前文
MapReduce编程实例
文章目录
前言
Hadoop测试项目:HadoopDemo
注意事项
如果下载了HadoopDemo作为测试,用到HDFS_CRUD.java
需要提前准备winutils。最好对应版本。
单词统计 WordCount
WordCountMapper.java
package top.rabbitcrows.hadoop.mr;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* 这里就是MapReduce程序 Map阶段业务逻辑实现的类 Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
* <p>
* KEYIN:表示mapper数据输入时key的数据类型,在默认读取数据组件下,叫作ImportFormat,它的行为是每行读取待处理的数据
* 读取一行,就返回一行给MR程序,这种情况下 KEYIN就表示每一行的起始偏移,因此数据类型是Long
* <p>
* VALUEIN:表示mapper数据输入的时候Value的数据类型,在默认读取数据组件下,
* valueIN就表示读取的一行内容 因此数据类型是String
* <p>
* KEYOUT:表示mapper阶段数据输出的时候key的数据类型,在本案例中输出的key是单词,因此数据类型是String
* ValueOUT:表示mapper阶段数据输出的时候value的数据类型,在本案例中输出的value是单次的此书,因此数据类型是Integer
* <p>
* 这里所说的数据类型String,Long都是JDK的自带的类型,
* 数据在分布式系统中跨网络传输就需要将数据序列化,默认JDK序列化时效率低下,因此
* 使用Hadoop封装的序列化类型。 long--LongWritable String --Text Integer intWritable ....
*
* @author LEHOSO
*/
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
/**
* 这里就是mapper阶段具体业务逻辑实现的方法 该方法的调用取决于读取数据的组件有没有给MR传入数据
* 如果有数据传入,每一个<k,v>对,map就会被调用一次
*/
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// 拿到传入进来的一行内容,把数据类型转换为String
String line = value.toString();
// 将这行内容按照分隔符切割
String[] words = line.split(" ");
// 遍历数组,每出现一个单词就标记一个数组1 例如:<单词,1>
for (String word : words) {
// 使用MR上下文context,把Map阶段处理的数据发送给Reduce阶段作为输入数据
context.write(new Text(word), new IntWritable(1));
//第一行 hadoop hadoop spark 发送出去的是<hadoop,1><hadoop,1><spark,1>
}
}
}
WordCountReducer.java
package top.rabbitcrows.hadoop.mr;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
//都要继承Reducer 这就是我们所说的变成模型,只需要套模板就行了
/**
* 这里是MR程序 reducer阶段处理的类
* <p>
* KEYIN:就是Reducer阶段输入的数据key类型,对应Mapper阶段输出KEY类型 ,在本案例中就是单词
* <p>
* VALUEIN:就是Reducer阶段输入的数据value类型,对应Mapper阶段输出VALUE类型 ,在本案例中就是个数
* <p>
* KEYOUT:就是Reducer阶段输出的数据key类型,在本案例中,就是单词 Text
* <p>
* VALUEOUT:reducer阶段输出的数据value类型,在本案例中,就是单词的总次数
*
* @author LEHOSO
*/
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
/**
* 这里是REDUCE阶段具体业务类的实现方法
* 第一行 hadoop hadoop spark 发送出去的是<hadoop,1><hadoop,1><spark,1>
* reduce接受所有来自Map阶段处理的数据之后,按照Key的字典序进行排序
* 按照key是否相同作一组去调用reduce方法
* 本方法的key就是这一组相同的kv对 共同的Key
* 把这一组的所有v作为一个迭代器传入我们的reduce方法
* <p>
* 迭代器:<hadoop,[1,1]>
*/
@Override
protected void reduce(Text key, Iterable<IntWritable> value,
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
//定义一个计数器
int count = 0;
//遍历一组迭代器,把每一个数量1累加起来就构成了单词的总次数
//
for (IntWritable iw : value) {
count += iw.get();
}
context.write(key, new IntWritable(count));
}
}
WordCountCombiner.java
package top.rabbitcrows.hadoop.mr;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class WordCountCombiner extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
protected void reduce(Text key, Iterable<IntWritable> values,
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// 1.局部汇总
int count = 0;
for (IntWritable v : values) {
count += v.get();
}
context.write(key, new IntWritable(count));
}
}
WordCountDriver.java
package top.rabbitcrows.hadoop.mr;
import org.apache.hadoop.conf.Configuration;
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;
/**
* Driver类就是MR程序运行的主类,本类中组装了一些程序运行时所需要的信息
* 比如:使用的Mapper类是什么,Reducer类,数据在什么地方,输出在哪里
*
* @author LEHOSO
*/
public class WordCountDriver {
public static void main(String[] args) throws Exception {
// 通过Job来封装本次MR的相关信息
Configuration conf = new Configuration();
conf.set("mapreduce.framework.name", "local");
Job wcjob = Job.getInstance(conf);
// 指定MR Job jar包运行主类
wcjob.setJarByClass(WordCountDriver.class);
// 指定本次MR所有的Mapper Reducer类
wcjob.setMapperClass(WordCountMapper.class);
wcjob.setReducerClass(WordCountReducer.class);
// 设置我们的业务逻辑 Mapper类的输出 key和 value的数据类型
wcjob.setMapOutputKeyClass(Text.class);
wcjob.setMapOutputValueClass(IntWritable.class);
// 设置我们的业务逻辑 Reducer类的输出 key和 value的数据类型
wcjob.setOutputKeyClass(Text.class);
wcjob.setOutputValueClass(IntWritable.class);
//设置Combiner组件
wcjob.setCombinerClass(WordCountCombiner.class);
// 指定要处理的数据所在的位置
FileInputFormat.setInputPaths(wcjob, new Path("input/mr"));
// 指定处理完成之后的结果所保存的位置
FileOutputFormat.setOutputPath(wcjob, new Path("output/mr"));
// 提交程序并且监控打印程序执行情况
boolean res = wcjob.waitForCompletion(true);
System.exit(res ? 0 : 1);
}
}
MapReduce 经典案例——倒排索引
InvertedIndexMapper.java
package top.rabbitcrows.mr.InvertedIndex;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import java.io.IOException;
/**
* @author LEHOSO
* @date 2021/11/2
* @apinote
*/
public class InvertedIndexMapper extends Mapper<LongWritable, Text, Text, Text> {
//存储单词和文档名称
private static Text KeyInfo = new Text();
//存储词频,初始化为1
private static final Text valueInfo = new Text("1");
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] fileds = StringUtils.split(line, " ");
//得到这行数据所在的文件切片
FileSplit fileSplit = (FileSplit) context.getInputSplit();
//根据文件切片得到文件名
String fileName = fileSplit.getPath().getName();
for (String filed : fileds) {
//key值由单词和文档名称组成,如“MapReduce:file1.txt”
KeyInfo.set(filed + ":" + fileName);
context.write(KeyInfo, valueInfo);
}
}
}
InvertedIndexCombiner.java
package top.rabbitcrows.mr.InvertedIndex;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* @author LEHOSO
* @date 2021/11/2
* @apinote
*/
public class InvertedIndexCombiner extends Reducer<Text, Text, Text, Text> {
private static Text info = new Text();
//输入:<MapReduce:file3.txt{1,1}>
//输出:<MapReduce:file3.txt:2>
@Override
protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
int sum = 0; //统计词频
for (Text value : values) {
sum += Integer.parseInt(value.toString());
}
int splitIndex = key.toString().indexOf(":");
//重新设置value值并由文档名称和词频组成
info.set(key.toString().substring(splitIndex + 1) + ":" + sum);
//重新设置key值为单词
key.set(key.toString().substring(0, splitIndex));
context.write(key, info);
}
}
InvertedIndexReducer.java
package top.rabbitcrows.mr.InvertedIndex;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* @author LEHOSO
* @date 2021/11/2
* @apinote
*/
public class InvertedIndexReducer extends Reducer<Text, Text, Text, Text> {
private static Text result = new Text();
//输入:<MapReduce:file3.txt:2}>
//输出:<MapReduce:file1.txt:1;file2.txt:1;file3.txt:2;>
@Override
protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
//生成文档列表
String fileList = new String();
for (Text value : values) {
fileList += value.toString() + ";";
}
result.set(fileList);
context.write(key, result);
}
}
InvertedIndexDriver.java
package top.rabbitcrows.mr.InvertedIndex;
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;
/**
* @author LEHOSO
* @date 2021/11/2
* @apinote
*/
public class InvertedIndexDriver {
public static void main(String[] args)
throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
// conf.set("mapreduce.framework.name", "local");
Job job = Job.getInstance(conf);
job.setJarByClass(InvertedIndexDriver.class);
job.setMapperClass(InvertedIndexMapper.class);
job.setReducerClass(InvertedIndexReducer.class);
job.setCombinerClass(InvertedIndexCombiner.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// 指定要处理的数据所在的位置
FileInputFormat.setInputPaths(job,
new Path("input/InvertedIndex/"));
// 指定处理完成之后的结果所保存的位置
FileOutputFormat.setOutputPath(job,
new Path("output/InvertedIndex"));
// 提交程序并且监控打印程序执行情况
boolean res = job.waitForCompletion(true);
System.exit(res ? 0 : 1);
}
}
MapReduce 经典案例——数据去重
DedupMapper.java
package top.rabbitcrows.mr.dedup;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* @author LEHOSO
* @date 2021/11/5
* @apinote
*/
public class DedupMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
private static Text field = new Text();
//<0,2021-11-1 a><11,2021-11-2 b>
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, NullWritable>.Context context) throws IOException, InterruptedException {
field = value;
//NullWritable.get()方法设置空值
context.write(field, NullWritable.get());
// <2018-3-3 c,null> <2018-3-4 d,null>
}
}
DedupReducer.java
package top.rabbitcrows.mr.dedup;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* @author LEHOSO
* @date 2021/11/5
* @apinote
*/
public class DedupReducer extends Reducer<Text, NullWritable,Text,NullWritable> {
//<2021-11-1,a,null><2021-11-2,b,null><2021-11-3,c,null>
@Override
protected void reduce(Text key, Iterable<NullWritable> values, Reducer<Text, NullWritable, Text, NullWritable>.Context context) throws IOException, InterruptedException {
context.write(key,NullWritable.get());
}
}
DedupDriver.java
package top.rabbitcrows.mr.dedup;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;
/**
* @author LEHOSO
* @date 2021/11/5
* @apinote
*/
public class DedupDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(DedupDriver.class);
job.setMapperClass(DedupMapper.class);
job.setReducerClass(DedupReducer.class);
job.setOutputKeyClass(Text.class);
job.setMapOutputValueClass(NullWritable.class);
FileInputFormat.setInputPaths(job, new Path("input/Dedup"));
// 指定处理完成之后的结果所保存的位置
FileOutputFormat.setOutputPath(job, new Path("output/Dedup"));
job.waitForCompletion(true);
}
}
MapReduce 经典案例——TopN
TopNMapper.java
package top.rabbitcrows.mr.topN;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
import java.util.TreeMap;
/**
* @author LEHOSO
* @date 2021/11/5
* @apinote
*/
public class TopNMapper extends Mapper<LongWritable, Text, NullWritable, IntWritable> {
private TreeMap<Integer, String> repToRecordMap = new TreeMap<Integer, String>();
// <0,10 3 8 7 6 5 1 2 9 4>
// <xx,11 12 17 14 15 20>
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, NullWritable, IntWritable>.Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] nums = line.split(" ");
for (String num : nums) {
//读取每行数据写入TreeMap,超过5个就会移除最小的数值
repToRecordMap.put(Integer.parseInt(num), " ");
if (repToRecordMap.size() > 5) {
repToRecordMap.remove(repToRecordMap.firstKey());
}
}
}
//重写cleanup()方法,读取完所有文件行数据后,再输出到Reduce阶段
@Override
protected void cleanup(Mapper<LongWritable, Text, NullWritable, IntWritable>.Context context) throws IOException, InterruptedException {
for (Integer i : repToRecordMap.keySet()) {
try {
context.write(NullWritable.get(), new IntWritable(i));
} catch (Exception e) {
e.printStackTrace();
}
}
}
}
TopNReducer.java
package top.rabbitcrows.mr.topN;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Comparator;
import java.util.TreeMap;
/**
* @author LEHOSO
* @date 2021/11/5
* @apinote
*/
public class TopNReducer extends Reducer<NullWritable, IntWritable, NullWritable, IntWritable> {
private TreeMap<Integer, String> repToRecordMap = new TreeMap<Integer, String>(new Comparator<Integer>() {
//返回一个基本类型的整型,谁大谁排后面.
//返回负数表示:o1 小于o2
//返回0表示:表示:o1和o2相等
//返回正数表示:o1大于o2。
public int compare(Integer a, Integer b) {
return b - a;
}
});
public void reduce(NullWritable key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
for (IntWritable value : values) {
repToRecordMap.put(value.get(), " ");
if (repToRecordMap.size() > 5) {
repToRecordMap.remove(repToRecordMap.firstKey());
}
}
for (Integer i : repToRecordMap.keySet()) {
context.write(NullWritable.get(), new IntWritable(i));
}
}
}
TopNDriver.java
package top.rabbitcrows.mr.topN;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
* @author LEHOSO
* @date 2021/11/5
* @apinote
*/
public class TopNDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance();
job.setJarByClass(TopNDriver.class);
job.setMapperClass(TopNMapper.class);
job.setReducerClass(TopNReducer.class);
job.setNumReduceTasks(1);
//map阶段输出的key
job.setMapOutputKeyClass(NullWritable.class);
//map阶段输出的value
job.setMapOutputValueClass(IntWritable.class);
//reduce阶段输出的key
job.setOutputKeyClass(NullWritable.class);
//reduce阶段输出的value
job.setMapOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path("input/TopN/num.txt"));
FileOutputFormat.setOutputPath(job, new Path("output/TopN"));
boolean res = job.waitForCompletion(true);
System.out.println(res ? 0 : 1);
}
}
Github下载地址
(HadoopDemo)[https://github.com/lehoso/HadoopDemo]