Examples of org.apache.lucene.index.RandomIndexWriter

org.apache.lucene.index.RandomIndexWriter
Silly class that randomizes the indexing experience. EG it may swap in a different merge policy/scheduler; may commit periodically; may or may not optimize in the end, may flush by doc count instead of RAM, etc.

  }


  private Directory getIndexStore(String field, String[] contents)
      throws IOException {
    Directory indexStore = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random, indexStore);
    for (int i = 0; i < contents.length; ++i) {
      Document doc = new Document();
      doc.add(newField(field, contents[i], Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.close();


    return indexStore;
  }

View Full Code Here

        {"*o*", "*op*", "*opq**", "op*q*", "*u?", "*t?1", "opq**"}, // these should find only doc 2
    };


    // prepare the index
    Directory dir = newDirectory();
    RandomIndexWriter iw = new RandomIndexWriter(random, dir, 
        newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random))
        .setMergePolicy(newLogMergePolicy()));
    for (int i = 0; i < docs.length; i++) {
      Document doc = new Document();
      doc.add(newField(field,docs[i],Store.NO,Index.ANALYZED));
      iw.addDocument(doc);
    }
    iw.close();
    
    IndexSearcher searcher = new IndexSearcher(dir, true);
    
    // test queries that must find all
    for (int i = 0; i < matchAll.length; i++) {

View Full Code Here


  @Override
  public void setUp() throws Exception {
    super.setUp();
    directory = newDirectory();
    RandomIndexWriter writer= new RandomIndexWriter(random, directory, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random)).setMergePolicy(newLogMergePolicy()));
    for (int i = 0; i < docFields.length; i++) {
      Document doc = new Document();
      doc.add(newField(field, docFields[i], Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    reader = writer.getReader();
    writer.close();
    searcher = newSearcher(reader);
  }

View Full Code Here

  @Override
  public void setUp() throws Exception {
    super.setUp();
    // create test index
    mDirectory = newDirectory();
    final RandomIndexWriter writer = new RandomIndexWriter(random,
        mDirectory, newIndexWriterConfig(TEST_VERSION_CURRENT,
                                         new StandardAnalyzer(TEST_VERSION_CURRENT)).setMergePolicy(newLogMergePolicy()));


    addDocument(writer, "1", "I think it should work.");
    addDocument(writer, "2", "I think it should work.");
    addDocument(writer, "3", "I think it should work.");
    addDocument(writer, "4", "I think it should work.");
    reader = writer.getReader();
    writer.close();
    searcher = newSearcher(reader);
  }

View Full Code Here

  
  @Override
  public void setUp() throws Exception {
    super.setUp();
    directory = newDirectory();
    RandomIndexWriter writer= new RandomIndexWriter(random, directory, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random)).setMergePolicy(newLogMergePolicy()));
    for (int i = 0; i < docFields.length; i++) {
      Document doc = new Document();
      doc.add(newField(KEY, ""+i, Field.Store.NO, Field.Index.NOT_ANALYZED));
      Field f = newField(FIELD, docFields[i], Field.Store.NO, Field.Index.ANALYZED);
      f.setBoost(i);
      doc.add(f);
      doc.add(newField(ALTFIELD, docFields[i], Field.Store.NO, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    reader = writer.getReader();
    writer.close();
    searcher = newSearcher(reader);
  }

View Full Code Here

 */
public class TestFuzzyQuery extends LuceneTestCase {


  public void testFuzziness() throws Exception {
    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random, directory);
    addDoc("aaaaa", writer);
    addDoc("aaaab", writer);
    addDoc("aaabb", writer);
    addDoc("aabbb", writer);
    addDoc("abbbb", writer);
    addDoc("bbbbb", writer);
    addDoc("ddddd", writer);


    IndexReader reader = writer.getReader();
    IndexSearcher searcher = newSearcher(reader);
    writer.close();


    FuzzyQuery query = new FuzzyQuery(new Term("field", "aaaaa"), FuzzyQuery.defaultMinSimilarity, 0);   
    ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;
    assertEquals(3, hits.length);

View Full Code Here

    directory.close();
  }


  public void testFuzzinessLong() throws Exception {
    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random, directory);
    addDoc("aaaaaaa", writer);
    addDoc("segment", writer);


    IndexReader reader = writer.getReader();
    IndexSearcher searcher = newSearcher(reader);
    writer.close();


    FuzzyQuery query;
    // not similar enough:
    query = new FuzzyQuery(new Term("field", "xxxxx"), FuzzyQuery.defaultMinSimilarity, 0);   
    ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;

View Full Code Here

    directory.close();
  }


  public void testTokenLengthOpt() throws IOException {
    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random, directory);
    addDoc("12345678911", writer);
    addDoc("segment", writer);


    IndexReader reader = writer.getReader();
    IndexSearcher searcher = newSearcher(reader);
    writer.close();


    Query query;
    // term not over 10 chars, so optimization shortcuts
    query = new FuzzyQuery(new Term("field", "1234569"), 0.9f);
    ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;

View Full Code Here

  }
  
  /** Test the TopTermsBoostOnlyBooleanQueryRewrite rewrite method. */
  public void testBoostOnlyRewrite() throws Exception {
    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random, directory);
    addDoc("Lucene", writer);
    addDoc("Lucene", writer);
    addDoc("Lucenne", writer);


    IndexReader reader = writer.getReader();
    IndexSearcher searcher = newSearcher(reader);
    writer.close();
    
    FuzzyQuery query = new FuzzyQuery(new Term("field", "Lucene"));
    query.setRewriteMethod(new MultiTermQuery.TopTermsBoostOnlyBooleanQueryRewrite(50));
    ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;
    assertEquals(3, hits.length);

View Full Code Here

  
  public void testGiga() throws Exception {


    MockAnalyzer analyzer = new MockAnalyzer(random);
    Directory index = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random, index);


    addDoc("Lucene in Action", w);
    addDoc("Lucene for Dummies", w);


    //addDoc("Giga", w);
    addDoc("Giga byte", w);


    addDoc("ManagingGigabytesManagingGigabyte", w);
    addDoc("ManagingGigabytesManagingGigabytes", w);


    addDoc("The Art of Computer Science", w);
    addDoc("J. K. Rowling", w);
    addDoc("JK Rowling", w);
    addDoc("Joanne K Roling", w);
    addDoc("Bruce Willis", w);
    addDoc("Willis bruce", w);
    addDoc("Brute willis", w);
    addDoc("B. willis", w);
    IndexReader r = w.getReader();
    w.close();


    Query q = new QueryParser(TEST_VERSION_CURRENT, "field", analyzer).parse( "giga~0.9" );


    // 3. search
    IndexSearcher searcher = newSearcher(r);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.index.RandomIndexWriter

org.apache.lucene.analysis.MockAnalyzer

org.apache.lucene.classification.ClassificationTestBase

org.apache.lucene.codecs.compressing.TestCompressingStoredFieldsFormat

org.apache.lucene.codecs.idversion.TestIDVersionPostingsFormat

org.apache.lucene.codecs.lucene40.TestReuseDocsEnum

org.apache.lucene.codecs.lucene41.TestBlockPostingsFormat3

org.apache.lucene.codecs.perfield.TestPerFieldPostingsFormat2

org.apache.lucene.codecs.pulsing.Test10KPulsings

org.apache.lucene.codecs.pulsing.TestPulsingReuse

org.apache.lucene.collation.TestICUCollationDocValuesField

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.