写一段java程序，把hdfs的小文件合并成大文件

在Hadoop框架中，合并小文件通常会利用MapReduce API或者其他的工具如Apache Hadoop Streaming。下面是一个简单的Java MapReduce示例，用于将HDFS上的小文件合并成一个大的文本文件：

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class FileMerger {

    public static void main(String[] args) throws IOException, InterruptedException {
        if (args.length != 3) {
            System.err.println("Usage: FileMerger <inputdir> <outputfile> <mapper>");
            System.exit(2);
        }

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Merge Small Files");

        job.setJarByClass(FileMerger.class); // Set the JAR file for this job
        job.setMapperClass(Mapper.class); // Define your Mapper class
        job.setOutputKeyClass(Text.class); // Output key type is text
        job.setOutputValueClass(Text.class); // Output value type is also text

        // Input and output paths
        FileInputFormat.addInputPath(job, new Path(args[0])); // The directory containing small files
        FileOutputFormat.setOutputPath(job, new Path(args[1])); // The target output file

        // Start the job
        boolean success = job.waitForCompletion(true);

        if (!success) {
            System.err.println("Job failed!");
        } else {
            System.out.println("Job completed successfully.");
        }
    }

}

// 定义Mapper类，这里假设它从每个输入行读取并连接所有小文件内容
class Mapper extends Mapper<LongWritable, Text, NullWritable, Text> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        word.set(line);
        context.write(null, word); // write the combined content to output
    }
}

在这个例子中，`Mapper`类负责接收小文件的内容，然后将其写入到输出键值对中。记住，这只是一个基础示例，实际应用中可能需要处理更复杂的逻辑，比如拆分、排序和合并操作。