研究MapReduce源码之实现自定义LineRecordReader完成多行读取文件内容

TextInputFormat是Hadoop默认的数据输入格式,但是它只能一行一行的读记录，如果要读取多行怎么办？
很简单 自己写一个输入格式，然后写一个对应的Recordreader就可以了，但是要实现确不是这么简单的

首先看看TextInputFormat是怎么实现一行一行读取的

大家看一看源码

public class TextInputFormat extends FileInputFormat<LongWritable, Text> {
   

  @Override
  public RecordReader<LongWritable, Text> 
    createRecordReader(InputSplit split,
                       TaskAttemptContext context) {
    String delimiter = context.getConfiguration().get(
        "textinputformat.record.delimiter");
    byte[] recordDelimiterBytes = null;
    if (null != delimiter)
      recordDelimiterBytes = delimiter.getBytes(Charsets.UTF_8);
    return new LineRecordReader(recordDelimiterBytes);
  }
//这个对文件做压缩用的
  @Override
  protected boolean isSplitable(JobContext context, Path file) {
    final CompressionCodec codec =
      new CompressionCodecFactory(context.getConfiguration()).getCodec(file);
    if (null == codec) {
      return true;
    }
    return codec instanceof SplittableCompressionCodec;
  }

}

我们只要看第一个createRecordReader方法即可，从源码分析可知，它new了一个LineRecordReader，那么我们再来看看LineRecordReader的源码，看看这小子的内部世界

public class LineRecordReader extends RecordReader<LongWritable, Text> {
  private static final Log LOG = LogFactory.getLog(LineRecordReader.class);
  public static final String MAX_LINE_LENGTH = 
    "mapreduce.input.linerecordreader.line.maxlength";

  private long start;
  private long pos;
  private long end;
  private SplitLineReader in;
  private FSDataInputStream fileIn;
  private Seekable filePosition;
  private int maxLineLength;
  private LongWritable key;
  private Text value;
  private boolean isCompressedInput;
  private Decompressor decompressor;
  private byte[] recordDelimiterBytes;

  public LineRecordReader() {
  }

  public LineRecordReader(byte[] recordDelimiter) {
    this.recordDelimiterBytes = recordDelimiter;
  }

  public void initialize(InputSplit genericSplit,
                         TaskAttemptContext context) throws IOException {
    FileSplit split = (FileSplit) genericSplit;
    Configuration job = context.getConfiguration();
    this.maxLineLength = job.getInt(MAX_LINE_LENGTH, Integer.MAX_VALUE);
    start = split.getStart();
    end = start + split.getLength();
    final Path file = split.getPath();

    // open the file and seek to the start of the split
    final FileSystem fs = file.getFileSystem(job);
    fileIn = fs.open(file);

    CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file);
    if (null!=codec) {
      isCompressedInput = true; 
      decompressor = CodecPool.getDecompressor(codec);
      if (codec instanceof SplittableCompressionCodec) {
        final SplitCompressionInputStream cIn =
          ((SplittableCompressionCodec)codec).createInputStream(
            fileIn, decompressor, start, end,
            SplittableCompressionCodec.READ_MODE.BYBLOCK);
        in = new CompressedSplitLineReader(cIn, job,
            this.recordDelimiterBytes);
        start = cIn.getAdjustedStart();
        end = cIn.getAdjustedEnd();
        filePosition = cIn;
      } else {
        in = new SplitLineReader(codec.createInputStream(fileIn,
            decompressor), job, this.recordDelimiterBytes);
        filePosition = fileIn;
      }
    } else {
      fileIn.seek(start);
      in = new UncompressedSplitLineReader(
          fileIn, job, this.recordDelimiterBytes, split.getLength());
      filePosition = fileIn;
    }
    // If this is not the first split, we always throw away first record
    // because we always (except the last split) read one extra line in
    // next() method.
    if (start != 0) {
      start += in.readLine(new Text(), 0, maxBytesToConsume(start));
    }
    this.pos = start;
  }


  private int maxBytesToConsume(long pos) {
    return isCompressedInput
      ? Integer.MAX_VALUE
      : (int) Math.max(Math.min(Integer.MAX_VALUE, end - pos), maxLineLength);
  }

  private long getFilePosition() throws IOException {
    long retVal;
    if (isCompressedInput && null != filePosition) {
      retVal = filePosition.getPos();
    } else {
      retVal = pos;
    }
    return retVal;
  }

  private int skipUtfByteOrderMark() throws IOException {
    // Strip BOM(Byte Order Mark)
    // Text only support UTF-8, we only need to check UTF-8 BOM
    // (0xEF,0xBB,0xBF) at the start of the text stream.
    int newMaxLineLength = (int) Math.min(3L + (long) maxLineLength,
        Integer.MAX_VALUE);
    int newSize = in.readLine(value, newMaxLineLength, maxBytesToConsume(pos));
    // Even we read 3 extra bytes for the first line,
    // we won't alter existing behavior (no backwards incompat issue).
    // Because the newSize is less than maxLineLength and
    // the number of bytes copied to Text is always no more than newSize.
    // If the return size from readLine is not less than maxLineLength,
    // we will discard the current line and read the next line.
    pos += newSize;
    int textLength = value.getLength();
    byte[] textBytes = value.getBytes();
    if ((textLength >= 3) && (textBytes[0] == (byte)0xEF) &&
        (textBytes[1] == (byte)0xBB) && (textBytes[2] == (byte)0xBF)) {
      // find UTF-8 BOM, strip it.
      LOG.info("Found UTF-8 BOM and skipped it");
      textLength -= 3;
      newSize -= 3;
      if (textLength > 0) {
        // It may work to use the same buffer and not do the copyBytes
        textBytes = value.copyBytes();
        value.set(textBytes, 3, textLength);
      } else {
        value.clear();
      }
    }
    return newSize;
  }

  public boolean nextKeyValue() throws IOException {
    if (key == null) {
      key = new LongWritable();
    }
    key.set(pos);
    if (value == null) {
      value = new Text();
    }
    int newSize = 0;
    // We always read one extra line, which lies outside the upper
    // split limit i.e. (end - 1)
    while (getFilePosition() <= end || in.needAdditionalRecordAfterSplit()) {
      if (pos == 0) {
        newSize = skipUtfByteOrderMark();
      } else {
        newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos));
        pos += newSize;
      }

      if ((newSize == 0) || (newSize < maxLineLength)) {
        break;
      }

      // line too long. try again
      LOG.info("Skipped line of size " + newSize + " at pos " + 
               (pos - newSize));
    }
    if (newSize == 0) {
      key = null;
      value = null;
      return false;
    } else {
      return true;
    }
  }

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

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

  /**
   * Get the progress within the split
   */
  public float getProgress() throws IOException {
    if (start == end) {
      return 0.0f;
    } else {
      return Math.min(1.0f, (getFilePosition() - start) / (float)(end - start));
    }
  }

  public synchronized void close() throws IOException {
    try {
      if (in != null) {
        in.close();
      }
    } finally {
      if (decompressor != null) {
        CodecPool.returnDecompressor(decompressor);
      }
    }
  }
}

（里面96-97行
in = new CompressedSplitLineReader(cIn, job, this.recordDelimiterBytes);

108-109行
in = new CompressedSplitLineReader(cIn, job,this.recordDelimiterBytes);

这是用来压缩的，大家不用管，知道有这回事就行了
其实这两个类都继承自SplitLineReader，是与压缩有关的，后面我们自定义的时候不用改，粘贴复制过来就行。
）
从上面发现了一个问题，看源码的第57行

private SplitLineReader in;

它引入了一个SplitLineReader 类,用这个小子来读取每一行，不信？你看源码的182-197行，如下（我的基于2.6.4版本的源码，不同的版本代码应该差别不大）

 while (getFilePosition() <= end || in.needAdditionalRecordAfterSplit()) {
      if (pos == 0) {
        newSize = skipUtfByteOrderMark();
      } else {
        newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos));
        pos += newSize;
      }

      if ((newSize == 0) || (newSize < maxLineLength)) {
        break;
      }

      // line too long. try again
      LOG.info("Skipped line of size " + newSize + " at pos " + 
               (pos - newSize));
    }

发现没有 ===》 newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos));

它用了SplitLineReader 里面的一个方法readLine来读取，所以我们就得继续跟踪去看看SplitLineReader 这个小子的庐山真面目，下面看SplitLineReader 的源码

public class SplitLineReader extends org.apache.hadoop.util.LineReader {
   
  public SplitLineReader(InputStream in, byte[] recordDelimiterBytes) {
    super(in, recordDelimiterBytes);
  }

  public SplitLineReader(InputStream in, Configuration conf,
      byte[] recordDelimiterBytes) throws IOException {
    super(in, conf, recordDelimiterBytes);
  }

  public boolean needAdditionalRecordAfterSplit() {
    return false;
  }
}

发现这家伙继承自LineReader（快接近我们的目标了，坚持看下去），发现这小子里面根本就没有readLine方法，大家是不是觉得我在忽悠大家，哈哈，我没有忽悠大家，它源码里面确实没有，但是但是，它可是继承了LineReader这个类，说不定他的父类LineReader有了，好，不信我们去看看LineReader
继续跟踪到LineReader的源码

public class LineReader implements Closeable {
   
  private static final int DEFAULT_BUFFER_SIZE = 64 * 1024;
  private int bufferSize = DEFAULT_BUFFER_SIZE;
  private InputStream in;
  private byte[] buffer;
  // the number of bytes of real data in the buffer
  private int bufferLength = 0;
  // the current position in the buffer
  private int bufferPosn = 0;

  private static final byte CR = '\r';
  private static final byte LF = '\n';

  // The line delimiter
  private final byte[] recordDelimiterBytes;

  /**
   * Create a line reader that reads from the given stream using the
   * default buffer-size (64k).
   * @param in The input stream
   * @throws IOException
   */
  public LineReader(InputStream in) {
    this(in, DEFAULT_BUFFER_SIZE);
  }

  /**
   * Create a line reader that reads from the given stream using the 
   * given buffer-size.
   * @param in The input stream
   * @param bufferSize Size of the read buffer
   * @throws IOException
   */
  public LineReader(InputStream in, int bufferSize) {
    this.in = in;
    this.bufferSize = bufferSize;
    this.buffer = new byte[this.bufferSize];
    this.recordDelimiterBytes = null;
  }

  /**
   * Create a line reader that reads from the given stream using the
   * <code>io.file.buffer.size</code> specified in the given
   * <code>Configuration</code>.
   * @param in input stream
   * @param conf configuration
   * @throws IOException
   */
  public LineReader(InputStream in, Configuration conf) throws IOException {
    this(in, conf.getInt("io.file.buffer.size", DEFAULT_BUFFER_SIZE));
  }

  /**
   * Create a line reader that reads from the given stream using the
   * default buffer-size, and using a custom delimiter of array of
   * bytes.
   * @param in The input stream
   * @param recordDelimiterBytes The delimiter
   */
  public LineReader(InputStream in, byte[] recordDelimiterBytes) {
    this.in = in;
    this.bufferSize = DEFAULT_BUFFER_SIZE;
    this.buffer = new byte[this.bufferSize];
    this.recordDelimiterBytes = recordDelimiterBytes;
  }

  /**
   * Create a line reader that reads from the given stream using the
   * given buffer-size, and using a custom delimiter of array of
   * bytes.
   * @param in The input stream
   * @param bufferSize Size of the read buffer
   * @param recordDelimiterBytes The delimiter
   * @throws IOException
   */
  public LineReader(InputStream in, int bufferSize,
      byte[] recordDelimiterBytes) {
    this.in = in;
    this.bufferSize = bufferSize;
    this.buffer = new byte[this.bufferSize];
    this.recordDelimiterBytes = recordDelimiterBytes;
  }

  /**
   * Create a line reader that reads from the given stream using the
   * <code>io.file.buffer.size</code> specified in the given
   * <code>Configuration</code>, and using a custom delimiter of array of
   * bytes.
   * @param in input stream
   * @param conf configuration
   * @param recordDelimiterBytes The delimiter
   * @throws IOException
   */
  public LineReader(InputStream in, Configuration conf,
      byte[] recordDelimiterBytes) throws IOException {
    this.in = in;