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

LUCENE-3043: GermanStemmer threw IOOBE on zero-length tokens 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1096194 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2011-04-23 17:48:17 +00:00
parent c0c695053c
commit 7db98455e7
3 changed files with 11 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lucene/contrib/CHANGES.txt
View File

@ -55,6 +55,9 @@ Bug Fixes
when using CachingTokenStream. This can be a significant performance bug for when using CachingTokenStream. This can be a significant performance bug for
large documents. (Mark Miller) large documents. (Mark Miller)
* LUCENE-3043: GermanStemmer threw IndexOutOfBoundsException if it encountered
a zero-length token. (Robert Muir)
New Features New Features
* LUCENE-3016: Add analyzer for Latvian. (Robert Muir) * LUCENE-3016: Add analyzer for Latvian. (Robert Muir)

3
modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanStemmer.java
View File

@ -132,7 +132,8 @@ public class GermanStemmer
strip( buffer ); strip( buffer );
} }
// Additional step for irregular plural nouns like "Matrizen -> Matrix". // Additional step for irregular plural nouns like "Matrizen -> Matrix".
if ( buffer.charAt( buffer.length() - 1 ) == ( 'z' ) ) { // NOTE: this length constraint is probably not a great value, its just to prevent AIOOBE on empty terms
if ( buffer.length() > 0 && buffer.charAt( buffer.length() - 1 ) == ( 'z' ) ) {
buffer.setCharAt( buffer.length() - 1, 'x' ); buffer.setCharAt( buffer.length() - 1, 'x' );
} }
} }

8
modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilter.java
View File

@ -26,7 +26,6 @@ import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer; import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter; import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.util.ReusableAnalyzerBase; import org.apache.lucene.analysis.util.ReusableAnalyzerBase;
import org.junit.Ignore;
import static org.apache.lucene.analysis.util.VocabularyAssert.*; import static org.apache.lucene.analysis.util.VocabularyAssert.*;
@ -53,8 +52,13 @@ public class TestGermanStemFilter extends BaseTokenStreamTestCase {
vocOut.close(); vocOut.close();
} }
// LUCENE-3043: we use keywordtokenizer in this test,
// so ensure the stemmer does not crash on zero-length strings.
public void testEmpty() throws Exception {
assertAnalyzesTo(analyzer, "", new String[] { "" });
}
/** blast some random strings through the analyzer */ /** blast some random strings through the analyzer */
@Ignore("bugs!")
public void testRandomStrings() throws Exception { public void testRandomStrings() throws Exception {
checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER); checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
} }