package com.openyuan;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* <p>
* 主类
* <p>
*
* @author Open开袁
**/
public class WordMain {
private static final Logger LOG = LoggerFactory.getLogger(WordMain.class);
public static void main(String[] args) throws Exception {
// 进行客户端身份的设置(root为虚拟机的用户名,hadoop集群节点的其中一个都可以)
System.setProperty("HADOOP_USER_NAME","root");
// Configuration类:读取Hadoop的配置文件,如 site-core.xml...;
// 也可用set方法重新设置(会覆盖):conf.set("fs.default.name", "hdfs://xxxx:9000")
Configuration conf = new Configuration();
// 将命令行中参数自动设置到变量conf中
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
/*
* 这里必须有输入输出
*/
if (otherArgs.length != 2) {
LOG.error("命令输入错误,请检查!");
System.exit(2);
}
// 删除输出目录
removeOutput(conf, otherArgs[1]);
/*
* 创建一个job
*/
Job job = new Job(conf, "word count"); // 新建一个 job,传入配置信息
job.setJarByClass(WordMain.class); // 设置 job 的主类
job.setMapperClass(WordMapper.class); // 设置 job 的 Mapper 类
job.setCombinerClass(WordCombiner.class); // 设置 job 的 作业合成类
job.setReducerClass(WordReducer.class); // 设置 job 的 Reducer 类
job.setOutputKeyClass(Text.class); // 设置 job 输出数据的关键类
job.setOutputValueClass(IntWritable.class); // 设置 job 输出值类
FileInputFormat.addInputPath(job, new Path(otherArgs[0])); // 文件输入
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); // 文件输出
boolean result = false;
try {
result = job.waitForCompletion(true);
} catch (Exception e) {
LOG.error("", e);
}
LOG.info("{} 单词统计MapReduce {}", GlobalUtil.getFormatDate(), result ? "成功" : "失败");
System.exit(result ? 0 : 1); // 等待完成退出
}
public static void removeOutput(Configuration conf, String outputPath) {
try {
// 通过FileSystem的静态get()方法获取HDFS文件系统客户端对象
FileSystem hdfs = FileSystem.get(conf);
// 待删除目录路径(outputPath)
Path src = new Path(outputPath);
// 删除
hdfs.delete(src,true);
} catch (Exception e) {
throw new RuntimeException("删除异常");
}
}
}
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
单词统计的MapReduce源码,统计多个文本数据集,最终输出每个单词的出现次数,可帮功能扩展修改 Map阶段 采集数据 Combiner阶段 合并数据 Reduce阶段 最终处理,进行排序等自定义操作 每个阶段都会打印对应的数据处理情况,在Map阶段打印每一次读取切割之后的每个单词内容;在Combiner阶段打印单个分片里的单词次数统计结果;在Reduce阶段打印单词出现次数Top10
资源推荐
资源详情
资源评论
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![doc](https://img-home.csdnimg.cn/images/20210720083327.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![docx](https://img-home.csdnimg.cn/images/20210720083331.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![thumb](https://img-home.csdnimg.cn/images/20210720083646.png)
![gz](https://img-home.csdnimg.cn/images/20210720083447.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![gz](https://img-home.csdnimg.cn/images/20210720083447.png)
![docx](https://img-home.csdnimg.cn/images/20210720083331.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![txt](https://img-home.csdnimg.cn/images/20210720083642.png)
![docx](https://img-home.csdnimg.cn/images/20210720083331.png)
收起资源包目录
![package](https://csdnimg.cn/release/downloadcmsfe/public/img/package.f3fc750b.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
共 28 条
- 1
资源评论
![avatar-default](https://csdnimg.cn/release/downloadcmsfe/public/img/lazyLogo2.1882d7f4.png)
![avatar](https://profile-avatar.csdnimg.cn/37581352f4bc4420997ed45c91fc7dce_weixin_47971206.jpg!1)
OpenYuan开袁
- 粉丝: 1w+
- 资源: 16
上传资源 快速赚钱
我的内容管理 展开
我的资源 快来上传第一个资源
我的收益
登录查看自己的收益我的积分 登录查看自己的积分
我的C币 登录后查看C币余额
我的收藏
我的下载
下载帮助
![voice](https://csdnimg.cn/release/downloadcmsfe/public/img/voice.245cc511.png)
![center-task](https://csdnimg.cn/release/downloadcmsfe/public/img/center-task.c2eda91a.png)
最新资源
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback-tip](https://img-home.csdnimg.cn/images/20220527035111.png)
安全验证
文档复制为VIP权益,开通VIP直接复制
![dialog-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/green-success.6a4acb44.png)