Small changes

src/main/java/eu/fbk/hlt/nlp/cluster/Comparator.java

@@ -88,13 +88,14 @@ public void run() {
 					graph.add(i, j, Abbreviation.id);
 					//System.out.println("Abbreviation:" + kx_i.getText() + "\t" + kx_j.getText());
 				}
+				/*
 				// apply the Acronym criteria
 				else if (Acronym.evaluate(kx_i, kx_j)) {
-					// if (kxs.inDocument(kx_i, kx_j)) {
+					//if (keys.inDocument(kx_i, kx_j)) {
 					graph.add(i, j, Acronym.id);
 					//System.out.println("Acronym:" + kx_i.getText() + "\t" + kx_j.getText());
-					// }
-				}
+					//}
+				}*/
 				// apply the Entailment criteria
 				else if (Entailment.evaluate(kx_i, kx_j)) {
 					graph.add(i, j, Entailment.id);
@@ -108,7 +109,7 @@ else if (ModifierSwap.evaluate(kx_i, kx_j)) {
 				// apply the Singular/Plural criteria
 				else if (SingularPlural.evaluate(kx_i, kx_j)) {
 					graph.add(i, j, SingularPlural.id);
-					System.out.println("SingularPlural:" + kx_i.getText() + "\t" + kx_j.getText());
+					//System.out.println("SingularPlural:" + kx_i.getText() + "\t" + kx_j.getText());
 				}
 				// apply the Singular/Plural criteria
 				else if (PrepositionalVariant.evaluate(kx_i, kx_j)) {

src/main/java/eu/fbk/hlt/nlp/cluster/Runner.java

@@ -10,7 +10,11 @@
 import java.io.Writer;
 import java.util.ArrayList;
 import java.util.Date;
+import java.util.HashMap;
+import java.util.HashSet;
 import java.util.List;
+import java.util.Map;
+import java.util.Set;
 import java.util.concurrent.atomic.AtomicBoolean;
 import java.util.logging.Logger;
 
@@ -333,6 +337,10 @@ public void run() {
 	 */
 	public static void printGraphs(String graphs, Keyphrases keyphrases, String dirOut) throws Exception {
 
+		//Map<Integer,Integer> documentsDistributionInClusters = new HashMap<Integer,Integer>();
+		//Set<String> documentsCounts = new HashSet<String>();
+
+
 		StringBuilder out = new StringBuilder();
 		int nNodes = 0;
 		String[] splitGraphs = graphs.split("\n");
@@ -349,9 +357,21 @@ public static void printGraphs(String graphs, Keyphrases keyphrases, String dirO
 				fout.write(out.toString().substring(0, out.toString().length() - 1) + "\n");
 				fout.write("</KEC_graph>\n");
 				out = new StringBuilder();
+
+				/*
+				if (documentsDistributionInClusters.containsKey(documentsCounts.size())) {
+					int freq = documentsDistributionInClusters.get(documentsCounts.size()).intValue() + 1;
+					documentsDistributionInClusters.put(documentsCounts.size(), freq);
+				}
+				else {
+					int freq = 1;
+					documentsDistributionInClusters.put(documentsCounts.size(), freq);
+				}
+				documentsCounts = new HashSet<String>();*/
+
+
 				fout.close();
 				continue;
-
 			}
 			String[] splitLine = splitGraphs[i].split(" ");
 			if (splitLine.length == 1) {
@@ -371,6 +391,15 @@ public static void printGraphs(String graphs, Keyphrases keyphrases, String dirO
 				out.append("  <text>" + kx.getText() + "</text>\n");
 				out.append("  <ids>" + keyphrases.getIDs(kx) + "</ids>\n");
 				out.append(" </node>\n");
+
+				/*
+				String[] documents = keyphrases.getIDs(kx).split(" ");
+				for (int z = 0; z < documents.length; z++)
+					documentsCounts.add(documents[z]);
+					*/
+
+
+
 			} else {
 				int kxSourceID = Integer.parseInt(splitLine[0]);
 				int kxTargetID = Integer.parseInt(splitLine[1]);
@@ -379,6 +408,12 @@ public static void printGraphs(String graphs, Keyphrases keyphrases, String dirO
 						+ kxTargetID + "\"/>\n");
 			}
 		}
+
+		//System.out.println("Documents distriution in clusters");
+		//for (Integer freq : documentsDistributionInClusters.keySet()) {
+			//System.out.println(freq + "\t" + documentsDistributionInClusters.get(freq));
+		//}
+		//System.out.println("===================================");
 
 	}
 

src/main/java/eu/fbk/hlt/nlp/cluster/Token.java

@@ -57,13 +57,13 @@ else if (dots == 1 && this.characters >= 1)
 
 		// assign the wordnet PoS
 		if (this.PoS.startsWith("S") || this.PoS.startsWith("Y")) //- n (noun): SS,SP,SN,SPN,YA,YF
-			this.wordnetAnnotation = "n#" + this.lemma;
+			this.wordnetAnnotation = "n#" + this.lemma.toLowerCase();
 		else if (this.PoS.startsWith("V")) //- v (verb): VI,VI+E,VIY,VIY+E,VF,VF+E,VFY,VFY+E,VSP,VSP+E,VSPY,VSPY+E,VPP,VPP+E,VPPY,VPPY+E,VG,VG+E,VGY,VGY+E,VM,VM+E,VMY,VMY+E
-			this.wordnetAnnotation = "v#" + this.lemma;
+			this.wordnetAnnotation = "v#" + this.lemma.toLowerCase();
 		else if (this.PoS.startsWith("A") || this.PoS.startsWith("D")) // - a (adjective): AS,AP,AN,DS,DP,DN  
-			this.wordnetAnnotation = "a#" + this.lemma;
+			this.wordnetAnnotation = "a#" + this.lemma.toLowerCase();
 		else if (this.PoS.startsWith("B")) // - r (adverb): B
-			this.wordnetAnnotation = "r#" + this.lemma;
+			this.wordnetAnnotation = "r#" + this.lemma.toLowerCase();
 
 	}
 

src/main/java/eu/fbk/hlt/nlp/criteria/Synonym.java

@@ -38,28 +38,18 @@ public static boolean evaluate(Keyphrase key1, Keyphrase key2, Keyphrases keys)
 			return false;
 		}
 
-		//String pippo = null;
-
 		int synonymsCount = 0;
 		for (int i = 0; i < key1.length(); i++) {
 			if (key1.get(i).getForm().equals(key2.get(i).getForm())) {
 			}
 			else if (key1.get(i).getPoS().equals(key2.get(i).getPoS()) &&
 					keys.synonyms(key1.get(i), key2.get(i))) {
 				synonymsCount++;
-				//pippo = "trovato t:" + key1.getText() + "\t" + key2.getText();
-				//System.out.println("trovato:" + key1.getText() + "\t" + key2.getText());
-				//System.out.println("trovato t:" + key1.get(i).getForm() + "\t" + key2.get(i).getForm());
 			}
 			else
 				return false;
 		} 
 
-		if (synonymsCount == 1) {
-			//System.out.println(synonymsCount);
-			//System.out.println(pippo);;
-		}
-
 		return (synonymsCount == 1);
 
 	}