Examples of org.apache.lucene.util.OpenBitSet

org.apache.lucene.util.OpenBitSet
An "open" BitSet implementation that allows direct access to the array of words storing the bits.
Unlike java.util.bitset, the fact that bits are packed into an array of longs is part of the interface. This allows efficient implementation of other algorithms by someone other than the author. It also allows one to efficiently implement alternate serialization or interchange formats.
OpenBitSet is faster than java.util.BitSet in most operations and *much* faster at calculating cardinality of sets and results of set operations. It can also handle sets of larger cardinality (up to 64 * 2**32-1)
The goals of OpenBitSet are the fastest implementation possible, and maximum code reuse. Extra safety and encapsulation may always be built on top, but if that's built in, the cost can never be removed (and hence people re-implement their own version in order to get better performance). If you want a "safe", totally encapsulated (and slower and limited) BitSet class, use java.util.BitSet.

Performance Results
Test system: Pentium 4, Sun Java 1.5_06 -server -Xbatch -Xmx64M
BitSet size = 1,000,000
Results are java.util.BitSet time divided by OpenBitSet time.

cardinality intersect_count union nextSetBit get iterator

50% full 3.36 3.96 1.44 1.46 1.99 1.58

1% full 3.31 3.90 1.04 0.99

Test system: AMD Opteron, 64 bit linux, Sun Java 1.5_06 -server -Xbatch -Xmx64M
BitSet size = 1,000,000
Results are java.util.BitSet time divided by OpenBitSet time.

cardinality intersect_count union nextSetBit get iterator

50% full 2.50 3.50 1.00 1.03 1.12 1.25

1% full 2.51 3.49 1.00 1.02

@version $Id$

	cardinality	intersect_count	union	nextSetBit	get	iterator
50% full	3.36	3.96	1.44	1.46	1.99	1.58
1% full	3.31	3.90		1.04		0.99

	cardinality	intersect_count	union	nextSetBit	get	iterator
50% full	2.50	3.50	1.00	1.03	1.12	1.25
1% full	2.51	3.49		1.00		1.02

    if (!(other instanceof BitDocSet)) {
      return other.intersection(this);
    }


    // Default... handle with bitsets.
    OpenBitSet newbits = (OpenBitSet)(this.getBits().clone());
    newbits.and(other.getBits());
    return new BitDocSet(newbits);
  }

View Full Code Here

    newbits.and(other.getBits());
    return new BitDocSet(newbits);
  }


  public DocSet union(DocSet other) {
    OpenBitSet newbits = (OpenBitSet)(this.getBits().clone());
    newbits.or(other.getBits());
    return new BitDocSet(newbits);
  }

View Full Code Here

  public int unionSize(DocSet other) {
    return this.size() + other.size() - this.intersectionSize(other);
  }


  public DocSet andNot(DocSet other) {
    OpenBitSet newbits = (OpenBitSet)(this.getBits().clone());
    newbits.andNot(other.getBits());
    return new BitDocSet(newbits);
  }

View Full Code Here

  public int andNotSize(DocSet other) {
    return this.size() - this.intersectionSize(other);
  }


  public Filter getTopFilter() {
    final OpenBitSet bs = getBits();


    return new Filter() {
      @Override
      public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
        int offset = 0;
        SolrIndexReader r = (SolrIndexReader)reader;
        while (r.getParent() != null) {
          offset += r.getBase();
          r = r.getParent();
        }


        if (r==reader) return bs;


        final int base = offset;
        final int maxDoc = reader.maxDoc();
        final int max = base + maxDoc;   // one past the max doc in this segment.


        return new DocIdSet() {
          @Override
          public DocIdSetIterator iterator() throws IOException {
            return new DocIdSetIterator() {
              int pos=base-1;
              int adjustedDoc=-1;


              @Override
              public int docID() {
                return adjustedDoc;
              }


              @Override
              public int nextDoc() throws IOException {
                pos = bs.nextSetBit(pos+1);
                return adjustedDoc = (pos>=0 && pos<max) ? pos-base : NO_MORE_DOCS;
              }


              @Override
              public int advance(int target) throws IOException {
                if (target==NO_MORE_DOCS) return adjustedDoc=NO_MORE_DOCS;
                pos = bs.nextSetBit(target+base);
                return adjustedDoc = (pos>=0 && pos<max) ? pos-base : NO_MORE_DOCS;
              }
            };
          }

View Full Code Here

      // use the query as a filter itself...
      DocListAndSet both3 = searcher.getDocListAndSet(query,query,sort,start, limit);
      test( both3.docList.equals(both.docList) );
      test( both3.docSet.equals(both.docSet) );


      OpenBitSet bits = both.docSet.getBits();
      OpenBitSet neg = ((OpenBitSet)bits.clone());
      neg.flip(0, bits.capacity());


      // use the negative as a filter (should result in 0 matches)
      // todo - fix if filter is not null
      both2 = searcher.getDocListAndSet(query,new BitDocSet(neg),sort, start, limit);
      test( both2.docList.size() == 0 );

View Full Code Here

    dir.close();


  }


  public DocIdSet randSet(int sz) {
    OpenBitSet obs = new OpenBitSet(sz);
    int n = r.nextInt(sz);
    for (int i=0; i<n; i++) {
      obs.fastSet(r.nextInt(sz));
    }
    return obs;
  }

View Full Code Here

public class TestDocSet extends LuceneTestCase {
  Random rand = random;
  float loadfactor;


  public OpenBitSet getRandomSet(int sz, int bitsToSet) {
    OpenBitSet bs = new OpenBitSet(sz);
    if (sz==0) return bs;
    for (int i=0; i<bitsToSet; i++) {
      bs.fastSet(rand.nextInt(sz));
    }
    return bs;
  }

View Full Code Here

  }


  protected void doSingle(int maxSize) {
    int sz = rand.nextInt(maxSize+1);
    int sz2 = rand.nextInt(maxSize);
    OpenBitSet bs1 = getRandomSet(sz, rand.nextInt(sz+1));
    OpenBitSet bs2 = getRandomSet(sz, rand.nextInt(sz2+1));


    DocSet a1 = new BitDocSet(bs1);
    DocSet a2 = new BitDocSet(bs2);
    DocSet b1 = getDocSet(bs1);
    DocSet b2 = getDocSet(bs2);


    checkEqual(bs1,b1);
    checkEqual(bs2,b2);


    iter(a1,b1);
    iter(a2,b2);


    OpenBitSet a_and = (OpenBitSet) bs1.clone(); a_and.and(bs2);
    OpenBitSet a_or = (OpenBitSet) bs1.clone(); a_or.or(bs2);
    // OpenBitSet a_xor = (OpenBitSet)bs1.clone(); a_xor.xor(bs2);
    OpenBitSet a_andn = (OpenBitSet) bs1.clone(); a_andn.andNot(bs2);


    checkEqual(a_and, b1.intersection(b2));
    checkEqual(a_or, b1.union(b2));
    checkEqual(a_andn, b1.andNot(b2));


    assertEquals(a_and.cardinality(), b1.intersectionSize(b2));
    assertEquals(a_or.cardinality(), b1.unionSize(b2));
    assertEquals(a_andn.cardinality(), b1.andNotSize(b2));
  }

View Full Code Here

    doMany(130, 10000);
    // doMany(130, 1000000);
  }


  public DocSet getRandomDocSet(int n, int maxDoc) {
    OpenBitSet obs = new OpenBitSet(maxDoc);
    int[] a = new int[n];
    for (int i=0; i<n; i++) {
      for(;;) {
        int idx = rand.nextInt(maxDoc);
        if (obs.getAndSet(idx)) continue;
        a[i]=idx;
        break;
      }
    }

View Full Code Here

      }
    }
  }


  public void doFilterTest(SolrIndexReader reader) throws IOException {
    OpenBitSet bs = getRandomSet(reader.maxDoc(), rand.nextInt(reader.maxDoc()+1));
    DocSet a = new BitDocSet(bs);
    DocSet b = getIntDocSet(bs);


    Filter fa = a.getTopFilter();
    Filter fb = b.getTopFilter();

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.util.OpenBitSet

com.browseengine.bobo.facets.data.MultiValueFacetDataCache

com.browseengine.bobo.facets.data.MultiValueWithWeightFacetDataCache

com.browseengine.bobo.facets.filter.BitSetFilter

com.browseengine.bobo.facets.filter.FacetOrFilter$FacetOrRandomAccessDocIdSet

com.browseengine.bobo.facets.filter.MultiValueORFacetFilter

com.browseengine.bobo.facets.range.ValueConverterBitSetBuilder

com.esri.gpt.catalog.lucene.AclFilter

com.esri.gpt.catalog.lucene.IsPartOfFilter

com.esri.gpt.catalog.lucene.SchemaFilter

com.esri.gpt.server.assertion.index.AsnFilter

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.

Examples of org.apache.lucene.util.OpenBitSet

Performance Results

Related Classes of org.apache.lucene.util.OpenBitSet