Examples of it.unimi.dsi.mg4j.search.DocumentIteratorBuilderVisitor

it.unimi.dsi.mg4j.search.DocumentIteratorBuilderVisitor
A {@link it.unimi.dsi.mg4j.query.nodes.QueryBuilderVisitor}that builds a {@link it.unimi.dsi.mg4j.search.DocumentIterator}resolving the queries using the objects in {@link it.unimi.dsi.mg4j.search}.
This elementary builder visitor invokes {@link it.unimi.dsi.mg4j.index.Index#documents(CharSequence)}to build the leaf {@linkplain it.unimi.dsi.mg4j.index.IndexIterator index iterators}. Thus, the resulting {@link it.unimi.dsi.mg4j.search.DocumentIterator} should be carefully{@linkplain it.unimi.dsi.mg4j.search.DocumentIterator#dispose() disposed} after usage (everyindex iterator may open a file or a socket).
{@link Prefix} and {@link MultiTerm} nodes cause the creation of a {@link MultiTermIndexIterator}, in the first case by calling {@link it.unimi.dsi.mg4j.index.Index#documents(CharSequence,int)} andin the second case by creating a {@link MultiTermIndexIterator} with the name and frequency equal to themaximum frequency over all terms. Other implementations might choose differently.
At construction time, you must provide a map from strings to indices that will be used to resolve {@link it.unimi.dsi.mg4j.query.nodes.Select} nodes. The map may be null, in which casesuch nodes will cause an {@link java.lang.IllegalArgumentException}. If a {@link it.unimi.dsi.mg4j.query.nodes.Select}node contains an index name that does not appear in the map a {@link NoSuchElementException}will be thrown instead.
A production site will likely substitute this builder visitor with one that reuses {@linkplain it.unimi.dsi.mg4j.index.IndexReader index readers} out of a pool.
Instances of this class may be safely reused by calling {@link #prepare()}.

    for( Index index: indexMap.values() ) if ( index.hasPayloads ) {
      if ( index.payload.getClass() == DatePayload.class ) index2Parser.put( index, DateFormat.getDateInstance( DateFormat.SHORT, Locale.UK ) );
    }
    */
    
    final QueryEngine queryEngine = new QueryEngine( simpleParser, new DocumentIteratorBuilderVisitor( indexMap, index2Parser, indexMap.get( indexMap.firstKey() ), MAX_STEMMING ), indexMap );
    queryEngine.setWeights( index2Weight );
    queryEngine.score( new Scorer[] { new BM25Scorer(), new VignaScorer() }, new double[] { 1, 1 } );
    // We set up an interval selector only if there is a collection for snippeting
    queryEngine.intervalSelector = documentCollection != null ? new IntervalSelector( 4, 40 ) : new IntervalSelector();
    queryEngine.multiplex = true;

View Full Code Here

     * (which in turn requires the set of index names and a default index), a document iterator
     * builder, which needs the index map, a default index, and a limit on prefix query
     * expansion, and finally the index map. */
    QueryEngine engine = new QueryEngine(
      new SimpleParser( indexMap.keySet(), "text", termProcessors ),
      new DocumentIteratorBuilderVisitor( indexMap, text, 1000 ), 
      indexMap
      
    );


    /* Optionally, we can score the results. Here we use a state-of-art ranking

View Full Code Here

  }




  public void testSkipBug() throws QueryParserException, QueryBuilderVisitorException, IOException {
    Query query = simpleParser.parse( "a + b + c" );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    assertEquals( 2, documentIterator.skipTo( 2 ) );
    documentIterator.dispose();
  }

View Full Code Here

    new IndexBuilder( basename, new StringArrayDocumentCollection( "a a b c d e" ) ).run();
    index = DiskBasedIndex.getInstance( basename + "-text", true, true );
    simpleParser = new SimpleParser( index.termProcessor );


    Query query = simpleParser.parse( "(a|b|d)<(a|b|d)" );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    documentIterator.nextDocument();
    IntervalIterator intervalIterator = documentIterator.intervalIterator();
    assertEquals( Interval.valueOf( 0, 1 ), intervalIterator.nextInterval() );
    assertEquals( Interval.valueOf( 1, 2 ), intervalIterator.nextInterval() );

View Full Code Here

  }


  
  public void testSkipBug() throws QueryParserException, QueryBuilderVisitorException, IOException {
    Query query = simpleParser.parse( "a | b | c" );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    assertEquals( 2, documentIterator.skipTo( 2 ) );
    documentIterator.dispose();
  }

View Full Code Here

    for( File f: new File( basename ).getParentFile().listFiles( (FileFilter)new PrefixFileFilter( new File( basename ).getName() ) ) )  f.delete();
  }


  public void testWeights() throws QueryBuilderVisitorException, IOException {
    Query query = new Weight( 0.5, new And( new Term( "a" ), new Term( "b" ) ) );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    assertEquals( .5, documentIterator.weight(), 0 );
    documentIterator.dispose();


    query = new Weight( .1, new Weight( 0.5, new And( new Weight( .2, new Term( "a" ) ), new Term( "b" ) ) ) );
    documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index, Integer.MAX_VALUE );
    documentIterator = query.accept( documentIteratorBuilderVisitor );
    assertEquals( .5, documentIterator.weight(), 0 );
    documentIterator.dispose();
}

View Full Code Here

    FileUtils.forceDelete( tempDir );
  }
  
  private void assertScores( String q, it.unimi.dsi.mg4j.index.Index index, Scorer scorer, double[] expected ) throws QueryParserException, QueryBuilderVisitorException, IOException {
    it.unimi.dsi.mg4j.query.nodes.Query query = simpleParser.parse( q );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    scorer.wrap( documentIterator );
    
    int i = 0;
    while ( documentIterator.nextDocument() != -1 ) {

View Full Code Here

      "t", // TODO: make it a parameter
      termProcessors
    );
        
    it.unimi.dsi.mg4j.query.nodes.Query query = simpleParser.parse( q );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( indexMap, defaultIndex, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    scorer.wrap( documentIterator );
    
    int i = 0;
    while ( documentIterator.hasNext() ) {

View Full Code Here

    TermCollectionVisitor termVisitor = new TermCollectionVisitor();
    CounterSetupVisitor setupVisitor = new CounterSetupVisitor( termVisitor );
    CounterCollectionVisitor counterCollectionVisitor = new CounterCollectionVisitor( setupVisitor );


    it.unimi.dsi.mg4j.query.nodes.Query query = simpleParser.parse( "this" );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, index0, Integer.MAX_VALUE );


    DocumentIterator indexIterator = query.accept( documentIteratorBuilderVisitor );


    indexIterator.nextDocument();

View Full Code Here

  public void testCountScorer() throws QueryParserException, QueryBuilderVisitorException, IOException {


    Scorer scorer = new CountScorer();


    it.unimi.dsi.mg4j.query.nodes.Query query = simpleParser.parse( "C" );
    DocumentIteratorBuilderVisitor documentIteratorBuilderVisitor = new DocumentIteratorBuilderVisitor( null, indexBody, Integer.MAX_VALUE );
    DocumentIterator documentIterator = query.accept( documentIteratorBuilderVisitor );
    scorer.wrap( documentIterator );
    
    final double expected[] = { 2, 1 };

View Full Code Here

TOP

Related Classes of it.unimi.dsi.mg4j.search.DocumentIteratorBuilderVisitor

it.unimi.dsi.fastutil.doubles.DoubleArrayList

it.unimi.dsi.mg4j.examples.RunQuery

it.unimi.dsi.mg4j.index.Index

it.unimi.dsi.mg4j.index.IndexIterator

it.unimi.dsi.mg4j.index.MultiTermIndexIteratorTest

it.unimi.dsi.mg4j.index.payload.Payload

it.unimi.dsi.mg4j.query.Query

it.unimi.dsi.mg4j.search.OrderedAndDocumentIteratorTest

it.unimi.dsi.mg4j.search.OrDocumentIteratorTest

it.unimi.dsi.mg4j.search.score.ScorerTest

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.