MapReduce的常见输入格式之NlineInputFormat

有两个文件：

NlineInputFormat

• 切片策略： 读取配置文件中的参数mapreduce.input.lineinputformat.linespermap，默认为1，以文件为单位，切片每此参数行作为1片！

• 既然有参数，那就可以修改，设置为每N行切为一片：

Configuration conf = new Configuration();
conf.set("mapreduce.input.lineinputformat.linespermap", "2")

RecordReader：LineRecordReader，一次处理一行，将一行内容的偏移量作为key，一行内容作为value
它们的数据类型：

LongWritable key
Text value

所以上面两个文件总共八行，若一行切一片，则有八片；两行切一片，则有四片。

WCMapper.java

public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	
	private Text out_key=new Text();
	private IntWritable out_value=new IntWritable(1);
	
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
			throws IOException, InterruptedException {
	
		System.out.println("keyin:"+key+"----keyout:"+value);
		
		String[] words = value.toString().split("\t");
		
		for (String word : words) {
			out_key.set(word);
			//写出数据(单词,1)
			context.write(out_key, out_value);
		}
		
	}
}

WCReducer.java

public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
	
	private IntWritable out_value=new IntWritable();
	
	// reduce一次处理一组数据，key相同的视为一组
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
		
		int sum=0;
		
		for (IntWritable intWritable : values) {
			sum+=intWritable.get();	
		}
		
		out_value.set(sum);
		
		//将累加的值写出
		context.write(key, out_value);
		
	}
}

WCDriver.java

public class WCDriver {
	
	public static void main(String[] args) throws Exception {
		
		Path inputPath=new Path("e:/mrinput/nline");
		Path outputPath=new Path("e:/mroutput/nline");
	
		//作为整个Job的配置
		Configuration conf = new Configuration();
		
		conf.set("mapreduce.input.lineinputformat.linespermap", "2");//设置为每两行切一片
		
		//保证输出目录不存在
		FileSystem fs=FileSystem.get(conf);
		
		if (fs.exists(outputPath)) {
			fs.delete(outputPath, true);
		}
		
		// ①创建Job
		Job job = Job.getInstance(conf);
		
		job.setJarByClass(WCDriver.class);
		
		// ②设置Job
		// 设置Job运行的Mapper，Reducer类型，Mapper,Reducer输出的key-value类型
		job.setMapperClass(WCMapper.class);
		job.setReducerClass(WCReducer.class);
		
		// Job需要根据Mapper和Reducer输出的Key-value类型准备序列化器，通过序列化器对输出的key-value进行序列化和反序列化
		// 如果Mapper和Reducer输出的Key-value类型一致，直接设置Job最终的输出类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		// 声明使用NLineInputFormat
		job.setInputFormatClass(NLineInputFormat.class);
		
		// 设置输入目录和输出目录
		FileInputFormat.setInputPaths(job, inputPath);
		FileOutputFormat.setOutputPath(job, outputPath);
		
		// ③运行Job
		job.waitForCompletion(true);
		
		
	}
}