FileDocCategorySizeDatePackage
TestCachingTokenFilter.javaAPI DocApache Lucene 2.2.03668Sat Jun 16 22:20:24 BST 2007org.apache.lucene.analysis

TestCachingTokenFilter

public class TestCachingTokenFilter extends TestCase
Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.

Fields Summary
private String[]
tokens
Constructors Summary
Methods Summary
private voidcheckTokens(org.apache.lucene.analysis.TokenStream stream)

    int count = 0;
    Token token;
    while ((token = stream.next()) != null) {
      assertTrue(count < tokens.length);
      assertEquals(tokens[count], token.termText);
      count++;
    }
    
    assertEquals(tokens.length, count);
public voidtestCaching()

  
       
    Directory dir = new RAMDirectory();
    IndexWriter writer = new IndexWriter(dir, new SimpleAnalyzer());
    Document doc = new Document();
    TokenStream stream = new TokenStream() {
      private int index = 0;
      
      public Token next() throws IOException {
        if (index == tokens.length) {
          return null;
        } else {
          return new Token(tokens[index++], 0, 0);
        }        
      }
      
    };
    
    stream = new CachingTokenFilter(stream);
    
    doc.add(new Field("preanalyzed", stream, TermVector.NO));
    
    // 1) we consume all tokens twice before we add the doc to the index
    checkTokens(stream);
    stream.reset();  
    checkTokens(stream);
    
    // 2) now add the document to the index and verify if all tokens are indexed
    //    don't reset the stream here, the DocumentWriter should do that implicitly
    writer.addDocument(doc);
    writer.close();
    
    IndexReader reader = IndexReader.open(dir);
    TermPositions termPositions = reader.termPositions(new Term("preanalyzed", "term1"));
    assertTrue(termPositions.next());
    assertEquals(1, termPositions.freq());
    assertEquals(0, termPositions.nextPosition());

    termPositions.seek(new Term("preanalyzed", "term2"));
    assertTrue(termPositions.next());
    assertEquals(2, termPositions.freq());
    assertEquals(1, termPositions.nextPosition());
    assertEquals(3, termPositions.nextPosition());
    
    termPositions.seek(new Term("preanalyzed", "term3"));
    assertTrue(termPositions.next());
    assertEquals(1, termPositions.freq());
    assertEquals(2, termPositions.nextPosition());
    reader.close();
    
    // 3) reset stream and consume tokens again
    stream.reset();
    checkTokens(stream);