Hadoop 如何保存Mapreduce';没有键、值对的s减速机输出?
我正在写一个Mapreduce程序来处理Dicom图像。 这个Mapreduce程序的目的是处理dicom图像,从中提取元数据,索引到solr,最后在Reducer阶段,它应该将原始图像保存在hdfs中。 我想在HDFS中保存相同的文件作为减速机输出 所以我已经实现了大部分功能,但在reducer阶段,在hdfs中存储同一个文件时,它不起作用 我已经用Dicom图像查看器测试了处理过的Dicom文件,它显示该文件已被选中,并且处理过的Dicom文件的大小略有增加Ex.原始Dicom大小为628Kb,当reducer将此文件保存在hdfs中时,其大小将更改为630Kb 我尝试过从这些链接中找到解决方案,但没有一个给出预期的结果 以下是将Dicom文件作为单个文件读取(不拆分)的代码 所以我完全不知道该怎么办。有些链接说这是不可能的,因为Mapreduce在pair上工作,有些链接说使用NullWritable。到目前为止,我已经尝试过NullWritable、SequenceFileOutputFormat,但都不起作用 有两件事:Hadoop 如何保存Mapreduce';没有键、值对的s减速机输出?,hadoop,mapreduce,hdfs,Hadoop,Mapreduce,Hdfs,我正在写一个Mapreduce程序来处理Dicom图像。 这个Mapreduce程序的目的是处理dicom图像,从中提取元数据,索引到solr,最后在Reducer阶段,它应该将原始图像保存在hdfs中。 我想在HDFS中保存相同的文件作为减速机输出 所以我已经实现了大部分功能,但在reducer阶段,在hdfs中存储同一个文件时,它不起作用 我已经用Dicom图像查看器测试了处理过的Dicom文件,它显示该文件已被选中,并且处理过的Dicom文件的大小略有增加Ex.原始Dicom大小为628K
itr.next()
两次,您无意中在reducer中一次消耗了两个元素,这是无济于事的nullwriteable
作为值。您的减速器将如下所示:
public static class Reduce extends Reducer<Text, BytesWritable, BytesWritable, NullWritable>{
@Override
protected void reduce(Text key, Iterable<BytesWritable> value,
Reducer<Text, BytesWritable, BytesWritable, NullWritable>.Context context)
throws IOException, InterruptedException {
NullWritable nullWritable = NullWritable.get();
Iterator<BytesWritable> itr = value.iterator();
while(itr.hasNext())
{
BytesWritable wr = itr.next();
wr.setCapacity(wr.getLength());
context.write(wr, nullWritable);
}
}
}
公共静态类Reduce扩展Reducer{
@凌驾
受保护的void reduce(文本键、Iterable值、,
(上下文)
抛出IOException、InterruptedException{
nullwriteable nullwriteable=nullwriteable.get();
迭代器itr=value.Iterator();
while(itr.hasNext())
{
BytesWritable wr=itr.next();
wr.setCapacity(wr.getLength());
write(wr,nullWritable);
}
}
}
另外,是否需要调用
setCapacity()
?嘿,本,谢谢你的帮助,我忘了评论itr.next(),我也试过了,但没用。无论如何,我找到了解决办法。我已经创建了一个自定义RecordWriter和自定义fileoutput格式,它可以工作,但我仍然不知道这是正确的方法。我将很快发布答案,请在您有空时查看。
public class WholeFileRecordReader extends RecordReader<NullWritable, BytesWritable>{
private FileSplit fileSplit;
private Configuration conf;
private BytesWritable value = new BytesWritable();
private boolean processed = false;
@Override
public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
this.fileSplit = (FileSplit) split;
this.conf = context.getConfiguration();
}
@Override
public boolean nextKeyValue() throws IOException, InterruptedException {
if (!processed) {
byte[] contents = new byte[(int) fileSplit.getLength()];
System.out.println("Inside nextKeyvalue");
System.out.println(fileSplit.getLength());
Path file = fileSplit.getPath();
FileSystem fs = file.getFileSystem(conf);
FSDataInputStream in = null;
try {
in = fs.open(file);
IOUtils.readFully(in, contents, 0, contents.length);
value.set(contents, 0, contents.length);
} finally {
IOUtils.closeStream(in);
}
processed = true;
return true;
}
return false;
}
@Override
public void close() throws IOException {
}
@Override
public NullWritable getCurrentKey() throws IOException, InterruptedException
{
return NullWritable.get();
}
@Override
public BytesWritable getCurrentValue() throws IOException, InterruptedException {
return value;
}
@Override
public float getProgress() throws IOException, InterruptedException {
return processed ? 1.0f : 0.0f;
}
}
public class MapClass{
public static class Map extends Mapper<NullWritable, BytesWritable, Text, BytesWritable>{
@Override
protected void map(NullWritable key, BytesWritable value,
Mapper<NullWritable, BytesWritable, Text, BytesWritable>.Context context)
throws IOException, InterruptedException {
value.setCapacity(value.getLength());
InputStream in = new ByteArrayInputStream(value.getBytes());
ProcessDicom.metadata(in); // Process dicom image and extract metadata from it
Text keyOut = getFileName(context);
context.write(keyOut, value);
}
private Text getFileName(Mapper<NullWritable, BytesWritable, Text, BytesWritable>.Context context)
{
InputSplit spl = context.getInputSplit();
Path filePath = ((FileSplit)spl).getPath();
String fileName = filePath.getName();
Text text = new Text(fileName);
return text;
}
@Override
protected void setup(Mapper<NullWritable, BytesWritable, Text, BytesWritable>.Context context)
throws IOException, InterruptedException {
super.setup(context);
}
}
public static class Reduce extends Reducer<Text, BytesWritable, BytesWritable, BytesWritable>{
@Override
protected void reduce(Text key, Iterable<BytesWritable> value,
Reducer<Text, BytesWritable, BytesWritable, BytesWritable>.Context context)
throws IOException, InterruptedException {
Iterator<BytesWritable> itr = value.iterator();
while(itr.hasNext())
{
BytesWritable wr = itr.next();
wr.setCapacity(wr.getLength());
context.write(new BytesWritable(key.copyBytes()), itr.next());
}
}
}
public class DicomIndexer{
public static void main(String[] argss) throws Exception{
String args[] = {"file:///home/b3ds/storage/dd","hdfs://192.168.38.68:8020/output"};
run(args);
}
public static void run(String[] args) throws Exception {
//Initialize the Hadoop job and set the jar as well as the name of the Job
Configuration conf = new Configuration();
Job job = new Job(conf, "WordCount");
job.setJarByClass(WordCount.class);
// job.getConfiguration().set("mapreduce.output.basename", "hi");
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(BytesWritable.class);
job.setOutputKeyClass(BytesWritable.class);
job.setOutputValueClass(BytesWritable.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(WholeFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
WholeFileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
public static class Reduce extends Reducer<Text, BytesWritable, BytesWritable, NullWritable>{
@Override
protected void reduce(Text key, Iterable<BytesWritable> value,
Reducer<Text, BytesWritable, BytesWritable, NullWritable>.Context context)
throws IOException, InterruptedException {
NullWritable nullWritable = NullWritable.get();
Iterator<BytesWritable> itr = value.iterator();
while(itr.hasNext())
{
BytesWritable wr = itr.next();
wr.setCapacity(wr.getLength());
context.write(wr, nullWritable);
}
}
}