林子雨编著《大数据基础编程、实验和案例教程》教材第7章的代码

大数据技术原理与应用

林子雨编著《大数据基础编程、实验和案例教程》(教材官网)教材中的代码,在纸质教材中的印刷效果不是很好,可能会影响读者对代码的理解,为了方便读者正确理解代码或者直接拷贝代码用于上机实验,这里提供全书配套的所有代码。
查看教材所有章节的代码

第7章 MapReduce基础编程

教材第140页

(温馨提示:代码框上方的复制代码按钮,也就是“两张A4纸图标”,用鼠标点击复制代码按钮,就可以把代码框中的代码复制到粘贴板,粘贴到其他地方。但是,有的浏览器可能不支持该功能)

I love Spark
I love Hadoop
Hadoop is good
Spark is fast

教材第141页

public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text(); 
        public TokenizerMapper() {
        }
        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString()); 
            while(itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
        }
    }

教材第142页

public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable(); 
        public IntSumReducer() {
        }
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0; 
            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        if(otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");        //设置环境参数
        job.setJarByClass(WordCount.class);                //设置整个程序的类名
        job.setMapperClass(WordCount.TokenizerMapper.class); //添加Mapper类
        job.setReducerClass(WordCount.IntSumReducer.class);  //添加Reducer类
        job.setOutputKeyClass(Text.class);                  //设置输出类型
        job.setOutputValueClass(IntWritable.class);             //设置输出类型 
        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));  //设置输入文件
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));//设置输出文件
        System.exit(job.waitForCompletion(true)?0:1);
    }

教材第143页

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
    public WordCount() {
    }
     public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        if(otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setCombinerClass(WordCount.IntSumReducer.class);
        job.setReducerClass(WordCount.IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class); 
        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public TokenizerMapper() {
        }
        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString()); 
            while(itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
        }
    }
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
        public IntSumReducer() {
        }
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0;
            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
}

教材第145页

cd /usr/local/hadoop
export CLASSPATH="/usr/local/hadoop/share/hadoop/common/hadoop-common-2.7.1.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.7.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-cli-1.2.jar:$CLASSPATH"
javac WordCount.java
jar -cvf WordCount.jar *.class

教材第154页

cd /usr/local/hadoop/myapp
ls
cd /usr/local/hadoop
./sbin/start-dfs.sh
cd /usr/local/hadoop
./bin/hdfs dfs –rm –r input
./bin/hdfs dfs –rm –r output
cd /usr/local/hadoop
./bin/hdfs dfs –mkdir input
cd /usr/local/hadoop
./bin/hdfs dfs –put ./wordfile1.txt input
./bin/hdfs dfs –put ./wordfile2.txt input
cd /usr/local/hadoop
./bin/hadoop jar ./myapp/WordCount.jar input output

教材第156页

cd /usr/local/hadoop
./bin/hdfs dfs –cat output/*