1 package org.apache.lucene.index;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.IOException;
21 import java.io.Reader;
23 import org.apache.lucene.analysis.Analyzer;
24 import org.apache.lucene.analysis.MockAnalyzer;
25 import org.apache.lucene.analysis.TokenFilter;
26 import org.apache.lucene.analysis.TokenStream;
27 import org.apache.lucene.analysis.WhitespaceTokenizer;
28 import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
29 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
30 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
31 import org.apache.lucene.document.Document;
32 import org.apache.lucene.document.Field;
33 import org.apache.lucene.document.Fieldable;
34 import org.apache.lucene.document.Field.Index;
35 import org.apache.lucene.document.Field.Store;
36 import org.apache.lucene.document.Field.TermVector;
37 import org.apache.lucene.index.FieldInfo.IndexOptions;
38 import org.apache.lucene.store.Directory;
39 import org.apache.lucene.util.AttributeSource;
40 import org.apache.lucene.util.LuceneTestCase;
41 import org.apache.lucene.util._TestUtil;
43 public class TestDocumentWriter extends LuceneTestCase {
44 private Directory dir;
47 public void setUp() throws Exception {
53 public void tearDown() throws Exception {
59 assertTrue(dir != null);
62 public void testAddDocument() throws Exception {
63 Document testDoc = new Document();
64 DocHelper.setupDoc(testDoc);
65 IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random)));
66 writer.addDocument(testDoc);
68 SegmentInfo info = writer.newestSegment();
70 //After adding the document, we should be able to read it back in
71 SegmentReader reader = SegmentReader.get(true, info, IndexReader.DEFAULT_TERMS_INDEX_DIVISOR);
72 assertTrue(reader != null);
73 Document doc = reader.document(0);
74 assertTrue(doc != null);
76 //System.out.println("Document: " + doc);
77 Fieldable [] fields = doc.getFields("textField2");
78 assertTrue(fields != null && fields.length == 1);
79 assertTrue(fields[0].stringValue().equals(DocHelper.FIELD_2_TEXT));
80 assertTrue(fields[0].isTermVectorStored());
82 fields = doc.getFields("textField1");
83 assertTrue(fields != null && fields.length == 1);
84 assertTrue(fields[0].stringValue().equals(DocHelper.FIELD_1_TEXT));
85 assertFalse(fields[0].isTermVectorStored());
87 fields = doc.getFields("keyField");
88 assertTrue(fields != null && fields.length == 1);
89 assertTrue(fields[0].stringValue().equals(DocHelper.KEYWORD_TEXT));
91 fields = doc.getFields(DocHelper.NO_NORMS_KEY);
92 assertTrue(fields != null && fields.length == 1);
93 assertTrue(fields[0].stringValue().equals(DocHelper.NO_NORMS_TEXT));
95 fields = doc.getFields(DocHelper.TEXT_FIELD_3_KEY);
96 assertTrue(fields != null && fields.length == 1);
97 assertTrue(fields[0].stringValue().equals(DocHelper.FIELD_3_TEXT));
99 // test that the norms are not present in the segment if
101 for (int i = 0; i < reader.core.fieldInfos.size(); i++) {
102 FieldInfo fi = reader.core.fieldInfos.fieldInfo(i);
104 assertTrue(fi.omitNorms == !reader.hasNorms(fi.name));
110 public void testPositionIncrementGap() throws IOException {
111 Analyzer analyzer = new Analyzer() {
113 public TokenStream tokenStream(String fieldName, Reader reader) {
114 return new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader);
118 public int getPositionIncrementGap(String fieldName) {
123 IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
125 Document doc = new Document();
126 doc.add(newField("repeated", "repeated one", Field.Store.YES, Field.Index.ANALYZED));
127 doc.add(newField("repeated", "repeated two", Field.Store.YES, Field.Index.ANALYZED));
129 writer.addDocument(doc);
131 SegmentInfo info = writer.newestSegment();
133 SegmentReader reader = SegmentReader.get(true, info, IndexReader.DEFAULT_TERMS_INDEX_DIVISOR);
135 TermPositions termPositions = reader.termPositions(new Term("repeated", "repeated"));
136 assertTrue(termPositions.next());
137 int freq = termPositions.freq();
138 assertEquals(2, freq);
139 assertEquals(0, termPositions.nextPosition());
140 assertEquals(502, termPositions.nextPosition());
144 public void testTokenReuse() throws IOException {
145 Analyzer analyzer = new Analyzer() {
147 public TokenStream tokenStream(String fieldName, Reader reader) {
148 return new TokenFilter(new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader)) {
149 boolean first = true;
150 AttributeSource.State state;
153 public boolean incrementToken() throws IOException {
156 payloadAtt.setPayload(null);
157 posIncrAtt.setPositionIncrement(0);
158 termAtt.setEmpty().append("b");
163 boolean hasNext = input.incrementToken();
164 if (!hasNext) return false;
165 if (Character.isDigit(termAtt.buffer()[0])) {
166 posIncrAtt.setPositionIncrement(termAtt.buffer()[0] - '0');
169 // set payload on first position only
170 payloadAtt.setPayload(new Payload(new byte[]{100}));
174 // index a "synonym" for every token
175 state = captureState();
181 public void reset() throws IOException {
187 final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
188 final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
189 final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
194 IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
196 Document doc = new Document();
197 doc.add(newField("f1", "a 5 a a", Field.Store.YES, Field.Index.ANALYZED));
199 writer.addDocument(doc);
201 SegmentInfo info = writer.newestSegment();
203 SegmentReader reader = SegmentReader.get(true, info, IndexReader.DEFAULT_TERMS_INDEX_DIVISOR);
205 TermPositions termPositions = reader.termPositions(new Term("f1", "a"));
206 assertTrue(termPositions.next());
207 int freq = termPositions.freq();
208 assertEquals(3, freq);
209 assertEquals(0, termPositions.nextPosition());
210 assertEquals(true, termPositions.isPayloadAvailable());
211 assertEquals(6, termPositions.nextPosition());
212 assertEquals(false, termPositions.isPayloadAvailable());
213 assertEquals(7, termPositions.nextPosition());
214 assertEquals(false, termPositions.isPayloadAvailable());
219 public void testPreAnalyzedField() throws IOException {
220 IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(
221 TEST_VERSION_CURRENT, new MockAnalyzer(random)));
222 Document doc = new Document();
224 doc.add(new Field("preanalyzed", new TokenStream() {
225 private String[] tokens = new String[] {"term1", "term2", "term3", "term2"};
226 private int index = 0;
228 private CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
231 public boolean incrementToken() throws IOException {
232 if (index == tokens.length) {
236 termAtt.setEmpty().append(tokens[index++]);
243 writer.addDocument(doc);
245 SegmentInfo info = writer.newestSegment();
247 SegmentReader reader = SegmentReader.get(true, info, IndexReader.DEFAULT_TERMS_INDEX_DIVISOR);
249 TermPositions termPositions = reader.termPositions(new Term("preanalyzed", "term1"));
250 assertTrue(termPositions.next());
251 assertEquals(1, termPositions.freq());
252 assertEquals(0, termPositions.nextPosition());
254 termPositions.seek(new Term("preanalyzed", "term2"));
255 assertTrue(termPositions.next());
256 assertEquals(2, termPositions.freq());
257 assertEquals(1, termPositions.nextPosition());
258 assertEquals(3, termPositions.nextPosition());
260 termPositions.seek(new Term("preanalyzed", "term3"));
261 assertTrue(termPositions.next());
262 assertEquals(1, termPositions.freq());
263 assertEquals(2, termPositions.nextPosition());
268 * Test adding two fields with the same name, but
269 * with different term vector setting (LUCENE-766).
271 public void testMixedTermVectorSettingsSameField() throws Exception {
272 Document doc = new Document();
273 // f1 first without tv then with tv
274 doc.add(newField("f1", "v1", Store.YES, Index.NOT_ANALYZED, TermVector.NO));
275 doc.add(newField("f1", "v2", Store.YES, Index.NOT_ANALYZED, TermVector.WITH_POSITIONS_OFFSETS));
276 // f2 first with tv then without tv
277 doc.add(newField("f2", "v1", Store.YES, Index.NOT_ANALYZED, TermVector.WITH_POSITIONS_OFFSETS));
278 doc.add(newField("f2", "v2", Store.YES, Index.NOT_ANALYZED, TermVector.NO));
280 IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(
281 TEST_VERSION_CURRENT, new MockAnalyzer(random)));
282 writer.addDocument(doc);
285 _TestUtil.checkIndex(dir);
287 IndexReader reader = IndexReader.open(dir, true);
289 TermFreqVector tfv1 = reader.getTermFreqVector(0, "f1");
291 assertEquals("the 'with_tv' setting should rule!",2,tfv1.getTerms().length);
293 TermFreqVector tfv2 = reader.getTermFreqVector(0, "f2");
295 assertEquals("the 'with_tv' setting should rule!",2,tfv2.getTerms().length);
300 * Test adding two fields with the same name, one indexed
301 * the other stored only. The omitNorms and omitTermFreqAndPositions setting
302 * of the stored field should not affect the indexed one (LUCENE-1590)
304 public void testLUCENE_1590() throws Exception {
305 Document doc = new Document();
307 doc.add(newField("f1", "v1", Store.NO, Index.ANALYZED_NO_NORMS));
308 doc.add(newField("f1", "v2", Store.YES, Index.NO));
310 Field f = newField("f2", "v1", Store.NO, Index.ANALYZED);
311 f.setIndexOptions(IndexOptions.DOCS_ONLY);
313 doc.add(newField("f2", "v2", Store.YES, Index.NO));
315 IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(
316 TEST_VERSION_CURRENT, new MockAnalyzer(random)));
317 writer.addDocument(doc);
318 writer.optimize(); // be sure to have a single segment
321 _TestUtil.checkIndex(dir);
323 SegmentReader reader = SegmentReader.getOnlySegmentReader(dir);
324 FieldInfos fi = reader.fieldInfos();
326 assertFalse("f1 should have no norms", reader.hasNorms("f1"));
327 assertEquals("omitTermFreqAndPositions field bit should not be set for f1", IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, fi.fieldInfo("f1").indexOptions);
329 assertTrue("f2 should have norms", reader.hasNorms("f2"));
330 assertEquals("omitTermFreqAndPositions field bit should be set for f2", IndexOptions.DOCS_ONLY, fi.fieldInfo("f2").indexOptions);