vernedeng commented on code in PR #11501: URL: https://github.com/apache/inlong/pull/11501#discussion_r1855785041
########## inlong-sort/sort-flink/sort-flink-v1.18/sort-connectors/kafka/src/main/java/org/apache/inlong/sort/kafka/source/KafkaSource.java: ########## @@ -0,0 +1,258 @@ +/* + * 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.inlong.sort.kafka.source; + +import org.apache.inlong.sort.kafka.source.reader.KafkaSourceReader; + +import org.apache.flink.annotation.Internal; +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.annotation.VisibleForTesting; +import org.apache.flink.api.common.serialization.DeserializationSchema; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.connector.source.Boundedness; +import org.apache.flink.api.connector.source.Source; +import org.apache.flink.api.connector.source.SourceReader; +import org.apache.flink.api.connector.source.SourceReaderContext; +import org.apache.flink.api.connector.source.SplitEnumerator; +import org.apache.flink.api.connector.source.SplitEnumeratorContext; +import org.apache.flink.api.java.typeutils.ResultTypeQueryable; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.connector.base.source.reader.RecordsWithSplitIds; +import org.apache.flink.connector.base.source.reader.synchronization.FutureCompletingBlockingQueue; +import org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumState; +import org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumStateSerializer; +import org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumerator; +import org.apache.flink.connector.kafka.source.enumerator.initializer.OffsetsInitializer; +import org.apache.flink.connector.kafka.source.enumerator.subscriber.KafkaSubscriber; +import org.apache.flink.connector.kafka.source.metrics.KafkaSourceReaderMetrics; +import org.apache.flink.connector.kafka.source.reader.KafkaPartitionSplitReader; +import org.apache.flink.connector.kafka.source.reader.KafkaRecordEmitter; +import org.apache.flink.connector.kafka.source.reader.deserializer.KafkaRecordDeserializationSchema; +import org.apache.flink.connector.kafka.source.reader.fetcher.KafkaSourceFetcherManager; +import org.apache.flink.connector.kafka.source.split.KafkaPartitionSplit; +import org.apache.flink.connector.kafka.source.split.KafkaPartitionSplitSerializer; +import org.apache.flink.core.io.SimpleVersionedSerializer; +import org.apache.flink.metrics.MetricGroup; +import org.apache.flink.util.UserCodeClassLoader; +import org.apache.flink.util.function.SerializableSupplier; +import org.apache.kafka.clients.consumer.ConsumerRecord; + +import javax.annotation.Nullable; + +import java.io.IOException; +import java.util.Collection; +import java.util.Optional; +import java.util.Properties; +import java.util.function.Consumer; +import java.util.function.Supplier; + +/** + * The Source implementation of Kafka. Please use a {@link KafkaSourceBuilder} to construct a {@link + * KafkaSource}. The following example shows how to create a KafkaSource emitting records of <code> + * String</code> type. + * + * <pre>{@code + * KafkaSource<String> source = KafkaSource + * .<String>builder() + * .setBootstrapServers(KafkaSourceTestEnv.brokerConnectionStrings) + * .setGroupId("MyGroup") + * .setTopics(Arrays.asList(TOPIC1, TOPIC2)) + * .setDeserializer(new TestingKafkaRecordDeserializationSchema()) + * .setStartingOffsets(OffsetsInitializer.earliest()) + * .build(); + * }</pre> + * + * <p>{@link org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumerator} only supports + * adding new splits and not removing splits in split discovery. + * + * <p>See {@link KafkaSourceBuilder} for more details on how to configure this source. + * + * @param <OUT> the output type of the source. + * copied from org.apache.flink:flink-connector-kafka:1.18.0 + */ +// TODO: Add a variable metricSchema to report audit information +@PublicEvolving Review Comment: This flink annotation should be removed ########## inlong-sort/sort-flink/sort-flink-v1.18/sort-connectors/kafka/src/main/java/org/apache/inlong/sort/kafka/source/KafkaSource.java: ########## @@ -0,0 +1,258 @@ +/* + * 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.inlong.sort.kafka.source; + +import org.apache.inlong.sort.kafka.source.reader.KafkaSourceReader; + +import org.apache.flink.annotation.Internal; +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.annotation.VisibleForTesting; +import org.apache.flink.api.common.serialization.DeserializationSchema; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.connector.source.Boundedness; +import org.apache.flink.api.connector.source.Source; +import org.apache.flink.api.connector.source.SourceReader; +import org.apache.flink.api.connector.source.SourceReaderContext; +import org.apache.flink.api.connector.source.SplitEnumerator; +import org.apache.flink.api.connector.source.SplitEnumeratorContext; +import org.apache.flink.api.java.typeutils.ResultTypeQueryable; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.connector.base.source.reader.RecordsWithSplitIds; +import org.apache.flink.connector.base.source.reader.synchronization.FutureCompletingBlockingQueue; +import org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumState; +import org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumStateSerializer; +import org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumerator; +import org.apache.flink.connector.kafka.source.enumerator.initializer.OffsetsInitializer; +import org.apache.flink.connector.kafka.source.enumerator.subscriber.KafkaSubscriber; +import org.apache.flink.connector.kafka.source.metrics.KafkaSourceReaderMetrics; +import org.apache.flink.connector.kafka.source.reader.KafkaPartitionSplitReader; +import org.apache.flink.connector.kafka.source.reader.KafkaRecordEmitter; +import org.apache.flink.connector.kafka.source.reader.deserializer.KafkaRecordDeserializationSchema; +import org.apache.flink.connector.kafka.source.reader.fetcher.KafkaSourceFetcherManager; +import org.apache.flink.connector.kafka.source.split.KafkaPartitionSplit; +import org.apache.flink.connector.kafka.source.split.KafkaPartitionSplitSerializer; +import org.apache.flink.core.io.SimpleVersionedSerializer; +import org.apache.flink.metrics.MetricGroup; +import org.apache.flink.util.UserCodeClassLoader; +import org.apache.flink.util.function.SerializableSupplier; +import org.apache.kafka.clients.consumer.ConsumerRecord; + +import javax.annotation.Nullable; + +import java.io.IOException; +import java.util.Collection; +import java.util.Optional; +import java.util.Properties; +import java.util.function.Consumer; +import java.util.function.Supplier; + +/** + * The Source implementation of Kafka. Please use a {@link KafkaSourceBuilder} to construct a {@link + * KafkaSource}. The following example shows how to create a KafkaSource emitting records of <code> + * String</code> type. + * + * <pre>{@code + * KafkaSource<String> source = KafkaSource + * .<String>builder() + * .setBootstrapServers(KafkaSourceTestEnv.brokerConnectionStrings) + * .setGroupId("MyGroup") + * .setTopics(Arrays.asList(TOPIC1, TOPIC2)) + * .setDeserializer(new TestingKafkaRecordDeserializationSchema()) + * .setStartingOffsets(OffsetsInitializer.earliest()) + * .build(); + * }</pre> + * + * <p>{@link org.apache.flink.connector.kafka.source.enumerator.KafkaSourceEnumerator} only supports + * adding new splits and not removing splits in split discovery. + * + * <p>See {@link KafkaSourceBuilder} for more details on how to configure this source. + * + * @param <OUT> the output type of the source. + * copied from org.apache.flink:flink-connector-kafka:1.18.0 + */ +// TODO: Add a variable metricSchema to report audit information +@PublicEvolving +public class KafkaSource<OUT> + implements + Source<OUT, KafkaPartitionSplit, KafkaSourceEnumState>, + ResultTypeQueryable<OUT> { + + private static final long serialVersionUID = -8755372893283732098L; + // Users can choose only one of the following ways to specify the topics to consume from. + private final KafkaSubscriber subscriber; + // Users can specify the starting / stopping offset initializer. + private final OffsetsInitializer startingOffsetsInitializer; + private final OffsetsInitializer stoppingOffsetsInitializer; + // Boundedness + private final Boundedness boundedness; + private final KafkaRecordDeserializationSchema<OUT> deserializationSchema; + // The configurations. + private final Properties props; + // Client rackId callback + private final SerializableSupplier<String> rackIdSupplier; + + KafkaSource( + KafkaSubscriber subscriber, + OffsetsInitializer startingOffsetsInitializer, + @Nullable OffsetsInitializer stoppingOffsetsInitializer, + Boundedness boundedness, + KafkaRecordDeserializationSchema<OUT> deserializationSchema, + Properties props, + SerializableSupplier<String> rackIdSupplier) { + this.subscriber = subscriber; + this.startingOffsetsInitializer = startingOffsetsInitializer; + this.stoppingOffsetsInitializer = stoppingOffsetsInitializer; + this.boundedness = boundedness; + this.deserializationSchema = deserializationSchema; + this.props = props; + this.rackIdSupplier = rackIdSupplier; + } + + /** + * Get a kafkaSourceBuilder to build a {@link KafkaSource}. + * + * @return a Kafka source builder. + */ + public static <OUT> KafkaSourceBuilder<OUT> builder() { + return new KafkaSourceBuilder<>(); + } + + @Override + public Boundedness getBoundedness() { + return this.boundedness; + } + + @Internal + @Override + public SourceReader<OUT, KafkaPartitionSplit> createReader(SourceReaderContext readerContext) + throws Exception { + return createReader(readerContext, (ignore) -> { + }); + } + + @VisibleForTesting + SourceReader<OUT, KafkaPartitionSplit> createReader( + SourceReaderContext readerContext, Consumer<Collection<String>> splitFinishedHook) + throws Exception { + FutureCompletingBlockingQueue<RecordsWithSplitIds<ConsumerRecord<byte[], byte[]>>> elementsQueue = + new FutureCompletingBlockingQueue<>(); + deserializationSchema.open( + new DeserializationSchema.InitializationContext() { + + @Override + public MetricGroup getMetricGroup() { + return readerContext.metricGroup().addGroup("deserializer"); + } + + @Override + public UserCodeClassLoader getUserCodeClassLoader() { + return readerContext.getUserCodeClassLoader(); + } + }); + final KafkaSourceReaderMetrics kafkaSourceReaderMetrics = + new KafkaSourceReaderMetrics(readerContext.metricGroup()); + + Supplier<KafkaPartitionSplitReader> splitReaderSupplier = + () -> new KafkaPartitionSplitReader( + props, + readerContext, + kafkaSourceReaderMetrics, + Optional.ofNullable(rackIdSupplier) + .map(Supplier::get) + .orElse(null)); + KafkaRecordEmitter<OUT> recordEmitter = new KafkaRecordEmitter<>(deserializationSchema); + + return new KafkaSourceReader<>( + elementsQueue, + new KafkaSourceFetcherManager( + elementsQueue, splitReaderSupplier::get, splitFinishedHook), + recordEmitter, + toConfiguration(props), + readerContext, + kafkaSourceReaderMetrics); + } + + @Internal + @Override + public SplitEnumerator<KafkaPartitionSplit, KafkaSourceEnumState> createEnumerator( + SplitEnumeratorContext<KafkaPartitionSplit> enumContext) { + return new KafkaSourceEnumerator( + subscriber, + startingOffsetsInitializer, + stoppingOffsetsInitializer, + props, + enumContext, + boundedness); + } + + @Internal Review Comment: ditto -- 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: commits-unsubscr...@inlong.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
