MapReduce处理csv
csv是由逗号“,”来分割的文件,在编写Mapper类的时候需要以“,”分割成一个个的数据
查看一下csv数据
以上是为了测试做的数据,要处理的结果就是经过mapreduce再原封不动的出来,因为是测试,所以内容不做任何处理
需求分析
因为MapReduce的输入和输出都是k,v键值对的形式,所以考虑将输出v封装成一个对象,对象属性按照csv文件进行设置
注意:因为封装为了对象使用MapReduce处理,就需要考虑序列化和反序列化,同时还需要考虑输入和输出的类型
介绍MapReduce中序列化和反序列化
MapReduce的序列化和反序列化
**序列化:**序列化就是把内存中的对象,转换成字节序列(或其他数据传输协议)以便于存储到磁
盘(持久化)和网络传输。
**反序列化:**反序列化就是将收到字节序列(或其他数据传输协议)或者是磁盘的持久化数据,转换
成内存中的对象。
自定义 bean 对象实现序列化接口(Writable )
具体实现 bean 对象序列化步骤如下 7 步。
- 必须实现 Writable 接口
- 反序列化时,需要反射调用空参构造函数,所以必须有空参构造
- 重写序列化方法
@Override
public void write(DataOutput dataOutput) throws IOException {
dataOutput.writeUTF(id);
dataOutput.writeUTF(name);
dataOutput.writeUTF(age);
dataOutput.writeUTF(sex);
}
- 重写反序列化方法
@Override
public void readFields(DataInput dataInput) throws IOException {
this.id = dataInput.readUTF();
this.name = dataInput.readUTF();
this.age = dataInput.readUTF();
this.sex = dataInput.readUTF();
}
- 注意反序列化的顺序和序列化的顺序完全一致
- 要想把结果显示在文件中,需要重写 toString(),可用"\t",","等分开,方便后续用。
@Override
public String toString() {
return id + "," + name + "," + age + "," + sex;
}
- 如果需要将自定义的 bean 放在 key 中传输,则还需要实现 Comparable 接口,因为MapReduce 框中的 Shuffle 过程要求对 key 必须能排序。
进行业务编写
封装对象CsvBean
在序列化和反序列化是,要根据属性类型选择序列化的类型,比如属性是String,就要选择writeUTF方法,反序列化时就是readUTF方法
package com.gis507.test.CsvSplit;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class CsvBean implements Writable{
private String id;
private String name;
private String age;
private String sex;
public CsvBean() {
}
public CsvBean(String id, String name, String age, String sex) {
this.id = id;
this.name = name;
this.age = age;
this.sex = sex;
}
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public String getName() {
return name;
}
public void setName(String name) {
this.name = name;
}
public String getAge() {
return age;
}
public void setAge(String age) {
this.age = age;
}
public String getSex() {
return sex;
}
public void setSex(String sex) {
this.sex = sex;
}
@Override
public String toString() {
return id + "," + name + "," + age + "," + sex;
}
@Override
public void write(DataOutput dataOutput) throws IOException {
dataOutput.writeUTF(id);
dataOutput.writeUTF(name);
dataOutput.writeUTF(age);
dataOutput.writeUTF(sex);
}
@Override
public void readFields(DataInput dataInput) throws IOException {
this.id = dataInput.readUTF();
this.name = dataInput.readUTF();
this.age = dataInput.readUTF();
this.sex = dataInput.readUTF();
}
}
Mapper类:CsvSplitMapper
package com.gis507.test.CsvSplit;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.checkerframework.checker.units.qual.C;
import java.io.IOException;
public class CsvSplitMapper extends Mapper<LongWritable, Text,Text,CsvBean> {
private Text outK = new Text();
private CsvBean outV = new CsvBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1获取一行转为String
String line = value.toString();
//2 按照逗号分割
// 1,jeryy,18,male,1
String[] csvComments = line.split(",");
//3 获取需要的值
String id = csvComments[0];
String name = csvComments[1];
String age = csvComments[2];
String sex = csvComments[3];
//4 封装到对象
outV.setId(id);
outV.setName(name);
outV.setAge(age);
outV.setSex(sex);
outK.set(id);
//5 写出
context.write(outK,outV);
}
}
Reducer类:CsvSplitReducer
package com.gis507.test.CsvSplit;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class CsvSplitReducer extends Reducer<Text,CsvBean, Text,CsvBean> {
@Override
protected void reduce(Text key, Iterable<CsvBean> values, Context context) throws IOException, InterruptedException {
for (CsvBean value : values) {
context.write(key,value);
}
}
}
Driver类:CsvSplitDriver
package com.gis507.test.CsvSplit;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 java.io.IOException;
public class CsvSplitDriver {
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
//1 获取job对象
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 关联Driver类
job.setJarByClass(CsvSplitDriver.class);
//3 关联Mapper和Reducer类
job.setMapperClass(CsvSplitMapper.class);
job.setReducerClass(CsvSplitReducer.class);
//4 设置Map的输入输出类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(CsvBean.class);
//5 设置最终的输入输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(CsvBean.class);
//6 设置输入输出路径
FileInputFormat.setInputPaths(job,new Path("D:\\AAUser\\dic\\Files\\testFile\\test.csv"));
FileOutputFormat.setOutputPath(job,new Path("D:\\AAUser\\dic\\Files\\testFile1"));
//7 提交job
boolean result = job.waitForCompletion(true);
System.exit(result?0:1);
}
}
输出结果: