Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/seqdbvol_8cpp_source.html below:

NCBI C++ ToolKit: src/objtools/blast/seqdb_reader/seqdbvol.cpp Source File

*

(0);

m_IsAA (prot_nucl ==

),

m_VolStart (vol_start),

m_HaveColumns (

),

m_SeqFileOpened(

),

m_HdrFileOpened(

),

m_HashFileOpened(

),

m_OidFileOpened(

)

start_offset = 0;

end_offset = 0;

(end_offset - start_offset - 1);

start_offset = 0;

end_offset = 0;

whole_bytes =

(end_offset - start_offset - 1);

remainder = amb_char & 3;

(whole_bytes * 4) + remainder;

start_offset = 0;

end_offset = 0;

whole_bytes =

(end_offset - start_offset - 1);

(whole_bytes * 4) + (oid & 0x03);

translated.resize(512);

0x21, 0x22, 0x24, 0x28,

0x41, 0x42, 0x44, 0x48,

0x81, 0x82, 0x84, 0x88 };

(pair1 = 0; pair1 < 16; pair1++) {

(pair2 = 0; pair2 < 16; pair2++) {

index = (pair1 * 16 + pair2) * 2;

translated[index] =

[pair1];

translated[index+1] =

[pair2];

vector<char> & buf4bit,

& expanded =

.Get().storage;

buf4bit.resize(estimated_length);

(

=0;

<inp_chars;

++) {

inp_char = (buf2bit[

] & 0xFF);

buf4bit[bytes] = expanded[ (inp_char*2) ];

buf4bit[bytes+1] = expanded[ (inp_char*2) + 1 ];

remainder_bits = 2 * bases_remain;

remainder_mask = (0xFF << (8 - remainder_bits)) & 0xFF;

last_masked = buf2bit[inp_chars] & remainder_mask;

buf4bit[bytes++] = expanded[ (last_masked*2) ];

(bases_remain > 2) {

buf4bit[bytes ++] = expanded[ (last_masked*2)+1 ];

buf4bit.resize(bytes);

(estimated_length == (

)buf4bit.size());

(

= 0;

<256;

++) {

p1 = (

>> 6) & 0x3;

p2 = (

>> 4) & 0x3;

p3 = (

>> 2) & 0x3;

translated.push_back(1 << p1);

translated.push_back(1 << p2);

translated.push_back(1 << p3);

translated.push_back(1 << p4);

& expanded =

.Get().storage;

pos = range.

;

input_chars_begin = range.

/ 4;

input_chars_end = (range.

+ 3) / 4;

whole_chars_begin = (range.

+ 3) / 4;

whole_chars_end = range.

/ 4;

p = input_chars_begin;

(p < whole_chars_begin) {

table_offset = (buf2bit[input_chars_begin] & 0xFF) * 4;

endpt = (input_chars_begin + 1) * 4;

(endpt > range.

) {

(

k = range.

; k < endpt; k++) {

buf8bit[pos++] = expanded[ table_offset + 1 ];

buf8bit[pos++] = expanded[ table_offset + 2 ];

buf8bit[pos++] = expanded[ table_offset + 3 ];

p = whole_chars_begin;

(p < whole_chars_end) {

table_offset = (buf2bit[p] & 0xFF) * 4;

buf8bit[pos++] = expanded[ table_offset ];

buf8bit[pos++] = expanded[ table_offset + 1 ];

buf8bit[pos++] = expanded[ table_offset + 2 ];

buf8bit[pos++] = expanded[ table_offset + 3 ];

(p < input_chars_end) {

table_offset = (buf2bit[p] & 0xFF) * 4;

remains = (range.

& 0x3);

buf8bit[pos++] = expanded[ table_offset ];

buf8bit[pos++] = expanded[ table_offset + 1 ];

buf8bit[pos++] = expanded[ table_offset + 2 ];

(

= range.

;

< range.

;

++)

(ambchars[

] >> 16) & 0xFFF;

ambchars[

+1];

(ambchars[

] >> 28) & 0xF;

(ambchars[

] >> 24) & 0xF;

ambchars[

] & 0xFFFFFF;

vector<Int4> & amb_chars)

(amb_chars.empty())

amb_num = amb_chars[0];

new_format = (amb_num & 0x80000000) != 0;

amb_num &= 0x7FFFFFFF;

(

=1;

< amb_num+1;

++) {

pos = position / 2;

rem = position & 1;

char_l = char_r << 4;

(j = 0; j <= row_len; j++) {

buf4bit[index] = (buf4bit[index] & 0x0F) + char_l;

buf4bit[index] = (buf4bit[index] & 0xF0) + char_r;

vector<Int4> & amb_chars,

(amb_chars.empty() || !seq )

;

amb_num = amb_chars[0];

new_format = (amb_num & 0x80000000) != 0;

(new_format) amb_num &= 0x7FFFFFFF;

(

= 1;

< amb_num+1;

++) {

(new_format) ++

;

(position + row_len <= region.

)

(position >= region.

)

(

j = 0; j < row_len; ++j, ++position)

( position >= region.

&& position < region.

)

seq[position] = trans_ch;

* seq_buffer,

vector<char> aa_data;

aa_data.resize(length);

(

= 0;

< length;

++) {

aa_data[

] = seq_buffer[

];

seqinst.

().SetNcbistdaa().Set().swap(aa_data);

* seq_buffer,

whole_bytes = length / 4;

partial_byte = ((length & 0x3) != 0) ? 1 : 0;

vector<char> na_data;

na_data.resize(whole_bytes + partial_byte);

(

= 0;

<whole_bytes;

++) {

na_data[

] = seq_buffer[

];

na_data[whole_bytes] = seq_buffer[whole_bytes] & (0xFF - 0x03);

seqinst.

().SetNcbi2na().Set().swap(na_data);

* seq_buffer,

vector<Int4> & amb_chars)

vector<char> buffer_4na;

seqinst.

().SetNcbi4na().Set().swap(buffer_4na);

list< CRef<CBlast_def_line> >::const_iterator TDefIt;

list< CRef<CSeq_id > >::const_iterator TSeqIt;

list< CRef<CBlast_def_line> > & dl = deflines->

();

first_defline(

);

(TDefIt iter = dl.begin(); iter != dl.end(); iter++) {

(! title.empty()) {

wrote_seqids(

);

list< CRef<CSeq_id > > & sl = defline.

();

first_seqid(

);

(TSeqIt seqit = sl.begin(); seqit != sl.end(); seqit++) {

(*seqit)->WriteAsFasta(oss);

first_seqid =

;

wrote_seqids =

;

first_defline =

;

list< CRef<CSeq_id> > TSeqidList;

(TSeqidList, iter, seqids) {

* preferred_seqid)

(preferred_gi !=

|| preferred_seqid) {

(preferred_gi !=

) {

seqid.

(preferred_seqid);

found =

;

new_bdls->

().push_front(*iter);

new_bdls->

().push_back(*iter);

list< CRef<CSeqdesc> >

* preferred_seqid)

provide_new_taxonomy_info =

;

* TAX_ORGREF_DB_NAME =

;

list< CRef<CSeqdesc> > taxonomy;

(bdls.

()) {

list< CRef<CBlast_def_line> > TBDLL;

TBDLL::const_iterator TBDLLConstIter;

TBDLL & dl = bdls->

();

(TBDLLConstIter iter = dl.begin(); iter != dl.end(); iter ++) {

((*iter)->CanGetTaxid()) {

taxid = (*iter)->GetTaxid();

have_org_desc =

;

have_org_desc =

;

found_taxid_in_taxonomy_blastdb =

;

((! have_org_desc) && provide_new_taxonomy_info) {

found_taxid_in_taxonomy_blastdb =

;

(provide_new_taxonomy_info) {

(have_org_desc) {

org_tag->

(TAX_ORGREF_DB_NAME);

(found_taxid_in_taxonomy_blastdb) {

org->

().push_back(org_tag);

taxonomy.push_back(desc);

(use_taxinfo_cache) {

(oss.size() == 1) {

vector<char> & v = *oss.front();

+= (**iter1).size();

temp.reserve(

);

temp.append(& (**iter3)[0], (*iter3)->size());

( !bioseq.IsSetDescr() ) {

( !(*iter)->IsUser() ) {

vector< CRef< CUser_field > >& usf = uobj.

();

(usf.front()->CanGetData());

(usf.front()->GetData().IsOss()) {

vector<char> hdr_data;

(! hdr_data.empty()) {

vector< vector<char>* > & strs = uf->

().SetOss();

strs.push_back(

vector<char>);

strs[0]->swap(hdr_data);

uobj->

().push_back(uf);

* target_seq_id,

list< CRef<CBlast_def_line> > TDeflines;

list< CRef< CSeq_id > > seqids;

((target_gi !=

) || target_seq_id) {

seqid.

(target_seq_id);

(TDeflines, iter, orig_deflines->

()) {

(filt_dl.

()) {

);

defline_set->

().push_back(filt_dl);

defline_set = orig_deflines;

(defline_set.

() ||

(! defline_set->

()) ||

(0 == defline_set->

().size())) {

defline = defline_set->

().front();

(! defline->CanGetSeqid()) {

seqids = defline->GetSeqid();

* seq_buffer = 0;

vector<Int4> ambchars;

(ambchars.empty()) {

bioseq->

().SetMol(is_prot

bioseq->

().swap(seqids);

desc1->

().swap(description);

seq_desc_set.

().push_back(desc1);

(! desc2.

()) {

seq_desc_set.

().push_back(desc2);

list< CRef<CSeqdesc> > tax =

bioseq->

().Set().push_back(*iter);

(alloc_type) {

retval = (

*)

(length);

retval =

[length];

(oid, & buf1, nucl_code, alloc_type, region, masks);

(!masks || masks->

())

;

begin(range.

);

end(range.

);

(i < masks->

() && (*masks)[

].second <= begin) ++

;

(i < masks->

() && (*masks)[

].

< end) {

(

j =

((*masks)[

].

, begin);

j <

((*masks)[

].second, end); ++j) {

seq[j] = mask_letter;

((partial_ranges ==

) || (partial_ranges->

() == 0)) {

*

(0);

num_ranges =

(partial_ranges->

());

((*partial_ranges)[num_ranges - 1].second >

(

)) {

*seq = *

+ (sentinel ? 1 : 0);

vector<Int4> ambchars;

begin(riter->first);

end(riter->second);

(*buffer)[0] = (char)15;

*

(0);

*seq = *

- range.

+ (sentinel ? 1 : 0);

vector<Int4> ambchars;

use_range_set =

;

|| rciter->second->GetRanges().empty()

use_range_set =

;

range_set = rciter->second->GetRanges();

(!use_range_set) {

begin(riter->first);

end(riter->second);

(range.

, riter->second));

(*buffer)[0] = (char)15;

(masks) masks->

();

(sequence.

() == 0) {

);

* seq_buffer = sequence.

();

whole_bytes =

(sequence.

()) - 1;

remainder = sequence[whole_bytes] & 3;

vector<Int4> ambchars;

ambchars.reserve(ambiguities.

()/4);

(

= 0;

< ambiguities.

();

+=4) {

ambchars.push_back(

);

**

)

start_offset = 0;

end_offset = 0;

(

== seqtype) {

length =

(end_offset - start_offset);

(! (*

- 1))

-1;

}

(

== seqtype) {

(! (*

))

-1;

whole_bytes =

(end_offset - start_offset - 1);

last_char = (*buffer)[whole_bytes];

remainder = last_char & 3;

length = (whole_bytes * 4) + remainder;

list< CRef< CSeq_id > > seqids;

((! defline_set.

()) && defline_set->

()) {

(! (*defline)->CanGetSeqid()) {

seqids.push_back(*seqid);

list< CRef< CSeq_id > > seqids;

((! defline_set.

()) && defline_set->

()) {

(! (*defline)->CanGetSeqid()) {

seqids.push_back(*seqid);

tax_ids.

(leaf_ids.begin(), leaf_ids.end());

(user_tax_ids.

() > tax_ids.

()) {

(user_tax_ids.

(*itr) != user_tax_ids.

()) {

(tax_ids.

(*itr) != tax_ids.

()) {

(taxid_set.

() > user_tax_ids.

()) {

(user_tax_ids.

(*itr) == user_tax_ids.

()) {

* changed)

list< CRef<CBlast_def_line> > TBDLL;

TBDLL::iterator TBDLLIter;

(useCache && cached.first.NotEmpty()) {

*changed = cached.second;

cached.first;

asn_changed =

;

TBDLL & dl = BDLS->

();

(TBDLLIter iter = dl.begin(); iter != dl.end(); ) {

have_memb =

;

memb_mask = 0x1 << (

-1);

((bits & memb_mask) == 0) {

have_user =

, have_volume =

;

(have_user && have_volume)

;

have_memb = have_user && have_volume;

( (*vtaxid)->GetNumTaxIds() > 0) {

TBDLLIter eraseme = iter++;

asn_changed =

;

cached.first = BDLS;

cached.second = asn_changed;

cached.first = BDLS;

cached.second = asn_changed;

list< CRef<CBlast_def_line> > TBDLL;

TBDLL::iterator TBDLLIter;

(useCache && cached.first.NotEmpty()) {

*changed = cached.second;

cached.first;

asn_changed =

;

TBDLL & dl = BDLS->

();

(TBDLLIter iter = dl.begin(); iter != dl.end(); ) {

have_memb =

;

memb_mask = 0x1 << (

-1);

((bits & memb_mask) == 0) {

have_user =

, have_volume =

;

(have_user && have_volume)

;

have_memb = have_user && have_volume;

( (*vtaxid)->GetNumTaxIds() > 0) {

TBDLLIter eraseme = iter++;

asn_changed =

;

cached.first = BDLS;

cached.second = asn_changed;

cached.first = BDLS;

cached.second = asn_changed;

* changed)

(! raw_data.

()) {

bdls.

(

objects::CBlast_def_line_set);

(! (**dl).CanGetSeqid()) {

(dbt.

() ==

) {

(! raw_data.

()) {

bdls.

(

objects::CBlast_def_line_set);

(! (**dl).CanGetSeqid()) {

(dbt.

() ==

) {

hdr_start = 0;

(asn_region, hdr_end - hdr_start);

vector<char> & hdr_data )

changed =

;

hdr_data.assign(s.data(), s.data() + s.size());

hdr_data.assign(raw.

(), raw.

() + raw.

());

vector<Int4> & ambchars)

start_offset = 0;

end_offset = 0;

);

length =

(end_offset - start_offset);

total = length / 4;

total &= 0x7FFFFFFF;

ambchars.resize(total);

(

= 0;

<total;

++) {

list< CRef< CBlast_def_line > >::const_iterator TI1;

TI1 it1 = BDLS->

().begin();

(; it1 != BDLS->

().end(); it1++) {

((*it1)->IsSetOther_info()) {

TI2 it2 = (*it1)->GetOther_info().begin();

TI2 it2end = (*it1)->GetOther_info().end();

(; it2 != it2end; it2++) {

! oids.empty();

+

);

+

);

+

);

+

);

+

);

+

);

+

);

list< CRef< CBlast_def_line > >::const_iterator TI1;

list< CRef< CSeq_id > >::const_iterator TI2;

TI1 it1 = BDLS->

().begin();

(; it1 != BDLS->

().end(); it1++) {

((*it1)->CanGetSeqid()) {

TI2 it2 = (*it1)->GetSeqid().begin();

TI2 it2end = (*it1)->GetSeqid().end();

(; it2 != it2end; it2++) {

((*it2)->IsGi()) {

gi = (*it2)->GetGi();

& str_id,

vector<int> & oids)

vcheck (

);

fits_in_four = (ident == -1) || ! (ident >> 32);

needs_four =

;

oids.push_back(oid);

oids.push_back(oid);

oids.push_back(oid);

oids.push_back((

) ident);

);

((! fits_in_four) && needs_four) {

);

vector<int> & oids)

pos = acc.find(

);

ver_str(acc, pos+1, acc.size()-(pos+1));

nover(acc, 0, pos);

((pos2 = nover.find(

)) != nover.npos) {

nover.erase(0, pos2+1);

list< CRef<CSeq_id> > ids =

found =

;

*

= (*seqid)->GetTextseq_Id();

oids.erase(

(oids.begin(), oids.end(), -1), oids.end());

simpler (

);

simpler (

);

(first_seq >= vol_cnt) {

);

(residue >= vol_len) {

);

dresidue = (double(residue) * end_of_bytes) / vol_len;

residue =

(dresidue);

(residue > (end_of_bytes-1)) {

residue = end_of_bytes - 1;

oid_beg = first_seq;

oid_end = vol_cnt-1;

oid_mid = (oid_beg + oid_end)/2;

(oid_beg < oid_end) {

(

>= residue) {

oid_beg = oid_mid + 1;

oid_mid = (oid_beg + oid_end)/2;

start_offset = 0;

start_offset;

((begin >= end) || (end > length)) {

);

v4.reserve((length+1)/2);

(

= 0;

< length_whole;

+= 2) {

(length_whole != length) {

((length_whole) == (length-1));

v4.push_back(

[length_whole] << 4);

* amb_length )

map_begin = 0;

amb_ok =

;

end_A = start_A = --end_S;

map_begin = start_S - 1;

map_end = end_A + 1;

map_begin = start_S;

s_len =

(end_S - start_S);

a_len =

(end_A - start_A);

(! (s_len && amb_ok)) {

);

*amb_length = a_len;

*seq_length = s_len;

*

+= (start_S - map_begin);

(! *seq_length) {

);

(((

&& *

) || a_len) && (! *seq_length)) {

(

>= (

(1) << 32)) {

);

low_id = high_id =

= 0;

high_id = (

)

;

cache_data)

(offset_ranges.

() && (! cache_data) && (! append_ranges)) {

(

.Empty() ||

->GetRanges().empty()) {

(offset_ranges.

() && (! cache_data)) {

flush_sequence = ((! append_ranges) ||

(! offset_ranges.

()) ||

(flush_sequence) {

->FlushSequence();

->SetRanges(offset_ranges, append_ranges, cache_data);

(append_ranges) {

((**gilist).GetNumSis() != 0)

((**gilist).GetNumTis() != 0)

);

[col_id]->GetBlob(oid, blob, keep, & locked);

[col_id]->GetMetaData();

titles.

((**iter).GetTitle());

alpha(

);

ei(

), ed(

), ed2(

);

ei[0] = ed[0] = ed2[0] = (

?

:

);

(

= 0;

< alpha.size();

++) {

ei[1] = ed[1] = ed2[1] = alpha[

];

( ! (big || small))

;

bytetest = 0x0011;

* ptr = (

*) &bytetest;

(ptr[0] == 0x11 && small) {

errmsg, errarg;

title = col->GetTitle();

(unique_titles[title]) {

errmsg =

;

unique_titles[title] = 1;

(noidc != noidv) {

errmsg =

;

(errmsg.size()) {

(errarg.size()) {

errmsg +=

(

) + errarg +

;

(

) + errmsg);

(

);

#define FENCE_SENTRY

This sentry value is used as a 'fence' around the valid portions of partially decoded sequences.

vector< TSeqRange > TRangeVector

ncbi::TMaskedQueryRegions mask

`Blob' Class for SeqDB (and WriteDB).

TTaxIds GetTaxIds() const

CNcbiOstrstreamToString class helps convert CNcbiOstrstream to a string Sample usage:

CObjectIStreamAsnBinary –.

CObjectOStreamAsnBinary –.

static char * Alloc(size_t length, bool clear=true)

Allocate memory that atlas will keep track of.

static bool ColumnExists(const string &basename, const string &extn, CSeqDBAtlas &atlas)

Determine if the column exists.

void UnLease()

Release memory held in the atlas layer by this object.

const char * GetFileDataPtr(const string &fname, TIndx offset)

Get a pointer to the specified offset.

static bool IndexExists(const string &name, const char prot_nucl)

TGi GetSeqGI(TOid oid, CSeqDBLockHold &locked)

int GetNumGis() const

Get the number of GIs in the array.

int GetNumSis() const

Get the number of Seq-ids in the array.

int GetNumTis() const

Get the number of TIs in the array.

Uint8 GetMaskOpts() const

set< TTaxId > & GetTaxIdsList()

const char * GetFileDataPtr(TIndx start) const

Read part of the file into a buffer.

string GetDate() const

Get the construction date of the volume.

void GetHdrStartEnd(int oid, TIndx &start, TIndx &end) const

Get the location of a sequence's header data.

void UnLease()

Release any memory leases temporarily held here.

string GetTitle() const

Get the volume title.

int GetNumOIDs() const

Get the number of oids in this volume.

string GetLMDBFileName() const

bool GetAmbStartEnd(int oid, TIndx &start, TIndx &end) const

Get the location of a sequence's ambiguity data.

Uint8 GetVolumeLength() const

Get the length of the volume (in bases).

int GetMinLength() const

Get the length of the shortest sequence in this volume.

void GetSeqStart(int oid, TIndx &start) const

Get the location of a sequence's packed sequence data.

char GetSeqType() const

Get the sequence data type.

int GetMaxLength() const

Get the length of the longest sequence in this volume.

void GetSeqStartEnd(int oid, TIndx &start, TIndx &end) const

Get the location of a sequence's packed sequence data.

TValue & Lookup(int key)

Find a value in the cache.

bool IdToOid(Int8 id, TOid &oid)

GI or TI translation.

void HashToOids(unsigned hash, vector< TOid > &oids)

Sequence hash lookup.

bool PigToOid(TPig pig, TOid &oid)

PIG translation.

void IdsToOids(int vol_start, int vol_end, CSeqDBGiList &ids)

Translate Gis and Tis to Oids for the given ID list.

void GetIdBounds(Int8 &low_id, Int8 &high_id, int &count)

Get Numeric Bounds.

void UnLease()

Return any memory held by this object to the atlas.

void StringToOids(const string &acc, vector< TOid > &oids, bool adjusted, bool &version_check)

String translation.

static bool IndexExists(const string &dbname, char prot_nucl, char file_ext_char)

Check if a given ISAM index exists.

int GetNumTis() const

Get the number of TIs in the array.

int GetNumGis() const

Get the number of GIs in the array.

int GetNumSis() const

Get the number of SeqIds in the array.

set< TTaxId > & GetTaxIdsList()

TRangeList m_Ranges

Range of offsets needed for this sequence.

void SetRanges(const TRangeList &ranges, bool append_ranges, bool cache_data)

Set ranges of the sequence that will be used.

static int ImmediateLength()

Sequences shorter than this will not use ranges in any case.

bool m_CacheData

True if caching of sequence data is required for this sequence.

void ReadBytes(char *buf, TIndx start, TIndx end) const

Read part of the file into a buffer.

const char * GetFileDataPtr(TIndx start) const

Get a pointer into the file contents.

static bool GetTaxNames(TTaxId tax_id, SSeqDBTaxInfo &info)

Get the taxonomy names for a given tax id.

void OptimizeGiLists() const

Simplify the GI list configuration.

bool m_HaveColumns

True if we have opened the columns for this volume.

list< CRef< CSeq_id > > GetSeqIDs(int oid) const

Get the Seq-ids associated with a sequence.

CFastMutex m_MtxCachedRange

CRef< CSeqDBIsam > m_IsamGi

Handles translation of GIs to OIDs.

void SeqidToOids(CSeq_id &seqid, vector< int > &oids, CSeqDBLockHold &locked) const

Find OIDs for the specified Seq-id.

Uint8 x_GetSeqResidueOffset(int oid) const

Returns the base-offset of the specified oid.

void x_OpenHashFile(void) const

void x_UnleasePigFile(void) const

int GetAmbigPartialSeq(int oid, char **buffer, int nucl_code, ESeqDBAllocType alloc_type, CSeqDB::TSequenceRanges *partial_ranges, CSeqDB::TSequenceRanges *masks) const

void x_UnleaseTiFile(void) const

CSeqDBAtlas & m_Atlas

The memory management layer.

void AccessionToOids(const string &acc, vector< int > &oids, CSeqDBLockHold &locked) const

Find OIDs for the specified accession or formatted Seq-id.

void GetColumnBlob(int col_id, int oid, CBlastDbBlob &blob, bool keep, CSeqDBLockHold &locked)

Fetch the data blob for the given column and oid.

CRef< CSeqDBHdrFile > m_Hdr

Contains header (defline) information for this volume.

void x_OpenSeqFile(void) const

CSeqDBIntCache< CRef< CSeqdesc > > m_TaxCache

This cache allows CBioseqs to share taxonomic objects.

void x_OpenTiFile(void) const

int GetAmbigSeq(int oid, char **buffer, int nucl_code, ESeqDBAllocType alloc_type, SSeqDBSlice *region, CSeqDB::TSequenceRanges *masks) const

Get a sequence with ambiguous regions.

vector< CRef< CSeqDBColumn > > m_Columns

Set of columns defined for this volume.

CRef< CSeqDBIdxFile > m_Idx

Metadata plus offsets into the sequence, header, and ambiguity data.

void x_OpenStrFile(void) const

int GetSeqLengthExact(int oid) const

Exact sequence length for nucleotide databases.

void x_StringToOids(const string &acc, ESeqDBIdType id_type, Int8 ident, const string &str_id, bool simplified, vector< int > &oids) const

void OpenSeqFile(CSeqDBLockHold &locked) const

Open sequence file.

int GetColumnId(const string &title, CSeqDBLockHold &locked)

Get an ID number for a given column title.

CRef< CSeqDBIsam > m_IsamStr

Handles translation of strings (accessions) to OIDs.

vector< CRef< CSeqDBGiList > > TGiLists

A set of GI lists.

CSeqDBIntCache< TDeflineCacheItem > m_DeflineCache

Cache of filtered deflines.

int x_GetAmbigSeq(int oid, char **buffer, int nucl_code, ESeqDBAllocType alloc_type, SSeqDBSlice *region, CSeqDB::TSequenceRanges *masks) const

Get a sequence with ambiguous regions.

int m_VolStart

Starting OID of this volume.

int GetNumOIDs() const

Get the number of OIDs for this volume.

bool GetGi(int oid, TGi &gi, CSeqDBLockHold &locked) const

Find the GI given an OID.

CRef< CBlast_def_line_set > x_GetHdrAsn1(int oid, bool adjust_oids, bool *changed) const

Get sequence header object.

void GetPigBounds(int &low_id, int &high_id, int &count, CSeqDBLockHold &locked) const

Get PIG Bounds.

void x_FilterHasId(const CSeq_id &id, bool &have_user, bool &have_vol) const

Determine if a user ID list affects this ID, and how.

string m_VolName

The name of this volume.

CTempString x_GetHdrAsn1Binary(int oid) const

Get sequence header binary data.

void FlushOffsetRangeCache()

Flush all offset ranges cached.

CSeqDBVol(CSeqDBAtlas &atlas, const string &name, char prot_nucl, CSeqDBGiList *user_list, CSeqDBNegativeList *neg_list, int vol_start, CSeqDBLockHold &locked)

Constructor.

void GetRawSeqAndAmbig(int oid, const char **buffer, int *seq_length, int *ambig_length) const

Get Raw Sequence and Ambiguity Data.

void x_OpenHdrFile(void) const

string GetLMDBFileName() const

Get sqlite file name associated with this volume Empty string if version 4.

void ListColumns(set< string > &titles, CSeqDBLockHold &locked)

List the titles of all columns for this volume.

int GetSeqLengthApprox(int oid) const

Approximate sequence length for nucleotide databases.

TRangeCache m_RangeCache

Cached/ranged sequence info.

int m_VolEnd

First OID past end of this volume.

bool m_SeqFileOpened

True if the volume file has been (at least tried to) opened.

bool GetPig(int oid, int &pig, CSeqDBLockHold &locked) const

Find the PIG given an OID.

int GetSeqLengthProt(int oid) const

Sequence length for protein databases.

CRef< CSeqDBSeqFile > m_Seq

Contains sequence data for this volume.

CRef< CSeqdesc > x_GetAsnDefline(int oid) const

Get sequence header information structures.

string GetTitle() const

Get the volume title.

CRef< CSeqDBGiIndex > m_GiIndex

The GI index file (for fast oid->gi conversion)

CRef< CSeqDBNegativeList > m_NegativeList

The negative ID list, if one exists.

TGiLists m_VolumeGiLists

The volume GI lists, if any exist.

CRef< CSeqDBIsam > m_IsamTi

Handles translation of TI (trace ids) to OIDs.

int x_GetSequence(int oid, const char **buffer) const

Get sequence data.

CRef< CSeqDBIsam > m_IsamHash

Handles translation of sequence hash value to OIDs.

void UnLease()

Return expendable resources held by this volume.

list< CRef< CSeqdesc > > x_GetTaxonomy(int oid, TGi preferred_gi, const CSeq_id *preferred_seq_id)

Get taxonomic descriptions of a sequence.

void IdsToOids(CSeqDBGiList &gis) const

Translate Gis to Oids for the given vector of Gi/Oid pairs.

CRef< CBlast_def_line_set > x_GetFilteredHeader(int oid, bool *changed) const

Get sequence header information.

char * x_AllocType(size_t length, ESeqDBAllocType alloc_type) const

Allocate memory in one of several ways.

void x_CheckVersions(const string &acc, vector< int > &oids) const

Check Seq-id versions for special sparse-id support case.

bool GiToOid(TGi gi, int &oid, CSeqDBLockHold &locked) const

Find the OID given a GI.

TGi GetSeqGI(int oid, CSeqDBLockHold &locked) const

Get the GI of a sequence This method returns the gi of the sequence.

CRef< CSeq_data > GetSeqData(int oid, TSeqPos begin, TSeqPos end, CSeqDBLockHold &locked) const

Fetch data as a CSeq_data object.

void GetGiBounds(TGi &low_id, TGi &high_id, int &count, CSeqDBLockHold &locked) const

Get GI Bounds.

int GetOidAtOffset(int first_seq, Uint8 residue, CSeqDBLockHold &locked) const

Find the OID at a given index into the database.

char GetSeqType() const

Get the sequence type stored in this database.

bool x_HaveIdFilter(void) const

Returns true if this volume has an ID list.

void x_OpenAllColumns(CSeqDBLockHold &locked)

Find all columns for this volume.

CRef< CBioseq > GetBioseq(int oid, TGi pref_gi, const CSeq_id *pref_seq_id, bool seqdata, CSeqDBLockHold &locked)

Get a CBioseq object for this sequence.

int GetMinLength() const

Get the length of the smallest sequence in this volume.

void x_UnleaseStrFile(void) const

CRef< CSeqDBGiList > m_UserGiList

The user ID list, if one exists.

CSeqDBAtlas::TIndx TIndx

Import TIndx definition from the CSeqDBAtlas class.

void x_OpenGiFile(void) const

pair< CRef< CBlast_def_line_set >, bool > TDeflineCacheItem

Filtered defline plus whether binary data needed changes.

CRef< CSeqDBIsam > m_IsamPig

Handles translation of GIs to OIDs.

bool m_IsAA

True if the volume is protein, false for nucleotide.

const map< string, string > & GetColumnMetaData(int col_id, CSeqDBLockHold &locked)

Get all metadata for the specified column.

CRef< CBlast_def_line_set > x_GetTaxDefline(int oid, TGi preferred_gi, const CSeq_id *preferred_seq_id)

Get defline filtered by several criteria.

void x_OpenOidFile(void) const

int GetMaxLength() const

Get the length of the largest sequence in this volume.

bool PigToOid(int pig, int &oid) const

Find the OID given a PIG.

bool TiToOid(Int8 ti, int &oid, CSeqDBLockHold &locked) const

Find the OID given a TI.

void x_OpenPigFile(void) const

void x_GetFilteredBinaryHeader(int oid, vector< char > &hdr_data) const

Get binary sequence header information.

Uint8 GetVolumeLength() const

Get the total length of this volume (in bases).

CRef< CBlast_def_line_set > GetFilteredHeader(int oid, CSeqDBLockHold &locked) const

Get filtered sequence header information.

string GetDate() const

Get the formatting date of the volume.

int m_MemBit

The filtering MEMB_BIT.

void x_UnleaseGiFile(void) const

void SetOffsetRanges(int oid, const TRangeList &offset_ranges, bool append_ranges, bool cache_data) const

Apply a range of offsets to a database sequence.

void GetStringBounds(string &low_id, string &high_id, int &count) const

Get String Bounds.

void HashToOids(unsigned hash, vector< int > &oids, CSeqDBLockHold &locked) const

Get the OIDs for a given sequence hash.

void x_GetAmbChar(int oid, vector< Int4 > &ambchars) const

Get ambiguity information.

char x_GetSeqType() const

Returns 'p' for protein databases, or 'n' for nucleotide.

static const char * kOidNotFound

String containing the error message in exceptions thrown when a given OID cannot be found.

static CRef< CBlast_def_line_set > ExtractBlastDefline(const CBioseq &bioseq)

Extract a Blast-def-line-set object from a Bioseq retrieved by CSeqDB.

@Seq_descr.hpp User-defined methods of the data storage class.

CTempString implements a light-weight string on top of a storage buffer whose lifetime management is ...

container_type::iterator iterator

const_iterator end() const

const_iterator find(const key_type &key) const

iterator_bool insert(const value_type &val)

const_iterator begin() const

const_iterator find(const key_type &key) const

const_iterator end() const

static int base_length[29]

static DLIST_TYPE *DLIST_NAME() first(DLIST_LIST_TYPE *list)

static void DLIST_NAME() remove(DLIST_LIST_TYPE *list, DLIST_TYPE *item)

static TDSRET convert(TDSSOCKET *tds, TDSICONV *conv, TDS_ICONV_DIRECTION direction, const char *from, size_t from_len, char *dest, size_t *dest_len)

#define GI_FROM(T, value)

unsigned int TSeqPos

Type for sequence locations and lengths.

#define ITERATE(Type, Var, Cont)

ITERATE macro to sequence through container elements.

#define TAX_ID_TO(T, tax_id)

#define NON_CONST_ITERATE(Type, Var, Cont)

Non constant version of ITERATE macro.

SStrictId_Tax::TId TTaxId

Taxon id type.

#define TAX_ID_FROM(T, value)

#define NCBI_THROW(exception_class, err_code, message)

Generic macro to throw an exception, given the exception class, error code and message string.

const string AsFastaString(void) const

E_SIC

Compare return values.

@ e_NO

different SeqId types-can't compare

@ e_YES

SeqIds compared, but are different.

void Close(void)

Detach reader from a data source.

void OpenFromBuffer(const char *buffer, size_t size)

Attach reader to a data source.

void AddReference(void) const

Add reference to object.

void Reset(void)

Reset reference object.

bool NotEmpty(void) const THROWS_NONE

Check if CRef is not empty – pointing to an object and has a non-null value.

void RemoveReference(void) const

Remove reference to object.

bool ReferencedOnlyOnce(void) const THROWS_NONE

Check if object is referenced only once.

bool Empty(void) const THROWS_NONE

Check if CRef is empty – not pointing to any object, which means having a null value.

uint8_t Uint1

1-byte (8-bit) unsigned integer

int16_t Int2

2-byte (16-bit) signed integer

int32_t Int4

4-byte (32-bit) signed integer

uint32_t Uint4

4-byte (32-bit) unsigned integer

int64_t Int8

8-byte (64-bit) signed integer

uint64_t Uint8

8-byte (64-bit) unsigned integer

void Reset(void)

Reset random number generator to initial startup condition (LFG only)

#define END_NCBI_SCOPE

End previously defined NCBI scope.

#define BEGIN_NCBI_SCOPE

Define ncbi namespace.

static string Int8ToString(Int8 value, TNumToStringFlags flags=0, int base=10)

Convert Int8 to string.

static int StringToInt(const CTempString str, TStringToNumFlags flags=0, int base=10)

Convert string to int.

static string IntToString(int value, TNumToStringFlags flags=0, int base=10)

Convert int to string.

const char * data(void) const

Return a pointer to the array represented.

size_type length(void) const

Return the length of the represented array.

static enable_if< is_arithmetic< TNumeric >::value||is_convertible< TNumeric, Int8 >::value, string >::type NumericToString(TNumeric value, TNumToStringFlags flags=0, int base=10)

Convert numeric value to string.

size_type size(void) const

Return the length of the represented array.

@ fConvErr_NoThrow

Do not throw an exception on error.

@ fAllowTrailingSymbols

Ignore trailing non-numerics characters.

#define DEFINE_STATIC_FAST_MUTEX(id)

Define static fast mutex and initialize it.

const TSeqid & GetSeqid(void) const

Get the Seqid member data.

bool CanGetTitle(void) const

Check if it is safe to call GetTitle method.

bool IsSetLinks(void) const

Check if a value has been assigned to Links data member.

TTaxid GetTaxid(void) const

Get the Taxid member data.

bool IsSet(void) const

Check if a value has been assigned to data member.

bool IsSetMemberships(void) const

bit arrays Repurposed to store the (multiple) taxIDs associated with WP proteins.

bool IsSetTaxid(void) const

Check if a value has been assigned to Taxid data member.

const TLinks & GetLinks(void) const

Get the Links member data.

const TMemberships & GetMemberships(void) const

Get the Memberships member data.

Tdata & Set(void)

Assign a value to data member.

bool CanGet(void) const

Check if it is safe to call Get method.

const Tdata & Get(void) const

Get the member data.

bool CanGetSeqid(void) const

Check if it is safe to call GetSeqid method.

bool CanGetMemberships(void) const

Check if it is safe to call GetMemberships method.

const TTitle & GetTitle(void) const

Get the Title member data.

bool IsStr(void) const

Check if variant Str is selected.

const TTag & GetTag(void) const

Get the Tag member data.

void SetTag(TTag &value)

Assign a value to Tag data member.

const TDb & GetDb(void) const

Get the Db member data.

vector< vector< char > * > TOss

TData & SetData(void)

Assign a value to Data data member.

void SetNum(TNum value)

Assign a value to Num data member.

const TStr & GetStr(void) const

Get the variant data.

void SetLabel(TLabel &value)

Assign a value to Label data member.

TStr & SetStr(void)

Select the variant.

const TData & GetData(void) const

Get the Data member data.

void SetType(TType &value)

Assign a value to Type data member.

void SetData(TData &value)

Assign a value to Data data member.

const TType & GetType(void) const

Get the Type member data.

void SetDb(const TDb &value)

Assign a value to Db data member.

TId GetId(void) const

Get the variant data.

void SetCommon(const TCommon &value)

Assign a value to Common data member.

TDb & SetDb(void)

Assign a value to Db data member.

void SetTaxname(const TTaxname &value)

Assign a value to Taxname data member.

TGeneral & SetGeneral(void)

Select the variant.

E_Choice Which(void) const

Which variant is currently selected.

TVersion GetVersion(void) const

Get the Version member data.

bool CanGetVersion(void) const

Check if it is safe to call GetVersion method.

bool CanGetAccession(void) const

Check if it is safe to call GetAccession method.

const TAccession & GetAccession(void) const

Get the Accession member data.

@ e_General

for other databases

@ e_Gi

GenInfo Integrated Database.

list< CRef< CSeqdesc > > Tdata

TId & SetId(void)

Assign a value to Id data member.

TTitle & SetTitle(void)

Select the variant.

void SetInst(TInst &value)

Assign a value to Inst data member.

TSource & SetSource(void)

Select the variant.

TNcbistdaa & SetNcbistdaa(void)

Select the variant.

void SetDescr(TDescr &value)

Assign a value to Descr data member.

TUser & SetUser(void)

Select the variant.

void SetRepr(TRepr value)

Assign a value to Repr data member.

Tdata & Set(void)

Assign a value to data member.

void SetLength(TLength value)

Assign a value to Length data member.

void SetSeq_data(TSeq_data &value)

Assign a value to Seq_data data member.

TNcbi4na & SetNcbi4na(void)

Select the variant.

void SetMol(TMol value)

Assign a value to Mol data member.

@ eRepr_raw

continuous sequence

@ eMol_na

just a nucleic acid

unsigned int

A callback function used to compare two keys in a database.

const struct ncbi::grid::netcache::search::fields::SIZE size

const CharType(& source)[N]

Static variables safety - create on demand, destroy on application termination.

Multi-threading – mutexes; rw-locks; semaphore.

ESeqDBAllocType

Certain methods have an "Alloc" version.

ESeqDBIdType SeqDB_SimplifySeqid(CSeq_id &bestid, const string *acc, Int8 &num_id, string &str_id, bool &simpler)

Seq-id simplification.

const int kSeqDBNuclNcbiNA8

Used to request ambiguities in Ncbi/NA8 format.

ESeqDBIdType SeqDB_SimplifyAccession(const string &acc, Int8 &num_id, string &str_id, bool &simpler)

String id simplification.

const int kSeqDBNuclBlastNA8

Used to request ambiguities in BLAST/NA8 format.

ESeqDBIdType

Various identifier formats used in Id lookup.

@ eStringId

Each PIG identifier refers to exactly one protein sequence.

@ eTiId

Genomic ID is a relatively stable numeric identifier for sequences.

@ ePigId

Trace ID is a numeric identifier for Trace sequences.

@ eHashId

Some sequence sources uses string identifiers.

@ eOID

Lookup from sequence hash values to OIDs.

T SeqDB_GetStdOrd(const T *stdord_obj)

Read a network order integer value.

The SeqDB oid filtering layer.

static bool s_SeqDB_SeqIdIn(const list< CRef< CSeq_id > > &seqids, const CSeq_id &target)

Search for a Seq-id in a list of Seq-ids.

bool s_IncludeDefline_Taxid(const CBlast_def_line &def, const set< TTaxId > &user_tax_ids)

static void s_SeqDBMapNA2ToNA4(const char *buf2bit, vector< char > &buf4bit, int base_length)

Convert sequence data from NA2 to NA4 format.

Uint4 s_ResVal(const vector< Int4 > &ambchars, Uint4 i)

Get ambiguous residue value (old version)

void SeqDB_UnpackAmbiguities(const CTempString &sequence, const CTempString &ambiguities, string &result)

Unpack an ambiguous nucleotide sequence.

static void s_SeqDBRebuildDNA_NA8(char *seq, const vector< Int4 > &amb_chars, const SSeqDBSlice &region)

Rebuild an ambiguous region from sequence and ambiguity data.

Uint4 s_ResLenOld(const vector< Int4 > &ambchars, Uint4 i)

Get ambiguous region length (old version)

Uint4 s_ResLenNew(const vector< Int4 > &ambchars, Uint4 i)

Get length of ambiguous region (new version)

set< pair< int, int > > TRangeVector

List of offset ranges as begin/end pairs.

bool s_IncludeDefline_NegativeTaxid(const CBlast_def_line &def, const set< TTaxId > &user_tax_ids)

Uint4 s_ResPosNew(const vector< Int4 > &ambchars, Uint4 i)

Get position of ambiguous region (new version)

static void s_SeqDBRebuildDNA_NA4(vector< char > &buf4bit, const vector< Int4 > &amb_chars)

Rebuild an ambiguous region from sequence and ambiguity data.

static void s_SeqDBWriteSeqDataProt(CSeq_inst &seqinst, const char *seq_buffer, int length)

Store protein sequence data in a Seq-inst.

static void s_GetBioseqTitle(CRef< CBlast_def_line_set > deflines, string &title)

Get the title string for a CBioseq.

static void s_SeqDBFitsInFour(T id)

static void s_SeqDBMapNA2ToNA4Setup(TTable &translated)

Build NA2 to NcbiNA4 translation table.

unsigned SeqDB_ncbina8_to_blastna8[]

static CRef< CBlast_def_line_set > s_OssToDefline(const CUser_field::TData::TOss &oss)

Efficiently decode a Blast-def-line-set from binary ASN.1.

static void s_SeqDBMapNA2ToNA8Setup(TTable &translated)

Build NA2 to Ncbi-NA8 translation table.

Uint4 s_ResPosOld(const vector< Int4 > &ambchars, Uint4 i)

Get ambiguous residue value (old version)

static void s_SeqDBMapNcbiNA8ToBlastNA8(char *buf, const SSeqDBSlice &range)

Convert sequence data from Ncbi-NA8 to Blast-NA8 format.

static void s_SeqDBMaskSequence(char *seq, CSeqDB::TSequenceRanges *masks, char mask_letter, const SSeqDBSlice &range)

static void s_SeqDBWriteSeqDataNucl(CSeq_inst &seqinst, const char *seq_buffer, int length)

Store non-ambiguous nucleotide sequence data in a Seq-inst.

CRef< CBlast_def_line_set > s_ExtractBlastDefline(const T &bioseq)

vector< Uint1 > TTable

Translation table type.

static void s_SeqDBMapNA2ToNA8(const char *buf2bit, char *buf8bit, const SSeqDBSlice &range)

Convert sequence data from NA2 to NA8 format.

bool s_IncludeDefline_MaskFilter(const CBlast_def_line &def, Uint8 mask)

Defines database volume access classes.

List of sequence offset ranges.

OID-Range type to simplify interfaces.

int begin

First oid in range.

int end

OID after last included oid.

string common_name

Common name, such as "noisy night monkey".

string scientific_name

Scientific name, such as "Aotus vociferans".

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4