Task* CAP3Worker::tick() {
U2OpStatus2Log os;
if (input->hasMessage()) {
Message inputMessage = getMessageAndSetupScriptValues(input);
SAFE_POINT(!inputMessage.isEmpty(), "NULL message!", NULL);
QVariantMap data = inputMessage.getData().toMap();
if (!data.contains(IN_URL_SLOT_ID)) {
os.setError("CAP3 input slot is empty!");
return new FailTask(os.getError());
}
QString dataset = data[BaseSlots::DATASET_SLOT().getId()].toString();
bool runCapForPreviousDataset = false;
if (dataset != currentDatasetName) {
if (!currentDatasetName.isEmpty()) {
runCapForPreviousDataset = true;
}
settings.inputFiles = inputSeqUrls;
inputSeqUrls.clear();
currentDatasetName = dataset;
}
inputSeqUrls << data.value(IN_URL_SLOT_ID).value<QString>();
if (runCapForPreviousDataset) {
return runCap3();
}
settings.inputFiles = inputSeqUrls;
}
else if (input->isEnded()) {
if (!settings.inputFiles.isEmpty()) {
return runCap3();
}
else {
datasetNumber = 0;
setDone();
}
}
return NULL;
}
Task *ConservationPlotWorker::tick() {
U2OpStatus2Log os;
while (inChannel->hasMessage()) {
Message m = getMessageAndSetupScriptValues(inChannel);
QVariantMap data = m.getData().toMap();
if (!data.contains(ANNOT_SLOT_ID)) {
os.setError("Annotations slot is empty");
return new FailTask(os.getError());
}
plotData = StorageUtils::getAnnotationTableHandlers(data[ANNOT_SLOT_ID]);
}
if (!inChannel->isEnded()) {
return NULL;
}
ConservationPlotSettings settings = createConservationPlotSettings(os);
if (os.hasError()) {
return new FailTask(os.getError());
}
ConservationPlotTask* t = new ConservationPlotTask(settings, context->getDataStorage(), plotData);
t->addListeners(createLogListeners());
connect(t, SIGNAL(si_stateChanged()), SLOT(sl_taskFinished()));
return t;
if (inChannel->isEnded()) {
setDone();
}
return NULL;
}
/**
* FASTQ format specification: http://maq.sourceforge.net/fastq.shtml
*/
static void load(IOAdapter* io, const U2DbiRef& dbiRef, const QVariantMap& hints, QList<GObject*>& objects, U2OpStatus& os,
int gapSize, int predictedSize, QString& writeLockReason, QMap<QString, QString>& skippedLines) {
DbiOperationsBlock opBlock(dbiRef, os);
CHECK_OP(os, );
Q_UNUSED(opBlock);
writeLockReason.clear();
bool merge = gapSize!=-1;
QByteArray sequence;
QByteArray qualityScores;
QStringList headers;
QSet<QString> uniqueNames;
QVector<U2Region> mergedMapping;
QByteArray gapSequence((merge ? gapSize : 0), 0);
sequence.reserve(predictedSize);
qualityScores.reserve(predictedSize);
// for lower case annotations
GObjectReference sequenceRef;
qint64 sequenceStart = 0;
U2SequenceImporter seqImporter(hints, true);
const QString folder = hints.value(DocumentFormat::DBI_FOLDER_HINT, U2ObjectDbi::ROOT_FOLDER).toString();
int seqNumber = 0;
int progressUpNum = 0;
const int objectsCountLimit = hints.contains(DocumentReadingMode_MaxObjectsInDoc) ? hints[DocumentReadingMode_MaxObjectsInDoc].toInt() : -1;
const bool settingsMakeUniqueName = !hints.value(DocumentReadingMode_DontMakeUniqueNames, false).toBool();
while (!os.isCoR()) {
U2OpStatus2Log warningOs;
//read header
QString sequenceName = readSequenceName(warningOs, io, '@');
// check for eof while trying to read another FASTQ block
if (io->isEof()) {
if (io->hasError()) {
os.setError(io->errorString());
}
break;
}
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
continue;
}
if(sequenceName.isEmpty()){
sequenceName = "Sequence";
}
if ((merge == false) || (seqNumber == 0)) {
QString objName = sequenceName;
if (settingsMakeUniqueName) {
objName = (merge) ? "Sequence" : TextUtils::variate(sequenceName, "_", uniqueNames);
objName.squeeze();
uniqueNames.insert(objName);
}
seqImporter.startSequence(warningOs, dbiRef, folder, objName, false);
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
}
//read sequence
if (merge && sequence.length() > 0) {
seqImporter.addDefaultSymbolsBlock(gapSize, warningOs);
sequenceStart += sequence.length();
sequenceStart+=gapSize;
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
}
sequence.clear();
readSequence(warningOs, io, sequence);
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
MemoryLocker lSequence(os, qCeil(sequence.size()/(1000*1000)));
CHECK_OP_BREAK(os);
Q_UNUSED(lSequence);
seqImporter.addBlock(sequence.data(),sequence.length(), warningOs);
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
QString qualSequenceName = readSequenceName(warningOs, io, '+');
if (!qualSequenceName.isEmpty()) {
if (sequenceName != qualSequenceName){
warningOs.setError(U2::FastqFormat::tr("Sequence name differs from quality scores name: %1 and %2").arg(sequenceName).arg(qualSequenceName));
}
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
}
// read qualities
qualityScores.clear();
readQuality(warningOs, io, qualityScores, sequence.size());
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
if(sequence.length() != qualityScores.length()){
warningOs.setError(U2::FastqFormat::tr("Bad quality scores: inconsistent size."));
}
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
U2OpStatusImpl seqOs;
seqImporter.finalizeSequenceAndValidate(seqOs);
continue;
}
seqNumber++;
progressUpNum++;
if (merge) {
headers.append(sequenceName);
mergedMapping.append(U2Region(sequenceStart, sequence.length() ));
}
else {
if (objectsCountLimit > 0 && objects.size() >= objectsCountLimit) {
os.setError(FastqFormat::tr("File \"%1\" contains too many sequences to be displayed. "
"However, you can process these data using instruments from the menu <i>Tools -> NGS data analysis</i> "
"or pipelines built with Workflow Designer.")
.arg(io->getURL().getURLString()));
break;
}
U2Sequence u2seq = seqImporter.finalizeSequenceAndValidate(warningOs);
if(errorLoggingBreak(warningOs, skippedLines, sequenceName)){
continue;
}
sequenceRef = GObjectReference(io->getURL().getURLString(), u2seq.visualName, GObjectTypes::SEQUENCE, U2EntityRef(dbiRef, u2seq.id));
U2SequenceObject* seqObj = new U2SequenceObject(u2seq.visualName, U2EntityRef(dbiRef, u2seq.id));
CHECK_EXT_BREAK(seqObj != NULL, os.setError("U2SequenceObject is NULL"));
seqObj->setQuality(DNAQuality(qualityScores));
objects << seqObj;
U1AnnotationUtils::addAnnotations(objects, seqImporter.getCaseAnnotations(), sequenceRef, NULL, hints);
}
if (PROGRESS_UPDATE_STEP == progressUpNum) {
progressUpNum = 0;
os.setProgress(io->getProgress());
}
}
CHECK_OP_EXT(os, qDeleteAll(objects); objects.clear(), );
bool emptyObjects = objects.isEmpty();
CHECK_EXT(!emptyObjects || merge, os.setError(Document::tr("Document is empty.")), );
SAFE_POINT(headers.size() == mergedMapping.size(), "headers <-> regions mapping failed!", );
if (!merge) {
return;
}
U2Sequence u2seq = seqImporter.finalizeSequenceAndValidate(os);
CHECK_OP(os,);
sequenceRef = GObjectReference(io->getURL().getURLString(), u2seq.visualName, GObjectTypes::SEQUENCE, U2EntityRef(dbiRef, u2seq.id));
U1AnnotationUtils::addAnnotations(objects, seqImporter.getCaseAnnotations(), sequenceRef, NULL, hints);
objects << new U2SequenceObject(u2seq.visualName, U2EntityRef(dbiRef, u2seq.id));
objects << DocumentFormatUtils::addAnnotationsForMergedU2Sequence(sequenceRef, dbiRef, headers, mergedMapping, hints);
if (headers.size() > 1) {
writeLockReason = QObject::tr("Document sequences were merged");
}
}
