jainankitk commented on code in PR #14439: URL: https://github.com/apache/lucene/pull/14439#discussion_r2049534867
########## lucene/sandbox/src/java/org/apache/lucene/sandbox/facet/plain/histograms/PointTreeBulkCollector.java: ########## @@ -0,0 +1,219 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.lucene.sandbox.facet.plain.histograms; + +import static org.apache.lucene.search.DocIdSetIterator.NO_MORE_DOCS; + +import java.io.IOException; +import java.util.function.Function; +import org.apache.lucene.index.PointValues; +import org.apache.lucene.internal.hppc.LongIntHashMap; +import org.apache.lucene.search.CollectionTerminatedException; +import org.apache.lucene.search.DocIdSetIterator; +import org.apache.lucene.util.ArrayUtil; + +class PointTreeBulkCollector { + static boolean collect( + final PointValues pointValues, + final long bucketWidth, + final LongIntHashMap collectorCounts, + final int maxBuckets) + throws IOException { + // TODO: Do we really need pointValues.getDocCount() == pointValues.size() + if (pointValues == null + || pointValues.getNumDimensions() != 1 + || pointValues.getDocCount() != pointValues.size() + || ArrayUtil.getValue(pointValues.getBytesPerDimension()) == null) { + return false; + } + + final Function<byte[], Long> byteToLong = + ArrayUtil.getValue(pointValues.getBytesPerDimension()); + final long minValue = getLongFromByte(byteToLong, pointValues.getMinPackedValue()); + final long maxValue = getLongFromByte(byteToLong, pointValues.getMaxPackedValue()); + long leafMinBucket = Math.floorDiv(minValue, bucketWidth); + long leafMaxBucket = Math.floorDiv(maxValue, bucketWidth); + + // We want that # leaf nodes is more than # buckets so that we can completely skip over + // some of the leaf nodes. Higher this ratio, more efficient it is than naive approach! + if ((pointValues.size() / 512) < (leafMaxBucket - leafMinBucket)) { + return false; Review Comment: The user does not need to get anything. We will just skip the optimized path and fall back to the original execution plan -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
