package com.wangzs;
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;
/**
* @title: 在文本文件中统计出现关键字的次数 <br/>
* @author: wangzs <br/>
* @date: 2018年4月26日
*/
public class SimpleAppTest {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setMaster("local").setAppName("SimpleAppTest");
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<String> logData = sc.textFile("E:\\pss_2018\\spark-2.5-learn\\src\\main\\resources\\README.md");
JavaRDD<String> rddA = logData.filter(new Function<String, Boolean>() {
@Override
public Boolean call(String s) throws Exception {
return s.contains("a");
}
});
long countA = rddA.count();
JavaRDD<String> rddB = logData.filter(new Function<String, Boolean>() {
@Override
public Boolean call(String s) throws Exception {
return s.contains("b");
}
});
long countB = rddB.count();
System.out.println("countA:" + countA + " \tcountB:" + countB);
}
}
<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.pss</groupId>
<artifactId>spark-2.5-learn</artifactId>
<version>0.0.1-SNAPSHOT</version>
<packaging>jar</packaging>
<name>spark-2.5-learn</name>
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency> <!-- Spark dependency -->
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.1.0</version>
</dependency>
</dependencies>
<build>
<pluginManagement>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.7</source>
<target>1.7</target>
</configuration>
</plugin>
<!-- 打包时跳过测试 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<skipTests>true</skipTests>
</configuration>
</plugin>
</plugins>
</pluginManagement>
</build>
</project>
统计结果:
countA:61 countB:30