Examples of org.apache.lucene.util.FixedBitSet

org.apache.lucene.util.FixedBitSet
BitSet of fixed length (numBits), backed by accessible ( {@link #getBits}) long[], accessed with an int index, implementing Bits and DocIdSet. Unlike {@link OpenBitSet} this bit set does not auto-expand, cannothandle long index, and does not have fastXX/XX variants (just X). @lucene.internal

    private PagedMutable docs;
    private PagedGrowableWriter values;
    private int size;
    
    public PackedNumericFieldUpdates(int maxDoc) {
      docsWithField = new FixedBitSet(64);
      docs = new PagedMutable(1, 1024, PackedInts.bitsRequired(maxDoc - 1), PackedInts.COMPACT);
      values = new PagedGrowableWriter(1, 1024, 1, PackedInts.FAST);
      size = 0;
    }

View Full Code Here


    @Override
    public UpdatesIterator getUpdates() {
      final PagedMutable docs = this.docs;
      final PagedGrowableWriter values = this.values;
      final FixedBitSet docsWithField = this.docsWithField;
      new InPlaceMergeSorter() {
        @Override
        protected void swap(int i, int j) {
          long tmpDoc = docs.get(j);
          docs.set(j, docs.get(i));
          docs.set(i, tmpDoc);
          
          long tmpVal = values.get(j);
          values.set(j, values.get(i));
          values.set(i, tmpVal);
          
          boolean tmpBool = docsWithField.get(j);
          if (docsWithField.get(i)) {
            docsWithField.set(j);
          } else {
            docsWithField.clear(j);
          }
          if (tmpBool) {
            docsWithField.set(i);
          } else {
            docsWithField.clear(i);
          }
        }
        
        @Override
        protected int compare(int i, int j) {
          int x = (int) docs.get(i);
          int y = (int) docs.get(j);
          return (x < y) ? -1 : ((x == y) ? 0 : 1);
        }
      }.sort(0, size);


      final int size = this.size;
      return new UpdatesIterator() {
        private long idx = 0; // long so we don't overflow if size == Integer.MAX_VALUE
        private int doc = -1;
        private Long value = null;
        
        @Override
        Long value() {
          return value;
        }
        
        @Override
        int nextDoc() {
          if (idx >= size) {
            value = null;
            return doc = DocIdSetIterator.NO_MORE_DOCS;
          }
          doc = (int) docs.get(idx);
          ++idx;
          while (idx < size && docs.get(idx) == doc) {
            ++idx;
          }
          if (!docsWithField.get((int) (idx - 1))) {
            value = null;
          } else {
            // idx points to the "next" element
            value = Long.valueOf(values.get(idx - 1));
          }

View Full Code Here

   * to record hits and you can override to e.g. record the docs in your own
   * {@link DocIdSet}.
   */
  protected Docs createDocs(final int maxDoc) {
    return new Docs() {
      private final FixedBitSet bits = new FixedBitSet(maxDoc);
      
      @Override
      public void addDoc(int docId) throws IOException {
        bits.set(docId);
      }
      
      @Override
      public DocIdSet getDocIdSet() {
        return bits;

View Full Code Here

    AtomicReaderContext context = (AtomicReaderContext) reader.getContext();
    w.close();


    List<Term> terms = new ArrayList<Term>();
    terms.add(new Term(fieldName, "19"));
    FixedBitSet bits = (FixedBitSet) termsFilter(random().nextBoolean(), terms).getDocIdSet(context, context.reader().getLiveDocs());
    assertNull("Must match nothing", bits);


    terms.add(new Term(fieldName, "20"));
    bits = (FixedBitSet) termsFilter(random().nextBoolean(), terms).getDocIdSet(context, context.reader().getLiveDocs());
    assertEquals("Must match 1", 1, bits.cardinality());


    terms.add(new Term(fieldName, "10"));
    bits = (FixedBitSet) termsFilter(random().nextBoolean(), terms).getDocIdSet(context, context.reader().getLiveDocs());
    assertEquals("Must match 2", 2, bits.cardinality());


    terms.add(new Term(fieldName, "00"));
    bits = (FixedBitSet) termsFilter(random().nextBoolean(), terms).getDocIdSet(context, context.reader().getLiveDocs());
    assertEquals("Must match 2", 2, bits.cardinality());


    reader.close();
    rd.close();
  }

View Full Code Here

    for (AtomicReaderContext context : multi.leaves()) {
      DocIdSet docIdSet = tf.getDocIdSet(context, context.reader().getLiveDocs());
      if (context.reader().docFreq(new Term(fieldName, "content1")) == 0) {
        assertNull(docIdSet);
      } else {
        FixedBitSet bits = (FixedBitSet) docIdSet;
        assertTrue("Must be >= 0", bits.cardinality() >= 0);      
      }
    }
    multi.close();
    reader1.close();
    reader2.close();

View Full Code Here

    
    
    AtomicReaderContext context = reader.leaves().get(0);
    TermsFilter tf = new TermsFilter(terms);


    FixedBitSet bits = (FixedBitSet) tf.getDocIdSet(context, context.reader().getLiveDocs());
    assertEquals("Must be num fields - 1 since we skip only one field", num-1, bits.cardinality());  
    reader.close();
    dir.close();
  }

View Full Code Here

    w.close();
    assertEquals(1, reader.leaves().size());
    AtomicReaderContext context = reader.leaves().get(0);
    TermsFilter tf = new TermsFilter(new ArrayList<Term>(terms));


    FixedBitSet bits = (FixedBitSet) tf.getDocIdSet(context, context.reader().getLiveDocs());
    assertEquals(context.reader().numDocs(), bits.cardinality());  
    reader.close();
    dir.close();
  }

View Full Code Here

      // Sort of silly:
      fastMatchFilter = new CachingWrapperFilter(new QueryWrapperFilter(new MatchAllDocsQuery())) {
          @Override
          protected DocIdSet cacheImpl(DocIdSetIterator iterator, AtomicReader reader)
            throws IOException {
            final FixedBitSet cached = new FixedBitSet(reader.maxDoc());
            filterWasUsed.set(true);
            cached.or(iterator);
            return cached;
          }
        };
    } else {
      fastMatchFilter = null;

View Full Code Here

      in.seek(termsStart);
      final BytesRef lastTerm = new BytesRef(10);
      long lastDocsStart = -1;
      int docFreq = 0;
      long totalTermFreq = 0;
      FixedBitSet visitedDocs = new FixedBitSet(maxDoc);
      final IntsRef scratchIntsRef = new IntsRef();
      while(true) {
        SimpleTextUtil.readLine(in, scratch);
        if (scratch.equals(END) || StringHelper.startsWith(scratch, FIELD)) {
          if (lastDocsStart != -1) {
            b.add(Util.toIntsRef(lastTerm, scratchIntsRef),
                  outputs.newPair(lastDocsStart,
                                  outputsInner.newPair((long) docFreq, totalTermFreq)));
            sumTotalTermFreq += totalTermFreq;
          }
          break;
        } else if (StringHelper.startsWith(scratch, DOC)) {
          docFreq++;
          sumDocFreq++;
          UnicodeUtil.UTF8toUTF16(scratch.bytes, scratch.offset+DOC.length, scratch.length-DOC.length, scratchUTF16);
          int docID = ArrayUtil.parseInt(scratchUTF16.chars, 0, scratchUTF16.length);
          visitedDocs.set(docID);
        } else if (StringHelper.startsWith(scratch, FREQ)) {
          UnicodeUtil.UTF8toUTF16(scratch.bytes, scratch.offset+FREQ.length, scratch.length-FREQ.length, scratchUTF16);
          totalTermFreq += ArrayUtil.parseInt(scratchUTF16.chars, 0, scratchUTF16.length);
        } else if (StringHelper.startsWith(scratch, TERM)) {
          if (lastDocsStart != -1) {
            b.add(Util.toIntsRef(lastTerm, scratchIntsRef), outputs.newPair(lastDocsStart,
                                                                            outputsInner.newPair((long) docFreq, totalTermFreq)));
          }
          lastDocsStart = in.getFilePointer();
          final int len = scratch.length - TERM.length;
          if (len > lastTerm.length) {
            lastTerm.grow(len);
          }
          System.arraycopy(scratch.bytes, TERM.length, lastTerm.bytes, 0, len);
          lastTerm.length = len;
          docFreq = 0;
          sumTotalTermFreq += totalTermFreq;
          totalTermFreq = 0;
          termCount++;
        }
      }
      docCount = (int) visitedDocs.cardinality();
      fst = b.finish();
      /*
      PrintStream ps = new PrintStream("out.dot");
      fst.toDot(ps);
      ps.close();

View Full Code Here

  private boolean advanceRpts(PhrasePositions pp) throws IOException {
    if (pp.rptGroup < 0) {
      return true; // not a repeater
    }
    PhrasePositions[] rg = rptGroups[pp.rptGroup];
    FixedBitSet bits = new FixedBitSet(rg.length); // for re-queuing after collisions are resolved
    int k0 = pp.rptInd;
    int k;
    while((k=collide(pp)) >= 0) {
      pp = lesser(pp, rg[k]); // always advance the lesser of the (only) two colliding pps
      if (!advancePP(pp)) {
        return false; // exhausted
      }
      if (k != k0) { // careful: mark only those currently in the queue
        bits = FixedBitSet.ensureCapacity(bits, k);
        bits.set(k); // mark that pp2 need to be re-queued
      }
    }
    // collisions resolved, now re-queue
    // empty (partially) the queue until seeing all pps advanced for resolving collisions
    int n = 0;
    // TODO would be good if we can avoid calling cardinality() in each iteration!
    int numBits = bits.length(); // larges bit we set
    while (bits.cardinality() > 0) {
      PhrasePositions pp2 = pq.pop();
      rptStack[n++] = pp2;
      if (pp2.rptGroup >= 0 
          && pp2.rptInd < numBits  // this bit may not have been set
          && bits.get(pp2.rptInd)) {
        bits.clear(pp2.rptInd);
      }
    }
    // add back to queue
    for (int i=n-1; i>=0; i--) {
      pq.add(rptStack[i]);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

com.greplin.lucene.filter.BaseFilterTest

com.greplin.lucene.filter.FixedBitSets

org.apache.lucene.codecs.asserting.AssertingDocValuesFormat$AssertingDocValuesConsumer

org.apache.lucene.codecs.bloom.FuzzySet

org.apache.lucene.codecs.lucene41.TestBlockPostingsFormat3$RandomBits

org.apache.lucene.codecs.memory.DirectDocValuesProducer

org.apache.lucene.codecs.memory.MemoryDocValuesProducer

org.apache.lucene.codecs.simpletext.SimpleTextFieldsReader$SimpleTextTerms

org.apache.lucene.facet.DrillSidewaysScorer

org.apache.lucene.facet.FacetsCollector

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.