edkuksa/russianmorphology
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test for suffix evristics

Browse Source 
git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@12 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
alexander.a.kuznetsov 2009-04-13 14:11:45 +00:00
parent 48ae7d4cb6
commit 57b600d629
2 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyAnalayzer.java
View File

@ -2,6 +2,9 @@ package org.apache.lucene.russian.morphology.analayzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.standard.StandardFilter;
import java.io.Reader;
import java.io.IOException;
@ -14,6 +17,9 @@ public class RussianMorphlogyAnalayzer extends Analyzer {
}
public TokenStream tokenStream(String fieldName, Reader reader) {
return null; //To change body of implemented methods use File | Settings | File Templates.
TokenStream result = new StandardTokenizer(reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
return new RussianMorphlogyFilter(result,suffixEvristics);
}
}

4
src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyFilter.java
View File

@ -10,7 +10,7 @@ import java.io.IOException;
public class RussianMorphlogyFilter extends TokenFilter {
private SuffixEvristics suffixEvristics;
public RussianMorphlogyFilter(TokenStream tokenStream, SuffixEvristics suffixEvristics) throws IOException {
public RussianMorphlogyFilter(TokenStream tokenStream, SuffixEvristics suffixEvristics) {
super(tokenStream);
this.suffixEvristics = suffixEvristics;
}
@ -18,7 +18,7 @@ public class RussianMorphlogyFilter extends TokenFilter {
public Token next(final Token reusableToken) throws IOException {
Token nextToken = input.next(reusableToken);
if(nextToken == null || nextToken.term().length() == 0) return nextToken;
String word = nextToken.term().toLowerCase();
String word = nextToken.term();
Character testC = word.charAt(0);
if (Character.UnicodeBlock.of(testC) != Character.UnicodeBlock.CYRILLIC){
return nextToken;