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

SOLR-3020: Add KeywordAttribute support to HunspellStemFilter 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1229519 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Simon Willnauer 2012-01-10 12:33:29 +00:00
parent 56a28c69f8
commit f19317d318
2 changed files with 67 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
modules/analysis/common/src/java/org/apache/lucene/analysis/hunspell/HunspellStemFilter.java
View File

@ -24,6 +24,7 @@ import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.hunspell.HunspellStemmer.Stem;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
/**
@ -34,6 +35,7 @@ public final class HunspellStemFilter extends TokenFilter {
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final PositionIncrementAttribute posIncAtt = addAttribute(PositionIncrementAttribute.class);
private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
private final HunspellStemmer stemmer;
private List<Stem> buffer;
@ -84,6 +86,10 @@ public final class HunspellStemFilter extends TokenFilter {
return false;
}
if (keywordAtt.isKeyword()) {
return true;
}
buffer = dedup ? stemmer.uniqueStems(termAtt.buffer(), termAtt.length()) : stemmer.stem(termAtt.buffer(), termAtt.length());
if (buffer.isEmpty()) { // we do not know this word, return it unchanged

61
modules/analysis/common/src/test/org/apache/lucene/analysis/hunspell/HunspellStemFilterTest.java Normal file
View File

@ -0,0 +1,61 @@
package org.apache.lucene.analysis.hunspell;
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.IOException;
import java.io.InputStream;
import java.io.StringReader;
import java.text.ParseException;
import java.util.Arrays;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
import org.junit.BeforeClass;
public class HunspellStemFilterTest extends BaseTokenStreamTestCase {
private static HunspellDictionary DICTIONARY;
@BeforeClass
public static void beforeClass() throws IOException, ParseException {
DICTIONARY = createDict(true);
}
public static HunspellDictionary createDict(boolean ignoreCase) throws IOException, ParseException {
InputStream affixStream = HunspellStemmerTest.class.getResourceAsStream("test.aff");
InputStream dictStream = HunspellStemmerTest.class.getResourceAsStream("test.dic");
return new HunspellDictionary(affixStream, dictStream, Version.LUCENE_40, ignoreCase);
}
/**
* Simple test for KeywordAttribute
*/
public void testKeywordAttribute() throws IOException {
MockTokenizer tokenizer = new MockTokenizer(new StringReader("lucene is awesome"), MockTokenizer.WHITESPACE, true);
tokenizer.setEnableChecks(true);
HunspellStemFilter filter = new HunspellStemFilter(tokenizer, DICTIONARY);
assertTokenStreamContents(filter, new String[]{"lucene", "lucen", "is", "awesome"}, new int[] {1, 0, 1, 1});
// assert with keywork marker
tokenizer = new MockTokenizer(new StringReader("lucene is awesome"), MockTokenizer.WHITESPACE, true);
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, Arrays.asList("Lucene"), true);
filter = new HunspellStemFilter(new KeywordMarkerFilter(tokenizer, set), DICTIONARY);
assertTokenStreamContents(filter, new String[]{"lucene", "is", "awesome"}, new int[] {1, 1, 1});
}
}