//------------------------------------------------------------------------------
void CheckDuplicates( const vector< string > & input,
const string & infmt,
const CWinMaskUtil::CIdSet * ids,
const CWinMaskUtil::CIdSet * exclude_ids )
{
typedef vector< string >::const_iterator input_iterator;
dup_lookup_table table;
CRef<CObjectManager> om(CObjectManager::GetInstance());
for( input_iterator i( input.begin() ); i != input.end(); ++i )
{
Uint4 seqnum( 0 );
for(CWinMaskUtil::CInputBioseq_CI bs_iter(*i, infmt); bs_iter; ++bs_iter)
{
CBioseq_Handle bsh = *bs_iter;
if( CWinMaskUtil::consider( bsh, ids, exclude_ids ) )
{
TSeqPos data_len = bsh.GetBioseqLength();
if( data_len < MIN_SEQ_LENGTH )
continue;
string id;
sequence::GetId(bsh, sequence::eGetId_Best)
.GetSeqId()->GetLabel(&id);
data_len -= SAMPLE_SKIP;
tracker track( table, id );
string index;
CSeqVector data =
bsh.GetSeqVector(CBioseq_Handle::eCoding_Iupac);
for( TSeqPos i = 0; i < data_len; ++i )
{
index.erase();
data.GetSeqData(i, i + SAMPLE_LENGTH, index);
const dup_lookup_table::sample * sample( table[index] );
if( sample != 0 )
track( index, seqnum, i, sample->begin(), sample->end() );
}
table.add_seq_info( id, data );
++seqnum;
}
}
}
}
//-------------------------------------------------------------------------
void CMaskWriterFasta::Print( objects::CBioseq_Handle& bsh,
const TMaskList & mask,
bool parsed_id )
{
PrintId( bsh, parsed_id );
os << endl;
CSeqVector data = bsh.GetSeqVector(CBioseq_Handle::eCoding_Iupac);
/// FIXME: this can be implemented as a call to CFastaOstream, which
/// understands masking via a seq-loc
// if( dest->GetIupacna().CanGet() )
if( true )
{
string accumulator;
TMaskList::const_iterator imask = mask.begin();
for( TSeqPos i = 0; i < data.size(); ++i )
{
char letter = data[i];
if( imask != mask.end() && i >= imask->first ) {
if( i <= imask->second )
letter = tolower((unsigned char) letter);
else
{
++imask;
if( imask != mask.end()
&& i >= imask->first && i <= imask->second )
letter = tolower((unsigned char) letter);
}
}
accumulator.append( 1, letter );
if( !((i + 1)%60) )
{
os << accumulator << "\n";
accumulator = "";
}
}
if( accumulator.length() ) os << accumulator << "\n";
}
}
void CNucProp::CountNmers(CSeqVector& seqvec, int n, vector<int>& table)
{
TSeqPos len = seqvec.size();
table.resize(NumberOfNmers(n));
// clear table
for (int i = 0; i < NumberOfNmers(n); i++) {
table[i] = 0;
}
string seq_string;
seqvec.GetSeqData(0, len, seq_string);
const char *seq;
seq = seq_string.data();
for (TSeqPos i = 0; i <= len-n; ++i) {
int nmerint = Nmer2Int(seq+i, n);
if (nmerint >= 0) { // if no ambiguity chars
table[nmerint]++;
}
}
}
void CSeqVector_CI::x_SetVector(CSeqVector& seq_vector)
{
if ( m_SeqMap ) {
// reset old values
m_Seg = CSeqMap_CI();
x_ResetCache();
x_ResetBackup();
}
m_Scope = seq_vector.m_Scope;
m_SeqMap = seq_vector.m_SeqMap;
m_TSE = seq_vector.m_TSE;
m_Strand = seq_vector.m_Strand;
m_Coding = seq_vector.m_Coding;
m_CachePos = seq_vector.size();
m_Randomizer = seq_vector.m_Randomizer;
m_ScannedStart = m_ScannedEnd = 0;
}
int CNucProp::GetPercentGC(const CSeqVector& seqvec)
{
TSeqPos gc_count = 0;
TSeqPos len = seqvec.size();
for (TSeqPos i = 0; i < len; ++i) {
switch (seqvec[i]) {
case 'C':
case 'G':
case 'S':
++gc_count;
break;
default:
break;
}
}
return (int) ((gc_count * 100.0) / len + 0.5);
}
void CSimpleOM::GetIupac(string& result, const CSeq_id& id, ENa_strand strand)
{
CSeqVector vec = GetSeqVector(id, strand);
vec.SetIupacCoding();
vec.GetSeqData(0, vec.size(), result);
}
void CSimpleOM::GetIupac(string& result, TGi gi, ENa_strand strand)
{
CSeqVector vec = GetSeqVector(gi, strand);
vec.SetIupacCoding();
vec.GetSeqData(0, vec.size(), result);
}