sg.edu.nus.comp.nlp.ims.util
Class CSurroundingWordFilter

java.lang.Object
  extended by sg.edu.nus.comp.nlp.ims.util.CSurroundingWordFilter

public class CSurroundingWordFilter
extends java.lang.Object

filter stop words and words that contains no alphabet.

Author:
zhongzhi

Field Summary
protected static java.util.regex.Pattern ALPHABET
           
protected static CSurroundingWordFilter DEFAULT
           
protected  java.util.HashSet<java.lang.String> m_StopWords
           
 
Constructor Summary
protected CSurroundingWordFilter()
          constructor
  CSurroundingWordFilter(java.util.HashSet<java.lang.String> p_StopWords)
          constructor
  CSurroundingWordFilter(java.io.InputStream p_StopwordStream)
          constructor given stop word list
  CSurroundingWordFilter(java.lang.String p_StopwordFile)
          constructor given stop word list
 
Method Summary
 boolean filter(java.lang.String p_Word)
          check whether word is in stop word list or contains no alphabet
static CSurroundingWordFilter getInstance()
          get an surrouding word filter with default stop word list
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

DEFAULT

protected static CSurroundingWordFilter DEFAULT

ALPHABET

protected static java.util.regex.Pattern ALPHABET

m_StopWords

protected java.util.HashSet<java.lang.String> m_StopWords
Constructor Detail

CSurroundingWordFilter

protected CSurroundingWordFilter()
constructor


CSurroundingWordFilter

public CSurroundingWordFilter(java.util.HashSet<java.lang.String> p_StopWords)
constructor

Parameters:
p_StopWords - stop word list

CSurroundingWordFilter

public CSurroundingWordFilter(java.io.InputStream p_StopwordStream)
                       throws java.io.IOException
constructor given stop word list

Parameters:
p_StopwordStream - stop word inputstream
Throws:
java.io.IOException - exception while loading stop words

CSurroundingWordFilter

public CSurroundingWordFilter(java.lang.String p_StopwordFile)
                       throws java.io.IOException
constructor given stop word list

Parameters:
p_StopwordFile - stop word file
Throws:
java.io.IOException - exception while loading stop words
Method Detail

filter

public boolean filter(java.lang.String p_Word)
check whether word is in stop word list or contains no alphabet

Parameters:
p_Word - word
Returns:
true if it should be filtered, else false

getInstance

public static CSurroundingWordFilter getInstance()
get an surrouding word filter with default stop word list

Returns:
surrounding feature filter