java - 运行Hadoop MapReduce作业时，将Filename/FileData作为Map的键/值输入

我在这里遇到了How to get Filename/File Contents as key/value input for MAP when running a Hadoop MapReduce Job?问题。尽管它解释了这个概念，但我无法成功地将其转换为代码。

基本上，我希望文件名作为键，文件数据作为值。为此，我按照上述问题的建议编写了一个自定义的RecordReader。但是我不明白如何在该类中将文件名作为键。另外，在编写自定义FileInputFormat类时，我不明白如何返回我之前编写的自定义RecordReader。
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;
    }

}

不完整的FileInputFormat类为:

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;
    }
}

最佳答案

在CustomRecordReader类中包含此代码。

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("");
}

删除SPDRecordReader构造函数(这是一个错误)。

并在CustomFileInputFormat类中包含此代码

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

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