hadoop提取文件内容 教你怎么使用hadoop来提取文件中的指定内容

package com.whj.mapreduce.outputformat;

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;

public class LogMapper extends Mapper<LongWritable,Text,Text,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//        不做任何处理
        context.write(value,NullWritable.get());
    }
}

package com.whj.mapreduce.outputformat;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class LogReducer extends Reducer<Text,NullWritable,Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        for (NullWritable value : values) {
            context.write(key,NullWritable.get());
        }
    }
}

package com.whj.mapreduce.outputformat;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class LogOutputFormat extends FileOutputFormat<Text,NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        LogRecordWriter lrw = new LogRecordWriter(job);
        return lrw;
    }
}

package com.whj.mapreduce.outputformat;

import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

import java.io.IOException;

public class LogRecordWriter extends RecordWriter<Text,NullWritable> {

    private FSDataOutputStream baiduOut;//ctrl+alt+f
    private FSDataOutputStream otherOut;

    public LogRecordWriter(TaskAttemptContext job) throws IOException {
//创建两条流
        FileSystem fs = FileSystem.get(job.getConfiguration());
        baiduOut = fs.create(new Path("D:\\temp\\outputformat.log"));
        otherOut = fs.create(new Path("D:\\temp\\other.log"));
    }

    @Override
    public void write(Text key, NullWritable nullWritable) throws IOException, InterruptedException {
//        具体写
        String log = key.toString();
        if(log.contains("baidu")){
            baiduOut.writeBytes(log+"\n");
        }else{
            otherOut.writeBytes(log+"\n");
        }
    }

    @Override
    public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
//关流
        IOUtils.closeStream(baiduOut);
        IOUtils.closeStream(otherOut);
    }
}

package com.whj.mapreduce.outputformat;

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;
public class LogDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(LogDriver.class);
        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        //设置自定义的 outputformat
        job.setOutputFormatClass(LogOutputFormat.class);
        FileInputFormat.setInputPaths(job, new Path("D:\\input"));
        // 虽 然 我 们 自 定 义 了 outputformat ， 但 是 因 为 我 们 的 outputformat 继承自fileoutputformat
        //而 fileoutputformat 要输出一个_SUCCESS 文件，所以在这还得指定一个输出目录
        FileOutputFormat.setOutputPath(job, new Path("D:\\temp\\logoutput"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    } }