Github user markap14 commented on a diff in the pull request:
https://github.com/apache/nifi/pull/295#discussion_r57019067
--- Diff:
nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-processors/src/main/java/org/apache/nifi/processors/kafka/Partitioners.java
---
@@ -0,0 +1,87 @@
+/*
+ * 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.nifi.processors.kafka;
+
+import java.util.Random;
+
+import kafka.producer.Partitioner;
+import kafka.utils.VerifiableProperties;
+
+/**
+ * Collection of implementation of common Kafka {@link Partitioner}s.
+ */
+final public class Partitioners {
+
+ private Partitioners() {
+ }
+ /**
+ * {@link Partitioner} that implements 'round-robin' mechanism which
evenly
+ * distributes load between all available partitions.
+ */
+ public static class RoundRobinPartitioner implements Partitioner {
+ private volatile int index;
+
+ public RoundRobinPartitioner(VerifiableProperties props) {
+ }
+
+ @Override
+ public int partition(Object key, int numberOfPartitions) {
+ int partitionIndex = this.next(numberOfPartitions);
+ return partitionIndex;
+ }
+
+ private int next(int numberOfPartitions) {
+ if (index == numberOfPartitions) {
+ index = 0;
+ }
+ int indexToReturn = index++;
+ return indexToReturn;
+ }
+ }
+
+ /**
+ * {@link Partitioner} that implements 'random' mechanism which
randomly
+ * distributes the load between all available partitions.
+ */
+ public static class RandomPartitioner implements Partitioner {
+ private final Random random;
+
+ public RandomPartitioner(VerifiableProperties props) {
+ this.random = new Random();
+ }
+
+ @Override
+ public int partition(Object key, int numberOfPartitions) {
+ return this.random.nextInt(numberOfPartitions);
+ }
+ }
+
+ /**
+ * {@link Partitioner} that implements 'key hash' mechanism which
+ * distributes the load between all available partitions based on
hashing
+ * the value of the key.
+ */
+ public static class HashPartitioner implements Partitioner {
+ public HashPartitioner(VerifiableProperties props) {
+ }
+
+ @Override
+ public int partition(Object key, int numberOfPartitions) {
+ return (key.hashCode() & Integer.MAX_VALUE) %
numberOfPartitions;
--- End diff --
What is the logic here behind `& Integer.MAX_VALUE`? Since `hashCode()`
will return an int, doing a bit-wise and with `Integer.MAX_VALUE` would just
return the same result as `hashCode()` returned, no?
Also, `key` could be null. Is this going to cause a problem?
---
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.
---
