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.FloatAssociationFacetField;
030import org.apache.lucene.facet.taxonomy.IntAssociationFacetField;
031import org.apache.lucene.facet.taxonomy.TaxonomyFacetSumFloatAssociations;
032import org.apache.lucene.facet.taxonomy.TaxonomyFacetSumIntAssociations;
033import org.apache.lucene.facet.taxonomy.TaxonomyReader;
034import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
035import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
036import org.apache.lucene.index.DirectoryReader;
037import org.apache.lucene.index.IndexWriter;
038import org.apache.lucene.index.IndexWriterConfig;
039import org.apache.lucene.index.IndexWriterConfig.OpenMode;
040import org.apache.lucene.search.IndexSearcher;
041import org.apache.lucene.search.MatchAllDocsQuery;
042import org.apache.lucene.store.ByteBuffersDirectory;
043import org.apache.lucene.store.Directory;
044
045/** Shows example usage of category associations. */
046public class AssociationsFacetsExample {
047
048  private final Directory indexDir = new ByteBuffersDirectory();
049  private final Directory taxoDir = new ByteBuffersDirectory();
050  private final FacetsConfig config;
051
052  /** Empty constructor */
053  public AssociationsFacetsExample() {
054    config = new FacetsConfig();
055    config.setMultiValued("tags", true);
056    config.setIndexFieldName("tags", "$tags");
057    config.setMultiValued("genre", true);
058    config.setIndexFieldName("genre", "$genre");
059  }
060
061  /** Build the example index. */
062  private void index() throws IOException {
063    IndexWriterConfig iwc =
064        new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE);
065    IndexWriter indexWriter = new IndexWriter(indexDir, iwc);
066
067    // Writes facet ords to a separate directory from the main index
068    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
069
070    Document doc = new Document();
071    // 3 occurrences for tag 'lucene'
072    doc.add(new IntAssociationFacetField(3, "tags", "lucene"));
073    // 87% confidence level of genre 'computing'
074    doc.add(new FloatAssociationFacetField(0.87f, "genre", "computing"));
075    indexWriter.addDocument(config.build(taxoWriter, doc));
076
077    doc = new Document();
078    // 1 occurrence for tag 'lucene'
079    doc.add(new IntAssociationFacetField(1, "tags", "lucene"));
080    // 2 occurrence for tag 'solr'
081    doc.add(new IntAssociationFacetField(2, "tags", "solr"));
082    // 75% confidence level of genre 'computing'
083    doc.add(new FloatAssociationFacetField(0.75f, "genre", "computing"));
084    // 34% confidence level of genre 'software'
085    doc.add(new FloatAssociationFacetField(0.34f, "genre", "software"));
086    indexWriter.addDocument(config.build(taxoWriter, doc));
087
088    indexWriter.close();
089    taxoWriter.close();
090  }
091
092  /** User runs a query and aggregates facets by summing their association values. */
093  private List<FacetResult> sumAssociations() throws IOException {
094    DirectoryReader indexReader = DirectoryReader.open(indexDir);
095    IndexSearcher searcher = new IndexSearcher(indexReader);
096    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
097
098    FacetsCollector fc = new FacetsCollector();
099
100    // MatchAllDocsQuery is for "browsing" (counts facets
101    // for all non-deleted docs in the index); normally
102    // you'd use a "normal" query:
103    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
104
105    Facets tags = new TaxonomyFacetSumIntAssociations("$tags", taxoReader, config, fc);
106    Facets genre = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
107
108    // Retrieve results
109    List<FacetResult> results = new ArrayList<>();
110    results.add(tags.getTopChildren(10, "tags"));
111    results.add(genre.getTopChildren(10, "genre"));
112
113    indexReader.close();
114    taxoReader.close();
115
116    return results;
117  }
118
119  /** User drills down on 'tags/solr'. */
120  private FacetResult drillDown() throws IOException {
121    DirectoryReader indexReader = DirectoryReader.open(indexDir);
122    IndexSearcher searcher = new IndexSearcher(indexReader);
123    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
124
125    // Passing no baseQuery means we drill down on all
126    // documents ("browse only"):
127    DrillDownQuery q = new DrillDownQuery(config);
128
129    // Now user drills down on Publish Date/2010:
130    q.add("tags", "solr");
131    FacetsCollector fc = new FacetsCollector();
132    FacetsCollector.search(searcher, q, 10, fc);
133
134    // Retrieve results
135    Facets facets = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
136    FacetResult result = facets.getTopChildren(10, "genre");
137
138    indexReader.close();
139    taxoReader.close();
140
141    return result;
142  }
143
144  /** Runs summing association example. */
145  public List<FacetResult> runSumAssociations() throws IOException {
146    index();
147    return sumAssociations();
148  }
149
150  /** Runs the drill-down example. */
151  public FacetResult runDrillDown() throws IOException {
152    index();
153    return drillDown();
154  }
155
156  /** Runs the sum int/float associations examples and prints the results. */
157  public static void main(String[] args) throws Exception {
158    System.out.println("Sum associations example:");
159    System.out.println("-------------------------");
160    List<FacetResult> results = new AssociationsFacetsExample().runSumAssociations();
161    System.out.println("tags: " + results.get(0));
162    System.out.println("genre: " + results.get(1));
163  }
164}