hddong commented on a change in pull request #25412: [SPARK-28691][EXAMPLES] Add Java/Scala DirectKerberizedKafkaWordCount examples URL: https://github.com/apache/spark/pull/25412#discussion_r313306191
########## File path: examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java ########## @@ -0,0 +1,107 @@ +/* + * 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.spark.examples.streaming; + +import java.util.HashMap; +import java.util.HashSet; +import java.util.Arrays; +import java.util.Map; +import java.util.Set; +import java.util.regex.Pattern; + +import scala.Tuple2; + +import org.apache.kafka.clients.CommonClientConfigs; +import org.apache.kafka.common.security.auth.SecurityProtocol; +import org.apache.kafka.clients.consumer.ConsumerConfig; +import org.apache.kafka.clients.consumer.ConsumerRecord; +import org.apache.kafka.common.serialization.StringDeserializer; + +import org.apache.spark.SparkConf; +import org.apache.spark.streaming.api.java.*; +import org.apache.spark.streaming.kafka010.ConsumerStrategies; +import org.apache.spark.streaming.kafka010.KafkaUtils; +import org.apache.spark.streaming.kafka010.LocationStrategies; +import org.apache.spark.streaming.Durations; + +/** + * Consumes messages from one or more topics in Kafka and does wordcount. + * Usage: JavaDirectKerberizedKafkaWordCount <brokers> <groupId> <topics> + * <brokers> is a list of one or more Kafka brokers + * <groupId> is a consumer group name to consume from topics + * <topics> is a list of one or more kafka topics to consume from + * + * Example: + * $ bin/run-example --files ${path}/kafka_jaas.conf \ + * --driver-java-options "-Djava.security.auth.login.config=${path}/kafka_jaas.conf" \ + * --conf \ + * "spark.executor.extraJavaOptions=-Djava.security.auth.login.config=./kafka_jaas.conf" \ + * streaming.JavaDirectKerberizedKafkaWordCount broker1-host:port,broker2-host:port \ + * consumer-group topic1,topic2 + */ + +public final class JavaDirectKerberizedKafkaWordCount { + private static final Pattern SPACE = Pattern.compile(" "); + + public static void main(String[] args) throws Exception { + if (args.length < 3) { + System.err.println( + "Usage: JavaDirectKerberizedKafkaWordCount <brokers> <groupId> <topics>\n" + + " <brokers> is a list of one or more Kafka brokers\n" + + " <groupId> is a consumer group name to consume from topics\n" + + " <topics> is a list of one or more kafka topics to consume from\n\n"); + System.exit(1); + } + + StreamingExamples.setStreamingLogLevels(); + + String brokers = args[0]; + String groupId = args[1]; + String topics = args[2]; + + // Create context with a 2 seconds batch interval + SparkConf sparkConf = new SparkConf().setAppName("JavaDirectKerberizedKafkaWordCount"); + JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, Durations.seconds(2)); + + Set<String> topicsSet = new HashSet<>(Arrays.asList(topics.split(","))); + Map<String, Object> kafkaParams = new HashMap<>(); + kafkaParams.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, brokers); + kafkaParams.put(ConsumerConfig.GROUP_ID_CONFIG, groupId); + kafkaParams.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class); + kafkaParams.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class); + kafkaParams.put(CommonClientConfigs.SECURITY_PROTOCOL_CONFIG, + SecurityProtocol.SASL_PLAINTEXT.name); + + // Create direct kafka stream with brokers and topics + JavaInputDStream<ConsumerRecord<String, String>> messages = KafkaUtils.createDirectStream( + jssc, + LocationStrategies.PreferConsistent(), + ConsumerStrategies.Subscribe(topicsSet, kafkaParams)); + + // Get the lines, split them into words, count the words and print + JavaDStream<String> lines = messages.map(ConsumerRecord::value); + JavaDStream<String> words = lines.flatMap(x -> Arrays.asList(SPACE.split(x)).iterator()); + JavaPairDStream<String, Integer> wordCounts = words.mapToPair(s -> new Tuple2<>(s, 1)) + .reduceByKey((i1, i2) -> i1 + i2); Review comment: ok, I will make it 2-spaces. ---------------------------------------------------------------- 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 With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
