@Override
public void reduce(DRemoteTask drt) {
try {
DParseTask other = (DParseTask) drt;
if (_sigma == null) _sigma = other._sigma;
if (_invalidValues == null) {
_enums = other._enums;
_min = other._min;
_max = other._max;
_mean = other._mean;
_sigma = other._sigma;
_scale = other._scale;
_colTypes = other._colTypes;
_nrows = other._nrows;
_invalidValues = other._invalidValues;
} else {
if (_phase == Pass.ONE) {
if (_nrows != other._nrows)
for (int i = 0; i < _nrows.length; ++i) _nrows[i] += other._nrows[i];
for (int i = 0; i < _ncolumns; ++i) {
if (_enums[i] != other._enums[i]) _enums[i].merge(other._enums[i]);
if (other._min[i] < _min[i]) _min[i] = other._min[i];
if (other._max[i] > _max[i]) _max[i] = other._max[i];
if (other._scale[i] < _scale[i]) _scale[i] = other._scale[i];
if (other._colTypes[i] > _colTypes[i]) _colTypes[i] = other._colTypes[i];
_mean[i] += other._mean[i];
}
} else if (_phase == Pass.TWO) {
for (int i = 0; i < _ncolumns; ++i) _sigma[i] += other._sigma[i];
} else assert false : "unexpected _phase value:" + _phase;
for (int i = 0; i < _ncolumns; ++i) _invalidValues[i] += other._invalidValues[i];
}
_myrows += other._myrows;
if (_error == null) _error = other._error;
else if (other._error != null) _error = _error + "\n" + other._error;
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* Map function for distributed parsing of the CSV files.
*
* <p>In first phase it calculates the min, max, means, encodings and other statistics about the
* dataset, determines the number of columns.
*
* <p>The second pass then encodes the parsed dataset to the result key, splitting it into equal
* sized chunks.
*/
@Override
public void map(Key key) {
try {
Key aryKey = null;
boolean arraylet = key._kb[0] == Key.ARRAYLET_CHUNK;
boolean skipFirstLine = _skipFirstLine;
if (arraylet) {
aryKey = ValueArray.getArrayKey(key);
_chunkId = ValueArray.getChunkIndex(key);
skipFirstLine = skipFirstLine || (ValueArray.getChunkIndex(key) != 0);
}
switch (_phase) {
case ONE:
assert (_ncolumns != 0);
// initialize the column statistics
phaseOneInitialize();
// perform the parse
CsvParser p = new CsvParser(aryKey, _ncolumns, _sep, _decSep, this, skipFirstLine);
p.parse(key);
if (arraylet) {
long idx = ValueArray.getChunkIndex(key);
int idx2 = (int) idx;
assert idx2 == idx;
assert (_nrows[idx2] == 0)
: idx
+ ": "
+ Arrays.toString(_nrows)
+ " ("
+ _nrows[idx2]
+ " -- "
+ _myrows
+ ")";
_nrows[idx2] = _myrows;
}
break;
case TWO:
assert (_ncolumns != 0);
// initialize statistics - invalid rows, sigma and row size
phaseTwoInitialize();
// calculate the first row and the number of rows to parse
int firstRow = 0;
int lastRow = _myrows;
_myrows = 0;
if (arraylet) {
long origChunkIdx = ValueArray.getChunkIndex(key);
firstRow = (origChunkIdx == 0) ? 0 : _nrows[(int) origChunkIdx - 1];
lastRow = _nrows[(int) origChunkIdx];
}
int rowsToParse = lastRow - firstRow;
// create the output streams
_outputStreams2 = createRecords(firstRow, rowsToParse);
assert (_outputStreams2.length > 0);
_ab = _outputStreams2[0].initialize();
// perform the second parse pass
CsvParser p2 = new CsvParser(aryKey, _ncolumns, _sep, _decSep, this, skipFirstLine);
p2.parse(key);
// store the last stream if not stored during the parse
if (_ab != null) _outputStreams2[_outputIdx].store();
break;
default:
assert (false);
}
ParseStatus.update(_resultKey, DKV.get(key).length(), _phase);
} catch (Exception e) {
e.printStackTrace();
_error = e.getMessage();
}
}