大数据课堂实验

今天我先搭建了环境

自己修改了网上的代码分为两个类 LogBean对数据进行封装打包

package org.apache.hadoop.examples;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class LogBean implements WritableComparable<LogBean> {
    private String id;
    private String time;
    private String traffic;
    private String book;
    private String voide;

    public LogBean() {
        super();
    }

    public LogBean(String id, String traffic, String time,String book,String voide) {
        this.time = time;
        this.id = id;
        this.traffic = traffic;
        this.book=book;
        this.voide=voide;

    }

    @Override
    public String toString() {
        return "LogBean{" +
                "id=‘" + id + ‘ ‘ +
                ", time=‘" + time+ ‘ ‘ +
                ", traffic=‘" + traffic + ‘ ‘ +
                  ", book=‘" + book + ‘ ‘ +
                    ", voide=‘" + voide + ‘ ‘ +
                ‘}‘;
    }

    public String getTime() {
        return time;
    }

    public void setTime(String time) {
        this.time = time;
    }

    public String getId() {
        return id;
    }

    public void setIp(String id) {
        this.id = id;
    }

    public String getBook() {
        return book;
    }

    public void setBook(String book) {
        this.book = book;
    }
    public String getVoide() {
        return voide;
    }

    public void setUrl(String voide) {
        this.voide = voide;
    }

    @Override
    public int compareTo(LogBean o) {
        return 0;
    }

    @Override
    public void write(DataOutput out) throws IOException {

        out.writeUTF(id);
        out.writeUTF(time);
        out.writeUTF(traffic);
        out.writeUTF(book);
        out.writeUTF(voide);

    }

    @Override
    public void readFields(DataInput in) throws IOException {

        id = in.readUTF();
        time = in.readUTF();
        traffic =in.readUTF();
        book =in.readUTF();
        voide =in.readUTF();
    }
}

　BaiDuLog.java

负责对数据进行处理然后筛选

package org.apache.hadoop.examples;
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 BaiduLog {
    public static class BaiduLogMapper extends Mapper<LongWritable,Text, Text, LogBean> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//            super.map(key, value, context);
            String log = value.toString();
            String str = "(cn.baidu.core.inteceptor.LogInteceptor:55)";
            if (log.indexOf(str)!=-1){
                String[] log_arr = log.split(str);
                String time = log_arr[0].substring(1, 10);
                String[] log_arr2 = log_arr[1].split("\t");
                String id = log_arr2[1];
                String traffic=log_arr2[2];
                String book = log_arr2[3];
                String voide =log_arr2[4];
                if (id.equals("null")){
                    id = log_arr2[1];
                }
                LogBean logbean = new LogBean(id,time,traffic,book,voide);
                context.write(new Text(ip),logbean);
            }
        }
    }
    public static class BaiduLogReducer extends Reducer<Text,LogBean,IntWritable,Text>{

@Override
        protected void reduce(Text key, Iterable<LogBean> values, Context context) throws IOException, InterruptedException {
//            super.reduce(key, values, context);
            int sum = 0;

StringBuffer str = new StringBuffer();
            int flag = 0;
            for (LogBean logbean:values){
                sum++;
                if (flag==0){
                    str.append(logbean.toString());
                    flag = 1;
                }
            }
            context.write(new IntWritable(sum),new Text(str.toString()));

}
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "avg");

job.setJarByClass(BaiduLog.class);
        job.setMapperClass(BaiduLog.BaiduLogMapper.class);
        job.setReducerClass(BaiduLog.BaiduLogReducer.class);

//        job.setCombinerClass(BaiduLog.BaiduLogReducer.class);

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

FileInputFormat.addInputPath(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }

}

但是最后hive数据库没装好，所以导致后续的发展受到了限制

原文地址：https://www.cnblogs.com/yang-qiu/p/11853953.html