edu.iastate.jtm
Class EntityFinder

java.lang.Object
  edu.iastate.jtm.gui.DefaultMonitorable
      edu.iastate.jtm.EntityFinder

All Implemented Interfaces:

Monitorable

Direct Known Subclasses:

Highlighter, MedCrawler

public class EntityFinder
extends DefaultMonitorable

Author:

dingjing

Nested Class Summary

class

EntityFinder.Hit

Field Summary

protected TrieDictionary	globalDic
protected EntityFinder.Hit[]	hits
protected AbstractDictionary	localDic
protected AbstractDictionary	peekDic
protected java.util.LinkedHashMap	peekRegex
protected PluralDetector	pluralDetector

Fields inherited from class edu.iastate.jtm.gui.DefaultMonitorable

message, monitorable, progress

Constructor Summary

EntityFinder()

EntityFinder(int ml, boolean skipSpace)
Creates a new instance of EntityFinder

Method Summary

int	findEntity(java.lang.CharSequence sen) Find entities in a string.
java.util.Set	getEntitiesFound()
int	getEntityCount()
TrieDictionary	getGlobalDictionary()
EntityFinder.Hit	getHit(int count)
int	getHitsCount()
PluralDetector	getPluralDetector()
java.lang.String	getTaggedText(java.lang.String tag, java.lang.String appendix, boolean addEqual)
int	getTotalHitsCount()
int	getTotalSenCount()
void	loadGlobalDictionary(java.io.File dic, boolean keyFirst)
void	loadPeekDefinition(java.io.File dic)
void	loadPluralDictionary(java.io.File dic)
void	loadPluralDictionary(java.net.URL dic)
void	outputHits()
void	setHitsThreshold(int t)
void	setMaxSentenceLength(int m)
void	setPeekNext(boolean p)
void	setRejectHits(boolean h)
void	setRejectLong(boolean r)
void	setVerbose(boolean v)

Methods inherited from class edu.iastate.jtm.gui.DefaultMonitorable

getMessage, getProgress, isDeterministic, isFinished, isMonitorable, isRunning, setMessage, setMonitorable, setProgress

Methods inherited from class java.lang.Object

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

Field Detail

pluralDetector

protected PluralDetector pluralDetector

globalDic

protected TrieDictionary globalDic

peekDic

protected AbstractDictionary peekDic

localDic

protected AbstractDictionary localDic

peekRegex

protected java.util.LinkedHashMap peekRegex

hits

protected EntityFinder.Hit[] hits

Constructor Detail

EntityFinder

public EntityFinder(int ml,
                    boolean skipSpace)

Creates a new instance of EntityFinder

Parameters:

skipSpace -

EntityFinder

public EntityFinder()

Method Detail

loadPluralDictionary

public void loadPluralDictionary(java.io.File dic)
                          throws java.io.IOException

Parameters:

dic -

Throws:

java.io.IOException

loadPluralDictionary

public void loadPluralDictionary(java.net.URL dic)
                          throws java.io.IOException

Throws:

java.io.IOException

getPluralDetector

public PluralDetector getPluralDetector()

loadGlobalDictionary

public void loadGlobalDictionary(java.io.File dic,
                                 boolean keyFirst)
                          throws java.io.IOException

Parameters:

dic -

keyFirst -

Throws:

java.io.IOException

getGlobalDictionary

public TrieDictionary getGlobalDictionary()

loadPeekDefinition

public void loadPeekDefinition(java.io.File dic)
                        throws java.io.IOException

Throws:

java.io.IOException

setVerbose

public void setVerbose(boolean v)

Parameters:

v -

setRejectLong

public void setRejectLong(boolean r)

setRejectHits

public void setRejectHits(boolean h)

setPeekNext

public void setPeekNext(boolean p)

setMaxSentenceLength

public void setMaxSentenceLength(int m)

setHitsThreshold

public void setHitsThreshold(int t)

getTotalHitsCount

public int getTotalHitsCount()

getHitsCount

public int getHitsCount()

getHit

public EntityFinder.Hit getHit(int count)

getTotalSenCount

public int getTotalSenCount()

getEntityCount

public int getEntityCount()

getEntitiesFound

public java.util.Set getEntitiesFound()

outputHits

public void outputHits()

getTaggedText

public java.lang.String getTaggedText(java.lang.String tag,
                                      java.lang.String appendix,
                                      boolean addEqual)

Parameters:

tag -

appendix -

Returns:

findEntity

public int findEntity(java.lang.CharSequence sen)

Find entities in a string. Abbreviations may be added into the local dictionary.

Parameters:

sen - String to be searched

Returns:

Number of entities found, not number of hits.