MapReduce-FileInputFormat

在运行 MapReduce 程序时，输入的文件格式包括：基于行的日志文件、二进制格式文件、数据库表等。那么，针对不同的数据类型，MapReduce 是如何读取这些数据？

FileInputFormat 用来读取数据，其本身为一个抽象类，继承自 InputFormat 抽象类，针对不同的类型的数据有不同的子类来处理。
FileInputFormat 常见的接口实现类包括：TextInputFormat、KeyValueTextInputFormat、NLinelnputFormat、CombineTextInputFormat 和自定义 ImputFormat 等。

1.TextInputFormat 与 CombineTextInputFormat 类似，都是按行读取，键为偏移量，值为当前行的类容，只是切片机制不同。

2.KeyValueTextInputFormat 也是按行读取，当前行内容被分隔符分为 key 和 value。默认分隔符为 tab(\t)，可设置。

测试数据

按照空格分割，控制台日志（会取第一个匹配字符进行分割）

测试代码，统计重复 key 的次数

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

import java.io.IOException;

public class KVDriver {

    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 IOException, ClassNotFoundException, InterruptedException {

        args = new String[]{"D:\\tmp\\input2", "D:\\tmp\\456"};
        Configuration conf = new Configuration();

        // 设置分隔符
        conf.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, " ");

        Job job = Job.getInstance(conf);
        job.setJarByClass(KVDriver.class);

        job.setMapperClass(KVMapper.class);
        job.setReducerClass(KVReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

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

        // 设置 FileInputFormat
        job.setInputFormatClass(KeyValueTextInputFormat.class);

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

class KVMapper extends Mapper<Text, Text, Text, IntWritable> {

    IntWritable v = new IntWritable(1);

    @Override
    protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
        // 查看 k-v
        System.out.println(key + "===" + value);
        context.write(key, v);
    }
}

class KVReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    IntWritable v = new IntWritable();

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

3.NLinelnputFormat 与 TextInputFormat 和 CombineTextInputFormat  类似，但切片机制不同。

每个 map 进程处理的 InputSplit 不再按 Blok 块去划分，而是按 NlinelnputFormat 指定的行数 N 来划分。即（输入文件的总行数/N=切片数），如果不整除，切片数=商+1。

同样的测试数据，设置一行为一个切片

k-v 值

切片数

测试代码，统计单词数量

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

import java.io.IOException;

public class NLineDriver {

    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 IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"D:\\tmp\\input2", "D:\\tmp\\456"};

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        job.setJarByClass(NLineDriver.class);
        job.setMapperClass(NLineMapper.class);
        job.setReducerClass(NLineReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

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

        // 使用 NLineInputFormat 处理记录数
        job.setInputFormatClass(NLineInputFormat.class);
        // 设置每个切片 InputSplit 中划分一条记录
        NLineInputFormat.setNumLinesPerSplit(job, 1);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}

class NLineMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    Text k = new Text();
    IntWritable v = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 查看 k-v
        System.out.println(key + "===" + value);
        // 获取一行
        String line = value.toString();
        // 切割
        String[] words = line.split(" ");
        // 循环写出
        for (String word : words) {
            k.set(word);
            context.write(k, v);
        }
    }
}

class NLineReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    IntWritable v = new IntWritable();

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