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.DrillSideways;
026import org.apache.lucene.facet.DrillSideways.DrillSidewaysResult;
027import org.apache.lucene.facet.FacetField;
028import org.apache.lucene.facet.FacetResult;
029import org.apache.lucene.facet.Facets;
030import org.apache.lucene.facet.FacetsCollector;
031import org.apache.lucene.facet.FacetsCollectorManager;
032import org.apache.lucene.facet.FacetsConfig;
033import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts;
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;
045
046/** Shows simple usage of faceted indexing and search. */
047public class SimpleFacetsExample {
048
049  private final Directory indexDir = new ByteBuffersDirectory();
050  private final Directory taxoDir = new ByteBuffersDirectory();
051  private final FacetsConfig config = new FacetsConfig();
052
053  /** Empty constructor */
054  public SimpleFacetsExample() {
055    config.setHierarchical("Publish Date", true);
056  }
057
058  /** Build the example index. */
059  void index() throws IOException {
060    IndexWriter indexWriter =
061        new IndexWriter(
062            indexDir, new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));
063
064    // Writes facet ords to a separate directory from the main index
065    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
066
067    Document doc = new Document();
068    doc.add(new FacetField("Author", "Bob"));
069    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
070    indexWriter.addDocument(config.build(taxoWriter, doc));
071
072    doc = new Document();
073    doc.add(new FacetField("Author", "Lisa"));
074    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
075    indexWriter.addDocument(config.build(taxoWriter, doc));
076
077    doc = new Document();
078    doc.add(new FacetField("Author", "Lisa"));
079    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
080    indexWriter.addDocument(config.build(taxoWriter, doc));
081
082    doc = new Document();
083    doc.add(new FacetField("Author", "Susan"));
084    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
085    indexWriter.addDocument(config.build(taxoWriter, doc));
086
087    doc = new Document();
088    doc.add(new FacetField("Author", "Frank"));
089    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
090    indexWriter.addDocument(config.build(taxoWriter, doc));
091
092    indexWriter.close();
093    taxoWriter.close();
094  }
095
096  /** User runs a query and counts facets. */
097  List<FacetResult> facetsWithSearch() throws IOException {
098    DirectoryReader indexReader = DirectoryReader.open(indexDir);
099    IndexSearcher searcher = new IndexSearcher(indexReader);
100    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
101
102    FacetsCollector fc = new FacetsCollector();
103
104    // MatchAllDocsQuery is for "browsing" (counts facets
105    // for all non-deleted docs in the index); normally
106    // you'd use a "normal" query:
107    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
108
109    // Retrieve results
110    List<FacetResult> results = new ArrayList<>();
111
112    // Count both "Publish Date" and "Author" dimensions
113    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
114    results.add(facets.getTopChildren(10, "Author"));
115    results.add(facets.getTopChildren(10, "Publish Date"));
116
117    indexReader.close();
118    taxoReader.close();
119
120    return results;
121  }
122
123  /** User runs a query and counts facets only without collecting the matching documents. */
124  private List<FacetResult> facetsOnly() throws IOException {
125    DirectoryReader indexReader = DirectoryReader.open(indexDir);
126    IndexSearcher searcher = new IndexSearcher(indexReader);
127    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
128
129    // MatchAllDocsQuery is for "browsing" (counts facets
130    // for all non-deleted docs in the index); normally
131    // you'd use a "normal" query:
132    FacetsCollector fc = searcher.search(new MatchAllDocsQuery(), new FacetsCollectorManager());
133
134    // Retrieve results
135    List<FacetResult> results = new ArrayList<>();
136
137    // Count both "Publish Date" and "Author" dimensions
138    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
139
140    results.add(facets.getTopChildren(10, "Author"));
141    results.add(facets.getTopChildren(10, "Publish Date"));
142
143    indexReader.close();
144    taxoReader.close();
145
146    return results;
147  }
148
149  /** User drills down on 'Publish Date/2010', and we return facets for 'Author' */
150  FacetResult drillDown() throws IOException {
151    DirectoryReader indexReader = DirectoryReader.open(indexDir);
152    IndexSearcher searcher = new IndexSearcher(indexReader);
153    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
154
155    // Passing no baseQuery means we drill down on all
156    // documents ("browse only"):
157    DrillDownQuery q = new DrillDownQuery(config);
158
159    // Now user drills down on Publish Date/2010:
160    q.add("Publish Date", "2010");
161    FacetsCollector fc = new FacetsCollector();
162    FacetsCollector.search(searcher, q, 10, fc);
163
164    // Retrieve results
165    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
166    FacetResult result = facets.getTopChildren(10, "Author");
167
168    indexReader.close();
169    taxoReader.close();
170
171    return result;
172  }
173
174  /**
175   * User drills down on 'Publish Date/2010', and we return facets for both 'Publish Date' and
176   * 'Author', using DrillSideways.
177   */
178  private List<FacetResult> drillSideways() throws IOException {
179    DirectoryReader indexReader = DirectoryReader.open(indexDir);
180    IndexSearcher searcher = new IndexSearcher(indexReader);
181    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
182
183    // Passing no baseQuery means we drill down on all
184    // documents ("browse only"):
185    DrillDownQuery q = new DrillDownQuery(config);
186
187    // Now user drills down on Publish Date/2010:
188    q.add("Publish Date", "2010");
189
190    DrillSideways ds = new DrillSideways(searcher, config, taxoReader);
191    DrillSidewaysResult result = ds.search(q, 10);
192
193    // Retrieve results
194    List<FacetResult> facets = result.facets.getAllDims(10);
195
196    indexReader.close();
197    taxoReader.close();
198
199    return facets;
200  }
201
202  /** Runs the search example. */
203  public List<FacetResult> runFacetOnly() throws IOException {
204    index();
205    return facetsOnly();
206  }
207
208  /** Runs the search example. */
209  public List<FacetResult> runSearch() throws IOException {
210    index();
211    return facetsWithSearch();
212  }
213
214  /** Runs the drill-down example. */
215  public FacetResult runDrillDown() throws IOException {
216    index();
217    return drillDown();
218  }
219
220  /** Runs the drill-sideways example. */
221  public List<FacetResult> runDrillSideways() throws IOException {
222    index();
223    return drillSideways();
224  }
225
226  /** Runs the search and drill-down examples and prints the results. */
227  public static void main(String[] args) throws Exception {
228    System.out.println("Facet counting example:");
229    System.out.println("-----------------------");
230    SimpleFacetsExample example = new SimpleFacetsExample();
231    List<FacetResult> results1 = example.runFacetOnly();
232    System.out.println("Author: " + results1.get(0));
233    System.out.println("Publish Date: " + results1.get(1));
234
235    System.out.println("Facet counting example (combined facets and search):");
236    System.out.println("-----------------------");
237    List<FacetResult> results = example.runSearch();
238    System.out.println("Author: " + results.get(0));
239    System.out.println("Publish Date: " + results.get(1));
240
241    System.out.println("Facet drill-down example (Publish Date/2010):");
242    System.out.println("---------------------------------------------");
243    System.out.println("Author: " + example.runDrillDown());
244
245    System.out.println("Facet drill-sideways example (Publish Date/2010):");
246    System.out.println("---------------------------------------------");
247    for (FacetResult result : example.runDrillSideways()) {
248      System.out.println(result);
249    }
250  }
251}