bool OctreePacketData::appendValue(const QByteArray& bytes) {
// TODO: make this a ByteCountCoded leading byte
uint16_t length = bytes.size();
bool success = appendValue(length);
if (success) {
success = appendRawData((const unsigned char*)bytes.constData(), bytes.size());
}
return success;
}
bool OctreePacketData::appendValue(const QString& string) {
// TODO: make this a ByteCountCoded leading byte
uint16_t length = string.size() + 1; // include NULL
bool success = appendValue(length);
if (success) {
success = appendRawData((const unsigned char*)qPrintable(string), length);
}
return success;
}
bool Table::readFromStream(std::istream *dataStream)
{
std::string inputLine;
size_t left = 0, right = 0;
unsigned int rowIndex, columnIndex;
// First, determine the number of columns:
std::getline(*dataStream, inputLine, '\n');
m_columnCount = (unsigned int)(std::count(inputLine.begin(), inputLine.end(), '\t') + 1);
// Create column objects:
for (columnIndex = 0; columnIndex < m_columnCount; columnIndex++)
{
push_back(new Column(columnIndex));
}
// Jump to the beginning of the file:
dataStream->seekg(0);
for (rowIndex = 0; !dataStream->eof(); rowIndex++)
{
//if (rowIndex % 1000 == 0)
// std::cout << "Reading row: " << rowIndex << std::endl;
// Read next input line:
std::getline(*dataStream, inputLine, '\n');
if (dataStream->eof())
break;
left = 0;
for (columnIndex = 0; (right = inputLine.find('\t', left)) != std::string::npos && columnIndex < m_columnCount; columnIndex++) {
appendValue(inputLine.substr(left, right-left), columnIndex);
left = right+1;
}
appendValue(inputLine.substr(left, std::string::npos), columnIndex);
}
m_rowCount = rowIndex;
return true;
}
int getSVLen(seqan::CharString const & str)
{
seqan::DirectionIterator<seqan::CharString const, seqan::Input>::Type inputIter =
directionIterator(str, seqan::Input());
// Parse out key/value pairs and interpret SVLEN.
seqan::CharString key, val;
enum { IN_KEY, IN_VALUE } state = IN_KEY;
for (; !atEnd(inputIter); ++inputIter)
{
if (*inputIter == '=')
{
state = IN_VALUE;
continue;
}
else if (*inputIter == ';')
{
if (key == "SVLEN")
return seqan::lexicalCast<int>(val);
clear(val);
clear(key);
state = IN_KEY;
continue;
}
else if (state == IN_KEY)
{
appendValue(key, *inputIter);
}
else // (state == IN_VALUE)
{
appendValue(val, *inputIter);
}
}
if (key == "SVLEN")
return seqan::lexicalCast<int>(val);
SEQAN_FAIL("Missing INFO SVLEN %s", toCString(str));
return 0;
}
bool OctreePacketData::appendValue(const QVector<float>& value) {
uint16_t qVecSize = value.size();
bool success = appendValue(qVecSize);
if (success) {
success = append((const unsigned char*)value.constData(), qVecSize * sizeof(float));
if (success) {
_bytesOfValues += qVecSize * sizeof(float);
_totalBytesOfValues += qVecSize * sizeof(float);
}
}
return success;
}
void CLIPSExtractValueInstructionBuilder::addFields(ExtractValueInst* inst, KnowledgeConstruction *kc, char* parent) {
CLIPSUnaryInstructionBuilder::addFields((UnaryInstruction*)inst, kc, parent);
addField("AggregateOperand", kc->route(inst->getAggregateOperand(), getNamer()));
openField("Indices");
for(ExtractValueInst::idx_iterator i = inst->idx_begin(), e = inst->idx_end();
i != e; ++i) {
char* buf = CharBuffer(32);
sprintf(buf, "%d", *i);
appendValue(buf);
free(buf);
}
closeField();
}
void CLIPSBasicBlockBuilder::addFields(BasicBlock* bb, KnowledgeConstructor *kc, char* parent, bool constructInstructions) {
CLIPSValueBuilder::addFields((Value*)bb, kc, parent);
char* name = (char*)bb->getName().data();
FunctionNamer& namer = getNamer();
namer.registerBasicBlock(name);
if(bb->isLandingPad()) addTrueField("IsLandingPad");
if(bb->hasAddressTaken()) addTrueField("HasAddressTaken");
pred_iterator pi = pred_begin(bb), pe = pred_end(bb);
if(pi != pe) {
openField("Predecessors");
for(; pi != pe; ++pi) {
BasicBlock* pred = *pi;
appendValue(pred->getName());
}
closeField();
}
succ_iterator si = succ_begin(bb), se = succ_end(bb);
if(si != se) {
openField("Successors");
for(; si != se; ++si) {
BasicBlock* succ = *si;
appendValue(succ->getName());
}
closeField();
}
if(constructInstructions && !bb->empty()) {
std::string tmp;
raw_string_ostream data(tmp);
openField("contents");
for(BasicBlock::iterator i = bb->begin(), e = bb->end(); i != e; ++i) {
Instruction* inst = i;
std::string res = kc->route(inst, namer, name);
appendValue(res);
data << " " << res;
}
closeField();
addField("Produces", data.str());
}
}
void print(TText const & score, MaxOnly const & /*tag*/)
{
int maxScore = score[0];
seqan::String<int> output;
appendValue(output, 0);
for (unsigned i = 1; i < seqan::length(score); ++i)
{
if (score[i] > maxScore)
{
maxScore = score[i];
clear(output);
resize(output, 1, i);
}
else if (score[i] == maxScore)
{
appendValue(output, i);
}
}
for (unsigned i = 0; i < seqan::length(output); ++i)
std::cout << output[i] << " ";
std::cout << std::endl;
}
void IntersectBed::writeEmptyBed(seqan::BedRecord<seqan::Bed6> const & bedRecord)
{
seqan::RoiRecord roiRecord;
roiRecord.ref = bedRecord.ref;
roiRecord.beginPos = bedRecord.beginPos;
roiRecord.endPos = bedRecord.endPos;
roiRecord.strand = bedRecord.strand;
roiRecord.name = bedRecord.name;
roiRecord.len = roiRecord.endPos - roiRecord.beginPos;
roiRecord.countMax = 0;
for (int i = 0; i < (int)roiRecord.len; ++i)
appendValue(roiRecord.count, 0);
writeRecord(roiFileOut, roiRecord);
}
/*****************************************************************************
Clone this linked list of values and return the new one.
@param { ValueP } list to the first Value in the list
@return { ValueP } new list of clones
*****************************************************************************/
ValueP cloneValues( ValueP list ){
ValueP newList; /* pointer to the currect value */
newList = NULL;
ValueP newNode; /* pointer to the result, found or created */
newNode = NULL;
/* search the list first */
while( list ){
newNode = newValue( list->letter, list->attribute );
newNode->count = list->count;
newList = appendValue( newList, newNode );
list = list->next;
}
return newList;
} /* end cloneValues */
String SVGParsingError::format(const String& tagName, const QualifiedName& name, const AtomicString& value) const
{
StringBuilder builder;
appendErrorContextInfo(builder, tagName, name);
builder.append(": ");
if (hasLocus() && locus() == value.length())
builder.append("Unexpected end of attribute. ");
auto message = messageForStatus(status());
builder.append(message.first);
appendValue(builder, *this, value);
builder.append(message.second);
return builder.toString();
}
/**Moves the entry in the line edit new2Add_edit to the
* listbox toAdd_List, expanding any run number lists
*/
void SANSAddFiles::add2Runs2Add() {
// split comma separated file names or run numbers into a list
ArrayProperty<std::string> commaSep(
"unusedName", m_SANSForm->new2Add_edit->text().toStdString());
const std::vector<std::string> nam = commaSep;
for (std::vector<std::string>::const_iterator i = nam.begin(); i != nam.end();
++i) { // each comma separated item could be a range of run numbers
// specified with a ':' or '-'
QStringList ranges;
std::vector<int> runNumRanges;
try { // if the entry is in the form 454:456, runNumRanges will be filled
// with the integers ({454, 455, 456}) otherwise it will throw
appendValue(*i, runNumRanges);
std::vector<int>::const_iterator num = runNumRanges.begin();
for (; num != runNumRanges.end(); ++num) {
ranges.append(QString::number(*num));
}
} catch (boost::bad_lexical_cast &) { // this means that we don't have a
// list of integers, treat it as full
// (and valid) filename
ranges.append(QString::fromStdString(*i));
}
for (QStringList::const_iterator k = ranges.begin(); k != ranges.end();
++k) {
// Don't display the full file path in the box, it's too long
QListWidgetItem *newL = insertListFront(QFileInfo(*k).fileName());
newL->setData(Qt::WhatsThisRole, QVariant(*k));
// Put the full path in the tooltip so people can see it if they want to
// do this with the file finding functionality of the FileProperty
FileProperty search("dummy", k->toStdString(), FileProperty::Load,
std::vector<std::string>(), Direction::Input);
if (search.isValid() == "") { // this means the file was found
newL->setToolTip(QString::fromStdString(search.value()));
// If we don't have an event workspace data set, then we disable the
// event options
if (!isEventWorkspace(QString::fromStdString(search.value()))) {
setBinningOptions(false);
}
}
}
}
m_SANSForm->new2Add_edit->clear();
}
bool getGappedParamsRecords(seqan::String<GappedParamsRecord> & records,
unsigned n,
char errorModel)
{
if (n < 15u || n > 75u)
return false; // We do not have parameter for these settings.
if (errorModel != 'L' && errorModel != 'H')
return false; // Invalid error model.
// We can iterate until readLength == 0 since the generator script creates
// a terminator record with this property and read length 0 does not make
// sense otherwise.
for (unsigned i = 0; RECORDS[i].readLength != 0; ++i)
if (RECORDS[i].readLength == n && RECORDS[i].type == errorModel)
appendValue(records, RECORDS[i]);
return true;
}
void ProjectSplicedRoi::_updateRanges(seqan::GffRecord const & record,
seqan::Segment<seqan::CharString, seqan::InfixSegment> const & name)
{
if (verbosity >= 3)
std::cerr << "Updating " << name << "\t" << record.beginPos << "\t" << record.endPos << "\n";
unsigned idx = 0;
if (getIdByName(groupNames, name, idx, groupNamesCache))
{
ranges[idx].i1 = std::min(ranges[idx].i1, (int)record.beginPos);
ranges[idx].i2 = std::max(ranges[idx].i2, (int)record.endPos);
}
else
{
idx = length(groupNames);
appendName(groupNames, name, groupNamesCache);
appendValue(ranges, TIntPair(record.beginPos, record.endPos));
}
}
bool OctreePacketData::appendValue(const QVector<glm::quat>& value) {
uint16_t qVecSize = value.size();
bool success = appendValue(qVecSize);
if (success) {
QByteArray dataByteArray(udt::MAX_PACKET_SIZE, 0);
unsigned char* start = reinterpret_cast<unsigned char*>(dataByteArray.data());
unsigned char* destinationBuffer = start;
for (int index = 0; index < value.size(); index++) {
destinationBuffer += packOrientationQuatToBytes(destinationBuffer, value[index]);
}
int quatsSize = destinationBuffer - start;
success = append(start, quatsSize);
if (success) {
_bytesOfValues += quatsSize;
_totalBytesOfValues += quatsSize;
}
}
return success;
}
/*****************************************************************************
Find an Value with the given attribute [column] and letter [class value]
in the list or create a new Value and append it to the list.
@param { ValueP, char, int, int } list, letter, attribute pointer to the first Value in the list, boolean for whether it is in the target class
@return { ValueP } found the matching Value
*****************************************************************************/
ValueP updateValue( ValueP list, char letter, int attribute, int isClass ){
ValueP current; /* pointer to the currect value */
current = list;
ValueP found; /* pointer to the result, found or created */
found = NULL;
/* search the list first */
while( current && !found ){
if( ( current->letter == letter ) && ( current->attribute == attribute ) ){
found = current;
}
current = current->next;
}
if( !found ){
found = newValue( letter, attribute );
list = appendValue( list, found );
}
found->count = found->count++;
found->classCount += isClass;
return( list );
} /* end findValue */
// inserts field into the dataLine at the current position
void CSVFile::insertValue (const char *field)
{
if (curPos == lineLength)
{
appendValue (field);
return;
}
int size = strlen (field);
if (size + lineLength >= LARGE)
return;
lineLength += size;
char temp[LARGE];
strcpy (temp, dataLine+curPos);
memcpy (dataLine+curPos, field, size);
curPos += size;
strcpy (dataLine+curPos, temp);
}
void SangerSequencingSimulator::_simulateQualities(
TQualities & quals, TCigarString const & cigar, unsigned sampleLength)
{
clear(quals);
unsigned pos = 0; // Position in result.
unsigned rPos = 0; // Position in fragment.
for (unsigned i = 0; i < length(cigar); ++i)
{
for (unsigned j = 0; j < cigar[i].count; ++j, ++pos)
{
double mean = 0.0, stdDev = 0.0;
double relPos = 1.0 * rPos / (1.0 * sampleLength);
rPos += (cigar[i].operation != 'D');
if (cigar[i].operation == 'D')
{
continue; // No quality to give out.
}
else if (cigar[i].operation == 'I' || cigar[i].operation == 'X')
{
mean = sangerOptions.qualityMatchStartMean + relPos * (sangerOptions.qualityMatchEndMean - sangerOptions.qualityMatchStartMean);
stdDev = sangerOptions.qualityMatchStartStdDev + relPos * (sangerOptions.qualityMatchEndStdDev - sangerOptions.qualityMatchStartStdDev);
}
else // cigar[i].operation == 'M'
{
mean = sangerOptions.qualityErrorStartMean + relPos * (sangerOptions.qualityErrorEndMean - sangerOptions.qualityErrorStartMean);
stdDev = sangerOptions.qualityErrorStartStdDev + relPos * (sangerOptions.qualityErrorEndStdDev - sangerOptions.qualityErrorStartStdDev);
}
std::normal_distribution<double> dist(mean, stdDev);
int q = static_cast<int>(dist(rng));
q = std::max(0, std::min(40, q));
appendValue(quals, (char)('!' + q));
}
}
}
void CXMLConfig::processTinyXMLOutput(TiXmlNode* node, String path, bool useAsDefault)
{
if ( !node ) return;
switch ( node->Type() )
{
case TiXmlNode::DOCUMENT:
rmTrailingSlash(path);
break;
case TiXmlNode::TEXT:
rmTrailingSlash(path);
appendValue(path, node->ToText()->Value(), useAsDefault);
break;
default:
break;
}
TiXmlNode* childNode;
for ( childNode = node->FirstChild(); childNode != 0; childNode = childNode->NextSibling() )
processTinyXMLOutput(childNode, path + String(node->Value()) + '/', useAsDefault);
}
int main()
{
seqan::StringSet<seqan::CharString> ids;
appendValue(ids, "id1");
appendValue(ids, "id2");
seqan::StringSet<seqan::Dna5String> seqs;
appendValue(seqs, "CGATCGATCGAT");
appendValue(seqs, "AAAAAAAAAAAA");
seqan::StringSet<seqan::CharString> quals;
appendValue(quals, "IIIIIIIIIHII");
appendValue(quals, "IIIIIIIIIHII");
for (unsigned i = 0; i < length(ids); ++i)
if (seqan::writeRecord(std::cout, ids[i], seqs[i], quals[i], seqan::Fastq()) != 0)
return 1; // Error writing.
return 0;
}
//initialize List of contingency tables (one for every kmer)
void initializeCont (seqan::StringSet<seqan::DnaString> kmers, Contingency & allContigs){
// //Contingeny table for finding of one single kmer to store intermediate results
// Contingency oneContig;
unsigned l;
l=length(kmers);
//mock vector for mRNA IDs
std::vector<int> mock;
mock.push_back(-1);
//reserve space
allContigs.kmerDN.reserve(l);
allContigs.kmerNoDN.reserve(l);
allContigs.noKmerDN.reserve(l);
allContigs.noKmerNoDN.reserve(l);
allContigs.idNoDN.reserve(l);
allContigs.idDN.reserve(l);
//Initialize list of Contingency table for all the kmers
for (unsigned i=0; i<l; i++){
appendValue(allContigs.kmerSeq, "");
allContigs.kmerDN.push_back(0);
allContigs.kmerNoDN.push_back(0);
allContigs.noKmerDN.push_back(0);
allContigs.noKmerNoDN.push_back(0);
//initialize ID Lists for the mRNAs, in which the kmer was found with -1, since there is no mRNA with rank -1
allContigs.idNoDN.push_back(mock);
allContigs.idDN.push_back(mock);
}
//assign the kmer to the position in the Contingencies Table
for (unsigned j=0; j<l; j++){
if (length(getValue(allContigs.kmerSeq, kmerToID(getValue(kmers, j))))>0){
std::cerr << "kmer already set" << '\n';
std::cerr << getValue(allContigs.kmerSeq, kmerToID(getValue(kmers, j)))<< '\n';
return;
}
else {assignValue(allContigs.kmerSeq, kmerToID(getValue(kmers, j)), getValue(kmers, j));}
}
}
int main()
{
seqan::GffStream out("-", seqan::GffStream::WRITE);
// Add sequence names.
addSequenceName(out, "ctg123");
// Write out the records.
seqan::GffRecord record;
record.rID = 0;
record.source = "";
record.type = "gene";
record.beginPos = 999;
record.endPos = 9000;
record.strand = '+';
record.score = seqan::GffRecord::INVALID_SCORE();
appendValue(record.tagName, "ID");
appendValue(record.tagValue, "gene0001");
appendValue(record.tagName, "Name");
appendValue(record.tagValue, "EDEN");
if (writeRecord(out, record) != 0)
std::cerr << "ERROR: Problem writing output file.";
clear(record.tagName);
clear(record.tagValue);
record.rID = 0;
record.source = "";
record.type = "TF_binding_site";
record.beginPos = 999;
record.endPos = 1012;
record.strand = '+';
record.score = seqan::GffRecord::INVALID_SCORE();
appendValue(record.tagName, "Parent");
appendValue(record.tagValue, "gene0001");
if (writeRecord(out, record) != 0)
std::cerr << "ERROR: Problem writing output file.";
return 0;
}
void CBWinProject::addLibrary(string libraryName, LibType libType) {
ofLogNotice() << "adding library " << libraryName;
appendValue(doc, "Add", "library", libraryName, true);
// overwriteMultiple for a lib if it's there (so libsorder.make will work)
// this is because we might need to say libosc, then ws2_32
}
void CBWinProject::addInclude(string includeName) {
ofLogNotice() << "adding include " << includeName;
appendValue(doc, "Add", "directory", includeName);
}
void CBWinProject::addSrc(string srcName, string folder, SrcType type) {
pugi::xml_node node = appendValue(doc, "Unit", "filename", srcName);
if(!node.empty()) {
node.child("Option").attribute("virtualFolder").set_value(folder.c_str());
}
}
void OptionsAssigner::appendValue(const std::string &value)
{
appendValue(Variant(value));
}
void CBWinProject::addLibrary(const LibraryBinary & lib){
appendValue(doc, "Add", "library", lib.path, true);
// overwriteMultiple for a lib if it's there (so libsorder.make will work)
// this is because we might need to say libosc, then ws2_32
}
void IntersectBed::writeRois(seqan::String<bool> const & bitmap,
seqan::String<int> const & counts,
int beginPos, // position of bitmap[0] and counts[0]
seqan::BedRecord<seqan::Bed6> const & bedRecord)
{
// We will build a string of ranges in bitmap/counts for writing out. The bitmap is used depending on the
// combination mode.
typedef seqan::Pair<int, int> TIntPair;
seqan::String<TIntPair> pairs;
// We also generate the names of the new regions.
seqan::StringSet<seqan::CharString> names;
switch (options.mode)
{
case IntersectBedOptions::PROJECTION:
// Use BED range only.
appendValue(pairs, TIntPair(bedRecord.beginPos - beginPos, bedRecord.endPos - beginPos));
break;
case IntersectBedOptions::INTERSECTION:
// Search for 0/1 and 1/0 flanks.
{
bool state = bitmap[0];
int lastFlank = 0;
for (unsigned i = 1; i < length(bitmap); ++i)
{
if (state)
{
if (!bitmap[i]) // Found a 1/0 flank.
{
appendValue(pairs, TIntPair(lastFlank, i));
state = false;
lastFlank = i;
}
}
else
{
if (bitmap[i]) // Found a 0/1 flank.
{
state = true;
lastFlank = i;
}
}
}
if (state)
appendValue(pairs, TIntPair(lastFlank, length(bitmap)));
}
break;
case IntersectBedOptions::UNION:
// Use whole range, including overlaps to the left of right.
appendValue(pairs, TIntPair(0, length(counts)));
break;
case IntersectBedOptions::DIFF:
SEQAN_FAIL("Difference does not implemented yet!");
break;
default:
SEQAN_FAIL("Cannot reach here!");
}
if (options.verbosity >= 2)
std::cerr << "Adding " << length(pairs) << " for BED " << bedRecord.name << "\n";
for (unsigned i = 0; i < length(pairs); ++i)
{
std::stringstream ss;
ss << bedRecord.name << "_" << i;
appendValue(names, ss.str());
}
seqan::RoiRecord record;
for (unsigned i = 0; i < length(pairs); ++i)
{
clear(record);
record.ref = bedRecord.ref;
record.beginPos = beginPos + pairs[i].i1;
record.endPos = beginPos + pairs[i].i2;
record.len = record.endPos - record.beginPos;
record.name = names[i];
record.strand = bedRecord.strand;
record.countMax = 0;
resize(record.count, pairs[i].i2 - pairs[i].i1, 0);
for (int k = 0, j = pairs[i].i1; j != pairs[i].i2; ++j, ++k)
{
record.countMax = std::max(record.countMax, (unsigned)counts[j]);
record.count[k] = counts[j];
}
writeRecord(roiFileOut, record);
}
}
int main(int argc, char const ** argv)
{
double startTime = 0;
// Parse command line.
FxFaidxOptions options;
seqan::ArgumentParser::ParseResult res = parseArgs(options, argc, argv);
if (res != seqan::ArgumentParser::PARSE_OK)
return res == seqan::ArgumentParser::PARSE_ERROR; // 1 on errors, 0 otherwise
// ---------------------------------------------------------------------------
// Index I/O
// ---------------------------------------------------------------------------
// Load index, create if necessary.
startTime = sysTime();
seqan::FaiIndex faiIndex;
if (load(faiIndex, toCString(options.inFastaPath), toCString(options.inFaiPath)) != 0)
{
if (options.verbosity >= 2)
std::cerr << "Building Index " << options.inFaiPath << " ...";
if (buildIndex(toCString(options.inFastaPath), toCString(options.inFaiPath), seqan::Fai()) != 0)
{
std::cerr << "Could not build FAI index at " << options.inFaiPath
<< " for FASTA file " << options.inFastaPath << "\n";
return 1;
}
if (load(faiIndex, toCString(options.inFastaPath), toCString(options.inFaiPath)) != 0)
{
std::cerr << "Could not load FAI index we just build.\n";
return 1;
}
}
if (options.verbosity >= 3)
std::cerr << "Took " << (startTime - sysTime()) << " s\n";
// ---------------------------------------------------------------------------
// Parse and Fetch Regions.
// ---------------------------------------------------------------------------
if (empty(options.regions))
return 0;
// Parse out regions.
seqan::String<Region> regions;
for (unsigned i = 0; i < length(options.regions); ++i)
{
Region region;
if (!parseRegion(region, options.regions[i]))
{
std::cerr << "Could not parse region " << options.regions[i] << "\n";
return 1;
}
unsigned seqId;
if (!getIdByName(faiIndex, region.seqName, seqId))
{
std::cerr << "Unknown sequence for region " << options.regions[i] << "\n";
return 1;
}
region.seqId = seqId;
if (region.seqId < 0 || (unsigned)region.seqId >= length(faiIndex.indexEntryStore))
{
std::cerr << "Invalid region " << options.regions[i] << "\n";
return 1;
}
appendValue(regions, region);
}
// Open output file.
std::ostream * outPtr = &std::cout;
std::ofstream outF;
if (!empty(options.outFastaPath))
{
outF.open(toCString(options.outFastaPath), std::ios::binary | std::ios::out);
if (!outF.good())
{
std::cerr << "Could not open output file " << options.outFastaPath << "\n";
return 1;
}
}
// Retrieve output infixes and write to result.
for (unsigned i = 0; i < length(regions); ++i)
{
Region const & region = regions[i];
seqan::CharString id = options.regions[i];
seqan::CharString seq;
unsigned beginPos = 0;
if (region.beginPos > 0)
beginPos = region.beginPos;
unsigned endPos = sequenceLength(faiIndex, (unsigned)region.seqId);
if (region.endPos > 0 && (unsigned)region.endPos < endPos)
endPos = region.endPos;
if (beginPos > endPos)
endPos = beginPos;
getSequenceInfix(seq, faiIndex, region.seqId, beginPos, endPos);
if (writeRecord(*outPtr, id, seq, seqan::Fasta()) != 0)
{
std::cerr << "Could not write infix for region " << options.regions[i] << " to output.\n";
return 1;
}
}
return 0;
}
seqan::ArgumentParser::ParseResult
parseArgs(SakOptions & options,
int argc,
char ** argv)
{
seqan::ArgumentParser parser("sak");
setShortDescription(parser, "Slicing and dicing of FASTA/FASTQ files..");
setVersion(parser, SEQAN_APP_VERSION " [" SEQAN_REVISION "]");
setDate(parser, SEQAN_DATE);
setCategory(parser, "Utilities");
addUsageLine(parser, "[\\fIOPTIONS\\fP] [\\fB-o\\fP \\fIOUT.{fa,fq}\\fP] \\fIIN.{fa,fq}\\fP");
addDescription(parser, "\"It slices, it dices and it makes the laundry!\"");
addDescription(parser, "Original SAK tool by David Weese. Rewrite by Manuel Holtgrewe.");
// The only argument is the input file.
addArgument(parser, seqan::ArgParseArgument(seqan::ArgParseArgument::INPUT_FILE, "IN"));
// Only FASTA and FASTQ files are allowed as input.
setValidValues(parser, 0, seqan::SeqFileIn::getFileExtensions());
// TODO(holtgrew): I want a custom help text!
// addOption(parser, seqan::ArgParseOption("h", "help", "This helpful screen."));
addOption(parser, seqan::ArgParseOption("v", "verbose", "Verbose, log to STDERR."));
hideOption(parser, "verbose");
addOption(parser, seqan::ArgParseOption("vv", "very-verbose", "Very verbose, log to STDERR."));
hideOption(parser, "very-verbose");
addSection(parser, "Output Options");
addOption(parser, seqan::ArgParseOption("o", "out-path",
"Path to the resulting file. If omitted, result is printed to stdout in FastQ format.",
seqan::ArgParseOption::OUTPUT_FILE, "FASTX"));
setValidValues(parser, "out-path", seqan::SeqFileOut::getFileExtensions());
addOption(parser, seqan::ArgParseOption("rc", "revcomp", "Reverse-complement output."));
addOption(parser, seqan::ArgParseOption("l", "max-length", "Maximal number of sequence characters to write out.",
seqan::ArgParseOption::INTEGER, "LEN"));
addSection(parser, "Filter Options");
addOption(parser, seqan::ArgParseOption("s", "sequence", "Select the given sequence for extraction by 0-based index.",
seqan::ArgParseOption::INTEGER, "NUM", true));
addOption(parser, seqan::ArgParseOption("sn", "sequence-name", "Select sequence with name prefix being \\fINAME\\fP.",
seqan::ArgParseOption::STRING, "NAME", true));
addOption(parser, seqan::ArgParseOption("ss", "sequences",
"Select sequences \\fIfrom\\fP-\\fIto\\fP where \\fIfrom\\fP and \\fIto\\fP "
"are 0-based indices.",
seqan::ArgParseArgument::STRING, "RANGE", true));
addOption(parser, seqan::ArgParseOption("i", "infix",
"Select characters \\fIfrom\\fP-\\fIto\\fP where \\fIfrom\\fP and \\fIto\\fP "
"are 0-based indices.",
seqan::ArgParseArgument::STRING, "RANGE", true));
addOption(parser, seqan::ArgParseOption("ll", "line-length",
"Set line length in output file. See section \\fILine Length\\fP for details.",
seqan::ArgParseArgument::INTEGER, "LEN", false));
setMinValue(parser, "line-length", "-1");
addTextSection(parser, "Line Length");
addText(parser,
"You can use the setting \\fB--line-length\\fP for setting the resulting line length. By default, "
"sequences in FASTA files are written with at most 70 characters per line and sequences in FASTQ files are "
"written without any line breaks. The quality sequence in FASTQ file is written in the same way as the "
"residue sequence.");
addText(parser,
"The default is selected with a \\fB--line-length\\fP value of \\fI-1\\fP and line breaks can be disabled "
"with a value of \\fI0\\fP.");
addTextSection(parser, "Usage Examples");
addListItem(parser, "\\fBsak\\fP \\fB-s\\fP \\fI10\\fP \\fIIN.fa\\fP",
"Cut out 11th sequence from \\fIIN.fa\\fP and write to stdout as FASTA.");
addListItem(parser, "\\fBsak\\fP \\fB-ss\\fP \\fI10-12\\fP \\fB-ss\\fP \\fI100-200\\fP \\fIIN.fq\\fP",
"Cut out 11th up to and including 12th and 101th up to and including 199th sequence from \\fIIN.fq\\fP "
"and write to stdout as FASTA.");
seqan::ArgumentParser::ParseResult res = parse(parser, argc, argv);
if (res != seqan::ArgumentParser::PARSE_OK)
return res;
getArgumentValue(options.inFastxPath, parser, 0);
seqan::CharString tmp;
getOptionValue(tmp, parser, "out-path");
if (isSet(parser, "out-path"))
getOptionValue(options.outPath, parser, "out-path");
if (isSet(parser, "verbose"))
options.verbosity = 2;
if (isSet(parser, "very-verbose"))
options.verbosity = 3;
if (isSet(parser, "sequence"))
{
std::vector<std::string> sequenceIds = getOptionValues(parser, "sequence");
for (unsigned i = 0; i < seqan::length(sequenceIds); ++i)
{
unsigned idx = 0;
if (!seqan::lexicalCast(idx, sequenceIds[i]))
{
std::cerr << "ERROR: Invalid sequence index " << sequenceIds[i] << "\n";
return seqan::ArgumentParser::PARSE_ERROR;
}
appendValue(options.seqIndices, idx);
}
}
if (isSet(parser, "sequences"))
{
std::vector<std::string> sequenceRanges = getOptionValues(parser, "sequences");
seqan::CharString buffer;
for (unsigned i = 0; i < seqan::length(sequenceRanges); ++i)
{
seqan::Pair<uint64_t> range;
if (!parseRange(range.i1, range.i2, sequenceRanges[i]))
{
std::cerr << "ERROR: Invalid range " << sequenceRanges[i] << "\n";
return seqan::ArgumentParser::PARSE_ERROR;
}
appendValue(options.seqIndexRanges, range);
}
}
if (isSet(parser, "infix"))
{
seqan::CharString buffer;
getOptionValue(buffer, parser, "infix");
if (!parseRange(options.seqInfixBegin, options.seqInfixEnd, buffer))
{
std::cerr << "ERROR: Invalid range " << buffer << "\n";
return seqan::ArgumentParser::PARSE_ERROR;
}
}
options.reverseComplement = isSet(parser, "revcomp");
if (isSet(parser, "max-length"))
getOptionValue(options.maxLength, parser, "max-length");
if (isSet(parser, "sequence-name"))
getOptionValue(options.readPattern, parser, "sequence-name");
getOptionValue(options.seqOutOptions.lineLength, parser, "line-length");
return res;
}
