我创建了一个hadoop作业,其中我使用创建的比较器类(job.setGroupingComparatorClass)PathDateComparator。运行作业时,我可以看到PathDateComparator的构造函数被调用,但compare函数没有被调用。

这是PathDateComparator类:

public class PathDateComparator extends WritableComparator {

    protected PathDateComparator() {
        super(Text.class, true);
        System.out.println("PathDateComparator");
    }

    private String getPath(String s) {
        System.out.println("s:" + s);
        String[] temp = s.split(IOUtil.tab);
        return temp[0];
    }

    @Override
    public int compare(Object o1, Object o2) {
        String k1 = ((Text) o1).toString();
        System.out.println("k1:" + k1);
        String path1 = getPath(k1);
        System.out.println("path1:" + path1);

        String k2 = ((Text) o2).toString();
        System.out.println("k2:" + k2);
        String path2 = getPath(k2);
        System.out.println("path2:" + path2);

        return path1.compareTo(path2);
    }

    @Override
    public int compare(WritableComparable o1, WritableComparable o2) {
        String k1 = ((Text) o1).toString();
        System.out.println("k1:" + k1);
        String path1 = getPath(k1);
        System.out.println("path1:" + path1);

        String k2 = ((Text) o2).toString();
        System.out.println("k2:" + k2);
        String path2 = getPath(k2);
        System.out.println("path2:" + path2);

        return path1.compareTo(path2);
    }

    @Override
    public int compare(byte[] bArray1, int offset1, int length1,
            byte[] bArray2, int offset2, int length2) {

        String k1 = new String(Arrays.copyOfRange(bArray1, offset1, offset1 + length1));
        System.out.println("k1:" + k1);
        String path1 = getPath(k1);
        System.out.println("path1:" + path1);

        String k2 = new String(Arrays.copyOfRange(bArray2, offset2, offset2 + length2));
        System.out.println("k2:" + k2);
        String path2 = getPath(k2);
        System.out.println("path2:" + path2);

        return path1.compareTo(path2);
    }
}

最佳答案

您引用的类(此处为PathDateComparator)需要是RawComparator的实现者。比较方法看起来不错。想法是该类仅用于比较编码为字节数组的键值。

10-08 03:24