Trejkaz created LUCENE-5905:
-------------------------------
Summary: Different behaviour of JapaneseAnalyzer at indexing time
vs. at search time
Key: LUCENE-5905
URL: https://issues.apache.org/jira/browse/LUCENE-5905
Project: Lucene - Core
Issue Type: Bug
Components: modules/analysis
Affects Versions: 4.9, 3.6.2
Environment: Java 8u5
Reporter: Trejkaz
A document with the word 秋葉原 in the body, when analysed by the JapaneseAnalyzer
(AKA Kuromoji), cannot be found when searching for the same text as a phrase
query.
Two programs are provided to reproduce the issue. Both programs print out the
term docs and positions and then the result of parsing the phrase query.
As shown by the output, at analysis time, there is a lone Japanese term "秋葉原".
At query parsing time, there are *three* such terms - "秋葉" and "秋葉原" at
position 0 and "原" at position 1. Because all terms must be present for a
phrase query to be a match, the query never matches, which is quite a serious
issue for us.
*Any workarounds, no matter how hacky, would be extremely helpful at this
point.*
My guess is that this is a quirk with the analyser. If it happened with
StandardAnalyzer, surely someone would have discovered it before I did.
Lucene 3.6.2 reproduction:
{code:java}
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.ja.JapaneseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermEnum;
import org.apache.lucene.index.TermPositions;
import org.apache.lucene.queryParser.standard.StandardQueryParser;
import
org.apache.lucene.queryParser.standard.config.StandardQueryConfigHandler;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;
import static org.hamcrest.Matchers.*;
import static org.junit.Assert.*;
public class TestJapaneseAnalysis {
@Test
public void testJapaneseAnalysis() throws Exception {
try (Directory directory = new RAMDirectory()) {
Analyzer analyser = new JapaneseAnalyzer(Version.LUCENE_36);
try (IndexWriter writer = new IndexWriter(directory,
new IndexWriterConfig(Version.LUCENE_36, analyser))) {
Document document = new Document();
document.add(new Field("content", "blah blah
commercial blah blah \u79CB\u8449\u539F blah blah", Field.Store.NO,
Field.Index.ANALYZED));
writer.addDocument(document);
}
try (IndexReader reader = IndexReader.open(directory);
TermEnum terms = reader.terms(new Term("content", ""));
TermPositions termPositions = reader.termPositions()) {
do {
Term term = terms.term();
if (term.field() != "content") {
break;
}
System.out.println(term);
termPositions.seek(terms);
while (termPositions.next()) {
System.out.println(" " + termPositions.doc());
int freq = termPositions.freq();
for (int i = 0; i < freq; i++) {
System.out.println(" " +
termPositions.nextPosition());
}
}
}
while (terms.next());
StandardQueryParser queryParser = new
StandardQueryParser(analyser);
queryParser.setDefaultOperator(StandardQueryConfigHandler.Operator.AND);
// quoted to work around strange behaviour of
StandardQueryParser treating this as a boolean query.
Query query =
queryParser.parse("\"\u79CB\u8449\u539F\"", "content");
System.out.println(query);
TopDocs topDocs = new
IndexSearcher(reader).search(query, 10);
assertThat(topDocs.totalHits, is(1));
}
}
}
}
{code}
Lucene 4.9 reproduction:
{code:java}
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.ja.JapaneseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.AtomicReader;
import org.apache.lucene.index.AtomicReaderContext;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.DocsAndPositionsEnum;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.queryparser.flexible.standard.StandardQueryParser;
import
org.apache.lucene.queryparser.flexible.standard.config.StandardQueryConfigHandler;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Bits;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.Version;
public class LuceneMissingTerms {
public static void main(String[] args) throws Exception {
try (Directory directory = new RAMDirectory()) {
Analyzer analyser = new JapaneseAnalyzer(Version.LUCENE_4_9);
try (IndexWriter writer = new IndexWriter(directory,
new IndexWriterConfig(Version.LUCENE_4_9, analyser))) {
Document document = new Document();
document.add(new TextField("content", "blah blah
commercial blah blah \u79CB\u8449\u539F blah blah", Field.Store.NO));
writer.addDocument(document);
}
try (IndexReader multiReader =
DirectoryReader.open(directory)) {
for (AtomicReaderContext atomicReaderContext :
multiReader.leaves()) {
AtomicReader reader = atomicReaderContext.reader();
Terms terms =
MultiFields.getFields(reader).terms("content");
TermsEnum termsEnum = terms.iterator(null);
BytesRef text;
//noinspection NestedAssignment
while ((text = termsEnum.next()) != null) {
System.out.println("term: " + text.utf8ToString());
Bits liveDocs = reader.getLiveDocs();
DocsAndPositionsEnum docsAndPositionsEnum
= termsEnum.docsAndPositions(liveDocs, null);
int doc;
//noinspection NestedAssignment
while ((doc =
docsAndPositionsEnum.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
System.out.println(" doc: " + doc);
int freq = docsAndPositionsEnum.freq();
for (int i = 0; i < freq; i++) {
int pos =
docsAndPositionsEnum.nextPosition();
System.out.println(" pos: " + pos);
}
}
}
}
StandardQueryParser queryParser = new
StandardQueryParser(analyser);
queryParser.setDefaultOperator(StandardQueryConfigHandler.Operator.AND);
// quoted to work around strange behaviour of
StandardQueryParser treating this as a boolean query.
Query query =
queryParser.parse("\"\u79CB\u8449\u539F\"", "content");
System.out.println(query);
TopDocs topDocs = new
IndexSearcher(multiReader).search(query, 10);
System.out.println(topDocs.totalHits);
}
}
}
}
{code}
--
This message was sent by Atlassian JIRA
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org
For additional commands, e-mail: dev-h...@lucene.apache.org
