一、实验目的:
1、使用java对hdfs中的文件进行处理
二、实验要求:
1、使用java对hdfs中的文件进行词频计数,并得到结果。
三、实验设备:
Windows电脑一台、VMware虚拟机、WindTerm终端模拟器、IntelliJ IDEA
四、实验过程:
代码
package edu.sugon;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;
import java.io.IOException;
public class WordCount {
static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
// super.map(key, value, context);
String row = value.toString();
String[] words = row.split(" ");
for (String word : words) {
context.write(new Text(word), new IntWritable(1));
}
}
}
static class WordCountReducer 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 {
// super.reduce(key, values, context);
int total = 0;
for (IntWritable i : values) {
total += i.get();
}
context.write(key, new IntWritable(total));
}
}
public static void main(String[] args) throws Exception {
System.setProperty("HADOOP_USER_NAME", "hadoop");
//main方法在哪个类
Job job = new Job(new Configuration());
job.setJarByClass(WordCount.class);
//设置mapper类
job.setMapperClass(WordCount.WordCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
//设置reducer类
job.setReducerClass(WordCount.WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//设置输入文件,输出文件
FileInputFormat.setInputPaths(job, new Path("hdfs://192.168.10.100/031701/c.txt"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.10.100/031701/wordcount"));
job.waitForCompletion(true);
}
}