この問題の解決策を見つけました。Highlighter
クラスの使用から の使用に変更しましたFastVectorHighlighter
。速度の改善も見られるようです (用語ベクトル データの保存を犠牲にして)。後でこの質問に出くわす人のために、これがどのように連携するかを示す単体テストを次に示します。
package com.sample.index;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.en.EnglishAnalyzer;
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.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.vectorhighlight.*;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import static junit.framework.Assert.assertEquals;
public class TestIndexStuff {
public static final String FIELD_NORMAL = "normal";
public static final String[] PRE_TAGS = new String[]{"["};
public static final String[] POST_TAGS = new String[]{"]"};
private IndexSearcher searcher;
private Analyzer analyzer = new EnglishAnalyzer(Version.LUCENE_35);
@Before
public void init() throws IOException {
RAMDirectory idx = new RAMDirectory();
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35, analyzer);
IndexWriter writer = new IndexWriter(idx, config);
addDocs(writer);
writer.close();
searcher = new IndexSearcher(IndexReader.open(idx));
}
private void addDocs(IndexWriter writer) throws IOException {
for (String text : new String[] {
"Pretty much everyone likes goats.",
"I have a goat that eats everything.",
"goats goats goats goats goats"}) {
Document doc = new Document();
doc.add(new Field(FIELD_NORMAL, text, Field.Store.YES,
Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
writer.addDocument(doc);
}
}
private FastVectorHighlighter makeHighlighter() {
FragListBuilder fragListBuilder = new SimpleFragListBuilder(200);
FragmentsBuilder fragmentBuilder = new SimpleFragmentsBuilder(PRE_TAGS, POST_TAGS);
return new FastVectorHighlighter(true, true, fragListBuilder, fragmentBuilder);
}
@Test
public void highlight() throws ParseException, IOException {
Query query = new QueryParser(Version.LUCENE_35, FIELD_NORMAL, analyzer)
.parse("goat");
FastVectorHighlighter highlighter = makeHighlighter();
FieldQuery fieldQuery = highlighter.getFieldQuery(query);
TopDocs topDocs = searcher.search(query, 10);
List<String> fragments = new ArrayList<String>();
for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
fragments.add(highlighter.getBestFragment(fieldQuery, searcher.getIndexReader(),
scoreDoc.doc, FIELD_NORMAL, 10000));
}
assertEquals(3, fragments.size());
assertEquals("[goats] [goats] [goats] [goats] [goats]", fragments.get(0).trim());
assertEquals("Pretty much everyone likes [goats].", fragments.get(1).trim());
assertEquals("I have a [goat] that eats everything.", fragments.get(2).trim());
}
}