在运行 Hadoop MapReduce 作业时获取文件名/文件数据作为 Map 的键/值输入

Basically, I want the file name as key and the file data as value. For that I wrote a custom RecordReader as recommended in the aforementioned question. But I couldn't understand how to get the file name as the key in this class. Also, while writing the custom FileInputFormat class, I couldn't understand how to return the custom RecordReader I wrote previously.

RecordReader 代码为:

import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

public class CustomRecordReader extends RecordReader<Text, Text> {

    private static final String LINE_SEPARATOR = System.getProperty("line.separator");

    private StringBuffer valueBuffer = new StringBuffer("");
    private Text key = new Text();
    private Text value = new Text();
    private RecordReader<Text, Text> recordReader;

    public SPDRecordReader(RecordReader<Text, Text> recordReader) {
        this.recordReader = recordReader;
    }

    @Override
    public void close() throws IOException {
        recordReader.close();
    }

    @Override
    public Text getCurrentKey() throws IOException, InterruptedException {
        return key;
    }

    @Override
    public Text getCurrentValue() throws IOException, InterruptedException {
        return value;
    }

    @Override
    public float getProgress() throws IOException, InterruptedException {
        return recordReader.getProgress();
    }

    @Override
    public void initialize(InputSplit arg0, TaskAttemptContext arg1)
            throws IOException, InterruptedException {
        recordReader.initialize(arg0, arg1);
    }

    @Override
    public boolean nextKeyValue() throws IOException, InterruptedException {

        if (valueBuffer.equals("")) {
            while (recordReader.nextKeyValue()) {
                valueBuffer.append(recordReader.getCurrentValue());
                valueBuffer.append(LINE_SEPARATOR);
            }
            value.set(valueBuffer.toString());
            return true;
        }
        return false;
    }

}

而不完整的FileInputFormat类是:

import java.io.IOException;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.InputSplit;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.RecordReader;
import org.apache.hadoop.mapred.Reporter;

public class CustomFileInputFormat extends FileInputFormat<Text, Text> {

    @Override
    protected boolean isSplitable(FileSystem fs, Path filename) {
        return false;
    }

    @Override
    public RecordReader<Text, Text> getRecordReader(InputSplit arg0, JobConf arg1,
            Reporter arg2) throws IOException {
        return null;
    }
}

推荐答案

在你的 CustomRecordReader 类中有这个代码.

private LineRecordReader lineReader;

private String fileName;

public CustomRecordReader(JobConf job, FileSplit split) throws IOException {
    lineReader = new LineRecordReader(job, split);
    fileName = split.getPath().getName();
}

public boolean next(Text key, Text value) throws IOException {
    // get the next line
    if (!lineReader.next(key, value)) {
        return false;
    }    

    key.set(fileName);
    value.set(value);

    return true;
}

public Text createKey() {
    return new Text("");
}

public Text createValue() {
    return new Text("");
}

public RecordReader<Text, Text> getRecordReader(
  InputSplit input, JobConf job, Reporter reporter)
  throws IOException {

    reporter.setStatus(input.toString());
    return new CustomRecordReader(job, (FileSplit)input);
}