capistrant commented on code in PR #18383: URL: https://github.com/apache/druid/pull/18383#discussion_r2271787821
########## embedded-tests/src/test/java/org/apache/druid/testing/embedded/indexing/KafkaDataFormatsTest.java: ########## @@ -0,0 +1,722 @@ +/* + * 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.druid.testing.embedded.indexing; + +import com.fasterxml.jackson.core.JsonProcessingException; +import org.apache.druid.data.input.AvroStreamInputRowParser; +import org.apache.druid.data.input.InputFormat; +import org.apache.druid.data.input.avro.AvroExtensionsModule; +import org.apache.druid.data.input.avro.AvroParseSpec; +import org.apache.druid.data.input.avro.AvroStreamInputFormat; +import org.apache.druid.data.input.avro.InlineSchemaAvroBytesDecoder; +import org.apache.druid.data.input.avro.SchemaRegistryBasedAvroBytesDecoder; +import org.apache.druid.data.input.impl.CSVParseSpec; +import org.apache.druid.data.input.impl.CsvInputFormat; +import org.apache.druid.data.input.impl.DelimitedInputFormat; +import org.apache.druid.data.input.impl.DelimitedParseSpec; +import org.apache.druid.data.input.impl.DimensionsSpec; +import org.apache.druid.data.input.impl.JSONParseSpec; +import org.apache.druid.data.input.impl.JsonInputFormat; +import org.apache.druid.data.input.impl.StringDimensionSchema; +import org.apache.druid.data.input.impl.StringInputRowParser; +import org.apache.druid.data.input.impl.TimestampSpec; +import org.apache.druid.data.input.protobuf.FileBasedProtobufBytesDecoder; +import org.apache.druid.data.input.protobuf.ProtobufExtensionsModule; +import org.apache.druid.data.input.protobuf.ProtobufInputFormat; +import org.apache.druid.data.input.protobuf.SchemaRegistryBasedProtobufBytesDecoder; +import org.apache.druid.indexing.kafka.KafkaIndexTaskModule; +import org.apache.druid.indexing.kafka.simulate.KafkaResource; +import org.apache.druid.indexing.kafka.supervisor.KafkaSupervisorIOConfig; +import org.apache.druid.indexing.kafka.supervisor.KafkaSupervisorSpec; +import org.apache.druid.indexing.kafka.supervisor.KafkaSupervisorTuningConfig; +import org.apache.druid.java.util.common.StringUtils; +import org.apache.druid.java.util.common.parsers.JSONPathSpec; +import org.apache.druid.query.DruidMetrics; +import org.apache.druid.segment.indexing.DataSchema; +import org.apache.druid.testing.embedded.EmbeddedBroker; +import org.apache.druid.testing.embedded.EmbeddedCoordinator; +import org.apache.druid.testing.embedded.EmbeddedDruidCluster; +import org.apache.druid.testing.embedded.EmbeddedHistorical; +import org.apache.druid.testing.embedded.EmbeddedIndexer; +import org.apache.druid.testing.embedded.EmbeddedOverlord; +import org.apache.druid.testing.embedded.junit5.EmbeddedClusterTestBase; +import org.apache.druid.testing.tools.AvroEventSerializer; +import org.apache.druid.testing.tools.AvroSchemaRegistryEventSerializer; +import org.apache.druid.testing.tools.CsvEventSerializer; +import org.apache.druid.testing.tools.DelimitedEventSerializer; +import org.apache.druid.testing.tools.EventSerializer; +import org.apache.druid.testing.tools.JsonEventSerializer; +import org.apache.druid.testing.tools.ProtobufEventSerializer; +import org.apache.druid.testing.tools.ProtobufSchemaRegistryEventSerializer; +import org.apache.druid.testing.tools.StreamGenerator; +import org.apache.druid.testing.tools.WikipediaStreamEventStreamGenerator; +import org.apache.kafka.clients.producer.ProducerRecord; +import org.joda.time.Period; +import org.junit.jupiter.api.Assertions; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.Timeout; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.List; +import java.util.Map; + +/** + * Embedded test of Kafka indexing for different data formats. + * Formats Included: + * <ul> + * <li>Avro (with and without schema registry)</li> + * <li>CSV</li> + * <li>JSON</li> + * <li>Protobuf (with and without schema registry)</li> + * </ul> + * + * This tests both InputFormat and Parser. Parser is deprecated for Kafka Ingestion, and those tests will be removed in the future. + */ +public class KafkaDataFormatsTest extends EmbeddedClusterTestBase +{ + private static final long CYCLE_PADDING_MS = 100; + private static final int EVENTS_PER_SECOND = 6; + private static final List<String> WIKI_DIM_LIST = List.of("timestamp", "page", "language", "user", + "unpatrolled", "newPage", "robot", "anonymous", "namespace", + "continent", "country", "region", "city", "added", + "deleted", "delta"); + + private final EmbeddedBroker broker = new EmbeddedBroker(); + private final EmbeddedIndexer indexer = new EmbeddedIndexer(); + private final EmbeddedOverlord overlord = new EmbeddedOverlord(); + private final EmbeddedHistorical historical = new EmbeddedHistorical(); + private final EmbeddedCoordinator coordinator = new EmbeddedCoordinator(); + private KafkaResource kafkaServer; + private KafkaSchemaRegistryResource schemaRegistry; + + @Override + public EmbeddedDruidCluster createCluster() + { + final EmbeddedDruidCluster cluster = EmbeddedDruidCluster.withEmbeddedDerbyAndZookeeper().useContainerFriendlyHostname(); + + kafkaServer = new KafkaResource(); + + schemaRegistry = new KafkaSchemaRegistryResource(kafkaServer); + + indexer.addProperty("druid.segment.handoff.pollDuration", "PT0.1s") + .addProperty("druid.worker.capacity", "10"); + overlord.addProperty("druid.manager.segments.useIncrementalCache", "ifSynced") + .addProperty("druid.manager.segments.pollDuration", "PT0.1s"); + coordinator.addProperty("druid.manager.segments.useIncrementalCache", "ifSynced"); + cluster.addExtension(KafkaIndexTaskModule.class) + .addExtension(ProtobufExtensionsModule.class) + .addExtension(AvroExtensionsModule.class) + .useLatchableEmitter() + .addCommonProperty("druid.monitoring.emissionPeriod", "PT0.1s") + .addCommonProperty( + "druid.monitoring.monitors", + "[\"org.apache.druid.server.metrics.TaskCountStatsMonitor\"]" + ) + .addResource(kafkaServer) + .addResource(schemaRegistry) + .addServer(coordinator) + .addServer(overlord) + .addServer(indexer) + .addServer(broker) + .addServer(historical); + + return cluster; + } + + @Test + @Timeout(30) + public void test_indexKafka_avroDataFormat_withParser() throws IOException + { + kafkaServer.createTopicWithPartitions(dataSource, 3); + EventSerializer serializer = new AvroEventSerializer(); + int recordCount = generateStreamAndPublishToKafka(dataSource, serializer, false); + + Map<String, Object> avroSchema = createWikipediaAvroSchemaMap(); + + InlineSchemaAvroBytesDecoder avroBytesDecoder = overlord.bindings().jsonMapper().readValue( + StringUtils.format("{\"type\": \"schema_inline\", \"schema\": %s}", + overlord.bindings().jsonMapper().writeValueAsString(avroSchema)), + InlineSchemaAvroBytesDecoder.class + ); Review Comment: ya, sorry. missed these. The next commit will get rid of all the json string parsing -- 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]
