【原创】MapReduce实战（一）

应用场景：

用户每天会在网站上产生各种各样的行为，比如浏览网页，下单等，这种行为会被网站记录下来，形成用户行为日志，并存储在hdfs上。格式如下：

17:03:35.012ᄑpageviewᄑ{“device_id”:”4405c39e85274857bbef58e013a08859″,”user_id”:”0921528165741295″,”ip”:”61.53.69.195″,”session_id”:”9d6dc377216249e4a8f33a44eef7576d”,”req_url”:”http://www.bigdataclass.com/product/1527235438747427″}

这是一个类Json 的非结构化数据，主要内容是用户访问网站留下的数据，该文本有device_id,user_id,ip，session_id，req_url等属性，前面还有17:03:20.586ᄑpageviewᄑ，这些非结构化的数据，我们想把该文本通过mr程序处理成被数仓所能读取的格式，比如Json串形式输出，具体形式如下：

{“time_log”:1527584600586,”device_id”:”4405c39e85274857bbef58e013a08859″,”user_id”:”0921528165741295″,”active_name”:”pageview”,”ip”:”61.53.69.195″,”session_id”:”9d6dc377216249e4a8f33a44eef7576d”,”req_url”:”http://www.bigdataclass.com/my/0921528165741295″}

代码工具：intellij idea, maven，jdk1.8

操作步骤：

配置 pom.xml

 1 <?xml version="1.0" encoding="UTF-8"?>
 2 <project xmlns="http://maven.apache.org/POM/4.0.0"
 3          xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 4          xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 5     <modelVersion>4.0.0</modelVersion>
 6 
 7     <groupId>netease.bigdata.course</groupId>
 8     <artifactId>etl</artifactId>
 9     <version>1.0-SNAPSHOT</version>
10 
11     <dependencies>
12         <dependency>
13             <groupId>org.apache.hadoop</groupId>
14             <artifactId>hadoop-client</artifactId>
15             <version>2.7.6</version>
16             <scope>provided</scope>
17         </dependency>
18         <dependency>
19             <groupId>com.alibaba</groupId>
20             <artifactId>fastjson</artifactId>
21             <version>1.2.4</version>
22         </dependency>
23     </dependencies>
24 
25     <build>
26         <sourceDirectory>src/main</sourceDirectory>
27         <plugins>
28            <plugin>
29                <groupId>org.apache.maven.plugins</groupId>
30                <artifactId>maven-assembly-plugin</artifactId>
31                <configuration>
32                    <descriptorRefs>
33                        <descriptorRef>
34                            jar-with-dependencies
35                        </descriptorRef>
36                    </descriptorRefs>
37                </configuration>
38                <executions>
39                    <execution>
40                        <id>make-assembly</id>
41                        <phase>package</phase>
42                        <goals>
43                            <goal>single</goal>
44                        </goals>
45                    </execution>
46                </executions>
47            </plugin>
48 
49         </plugins>
50     </build>
51 
52 </project>

2.编写主类这里为了简化代码量，我将方法类和执行类都写在ParseLogJob.java类中

package com.bigdata.etl.job;

import com.alibaba.fastjson.JSONObject;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;

public class ParseLogJob extends Configured implements Tool {
    //日志解析函数  (输入每一行的值)
    public static  Text parseLog(String row) throws ParseException {
        String[] logPart = StringUtils.split(row, "\u1111");
        SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
        long timeLog = dateFormat.parse(logPart[0]).getTime();
        String activeName = logPart[1];
        JSONObject bizData=JSONObject.parseObject(logPart[2]);
        JSONObject logData = new JSONObject();

        logData.put("active_name",activeName);
        logData.put("time_log",timeLog);
        logData.putAll(bizData);
        return new Text(logData.toJSONString());
    }


    //输入key类型，输入value类型，输出。。(序列化类型)
    public static class LogMapper extends Mapper<LongWritable,Text,NullWritable,Text>{
        //输入key值 输入value值 map运行的上下文变量
        public void map(LongWritable key ,Text value ,Context context) throws IOException,InterruptedException{
            try {
                Text parseLog = parseLog(value.toString());
                context.write(null,parseLog);
            } catch (ParseException e) {
                e.printStackTrace();
            }

        }
    }

    public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration config = getConf();
        Job job= Job.getInstance(config);
        job.setJarByClass(ParseLogJob.class);
        job.setJobName("parseLog");
        job.setMapperClass(LogMapper.class);
        //设置reduce 为0
        job.setNumReduceTasks(0);
        //命令行第一个参数作为输入路径
        FileInputFormat.addInputPath(job,new Path(args[0]));
        //第二个参数  输出路径
        Path outPutPath = new Path(args[1]);
        FileOutputFormat.setOutputPath(job,outPutPath);
        //防止报错  删除输出路径
        FileSystem fs = FileSystem.get(config);
        if (fs.exists(outPutPath)){
            fs.delete(outPutPath,true);
        }
        if (!job.waitForCompletion(true)){
            throw new RuntimeException(job.getJobName()+"fail");
        }
        return 0;
    }
    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new ParseLogJob(), args);
        System.exit(res);
    }
}