Github user abhishekagarwal87 commented on a diff in the pull request:
https://github.com/apache/storm/pull/1131#discussion_r55333414
--- Diff:
external/storm-kafka-client/src/main/java/org/apache/storm/kafka/spout/KafkaSpout.java
---
@@ -0,0 +1,458 @@
+/*
+ * 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.storm.kafka.spout;
+
+import org.apache.kafka.clients.consumer.ConsumerRebalanceListener;
+import org.apache.kafka.clients.consumer.ConsumerRecord;
+import org.apache.kafka.clients.consumer.ConsumerRecords;
+import org.apache.kafka.clients.consumer.KafkaConsumer;
+import org.apache.kafka.clients.consumer.OffsetAndMetadata;
+import org.apache.kafka.common.TopicPartition;
+import
org.apache.storm.kafka.spout.KafkaSpoutConfig.FirstPollOffsetStrategy;
+import org.apache.storm.spout.SpoutOutputCollector;
+import org.apache.storm.task.TopologyContext;
+import org.apache.storm.topology.OutputFieldsDeclarer;
+import org.apache.storm.topology.base.BaseRichSpout;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.util.Collection;
+import java.util.Comparator;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.NavigableSet;
+import java.util.TreeSet;
+import java.util.concurrent.TimeUnit;
+
+import static
org.apache.storm.kafka.spout.KafkaSpoutConfig.FirstPollOffsetStrategy.EARLIEST;
+import static
org.apache.storm.kafka.spout.KafkaSpoutConfig.FirstPollOffsetStrategy.LATEST;
+import static
org.apache.storm.kafka.spout.KafkaSpoutConfig.FirstPollOffsetStrategy.UNCOMMITTED_EARLIEST;
+import static
org.apache.storm.kafka.spout.KafkaSpoutConfig.FirstPollOffsetStrategy.UNCOMMITTED_LATEST;
+
+public class KafkaSpout<K, V> extends BaseRichSpout {
+ private static final Logger LOG =
LoggerFactory.getLogger(KafkaSpout.class);
+ private static final Comparator<MessageId> OFFSET_COMPARATOR = new
OffsetComparator();
+
+ // Storm
+ protected SpoutOutputCollector collector;
+
+ // Kafka
+ private final KafkaSpoutConfig<K, V> kafkaSpoutConfig;
+ private KafkaConsumer<K, V> kafkaConsumer;
+ private transient boolean consumerAutoCommitMode;
+ private transient FirstPollOffsetStrategy firstPollOffsetStrategy;
+
+ // Bookkeeping
+ private KafkaSpoutStreams kafkaSpoutStreams;
+ private KafkaTupleBuilder<K, V> tupleBuilder;
+ private transient Timer timer; //
timer == null for auto commit mode
+ private transient Map<TopicPartition, OffsetEntry> acked; //
emitted tuples that were successfully acked. These tuples will be committed
periodically when the timer expires, on consumer rebalance, or on
close/deactivate
+ private transient int maxRetries; //
Max number of times a tuple is retried
+ private transient boolean initialized; // Flag indicating
that the spout is still undergoing initialization process.
+ // Initialization is
only complete after the first call to
KafkaSpoutConsumerRebalanceListener.onPartitionsAssigned()
+
+
+ public KafkaSpout(KafkaSpoutConfig<K, V> kafkaSpoutConfig,
KafkaTupleBuilder<K, V> tupleBuilder) {
+ this.kafkaSpoutConfig = kafkaSpoutConfig; // Pass
in configuration
+ this.kafkaSpoutStreams = kafkaSpoutConfig.getKafkaSpoutStreams();
+ this.tupleBuilder = tupleBuilder;
+ }
+
+ @Override
+ public void open(Map conf, TopologyContext context,
SpoutOutputCollector collector) {
+ initialized = false;
+
+ // Spout internals
+ this.collector = collector;
+ maxRetries = kafkaSpoutConfig.getMaxTupleRetries();
+
+ // Offset management
+ firstPollOffsetStrategy =
kafkaSpoutConfig.getFirstPollOffsetStrategy();
+ consumerAutoCommitMode =
kafkaSpoutConfig.isConsumerAutoCommitMode();
+
+ if (!consumerAutoCommitMode) { // If it is auto commit, no
need to commit offsets manually
+ timer = new Timer(500,
kafkaSpoutConfig.getOffsetsCommitFreqMs(), TimeUnit.MILLISECONDS);
+ acked = new HashMap<>();
+ }
+ LOG.debug("Kafka Spout opened with the following configuration:
{}", kafkaSpoutConfig);
--- End diff --
can this be LOG.info
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
