统计不同文件中单词的个数

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接： https://blog.csdn.net/weixin_45526489/article/details/100769856

package FileCount;

import org.apache.hadoop.conf.Configuration;


import org.apache.hadoop.fs.FileSystem;
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.mapred.FileSplit;
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 InveseIndexOne {
    public static class InveseIndexOneMap extends Mapper<LongWritable, Text, Text, IntWritable> {
        String fileName = null;
        Text k = new Text();

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            FileSplit inputSplit = (FileSplit) context.getInputSplit();
            //获取文件名字
            fileName = inputSplit.getPath().getName();
        }

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] words = value.toString().split(" ");
            for (String word : words) {
                k.set(word + "-" + fileName);
                context.write(k, new IntWritable(1));
            }
        }

    }

    public static class InveseIndexOneReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            Integer count = 0;
            for (IntWritable value : values) {
                count++;
            }
            context.write(key, new IntWritable(count));
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(InveseIndexOne.class);
        job.setMapperClass(InveseIndexOneMap.class);
        job.setReducerClass(InveseIndexOneReduce.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job,new Path(args[0]));
        Path output = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(conf);
        boolean exists = fileSystem.exists(output);
        if(exists){
            fileSystem.delete(output,true);

        }
        FileOutputFormat.setOutputPath(job,output);
        boolean b = job.waitForCompletion(true);
        System.exit(b?0:1);
    }
}

package FileCount;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

import java.io.IOException;

public class InveseIndextwo {
    public static class InveseIndextwoMap extends Mapper<LongWritable, Text,Text,Text>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] split = value.toString().split("-");
            String word = split[0];
            String index =split[1];
            context.write(new Text(word),new Text(index));

        }
    }
    public static class InveseIndextwoReducer extends Reducer<Text,Text,Text,Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            StringBuilder sb = new StringBuilder();
            for(Text value:values){
                sb.append(value).append(",");
            }
            context.write(key,new Text(sb.toString()));
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance();
        job.setJarByClass(InveseIndextwo.class);
        job.setMapperClass(InveseIndextwoMap.class);
        job.setReducerClass(InveseIndextwoReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        FileInputFormat.setInputPaths(job,new Path(args[0]));
        Path output = new Path(args[1]);

        FileSystem fileSystem = FileSystem.get(conf);
        boolean exists = fileSystem.exists(output);
        if(exists){
            fileSystem.delete(output,true);
        }
        FileOutputFormat.setOutputPath(job,output);
        boolean b = job.waitForCompletion(true);
        System.exit(b?0:1);
    }
}