/** return progress based on the amount of data processed so far. */
public float getProgress() throws IOException, InterruptedException {
long subprogress = 0; // bytes processed in current split
if (null != curReader) {
// idx is always one past the current subsplit's true index.
subprogress = (long) (curReader.getProgress() * split.getLength(idx - 1));
}
return Math.min(1.0f, (progress + subprogress) / (float) (split.getLength()));
}
public boolean nextKeyValue() throws IOException, InterruptedException {
while ((curReader == null) || !curReader.nextKeyValue()) {
if (!initNextRecordReader()) {
return false;
}
}
return true;
}
/** Get the record reader for the next chunk in this CombineFileSplit. */
protected boolean initNextRecordReader() throws IOException {
if (curReader != null) {
curReader.close();
curReader = null;
if (idx > 0) {
progress += split.getLength(idx - 1); // done processing so far
}
}
// if all chunks have been processed, nothing more to do.
if (idx == split.getNumPaths()) {
return false;
}
// get a record reader for the idx-th chunk
try {
Configuration conf = context.getConfiguration();
// setup some helper config variables.
conf.set(MRJobConfig.MAP_INPUT_FILE, split.getPath(idx).toString());
conf.setLong(MRJobConfig.MAP_INPUT_START, split.getOffset(idx));
conf.setLong(MRJobConfig.MAP_INPUT_PATH, split.getLength(idx));
curReader = rrConstructor.newInstance(new Object[] {split, context, Integer.valueOf(idx)});
if (idx > 0) {
// initialize() for the first RecordReader will be called by MapTask;
// we're responsible for initializing subsequent RecordReaders.
curReader.initialize(split, context);
}
} catch (Exception e) {
throw new RuntimeException(e);
}
idx++;
return true;
}
public void close() throws IOException {
if (curReader != null) {
curReader.close();
curReader = null;
}
}
public V getCurrentValue() throws IOException, InterruptedException {
return curReader.getCurrentValue();
}
public K getCurrentKey() throws IOException, InterruptedException {
return curReader.getCurrentKey();
}