List of usage examples for org.apache.lucene.search DocIdSetIterator docID
public abstract int docID();
-1 if #nextDoc() or #advance(int) were not called yet. From source file:org.codelibs.elasticsearch.search.profile.query.ProfileScorer.java
License:Apache License
@Override public DocIdSetIterator iterator() { final DocIdSetIterator in = scorer.iterator(); return new DocIdSetIterator() { @Override// w ww . j a v a 2s.co m public int advance(int target) throws IOException { profile.startTime(QueryTimingType.ADVANCE); try { return in.advance(target); } finally { profile.stopAndRecordTime(); } } @Override public int nextDoc() throws IOException { profile.startTime(QueryTimingType.NEXT_DOC); try { return in.nextDoc(); } finally { profile.stopAndRecordTime(); } } @Override public int docID() { return in.docID(); } @Override public long cost() { return in.cost(); } }; }
From source file:org.codelibs.elasticsearch.search.profile.query.ProfileScorer.java
License:Apache License
@Override public TwoPhaseIterator twoPhaseIterator() { final TwoPhaseIterator in = scorer.twoPhaseIterator(); if (in == null) { return null; }//from ww w . jav a2s .c o m final DocIdSetIterator inApproximation = in.approximation(); final DocIdSetIterator approximation = new DocIdSetIterator() { @Override public int advance(int target) throws IOException { profile.startTime(QueryTimingType.ADVANCE); try { return inApproximation.advance(target); } finally { profile.stopAndRecordTime(); } } @Override public int nextDoc() throws IOException { profile.startTime(QueryTimingType.NEXT_DOC); try { return inApproximation.nextDoc(); } finally { profile.stopAndRecordTime(); } } @Override public int docID() { return inApproximation.docID(); } @Override public long cost() { return inApproximation.cost(); } }; return new TwoPhaseIterator(approximation) { @Override public boolean matches() throws IOException { profile.startTime(QueryTimingType.MATCH); try { return in.matches(); } finally { profile.stopAndRecordTime(); } } @Override public float matchCost() { return in.matchCost(); } }; }
From source file:org.elasticsearch.common.lucene.search.function.MinScoreScorerTests.java
License:Apache License
private static Scorer scorer(int maxDoc, final int[] docs, final float[] scores, final boolean twoPhase) { final DocIdSetIterator iterator = twoPhase ? DocIdSetIterator.all(maxDoc) : iterator(docs); return new Scorer(null) { public DocIdSetIterator iterator() { if (twoPhase) { return TwoPhaseIterator.asDocIdSetIterator(twoPhaseIterator()); } else { return iterator; }//ww w. j ava2 s . c o m } public TwoPhaseIterator twoPhaseIterator() { if (twoPhase) { return new TwoPhaseIterator(iterator) { @Override public boolean matches() throws IOException { return Arrays.binarySearch(docs, iterator.docID()) >= 0; } @Override public float matchCost() { return 10; } }; } else { return null; } } @Override public int docID() { return iterator.docID(); } @Override public float score() throws IOException { final int idx = Arrays.binarySearch(docs, docID()); return scores[idx]; } @Override public int freq() throws IOException { return 1; } }; }
From source file:org.elasticsearch.common.lucene.search.XBooleanFilter.java
License:Apache License
static boolean iteratorMatch(DocIdSetIterator docIdSetIterator, int target) throws IOException { assert docIdSetIterator != null; int current = docIdSetIterator.docID(); if (current == DocIdSetIterator.NO_MORE_DOCS || target < current) { return false; } else {/*from w w w. j av a 2s . c om*/ if (current == target) { return true; } else { return docIdSetIterator.advance(target) == target; } } }
From source file:org.elasticsearch.index.search.geo.GeoDistanceRangeQuery.java
License:Apache License
@Override public Weight createWeight(IndexSearcher searcher, boolean needsScores) throws IOException { final Weight boundingBoxWeight; if (boundingBoxFilter != null) { boundingBoxWeight = searcher.createNormalizedWeight(boundingBoxFilter, false); } else {// w w w . j a va 2 s. co m boundingBoxWeight = null; } return new ConstantScoreWeight(this) { @Override public Scorer scorer(LeafReaderContext context) throws IOException { final DocIdSetIterator approximation; if (boundingBoxWeight != null) { Scorer s = boundingBoxWeight.scorer(context); if (s == null) { // if the approximation does not match anything, we're done return null; } approximation = s.iterator(); } else { approximation = DocIdSetIterator.all(context.reader().maxDoc()); } final MultiGeoPointValues values = indexFieldData.load(context).getGeoPointValues(); final TwoPhaseIterator twoPhaseIterator = new TwoPhaseIterator(approximation) { @Override public boolean matches() throws IOException { final int doc = approximation.docID(); values.setDocument(doc); final int length = values.count(); for (int i = 0; i < length; i++) { GeoPoint point = values.valueAt(i); if (distanceBoundingCheck.isWithin(point.lat(), point.lon())) { double d = fixedSourceDistance.calculate(point.lat(), point.lon()); if (d >= inclusiveLowerPoint && d <= inclusiveUpperPoint) { return true; } } } return false; } @Override public float matchCost() { if (distanceBoundingCheck == GeoDistance.ALWAYS_INSTANCE) { return 0.0f; } else { // TODO: is this right (up to 4 comparisons from GeoDistance.SimpleDistanceBoundingCheck)? return 4.0f; } } }; return new ConstantScoreScorer(this, score(), twoPhaseIterator); } }; }
From source file:org.elasticsearch.index.search.geo.LegacyGeoDistanceRangeQuery.java
License:Apache License
@Override public Weight createWeight(IndexSearcher searcher, boolean needsScores) throws IOException { final Weight boundingBoxWeight; if (boundingBoxFilter != null) { boundingBoxWeight = searcher.createNormalizedWeight(boundingBoxFilter, false); } else {/* w ww .j ava2 s . c om*/ boundingBoxWeight = null; } return new ConstantScoreWeight(this) { @Override public Scorer scorer(LeafReaderContext context) throws IOException { final DocIdSetIterator approximation; if (boundingBoxWeight != null) { Scorer s = boundingBoxWeight.scorer(context); if (s == null) { // if the approximation does not match anything, we're done return null; } approximation = s.iterator(); } else { approximation = DocIdSetIterator.all(context.reader().maxDoc()); } final MultiGeoPointValues values = indexFieldData.load(context).getGeoPointValues(); final TwoPhaseIterator twoPhaseIterator = new TwoPhaseIterator(approximation) { @Override public boolean matches() throws IOException { final int doc = approximation.docID(); values.setDocument(doc); final int length = values.count(); for (int i = 0; i < length; i++) { GeoPoint point = values.valueAt(i); if (bbox == null || GeoUtils.rectangleContainsPoint(bbox, point.lat(), point.lon())) { double d = geoDistance.calculate(lat, lon, point.lat(), point.lon(), DistanceUnit.DEFAULT); if (d >= inclusiveLowerPoint && d <= inclusiveUpperPoint) { return true; } } } return false; } @Override public float matchCost() { if (bbox != null) { // always within bounds so we're going to compute distance for every point return values.count(); } else { // TODO: come up with better estimate of boundary points return 4.0f; } } }; return new ConstantScoreScorer(this, score(), twoPhaseIterator); } }; }
From source file:org.elasticsearch.search.aggregations.bucket.composite.CompositeAggregator.java
License:Apache License
/** * Replay the documents that might contain a top bucket and pass top buckets to * the {@link this#deferredCollectors}./*from ww w . ja v a2 s . co m*/ */ private void runDeferredCollections() throws IOException { final boolean needsScores = needsScores(); Weight weight = null; if (needsScores) { Query query = context.query(); weight = context.searcher().createNormalizedWeight(query, true); } deferredCollectors.preCollection(); for (Entry entry : entries) { DocIdSetIterator docIdSetIterator = entry.docIdSet.iterator(); if (docIdSetIterator == null) { continue; } final LeafBucketCollector subCollector = deferredCollectors.getLeafCollector(entry.context); final LeafBucketCollector collector = queue.getLeafCollector(entry.context, getSecondPassCollector(subCollector)); DocIdSetIterator scorerIt = null; if (needsScores) { Scorer scorer = weight.scorer(entry.context); if (scorer != null) { scorerIt = scorer.iterator(); subCollector.setScorer(scorer); } } int docID; while ((docID = docIdSetIterator.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) { if (needsScores) { assert scorerIt != null && scorerIt.docID() < docID; scorerIt.advance(docID); // aggregations should only be replayed on matching documents assert scorerIt.docID() == docID; } collector.collect(docID); } } deferredCollectors.postCollection(); }
From source file:org.elasticsearch.search.aggregations.bucket.composite.SortedDocsProducer.java
License:Apache License
/** * Visits all non-deleted documents in <code>iterator</code> and fills the provided <code>queue</code> * with the top composite buckets extracted from the collection. * Documents that contain a top composite bucket are added in the provided <code>builder</code> if it is not null. * * Returns true if the queue is full and the current <code>leadSourceBucket</code> did not produce any competitive * composite buckets./*from w w w .j av a 2s . c om*/ */ protected boolean processBucket(CompositeValuesCollectorQueue queue, LeafReaderContext context, DocIdSetIterator iterator, Comparable<?> leadSourceBucket, @Nullable DocIdSetBuilder builder) throws IOException { final int[] topCompositeCollected = new int[1]; final boolean[] hasCollected = new boolean[1]; final LeafBucketCollector queueCollector = new LeafBucketCollector() { int lastDoc = -1; // we need to add the matching document in the builder // so we build a bulk adder from the approximate cost of the iterator // and rebuild the adder during the collection if needed int remainingBits = (int) Math.min(iterator.cost(), Integer.MAX_VALUE); DocIdSetBuilder.BulkAdder adder = builder == null ? null : builder.grow(remainingBits); @Override public void collect(int doc, long bucket) throws IOException { hasCollected[0] = true; int slot = queue.addIfCompetitive(); if (slot != -1) { topCompositeCollected[0]++; if (adder != null && doc != lastDoc) { if (remainingBits == 0) { // the cost approximation was lower than the real size, we need to grow the adder // by some numbers (128) to ensure that we can add the extra documents adder = builder.grow(128); remainingBits = 128; } adder.add(doc); remainingBits--; lastDoc = doc; } } } }; final Bits liveDocs = context.reader().getLiveDocs(); final LeafBucketCollector collector = queue.getLeafCollector(leadSourceBucket, context, queueCollector); while (iterator.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) { if (liveDocs == null || liveDocs.get(iterator.docID())) { collector.collect(iterator.docID()); } } if (queue.isFull() && hasCollected[0] && topCompositeCollected[0] == 0) { return true; } return false; }
From source file:org.elasticsearch.search.aggregations.bucket.MergingBucketsDeferringCollector.java
License:Apache License
/** * Replay the wrapped collector, but only on a selection of buckets. */// w w w. j a va2s . c o m @Override public void prepareSelectedBuckets(long... selectedBuckets) throws IOException { if (finished == false) { throw new IllegalStateException( "Cannot replay yet, collection is not finished: postCollect() has not been called"); } if (this.selectedBuckets != null) { throw new IllegalStateException("Already been replayed"); } final LongHash hash = new LongHash(selectedBuckets.length, BigArrays.NON_RECYCLING_INSTANCE); for (long bucket : selectedBuckets) { hash.add(bucket); } this.selectedBuckets = hash; boolean needsScores = collector.needsScores(); Weight weight = null; if (needsScores) { weight = searchContext.searcher().createNormalizedWeight(searchContext.query(), true); } for (Entry entry : entries) { final LeafBucketCollector leafCollector = collector.getLeafCollector(entry.context); DocIdSetIterator docIt = null; if (needsScores && entry.docDeltas.size() > 0) { Scorer scorer = weight.scorer(entry.context); // We don't need to check if the scorer is null // since we are sure that there are documents to replay // (entry.docDeltas it not empty). docIt = scorer.iterator(); leafCollector.setScorer(scorer); } final PackedLongValues.Iterator docDeltaIterator = entry.docDeltas.iterator(); final PackedLongValues.Iterator buckets = entry.buckets.iterator(); int doc = 0; for (long i = 0, end = entry.docDeltas.size(); i < end; ++i) { doc += docDeltaIterator.next(); final long bucket = buckets.next(); final long rebasedBucket = hash.find(bucket); if (rebasedBucket != -1) { if (needsScores) { if (docIt.docID() < doc) { docIt.advance(doc); } // aggregations should only be replayed on matching // documents assert docIt.docID() == doc; } leafCollector.collect(doc, rebasedBucket); } } } collector.postCollection(); }
From source file:org.elasticsearch.search.profile.ProfileScorer.java
License:Apache License
@Override public DocIdSetIterator iterator() { final DocIdSetIterator in = scorer.iterator(); return new DocIdSetIterator() { @Override/*from w w w . j a va2s . c o m*/ public int advance(int target) throws IOException { profile.startTime(ProfileBreakdown.TimingType.ADVANCE); try { return in.advance(target); } finally { profile.stopAndRecordTime(); } } @Override public int nextDoc() throws IOException { profile.startTime(ProfileBreakdown.TimingType.NEXT_DOC); try { return in.nextDoc(); } finally { profile.stopAndRecordTime(); } } @Override public int docID() { return in.docID(); } @Override public long cost() { return in.cost(); } }; }