_ent+"Word_"+wd+"> rdfs:label \""+splitted[3]+"\"@en .\n");
231 fw2.write("<"+prep_ent+"Word_"+wd+"> rdf:type "+"<"+prep_ont+"Word>.\n");
232 }
233
234 if (!splitted[1].equals("")){
235 String wd = URLEncoder.encode(splitted[1],"utf-8");
236 fw2.write("<"+resUri+ "> "+"<"+prep_ont+"prepType> <"+prep_ent+"Type_"+wd+">.\n");
237 fw2.write("<"+prep_ent+"Type_"+wd+"> rdfs:label \""+splitted[1]+"\"@en .\n");
238 fw2.write("<"+prep_ent+"Word_"+wd+"> rdf:type "+"<"+prep_ont+"Type>.\n");
239 }
240
241 fw2.flush();
242 return resUri;
243
244
245
246
195 } 247 }
196 /** 248 /**
197 * @param args 249 * @param args
198 */ 250 */
199 public static void main(String[] args) { 251 public static void main(String[] args) {