CRef<CSeq_entry>
CShortReadFastaInputSource::x_ReadFastaOneSeq(CRef<ILineReader> line_reader)
{
int start = 0;
// parse the last read defline
CTempString line = **line_reader;
CTempString id = x_ParseDefline(line);
CRef<CSeq_id> seqid(new CSeq_id);
seqid->Set(CSeq_id::e_Local, id);
++(*line_reader);
line = **line_reader;
while (line[0] != '>') {
// ignore empty lines
if (line.empty() && !line_reader->AtEOF()) {
++(*line_reader);
line = **line_reader;
continue;
}
// copy the sequence
// increase the sequence buffer if necessary
if (start + line.length() + 1 > m_SeqBuffLen) {
string tmp;
m_SeqBuffLen = 2 * (start + line.length() + 1);
tmp.reserve(m_SeqBuffLen);
memcpy(&tmp[0], &m_Sequence[0], start);
m_Sequence.swap(tmp);
}
memcpy(&m_Sequence[start], line.data(), line.length());
start += line.length();
if (line_reader->AtEOF()) {
break;
}
// read next line
++(*line_reader);
line = **line_reader;
}
// set up sequence
if (start > 0) {
CRef<CSeq_entry> seq_entry(new CSeq_entry);
CBioseq& bioseq = seq_entry->SetSeq();
bioseq.SetInst().SetMol(CSeq_inst::eMol_na);
bioseq.SetInst().SetRepr(CSeq_inst::eRepr_raw);
bioseq.SetId().clear();
bioseq.SetId().push_back(seqid);
bioseq.SetInst().SetLength(start);
m_Sequence[start] = 0;
bioseq.SetInst().SetSeq_data().SetIupacna(CIUPACna(&m_Sequence[0]));
bioseq.SetDescr();
m_BasesAdded += start;
return seq_entry;
}
return CRef<CSeq_entry>();
}
static bool IsInteger(const CTempString& value)
{
if (value.empty())
return false;
const char* digit = value.end();
while (--digit > value.begin())
if (!isdigit(*digit))
return false;
return isdigit(*digit) || (*digit == '-' && value.length() > 1);
}
bool g_FixMisplacedPID(CJsonNode& stat_info, CTempString& executable_path,
const char* pid_key)
{
SIZE_TYPE misplaced_pid = NStr::Find(executable_path, "; PID: ");
if (misplaced_pid == NPOS)
return false;
SIZE_TYPE pos = misplaced_pid + sizeof("; PID: ") - 1;
stat_info.SetInteger(pid_key, NStr::StringToInt8(
CTempString(executable_path.data() + pos,
executable_path.length() - pos)));
executable_path.erase(misplaced_pid);
return true;
}
// ----------------------------------------------------------------------------
void CUCSCRegionReader::xSmartFieldSplit(vector<string>& fields, CTempString line)
{
NStr::Split(line, " \t.-:", fields, NStr::fSplit_Tokenize);
if (line[line.length()-1] == '-')
fields.push_back("-");
while (fields.size() > 3)
{
if (fields.size() == 4 && (fields.back() == "+" || fields.back() == "-"))
break;
// try to merge first column
size_t len = fields[0].length();
if (line[len] == '.')
{
fields[0] += line[len];
fields[0] += fields[1];
fields.erase(fields.begin()+1);
} else {
break;
}
}
}
BEGIN_NCBI_SCOPE
static void NormalizeStatKeyName(CTempString& key)
{
char* begin = const_cast<char*>(key.data());
char* end = begin + key.length();
while (begin < end && !isalnum(*begin))
++begin;
while (begin < end && !isalnum(end[-1]))
--end;
if (begin == end) {
key = "_";
return;
}
key.assign(begin, end - begin);
for (; begin < end; ++begin)
*begin = isalnum(*begin) ? tolower(*begin) : '_';
}
inline
CLightString::CLightString(const CTempString& str)
: m_String(str.data()), m_Length(str.length())
{
}
CRef<CSeq_entry>
CShortReadFastaInputSource::x_ReadFastqOneSeq(CRef<ILineReader> line_reader)
{
CTempString line;
CTempString id;
CRef<CSeq_entry> retval;
// first read defline
++(*line_reader);
line = **line_reader;
// skip empty lines
while (!line_reader->AtEOF() && line.empty()) {
++(*line_reader);
line = **line_reader;
}
if (line[0] != '@') {
NCBI_THROW(CInputException, eInvalidInput, (string)"FASTQ parse error:"
" defline expected at line: " +
NStr::IntToString(line_reader->GetLineNumber()));
}
id = x_ParseDefline(line);
CRef<CSeq_id> seqid(new CSeq_id);
seqid->Set(CSeq_id::e_Local, id);
// read sequence
++(*line_reader);
line = **line_reader;
// skip empty lines
while (!line_reader->AtEOF() && line.empty()) {
++(*line_reader);
line = **line_reader;
}
// set up sequence
if (line.length() > 0) {
CRef<CSeq_entry> seq_entry(new CSeq_entry);
CBioseq& bioseq = seq_entry->SetSeq();
bioseq.SetInst().SetMol(CSeq_inst::eMol_na);
bioseq.SetInst().SetRepr(CSeq_inst::eRepr_raw);
bioseq.SetId().clear();
bioseq.SetId().push_back(seqid);
bioseq.SetInst().SetLength(line.length());
bioseq.SetInst().SetSeq_data().SetIupacna(CIUPACna(line.data()));
bioseq.SetDescr();
m_BasesAdded += line.length();
retval = seq_entry;
}
// read and skip second defline
++(*line_reader);
line = **line_reader;
// skip empty lines
while (!line_reader->AtEOF() && line.empty()) {
++(*line_reader);
line = **line_reader;
}
if (line[0] != '+') {
NCBI_THROW(CInputException, eInvalidInput, (string)"FASTQ parse error:"
" defline expected at line: " +
NStr::IntToString(line_reader->GetLineNumber()));
}
// read and skip quality scores
++(*line_reader);
line = **line_reader;
// skip empty lines
while (!line_reader->AtEOF() && line.empty()) {
++(*line_reader);
line = **line_reader;
}
return retval;
}