MapReduce-TextInputFormat 切片机制

MapReduce 默认使用 TextInputFormat 进行切片，其机制如下

（1）简单地按照文件的内容长度进行切片
（2）切片大小，默认等于Block大小，可单独设置
（3）切片时不考虑数据集整体，而是逐个针对每一个文件单独切片

例如：
（1）输入数据有两个文件：
filel.txt 320M
file2.txt 10M
（2）经过 FilelnputFormat（TextInputFormat为其实现类）的切片机制运算后，形成的切片信息如下：
filel.txt.splitl--0~128
filel.txt.split2--128～256
filel.txt.split3--256～320
file2.txt.splitl--0～10M

测试读取数据的方式

输入数据（中间为空格，末尾为换行符）

map 阶段的 k-v

可以看出 k 为偏移量，v 为一行的值，即 TextInputFormat 按行读取

以 WordCount 为例进行测试，测试切片数

测试数据，三个相同的文件

测试代码

package com.mapreduce.wordcount;

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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

import java.io.IOException;
import java.util.StringTokenizer;

public class WordCount {

    static {
        try {
            // 设置 HADOOP_HOME 环境变量
            System.setProperty("hadoop.home.dir", "D:/DevelopTools/hadoop-2.9.2/");
            // 日志初始化
            BasicConfigurator.configure();
            // 加载库文件
            System.load("D:/DevelopTools/hadoop-2.9.2/bin/hadoop.dll");
        } catch (UnsatisfiedLinkError e) {
            System.err.println("Native code library failed to load.\n" + e);
            System.exit(1);
        }
    }

    public static void main(String[] args) throws Exception {
        args = new String[]{"D:\\tmp\\input2", "D:\\tmp\\456"};
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);

        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);

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

        // 设置 InputFormat，默认为 TextInputFormat.class，这里显式设置下，后面设置切片大小
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.setMinInputSplitSize(job, 1);
        TextInputFormat.setMaxInputSplitSize(job, 1024 * 1024 * 128);

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

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            // 查看 k-v
            System.out.println(key + "\t" + value);
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

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