大家好stackoverflow的好朋友们，
我运行了一个mapreduce代码，在文件中查找唯一的单词。输入数据集（文件）位于hdfs的文件夹中。所以我在运行mapreduce程序时输入了文件夹的名称。
我不知道在同一个文件夹里还有另外两个文件。mapreduce程序继续运行，读取所有3个文件并给出输出。输出良好。
这是mapreduce的默认行为吗？这意味着如果您指向一个文件夹而不仅仅是一个文件（作为输入数据集），mapreduce会使用该文件夹中的所有文件吗？我感到惊讶的原因是，在mapper中，没有读取多个文件的代码。我知道驱动程序中的第一个参数args[0]是我给出的文件夹名。
这是驱动程序代码：

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class DataSort {

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

/*
 * Validate that two arguments were passed from the command line.
 */
if (args.length != 2) {
  System.out.printf("Usage: StubDriver <input dir> <output dir>\n");
  System.exit(-1);
}

Job job=Job.getInstance();

/*
 * Specify the jar file that contains your driver, mapper, and reducer.
 * Hadoop will transfer this jar file to nodes in your cluster running 
 * mapper and reducer tasks.
 */
job.setJarByClass(DataSort.class);

/*
 * Specify an easily-decipherable name for the job.
 * This job name will appear in reports and logs.
 */
job.setJobName("Data Sort");

/*
 * TODO implement
 */
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));

job.setMapperClass(ValueIdentityMapper.class);
job.setReducerClass(IdentityReducer.class);

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

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

/*
 * Start the MapReduce job and wait for it to finish.
 * If it finishes successfully, return 0. If not, return 1.
 */
boolean success = job.waitForCompletion(true);
System.exit(success ? 0 : 1);
  }
}

Map程序代码：

import java.io.IOException;  
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class ValueIdentityMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

 @Override
  public void map(LongWritable key, Text value, Context context)
  throws IOException, InterruptedException {

    String line=value.toString();
    for (String word:line.split("\\W+"))
    {
        if (word.length()>0)
        {
            context.write(new Text(word),new IntWritable(1));
        }
    }

 }

}
减速机代码：

import java.io.IOException;

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

public class IdentityReducer extends Reducer<Text, IntWritable, Text, Text>    {

 @Override
 public void reduce(Text key, Iterable<IntWritable> values, Context context)
  throws IOException, InterruptedException {

    String word="";
    context.write(key, new Text(word));
  }
 }