第二章——hive入门教程之word count

如果使用java编写mapreduce程序实现wordcount也很简单，如下代码就实现了一个简单的hello world程序：word count。需要的pom.xml依赖


    
        2.5
        2.7.2
        provided
    

    
        
            org.ikeguang
            common
            1.0-SNAPSHOT
        

        
        
            org.apache.hadoop
            hadoop-common
            ${hadoop.version}
            ${scopeType}
        

        
            org.apache.hadoop
            hadoop-hdfs
            ${hadoop.version}
            ${scopeType}
        

        
        
            org.apache.hadoop
            hadoop-mapreduce-client-core
            ${hadoop.version}
            ${scopeType}
        

        
            org.apache.hadoop
            hadoop-mapreduce-client-common
            ${hadoop.version}
            ${scopeType}

代码

1)、WordCountMapper.java程序：

package org.ikeguang.hadoop.mapreduce.wordcount;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * Created by keguang on 2019-12-07.
 */
public class WordCountMapper extends Mapper {

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

2)、WordCountReducer.java程序：

package org.ikeguang.hadoop.mapreduce.wordcount;

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

import java.io.IOException;

/**
 * Created by keguang on 2019-12-07.
 */
public class WordCountReducer extends Reducer {

    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for(IntWritable val : values){
            sum = sum + val.get();
        }

        context.write(key, new IntWritable(sum));
    }
}

3)、WordCountDriver.java程序:

package org.ikeguang.hadoop.mapreduce.wordcount;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.CombineTextInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.ikeguang.hadoop.util.HdfsUtil;

/**
 * Created by keguang on 2019-12-07.
 */
public class WordCountDriver extends Configured implements Tool{

    public static void main(String[] args) throws Exception {
        int ec = ToolRunner.run(new Configuration(),new WordCountDriver(),args);
        System.exit(ec);
    }

    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance();
        job.setJobName("wordcount");

        job.setJarByClass(WordCountDriver.class);
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setReducerClass(WordCountReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 输入输出路径
        String inpath = args[0];
        String output_path = args[1];

        FileInputFormat.addInputPath(job, new Path(inpath));

        if(HdfsUtil.existsFiles(conf,output_path)){
            HdfsUtil.deleteFolder(conf,output_path);
        }

        // 输入路径可以递归
        FileInputFormat.setInputDirRecursive(job,true);

        // 输入数据小文件合并
        job.setInputFormatClass(CombineTextInputFormat.class);

        // 一个map最少处理128M文件
        CombineTextInputFormat.setMinInputSplitSize(job,134217728);
        // 最多处理256M文件
        CombineTextInputFormat.setMaxInputSplitSize(job,new Long(268435456));

        // job.setNumReduceTasks(10);

        // 输出路径
        FileOutputFormat.setOutputPath(job,new Path(output_path));

        return job.waitForCompletion(true)?0:1;
    }
}

统计英文的单词数，启动程序的命令是：

hadoop jar hadoop-1.0-SNAPSHOT.jar org.ikeguang.hadoop.mapreduce.wordcount.WordCountDriver /data/wordcount/input /data/wordcount/output

hadoop-1.0-SNAPSHOT.jar：最终的jar包名字;
org.ikeguang.hadoop.mapreduce.wordcount.WordCountDriver：java程序主类(入口);
data/wordcount/input：hdfs数据输入目录;
/data/wordcount/output：hdfs数据输出目录;

结果：

Bingley 3
But 2
England;    1
Her 1
However 1
I   15
IT  1
Indeed  1
Jane,   1
Lady    1
Lizzy   2

但是需要写代码程序，终归是有门槛的，如果写hive sql简称HQL的话，只需要这样：

select word, count(1) from table group by word;

注：假设这里的word列存放单个词。
只要会sql基本语法，每个人都能上手hive进行大数据分析，其功德是无量的。

第二章——hive入门教程之word count

代码

文章评论