hello tom hello jerry hello tom
hello jerry hello jerry tom jerry
hello jerry hello tom
[plain] view plain copy hello c.txt-->2 b.txt-->2 a.txt-->3 jerry c.txt-->1 b.txt-->3 a.txt-->1 tom c.txt-->1 b.txt-->1 a.txt-->2
-------------第一步Mapper的输出结果格式如下:--------------------
context.wirte("hello->a.txt", "1")
context.wirte("hello->a.txt", "1")
context.wirte("hello->a.txt", "1")
context.wirte("hello->b.txt", "1")
context.wirte("hello->b.txt", "1")
context.wirte("hello->c.txt", "1")
context.wirte("hello->c.txt", "1")
-------------第一步Reducer的得到的输入数据格式如下:-------------
<"hello->a.txt", {1,1,1}>
<"hello->b.txt", {1,1}>
<"hello->c.txt", {1,1}>
-------------第一步Reducer的输出数据格式如下---------------------
context.write("hello->a.txt", "3")
context.write("hello->b.txt", "2")
context.write("hello->c.txt", "2")
-------------第二步Mapper得到的输入数据格式如下:-----------------
context.write("hello->a.txt", "3")
context.write("hello->b.txt", "2")
context.write("hello->c.txt", "2")
-------------第二步Mapper输出的数据格式如下:--------------------
context.write("hello", "a.txt->3")
context.write("hello", "b.txt->2")
context.write("hello", "c.txt->2")
-------------第二步Reducer得到的输入数据格式如下:-----------------
<"hello", {"a.txt->3", "b.txt->2", "c.txt->2"}>
-------------第二步Reducer输出的数据格式如下:-----------------
context.write("hello", "a.txt->3 b.txt->2 c.txt->2")
最终结果为:
hello a.txt->3 b.txt->2 c.txt->2
package com.lyz.hdfs.mr.ii;
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
* 倒排索引第一步Map Reduce程序,此处程序将所有的Map/Reduce/Runner程序放在一个类中
* @author liuyazhuang
*
*/
public class InverseIndexStepOne {
/**
* 完成倒排索引第一步的mapper程序
* @author liuyazhuang
*
*/
public static class StepOneMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
//获取一行数据
String line = value.toString();
//切分出每个单词
String[] fields = StringUtils.split(line, " ");
//获取数据的切片信息
FileSplit fileSplit = (FileSplit) context.getInputSplit();
//根据切片信息获取文件名称
String fileName = fileSplit.getPath().getName();
for(String field : fields){
context.write(new Text(field + "-->" + fileName), new LongWritable(1));
}
}
}
/**
* 完成倒排索引第一步的Reducer程序
* 最终输出结果为:
* hello-->a.txt 3
hello-->b.txt 2
hello-->c.txt 2
jerry-->a.txt 1
jerry-->b.txt 3
jerry-->c.txt 1
tom-->a.txt 2
tom-->b.txt 1
tom-->c.txt 1
* @author liuyazhuang
*
*/
public static class StepOneReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
@Override
protected void reduce(Text key, Iterable<LongWritable> values,
Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
long counter = 0;
for(LongWritable value : values){
counter += value.get();
}
context.write(key, new LongWritable(counter));
}
}
//运行第一步的MR程序
public static void main(String[] args) throws Exception{
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(InverseIndexStepOne.class);
job.setMapperClass(StepOneMapper.class);
job.setReducerClass(StepOneReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileInputFormat.addInputPath(job, new Path("D:/hadoop_data/ii"));
FileOutputFormat.setOutputPath(job, new Path("D:/hadoop_data/ii/result"));
job.waitForCompletion(true);
}
}
hello tom hello jerry hello tom
hello jerry hello jerry tom jerry
hello jerry hello tom
hello-->a.txt 3 hello-->b.txt 2 hello-->c.txt 2 jerry-->a.txt 1 jerry-->b.txt 3 jerry-->c.txt 1 tom-->a.txt 2 tom-->b.txt 1 tom-->c.txt 1
package com.lyz.hdfs.mr.ii;
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
* 倒排索引第二步Map Reduce程序,此处程序将所有的Map/Reduce/Runner程序放在一个类中
* @author liuyazhuang
*
*/
public class InverseIndexStepTwo {
/**
* 完成倒排索引第二步的mapper程序
*
* 从第一步MR程序中得到的输入信息为:
* hello-->a.txt 3
hello-->b.txt 2
hello-->c.txt 2
jerry-->a.txt 1
jerry-->b.txt 3
jerry-->c.txt 1
tom-->a.txt 2
tom-->b.txt 1
tom-->c.txt 1
* @author liuyazhuang
*
*/
public static class StepTwoMapper extends Mapper<LongWritable, Text, Text, Text>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] fields = StringUtils.split(line, "t");
String[] wordAndFileName = StringUtils.split(fields[0], "-->");
String word = wordAndFileName[0];
String fileName = wordAndFileName[1];
long counter = Long.parseLong(fields[1]);
context.write(new Text(word), new Text(fileName + "-->" + counter));
}
}
/**
* 完成倒排索引第二步的Reducer程序
* 得到的输入信息格式为:
* <"hello", {"a.txt->3", "b.txt->2", "c.txt->2"}>,
* 最终输出结果如下:
* hello c.txt-->2 b.txt-->2 a.txt-->3
jerry c.txt-->1 b.txt-->3 a.txt-->1
tom c.txt-->1 b.txt-->1 a.txt-->2
* @author liuyazhuang
*
*/
public static class StepTwoReducer extends Reducer<Text, Text, Text, Text>{
@Override
protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
String result = "";
for(Text value : values){
result += value + " ";
}
context.write(key, new Text(result));
}
}
//运行第一步的MR程序
public static void main(String[] args) throws Exception{
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(InverseIndexStepTwo.class);
job.setMapperClass(StepTwoMapper.class);
job.setReducerClass(StepTwoReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path("D:/hadoop_data/ii/result/part-r-00000"));
FileOutputFormat.setOutputPath(job, new Path("D:/hadoop_data/ii/result/final"));
job.waitForCompletion(true);
}
}
hello-->a.txt 3 hello-->b.txt 2 hello-->c.txt 2 jerry-->a.txt 1 jerry-->b.txt 3 jerry-->c.txt 1 tom-->a.txt 2 tom-->b.txt 1 tom-->c.txt 1
hello c.txt-->2 b.txt-->2 a.txt-->3 jerry c.txt-->1 b.txt-->3 a.txt-->1 tom c.txt-->1 b.txt-->1 a.txt-->2
机械节能产品生产企业官网模板...
大气智能家居家具装修装饰类企业通用网站模板...
礼品公司网站模板
宽屏简约大气婚纱摄影影楼模板...
蓝白WAP手机综合医院类整站源码(独立后台)...苏ICP备2024110244号-2 苏公网安备32050702011978号 增值电信业务经营许可证编号:苏B2-20251499 | Copyright 2018 - 2025 源码网商城 (www.ymwmall.com) 版权所有