Hadoop笔记-Mapper处理SequenceFile文件

一、自定义Mapper

import java.io.IOException;

import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/**
 * <b>合并小文件 Mapper<br>
 * </b>
 * Text, BytesWritable, Text, Text
 * 输入Key类型，输入Value类型，输出Key类型，输出Value类型
 */
public class DecomposeFileMapper extends Mapper<Text, BytesWritable, Text, Text> {

	@Override
	protected void map(Text key, BytesWritable value, Context context) throws IOException, InterruptedException {
		// 字节转文本
		String content = new String(value.copyBytes());
		// 文件名称
		String fileName = key.toString();
		// TODO 可以根据需要处理content文本
		context.write(new Text(fileName), new Text(content));
	}
}

二、自定义Reducer

import java.io.IOException;

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

public class DecomposeFileReducer extends Reducer<Text, Text, Text, Text> {

	@Override
	protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
		context.write(key, values.iterator().next());
	}
}

三、执行MR

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class DecomposeFileDriver {

	public static void main(String[] args) throws Exception {

		// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
		String inputDir = "e:/output1";
		String outputDir = "e:/output2";
		process(inputDir, outputDir);
	}

	/**
	 * 执行hdfs
	 * @param inputDir 输入文件夹地址
	 * @param outputDir 输出文件夹地址
	 * @throws IOException
	 * @throws InterruptedException
	 * @throws ClassNotFoundException
	 */
	private static void process(String inputDir, String outputDir) throws IOException, InterruptedException, ClassNotFoundException {

		// 1 获取job对象
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);

		// 2 设置jar包存储位置、关联自定义的mapper和reducer
		job.setJarByClass(DecomposeFileDriver.class);
		job.setMapperClass(DecomposeFileMapper.class);
		job.setReducerClass(DecomposeFileReducer.class);

		// 7设置输入的inputFormat
		job.setInputFormatClass(SequenceFileInputFormat.class);

		// 3 设置map输出端的kv类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);

		// 4 设置最终输出端的kv类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);

		// 5 设置输入输出路径
		FileInputFormat.setInputPaths(job, new Path(inputDir));
		FileOutputFormat.setOutputPath(job, new Path(outputDir));

		// 6 提交job
		boolean result = job.waitForCompletion(true);
		System.exit(result ? 0 : 1);
	}
}

注意点：

要使用value.copyBytes()

不要写成value.getBytes()