cpoerschke commented on code in PR #2382: URL: https://github.com/apache/solr/pull/2382#discussion_r1604773128
########## solr/modules/monitor/src/java/org/apache/solr/monitor/update/MonitorUpdateRequestProcessor.java: ########## @@ -0,0 +1,257 @@ +/* + * + * * 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.monitor.update; + +import java.io.IOException; +import java.io.Reader; +import java.util.ArrayList; +import java.util.List; +import java.util.Map; +import java.util.Optional; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.document.Document; +import org.apache.lucene.document.Field; +import org.apache.lucene.document.InvertableType; +import org.apache.lucene.document.StoredValue; +import org.apache.lucene.index.DocValuesType; +import org.apache.lucene.index.IndexableField; +import org.apache.lucene.index.IndexableFieldType; +import org.apache.lucene.monitor.MonitorFields; +import org.apache.lucene.monitor.MonitorQuery; +import org.apache.lucene.monitor.Presearcher; +import org.apache.lucene.monitor.QCEVisitor; +import org.apache.lucene.util.BytesRef; +import org.apache.solr.common.SolrException; +import org.apache.solr.common.SolrInputDocument; +import org.apache.solr.common.util.JavaBinCodec; +import org.apache.solr.core.SolrCore; +import org.apache.solr.monitor.MonitorConstants; +import org.apache.solr.monitor.MonitorSchemaFields; +import org.apache.solr.monitor.SimpleQueryParser; +import org.apache.solr.schema.IndexSchema; +import org.apache.solr.schema.SchemaField; +import org.apache.solr.update.AddUpdateCommand; +import org.apache.solr.update.processor.UpdateRequestProcessor; + +public class MonitorUpdateRequestProcessor extends UpdateRequestProcessor { + + private final SolrCore core; + private final IndexSchema indexSchema; + private final Presearcher presearcher; + private final MonitorSchemaFields monitorSchemaFields; + + public MonitorUpdateRequestProcessor( + UpdateRequestProcessor next, SolrCore core, Presearcher presearcher) { + super(next); + this.core = core; + this.indexSchema = core.getLatestSchema(); + this.presearcher = presearcher; + this.monitorSchemaFields = new MonitorSchemaFields(indexSchema); + } + + @Override + public void processAdd(AddUpdateCommand cmd) throws IOException { + var solrInputDocument = cmd.getSolrInputDocument(); + var queryId = + (String) solrInputDocument.getFieldValue(indexSchema.getUniqueKeyField().getName()); + var queryFieldValue = solrInputDocument.getFieldValue(MonitorFields.MONITOR_QUERY); + if (queryFieldValue != null) { + var payload = + Optional.ofNullable(solrInputDocument.getFieldValue(MonitorFields.PAYLOAD)) + .map(Object::toString) + .orElse(null); + List<SolrInputDocument> children = + Optional.of(queryFieldValue) + .filter(String.class::isInstance) + .map(String.class::cast) + .map( + queryStr -> + new MonitorQuery( + queryId, SimpleQueryParser.parse(queryStr, core), queryStr, Map.of())) + .stream() + .flatMap(monitorQuery -> decompose(monitorQuery, payload)) + .map(this::toSolrInputDoc) + .collect(Collectors.toList()); + if (children.isEmpty()) { + throw new SolrException( + SolrException.ErrorCode.INVALID_STATE, "Query could not be decomposed"); + } + SolrInputDocument firstChild = children.get(0); + if (solrInputDocument.hasChildDocuments()) { + solrInputDocument.getChildDocuments().clear(); + } + solrInputDocument.addChildDocuments(children.stream().skip(1).collect(Collectors.toList())); + if (solrInputDocument.hasChildDocuments()) { + solrInputDocument + .getChildDocuments() + .forEach( + child -> + solrInputDocument.forEach( + field -> { + if (!MonitorFields.RESERVED_MONITOR_FIELDS.contains(field.getName())) { + child.addField(field.getName(), field.getValue()); + } Review Comment: I see a mix of 'engineering' and 'product' complexity here, perhaps relatively marginal engineering complexity but still, and it's not yet clear to me when/why additional non-monitor data fields would be sent from a use case/product perspective. To elaborate a bit more: * 'engineering' aspects: * supporting additional non-monitor data fields introduces the 'reserved vs. non-reserved monitor fields' concept i.e. * the non-reserved fields need to be copied over but the reserved fields must not be copied over because they are already there. * this needs to be understood at the implementation level and covered with test functionality. * the concept is present in the update processor and in the aliasing prefetcher. * 'product' aspects: * _"pass (only) a query id and a query in each document"_ is a very accessible user interface. * _"pass (only) a query id and a query in each document, and optionally a payload"_ is a more sophisticated user interface and more explanation/documentation is needed about the optional payload. * _"pass a query id and a query in each document, and optionally a payload, and anything else you like with some caveats"_ seems a less accessible user interface, with more choice i.e. decision making required of the user. My preference for an initial phase would be the minimal product approach i.e. disallowing additional fields. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
