十二 Spark+Kafka+Mysql 整合
如果程式缺少包,需要匯入到系統中去,採用如下方法
for i in `ls /data/spark-workspace/lib/*.jar`
do
LIBJAR=$i,$LIBJAR
done
export LIBJARS=${LIBJAR%?}
/* mvn dependency:copy-dependencies https://blog.csdn.net/u013514928/article/details/77930183
檔案位置
.//spark/examples/src/main/java/org/apache/spark/examples/streaming/JavaKafkaWordCount.java
執行 其中org.apache.spark.examples.streaming是包的名字,JavaKafkaWordCount是程式的名字, /data/example/pro-spark-example-1.6.2.jar是編譯出target中的jar包位置
./spark-submit --master spark://kolla:7077 --name Spark-kafka-wordcount --class org.apache.spark.examples.streaming.JavaKafkaWordCount /data/example/pro-spark-example-1.6.2.jar
*/
/*
* 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.Iterator;
import java.util.Map;
import java.util.regex.Pattern;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.function.VoidFunction;
import org.apache.spark.sql.MysqlUtil;
import org.apache.spark.streaming.Duration;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaPairReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.apache.spark.streaming.kafka.KafkaUtils;
import scala.Tuple2;
import com.google.common.collect.Lists;
/**
* Consumes messages from one or more topics in Kafka and does wordcount.
*
* Usage: JavaKafkaWordCount <zkQuorum> <group> <topics> <numThreads>
* <zkQuorum> is a list of one or more zookeeper servers that make quorum
* <group> is the name of kafka consumer group
* <topics> is a list of one or more kafka topics to consume from
* <numThreads> is the number of threads the kafka consumer should use
*
* To run this example:
* `$ bin/run-example org.apache.spark.examples.streaming.JavaKafkaWordCount zoo01,zoo02, \
* zoo03 my-consumer-group topic1,topic2 1`
*/
public final class JavaKafkaWordCount {
private static final Pattern SPACE = Pattern.compile(" ");
private JavaKafkaWordCount() {
}
public static void main(String[] args) {
// if (args.length < 4) {
// System.err.println("Usage: JavaKafkaWordCount <zkQuorum> <group> <topics> <numThreads>");
// System.exit(1);
// }
// StreamingExamples.setStreamingLogLevels();
SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaWordCount");
// Create the context with 2 seconds batch size
//每個兩秒鐘獲取一次資料,獲取資料後再進行處理
JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, new Duration(2000));
//topic只有一個test
int numThreads = Integer.parseInt("1");
Map<String, Integer> topicMap = new HashMap<String, Integer>();
String[] topics = {"test"};
for (String topic: topics) {
topicMap.put(topic, numThreads);
}
/*
static JavaPairReceiverInputDStream<java.lang.String,java.lang.String>
createStream(
JavaStreamingContext jssc,
java.lang.String zkQuorum,
java.lang.String groupId,
java.util.Map<java.lang.String,java.lang.Integer> topics
)
Create an input stream that pulls messages from Kafka Brokers.
*/
String zk="192.168.10.141:2181/kafka";
String groupId="spark";
JavaPairReceiverInputDStream<String, String> messages =
KafkaUtils.createStream(jssc, zk, groupId, topicMap);
JavaDStream<String> lines = messages.map(new Function<Tuple2<String, String>, String>() {
@Override
public String call(Tuple2<String, String> tuple2) {
return tuple2._2();
}
});
JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String x) {
return Lists.newArrayList(SPACE.split(x));
}
});
JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) {
return new Tuple2<String, Integer>(s, 1);
}
}).reduceByKey(new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});
VoidFunction<JavaPairRDD<String, Integer>> foreachFunc = new VoidFunction<JavaPairRDD<String,Integer>>() {
private static final long serialVersionUID = 1L;
@Override
public void call(JavaPairRDD<String, Integer> results) throws Exception {
VoidFunction<Iterator<Tuple2<String, Integer>>> result = new VoidFunction<Iterator<Tuple2<String,Integer>>>() {
@Override
public void call(Iterator<Tuple2<String, Integer>> r) throws Exception {
System.out.println("寮�濮嬭繘鍏ysql錼嶄綔");
MysqlUtil.saveWC(r);
}
};
results.foreachPartition(result );
}
};
wordCounts.foreachRDD(foreachFunc );
wordCounts.print();
jssc.start();
jssc.awaitTermination();
}
}