org.apache.lucene.benchmark.quality.QualityBenchmark Maven / Gradle / Ivy

/*
 * 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.
 */
package org.apache.lucene.benchmark.quality;

import java.io.IOException;
import java.io.PrintWriter;

import org.apache.lucene.benchmark.quality.utils.DocNameExtractor;
import org.apache.lucene.benchmark.quality.utils.SubmissionReport;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TopDocs;

/**
 * Main entry point for running a quality benchmark.
 * 
 * There are two main configurations for running a quality benchmark: 

 * Against existing judgements.
 * For submission (e.g. for a contest).
 * 
 * The first configuration requires a non null
 * {@link org.apache.lucene.benchmark.quality.Judge Judge}. 
 * The second configuration requires a non null 
 * {@link org.apache.lucene.benchmark.quality.utils.SubmissionReport SubmissionLogger}.
 */
public class QualityBenchmark {

  /** Quality Queries that this quality benchmark would execute. */
  protected QualityQuery qualityQueries[];
  
  /** Parser for turning QualityQueries into Lucene Queries. */
  protected QualityQueryParser qqParser;
  
  /** Index to be searched. */
  protected IndexSearcher searcher;

  /** index field to extract doc name for each search result; used for judging the results. */  
  protected String docNameField;
  
  /** maximal number of queries that this quality benchmark runs. Default: maxint. Useful for debugging. */
  private int maxQueries = Integer.MAX_VALUE;
  
  /** maximal number of results to collect for each query. Default: 1000. */
  private int maxResults = 1000;

  /**
   * Create a QualityBenchmark.
   * @param qqs quality queries to run.
   * @param qqParser parser for turning QualityQueries into Lucene Queries. 
   * @param searcher index to be searched.
   * @param docNameField name of field containing the document name.
   *        This allows to extract the doc name for search results,
   *        and is important for judging the results.  
   */
  public QualityBenchmark(QualityQuery qqs[], QualityQueryParser qqParser, 
      IndexSearcher searcher, String docNameField) {
    this.qualityQueries = qqs;
    this.qqParser = qqParser;
    this.searcher = searcher;
    this.docNameField = docNameField;
  }

  /**
   * Run the quality benchmark.
   * @param judge the judge that can tell if a certain result doc is relevant for a certain quality query. 
   *        If null, no judgements would be made. Usually null for a submission run. 
   * @param submitRep submission report is created if non null.
   * @param qualityLog If not null, quality run data would be printed for each query.
   * @return QualityStats of each quality query that was executed.
   * @throws Exception if quality benchmark failed to run.
   */
  public  QualityStats [] execute(Judge judge, SubmissionReport submitRep, 
                                  PrintWriter qualityLog) throws Exception {
    int nQueries = Math.min(maxQueries, qualityQueries.length);
    QualityStats stats[] = new QualityStats[nQueries]; 
    for (int i=0; i