int CSeq_id_Handle::CompareOrdered(const CSeq_id_Handle& id) const
{
// small optimization to avoid creation of temporary CSeq_id objects
if ( int diff = Which() - id.Which() ) {
return diff;
}
if ( IsGi() && id.IsGi() ) {
return GetGi() - id.GetGi();
}
return GetSeqId()->CompareOrdered(*id.GetSeqId());
}
static TReadId sx_GetReadId(const CSeq_id_Handle& idh)
{
if ( idh.Which() != CSeq_id::e_General ) {
return TReadId();
}
CConstRef<CSeq_id> id = idh.GetSeqId();
const CDbtag& general = id->GetGeneral();
if ( general.GetDb() != "SRA") {
return TReadId();
}
return sx_GetReadId(general.GetTag().GetStr(), true);
}
int
CLocalBlastDbAdapter::GetTaxId(const CSeq_id_Handle& idh)
{
int retval = static_cast<int>(kInvalidSeqPos);
CConstRef<CSeq_id> id = idh.GetSeqId();
if (id.NotEmpty()) {
int oid = 0;
if (SeqidToOid(*id, oid)) {
map<int, int> gi_to_taxid;
m_SeqDB->GetTaxIDs(oid, gi_to_taxid);
if (idh.IsGi()) {
retval = gi_to_taxid[GI_TO(int, idh.GetGi())];
} else {
Uint4 GetSequenceType(const CBioseq_Handle& bsh)
{
if (bsh.IsAa()) {
return CSeq_id::fAcc_prot;
}
const CMolInfo* info = sequence::GetMolInfo(bsh);
if (info) {
if (info->GetBiomol() == CMolInfo::eBiomol_mRNA ||
info->GetBiomol() == CMolInfo::eBiomol_pre_RNA ||
info->GetBiomol() == CMolInfo::eBiomol_tRNA ||
info->GetBiomol() == CMolInfo::eBiomol_snRNA ||
info->GetBiomol() == CMolInfo::eBiomol_scRNA ||
info->GetBiomol() == CMolInfo::eBiomol_cRNA ||
info->GetBiomol() == CMolInfo::eBiomol_snoRNA ||
info->GetBiomol() == CMolInfo::eBiomol_ncRNA ||
info->GetBiomol() == CMolInfo::eBiomol_tmRNA) {
return (CSeq_id::fAcc_nuc | CSeq_id::eAcc_mrna);
}
if (info->GetBiomol() == CMolInfo::eBiomol_genomic) {
return (CSeq_id::fAcc_nuc | CSeq_id::fAcc_genomic);
}
}
CSeq_id_Handle idh = sequence::GetId(*bsh.GetSeqId(), bsh.GetScope(),
sequence::eGetId_Best);
CSeq_id::EAccessionInfo id_info = idh.GetSeqId()->IdentifyAccession();
if ((id_info & CSeq_id::eAcc_division_mask) == CSeq_id::eAcc_est ||
id_info == CSeq_id::eAcc_refseq_mrna ||
id_info == CSeq_id::eAcc_refseq_mrna_predicted ||
id_info == CSeq_id::eAcc_gpipe_mrna) {
return (CSeq_id::fAcc_nuc | CSeq_id::eAcc_mrna);
}
if (id_info == CSeq_id::eAcc_refseq_chromosome ||
id_info == CSeq_id::eAcc_refseq_contig ||
id_info == CSeq_id::eAcc_refseq_genomic ||
id_info == CSeq_id::eAcc_refseq_genome ||
id_info == CSeq_id::eAcc_refseq_wgs_intermed) {
return (CSeq_id::fAcc_nuc | CSeq_id::fAcc_genomic);
}
return (CSeq_id::eAcc_unknown);
}
//----------------------------------------------------------------
void CEditsSaver::AddId(const CBioseq_Handle& handle,
const CSeq_id_Handle& id,
ECallMode mode)
{
CRef<CSeqEdit_Cmd> cmd;
SCmdCreator<CSeqEdit_Cmd::e_Add_id>::CreateCmd(handle,cmd).
SetAdd_id(const_cast<CSeq_id&>(*id.GetSeqId()));
GetDBEngine().SaveCommand(*cmd);
GetDBEngine().NotifyIdChanged(id, cmd->GetBlobId());
}
void CEditsSaver::RemoveId(const CBioseq_Handle& handle,
const CSeq_id_Handle& id,
ECallMode mode)
{
CRef<CSeqEdit_Cmd> cmd;
SCmdCreator<CSeqEdit_Cmd::e_Remove_id>::CreateCmd(handle,
CBioObjectId(id),
cmd).
SetRemove_id(const_cast<CSeq_id&>(*id.GetSeqId()));
GetDBEngine().SaveCommand(*cmd);
GetDBEngine().NotifyIdChanged(id,"");
}
Int8 CLDS2_Database::x_GetLdsSeqId(const CSeq_id_Handle& id)
{
CSQLITE_Statement* st = NULL;
if ( id.IsGi() ) {
// Try to use integer index
st = &x_GetStatement(eSt_GetLdsSeqIdForIntId);
st->Bind(1, id.GetGi());
}
else {
// Use text index
st = &x_GetStatement(eSt_GetLdsSeqIdForTxtId);
st->Bind(1, id.AsString());
}
if ( st->Step() ) {
Int8 ret = st->GetInt8(0);
st->Reset();
return ret;
}
// Id not in the database yet -- add new entry.
st = &x_GetStatement(eSt_AddLdsSeqId);
st->Bind(1, id.AsString());
if ( id.IsGi() ) {
st->Bind(2, id.GetGi());
}
else {
// HACK: reset GI to null if not available.
st->Bind(2, (void*)NULL, 0);
}
CNcbiOstrstream out;
out << MSerial_AsnBinary << *id.GetSeqId();
string buf = CNcbiOstrstreamToString(out);
st->Bind(3, buf.size());
st->Bind(4, buf.data(), buf.size());
st->Execute();
Int8 ret = st->GetLastInsertedRowid();
st->Reset();
return ret;
}
static inline CRef<CSeq_id> s_ConvertId(const CSeq_id_Handle& handle)
{
return CRef<CSeq_id>(const_cast<CSeq_id*>(&*handle.GetSeqId()));
}
CAlignSort::SSortKey
CAlignSort::SAlignExtractor::operator()(const CSeq_align& align)
{
SSortKey key;
ITERATE (vector<string>, iter, key_toks) {
SSortKey::TItem item;
if (NStr::EqualNocase(*iter, "query")) {
CSeq_id_Handle idh =
CSeq_id_Handle::GetHandle(align.GetSeq_id(0));
idh = sequence::GetId(idh, *scope,
sequence::eGetId_Canonical);
item.first = idh.GetSeqId()->AsFastaString();
}
else if (NStr::EqualNocase(*iter, "subject")) {
CSeq_id_Handle idh =
CSeq_id_Handle::GetHandle(align.GetSeq_id(1));
idh = sequence::GetId(idh, *scope,
sequence::eGetId_Canonical);
item.first = idh.GetSeqId()->AsFastaString();
}
else if (NStr::EqualNocase(*iter, "query_start")) {
item.second = align.GetSeqStart(0);
}
else if (NStr::EqualNocase(*iter, "subject_start")) {
item.second = align.GetSeqStart(1);
}
else if (NStr::EqualNocase(*iter, "query_end")) {
item.second = align.GetSeqStop(0);
}
else if (NStr::EqualNocase(*iter, "subject_end")) {
item.second = align.GetSeqStop(1);
}
else if (NStr::EqualNocase(*iter, "query_strand")) {
item.second = align.GetSeqStrand(0);
}
else if (NStr::EqualNocase(*iter, "subject_strand")) {
item.second = align.GetSeqStrand(1);
}
else if (NStr::EqualNocase(*iter, "query_align_len")) {
item.second = align.GetSeqRange(0).GetLength();
}
else if (NStr::EqualNocase(*iter, "subject_align_len")) {
item.second = align.GetSeqRange(1).GetLength();
}
else if (NStr::EqualNocase(*iter, "query_traceback")) {
CScoreBuilder builder;
item.first = builder.GetTraceback(*scope, align, 0);
}
else if (NStr::EqualNocase(*iter, "subject_traceback")) {
CScoreBuilder builder;
item.first = builder.GetTraceback(*scope, align, 1);
}
else {
/// assume it is a score
CScoreLookup lookup;
lookup.SetScope(*scope);
item.second = lookup.GetScore(align, *iter);
}
key.items.push_back(item);
}
void CGenbankGatherer::x_DoSingleSection(CBioseqContext& ctx) const
{
CConstRef<IFlatItem> item;
const CFlatFileConfig& cfg = ctx.Config();
// these macros make the code easier to read and less repetitive
#define GATHER_BLOCK(BlockType, ItemClassName) \
if( cfg.IsShownGenbankBlock(CFlatFileConfig::fGenbankBlocks_##BlockType) ) { \
item.Reset( new ItemClassName(ctx) ); \
ItemOS() << item; \
}
#define GATHER_ANCHOR(BlockType, block_str) \
if( cfg.IsShownGenbankBlock(CFlatFileConfig::fGenbankBlocks_##BlockType) ) { \
item.Reset( new CHtmlAnchorItem(ctx, (block_str) ) ); \
ItemOS() << item; \
}
#define GATHER_VIA_FUNC(BlockType, FuncName) \
if( cfg.IsShownGenbankBlock(CFlatFileConfig::fGenbankBlocks_##BlockType) ) { \
FuncName(); \
}
// if there's a callback, let it know we've entered another bioseq
if( cfg.GetGenbankBlockCallback() ) {
CFlatFileConfig::CGenbankBlockCallback::EBioseqSkip eBioseqSkip =
cfg.GetGenbankBlockCallback()->notify_bioseq( ctx );
if( eBioseqSkip == CFlatFileConfig::CGenbankBlockCallback::eBioseqSkip_Yes ) {
return;
}
}
// gather needed blocks
GATHER_BLOCK(Head, CStartSectionItem);
GATHER_ANCHOR(Locus, "locus");
GATHER_BLOCK(Locus, CLocusItem);
GATHER_BLOCK(Defline, CDeflineItem);
GATHER_BLOCK(Accession, CAccessionItem);
GATHER_BLOCK(Version, CVersionItem);
GATHER_BLOCK(Project, CGenomeProjectItem);
if ( ctx.IsProt() ) {
bool show_dbsource = true;
CBioseq_Handle& bsh = ctx.GetHandle();
FOR_EACH_SEQID_ON_BIOSEQ_HANDLE (sid_itr, bsh) {
CSeq_id_Handle sid = *sid_itr;
switch (sid.Which()) {
case NCBI_SEQID(Other):
{
CConstRef<CSeq_id> id = sid.GetSeqId();
const CTextseq_id& tsid = *id->GetTextseq_Id ();
if (tsid.IsSetAccession()) {
const string& acc = tsid.GetAccession ();
if (NStr::StartsWith (acc, "WP_")) {
show_dbsource = false;
}
}
break;
}
default:
break;
}
}