Hadoop之多行读取数据

一，需求：
在map执行前，即setInputFormatClass过程，会进行数据的读入，默认的是每次读入一行数据，进行计算。现在需要改成每次读入两行数据并且合并结果输出。

二，思路及解决方法：
建议先看看他们的源码，理解思路。
我这里是采用的TextInputFormat.class的输入格式。它的key是每一行的偏移位置，value就是它这一行的内容。其中有创建LineRecordReader类，它就是用来读取数据的封装类，我们需要重写它。
在LineRecordReader类中，观察出其nextKeyValue()方法中，有涉及到读取数据的方法，readLine（），在这个readLine（）方法之前加个boolean值，用来控制后面不会将已经读到了的数据清空，然后再加个for循环用来做多次读取。再把这个传到readLine（）中重写这个方法。
这事又需要重写它的父类LineReader，在LineRecordReader中是调用的SplitLineReader类，它是继承的LineReader类，还需要重写其他两个类，UncompressedSplitLineReader和CompressedSplitLineReader这两个类好像是用来做压缩的，不用管直接复制就行。
回到LineReader类，我们需要重载他的readLine（）方法增加了一个boolean的参数。并将参数传到重载的readCustomLine（）和readDefaultLine（）在这个两个方法中只需利用boolean值，对数据清除进行判断，其他代码复制即可。
下面一个简图展示这个过程：

1，输入的数据：

2，结果：

源码展示：
,1， 测试类

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TestUserInputFormat {
    public static class UserMapper extends Mapper<LongWritable,Text, LongWritable, Text>{
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, LongWritable, Text>.Context context) throws IOException, InterruptedException {
            context.write(key, value);
        }
    }

    public static void main(String[] args) {
        try {
            Configuration conf=new Configuration();
            Job job=Job.getInstance(conf,"Test lineRecordReader");
            job.setJarByClass(TestUserInputFormat.class);
            job.setInputFormatClass(TextInputFormat.class);
            job.setMapperClass(UserMapper.class);
            job.setOutputKeyClass(LongWritable.class);
            job.setOutputValueClass(Text.class);
            FileInputFormat.addInputPath(job, new Path("hdfs://192.168.61.128:9000/inline/"));
            FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.61.128:9000/outline/"+System.currentTimeMillis()+"/"));
            System.exit(job.waitForCompletion(true) ? 0 : 1);
        } catch (IllegalStateException e) {
            e.printStackTrace();
        } catch (IllegalArgumentException e) {
            e.printStackTrace();
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
    }
}

2，输入格式类

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.InputFormat;
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;

import com.google.common.base.Charsets;

/** An {@link InputFormat} for plain text files.  Files are broken into lines.
 * Either linefeed or carriage-return are used to signal end of line.  Keys are
 * the position in the file, and values are the line of text.. */
@InterfaceAudience.Public
@InterfaceStability.Stable
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);
  }

  @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;
  }

}

3，读取数据类：

import java.io.IOException;
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.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.Seekable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CodecPool;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.SplitCompressionInputStream;
import org.apache.hadoop.io.compress.SplittableCompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.io.compress.Decompressor;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.commons.logging.LogFactory;
import org.apache.commons.logging.Log;

/**
 * Treats keys as offset in file and value as line. 
 */
@InterfaceAudience.LimitedPrivate({"MapReduce", "Pig"})
@InterfaceStability.Evolving
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