Java Code Examples for org.apache.hadoop.mapreduce.lib.input.CombineFileSplit#getOffset()

The following examples show how to use org.apache.hadoop.mapreduce.lib.input.CombineFileSplit#getOffset() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example 1

Source File: MultiFileWordCount.java From hadoop with Apache License 2.0

6 votes

public CombineFileLineRecordReader(CombineFileSplit split,
    TaskAttemptContext context, Integer index) throws IOException {
  
  this.path = split.getPath(index);
  fs = this.path.getFileSystem(context.getConfiguration());
  this.startOffset = split.getOffset(index);
  this.end = startOffset + split.getLength(index);
  boolean skipFirstLine = false;
  
  //open the file
  fileIn = fs.open(path);
  if (startOffset != 0) {
    skipFirstLine = true;
    --startOffset;
    fileIn.seek(startOffset);
  }
  reader = new LineReader(fileIn);
  if (skipFirstLine) {  // skip first line and re-establish "startOffset".
    startOffset += reader.readLine(new Text(), 0,
                (int)Math.min((long)Integer.MAX_VALUE, end - startOffset));
  }
  this.pos = startOffset;
}

Example 2

Source File: MultiFileWordCount.java From big-c with Apache License 2.0

6 votes

public CombineFileLineRecordReader(CombineFileSplit split,
    TaskAttemptContext context, Integer index) throws IOException {
  
  this.path = split.getPath(index);
  fs = this.path.getFileSystem(context.getConfiguration());
  this.startOffset = split.getOffset(index);
  this.end = startOffset + split.getLength(index);
  boolean skipFirstLine = false;
  
  //open the file
  fileIn = fs.open(path);
  if (startOffset != 0) {
    skipFirstLine = true;
    --startOffset;
    fileIn.seek(startOffset);
  }
  reader = new LineReader(fileIn);
  if (skipFirstLine) {  // skip first line and re-establish "startOffset".
    startOffset += reader.readLine(new Text(), 0,
                (int)Math.min((long)Integer.MAX_VALUE, end - startOffset));
  }
  this.pos = startOffset;
}

Example 3

Source File: AbstractCombineFileRecordReader.java From kite with Apache License 2.0

6 votes

@Override
public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
  if (delegate != null) {
    delegate.close();
  }
  if (split instanceof CombineFileSplit) {
    CombineFileSplit combineSplit = (CombineFileSplit) split;
    FileSplit fileSplit = new FileSplit(combineSplit.getPath(idx), combineSplit.getOffset(idx),
        combineSplit.getLength(idx), combineSplit.getLocations());
    delegate = getInputFormat().createRecordReader(fileSplit, context);
    delegate.initialize(fileSplit, context);
  } else {
    throw new DatasetOperationException(
        "Split is not a CombineFileSplit: %s:%s",
        split.getClass().getCanonicalName(), split);
  }
}

Example 4

Source File: CsvBlurDriver.java From incubator-retired-blur with Apache License 2.0

5 votes

@SuppressWarnings("unused")
public SequenceFileRecordReaderWrapper(CombineFileSplit split, TaskAttemptContext context, Integer index)
    throws IOException {
  fileSplit = new FileSplit(split.getPath(index), split.getOffset(index), split.getLength(index),
      split.getLocations());
  delegate = new SequenceFileInputFormat<Writable, Text>().createRecordReader(fileSplit, context);
}