dsmiley commented on code in PR #3418: URL: https://github.com/apache/solr/pull/3418#discussion_r2322678396
########## solr/core/src/java/org/apache/solr/handler/component/CombinedQueryComponent.java: ########## @@ -0,0 +1,598 @@ +/* + * 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.handler.component; + +import java.io.IOException; +import java.io.PrintWriter; +import java.io.StringWriter; +import java.lang.invoke.MethodHandles; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Objects; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.lucene.search.Explanation; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.Sort; +import org.apache.lucene.search.SortField; +import org.apache.solr.client.solrj.SolrServerException; +import org.apache.solr.common.SolrDocument; +import org.apache.solr.common.SolrDocumentList; +import org.apache.solr.common.SolrException; +import org.apache.solr.common.params.CombinerParams; +import org.apache.solr.common.params.CursorMarkParams; +import org.apache.solr.common.params.GroupParams; +import org.apache.solr.common.params.ShardParams; +import org.apache.solr.common.params.SolrParams; +import org.apache.solr.common.util.NamedList; +import org.apache.solr.common.util.SimpleOrderedMap; +import org.apache.solr.common.util.StrUtils; +import org.apache.solr.core.SolrCore; +import org.apache.solr.response.BasicResultContext; +import org.apache.solr.response.ResultContext; +import org.apache.solr.response.SolrQueryResponse; +import org.apache.solr.schema.IndexSchema; +import org.apache.solr.schema.SchemaField; +import org.apache.solr.search.DocListAndSet; +import org.apache.solr.search.QueryResult; +import org.apache.solr.search.SolrReturnFields; +import org.apache.solr.search.SortSpec; +import org.apache.solr.search.combine.QueryAndResponseCombiner; +import org.apache.solr.search.combine.ReciprocalRankFusion; +import org.apache.solr.util.SolrResponseUtil; +import org.apache.solr.util.plugin.SolrCoreAware; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * The CombinedQueryComponent class extends QueryComponent and provides support for executing + * multiple queries and combining their results. + */ +public class CombinedQueryComponent extends QueryComponent implements SolrCoreAware { + + private static final Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass()); + public static final String COMPONENT_NAME = "combined_query"; + protected NamedList<?> initParams; + private final Map<String, QueryAndResponseCombiner> combiners = new HashMap<>(); + private int maxCombinerQueries; + + @Override + public void init(NamedList<?> args) { + super.init(args); + this.initParams = args; + this.maxCombinerQueries = CombinerParams.DEFAULT_MAX_COMBINER_QUERIES; + } + + @Override + public void inform(SolrCore core) { + for (Map.Entry<String, ?> initEntry : initParams) { + if ("combiners".equals(initEntry.getKey()) + && initEntry.getValue() instanceof NamedList<?> all) { + for (int i = 0; i < all.size(); i++) { + String name = all.getName(i); + NamedList<?> combinerConfig = (NamedList<?>) all.getVal(i); + String className = (String) combinerConfig.get("class"); + QueryAndResponseCombiner combiner = + core.getResourceLoader().newInstance(className, QueryAndResponseCombiner.class); + combiner.init(combinerConfig); + combiners.compute( + name, + (k, existingCombiner) -> { + if (existingCombiner == null) { + return combiner; + } + throw new SolrException( + SolrException.ErrorCode.BAD_REQUEST, + "Found more than one combiner with same name"); + }); + } + } + } + Object maxQueries = initParams.get("maxCombinerQueries"); + if (maxQueries != null) { + this.maxCombinerQueries = Integer.parseInt(maxQueries.toString()); + } + combiners.computeIfAbsent( + CombinerParams.RECIPROCAL_RANK_FUSION, + key -> { + ReciprocalRankFusion reciprocalRankFusion = new ReciprocalRankFusion(); + reciprocalRankFusion.init(initParams); + return reciprocalRankFusion; + }); + } + + /** + * Overrides the prepare method to handle combined queries. + * + * @param rb the ResponseBuilder to prepare + * @throws IOException if an I/O error occurs during preparation + */ + @Override + public void prepare(ResponseBuilder rb) throws IOException { + if (rb instanceof CombinedQueryResponseBuilder crb) { + SolrParams params = crb.req.getParams(); + if (params.get(CursorMarkParams.CURSOR_MARK_PARAM) != null + || params.getBool(GroupParams.GROUP, false)) { + throw new SolrException( + SolrException.ErrorCode.BAD_REQUEST, "Unsupported functionality for Combined Queries."); + } + String[] queriesToCombineKeys = params.getParams(CombinerParams.COMBINER_QUERY); + if (queriesToCombineKeys.length > maxCombinerQueries) { + throw new SolrException( + SolrException.ErrorCode.BAD_REQUEST, + "Too many queries to combine: limit is " + maxCombinerQueries); + } + for (String queryKey : queriesToCombineKeys) { + final var unparsedQuery = params.get(queryKey); + ResponseBuilder rbNew = new ResponseBuilder(rb.req, new SolrQueryResponse(), rb.components); + rbNew.setQueryString(unparsedQuery); + super.prepare(rbNew); Review Comment: I think user-managed/standalone vs SolrCloud is orthogonal. This is about a single shard working correctly (in whatever Solr mode). IMO it's not optional for basic paging parameters to work correctly with one shard. I could imagine we'd prefer a mechanism for a SearchComponent to force the "shortCircuit"=false thereby ensuring there's always a distributed phase. Maybe that could be done by re-ordering SearchHandler's call to `getAndPrepShardHandler` to be _after_ `prepareComponents` (swap adjacent lines)? Then the prepare method of this component could force distrib and add the shortCircuit=false or something like that. And/or maybe a component should have a more elegant callback to communicate that it forces distributed search (even when there's one shard/core). This would overall simplify this component, no longer needing to handle paging in process(); instead do for distributed-search only. -- 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...@solr.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@solr.apache.org For additional commands, e-mail: issues-h...@solr.apache.org
