spark2.1.0-在文本文件中统计出现关键字的次数

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


  • 1
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值