dsmiley commented on a change in pull request #1171: SOLR-13892: Add 'top-level' docValues Join implementation URL: https://github.com/apache/lucene-solr/pull/1171#discussion_r370307365
########## File path: solr/core/src/java/org/apache/solr/search/TopLevelJoinQuery.java ########## @@ -0,0 +1,218 @@ +/* + * 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.solr.search; + +import java.io.IOException; +import java.lang.invoke.MethodHandles; + +import org.apache.lucene.index.DocValues; +import org.apache.lucene.index.LeafReader; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.index.SortedSetDocValues; +import org.apache.lucene.search.Collector; +import org.apache.lucene.search.ConstantScoreScorer; +import org.apache.lucene.search.ConstantScoreWeight; +import org.apache.lucene.search.DocIdSetIterator; +import org.apache.lucene.search.IndexSearcher; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.ScoreMode; +import org.apache.lucene.search.Scorer; +import org.apache.lucene.search.TwoPhaseIterator; +import org.apache.lucene.search.Weight; +import org.apache.lucene.util.BytesRef; +import org.apache.lucene.util.LongBitSet; +import org.apache.solr.common.SolrException; +import org.apache.solr.schema.IndexSchema; +import org.apache.solr.schema.SchemaField; +import org.apache.solr.search.join.MultiValueTermOrdinalCollector; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class TopLevelJoinQuery extends JoinQuery { + private static final Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass()); + + public TopLevelJoinQuery(String fromField, String toField, String coreName, Query subQuery) { + super(fromField, toField, coreName, subQuery); + } + + @Override + public Weight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException { + if (! (searcher instanceof SolrIndexSearcher)) { + log.debug("Falling back to JoinQueryWeight because searcher [{}] is not the required SolrIndexSearcher", searcher); + return super.createWeight(searcher, scoreMode, boost); + } + + final SolrIndexSearcher solrSearcher = (SolrIndexSearcher) searcher; + final JoinQueryWeight weight = new JoinQueryWeight(solrSearcher, ScoreMode.COMPLETE_NO_SCORES, 1.0f); + final SolrIndexSearcher fromSearcher = weight.fromSearcher; + final SolrIndexSearcher toSearcher = weight.toSearcher; + + try { + final SortedSetDocValues topLevelFromDocValues = validateAndFetchDocValues(fromSearcher, fromField, "from"); + final SortedSetDocValues topLevelToDocValues = validateAndFetchDocValues(toSearcher, toField, "to"); + if (topLevelFromDocValues.getValueCount() == 0 || topLevelToDocValues.getValueCount() == 0) { + return createNoMatchesWeight(boost); + } + + final LongBitSet fromOrdBitSet = findOrdinalsMatchingFromQuery(fromSearcher, topLevelFromDocValues); + final LongBitSet toOrdBitSet = new LongBitSet(topLevelToDocValues.getValueCount()); + final BitsetBounds toBitsetBounds = convertFromOrdinalsIntoToField(fromOrdBitSet, topLevelFromDocValues, toOrdBitSet, topLevelToDocValues); + + final boolean toMultivalued = toSearcher.getSchema().getFieldOrNull(toField).multiValued(); + return new ConstantScoreWeight(this, boost) { + public Scorer scorer(LeafReaderContext context) throws IOException { + if (toBitsetBounds.lower == BitsetBounds.NO_MATCHES) { + return null; + } + + final DocIdSetIterator toApproximation = (toMultivalued) ? context.reader().getSortedSetDocValues(toField) : + context.reader().getSortedDocValues(toField); + if (toApproximation == null) { + return null; + } + + final int docBase = context.docBase; + return new ConstantScoreScorer(this, this.score(), scoreMode, new TwoPhaseIterator(toApproximation) { + public boolean matches() throws IOException { + final boolean hasDoc = topLevelToDocValues.advanceExact(docBase + approximation.docID()); + if (hasDoc) { + for (long ord = topLevelToDocValues.nextOrd(); ord != -1L; ord = topLevelToDocValues.nextOrd()) { + if (toOrdBitSet.get(ord)) { + return true; + } + } + } + return false; + } + + public float matchCost() { + return 10.0F; + } + }); + + } + + public boolean isCacheable(LeafReaderContext ctx) { + return false; + } + }; + } catch (IOException e) { + throw new RuntimeException(e); + } + } + + private Weight createNoMatchesWeight(float boost) { + return new ConstantScoreWeight(this, boost) { + @Override + public Scorer scorer(LeafReaderContext context) throws IOException { + return null; + } + + @Override + public boolean isCacheable(LeafReaderContext ctx) { + return false; + } + }; + } + + private SortedSetDocValues validateAndFetchDocValues(SolrIndexSearcher solrSearcher, String fieldName, String querySide) throws IOException { + final IndexSchema schema = solrSearcher.getSchema(); + final SchemaField field = schema.getFieldOrNull(fieldName); + if (field == null) { + throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, querySide + " field '" + fieldName + "' does not exist"); + } + + if (!field.hasDocValues()) { + throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, + "'top-level' join queries require both 'from' and 'to' fields to have docValues, but " + querySide + + " field [" + fieldName + "] does not."); + } + + final LeafReader leafReader = solrSearcher.getSlowAtomicReader(); + if (field.multiValued()) { + return DocValues.getSortedSet(leafReader, fieldName); + } + return DocValues.singleton(DocValues.getSorted(leafReader, fieldName)); + } + + private LongBitSet findOrdinalsMatchingFromQuery(SolrIndexSearcher fromSearcher, SortedSetDocValues fromDocValues) throws IOException { Review comment: Couldn't you rename the method and it's variables to remove "From" and it would be just as valid? Okay I see why not; this is an instance method that refers to 'fromField' but if that's the only distinction then maybe it should be a static method and take that argument? ---------------------------------------------------------------- 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
