org.apache.lucene.analysis.ja
Class Token

java.lang.Object
  extended by org.apache.lucene.analysis.ja.Token

public class Token
extends Object

Analyzed token with morphological data from its dictionary.


Constructor Summary
Token(int wordId, char[] surfaceForm, int offset, int length, JapaneseTokenizer.Type type, int position, Dictionary dictionary)
           
 
Method Summary
 String getBaseForm()
           
 String getInflectionForm()
           
 String getInflectionType()
           
 int getLength()
           
 int getOffset()
           
 String getPartOfSpeech()
           
 int getPosition()
          Get index of this token in input text
 int getPositionLength()
          Get the length (in tokens) of this token.
 String getPronunciation()
           
 String getReading()
           
 char[] getSurfaceForm()
           
 String getSurfaceFormString()
           
 boolean isKnown()
          Returns true if this token is known word
 boolean isUnknown()
          Returns true if this token is unknown word
 boolean isUser()
          Returns true if this token is defined in user dictionary
 void setPositionLength(int positionLength)
          Set the position length (in tokens) of this token.
 String toString()
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Constructor Detail

Token

public Token(int wordId,
             char[] surfaceForm,
             int offset,
             int length,
             JapaneseTokenizer.Type type,
             int position,
             Dictionary dictionary)
Method Detail

toString

public String toString()
Overrides:
toString in class Object

getSurfaceForm

public char[] getSurfaceForm()
Returns:
surfaceForm

getOffset

public int getOffset()
Returns:
offset into surfaceForm

getLength

public int getLength()
Returns:
length of surfaceForm

getSurfaceFormString

public String getSurfaceFormString()
Returns:
surfaceForm as a String

getReading

public String getReading()
Returns:
reading. null if token doesn't have reading.

getPronunciation

public String getPronunciation()
Returns:
pronunciation. null if token doesn't have pronunciation.

getPartOfSpeech

public String getPartOfSpeech()
Returns:
part of speech.

getInflectionType

public String getInflectionType()
Returns:
inflection type or null

getInflectionForm

public String getInflectionForm()
Returns:
inflection form or null

getBaseForm

public String getBaseForm()
Returns:
base form or null if token is not inflected

isKnown

public boolean isKnown()
Returns true if this token is known word

Returns:
true if this token is in standard dictionary. false if not.

isUnknown

public boolean isUnknown()
Returns true if this token is unknown word

Returns:
true if this token is unknown word. false if not.

isUser

public boolean isUser()
Returns true if this token is defined in user dictionary

Returns:
true if this token is in user dictionary. false if not.

getPosition

public int getPosition()
Get index of this token in input text

Returns:
position of token

setPositionLength

public void setPositionLength(int positionLength)
Set the position length (in tokens) of this token. For normal tokens this is 1; for compound tokens it's > 1.


getPositionLength

public int getPositionLength()
Get the length (in tokens) of this token. For normal tokens this is 1; for compound tokens it's > 1.

Returns:
position length of token


Copyright © 2000-2013 Apache Software Foundation. All Rights Reserved.