FileInputFormat，其中文件名是 KEY，文本内容是 VALUE

Question

我想使用整个文件作为 MAP 处理的单个记录，并以文件名作为键。
我已阅读以下帖子： 运行 Hadoop MapReduce 作业时如何获取文件名/文件内容作为 MAP 的键/值输入？
虽然最佳答案的理论是可靠的，但实际上没有提供代码或“操作方法”。

这是我的自定义 FileInputFormat 和相应的 RecordReader，它们可以编译，但不会生成任何记录数据。
感谢您的任何帮助。

public class CommentsInput
    extends FileInputFormat<Text,Text> {
protected boolean isSplitable(FileSystem fs, Path filename)
{
    return false;
}
@Override
public RecordReader<Text, Text> createRecordReader(InputSplit split, TaskAttemptContext ctx)
        throws IOException, InterruptedException {
    return new CommentFileRecordReader((FileSplit) split, ctx.getConfiguration());
}

//////////////////////////////////////////////////

public class CommentFileRecordReader
    extends RecordReader<Text,Text> {
private InputStream in;
private long start;
private long length;
private long position;
private Text key;
private Text value;
private boolean processed;
private FileSplit fileSplit;
private Configuration conf;

public CommentFileRecordReader(FileSplit fileSplit, Configuration conf) throws IOException
{
    this.fileSplit = fileSplit;
    this.conf=conf;
}

/** Boilerplate initialization code for file input streams. */
@Override
public void initialize(InputSplit split,
                     TaskAttemptContext context)
                        throws IOException, InterruptedException {
    Configuration conf = context.getConfiguration();

    fileSplit = (FileSplit) split;
    this.start = fileSplit.getStart();
    this.length = fileSplit.getLength();
    this.position = 0;
    this.processed = false;

    Path path = fileSplit.getPath();
    FileSystem fs = path.getFileSystem(conf);
    FSDataInputStream in = fs.open(path);

    CompressionCodecFactory codecs = new CompressionCodecFactory(conf);
    CompressionCodec codec = codecs.getCodec(path);
    if (codec != null)
        this.in = codec.createInputStream(in);
    else
        this.in = in;

    // If using Writables:
    // key = new Text();
    // value = new Text();
}
public boolean next(Text key, Text value) throws IOException
{
    if(!processed)
    {
        key = new Text(fileSplit.getPath().toString());
        Path file = fileSplit.getPath();
        FileSystem fs = file.getFileSystem(conf);
        FSDataInputStream in = null;
        byte[] contents = new byte[(int) fileSplit.getLength()];
        try
        {
            in = fs.open(file);
            IOUtils.readFully(in, contents, 0, contents.length);
            value.set(contents.toString());
        }
        finally
        {
            IOUtils.closeStream(in);
        }
        processed = true;
        return true;
    }
    return false;
}

@Override
public boolean nextKeyValue() throws IOException {
    // TODO parse the next key value, update position and return true.
    return false;
}

@Override
public Text getCurrentKey() {
    return key;
}

@Override
public Text getCurrentValue() {
    return value;
}

/** Returns our progress within the split, as a float between 0 and 1. */
@Override
public float getProgress() {
    if (length == 0)
        return 0.0f;
    return Math.min(1.0f, position / (float)length);
}

@Override
public void close() throws IOException {
    if (in != null)
        in.close();
}
}  

Answer 1

您需要找到一种方法来定义您自己的关键类并确保您的类使用它。您可以查找如何定义自己的密钥类，并且可以通过在其路径上调用 hte getName() 方法来获取文件名，然后使用它来制作密钥。