Java FixedBitSet.cardinality方法代码示例

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
private boolean openBitSetContains(int[] expectedDocs, FixedBitSet actual, int maxDoc) throws IOException {
  if (expectedDocs.length != actual.cardinality()) {
    return false;
  }

  FixedBitSet expected = new FixedBitSet(maxDoc);
  for (int expectedDoc : expectedDocs) {
    expected.set(expectedDoc);
  }

  int docId;
  DocIdSetIterator iterator = expected.iterator();
  while ((docId = iterator.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
    if (!actual.get(docId)) {
      return false;
    }
  }

  return true;
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
/** pp was just advanced. If that caused a repeater collision, resolve by advancing the lesser
 * of the two colliding pps. Note that there can only be one collision, as by the initialization
 * there were no collisions before pp was advanced.  */
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]);
  }
  return true;
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
@Override
public DocIdSet getDocIdSet(AtomicReaderContext context, Bits acceptDocs) {
  assertNull("acceptDocs should be null, as we have an index without deletions", acceptDocs);
  final FixedBitSet set = new FixedBitSet(context.reader().maxDoc());
  int docBase = context.docBase;
  final int limit = docBase+context.reader().maxDoc();
  for (int index=0;index < docs.length; index++) {
    final int docId = docs[index];
    if (docId >= docBase && docId < limit) {
      set.set(docId-docBase);
    }
  }
  return set.cardinality() == 0 ? null:set;
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
public DocSet getHashDocSet(FixedBitSet bs) {
  int[] docs = new int[bs.cardinality()];
  FixedBitSetIterator iter = new FixedBitSetIterator(bs);
  for (int i=0; i<docs.length; i++) {
    docs[i] = iter.nextDoc();
  }
  return new HashDocSet(docs,0,docs.length);
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
public DocSet getIntDocSet(FixedBitSet bs) {
  int[] docs = new int[bs.cardinality()];
  FixedBitSetIterator iter = new FixedBitSetIterator(bs);
  for (int i=0; i<docs.length; i++) {
    docs[i] = iter.nextDoc();
  }
  return new SortedIntDocSet(docs);
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
public DocSet getDocSlice(FixedBitSet bs) {
  int len = bs.cardinality();
  int[] arr = new int[len+5];
  arr[0]=10; arr[1]=20; arr[2]=30; arr[arr.length-1]=1; arr[arr.length-2]=2;
  int offset = 3;
  int end = offset + len;

  FixedBitSetIterator iter = new FixedBitSetIterator(bs);
  // put in opposite order... DocLists are not ordered.
  for (int i=end-1; i>=offset; i--) {
    arr[i] = iter.nextDoc();
  }

  return new DocSlice(offset, len, arr, null, len*2, 100.0f);
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
private void loadTerms() throws IOException {
  PositiveIntOutputs posIntOutputs = PositiveIntOutputs.getSingleton();
  final Builder<PairOutputs.Pair<Long,PairOutputs.Pair<Long,Long>>> b;
  final PairOutputs<Long,Long> outputsInner = new PairOutputs<>(posIntOutputs, posIntOutputs);
  final PairOutputs<Long,PairOutputs.Pair<Long,Long>> outputs = new PairOutputs<>(posIntOutputs,
                                                                                                                  outputsInner);
  b = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
  IndexInput in = SimpleTextFieldsReader.this.in.clone();
  in.seek(termsStart);
  final BytesRefBuilder lastTerm = new BytesRefBuilder();
  long lastDocsStart = -1;
  int docFreq = 0;
  long totalTermFreq = 0;
  FixedBitSet visitedDocs = new FixedBitSet(maxDoc);
  final IntsRefBuilder scratchIntsRef = new IntsRefBuilder();
  while(true) {
    SimpleTextUtil.readLine(in, scratch);
    if (scratch.get().equals(END) || StringHelper.startsWith(scratch.get(), FIELD)) {
      if (lastDocsStart != -1) {
        b.add(Util.toIntsRef(lastTerm.get(), scratchIntsRef),
              outputs.newPair(lastDocsStart,
                              outputsInner.newPair((long) docFreq, totalTermFreq)));
        sumTotalTermFreq += totalTermFreq;
      }
      break;
    } else if (StringHelper.startsWith(scratch.get(), DOC)) {
      docFreq++;
      sumDocFreq++;
      scratchUTF16.copyUTF8Bytes(scratch.bytes(), DOC.length, scratch.length()-DOC.length);
      int docID = ArrayUtil.parseInt(scratchUTF16.chars(), 0, scratchUTF16.length());
      visitedDocs.set(docID);
    } else if (StringHelper.startsWith(scratch.get(), FREQ)) {
      scratchUTF16.copyUTF8Bytes(scratch.bytes(), FREQ.length, scratch.length()-FREQ.length);
      totalTermFreq += ArrayUtil.parseInt(scratchUTF16.chars(), 0, scratchUTF16.length());
    } else if (StringHelper.startsWith(scratch.get(), TERM)) {
      if (lastDocsStart != -1) {
        b.add(Util.toIntsRef(lastTerm.get(), scratchIntsRef), outputs.newPair(lastDocsStart,
                                                                        outputsInner.newPair((long) docFreq, totalTermFreq)));
      }
      lastDocsStart = in.getFilePointer();
      final int len = scratch.length() - TERM.length;
      lastTerm.grow(len);
      System.arraycopy(scratch.bytes(), TERM.length, lastTerm.bytes(), 0, len);
      lastTerm.setLength(len);
      docFreq = 0;
      sumTotalTermFreq += totalTermFreq;
      totalTermFreq = 0;
      termCount++;
    }
  }
  docCount = visitedDocs.cardinality();
  fst = b.finish();
  /*
  PrintStream ps = new PrintStream("out.dot");
  fst.toDot(ps);
  ps.close();
  System.out.println("SAVED out.dot");
  */
  //System.out.println("FST " + fst.sizeInBytes());
}
 

import org.apache.lucene.util.FixedBitSet; //导入方法依赖的package包/类
public LiveDocsReader(AtomicReaderContext context, FixedBitSet liveDocs) throws IOException {
  super(context.reader());
  this.liveDocs = liveDocs;
  this.numDocs = liveDocs.cardinality();
}