FileDocCategorySizeDatePackage
TestDocumentWriter.javaAPI DocApache Lucene 2.2.06237Sat Jun 16 22:20:28 BST 2007org.apache.lucene.index

TestDocumentWriter

public class TestDocumentWriter 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 RAMDirectory
dir
Constructors Summary
public TestDocumentWriter(String s)

    super(s);
  
Methods Summary
protected voidsetUp()

    dir = new RAMDirectory();
  
protected voidtearDown()


  
public voidtest()

    assertTrue(dir != null);

  
public voidtestAddDocument()

    Document testDoc = new Document();
    DocHelper.setupDoc(testDoc);
    Analyzer analyzer = new WhitespaceAnalyzer();
    Similarity similarity = Similarity.getDefault();
    DocumentWriter writer = new DocumentWriter(dir, analyzer, similarity, 50);
    String segName = "test";
    writer.addDocument(segName, testDoc);
    //After adding the document, we should be able to read it back in
    SegmentReader reader = SegmentReader.get(new SegmentInfo(segName, 1, dir));
    assertTrue(reader != null);
    Document doc = reader.document(0);
    assertTrue(doc != null);

    //System.out.println("Document: " + doc);
    Fieldable [] fields = doc.getFields("textField2");
    assertTrue(fields != null && fields.length == 1);
    assertTrue(fields[0].stringValue().equals(DocHelper.FIELD_2_TEXT));
    assertTrue(fields[0].isTermVectorStored());

    fields = doc.getFields("textField1");
    assertTrue(fields != null && fields.length == 1);
    assertTrue(fields[0].stringValue().equals(DocHelper.FIELD_1_TEXT));
    assertFalse(fields[0].isTermVectorStored());

    fields = doc.getFields("keyField");
    assertTrue(fields != null && fields.length == 1);
    assertTrue(fields[0].stringValue().equals(DocHelper.KEYWORD_TEXT));

    fields = doc.getFields(DocHelper.NO_NORMS_KEY);
    assertTrue(fields != null && fields.length == 1);
    assertTrue(fields[0].stringValue().equals(DocHelper.NO_NORMS_TEXT));

    fields = doc.getFields(DocHelper.TEXT_FIELD_3_KEY);
    assertTrue(fields != null && fields.length == 1);
    assertTrue(fields[0].stringValue().equals(DocHelper.FIELD_3_TEXT));

    // test that the norm file is not present if omitNorms is true
    for (int i = 0; i < reader.fieldInfos.size(); i++) {
      FieldInfo fi = reader.fieldInfos.fieldInfo(i);
      if (fi.isIndexed) {
        assertTrue(fi.omitNorms == !dir.fileExists(segName + ".f" + i));
      }
    }

  
public voidtestPositionIncrementGap()

    Analyzer analyzer = new Analyzer() {
      public TokenStream tokenStream(String fieldName, Reader reader) {
        return new WhitespaceTokenizer(reader);
      }

      public int getPositionIncrementGap(String fieldName) {
        return 500;
      }
    };

    Similarity similarity = Similarity.getDefault();
    DocumentWriter writer = new DocumentWriter(dir, analyzer, similarity, 50);
    Document doc = new Document();
    doc.add(new Field("repeated", "repeated one", Field.Store.YES, Field.Index.TOKENIZED));
    doc.add(new Field("repeated", "repeated two", Field.Store.YES, Field.Index.TOKENIZED));

    String segName = "test";
    writer.addDocument(segName, doc);
    SegmentReader reader = SegmentReader.get(new SegmentInfo(segName, 1, dir));

    TermPositions termPositions = reader.termPositions(new Term("repeated", "repeated"));
    assertTrue(termPositions.next());
    int freq = termPositions.freq();
    assertEquals(2, freq);
    assertEquals(0, termPositions.nextPosition());
    assertEquals(502, termPositions.nextPosition());
  
public voidtestPreAnalyzedField()

    Similarity similarity = Similarity.getDefault();
    DocumentWriter writer = new DocumentWriter(dir, new SimpleAnalyzer(), similarity, 50);
    Document doc = new Document();
    
    doc.add(new Field("preanalyzed", new TokenStream() {
      private String[] tokens = new String[] {"term1", "term2", "term3", "term2"};
      private int index = 0;
      
      public Token next() throws IOException {
        if (index == tokens.length) {
          return null;
        } else {
          return new Token(tokens[index++], 0, 0);
        }        
      }
      
    }, TermVector.NO));
    
    String segName = "test";
    writer.addDocument(segName, doc);
    SegmentReader reader = SegmentReader.get(new SegmentInfo(segName, 1, 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());