001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *     http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.lucene.demo.facet;
018
019import java.io.IOException;
020import java.util.ArrayList;
021import java.util.List;
022import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
023import org.apache.lucene.document.Document;
024import org.apache.lucene.facet.DrillDownQuery;
025import org.apache.lucene.facet.FacetResult;
026import org.apache.lucene.facet.Facets;
027import org.apache.lucene.facet.FacetsCollector;
028import org.apache.lucene.facet.FacetsConfig;
029import org.apache.lucene.facet.taxonomy.AssociationAggregationFunction;
030import org.apache.lucene.facet.taxonomy.FloatAssociationFacetField;
031import org.apache.lucene.facet.taxonomy.IntAssociationFacetField;
032import org.apache.lucene.facet.taxonomy.TaxonomyFacetFloatAssociations;
033import org.apache.lucene.facet.taxonomy.TaxonomyFacetIntAssociations;
034import org.apache.lucene.facet.taxonomy.TaxonomyReader;
035import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
036import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
037import org.apache.lucene.index.DirectoryReader;
038import org.apache.lucene.index.IndexWriter;
039import org.apache.lucene.index.IndexWriterConfig;
040import org.apache.lucene.index.IndexWriterConfig.OpenMode;
041import org.apache.lucene.search.IndexSearcher;
042import org.apache.lucene.search.MatchAllDocsQuery;
043import org.apache.lucene.store.ByteBuffersDirectory;
044import org.apache.lucene.store.Directory;
045import org.apache.lucene.util.IOUtils;
046
047/** Shows example usage of category associations. */
048public class AssociationsFacetsExample {
049
050  private final Directory indexDir = new ByteBuffersDirectory();
051  private final Directory taxoDir = new ByteBuffersDirectory();
052  private final FacetsConfig config;
053
054  /** Empty constructor */
055  public AssociationsFacetsExample() {
056    config = new FacetsConfig();
057    config.setMultiValued("tags", true);
058    config.setIndexFieldName("tags", "$tags");
059    config.setMultiValued("genre", true);
060    config.setIndexFieldName("genre", "$genre");
061  }
062
063  /** Build the example index. */
064  private void index() throws IOException {
065    IndexWriterConfig iwc =
066        new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE);
067    IndexWriter indexWriter = new IndexWriter(indexDir, iwc);
068
069    // Writes facet ords to a separate directory from the main index
070    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
071
072    Document doc = new Document();
073    // 3 occurrences for tag 'lucene'
074    doc.add(new IntAssociationFacetField(3, "tags", "lucene"));
075    // 87% confidence level of genre 'computing'
076    doc.add(new FloatAssociationFacetField(0.87f, "genre", "computing"));
077    indexWriter.addDocument(config.build(taxoWriter, doc));
078
079    doc = new Document();
080    // 1 occurrence for tag 'lucene'
081    doc.add(new IntAssociationFacetField(1, "tags", "lucene"));
082    // 2 occurrence for tag 'solr'
083    doc.add(new IntAssociationFacetField(2, "tags", "solr"));
084    // 75% confidence level of genre 'computing'
085    doc.add(new FloatAssociationFacetField(0.75f, "genre", "computing"));
086    // 34% confidence level of genre 'software'
087    doc.add(new FloatAssociationFacetField(0.34f, "genre", "software"));
088    indexWriter.addDocument(config.build(taxoWriter, doc));
089
090    IOUtils.close(indexWriter, taxoWriter);
091  }
092
093  /** User runs a query and aggregates facets by summing their association values. */
094  private List<FacetResult> sumAssociations() throws IOException {
095    DirectoryReader indexReader = DirectoryReader.open(indexDir);
096    IndexSearcher searcher = new IndexSearcher(indexReader);
097    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
098
099    FacetsCollector fc = new FacetsCollector();
100
101    // MatchAllDocsQuery is for "browsing" (counts facets
102    // for all non-deleted docs in the index); normally
103    // you'd use a "normal" query:
104    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
105
106    Facets tags =
107        new TaxonomyFacetIntAssociations(
108            "$tags", taxoReader, config, fc, AssociationAggregationFunction.SUM);
109    Facets genre =
110        new TaxonomyFacetFloatAssociations(
111            "$genre", taxoReader, config, fc, AssociationAggregationFunction.SUM);
112
113    // Retrieve results
114    List<FacetResult> results = new ArrayList<>();
115    results.add(tags.getTopChildren(10, "tags"));
116    results.add(genre.getTopChildren(10, "genre"));
117
118    IOUtils.close(indexReader, taxoReader);
119
120    return results;
121  }
122
123  /** User drills down on 'tags/solr'. */
124  private FacetResult drillDown() throws IOException {
125    DirectoryReader indexReader = DirectoryReader.open(indexDir);
126    IndexSearcher searcher = new IndexSearcher(indexReader);
127    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
128
129    // Passing no baseQuery means we drill down on all
130    // documents ("browse only"):
131    DrillDownQuery q = new DrillDownQuery(config);
132
133    // Now user drills down on Publish Date/2010:
134    q.add("tags", "solr");
135    FacetsCollector fc = new FacetsCollector();
136    FacetsCollector.search(searcher, q, 10, fc);
137
138    // Retrieve results
139    Facets facets =
140        new TaxonomyFacetFloatAssociations(
141            "$genre", taxoReader, config, fc, AssociationAggregationFunction.SUM);
142    FacetResult result = facets.getTopChildren(10, "genre");
143
144    IOUtils.close(indexReader, taxoReader);
145
146    return result;
147  }
148
149  /** Runs summing association example. */
150  public List<FacetResult> runSumAssociations() throws IOException {
151    index();
152    return sumAssociations();
153  }
154
155  /** Runs the drill-down example. */
156  public FacetResult runDrillDown() throws IOException {
157    index();
158    return drillDown();
159  }
160
161  /** Runs the sum int/float associations examples and prints the results. */
162  public static void main(String[] args) throws Exception {
163    System.out.println("Sum associations example:");
164    System.out.println("-------------------------");
165    List<FacetResult> results = new AssociationsFacetsExample().runSumAssociations();
166    System.out.println("tags: " + results.get(0));
167    System.out.println("genre: " + results.get(1));
168  }
169}