org.apache.lucene.benchmark.byTask.tasks.ReadTask Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of lucene-benchmark Show documentation
Apache Lucene (module: benchmark)
There is a newer version: 9.11.1
package org.apache.lucene.benchmark.byTask.tasks;

/*
 * 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.util.Collection;
import java.util.HashSet;

import java.util.List;
import java.util.Set;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.benchmark.byTask.PerfRunData;
import org.apache.lucene.benchmark.byTask.feeds.QueryMaker;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexableField;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.TopFieldCollector;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Sort;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.Bits;


/**
 * Read index (abstract) task.
 * Sub classes implement withSearch(), withWarm(), withTraverse() and withRetrieve()
 * methods to configure the actual action.
 * 
 * 
Note: All ReadTasks reuse the reader if it is already open.
 * Otherwise a reader is opened at start and closed at the end.
 * 

 * The search.num.hits config parameter sets
 * the top number of hits to collect during searching.  If
 * print.hits.field is set, then each hit is
 * printed along with the value of that field.
 *
 * Other side effects: none.
 */
public abstract class ReadTask extends PerfTask {

  private final QueryMaker queryMaker;

  public ReadTask(PerfRunData runData) {
    super(runData);
    if (withSearch()) {
      queryMaker = getQueryMaker();
    } else {
      queryMaker = null;
    }
  }
  @Override
  public int doLogic() throws Exception {
    int res = 0;

    // open reader or use existing one
    IndexSearcher searcher = getRunData().getIndexSearcher();

    IndexReader reader;

    final boolean closeSearcher;
    if (searcher == null) {
      // open our own reader
      Directory dir = getRunData().getDirectory();
      reader = DirectoryReader.open(dir);
      searcher = new IndexSearcher(reader);
      closeSearcher = true;
    } else {
      // use existing one; this passes +1 ref to us
      reader = searcher.getIndexReader();
      closeSearcher = false;
    }

    // optionally warm and add num docs traversed to count
    if (withWarm()) {
      Document doc = null;
      Bits liveDocs = MultiFields.getLiveDocs(reader);
      for (int m = 0; m < reader.maxDoc(); m++) {
        if (null == liveDocs || liveDocs.get(m)) {
          doc = reader.document(m);
          res += (doc == null ? 0 : 1);
        }
      }
    }

    if (withSearch()) {
      res++;
      Query q = queryMaker.makeQuery();
      Sort sort = getSort();
      TopDocs hits = null;
      final int numHits = numHits();
      if (numHits > 0) {
        if (withCollector() == false) {
          if (sort != null) {
            // TODO: instead of always passing false we
            // should detect based on the query; if we make
            // the IndexSearcher search methods that take
            // Weight public again, we can go back to
            // pulling the Weight ourselves:
            TopFieldCollector collector = TopFieldCollector.create(sort, numHits,
                                                                   true, withScore(),
                                                                   withMaxScore(),
                                                                   false);
            searcher.search(q, null, collector);
            hits = collector.topDocs();
          } else {
            hits = searcher.search(q, numHits);
          }
        } else {
          Collector collector = createCollector();
          searcher.search(q, null, collector);
          //hits = collector.topDocs();
        }

        final String printHitsField = getRunData().getConfig().get("print.hits.field", null);
        if (hits != null && printHitsField != null && printHitsField.length() > 0) {
          System.out.println("totalHits = " + hits.totalHits);
          System.out.println("maxDoc()  = " + reader.maxDoc());
          System.out.println("numDocs() = " + reader.numDocs());
          for(int i=0;i getFieldsToHighlight(Document document) {
    List fields = document.getFields();
    Set result = new HashSet(fields.size());
    for (final IndexableField f : fields) {
      result.add(f.name());
    }
    return result;
  }

}