小编yik*_*han的帖子

使用java编写spark程序，代码如下：

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;

public class SimpleApp {
  public static void main(String[] args) {
      SparkConf conf = new SparkConf().setAppName("wordCount").setMaster("local"); 
      JavaSparkContext sc = new JavaSparkContext(conf); 
      JavaRDD<String> input = sc.textFile("/bigdata/softwares/spark-2.1.0-bin-hadoop2.7/testdata/a.txt");
      System.out.println();
      Long bCount = input.filter(new Function<String,Boolean>(){
         public Boolean call(String s){return s.contains("yes");}
      }).count();
      Long cCount = input.filter(new Function<String,Boolean>(){
         public Boolean call(String s){return s.contains("ywq");}
      }).count();
      System.out.println("yes:"+bCount+"  ywq:"+cCount+"  all?");
//    sc.stop();
  }
}

Pom如下？

<dependencies>
        <dependency> <!-- Spark dependency -->
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>      
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId> …