1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49

public List<InputSplit> getSplits(JobContext job) throws IOException {
    // 首先计算分片的最大和最小值。这两个值将会用来计算分片的大小
    long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
    long maxSize = getMaxSplitSize(job);

    // generate splits
    List<InputSplit> splits = new ArrayList<InputSplit>();
    List<FileStatus> files = listStatus(job);
    for (FileStatus file: files) {
        Path path = file.getPath();
        long length = file.getLen();
        if (length != 0) {
              FileSystem fs = path.getFileSystem(job.getConfiguration());
            // 获取该文件所有的block信息列表[hostname, offset, length]
              BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length);
            // 判断文件是否可分割，通常是可分割的，但如果文件是压缩的，将不可分割
              if (isSplitable(job, path)) {
                long blockSize = file.getBlockSize();
                // 计算分片大小
                // 即 Math.max(minSize, Math.min(maxSize, blockSize));
                long splitSize = computeSplitSize(blockSize, minSize, maxSize);

                long bytesRemaining = length;
                // 循环分片。
                // 当剩余数据与分片大小比值大于Split_Slop时，继续分片， 小于等于时，停止分片
                while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
                      int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
                      splits.add(makeSplit(path, length-bytesRemaining, splitSize, blkLocations[blkIndex].getHosts()));
                      bytesRemaining -= splitSize;
                }
                // 处理余下的数据
                if (bytesRemaining != 0) {
                    splits.add(makeSplit(path, length-bytesRemaining, bytesRemaining, blkLocations[blkLocations.length-1].getHosts()));
                }
            } else {
                // 不可split，整块返回
                splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts()));
            }
        } else {
            // 对于长度为0的文件，创建空Hosts列表，返回
            splits.add(makeSplit(path, 0, length, new String[0]));
        }
    }

    // 设置输入文件数量
    job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
    LOG.debug("Total # of splits: " + splits.size());
    return splits;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80

public class LineRecordReader extends RecordReader<LongWritable, Text> {
    private CompressionCodecFactory compressionCodecs = null;
    private long start;
    private long pos;
    private long end;
    private LineReader in;
    private int maxLineLength;
    private LongWritable key = null;
    private Text value = null;

    // initialize函数即对LineRecordReader的一个初始化
    // 主要是计算分片的始末位置，打开输入流以供读取K-V对，处理分片经过压缩的情况等
    public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException {
        FileSplit split = (FileSplit) genericSplit;
        Configuration job = context.getConfiguration();
        this.maxLineLength = job.getInt("mapred.linerecordreader.maxlength", Integer.MAX_VALUE);
        start = split.getStart();
        end = start + split.getLength();
        final Path file = split.getPath();
        compressionCodecs = new CompressionCodecFactory(job);
        final CompressionCodec codec = compressionCodecs.getCodec(file);

        // 打开文件，并定位到分片读取的起始位置
        FileSystem fs = file.getFileSystem(job);
        FSDataInputStream fileIn = fs.open(split.getPath());

        boolean skipFirstLine = false;
        if (codec != null) {
            // 文件是压缩文件的话，直接打开文件
            in = new LineReader(codec.createInputStream(fileIn), job);
            end = Long.MAX_VALUE;
        } else {
            // 只要不是第一个split，则忽略本split的第一行数据
            if (start != 0) {
                skipFirstLine = true;
                --start;
                // 定位到偏移位置，下次读取就会从偏移位置开始
                fileIn.seek(start);
            }
            in = new LineReader(fileIn, job);
        }

        if (skipFirstLine) {
            // 忽略第一行数据，重新定位start
            start += in.readLine(new Text(), 0, (int) Math.min((long) Integer.MAX_VALUE, end - start));
        }
        this.pos = start;
    }

    public boolean nextKeyValue() throws IOException {
        if (key == null) {
            key = new LongWritable();
        }
        key.set(pos);// key即为偏移量
        if (value == null) {
            value = new Text();
        }
        int newSize = 0;
        while (pos < end) {
            newSize = in.readLine(value, maxLineLength,    Math.max((int) Math.min(Integer.MAX_VALUE, end - pos), maxLineLength));
            // 读取的数据长度为0，则说明已读完
            if (newSize == 0) {
                break;
            }
            pos += newSize;
            // 读取的数据长度小于最大行长度，也说明已读取完毕
            if (newSize < maxLineLength) {
                break;
            }
            // 执行到此处，说明该行数据没读完，继续读入
        }
        if (newSize == 0) {
            key = null;
            value = null;
            return false;
        } else {
            return true;
        }
    }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59

public class Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT> {
    /**
     * 预处理，仅在map task启动时运行一次
     */
    protected void setup(Context context) throws  IOException, InterruptedException {
    }

    /**
     * 对于InputSplit中的每一对<key, value>都会运行一次
     */
    @SuppressWarnings("unchecked")
    protected void map(KEYIN key, VALUEIN value, Context context) throws IOException, InterruptedException {
        context.write((KEYOUT) key, (VALUEOUT) value);
    }

    /**
     * 扫尾工作，比如关闭流等
     */
    protected void cleanup(Context context) throws IOException, InterruptedException {
    }

    /**
     * map task的驱动器
     */
    public void run(Context context) throws IOException, InterruptedException {
        setup(context);
        while (context.nextKeyValue()) {
            map(context.getCurrentKey(), context.getCurrentValue(), context);
        }
        cleanup(context);
    }
}

public class MapContext<KEYIN, VALUEIN, KEYOUT, VALUEOUT> extends TaskInputOutputContext<KEYIN, VALUEIN, KEYOUT, VALUEOUT> {
    private RecordReader<KEYIN, VALUEIN> reader;
    private InputSplit split;

    /**
     * Get the input split for this map.
     */
    public InputSplit getInputSplit() {
        return split;
    }

    @Override
    public KEYIN getCurrentKey() throws IOException, InterruptedException {
        return reader.getCurrentKey();
    }

    @Override
    public VALUEIN getCurrentValue() throws IOException, InterruptedException {
        return reader.getCurrentValue();
    }

    @Override
    public boolean nextKeyValue() throws IOException, InterruptedException {
        return reader.nextKeyValue();
    }
}

1
2
3
4
5

# 第一种
export LIBJARS=$MYLIB/commons-lang-2.3.jar, hadoop jar prohadoop-0.0.1-SNAPSHOT.jar org.aspress.prohadoop.c3. WordCountUsingToolRunner -libjars $LIBJARS

#第二种
hadoop jar prohadoop-0.0.1-SNAPSHOT-jar-with-dependencies.jar org.aspress.prohadoop.c3. WordCountUsingToolRunner The dependent libraries are now included inside the application JAR file