在Hadoop中,可以为TextOutputFormat指定记录分隔符

Question

我看到了一种使用mapreduce.textoutputformat.separator(使用api的1.03)覆盖键和值之间的分隔符的机制.但我希望能够控制记录之间的分隔符.仅供参考我使用ArrayWritable作为值,使用NullWritable作为键.

Answer 1

据我所知这是不可能的,因为TextOutputFormat用于toString()获取值的文本表示,并且如果ArrayWritable它没有实现toString(),所以Object.toString()如果你要写一个ArrayWritable输出到你的输出,你可能会得到默认值Reducer.或者你可能想要更改行之间的分隔符,在这种情况下,它与TextOutputFormat使用默认情况下的\n字符的问题是一样的问题.

话虽如此,您可以通过实现自定义输出格式来实现,您可以在其中定义自己的输出格式RecordWriter并在getRecordWriter方法中具有自定义配置属性.这是一个快速和脏的实现这样一个类(未经测试),它应该做你需要的,让你ArrayWritable通过属性mapred.arraywritable.separator控制分隔符和mapred.line.separator的行之间的分隔符:

import java.io.DataOutputStream;
import java.io.IOException;
import java.io.UnsupportedEncodingException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.ArrayWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;

public class ArrayTextOutputFormat<K, V> extends TextOutputFormat<K, V> {

protected static class ArrayLineRecordWriter<K, V> extends
        LineRecordWriter<K, V> {


    private static final String utf8 = "UTF-8";
    private final byte[] arraySeparator;
    private final byte[] keyValueSeparator;
    private final byte[] lineSeparator;

    public ArrayLineRecordWriter(DataOutputStream out,
            String keyValueSeparator, String arraySeparator, String lineSeparator) {
        super(out);
        try {
            this.keyValueSeparator = keyValueSeparator.getBytes(utf8);
            this.arraySeparator = arraySeparator.getBytes(utf8);
            this.lineSeparator = lineSeparator.getBytes(utf8);
        } catch (UnsupportedEncodingException uee) {
            throw new IllegalArgumentException("can't find " + utf8
                    + " encoding");
        }
    }

    private void writeObject(Object o) throws IOException {
        if (o instanceof Text) {
            Text to = (Text) o;
            out.write(to.getBytes(), 0, to.getLength());
        } else if (o instanceof ArrayWritable) {
            ArrayWritable awo = (ArrayWritable) o;
            for (String wrt : awo.toStrings()) {
                out.write(wrt.toString().getBytes(utf8));
                out.write(arraySeparator);
            }
        } else {
            out.write(o.toString().getBytes(utf8));
        }
    }

    public synchronized void write(K key, V value) throws IOException {

        boolean nullKey = key == null || key instanceof NullWritable;
        boolean nullValue = value == null || value instanceof NullWritable;
        if (nullKey && nullValue) {
            return;
        }
        if (!nullKey) {
            writeObject(key);
        }
        if (!(nullKey || nullValue)) {
            out.write(keyValueSeparator);
        }
        if (!nullValue) {
            writeObject(value);
        }
        out.write(lineSeparator);
    }
}

public RecordWriter<K, V> getRecordWriter(TaskAttemptContext job)
        throws IOException, InterruptedException {
    Configuration conf = job.getConfiguration();
    boolean isCompressed = getCompressOutput(job);
    String keyValueSeparator = conf.get(
            "mapred.textoutputformat.separator", "\t");
    String arraySeparator = conf.get("mapred.arraywritable.separator", "|");
    String lineSeparator = conf.get("mapred.line.separator");
    CompressionCodec codec = null;
    String extension = "";
    if (isCompressed) {
        Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(
                job, GzipCodec.class);
        codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass,
                conf);
        extension = codec.getDefaultExtension();
    }
    Path file = getDefaultWorkFile(job, extension);
    FileSystem fs = file.getFileSystem(conf);
    if (!isCompressed) {
        FSDataOutputStream fileOut = fs.create(file, false);
        return new ArrayLineRecordWriter<K, V>(fileOut, keyValueSeparator,
                arraySeparator, lineSeparator);
    } else {
        FSDataOutputStream fileOut = fs.create(file, false);
        return new ArrayLineRecordWriter<K, V>(new DataOutputStream(
                codec.createOutputStream(fileOut)), keyValueSeparator,
                arraySeparator, lineSeparator);
    }
}
}