You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2011/01/19 13:05:00 UTC
svn commit: r1060779 - in /lucene/dev/trunk/lucene/contrib: CHANGES.txt
highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java
highlighter/src/test/org/apache/lucene/search/highlight/TokenSourcesTest.java
Author: rmuir
Date: Wed Jan 19 12:05:00 2011
New Revision: 1060779
URL: http://svn.apache.org/viewvc?rev=1060779&view=rev
Log:
LUCENE-2874: Highlighting overlapping tokens outputs doubled words
Added:
lucene/dev/trunk/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/TokenSourcesTest.java (with props)
Modified:
lucene/dev/trunk/lucene/contrib/CHANGES.txt
lucene/dev/trunk/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java
Modified: lucene/dev/trunk/lucene/contrib/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/CHANGES.txt?rev=1060779&r1=1060778&r2=1060779&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/CHANGES.txt (original)
+++ lucene/dev/trunk/lucene/contrib/CHANGES.txt Wed Jan 19 12:05:00 2011
@@ -140,6 +140,9 @@ Bug fixes
* LUCENE-591: The demo indexer now indexes meta keywords.
(Curtis d'Entremont via Robert Muir)
+
+ * LUCENE-2874: Highlighting overlapping tokens outputted doubled words.
+ (Pierre Gossé via Robert Muir)
API Changes
Modified: lucene/dev/trunk/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java?rev=1060779&r1=1060778&r2=1060779&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java (original)
+++ lucene/dev/trunk/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java Wed Jan 19 12:05:00 2011
@@ -233,7 +233,10 @@ public class TokenSources {
.size()]);
ArrayUtil.quickSort(tokensInOriginalOrder, new Comparator<Token>() {
public int compare(Token t1, Token t2) {
- return t1.startOffset() - t2.endOffset();
+ if (t1.startOffset() == t2.startOffset())
+ return t1.endOffset() - t2.endOffset();
+ else
+ return t1.startOffset() - t2.startOffset();
}
});
}
Added: lucene/dev/trunk/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/TokenSourcesTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/TokenSourcesTest.java?rev=1060779&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/TokenSourcesTest.java (added)
+++ lucene/dev/trunk/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/TokenSourcesTest.java Wed Jan 19 12:05:00 2011
@@ -0,0 +1,191 @@
+package org.apache.lucene.search.highlight;
+
+/**
+ * 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.Reader;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.document.Field.TermVector;
+import org.apache.lucene.index.CorruptIndexException;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.index.TermPositionVector;
+import org.apache.lucene.search.DisjunctionMaxQuery;
+import org.apache.lucene.search.IndexSearcher;
+import org.apache.lucene.search.TopDocs;
+import org.apache.lucene.search.spans.SpanTermQuery;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.LockObtainFailedException;
+import org.apache.lucene.util.LuceneTestCase;
+
+// LUCENE-2874
+public class TokenSourcesTest extends LuceneTestCase {
+ private static final String FIELD = "text";
+
+ private static final class OverlapAnalyzer extends Analyzer {
+
+ @Override
+ public TokenStream tokenStream(String fieldName, Reader reader) {
+ return new TokenStreamOverlap();
+ }
+ }
+
+ private static final class TokenStreamOverlap extends TokenStream {
+ private Token[] tokens;
+
+ private int i = -1;
+
+ private final CharTermAttribute termAttribute = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAttribute = addAttribute(OffsetAttribute.class);
+ private final PositionIncrementAttribute positionIncrementAttribute = addAttribute(PositionIncrementAttribute.class);
+
+ public TokenStreamOverlap() {
+ reset();
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ this.i++;
+ if (this.i >= this.tokens.length) {
+ return false;
+ }
+ clearAttributes();
+ termAttribute.setEmpty().append(this.tokens[i]);
+ offsetAttribute.setOffset(this.tokens[i].startOffset(),
+ this.tokens[i].endOffset());
+ positionIncrementAttribute.setPositionIncrement(this.tokens[i]
+ .getPositionIncrement());
+ return true;
+ }
+
+ @Override
+ public void reset() {
+ this.i = -1;
+ this.tokens = new Token[] {
+ new Token(new char[] { 't', 'h', 'e' }, 0, 3, 0, 3),
+ new Token(new char[] { '{', 'f', 'o', 'x', '}' }, 0, 5, 0, 7),
+ new Token(new char[] { 'f', 'o', 'x' }, 0, 3, 4, 7),
+ new Token(new char[] { 'd', 'i', 'd' }, 0, 3, 8, 11),
+ new Token(new char[] { 'n', 'o', 't' }, 0, 3, 12, 15),
+ new Token(new char[] { 'j', 'u', 'm', 'p' }, 0, 4, 16, 20) };
+ this.tokens[1].setPositionIncrement(0);
+ }
+ }
+
+ public void testOverlapWithOffset() throws CorruptIndexException,
+ LockObtainFailedException, IOException, InvalidTokenOffsetsException {
+ final String TEXT = "the fox did not jump";
+ final Directory directory = newDirectory();
+ final IndexWriter indexWriter = new IndexWriter(directory,
+ newIndexWriterConfig(TEST_VERSION_CURRENT, new OverlapAnalyzer()));
+ try {
+ final Document document = new Document();
+ document.add(new Field(FIELD, new TokenStreamOverlap(),
+ TermVector.WITH_OFFSETS));
+ indexWriter.addDocument(document);
+ } finally {
+ indexWriter.close();
+ }
+ final IndexReader indexReader = IndexReader.open(directory, true);
+ try {
+ assertEquals(1, indexReader.numDocs());
+ final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ try {
+ final DisjunctionMaxQuery query = new DisjunctionMaxQuery(1);
+ query.add(new SpanTermQuery(new Term(FIELD, "{fox}")));
+ query.add(new SpanTermQuery(new Term(FIELD, "fox")));
+ // final Query phraseQuery = new SpanNearQuery(new SpanQuery[] {
+ // new SpanTermQuery(new Term(FIELD, "{fox}")),
+ // new SpanTermQuery(new Term(FIELD, "fox")) }, 0, true);
+
+ TopDocs hits = indexSearcher.search(query, 1);
+ assertEquals(1, hits.totalHits);
+ final Highlighter highlighter = new Highlighter(
+ new SimpleHTMLFormatter(), new SimpleHTMLEncoder(),
+ new QueryScorer(query));
+ final TokenStream tokenStream = TokenSources
+ .getTokenStream(
+ (TermPositionVector) indexReader.getTermFreqVector(0, FIELD),
+ false);
+ assertEquals("<B>the fox</B> did not jump",
+ highlighter.getBestFragment(tokenStream, TEXT));
+ } finally {
+ indexSearcher.close();
+ }
+ } finally {
+ indexReader.close();
+ directory.close();
+ }
+ }
+
+ public void testOverlapWithPositionsAndOffset() throws CorruptIndexException,
+ LockObtainFailedException, IOException, InvalidTokenOffsetsException {
+ final String TEXT = "the fox did not jump";
+ final Directory directory = newDirectory();
+ final IndexWriter indexWriter = new IndexWriter(directory,
+ newIndexWriterConfig(TEST_VERSION_CURRENT, new OverlapAnalyzer()));
+ try {
+ final Document document = new Document();
+ document.add(new Field(FIELD, new TokenStreamOverlap(),
+ TermVector.WITH_POSITIONS_OFFSETS));
+ indexWriter.addDocument(document);
+ } finally {
+ indexWriter.close();
+ }
+ final IndexReader indexReader = IndexReader.open(directory, true);
+ try {
+ assertEquals(1, indexReader.numDocs());
+ final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ try {
+ final DisjunctionMaxQuery query = new DisjunctionMaxQuery(1);
+ query.add(new SpanTermQuery(new Term(FIELD, "{fox}")));
+ query.add(new SpanTermQuery(new Term(FIELD, "fox")));
+ // final Query phraseQuery = new SpanNearQuery(new SpanQuery[] {
+ // new SpanTermQuery(new Term(FIELD, "{fox}")),
+ // new SpanTermQuery(new Term(FIELD, "fox")) }, 0, true);
+
+ TopDocs hits = indexSearcher.search(query, 1);
+ assertEquals(1, hits.totalHits);
+ final Highlighter highlighter = new Highlighter(
+ new SimpleHTMLFormatter(), new SimpleHTMLEncoder(),
+ new QueryScorer(query));
+ final TokenStream tokenStream = TokenSources
+ .getTokenStream(
+ (TermPositionVector) indexReader.getTermFreqVector(0, FIELD),
+ false);
+ assertEquals("<B>the fox</B> did not jump",
+ highlighter.getBestFragment(tokenStream, TEXT));
+ } finally {
+ indexSearcher.close();
+ }
+ } finally {
+ indexReader.close();
+ directory.close();
+ }
+ }
+
+}