SPark单词统计

package com.org.spark.test;



import com.google.common.collect.Lists;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.util.Arrays;
import java.util.List;
import java.util.regex.Pattern;

public final class WordCount {
   private static final Pattern SPACE = Pattern.compile(" ");

    public static void main(String[] args) throws Exception {

        List<String> wordContent= Lists.newArrayList("hello hello lilei",
                "jim and zhangsan hello",
                "zhangsan say lilei");

           SparkConf sparkConf = new SparkConf().setMaster("local[1]").setAppName("wordcount");
           JavaSparkContext ctx = new JavaSparkContext(sparkConf);
          // JavaRDD<String> lines = ctx.parallelize(wordContent);
           JavaRDD<String> lines = ctx.textFile(args[0]);
           JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
                @Override
               public Iterable<String> call(String s) {
                        return Arrays.asList(SPACE.split(s));
                    }
                 });

         JavaPairRDD<String, Integer> ones = words.mapToPair(new PairFunction<String, String, Integer>() {
                  @Override
                  public Tuple2<String, Integer> call(String s) {
                        return new Tuple2<String, Integer>(s, 1);
                      }
                 });

            JavaPairRDD<String, Integer> counts = ones.reduceByKey(new Function2<Integer, Integer, Integer>() {
                 @Override
                  public Integer call(Integer i1, Integer i2) {
                       return i1 + i2;
                      }
               });

           List<Tuple2<String, Integer>> output = counts.collect();
             for (Tuple2<?, ?> tuple : output) {
                   System.out.println(tuple._1() + ": " + tuple._2());
               }
             ctx.stop();
          }
   }

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.org.spark.test</groupId>
    <artifactId>spark-wordcount</artifactId>
    <version>1.0-SNAPSHOT</version>
    <packaging>jar</packaging>

    <name>spark-project</name>
    <url>http://maven.apache.org</url>
<dependencies>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.10</artifactId>
        <version>1.6.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming_2.10</artifactId>
        <version>1.6.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-hive_2.10</artifactId>
        <version>1.6.1</version>
        <scope>provided</scope>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.10</artifactId>
        <version>1.6.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.4.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming-kafka_2.11</artifactId>
        <version>1.5.1</version>
    </dependency>
    <dependency>
        <groupId>mysql</groupId>
        <artifactId>mysql-connector-java</artifactId>
        <version>5.1.6</version>
    </dependency>
    <dependency>
        <groupId>org.json</groupId>
        <artifactId>json</artifactId>
        <version>20090211</version>
    </dependency>
    <dependency>
        <groupId>com.alibaba</groupId>
        <artifactId>fastjson</artifactId>
        <version>1.1.41</version>
    </dependency>
    <dependency>
        <groupId>fastutil</groupId>
        <artifactId>fastutil</artifactId>
        <version>5.0.9</version>
    </dependency>
</dependencies>
 <build>
     <plugins>
     <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-shade-plugin</artifactId>
         <version>1.6</version>
         <executions>
             <execution>
                 <phase>package</phase>
                 <goals>
                     <goal>shade</goal>
                 </goals>
             </execution>
         </executions>
     </plugin>
     </plugins>
 </build>


</project>

spark-submit提交

./bin/spark-submit --master spark://172.16.80.228:7077  --name WordCoun   --class com.org.spark.test.WordCount --executor-memory 1G --total-executor-cores 1 lib/spark-workcount.jar