void GffRecord::printNull(QuickString &outBuf) const
{
outBuf.append(".\t.\t.\t-1\t-1\t.\t.\t.", 17);
if (_numFields > 8) {
outBuf.append("\t.", 2);
}
}
bool BufferedStreamMgr::getLine(QuickString &line)
{
line.clear();
if (_mainBufCurrStartPos >= _mainBufCurrLen) {
if (!readFileChunk()) {
_eof = true;
return false;
}
}
while (1) {
int searchPos = _mainBufCurrStartPos;
while (searchPos < _mainBufCurrLen && _mainBuf[searchPos] != '\n') {
searchPos++;
}
line.append((char *)_mainBuf + _mainBufCurrStartPos, searchPos - _mainBufCurrStartPos);
_mainBufCurrStartPos = searchPos +1;
if (searchPos == _mainBufCurrLen) { //hit end of buffer, but no newline yet
if (!readFileChunk()) { //hit eof
return true;
}
} else if (_mainBuf[searchPos] == '\n') {
return true;
}
}
}
OneStringBase& QuickString<quickSize>::substr(int pos, int sublen)
{
// Check sublen flag. If -1, then go to the end of the QuickString
if(sublen == -1)
{
// Calculate the size from the position to the end of the QuickString
sublen = size() - pos;
}
// Check for valid index
if((pos >= quickSize) || (pos < 0))
{
ioc << cat_error << ta_bold << fg_red << "QuickString Error:" <<
" Index Out of Bounds" << io_end;
return *this;
}
// If the substring size is too large throw an error
else if(sublen + pos > size())
{
ioc << cat_error << ta_bold << fg_red << "QuickString Error: " <<
"Size exceeds limits of QuickString"<<io_end;
return *this;
}
else
{
// Create a new OneString and append each character that is found
// in the substring
QuickString<quickSize>* newPaw = new QuickString();
for(int i = 0; i < sublen; i++)
{
newPaw->append(master[pos]);
pos++;
}
return *newPaw;
}
}
void VcfRecord::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const {
outBuf.append(_chrName);
outBuf.append('\t');
outBuf.append(_startPosStr);
printOtherFields(outBuf);
}
void Bed3Interval::print(QuickString &outBuf) const
{
outBuf.append(_chrName);
outBuf.append('\t');
outBuf.append(_startPos);
outBuf.append('\t');
outBuf.append(_endPos);
}
void Bed3Interval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const
{
outBuf.append(_chrName);
outBuf.append('\t');
outBuf.append(start);
outBuf.append('\t');
outBuf.append(end);
}
void BedPlusInterval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const
{
Bed6Interval::print(outBuf, start, end);
for (int i=0; i < (int)_otherIdxs.size(); i++) {
outBuf.append('\t');
outBuf.append(*(_otherIdxs[i]));
}
}
void ContextBase::setErrorMsg(QuickString &msg, bool onlyWarn, const Record * record, QuickString str1, const QuickString str2, const QuickString str3) {
if (onlyWarn) {
msg = "\n***** WARNING: ";
} else {
msg = "\n***** ERROR: ";
}
msg.append(str1);
msg.append(str2);
msg.append(str3);
msg.append(" Exiting...\n");
if (record != NULL) {
record->print(msg);
}
}
void VcfRecord::printOtherFields(QuickString &outBuf) const {
outBuf.append('\t');
outBuf.append(_name);
outBuf.append('\t');
outBuf.append(_varAlt);
outBuf.append('\t');
outBuf.append(_varRef);
outBuf.append('\t');
outBuf.append(_score);
for (int i= 0; i < (int)_otherIdxs.size(); i++) {
outBuf.append('\t');
outBuf.append(*(_otherIdxs[i]));
}
}
void GffRecord::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const
{
outBuf.append(_chrName);
outBuf.append('\t');
outBuf.append(_source);
outBuf.append('\t');
outBuf.append(_name);
outBuf.append('\t');
outBuf.append(start);
outBuf.append('\t');
outBuf.append(end);
outBuf.append('\t');
printRemainingFields(outBuf);
}
void GffRecord::print(QuickString &outBuf) const
{
outBuf.append(_chrName);
outBuf.append('\t');
outBuf.append(_source);
outBuf.append('\t');
outBuf.append(_name);
outBuf.append('\t');
outBuf.append(_startPosStr);
outBuf.append('\t');
outBuf.append(_endPosStr);
outBuf.append('\t');
printRemainingFields(outBuf);
}
void VcfRecord::printOtherFields(QuickString &outBuf) const {
outBuf.append('\t');
outBuf.append(_name);
outBuf.append('\t');
outBuf.append(_varRef);
outBuf.append('\t');
outBuf.append(_varAlt);
outBuf.append('\t');
outBuf.append(_score);
outBuf.append('\t');
_plusFields.printFields(outBuf);
}
void BedPlusInterval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const
{
Bed3Interval::print(outBuf, start, end);
outBuf.append('\t');
printBed6PlusFields(outBuf);
_plusFields.printFields(outBuf);
}
void ComplementFile::printRecord(int endPos)
{
_outRecord.setStartPos(_currStartPos);
QuickString startStr;
startStr.append(_currStartPos);
_outRecord.setStartPosStr(startStr);
_outRecord.setEndPos(endPos);
QuickString endStr;
endStr.append(endPos);
_outRecord.setEndPosStr(endStr);
_outputMgr->printRecord(&_outRecord);
_outputMgr->newline();
}
bool BufferedStreamMgr::getTypeData()
{
QuickString currScanBuffer;
_inputStreamMgr->getSavedData(currScanBuffer);
do {
if (!_typeChecker.scanBuffer(currScanBuffer.c_str(), currScanBuffer.size()) && !_typeChecker.needsMoreData()) {
return false;
} else if (_typeChecker.needsMoreData()) {
_inputStreamMgr->populateScanBuffer();
currScanBuffer.clear();
_inputStreamMgr->getSavedData(currScanBuffer);
}
} while (_typeChecker.needsMoreData());
_inputStreamMgr->reset();
return true;
}
void BedPlusInterval::printNull(QuickString &outBuf) const
{
Bed6Interval::printNull(outBuf);
for (int i=startOtherIdx; i < _numPrintFields; i++) {
outBuf.append("\t.");
}
}
void GffPlusRecord::printNull(QuickString &outBuf) const
{
GffRecord::printNull(outBuf);
for (int i=_numFields; i < _numPrintFields; i++) {
outBuf.append("\t.");
}
}
void GroupBy::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits)
{
const Record *rec = hits.getKey();
const QuickString &opVal = _context->getColumnOpsVal(hits);
if (upCast(_context)->printFullCols()) {
outputMgr->printRecord(rec, opVal);
} else {
QuickString outBuf;
for (int i=0; i < (int)_groupCols.size(); i++) {
outBuf.append(rec->getField(_groupCols[i]));
outBuf.append('\t');
}
outBuf.append(opVal);
outputMgr->printRecord(NULL, outBuf);
}
}
void BedPlusInterval::printNull(QuickString &outBuf) const
{
Bed3Interval::printNull(outBuf);
printBed6PlusNullFields(outBuf);
for (int i=_numFixedFields; i < _numPrintFields; i++) {
outBuf.append("\t.");
}
}
//This functions recognizes only numbers with digits, plus sign, minus sign, decimal point, e, or E. Hexadecimal and pointers not currently supported.
bool isNumeric(const QuickString &str) {
for (int i=0; i < (int)str.size(); i++) {
char currChar = str[i];
if (!(isdigit(currChar) || currChar == '-' || currChar == '.' || currChar == '+' || currChar == 'e' || currChar == 'E')) {
return false;
}
}
return true;
}
void NewGenomeFile::loadGenomeFileIntoMap() {
ifstream genFile(_genomeFileName.c_str());
if (!genFile.good()) {
cerr << "Error: Can't open genome file" << _genomeFileName << "Exiting..." << endl;
exit(1);
}
string sLine;
Tokenizer fieldTokens;
CHRPOS chrSize = 0;
QuickString chrName;
while (!genFile.eof()) {
sLine.clear();
chrSize = 0;
chrName.clear();
getline(genFile, sLine);
int numFields = fieldTokens.tokenize(sLine.c_str());
if (numFields != 2) {
continue;
}
chrName = fieldTokens.getElem(0);
chrSize = str2chrPos(fieldTokens.getElem(1));
_maxId++;
_chromSizeIds[chrName] = pair<CHRPOS, int>(chrSize, _maxId);
_startOffsets.push_back(_genomeLength);
_genomeLength += chrSize;
_chromList.push_back(chrName);
}
if (_maxId == -1) {
cerr << "Error: The genome file " << _genomeFileName << " has no valid entries. Exiting." << endl;
exit(1);
}
// Special: BAM files can have unmapped reads, which show as no chromosome, or an empty chrom string.
// Add in an empty chrom so these don't error.
_maxId++;
_chromSizeIds[""] = pair<CHRPOS, int>(0, _maxId);
_chromList.push_back("");
_startOffsets.push_back(_genomeLength); //insert the final length as the last element
//to help with the lower_bound call in the projectOnGenome method.
genFile.close();
}
void QuickString::substr (QuickString &newStr, size_t pos, size_t len) const
{
if (pos >= _currSize) {
return;
}
if (pos + len >= _currSize) {
len = _currSize - pos;
}
newStr.set(_buffer + pos, len);
}
Record *BlockMgr::allocateAndAssignRecord(const Record *keyRecord, int startPos, int endPos)
{
Record *record = _blockRecordsMgr->allocateRecord();
record->setChrName(keyRecord->getChrName());
record->setChromId(keyRecord->getChromId());
record->setStartPos(startPos);
record->setEndPos(endPos);
QuickString startPosStr;
QuickString endPosStr;
startPosStr.append(startPos);
endPosStr.append(endPos);
record->setStartPosStr(startPosStr);
record->setEndPosStr(endPosStr);
record->setName(keyRecord->getName());
record->setScore(keyRecord->getScore());
record->setStrand(keyRecord->getStrand());
return record;
}
bool QuickString::stricmp(const QuickString &str) const {
if (str.size() != _currSize) {
return true;
}
for (size_t i=0; i < _currSize; i++) {
if (tolower(str[i]) != tolower(_buffer[i])) {
return true;
}
}
return false;
}
void RecordOutputMgr::printRecord(const Record *record, const QuickString & value)
{
_afterVal = value;
printRecord(record);
if (!value.empty()) {
tab();
_outBuf.append(value);
}
newline();
if (needsFlush()) flush();
}
bool isHeaderLine(const QuickString &line) {
if (line[0] == '>') {
return true;
}
if (line[0] == '!') {
return true;
}
if (line[0] == '#') {
return true;
}
//GFF file headers can also start with the words "browser" or "track", followed by a whitespace character.
if (memcmp(line.c_str(), "browser", 7) == 0 && isspace(line[7])) {
return true;
}
if (memcmp(line.c_str(), "track", 5) == 0 && isspace(line[5])) {
return true;
}
if (memcmp(line.c_str(), "visibility", 10) == 0) {
return true;
}
return false;
}
void BamRecord::printUnmapped(QuickString &outBuf) const {
outBuf.append(_chrName.empty() ? "." : _chrName);
outBuf.append("\t-1\t-1\t");
outBuf.append(_name.empty() ? "." : _name);
outBuf.append('\t');
outBuf.append(_score.empty() ? "." : _score);
outBuf.append("\t.\t-1\t-1\t-1\t0,0,0\t0\t.\t."); // dot for strand, -1 for blockStarts and blockEnd
}
void GffRecord::printRemainingFields(QuickString &outBuf) const
{
outBuf.append(_score);
outBuf.append('\t');
outBuf.append(_strand);
outBuf.append('\t');
outBuf.append(_frame);
if (_numFields == 9) {
outBuf.append('\t');
outBuf.append(_group);
}
}
bool BufferedStreamMgr::getLine(QuickString &line)
{
line.clear();
if (_mainBufCurrStartPos >= _mainBufCurrLen) {
if (!readFileChunk()) {
_eof = true;
return false;
}
}
bool retVal = true;
while (1) {
int searchPos = _mainBufCurrStartPos;
while (searchPos < _mainBufCurrLen && _mainBuf[searchPos] != '\n') {
searchPos++;
}
line.append((char *)_mainBuf + _mainBufCurrStartPos, searchPos - _mainBufCurrStartPos);
_mainBufCurrStartPos = searchPos +1;
if (searchPos == _mainBufCurrLen) { //hit end of buffer, but no newline yet
if (!readFileChunk()) { //hit eof
retVal = true;
break;
}
} else if (_mainBuf[searchPos] == '\n') {
retVal = true;
break;
}
}
//strip any whitespace characters, such as DOS newline characters or extra tabs,
//from the end of the line
int lastPos = line.size();
while (isspace(line[lastPos-1])) lastPos--;
line.resize(lastPos);
return retVal;
}
bool ComplementFile::fastForward(const QuickString &newChrom) {
if (!newChrom.empty() && !_genomeFile->hasChrom(newChrom)) return false;
int i= _currPosInGenomeList +1;
while (i < (int)_chromList.size() && _chromList[i] != newChrom) {
_outRecord.setChrName(_chromList[i]);
_currStartPos = 0;
int endPos = _genomeFile->getChromSize(_chromList[i]);
printRecord(endPos);
i++;
}
if (newChrom.empty()) return true;
if (i== (int)_chromList.size()) {
//reached end but didn't find new chrom. Genome and DB are not sorted in same order.
cerr << "***** ERROR: genome file and input file are not sorted in same order. Exiting..." << endl;
exit(1);
//this is where we'd return false if we weren't exiting.
}
_currChrom = newChrom;
_currPosInGenomeList = i;
return true;
}