mayya-sharipova commented on a change in pull request #1351: LUCENE-9280: Collectors to skip noncompetitive documents URL: https://github.com/apache/lucene-solr/pull/1351#discussion_r395291803
########## File path: lucene/core/src/java/org/apache/lucene/search/LongDocValuesPointComparator.java ########## @@ -0,0 +1,208 @@ +/* + * 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.search; + +import org.apache.lucene.document.LongPoint; +import org.apache.lucene.index.DocValues; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.index.NumericDocValues; +import org.apache.lucene.index.PointValues; +import org.apache.lucene.util.DocIdSetBuilder; + +import java.io.IOException; +import java.util.Arrays; + +import static org.apache.lucene.search.FieldComparator.IteratorSupplierComparator; + +public class LongDocValuesPointComparator extends IteratorSupplierComparator<Long> { + private final String field; + private final int numHits; + private final boolean reverse; + private final long missingValue; + private final long[] values; + private long bottom; + private long topValue; + boolean hasTopValue = false; // indicates that topValue for searchAfter is set + protected NumericDocValues docValues; + private DocIdSetIterator iterator; + private PointValues pointValues; + private HitsThresholdChecker hitsThresholdChecker = null; + private int maxDoc; + private int maxDocVisited; + private int updateCounter = 0; + + public LongDocValuesPointComparator(String field, int numHits, boolean reverse, Long missingValue) { + this.field = field; + this.numHits = numHits; + this.reverse = reverse; + this.missingValue = missingValue != null ? missingValue : 0L; + this.values = new long[numHits]; + } + + @Override + void setHitsThresholdChecker(HitsThresholdChecker hitsThresholdChecker) { + this.hitsThresholdChecker = hitsThresholdChecker; + } + + private long getValueForDoc(int doc) throws IOException { + if (docValues.advanceExact(doc)) { + return docValues.longValue(); + } else { + return missingValue; + } + } + + @Override + public int compare(int slot1, int slot2) { + return Long.compare(values[slot1], values[slot2]); + } + + @Override + public void setTopValue(Long value) { + topValue = value; + hasTopValue = true; + } + + @Override + public Long value(int slot) { + return Long.valueOf(values[slot]); + } + + @Override + public LeafFieldComparator getLeafComparator(LeafReaderContext context) throws IOException { + docValues = DocValues.getNumeric(context.reader(), field); + iterator = docValues; + pointValues = context.reader().getPointValues(field); + maxDoc = context.reader().maxDoc(); + maxDocVisited = 0; + return this; + } + + @Override + public void setBottom(int slot) throws IOException { + this.bottom = values[slot]; + // can't use hitsThresholdChecker.isThresholdReached() as it uses > numHits, + // while we want to update iterator as soon as threshold reaches numHits + if (hitsThresholdChecker != null && (hitsThresholdChecker.getHitsThreshold() >= numHits)) { Review comment: @jimczi I am not very happy about this change because of 2 reasons: 1) We can't use `hitsThresholdChecker.isThresholdReached` as it checks for greater than numHits, but we need to check starting with equal, as if there are no competitive docs later `setBottom` will not be called. Do you know the reason why `hitsThresholdChecker.isThresholdReached` checks for greater than numHits and not greater or equal numHits? 2) totalHitsRelation may not end up to be set to TotalHits.Relation.GREATER_THAN_OR_EQUAL_TO, as we set it only when we have later competitive hits. I think it is better to have a previous implementation with a dedicated `updateIterator` function called from `TopFieldCollector`. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
