1 package org.apache.lucene.facet.example.multiCL;
4 import java.util.Random;
6 import org.apache.lucene.document.Document;
7 import org.apache.lucene.document.Field;
8 import org.apache.lucene.document.Field.Index;
9 import org.apache.lucene.document.Field.Store;
10 import org.apache.lucene.index.IndexWriter;
11 import org.apache.lucene.index.IndexWriterConfig;
12 import org.apache.lucene.index.Term;
13 import org.apache.lucene.index.IndexWriterConfig.OpenMode;
14 import org.apache.lucene.store.Directory;
15 import org.apache.lucene.store.RAMDirectory;
17 import org.apache.lucene.DocumentBuilder;
18 import org.apache.lucene.facet.example.ExampleUtils;
19 import org.apache.lucene.facet.example.simple.SimpleUtils;
20 import org.apache.lucene.facet.index.CategoryDocumentBuilder;
21 import org.apache.lucene.facet.index.params.CategoryListParams;
22 import org.apache.lucene.facet.index.params.FacetIndexingParams;
23 import org.apache.lucene.facet.index.params.PerDimensionIndexingParams;
24 import org.apache.lucene.facet.taxonomy.CategoryPath;
25 import org.apache.lucene.facet.taxonomy.lucene.LuceneTaxonomyWriter;
28 * Licensed to the Apache Software Foundation (ASF) under one or more
29 * contributor license agreements. See the NOTICE file distributed with
30 * this work for additional information regarding copyright ownership.
31 * The ASF licenses this file to You under the Apache License, Version 2.0
32 * (the "License"); you may not use this file except in compliance with
33 * the License. You may obtain a copy of the License at
35 * http://www.apache.org/licenses/LICENSE-2.0
37 * Unless required by applicable law or agreed to in writing, software
38 * distributed under the License is distributed on an "AS IS" BASIS,
39 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
40 * See the License for the specific language governing permissions and
41 * limitations under the License.
45 * Sample indexer creates an index, and adds to it sample documents and facets
46 * with multiple CategoryLists specified for different facets, so there are different
47 * category lists for different facets.
49 * @lucene.experimental
51 public class MultiCLIndexer {
53 // Number of documents to index
54 public static int NUM_DOCS = 100;
55 // Number of facets to add per document
56 public static int NUM_FACETS_PER_DOC = 10;
57 // Number of tokens in title
58 public static int TITLE_LENGTH = 5;
59 // Number of tokens in text
60 public static int TEXT_LENGTH = 100;
62 // Lorum ipsum to use as content - this will be tokenized and used for document
64 static String words = "Sed ut perspiciatis unde omnis iste natus error sit "
65 + "voluptatem accusantium doloremque laudantium totam rem aperiam "
66 + "eaque ipsa quae ab illo inventore veritatis et quasi architecto "
67 + "beatae vitae dicta sunt explicabo Nemo enim ipsam voluptatem "
68 + "quia voluptas sit aspernatur aut odit aut fugit sed quia consequuntur "
69 + "magni dolores eos qui ratione voluptatem sequi nesciunt Neque porro "
70 + "quisquam est qui dolorem ipsum quia dolor sit amet consectetur adipisci velit "
71 + "sed quia non numquam eius modi tempora incidunt ut labore et dolore "
72 + "magnam aliquam quaerat voluptatem Ut enim ad minima veniam "
73 + "quis nostrum exercitationem ullam corporis suscipit laboriosam "
74 + "nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure"
75 + "reprehenderit qui in ea voluptate velit esse quam nihil molestiae "
76 + "consequatur vel illum qui dolorem eum fugiat quo voluptas nulla pariatur";
77 // PerDimensionIndexingParams for multiple category lists
78 public static PerDimensionIndexingParams MULTI_IPARAMS = new PerDimensionIndexingParams();
80 // Initialize PerDimensionIndexingParams
82 MULTI_IPARAMS.addCategoryListParams(new CategoryPath("0"),
83 new CategoryListParams(new Term("$Digits", "Zero")));
84 MULTI_IPARAMS.addCategoryListParams(new CategoryPath("1"),
85 new CategoryListParams(new Term("$Digits", "One")));
86 MULTI_IPARAMS.addCategoryListParams(new CategoryPath("2"),
87 new CategoryListParams(new Term("$Digits", "Two")));
88 MULTI_IPARAMS.addCategoryListParams(new CategoryPath("3"),
89 new CategoryListParams(new Term("$Digits", "Three")));
90 MULTI_IPARAMS.addCategoryListParams(new CategoryPath("4"),
91 new CategoryListParams(new Term("$Digits", "Four")));
92 MULTI_IPARAMS.addCategoryListParams(new CategoryPath("5"),
93 new CategoryListParams(new Term("$Digits", "Five")));
97 * Create an index, and adds to it sample documents and facets.
98 * @param indexDir Directory in which the index should be created.
99 * @param taxoDir Directory in which the taxonomy index should be created.
100 * @throws Exception on error (no detailed exception handling here for sample simplicity
102 public static void index(Directory indexDir, Directory taxoDir)
105 Random random = new Random(2003);
107 String[] docTitles = new String[NUM_DOCS];
108 String[] docTexts = new String[NUM_DOCS];
109 CategoryPath[][] cPaths = new CategoryPath[NUM_DOCS][NUM_FACETS_PER_DOC];
111 String[] tokens = words.split(" ");
112 for (int docNum = 0; docNum < NUM_DOCS; docNum++) {
115 for (int j = 0; j < TITLE_LENGTH; j++) {
116 title = title + tokens[random.nextInt(tokens.length)] + " ";
118 docTitles[docNum] = title;
120 for (int j = 0; j < TEXT_LENGTH; j++) {
121 text = text + tokens[random.nextInt(tokens.length)] + " ";
123 docTexts[docNum] = text;
125 for (int facetNum = 0; facetNum < NUM_FACETS_PER_DOC; facetNum++) {
126 cPaths[docNum][facetNum] = new CategoryPath(Integer
127 .toString(random.nextInt(7)), Integer.toString(random.nextInt(10)));
130 index(indexDir, taxoDir, MULTI_IPARAMS, docTitles, docTexts, cPaths);
134 * More advanced method for specifying custom indexing params, doc texts,
135 * doc titles and category paths.
137 public static void index(Directory indexDir, Directory taxoDir,
138 FacetIndexingParams iParams, String[] docTitles,
139 String[] docTexts, CategoryPath[][] cPaths) throws Exception {
140 // create and open an index writer
141 IndexWriter iw = new IndexWriter(indexDir, new IndexWriterConfig(
142 ExampleUtils.EXAMPLE_VER, SimpleUtils.analyzer).setOpenMode(OpenMode.CREATE));
143 // create and open a taxonomy writer
144 LuceneTaxonomyWriter taxo = new LuceneTaxonomyWriter(taxoDir, OpenMode.CREATE);
145 index(iw, taxo, iParams, docTitles, docTexts, cPaths);
149 * More advanced method for specifying custom indexing params, doc texts,
150 * doc titles and category paths.
152 * Create an index, and adds to it sample documents and facets.
154 * on error (no detailed exception handling here for sample
157 public static void index(IndexWriter iw, LuceneTaxonomyWriter taxo,
158 FacetIndexingParams iParams, String[] docTitles,
159 String[] docTexts, CategoryPath[][] cPaths) throws Exception {
161 // loop over sample documents
163 int nFacetsAdded = 0;
164 for (int docNum = 0; docNum < SimpleUtils.docTexts.length; docNum++) {
165 List<CategoryPath> facetList = SimpleUtils.categoryPathArrayToList(cPaths[docNum]);
167 // we do not alter indexing parameters!
168 // a category document builder will add the categories to a document
169 // once build() is called
170 DocumentBuilder categoryDocBuilder = new CategoryDocumentBuilder(
171 taxo, iParams).setCategoryPaths(facetList);
173 // create a plain Lucene document and add some regular Lucene fields
175 Document doc = new Document();
176 doc.add(new Field(SimpleUtils.TITLE, docTitles[docNum], Store.YES, Index.ANALYZED));
177 doc.add(new Field(SimpleUtils.TEXT, docTexts[docNum], Store.NO, Index.ANALYZED));
179 // finally add the document to the index
180 categoryDocBuilder.build(doc);
184 nFacetsAdded += facetList.size();
188 // we commit changes to the taxonomy index prior to committing them to
190 // this is important, so that all facets referred to by documents in the
192 // will indeed exist in the taxonomy index.
196 // close the taxonomy index and the index - all modifications are
197 // now safely in the provided directories: indexDir and taxoDir.
201 ExampleUtils.log("Indexed " + nDocsAdded + " documents with overall "
202 + nFacetsAdded + " facets.");
205 public static void main(String[] args) throws Exception {
206 index(new RAMDirectory(), new RAMDirectory());