idl.tmt.representation
Class BagOfWordsRepresentationBuilder

java.lang.Object
  |
  +--idl.tmt.representation.BagOfWordsRepresentationBuilder

All Implemented Interfaces:

RepresentationBuilder

Direct Known Subclasses:

BodyTextRepresentationBuilder, H1TextRepresentationBuilder, LinkTextRepresentationBuilder, MetaTextRepresentationBuilder, TitleTextRepresentationBuilder

public abstract class BagOfWordsRepresentationBuilder

extends java.lang.Object

implements RepresentationBuilder

Abstract representation builder to handle keeping track of the in-process document representations, and finalizing the TmtMatrix object. Created on Apr 7, 2004

Author:

jelsas

Field Summary

private boolean	binarize
private boolean	debug
private TmtMatrix	myMatrix
private int	numDocs
private java.util.HashMap	rep
private boolean	shareTermlist
private TermList	termList
protected TextDocumentParser	textParser
private double	weight

Constructor Summary

BagOfWordsRepresentationBuilder()

Method Summary

protected void	addTermToDocRepresentation(int docID, java.lang.String term)
protected void	buildRepresentation()
void	cleanup()
TmtMatrix	getRepresentation()
TermList	getTermList()
double	getWeight()
boolean	isBinarize()
boolean	isDebug()
boolean	isShareTermlist()
void	setBinarize(boolean binarize)
void	setDebug(boolean debug)
void	setNumDocuments(int numDocs)
void	setShareTermlist(boolean shareTermlist)
void	setTermList(TermList termList)
void	setTextParser(TextDocumentParser textParser)
void	setWeight(double weight)
java.lang.String	toString()

Methods inherited from class java.lang.Object

, clone, equals, finalize, getClass, hashCode, notify, notifyAll, registerNatives, wait, wait, wait

Field Detail

myMatrix

private TmtMatrix myMatrix

numDocs

private int numDocs

binarize

private boolean binarize

shareTermlist

private boolean shareTermlist

debug

private boolean debug

weight

private double weight

termList

private TermList termList

textParser

protected TextDocumentParser textParser

rep

private java.util.HashMap rep

Constructor Detail

BagOfWordsRepresentationBuilder

public BagOfWordsRepresentationBuilder()

Method Detail

setNumDocuments

public void setNumDocuments(int numDocs)

Specified by:

setNumDocuments in interface RepresentationBuilder

addTermToDocRepresentation

protected void addTermToDocRepresentation(int docID,
                                          java.lang.String term)

buildRepresentation

protected void buildRepresentation()

getRepresentation

public TmtMatrix getRepresentation()

Specified by:

getRepresentation in interface RepresentationBuilder

setTermList

public void setTermList(TermList termList)

getTermList

public TermList getTermList()

Specified by:

getTermList in interface RepresentationBuilder

setBinarize

public void setBinarize(boolean binarize)

isBinarize

public boolean isBinarize()

setWeight

public void setWeight(double weight)

Specified by:

setWeight in interface RepresentationBuilder

getWeight

public double getWeight()

Specified by:

getWeight in interface RepresentationBuilder

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

setShareTermlist

public void setShareTermlist(boolean shareTermlist)

isShareTermlist

public boolean isShareTermlist()

setTextParser

public void setTextParser(TextDocumentParser textParser)

cleanup

public void cleanup()

Specified by:

cleanup in interface RepresentationBuilder

setDebug

public void setDebug(boolean debug)

isDebug

public boolean isDebug()