public class MultiDocumentHandler
extends java.lang.Object
Modifier and Type | Field and Description |
---|---|
private cern.colt.list.DoubleArrayList[] |
allscores |
private double |
degree |
private java.lang.Object[] |
itemNames |
private java.util.ArrayList<java.lang.String>[] |
parsedDocuments |
private java.util.ArrayList<java.lang.String> |
resultdoc |
private java.util.ArrayList<java.lang.String> |
resultfilenames |
private cern.colt.list.DoubleArrayList |
resultscores |
private static java.lang.String |
WORD_DELIMITER |
Constructor and Description |
---|
MultiDocumentHandler(java.lang.Object[] items,
java.util.ArrayList<java.lang.String>[] parsedDoc) |
Modifier and Type | Method and Description |
---|---|
(package private) void |
compareDocuments(int d1,
int d2) |
(package private) double |
computeSimilarity(java.lang.String sent,
java.lang.String sent2) |
void |
createAllResults(double threshold) |
(package private) void |
find_similarities(double degr)
identifies sentence similarity across documents; numdoc sets the minimum number of documents in which similarity
of sentence occurs; degree sets similarity degree;
|
java.util.ArrayList<java.lang.String> |
getResultDocs() |
java.util.ArrayList<java.lang.String> |
getResultFileNames() |
cern.colt.list.DoubleArrayList |
getResultScores() |
void |
removeRedundancy(java.util.ArrayList<java.lang.String> resultd,
cern.colt.list.DoubleArrayList resultsc,
java.util.ArrayList<java.lang.String> resultfile) |
(package private) void |
storeScores(cern.colt.list.DoubleArrayList[] scores) |
private static final java.lang.String WORD_DELIMITER
private java.util.ArrayList<java.lang.String>[] parsedDocuments
private cern.colt.list.DoubleArrayList[] allscores
private java.util.ArrayList<java.lang.String> resultdoc
private java.util.ArrayList<java.lang.String> resultfilenames
private cern.colt.list.DoubleArrayList resultscores
private double degree
private java.lang.Object[] itemNames
MultiDocumentHandler(java.lang.Object[] items, java.util.ArrayList<java.lang.String>[] parsedDoc)
public void createAllResults(double threshold)
public void removeRedundancy(java.util.ArrayList<java.lang.String> resultd, cern.colt.list.DoubleArrayList resultsc, java.util.ArrayList<java.lang.String> resultfile)
public java.util.ArrayList<java.lang.String> getResultDocs()
public cern.colt.list.DoubleArrayList getResultScores()
public java.util.ArrayList<java.lang.String> getResultFileNames()
void find_similarities(double degr)
void compareDocuments(int d1, int d2)
double computeSimilarity(java.lang.String sent, java.lang.String sent2)
void storeScores(cern.colt.list.DoubleArrayList[] scores)