码迷,mamicode.com
首页 > 其他好文 > 详细

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

时间:2016-05-03 22:19:41      阅读:304      评论:0      收藏:0      [点我收藏+]

标签:

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;
    this.bufferSize = conf.getInt("io.file.buffer.size", DEFAULT_BUFFER_SIZE);
    this.buffer = new byte[this.bufferSize];
    this.recordDelimiterBytes = recordDelimiterBytes;
  }


  /**
   * Close the underlying stream.
   * @throws IOException
   */
  public void close() throws IOException {
    in.close();
  }

  /**
   * Read one line from the InputStream into the given Text.
   *
   * @param str the object to store the given line (without newline)
   * @param maxLineLength the maximum number of bytes to store into str;
   *  the rest of the line is silently discarded.
   * @param maxBytesToConsume the maximum number of bytes to consume
   *  in this call.  This is only a hint, because if the line cross
   *  this threshold, we allow it to happen.  It can overshoot
   *  potentially by as much as one buffer length.
   *
   * @return the number of bytes read including the (longest) newline
   * found.
   *
   * @throws IOException if the underlying stream throws
   */
  public int readLine(Text str, int maxLineLength,
                      int maxBytesToConsume) throws IOException {
    if (this.recordDelimiterBytes != null) {
      return readCustomLine(str, maxLineLength, maxBytesToConsume);
    } else {
      return readDefaultLine(str, maxLineLength, maxBytesToConsume);
    }
  }

  protected int fillBuffer(InputStream in, byte[] buffer, boolean inDelimiter)
      throws IOException {
    return in.read(buffer);
  }

  /**
   * Read a line terminated by one of CR, LF, or CRLF.
   */
  private int readDefaultLine(Text str, int maxLineLength, int maxBytesToConsume)
  throws IOException {
    /* We‘re reading data from in, but the head of the stream may be
     * already buffered in buffer, so we have several cases:
     * 1. No newline characters are in the buffer, so we need to copy
     *    everything and read another buffer from the stream.
     * 2. An unambiguously terminated line is in buffer, so we just
     *    copy to str.
     * 3. Ambiguously terminated line is in buffer, i.e. buffer ends
     *    in CR.  In this case we copy everything up to CR to str, but
     *    we also need to see what follows CR: if it‘s LF, then we
     *    need consume LF as well, so next call to readLine will read
     *    from after that.
     * We use a flag prevCharCR to signal if previous character was CR
     * and, if it happens to be at the end of the buffer, delay
     * consuming it until we have a chance to look at the char that
     * follows.
     */
    str.clear();
    int txtLength = 0; //tracks str.getLength(), as an optimization
    int newlineLength = 0; //length of terminating newline
    boolean prevCharCR = false; //true of prev char was CR
    long bytesConsumed = 0;
    do {
      int startPosn = bufferPosn; //starting from where we left off the last time
      if (bufferPosn >= bufferLength) {
        startPosn = bufferPosn = 0;
        if (prevCharCR) {
          ++bytesConsumed; //account for CR from previous read
        }
        bufferLength = fillBuffer(in, buffer, prevCharCR);
        if (bufferLength <= 0) {
          break; // EOF
        }
      }
      for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline
        if (buffer[bufferPosn] == LF) {
          newlineLength = (prevCharCR) ? 2 : 1;
          ++bufferPosn; // at next invocation proceed from following byte
          break;
        }
        if (prevCharCR) { //CR + notLF, we are at notLF
          newlineLength = 1;
          break;
        }
        prevCharCR = (buffer[bufferPosn] == CR);
      }
      int readLength = bufferPosn - startPosn;
      if (prevCharCR && newlineLength == 0) {
        --readLength; //CR at the end of the buffer
      }
      bytesConsumed += readLength;
      int appendLength = readLength - newlineLength;
      if (appendLength > maxLineLength - txtLength) {
        appendLength = maxLineLength - txtLength;
      }
      if (appendLength > 0) {
        str.append(buffer, startPosn, appendLength);
        txtLength += appendLength;
      }
    } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume);

    if (bytesConsumed > Integer.MAX_VALUE) {
      throw new IOException("Too many bytes before newline: " + bytesConsumed);
    }
    return (int)bytesConsumed;
  }

  /**
   * Read a line terminated by a custom delimiter.
   */
  private int readCustomLine(Text str, int maxLineLength, int maxBytesToConsume)
      throws IOException {
   /* We‘re reading data from inputStream, but the head of the stream may be
    *  already captured in the previous buffer, so we have several cases:
    * 
    * 1. The buffer tail does not contain any character sequence which
    *    matches with the head of delimiter. We count it as a 
    *    ambiguous byte count = 0
    *    
    * 2. The buffer tail contains a X number of characters,
    *    that forms a sequence, which matches with the
    *    head of delimiter. We count ambiguous byte count = X
    *    
    *    // ***  eg: A segment of input file is as follows
    *    
    *    " record 1792: I found this bug very interesting and
    *     I have completely read about it. record 1793: This bug
    *     can be solved easily record 1794: This ." 
    *    
    *    delimiter = "record";
    *        
    *    supposing:- String at the end of buffer =
    *    "I found this bug very interesting and I have completely re"
    *    There for next buffer = "ad about it. record 179       ...."           
    *     
    *     The matching characters in the input
    *     buffer tail and delimiter head = "re" 
    *     Therefore, ambiguous byte count = 2 ****   //
    *     
    *     2.1 If the following bytes are the remaining characters of
    *         the delimiter, then we have to capture only up to the starting 
    *         position of delimiter. That means, we need not include the 
    *         ambiguous characters in str.
    *     
    *     2.2 If the following bytes are not the remaining characters of
    *         the delimiter ( as mentioned in the example ), 
    *         then we have to include the ambiguous characters in str. 
    */
    str.clear();
    int txtLength = 0; // tracks str.getLength(), as an optimization
    long bytesConsumed = 0;
    int delPosn = 0;
    int ambiguousByteCount=0; // To capture the ambiguous characters count
    do {
      int startPosn = bufferPosn; // Start from previous end position
      if (bufferPosn >= bufferLength) {
        startPosn = bufferPosn = 0;
        bufferLength = fillBuffer(in, buffer, ambiguousByteCount > 0);
        if (bufferLength <= 0) {
          if (ambiguousByteCount > 0) {
            str.append(recordDelimiterBytes, 0, ambiguousByteCount);
            bytesConsumed += ambiguousByteCount;
          }
          break; // EOF
        }
      }
      for (; bufferPosn < bufferLength; ++bufferPosn) {
        if (buffer[bufferPosn] == recordDelimiterBytes[delPosn]) {
          delPosn++;
          if (delPosn >= recordDelimiterBytes.length) {
            bufferPosn++;
            break;
          }
        } else if (delPosn != 0) {
          bufferPosn--;
          delPosn = 0;
        }
      }
      int readLength = bufferPosn - startPosn;
      bytesConsumed += readLength;
      int appendLength = readLength - delPosn;
      if (appendLength > maxLineLength - txtLength) {
        appendLength = maxLineLength - txtLength;
      }
      bytesConsumed += ambiguousByteCount;
      if (appendLength >= 0 && ambiguousByteCount > 0) {
        //appending the ambiguous characters (refer case 2.2)
        str.append(recordDelimiterBytes, 0, ambiguousByteCount);
        ambiguousByteCount = 0;
        // since it is now certain that the split did not split a delimiter we
        // should not read the next record: clear the flag otherwise duplicate
        // records could be generated
        unsetNeedAdditionalRecordAfterSplit();
      }
      if (appendLength > 0) {
        str.append(buffer, startPosn, appendLength);
        txtLength += appendLength;
      }
      if (bufferPosn >= bufferLength) {
        if (delPosn > 0 && delPosn < recordDelimiterBytes.length) {
          ambiguousByteCount = delPosn;
          bytesConsumed -= ambiguousByteCount; //to be consumed in next
        }
      }
    } while (delPosn < recordDelimiterBytes.length 
        && bytesConsumed < maxBytesToConsume);
    if (bytesConsumed > Integer.MAX_VALUE) {
      throw new IOException("Too many bytes before delimiter: " + bytesConsumed);
    }
    return (int) bytesConsumed; 
  }

  /**
   * Read from the InputStream into the given Text.
   * @param str the object to store the given line
   * @param maxLineLength the maximum number of bytes to store into str.
   * @return the number of bytes read including the newline
   * @throws IOException if the underlying stream throws
   */
  public int readLine(Text str, int maxLineLength) throws IOException {
    return readLine(str, maxLineLength, Integer.MAX_VALUE);
  }

  /**
   * Read from the InputStream into the given Text.
   * @param str the object to store the given line
   * @return the number of bytes read including the newline
   * @throws IOException if the underlying stream throws
   */
  public int readLine(Text str) throws IOException {
    return readLine(str, Integer.MAX_VALUE, Integer.MAX_VALUE);
  }

  protected int getBufferPosn() {
    return bufferPosn;
  }

  protected int getBufferSize() {
    return bufferSize;
  }

  protected void unsetNeedAdditionalRecordAfterSplit() {
    // needed for custom multi byte line delimiters only
    // see MAPREDUCE-6549 for details
  }
}

它里面有很多方法,真的有我们要的readLine方法,说明我的推断没有错,没有忽悠大家,它重载了好几个readLine方法
其他我们不去管,我们只管对我们有用的,如下

 public int readLine(Text str, int maxLineLength,
                      int maxBytesToConsume) throws IOException {
    if (this.recordDelimiterBytes != null) {
      return readCustomLine(str, maxLineLength, maxBytesToConsume);
    } else {
      return readDefaultLine(str, maxLineLength, maxBytesToConsume);
    }
  }

它里面调用了readCustomLine方法和readDefaultLine方法,下面看看这两个方法

 private int readCustomLine(Text str, int maxLineLength, int maxBytesToConsume)
      throws IOException {
    str.clear();
    int txtLength = 0; // tracks str.getLength(), as an optimization
    long bytesConsumed = 0;
    int delPosn = 0;
    int ambiguousByteCount=0; // To capture the ambiguous characters count
    do {
      int startPosn = bufferPosn; // Start from previous end position
      if (bufferPosn >= bufferLength) {
        startPosn = bufferPosn = 0;
        bufferLength = fillBuffer(in, buffer, ambiguousByteCount > 0);
        if (bufferLength <= 0) {
          if (ambiguousByteCount > 0) {
            str.append(recordDelimiterBytes, 0, ambiguousByteCount);
            bytesConsumed += ambiguousByteCount;
          }
          break; // EOF
        }
      }
      for (; bufferPosn < bufferLength; ++bufferPosn) {
        if (buffer[bufferPosn] == recordDelimiterBytes[delPosn]) {
          delPosn++;
          if (delPosn >= recordDelimiterBytes.length) {
            bufferPosn++;
            break;
          }
        } else if (delPosn != 0) {
          bufferPosn--;
          delPosn = 0;
        }
      }
      int readLength = bufferPosn - startPosn;
      bytesConsumed += readLength;
      int appendLength = readLength - delPosn;
      if (appendLength > maxLineLength - txtLength) {
        appendLength = maxLineLength - txtLength;
      }
      bytesConsumed += ambiguousByteCount;
      if (appendLength >= 0 && ambiguousByteCount > 0) {
        //appending the ambiguous characters (refer case 2.2)
        str.append(recordDelimiterBytes, 0, ambiguousByteCount);
        ambiguousByteCount = 0;
        // since it is now certain that the split did not split a delimiter we
        // should not read the next record: clear the flag otherwise duplicate
        // records could be generated
        unsetNeedAdditionalRecordAfterSplit();
      }
      if (appendLength > 0) {
        str.append(buffer, startPosn, appendLength);
        txtLength += appendLength;
      }
      if (bufferPosn >= bufferLength) {
        if (delPosn > 0 && delPosn < recordDelimiterBytes.length) {
          ambiguousByteCount = delPosn;
          bytesConsumed -= ambiguousByteCount; //to be consumed in next
        }
      }
    } while (delPosn < recordDelimiterBytes.length 
        && bytesConsumed < maxBytesToConsume);
    if (bytesConsumed > Integer.MAX_VALUE) {
      throw new IOException("Too many bytes before delimiter: " + bytesConsumed);
    }
    return (int) bytesConsumed; 
  }
 private int readDefaultLine(Text str, int maxLineLength, int maxBytesToConsume)
  throws IOException {
    str.clear();
    int txtLength = 0; //tracks str.getLength(), as an optimization
    int newlineLength = 0; //length of terminating newline
    boolean prevCharCR = false; //true of prev char was CR
    long bytesConsumed = 0;
    do {
      int startPosn = bufferPosn; //starting from where we left off the last time
      if (bufferPosn >= bufferLength) {
        startPosn = bufferPosn = 0;
        if (prevCharCR) {
          ++bytesConsumed; //account for CR from previous read
        }
        bufferLength = fillBuffer(in, buffer, prevCharCR);
        if (bufferLength <= 0) {
          break; // EOF
        }
      }
      for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline
        if (buffer[bufferPosn] == LF) {
          newlineLength = (prevCharCR) ? 2 : 1;
          ++bufferPosn; // at next invocation proceed from following byte
          break;
        }
        if (prevCharCR) { //CR + notLF, we are at notLF
          newlineLength = 1;
          break;
        }
        prevCharCR = (buffer[bufferPosn] == CR);
      }
      int readLength = bufferPosn - startPosn;
      if (prevCharCR && newlineLength == 0) {
        --readLength; //CR at the end of the buffer
      }
      bytesConsumed += readLength;
      int appendLength = readLength - newlineLength;
      if (appendLength > maxLineLength - txtLength) {
        appendLength = maxLineLength - txtLength;
      }
      if (appendLength > 0) {
        str.append(buffer, startPosn, appendLength);
        txtLength += appendLength;
      }
    } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume);

    if (bytesConsumed > Integer.MAX_VALUE) {
      throw new IOException("Too many bytes before newline: " + bytesConsumed);
    }
    return (int)bytesConsumed;
  }

注意注意readCustomLine和readDefaultLine方法的第一句都用了一句代码(重点,后面我们自定义时要改的地方)
他们都用了str.clear();
这句代码什么意思,意思是系统每读完一行,它会清空这一行的值!!!
如果我们自定义读取多行的时候,肯定不能清空它,因为我们需要它来计数第二行的位置
比如
123,
456
789,
111
如果一次读两行的话 假如我把第一行清空了,那么我第二行的偏移量就得不到正确的值了,读出来的值本应该是
123,456
789,111
但是如果清空了的话 就读出来少了一行
变成了
456
111

所以我们只有独到最后一行才清空值,它前面的行都不能清空

这就要求我们到时候自己重载一个方法了,到时候再说,大家接着看

有没有晕了,没有? 那就好,我都说得这么清楚了,还晕的话,大家就先休息一下

我帮大家理一理:看都用到了哪些类

技术分享

最开始TextInputFormat里面用到了LineRecordReader,LineRecordReader里面用到了SplitLineReader,而SplitLineReader里面用到了LineReader
自定义的时候思路按这个来
TextInputFormat–》LineRecordReader–》SplitLineReader–》LineReader

下面写第一个自定义的TextInputFormat

package com.my.input;

import java.io.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.io.compress.SplittableCompressionCodec;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;


public class myInputFormat extends FileInputFormat<Text,Text> {
    //用来压缩的
    @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;
      }

    @Override
    public RecordReader<Text, Text> createRecordReader(InputSplit genericSplit, TaskAttemptContext context)
            throws IOException, InterruptedException {
        context.setStatus(genericSplit.toString());
        return new MyRecordReader(context.getConfiguration());
    }

}

接着写一个自定义的LineRecordReader
其中修改了182行开始的以下代码

因为我这里要实现输出多行,所以写了一个for循环,又由于我前面说得前面的行不能清空,所以要加一个boolean标志量

 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));
    }

改为

boolean clear = true;
        for (int i = 1; i <= 2; i++) {
            if (i == 2) {
                clear = false;
            }
            while (getFilePosition() <= end || in.needAdditionalRecordAfterSplit()) {
                if (pos == 0) {
                    newSize = skipUtfByteOrderMark();
                } else {
                    newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos), clear);
                    pos += newSize;
                }

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

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

再写自定义SplitLineReader

package com.my.lingRecordReader;
import java.io.IOException;
import java.io.InputStream;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;

@InterfaceAudience.Private
@InterfaceStability.Unstable
public class MySplitLineReader extends MyLineReader {
  public MySplitLineReader(InputStream in, byte[] recordDelimiterBytes) {
    super(in, recordDelimiterBytes);
  }

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

  public boolean needAdditionalRecordAfterSplit() {
    return false;
  }
}

最后写自定义LineReader
它重载了一个readLine(Text str, int maxLineLength, int maxBytesToConsume, boolean clear)方法来实现不清空前面读取的行的值

package com.my.lingRecordReader;

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import java.io.Closeable;
import java.io.IOException;
import java.io.InputStream;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.Text;

/**
 * A class that provides a line reader from an input stream. Depending on the
 * constructor used, lines will either be terminated by:
 * <ul>
 * <li>one of the following: ‘\n‘ (LF) , ‘\r‘ (CR), or ‘\r\n‘ (CR+LF).</li>
 * <li><em>or</em>, a custom byte sequence delimiter</li>
 * </ul>
 * In both cases, EOF also terminates an otherwise unterminated line.
 */
@InterfaceAudience.LimitedPrivate({ "MapReduce" })
@InterfaceStability.Unstable
public class MyLineReader 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 MyLineReader(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 MyLineReader(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 MyLineReader(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 MyLineReader(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 MyLineReader(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 MyLineReader(InputStream in, Configuration conf, byte[] recordDelimiterBytes) throws IOException {
        this.in = in;
        this.bufferSize = conf.getInt("io.file.buffer.size", DEFAULT_BUFFER_SIZE);
        this.buffer = new byte[this.bufferSize];
        this.recordDelimiterBytes = recordDelimiterBytes;
    }

    /**
     * Close the underlying stream.
     * 
     * @throws IOException
     */
    public void close() throws IOException {
        in.close();
    }

    /**
     * Read one line from the InputStream into the given Text.
     *
     * @param str
     *            the object to store the given line (without newline)
     * @param maxLineLength
     *            the maximum number of bytes to store into str; the rest of the
     *            line is silently discarded.
     * @param maxBytesToConsume
     *            the maximum number of bytes to consume in this call. This is
     *            only a hint, because if the line cross this threshold, we
     *            allow it to happen. It can overshoot potentially by as much as
     *            one buffer length.
     *
     * @return the number of bytes read including the (longest) newline found.
     *
     * @throws IOException
     *             if the underlying stream throws
     */
    public int readLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException {
        if (this.recordDelimiterBytes != null) {
            return readCustomLine(str, maxLineLength, maxBytesToConsume);
        } else {
            return readDefaultLine(str, maxLineLength, maxBytesToConsume);
        }
    }

    public int readLine(Text str, int maxLineLength, int maxBytesToConsume, boolean clear) throws IOException {
        if (this.recordDelimiterBytes != null) {
            return readCustomLine(str, maxLineLength, maxBytesToConsume,clear);
        } else {
            return readDefaultLine(str, maxLineLength, maxBytesToConsume,clear);
        }
    }

    protected int fillBuffer(InputStream in, byte[] buffer, boolean inDelimiter) throws IOException {
        return in.read(buffer);
    }

    private int readDefaultLine(Text str, int maxLineLength, int maxBytesToConsume, boolean clear) throws IOException {
        if (clear) {
            str.clear();
        }
        int txtLength = 0; // tracks str.getLength(), as an optimization
        int newlineLength = 0; // length of terminating newline
        boolean prevCharCR = false; // true of prev char was CR
        long bytesConsumed = 0;
        do {
            int startPosn = bufferPosn; // starting from where we left off the
                                        // last time
            if (bufferPosn >= bufferLength) {
                startPosn = bufferPosn = 0;
                if (prevCharCR) {
                    ++bytesConsumed; // account for CR from previous read
                }
                bufferLength = fillBuffer(in, buffer, prevCharCR);
                if (bufferLength <= 0) {
                    break; // EOF
                }
            }
            for (; bufferPosn < bufferLength; ++bufferPosn) { // search for
                                                                // newline
                if (buffer[bufferPosn] == LF) {
                    newlineLength = (prevCharCR) ? 2 : 1;
                    ++bufferPosn; // at next invocation proceed from following
                                    // byte
                    break;
                }
                if (prevCharCR) { // CR + notLF, we are at notLF
                    newlineLength = 1;
                    break;
                }
                prevCharCR = (buffer[bufferPosn] == CR);
            }
            int readLength = bufferPosn - startPosn;
            if (prevCharCR && newlineLength == 0) {
                --readLength; // CR at the end of the buffer
            }
            bytesConsumed += readLength;
            int appendLength = readLength - newlineLength;
            if (appendLength > maxLineLength - txtLength) {
                appendLength = maxLineLength - txtLength;
            }
            if (appendLength > 0) {
                str.append(buffer, startPosn, appendLength);
                txtLength += appendLength;
            }
        } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume);

        if (bytesConsumed > Integer.MAX_VALUE) {
            throw new IOException("Too many bytes before newline: " + bytesConsumed);
        }
        return (int) bytesConsumed;
    }

    /**
     * Read a line terminated by one of CR, LF, or CRLF.
     */
    private int readDefaultLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException {
        str.clear();
        int txtLength = 0; // tracks str.getLength(), as an optimization
        int newlineLength = 0; // length of terminating newline
        boolean prevCharCR = false; // true of prev char was CR
        long bytesConsumed = 0;
        do {
            int startPosn = bufferPosn; // starting from where we left off the
                                        // last time
            if (bufferPosn >= bufferLength) {
                startPosn = bufferPosn = 0;
                if (prevCharCR) {
                    ++bytesConsumed; // account for CR from previous read
                }
                bufferLength = fillBuffer(in, buffer, prevCharCR);
                if (bufferLength <= 0) {
                    break; // EOF
                }
            }
            for (; bufferPosn < bufferLength; ++bufferPosn) { // search for
                                                                // newline
                if (buffer[bufferPosn] == LF) {
                    newlineLength = (prevCharCR) ? 2 : 1;
                    ++bufferPosn; // at next invocation proceed from following
                                    // byte
                    break;
                }
                if (prevCharCR) { // CR + notLF, we are at notLF
                    newlineLength = 1;
                    break;
                }
                prevCharCR = (buffer[bufferPosn] == CR);
            }
            int readLength = bufferPosn - startPosn;
            if (prevCharCR && newlineLength == 0) {
                --readLength; // CR at the end of the buffer
            }
            bytesConsumed += readLength;
            int appendLength = readLength - newlineLength;
            if (appendLength > maxLineLength - txtLength) {
                appendLength = maxLineLength - txtLength;
            }
            if (appendLength > 0) {
                str.append(buffer, startPosn, appendLength);
                txtLength += appendLength;
            }
        } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume);

        if (bytesConsumed > Integer.MAX_VALUE) {
            throw new IOException("Too many bytes before newline: " + bytesConsumed);
        }
        return (int) bytesConsumed;
    }

    private int readCustomLine(Text str, int maxLineLength, int maxBytesToConsume, boolean clear) throws IOException {
        if (clear) {
            str.clear();
        }
        int txtLength = 0; // tracks str.getLength(), as an optimization
        long bytesConsumed = 0;
        int delPosn = 0;
        int ambiguousByteCount = 0; // To capture the ambiguous characters count
        do {
            int startPosn = bufferPosn; // Start from previous end position
            if (bufferPosn >= bufferLength) {
                startPosn = bufferPosn = 0;
                bufferLength = fillBuffer(in, buffer, ambiguousByteCount > 0);
                if (bufferLength <= 0) {
                    if (ambiguousByteCount > 0) {
                        str.append(recordDelimiterBytes, 0, ambiguousByteCount);
                        bytesConsumed += ambiguousByteCount;
                    }
                    break; // EOF
                }
            }
            for (; bufferPosn < bufferLength; ++bufferPosn) {
                if (buffer[bufferPosn] == recordDelimiterBytes[delPosn]) {
                    delPosn++;
                    if (delPosn >= recordDelimiterBytes.length) {
                        bufferPosn++;
                        break;
                    }
                } else if (delPosn != 0) {
                    bufferPosn--;
                    delPosn = 0;
                }
            }
            int readLength = bufferPosn - startPosn;
            bytesConsumed += readLength;
            int appendLength = readLength - delPosn;
            if (appendLength > maxLineLength - txtLength) {
                appendLength = maxLineLength - txtLength;
            }
            bytesConsumed += ambiguousByteCount;
            if (appendLength >= 0 && ambiguousByteCount > 0) {
                // appending the ambiguous characters (refer case 2.2)
                str.append(recordDelimiterBytes, 0, ambiguousByteCount);
                ambiguousByteCount = 0;
                // since it is now certain that the split did not split a
                // delimiter we
                // should not read the next record: clear the flag otherwise
                // duplicate
                // records could be generated
                unsetNeedAdditionalRecordAfterSplit();
            }
            if (appendLength > 0) {
                str.append(buffer, startPosn, appendLength);
                txtLength += appendLength;
            }
            if (bufferPosn >= bufferLength) {
                if (delPosn > 0 && delPosn < recordDelimiterBytes.length) {
                    ambiguousByteCount = delPosn;
                    bytesConsumed -= ambiguousByteCount; // to be consumed in
                                                            // next
                }
            }
        } while (delPosn < recordDelimiterBytes.length && bytesConsumed < maxBytesToConsume);
        if (bytesConsumed > Integer.MAX_VALUE) {
            throw new IOException("Too many bytes before delimiter: " + bytesConsumed);
        }
        return (int) bytesConsumed;
    }

    /**
     * Read a line terminated by a custom delimiter.
     */
    private int readCustomLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException {
        str.clear();
        int txtLength = 0; // tracks str.getLength(), as an optimization
        long bytesConsumed = 0;
        int delPosn = 0;
        int ambiguousByteCount = 0; // To capture the ambiguous characters count
        do {
            int startPosn = bufferPosn; // Start from previous end position
            if (bufferPosn >= bufferLength) {
                startPosn = bufferPosn = 0;
                bufferLength = fillBuffer(in, buffer, ambiguousByteCount > 0);
                if (bufferLength <= 0) {
                    if (ambiguousByteCount > 0) {
                        str.append(recordDelimiterBytes, 0, ambiguousByteCount);
                        bytesConsumed += ambiguousByteCount;
                    }
                    break; // EOF
                }
            }
            for (; bufferPosn < bufferLength; ++bufferPosn) {
                if (buffer[bufferPosn] == recordDelimiterBytes[delPosn]) {
                    delPosn++;
                    if (delPosn >= recordDelimiterBytes.length) {
                        bufferPosn++;
                        break;
                    }
                } else if (delPosn != 0) {
                    bufferPosn--;
                    delPosn = 0;
                }
            }
            int readLength = bufferPosn - startPosn;
            bytesConsumed += readLength;
            int appendLength = readLength - delPosn;
            if (appendLength > maxLineLength - txtLength) {
                appendLength = maxLineLength - txtLength;
            }
            bytesConsumed += ambiguousByteCount;
            if (appendLength >= 0 && ambiguousByteCount > 0) {
                // appending the ambiguous characters (refer case 2.2)
                str.append(recordDelimiterBytes, 0, ambiguousByteCount);
                ambiguousByteCount = 0;
                // since it is now certain that the split did not split a
                // delimiter we
                // should not read the next record: clear the flag otherwise
                // duplicate
                // records could be generated
                unsetNeedAdditionalRecordAfterSplit();
            }
            if (appendLength > 0) {
                str.append(buffer, startPosn, appendLength);
                txtLength += appendLength;
            }
            if (bufferPosn >= bufferLength) {
                if (delPosn > 0 && delPosn < recordDelimiterBytes.length) {
                    ambiguousByteCount = delPosn;
                    bytesConsumed -= ambiguousByteCount; // to be consumed in
                                                            // next
                }
            }
        } while (delPosn < recordDelimiterBytes.length && bytesConsumed < maxBytesToConsume);
        if (bytesConsumed > Integer.MAX_VALUE) {
            throw new IOException("Too many bytes before delimiter: " + bytesConsumed);
        }
        return (int) bytesConsumed;
    }

    /**
     * Read from the InputStream into the given Text.
     * 
     * @param str
     *            the object to store the given line
     * @param maxLineLength
     *            the maximum number of bytes to store into str.
     * @return the number of bytes read including the newline
     * @throws IOException
     *             if the underlying stream throws
     */
    public int readLine(Text str, int maxLineLength) throws IOException {
        return readLine(str, maxLineLength, Integer.MAX_VALUE);
    }

    /**
     * Read from the InputStream into the given Text.
     * 
     * @param str
     *            the object to store the given line
     * @return the number of bytes read including the newline
     * @throws IOException
     *             if the underlying stream throws
     */
    public int readLine(Text str) throws IOException {
        return readLine(str, Integer.MAX_VALUE, Integer.MAX_VALUE);
    }

    protected int getBufferPosn() {
        return bufferPosn;
    }

    protected int getBufferSize() {
        return bufferSize;
    }

    protected void unsetNeedAdditionalRecordAfterSplit() {
        // needed for custom multi byte line delimiters only
        // see MAPREDUCE-6549 for details
    }
}

下面是两个帮助类,用来压缩的,自定义一下(其实是复制源码,没有改动,只改了类名,因为我改了整个继承结构,所以只能加一个压缩的)

package com.my.lingRecordReader;
/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
import java.io.IOException;
import java.io.InputStream;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.SplitCompressionInputStream;


/**
 * Line reader for compressed splits
 *
 * Reading records from a compressed split is tricky, as the
 * LineRecordReader is using the reported compressed input stream
 * position directly to determine when a split has ended.  In addition the
 * compressed input stream is usually faking the actual byte position, often
 * updating it only after the first compressed block after the split is
 * accessed.
 *
 * Depending upon where the last compressed block of the split ends relative
 * to the record delimiters it can be easy to accidentally drop the last
 * record or duplicate the last record between this split and the next.
 *
 * Split end scenarios:
 *
 * 1) Last block of split ends in the middle of a record
 *      Nothing special that needs to be done here, since the compressed input
 *      stream will report a position after the split end once the record
 *      is fully read.  The consumer of the next split will discard the
 *      partial record at the start of the split normally, and no data is lost
 *      or duplicated between the splits.
 *
 * 2) Last block of split ends in the middle of a delimiter
 *      The line reader will continue to consume bytes into the next block to
 *      locate the end of the delimiter.  If a custom delimiter is being used
 *      then the next record must be read by this split or it will be dropped.
 *      The consumer of the next split will not recognize the partial
 *      delimiter at the beginning of its split and will discard it along with
 *      the next record.
 *
 *      However for the default delimiter processing there is a special case
 *      because CR, LF, and CRLF are all valid record delimiters.  If the
 *      block ends with a CR then the reader must peek at the next byte to see
 *      if it is an LF and therefore part of the same record delimiter.
 *      Peeking at the next byte is an access to the next block and triggers
 *      the stream to report the end of the split.  There are two cases based
 *      on the next byte:
 *
 *      A) The next byte is LF
 *           The split needs to end after the current record is returned.  The
 *           consumer of the next split will discard the first record, which
 *           is degenerate since LF is itself a delimiter, and start consuming
 *           records after that byte.  If the current split tries to read
 *           another record then the record will be duplicated between splits.
 *
 *      B) The next byte is not LF
 *           The current record will be returned but the stream will report
 *           the split has ended due to the peek into the next block.  If the
 *           next record is not read then it will be lost, as the consumer of
 *           the next split will discard it before processing subsequent
 *           records.  Therefore the next record beyond the reported split end
 *           must be consumed by this split to avoid data loss.
 *
 * 3) Last block of split ends at the beginning of a delimiter
 *      This is equivalent to case 1, as the reader will consume bytes into
 *      the next block and trigger the end of the split.  No further records
 *      should be read as the consumer of the next split will discard the
 *      (degenerate) record at the beginning of its split.
 *
 * 4) Last block of split ends at the end of a delimiter
 *      Nothing special needs to be done here. The reader will not start
 *      examining the bytes into the next block until the next record is read,
 *      so the stream will not report the end of the split just yet.  Once the
 *      next record is read then the next block will be accessed and the
 *      stream will indicate the end of the split.  The consumer of the next
 *      split will correctly discard the first record of its split, and no
 *      data is lost or duplicated.
 *
 *      If the default delimiter is used and the block ends at a CR then this
 *      is treated as case 2 since the reader does not yet know without
 *      looking at subsequent bytes whether the delimiter has ended.
 *
 * NOTE: It is assumed that compressed input streams *never* return bytes from
 *       multiple compressed blocks from a single read.  Failure to do so will
 *       violate the buffering performed by this class, as it will access
 *       bytes into the next block after the split before returning all of the
 *       records from the previous block.
 */
@InterfaceAudience.Private
@InterfaceStability.Unstable
public class MyCompressedSplitLineReader extends MySplitLineReader {

  SplitCompressionInputStream scin;
  private boolean usingCRLF;
  private boolean needAdditionalRecord = false;
  private boolean finished = false;

  public MyCompressedSplitLineReader(SplitCompressionInputStream in,
                                   Configuration conf,
                                   byte[] recordDelimiterBytes)
                                       throws IOException {
    super(in, conf, recordDelimiterBytes);
    scin = in;
    usingCRLF = (recordDelimiterBytes == null);
  }

  @Override
  protected int fillBuffer(InputStream in, byte[] buffer, boolean inDelimiter)
      throws IOException {
    int bytesRead = in.read(buffer);

    // If the split ended in the middle of a record delimiter then we need
    // to read one additional record, as the consumer of the next split will
    // not recognize the partial delimiter as a record.
    // However if using the default delimiter and the next character is a
    // linefeed then next split will treat it as a delimiter all by itself
    // and the additional record read should not be performed.
    if (inDelimiter && bytesRead > 0) {
      if (usingCRLF) {
        needAdditionalRecord = (buffer[0] != ‘\n‘);
      } else {
        needAdditionalRecord = true;
      }
    }
    return bytesRead;
  }

  @Override
  public int readLine(Text str, int maxLineLength, int maxBytesToConsume)
      throws IOException {
    int bytesRead = 0;
    if (!finished) {
      // only allow at most one more record to be read after the stream
      // reports the split ended
      if (scin.getPos() > scin.getAdjustedEnd()) {
        finished = true;
      }

      bytesRead = super.readLine(str, maxLineLength, maxBytesToConsume);
    }
    return bytesRead;
  }

  @Override
  public boolean needAdditionalRecordAfterSplit() {
    return !finished && needAdditionalRecord;
  }
}

第二个与压缩有关的类

package com.my.lingRecordReader;

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */


import java.io.IOException;
import java.io.InputStream;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.io.Text;

/**
 * SplitLineReader for uncompressed files.
 * This class can split the file correctly even if the delimiter is multi-bytes.
 */
@InterfaceAudience.Private
@InterfaceStability.Unstable
public class MyUncompressedSplitLineReader extends MySplitLineReader {
  private boolean needAdditionalRecord = false;
  private long splitLength;
  /** Total bytes read from the input stream. */
  private long totalBytesRead = 0;
  private boolean finished = false;
  private boolean usingCRLF;

  public MyUncompressedSplitLineReader(FSDataInputStream in, Configuration conf,
      byte[] recordDelimiterBytes, long splitLength) throws IOException {
    super(in, conf, recordDelimiterBytes);
    this.splitLength = splitLength;
    usingCRLF = (recordDelimiterBytes == null);
  }

  @Override
  protected int fillBuffer(InputStream in, byte[] buffer, boolean inDelimiter)
      throws IOException {
    int maxBytesToRead = buffer.length;
    if (totalBytesRead < splitLength) {
      maxBytesToRead = Math.min(maxBytesToRead,
                                (int)(splitLength - totalBytesRead));
    }
    int bytesRead = in.read(buffer, 0, maxBytesToRead);

    // If the split ended in the middle of a record delimiter then we need
    // to read one additional record, as the consumer of the next split will
    // not recognize the partial delimiter as a record.
    // However if using the default delimiter and the next character is a
    // linefeed then next split will treat it as a delimiter all by itself
    // and the additional record read should not be performed.
    if (totalBytesRead == splitLength && inDelimiter && bytesRead > 0) {
      if (usingCRLF) {
        needAdditionalRecord = (buffer[0] != ‘\n‘);
      } else {
        needAdditionalRecord = true;
      }
    }
    if (bytesRead > 0) {
      totalBytesRead += bytesRead;
    }
    return bytesRead;
  }

  @Override
  public int readLine(Text str, int maxLineLength, int maxBytesToConsume)
      throws IOException {
    int bytesRead = 0;
    if (!finished) {
      // only allow at most one more record to be read after the stream
      // reports the split ended
      if (totalBytesRead > splitLength) {
        finished = true;
      }

      bytesRead = super.readLine(str, maxLineLength, maxBytesToConsume);
    }
    return bytesRead;
  }

  @Override
  public boolean needAdditionalRecordAfterSplit() {
    return !finished && needAdditionalRecord;
  }

  @Override
  protected void unsetNeedAdditionalRecordAfterSplit() {
    needAdditionalRecord = false;
  }
}

最后就可以来测试了

先看看测试前的文件内容
技术分享

package com.my.lingRecordReader;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import com.my.input.myInputFormat;

public class myTest {
    /**
     * 
     * @author 汤高

     */
    //Map过程
    static int count=0;
    public static class MyTestMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
        /***
         * 
         */
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
                throws IOException, InterruptedException {
            //默认的map的value是每一行,我这里自定义的是以空格分割
            count++;
            //String[] vs = value.toString().split(",");
            //for (String v : vs) {
                //写出去
                context.write(new Text(value), key);
            //}
            System.out.println("========>"+count);
        }
    }

    public static void main(String[] args) {

        Configuration conf=new Configuration();
        try {
            //args从控制台获取路径 解析得到域名
            String[] paths=new GenericOptionsParser(conf,args).getRemainingArgs();
            if(paths.length<2){
                throw new RuntimeException("必須輸出 輸入 和输出路径");
            }
            //得到一个Job 并设置名字
            Job job=Job.getInstance(conf,"myTest");
            //设置Jar 使本程序在Hadoop中运行
            job.setJarByClass(myTest.class);
            //设置Map处理类
            job.setMapperClass(MyTestMapper.class);
            job.setInputFormatClass(MyTextInputFormat.class);
            //设置map的输出类型,因为不一致,所以要设置
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(LongWritable.class);
            //设置输入和输出目录
            FileInputFormat.addInputPath(job, new Path(paths[0]));
            FileOutputFormat.setOutputPath(job, new Path(paths[1] + System.currentTimeMillis()));// 整合好结果后输出的位置
            //启动运行
            System.exit(job.waitForCompletion(true) ? 0:1);
        } catch (IOException e) {
            e.printStackTrace();
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
    }


}

测试结果:
技术分享

看第2列的偏移量,发现已经实现了一次读多行(我测试的是2行)

到此所有分析已经完了,研究源码真不容易,花了我一个晚上去研究hadoop的源码,然后再花了几个小时把这些内容写成博客,所以,码字不易,转载请指明出处http://blog.csdn.net/tanggao1314/article/details/51307642

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

标签:

原文地址:http://blog.csdn.net/tanggao1314/article/details/51307642

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!