Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add StopFilter makeStopSet methods that take a list, since we just call Arrays.asList() again anyway and we might already have a list 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@760058 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Grant Ingersoll 2009-03-30 17:26:55 +00:00
parent 7aa012ca27
commit c2b6731cc4
1 changed files with 26 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/java/org/apache/lucene/analysis/StopFilter.java
View File

@ -20,6 +20,7 @@ package org.apache.lucene.analysis;
import java.io.IOException;
import java.util.Arrays;
import java.util.Set;
import java.util.List;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
@ -112,8 +113,20 @@ public final class StopFilter extends TokenFilter {
}
/**
* Builds a Set from an array of stop words,
* appropriate for passing into the StopFilter constructor.
* This permits this stopWords construction to be cached once when
* an Analyzer is constructed.
*
* @param stopWords
* @see #makeStopSet(java.lang.String[], boolean) passing false to ignoreCase
*/
public static final Set makeStopSet(List/*<String>*/ stopWords) {
return makeStopSet(stopWords, false);
}
/**
*
* @param stopWords An array of stopwords
* @param ignoreCase If true, all words are lower cased first.
* @return a Set containing the words
*/
@ -123,6 +136,18 @@ public final class StopFilter extends TokenFilter {
return stopSet;
}
/**
*
* @param stopWords A List of Strings representing the stopwords
* @param ignoreCase if true, all words are lower cased first
* @return A Set containing the words
*/
public static final Set makeStopSet(List/*<String>*/ stopWords, boolean ignoreCase){
CharArraySet stopSet = new CharArraySet(stopWords.size(), ignoreCase);
stopSet.addAll(stopWords);
return stopSet;
}
/**
* Returns the next input Token whose term() is not a stop word.
*/