flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From rmetzger <...@git.apache.org>
Subject [GitHub] flink pull request #2369: [FLINK-4035] Add a streaming connector for Apache ...
Date Mon, 26 Sep 2016 14:46:05 GMT
Github user rmetzger commented on a diff in the pull request:

    https://github.com/apache/flink/pull/2369#discussion_r80491475
  
    --- Diff: flink-streaming-connectors/flink-connector-kafka-0.10/src/main/java/org/apache/flink/streaming/connectors/kafka/FlinkKafkaProducer010.java
---
    @@ -0,0 +1,399 @@
    +/*
    + * 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;
    +
    +import org.apache.flink.api.common.functions.IterationRuntimeContext;
    +import org.apache.flink.api.common.functions.RichFunction;
    +import org.apache.flink.api.common.functions.RuntimeContext;
    +import org.apache.flink.api.java.typeutils.GenericTypeInfo;
    +import org.apache.flink.configuration.Configuration;
    +import org.apache.flink.streaming.api.datastream.DataStream;
    +import org.apache.flink.streaming.api.datastream.DataStreamSink;
    +import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
    +import org.apache.flink.streaming.api.functions.sink.SinkFunction;
    +import org.apache.flink.streaming.api.operators.StreamSink;
    +import org.apache.flink.streaming.connectors.kafka.partitioner.FixedPartitioner;
    +import org.apache.flink.streaming.connectors.kafka.partitioner.KafkaPartitioner;
    +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord;
    +import org.apache.flink.streaming.util.serialization.KeyedSerializationSchema;
    +import org.apache.flink.streaming.util.serialization.KeyedSerializationSchemaWrapper;
    +import org.apache.flink.streaming.util.serialization.SerializationSchema;
    +import org.apache.kafka.clients.producer.ProducerRecord;
    +
    +import java.util.Properties;
    +
    +import static org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducerBase.getPropertiesFromBrokerList;
    +
    +
    +/**
    + * Flink Sink to produce data into a Kafka topic. This producer is compatible with Kafka
0.10.x
    + *
    + * Implementation note: This producer is a hybrid between a regular regular sink function
(a)
    + * and a custom operator (b).
    + *
    + * For (a), the class implements the SinkFunction and RichFunction interfaces.
    + * For (b), it extends the StreamTask class.
    + *
    + * Details about approach (a):
    + *
    + *  Pre Kafka 0.10 producers only follow approach (a), allowing users to use the producer
using the
    + *  DataStream.addSink() method.
    + *  Since the APIs exposed in that variant do not allow accessing the the timestamp attached
to the record
    + *  the Kafka 0.10 producer has a section invocation option, approach (b).
    + *
    + * Details about approach (b):
    + *  Kafka 0.10 supports writing the timestamp attached to a record to Kafka. When adding
the
    + *  FlinkKafkaProducer010 using the FlinkKafkaProducer010.writeToKafka() method, the
Kafka producer
    + *  can access the internal record timestamp of the record and write it to Kafka.
    + *
    + * All methods and constructors in this class are marked with the approach they are needed
for.
    + */
    +public class FlinkKafkaProducer010<T> extends StreamSink<T> implements SinkFunction<T>,
RichFunction {
    +
    +	/**
    +	 * Flag controlling whether we are writing the Flink record's timestamp into Kafka.
    +	 */
    +	private boolean writeTimestampToKafka = false;
    +
    +	// ---------------------- "Constructors" for timestamp writing ------------------
    +
    +	/**
    +	 * Creates a FlinkKafkaProducer for a given topic. The sink produces a DataStream to
    +	 * the topic.
    +	 *
    +	 * This constructor allows writing timestamps to Kafka, it follow approach (b) (see
above)
    +	 *
    +	 * @param inStream The stream to write to Kafka
    +	 * @param topicId ID of the Kafka topic.
    +	 * @param serializationSchema User defined serialization schema supporting key/value
messages
    +	 * @param producerConfig Properties with the producer configuration.
    +	 */
    +	public static <T> FlinkKafkaProducer010Configuration writeToKafka(DataStream<T>
inStream,
    +										String topicId,
    +										KeyedSerializationSchema<T> serializationSchema,
    +										Properties producerConfig) {
    +		return writeToKafka(inStream, topicId, serializationSchema, producerConfig, new FixedPartitioner<T>());
    +	}
    +
    +
    +	/**
    +	 * Creates a FlinkKafkaProducer for a given topic. the sink produces a DataStream to
    +	 * the topic.
    +	 *
    +	 * This constructor allows writing timestamps to Kafka, it follow approach (b) (see
above)
    +	 *
    +	 * @param inStream The stream to write to Kafka
    +	 * @param topicId ID of the Kafka topic.
    +	 * @param serializationSchema User defined (keyless) serialization schema.
    +	 * @param producerConfig Properties with the producer configuration.
    +	 */
    +	public static <T> FlinkKafkaProducer010Configuration writeToKafka(DataStream<T>
inStream,
    --- End diff --
    
    Its a good idea, I'll rename the methods


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message