[
https://issues.apache.org/jira/browse/FLINK-9697?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16649173#comment-16649173
]
ASF GitHub Bot commented on FLINK-9697:
---------------------------------------
eliaslevy commented on a change in pull request #6703: [FLINK-9697] Provide
connector for Kafka 2.0.0
URL: https://github.com/apache/flink/pull/6703#discussion_r224964438
##########
File path:
flink-connectors/flink-connector-kafka/src/main/java/org/apache/flink/streaming/connectors/kafka/FlinkKafkaConsumer.java
##########
@@ -0,0 +1,321 @@
+/*
+ * 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.annotation.PublicEvolving;
+import org.apache.flink.api.common.serialization.DeserializationSchema;
+import org.apache.flink.metrics.MetricGroup;
+import org.apache.flink.streaming.api.functions.AssignerWithPeriodicWatermarks;
+import
org.apache.flink.streaming.api.functions.AssignerWithPunctuatedWatermarks;
+import org.apache.flink.streaming.api.operators.StreamingRuntimeContext;
+import org.apache.flink.streaming.connectors.kafka.config.OffsetCommitMode;
+import org.apache.flink.streaming.connectors.kafka.internal.KafkaFetcher;
+import
org.apache.flink.streaming.connectors.kafka.internal.KafkaPartitionDiscoverer;
+import org.apache.flink.streaming.connectors.kafka.internals.AbstractFetcher;
+import
org.apache.flink.streaming.connectors.kafka.internals.AbstractPartitionDiscoverer;
+import
org.apache.flink.streaming.connectors.kafka.internals.KafkaTopicPartition;
+import
org.apache.flink.streaming.connectors.kafka.internals.KafkaTopicsDescriptor;
+import
org.apache.flink.streaming.util.serialization.KeyedDeserializationSchema;
+import
org.apache.flink.streaming.util.serialization.KeyedDeserializationSchemaWrapper;
+import org.apache.flink.util.PropertiesUtil;
+import org.apache.flink.util.SerializedValue;
+
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.consumer.KafkaConsumer;
+import org.apache.kafka.clients.consumer.OffsetAndTimestamp;
+import org.apache.kafka.common.TopicPartition;
+import org.apache.kafka.common.serialization.ByteArrayDeserializer;
+
+import java.util.Collection;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Properties;
+import java.util.regex.Pattern;
+
+import static org.apache.flink.util.Preconditions.checkNotNull;
+import static org.apache.flink.util.PropertiesUtil.getBoolean;
+import static org.apache.flink.util.PropertiesUtil.getLong;
+
+/**
+ * The Flink Kafka Consumer is a streaming data source that pulls a parallel
data stream from
+ * Apache Kafka 2.x. The consumer can run in multiple parallel instances, each
of which will pull
+ * data from one or more Kafka partitions.
+ *
+ * <p>The Flink Kafka Consumer participates in checkpointing and guarantees
that no data is lost
+ * during a failure, and that the computation processes elements "exactly
once".
+ * (Note: These guarantees naturally assume that Kafka itself does not loose
any data.)</p>
+ *
+ * <p>Please note that Flink snapshots the offsets internally as part of its
distributed checkpoints. The offsets
+ * committed to Kafka / ZooKeeper are only to bring the outside view of
progress in sync with Flink's view
+ * of the progress. That way, monitoring and other jobs can get a view of how
far the Flink Kafka consumer
+ * has consumed a topic.</p>
+ *
+ * <p>Please refer to Kafka's documentation for the available configuration
properties:
+ * http://kafka.apache.org/documentation.html#newconsumerconfigs</p>
+ */
+@PublicEvolving
+public class FlinkKafkaConsumer<T> extends FlinkKafkaConsumerBase<T> {
+
+ /** Configuration key to change the polling timeout. **/
+ public static final String KEY_POLL_TIMEOUT = "flink.poll-timeout";
+
+ /** From Kafka's Javadoc: The time, in milliseconds, spent waiting in
poll if data is not
+ * available. If 0, returns immediately with any records that are
available now. */
+ public static final long DEFAULT_POLL_TIMEOUT = 100L;
+
+ //
------------------------------------------------------------------------
+
+ /** User-supplied properties for Kafka. **/
+ protected final Properties properties;
+
+ /** From Kafka's Javadoc: The time, in milliseconds, spent waiting in
poll if data is not
+ * available. If 0, returns immediately with any records that are
available now */
+ protected final long pollTimeout;
+
+ //
------------------------------------------------------------------------
+
+ /**
+ * Creates a new Kafka streaming source consumer for Kafka 2.0.x.
Review comment:
We probably want to remove all version references from the comments for the
Kafka connector that will track the latest version.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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
> Provide connector for Kafka 2.0.0
> ---------------------------------
>
> Key: FLINK-9697
> URL: https://issues.apache.org/jira/browse/FLINK-9697
> Project: Flink
> Issue Type: Improvement
> Reporter: Ted Yu
> Assignee: vinoyang
> Priority: Major
> Labels: pull-request-available
>
> Kafka 2.0.0 would be released soon.
> Here is vote thread:
> [http://search-hadoop.com/m/Kafka/uyzND1vxnEd23QLxb?subj=+VOTE+2+0+0+RC1]
> We should provide connector for Kafka 2.0.0 once it is released.
> Upgrade to 2.0 documentation :
> http://kafka.apache.org/20/documentation.html#upgrade_2_0_0
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
