/**
* Executes the phase two of the parser task.
*
* <p>In phase two the data is encoded to the final VA, which is then created properly at the end.
*
* <p>For CSV launches the distributed computation.
*
* <p>For XLS and XLSX parsers computes all the chunks itself as there is no option for their
* distributed processing.
*/
public void passTwo() throws Exception {
switch (_parserType) {
case CSV:
// for CSV parser just launch the distributed parser on the chunks
// again
this.invoke(_sourceDataset._key);
break;
case XLS:
case XLSX:
// initialize statistics - invalid rows, sigma and row size
phaseTwoInitialize();
// create the output streams
_outputStreams2 = createRecords(0, _myrows);
assert (_outputStreams2.length > 0);
_ab = _outputStreams2[0].initialize();
// perform the second parse pass
CustomParser p =
(_parserType == CustomParser.Type.XLS) ? new XlsParser(this) : new XlsxParser(this);
p.parse(_sourceDataset._key);
// store the last stream if not stored during the parse
if (_ab != null) _outputStreams2[_outputIdx].store();
break;
default:
throw new Error("NOT IMPLEMENTED");
}
// normalize sigma
for (int i = 0; i < _ncolumns; ++i)
_sigma[i] = Math.sqrt(_sigma[i] / (_numRows - _invalidValues[i]));
createValueArrayHeader();
}
/**
* 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();
}
}