Sebastian Yonekura Baeza created LUCENE-7704:
------------------------------------------------
Summary: SysnonymGraphFilter doesn't respect ignoreCase parameter
Key: LUCENE-7704
URL: https://issues.apache.org/jira/browse/LUCENE-7704
Project: Lucene - Core
Issue Type: Bug
Components: modules/analysis
Affects Versions: 6.4.1
Reporter: Sebastian Yonekura Baeza
Priority: Minor
Hi, it seems that SynonymGraphFilter doesn't respect ignoreCase parameter. In
particular this test doesn't pass:
{code:title=UppercaseSynonymMapTest.java|borderStyle=solid}
package com.mapcity.suggest.lucene;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.synonym.SynonymGraphFilter;
import org.apache.lucene.analysis.synonym.SynonymMap;
import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.CharsRefBuilder;
import org.junit.Test;
import java.io.IOException;
import static
org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents;
/**
* @author Sebastian Yonekura
* Created on 22-02-17
*/
public class UppercaseSynonymMapTest {
@Test
public void analyzerTest01() throws IOException {
// This passes
testAssertMapping("word", "synonym");
// this one not
testAssertMapping("word".toUpperCase(), "synonym");
}
private void testAssertMapping(String inputString, String outputString)
throws IOException {
SynonymMap.Builder builder = new SynonymMap.Builder(false);
CharsRef input = SynonymMap.Builder.join(inputString.split(" "), new
CharsRefBuilder());
CharsRef output = SynonymMap.Builder.join(outputString.split(" "), new
CharsRefBuilder());
builder.add(input, output, true);
Analyzer analyzer = new CustomAnalyzer(builder.build());
TokenStream tokenStream = analyzer.tokenStream("field", inputString);
assertTokenStreamContents(tokenStream, new String[]{
outputString, inputString
});
}
static class CustomAnalyzer extends Analyzer {
private SynonymMap synonymMap;
CustomAnalyzer(SynonymMap synonymMap) {
this.synonymMap = synonymMap;
}
@Override
protected TokenStreamComponents createComponents(String s) {
Tokenizer tokenizer = new WhitespaceTokenizer();
TokenStream tokenStream = new SynonymGraphFilter(tokenizer,
synonymMap, true); // Ignore case True
return new TokenStreamComponents(tokenizer, tokenStream);
}
}
}
{code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]