curcur commented on a change in pull request #11725: URL: https://github.com/apache/flink/pull/11725#discussion_r425554722
########## File path: flink-connectors/flink-connector-kafka/src/main/java/org/apache/flink/streaming/connectors/kafka/shuffle/FlinkKafkaShuffleProducer.java ########## @@ -0,0 +1,195 @@ +/* + * 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.flink.streaming.connectors.kafka.shuffle; + +import org.apache.flink.annotation.Internal; +import org.apache.flink.api.common.serialization.TypeInformationSerializationSchema; +import org.apache.flink.api.common.typeutils.TypeSerializer; +import org.apache.flink.api.java.functions.KeySelector; +import org.apache.flink.core.memory.DataOutputSerializer; +import org.apache.flink.runtime.state.KeyGroupRangeAssignment; +import org.apache.flink.streaming.api.watermark.Watermark; +import org.apache.flink.streaming.connectors.kafka.FlinkKafkaException; +import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer; +import org.apache.flink.util.Preconditions; +import org.apache.flink.util.PropertiesUtil; + +import org.apache.kafka.clients.producer.ProducerRecord; + +import java.io.IOException; +import java.io.Serializable; +import java.util.Properties; + +import static org.apache.flink.streaming.connectors.kafka.shuffle.FlinkKafkaShuffle.PARTITION_NUMBER; + +/** + * Flink Kafka Shuffle Producer Function. + * It is different from {@link FlinkKafkaProducer} in the way handling elements and watermarks + */ +@Internal +public class FlinkKafkaShuffleProducer<IN, KEY> extends FlinkKafkaProducer<IN> { + private final KafkaSerializer<IN> kafkaSerializer; + private final KeySelector<IN, KEY> keySelector; + private final int numberOfPartitions; + + FlinkKafkaShuffleProducer( + String defaultTopicId, + TypeInformationSerializationSchema<IN> schema, + Properties props, + KeySelector<IN, KEY> keySelector, + Semantic semantic, + int kafkaProducersPoolSize) { + super(defaultTopicId, (element, timestamp) -> null, props, semantic, kafkaProducersPoolSize); + + this.kafkaSerializer = new KafkaSerializer<>(schema.getSerializer()); + this.keySelector = keySelector; + + Preconditions.checkArgument( + props.getProperty(PARTITION_NUMBER) != null, + "Missing partition number for Kafka Shuffle"); + numberOfPartitions = PropertiesUtil.getInt(props, PARTITION_NUMBER, Integer.MIN_VALUE); + } + + /** + * This is the function invoked to handle each element. + * @param transaction transaction state; + * elements are written to Kafka in transactions to guarantee different level of data consistency + * @param next element to handle + * @param context context needed to handle the element + * @throws FlinkKafkaException for kafka error + */ + @Override + public void invoke(KafkaTransactionState transaction, IN next, Context context) throws FlinkKafkaException { + checkErroneous(); + + // write timestamp to Kafka if timestamp is available + Long timestamp = context.timestamp(); + + int[] partitions = getPartitions(transaction); + int partitionIndex; + try { + partitionIndex = KeyGroupRangeAssignment + .assignKeyToParallelOperator(keySelector.getKey(next), partitions.length, partitions.length); + } catch (Exception e) { + throw new RuntimeException("Fail to assign a partition number to record"); + } + + ProducerRecord<byte[], byte[]> record = new ProducerRecord<>( + defaultTopicId, partitionIndex, timestamp, null, kafkaSerializer.serializeRecord(next, timestamp)); Review comment: OK, I will do another pass. ---------------------------------------------------------------- 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
