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

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/dbindex__factory_8cpp_source.html below:

NCBI C++ ToolKit: src/algo/blast/dbindex/dbindex_factory.cpp Source File

std::ostringstream os;

<

word_t >

{ os.write(

*

( &word ),

(

) ); }

objects::CSeqVector

;

objects::CSeq_loc::TPacked_int::Tdata

;

TSeqStore::size_type

= 100*1024*1024;

TSeqStore::size_type

= 10*1024*1024;

objects::CSeq_loc::TPacked_int::Tdata

;

( loc->IsPacked_int() ) {

&( loc->GetPacked_int().Get() ) );

TLocsVec::const_iterator

;

TLocs::const_iterator

;

std::vector< SSeqSeg >

;

= (*vit_)->begin();

(

!= (*vit_)->end() ) {

= (*it_)->GetFrom();

= (*it_)->GetTo() + 1;

( ++it_ != (*vit_)->end() ) {

start_ = (*it_)->GetFrom();

stop_ = (*it_)->GetTo() + 1;

( Good() ) it_ = (*vit_)->begin();

}

( notdone && pos < stop_ );

( c_locs_.empty() )

;

( vit_ != c_locs_.begin() && (*vit_)->empty() ) {

( !(*vit_)->empty() ) {

it_ = (*vit_)->end();

start_ = (*it_)->GetFrom();

stop_ = (*it_)->GetTo() + 1;

vit_ = c_locs_.end();

( it_ != (*vit_)->begin() ) {

start_ = (*it_)->GetFrom();

stop_ = (*it_)->GetTo() + 1;

( vit_ == c_locs_.begin() ) {

( vit_ != c_locs_.begin() && (*vit_)->empty() ) {

( !(*vit_)->empty() ) {

it_ = (*vit_)->end();

start_ = (*it_)->GetFrom();

stop_ = (*it_)->GetTo() + 1;

( Good() && pos >= stop_ ) Advance();

( !Good() )

;

pos >= start_;

entry->Which() != objects::CSeq_entry_Base::e_Seq ) {

);

objects::CScope scope( *

);

objects::CSeq_entry_Handle seh = scope.AddTopLevelSeqEntry( *entry );

objects::CBioseq_Handle bsh = seh.GetSeq();

= bsh.GetSeqVector( objects::CBioseq_Handle::eCoding_Iupac );

pos =

(idstr.find_first_of(

));

idstr = idstr.substr( 0, pos );

=

;

( TMask::const_iterator mask_it =

.begin();

mask_it !=

.end(); ++mask_it ) {

chunks_.size()*

(

));

( TSubjects::const_iterator cit =

.begin();

( TChunks::const_iterator cit = chunks_.begin();

cit != chunks_.end(); ++cit ) {

TSeqStore::size_type seq_off )

( chunk_start >=

.size() ) {

chunk_len = chunk_end - chunk_start;

( chunk_len > 0 ) {

=

, in1;

(

pos = chunk_start;

pos < chunk_end; ++pos,

= (

+ 1)%

) {

( segs.empty() ) {

segs.push_back(

( 0 ) );

segs.rbegin()->stop_ = pos - chunk_start;

}

( !in1 &&

) {

segs.push_back(

( pos - chunk_start ) );

( segs.empty() ) {

segs.push_back(

( 0 ) );

segs.rbegin()->stop_ = chunk_end - chunk_start;

*

.rbegin() =

(chunks_.size());

TSeqStore::size_type newsize =

(TSeqStore::size_type)(chunks_[

].seq_start_);

cur_lid_len_( 0 ), offset_bits_( 16 )

starting = (this->

== 0);

TBase::TSeqStore::size_type seq_off =

this->

.rbegin()->seq_start_

TBase::TSeq::size_type seqlen = this->

.size();

chunk_len = chunk_end - chunk_start;

(

.size() >= lid_limit ) {

( starting && seqlen > 0 ) {

(

pos = 0; pos < seqlen; ++pos,

= (

+ 1)%

) {

accum = (accum << 2) +

;

accum <<= (

-

)*2;

TLIdMap::const_reverse_iterator iter =

.rbegin();

( iter !=

.rend() && iter->seq_start_ > soff ) ++iter;

( iter->seq_start_ <= soff );

off += (soff - iter->seq_start_)*

;

TLIdMap::const_reverse_iterator iter =

.rbegin();

( iter !=

.rend() && iter->seq_start_ > soff ) ++iter;

( iter->seq_start_ <= soff );

off += (soff - iter->seq_start_)*

;

( TLengthTable::const_iterator it =

.begin();

( TLIdMap::const_iterator it =

.begin();

( d == 0 )

;

( d->

!= 0 ) d = d->

;

{

!(rhs == lhs); }

( newsize == 0 ) {

(

< newsize ) {

m =

;

(

=

;

> m; --

)

( (*cit)%

== 0 ) { skip =

;

; }

( !skip && (*cit)%m == 0 )

( os, *cit );

->SetDataPool( pool );

( THashTable::const_iterator cit =

.begin();

( cit->Size() > 0 ) ++this->

;

std::unique_ptr< CNcbiOfstream >

;

nmer = 0;

( THashTable::const_iterator cit =

.begin();

( cit->Size() != 0 ) {

( cit->Size() != 0 )

( stat && cit->Size() > 0 ) {

*

<<

<< setw( 10 ) << nmer

<<

<< dec << cit->Size() << endl;

( THashTable::const_iterator cit =

.begin();

end_diff = stop - curr;

[(THashTable::size_type)nmer].AddData(

[(THashTable::size_type)nmer].AddData(

letter_mask = 0x3;

= 0;

(

curr = start; curr < stop; ++curr, ++

) {

nmer = ((nmer<<2)&nmer_mask) +

;

( TSeqInfo::TSegs::const_iterator it = sinfo.

.begin();

it != sinfo.

.end(); ++it ) {

sinfo.

, it->start_, it->stop_ );

( THashTable::iterator it =

.begin();

(

= 0;

< 7; ++

)

( os, (

)0 );

(

= 0;

< 7; ++

)

( os, (

)0 );

, oname, start, start_chunk, stop, stop_chunk, options );

, oname, start, start_chunk, stop, stop_chunk, options );

std::unique_ptr< COffsetList::CDataPool > pool(

TOffsetData offset_data( subject_map, options, pool.get() );

vector< string > idmap;

(

< stop ) {

idstr = subject_map.NewSequenceInit( *sd, start_chunk );

idmap.push_back( idstr );

( subject_map.AddSequenceChunk( overflow ) ) {

offset_data.Update();

std::cerr <<

<<

<< std::endl;

((

)

(

))*offset_data.total();

subject_map.RollBack();

offset_data.Update();

subject_map.Commit();

stop = start + subject_map.GetLastSequence() - 1;

stop_chunk = subject_map.GetLastSequenceChunk();

subject_map.Commit();

std::ostringstream os;

os <<

<< start + subject_map.GetLastSequence() - 1

<<

<< subject_map.GetLastSequenceChunk()

std::ostringstream os;

os <<

<< subject_map.total() +

(

)*offset_data.total()

<<

<< std::endl;

( os, options, start, start_chunk, stop, stop_chunk );

offset_data.Save( os );

subject_map.Save( os );

( options.

) {

mapname = oname +

;

!= idmap.end(); ++

) {

maps << *

<<

;

, oname, start, start_chunk,

stop, stop_chunk, options );

( fname, oname, start, stop,

, options );

TIndex_Impl::Create(

, oname, start, start_chunk, stop, stop_chunk, options );

Structures and functions prototypes used for BLAST gapped extension.

Structures and API used for saving BLAST hits.

ncbi::TMaskedQueryRegions mask

Types of exception the indexing library can throw.

Index factory implementation.

static void Create(CSequenceIStream &input, const std::string &oname, TSeqNum start, TSeqNum start_chunk, TSeqNum &stop, TSeqNum &stop_chunk, const SOptions &options)

Create an index implementation object.

virtual ~CDbIndex_Factory()

Object destructor.

static const Uint8 MEGABYTE

Obvious...

static void SaveHeader(CNcbiOstream &os, const SOptions &options, TSeqNum start, TSeqNum start_chunk, TSeqNum stop, TSeqNum stop_chunk)

Save the index header.

static void do_create(CSequenceIStream &input, const std::string &oname, TSeqNum start, TSeqNum start_chunk, TSeqNum &stop, TSeqNum &stop_chunk, const SOptions &options)

Called by CDbIndex::Create() (should be merged?).

static void do_create_1_2(CSequenceIStream &input, const std::string &oname, TSeqNum start, TSeqNum start_chunk, TSeqNum &stop, TSeqNum &stop_chunk, const SOptions &options)

Another forward from do_create() (should be merged?).

Base class providing high level interface to index objects.

Uint4 TWord

Type representing main memory unit of the index structure.

static const unsigned char VERSION

Index version that this library handles.

static void MakeIndex(const std::string &fname, const std::string &oname, TSeqNum start, TSeqNum start_chunk, TSeqNum &stop, TSeqNum &stop_chunk, const SOptions &options)

Create an index object.

CSequenceIStream::TStreamPos TSeqNum

Type used to enumerate sequences in the index.

A class responsible for creation and management of Nmer offset lists.

CSubjectMap_Factory TSubjectMap

Rename for consistency.

std::vector< TOffsetList > THashTable

Type used for mapping Nmer values to corresponding offset lists.

TWord total_

Current size of the structure in bytes.

TSubjectMap::TSeqInfo TSeqInfo

Forwarding from TSubjectMap.

void AddSeqInfo(const TSeqInfo &sinfo)

Update offset lists with information corresponding to the given sequence.

void Save(CNcbiOstream &os)

Save the offset lists into the binary output stream.

void AddSeqSeg(const Uint1 *seq, TWord seqlen, TSeqPos start, TSeqPos stop)

Update offset lists with information corresponding to the given valid segment of a sequence.

CDbIndex::TSeqNum TSeqNum

Forwarding from CDbIndex.

TSubjectMap & subject_map_

Instance of subject map structure.

void EncodeAndAddOffset(TWord nmer, TSeqPos start, TSeqPos stop, TSeqPos curr, TWord offset)

Encode the offset data and add to the offset list corresponding to the given Nmer value.

unsigned long code_bits_

Number of bits to encode special offset prefixes.

THashTable hash_table_

Mapping from Nmer values to the corresponding offset lists.

TSeqNum last_seq_

Logical oid of last processed sequence.

const CDbIndex::SOptions & options_

Index options.

void Truncate()

Truncate the offset lists according to the information from the subject map.

unsigned long hkey_width_

Nmer width in bases.

COffsetList TOffsetList

Type used for individual offset lists.

COffsetData_Factory(TSubjectMap &subject_map, const CDbIndex::SOptions &options, COffsetList::CDataPool *pool)

Object constructor.

const TWord total() const

Get the total memory usage by offset lists in bytes.

void Update()

Bring offset lists up to date with the corresponding subject map instance.

static const Uint4 BLOCK_SIZE

vector< SDataUnit > TBlock

CDataIterator & operator--()

CDataIterator & operator++()

friend bool operator!=(const CDataIterator &rhs, const CDataIterator &lhs)

friend bool operator==(const CDataIterator &rhs, const CDataIterator &lhs)

CDataIterator(SDataUnit *cunit, Uint4 cindex, Uint4 size)

CDataIterator const_iterator

void SetDataPool(CDataPool *pool)

const_iterator end() const

void resize(Uint4 newsize)

const_iterator begin() const

void push_back(const TWord &d)

Type representing an offset list corresponding to an Nmer.

CData TData

Type used to store offset list data.

TWord Size() const

Return the size of the offset list in words.

void SetIndexParams(const TOptions &options)

Set the index creation parameters.

unsigned long min_offset_

Minimum offset used by the index.

void SetDataPool(CDataPool *pool)

void AddData(TWord item, TWord &total)

Add an offset to the list.

void Save(CNcbiOstream &os) const

Save the offset list.

TData data_

Offset list data storage.

unsigned long mult_

Max multiple to use in list pre-ordering.

static const Uint4 DATA_UNIT_SIZE

void TruncateList(TWord offset, TWord &total)

Truncate the list to the value of offset.

Sequence stream for reading FASTA formatted files.

Class used to abstract reading nucleotide sequences from various sources.

TSeqData::TMask TMask

Public alias for type containing masking info.

A helper class used when creating internal set masked locations in the process of converting the sequ...

TLocs::const_iterator it_

State of the iterator over *vit_ (inner iteration).

bool In(TSeqPos pos)

Check if a point falls within the intervals stored in the object.

TSeqPos start_

Left end of *it_.

objects::CSeq_loc::TPacked_int::Tdata TLocs

See documentation for CSubjectMap_Factory_Base::TLocs.

std::vector< const TLocs * > TLocsVec

Collection of TLocs extracted from CSequenceIStream::TSeqData.

void Init()

Initialize the iterators after the masked locations are added.

bool Good() const

Check if the end of iteration has been reached.

void Advance()

Iteration step.

void Adjust(TSeqPos pos)

Backtrack to the first interval to the left of pos or to the beginning, if not possible.

TLocsVec c_locs_

Container with sets of masked intervals.

bool Retreat()

Iteration step backwords.

TSeqPos stop_

One past the right end of *it_.

CMaskHelper()

Default object constructor.

void Add(const TMask::value_type &loc)

Add a set of masked intervals.

TLocsVec::const_iterator vit_

State of the iterator over c_locs_ (outer iteration).

CSequenceIStream::TMask TMask

forwarded type

Part of the CSubjectMap_Factory class that is independent of template parameters.

CSequenceIStream::TMask TMask

Masking information.

TSeqStore seq_store_

Container for storing the packed sequence data.

TSeqNum committed_

Logical number of the last committed sequence.

unsigned long report_level_

Level of reporting requested by the user.

TSeqStore::size_type ss_cap_

Current seq_store capacity.

CRef< CMaskHelper > mask_helper_

Auxiliary object used to compute unmasked parts of the sequences.

CDbIndex::TSeqNum TSeqNum

forwarded type

TSeqNum last_chunk_

Logical number of last processed sequence.

unsigned long chunk_size_

Maximum internal sequence size.

string extractSeqVector(TSeqData &sd)

Helper function used to extract CSeqVector instance from a TSeqData object.

unsigned long chunk_overlap_

Length of overlap between consequtive chunks of one sequence.

objects::CSeq_loc::TPacked_int::Tdata TLocs

The inner most type needed to access mask data in the representation returned by ReadFasta().

static const TSeqStore::size_type SS_THRESH

Threshold for the difference between seqstore size and capacity.

unsigned long stride_

Stride selected in index creation options.

objects::CSeqVector TSeq

Sequence data without masking.

unsigned long min_offset_

Minimum offset value used by the index.

const Uint1 * seq_store_start() const

Get the start of the compressed sequence storage space.

std::vector< Uint1 > TSeqStore

Container type used to store compressed sequence information.

static const TSeqStore::size_type SS_INCR

Increment used to increase seqstore capacity.

string NewSequenceInit(TSeqData &sd, TSeqNum start_chunk)

Start processing of the new input sequence.

CSequenceIStream::TSeqData TSeqData

forwarded type

TSubjects subjects_

Mapping from subject oid to chunk information.

std::vector< TSeqNum > TSubjects

Type for storing mapping from subject oids to the chunk numbers.

CRef< objects::CObjectManager > om_

Reference to the ObjectManager instance.

TSeq c_seq_

Sequence data of the sequence currently being processed.

TSeqNum c_chunk_

Current chunk number of the sequence currently being processed.

CSubjectMap_Factory_Base(const TOptions &options)

Object constructor.

To be merged with CSubjectMap_Factory_Base.

bool AddSequenceChunk(TSeqStore::size_type seq_off)

Append the next chunk of the input sequence currently being processed to the subject map.

TSeqNum GetLastSequenceChunk() const

Get the oid of the last chunk number of the last processed sequence.

CSubjectMap_Factory_TBase(const TOptions &options)

Object constructor.

void Commit()

Finalize processing of the current input sequence.

void Save(CNcbiOstream &os) const

Save the subject map and sequence info.

TSeqNum LastGoodSequence() const

Get the internal oid of the last valid sequence.

void RollBack()

Revert to the state before the start of processing of the current input sequence.

TChunks chunks_

Collection of sequence chunks (or logical sequences).

TSeqNum GetLastSequence() const

Get the oid of the last processed sequence.

std::vector< SSeqInfo > TChunks

Type for the collection of sequence chunks.

const TSeqInfo * GetSeqInfo(TSeqNum snum) const

Get the chunk info by internal oid.

SSeqSeg TSeqSeg

Type definition for external users.

SSeqInfo TSeqInfo

Type definition for external users.

TWord total() const

Get the total memory usage by the subject map in bytes.

To be merged with CSubjectMap_Factory_Base.

Uint1 offset_bits_

Number of bits used to encode offset.

string NewSequenceInit(TSeqData &sd, TSeqNum start_chunk)

Start processing of the new input sequence.

vector< TWord > TLengthTable

Type of lengths table.

TSeqPos cur_lid_len_

Current length of local sequence.

TLengthTable lengths_

The table of subject sequence lengths.

void Save(CNcbiOstream &os) const

Save the subject map and sequence info.

TLIdMap lid_map_

Maping of local sequence ids to chunks.

vector< SLIdMapElement > TLIdMap

Type of mapping of local sequence ids to chunks.

TWord MakeOffset(const Uint1 *seq, TSeqPos off) const

Encode an offset given a pointer to the compressed sequence data and relative offset.

CSubjectMap_Factory_TBase TBase

Base class.

bool CheckOffset(const Uint1 *seq, TSeqPos off) const

Check if index information should be produced for this offset.

CSubjectMap_Factory(const TOptions &options)

Object constructor.

bool AddSequenceChunk(bool &overflow)

Append the next chunk of the input sequence currently being processed to the subject map.

Type representing subject map data.

static const int chunk_size

const unsigned long WIDTH_32

32-bit index.

const unsigned long OFFSET_COMBINED

Combination of chunk number and chunk-based offset.

unsigned long GetMinOffset(unsigned long stride)

Compute the minimum offset value needed encode offsets based on stride.

const unsigned long UNCOMPRESSED

No compression.

unsigned long GetCodeBits(unsigned long stride)

Compute the number of bits to encode special offsets based on stride.

Uint1 base_value(objects::CSeqVectorTypes::TResidue r)

Convertion from IUPACNA to NCBI2NA (+1).

void WriteWord(CNcbiOstream &os, word_t word)

Write a word into a binary output stream.

static const unsigned long CR

CDbIndex::TWord TWord

Alias for CDbIndex::TWord type.

const std::string to_hex_str(TWord word)

Convert an integer to hex string representation.

CDbIndex::TSeqNum TSeqNum

Forwarding declarations for convenience.

objects::CSeqVectorTypes::TResidue TResidue

unsigned int TSeqPos

Type for sequence locations and lengths.

#define NCBI_THROW(exception_class, err_code, message)

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

NCBI_XOBJUTIL_EXPORT string GetTitle(const CBioseq_Handle &hnd, TGetTitleFlags flags=0)

TObjectType * GetNonNullPointer(void)

Get pointer value and throw a null pointer exception if pointer is null.

TObjectType * GetPointerOrNull(void) THROWS_NONE

Get pointer value.

uint8_t Uint1

1-byte (8-bit) unsigned integer

uint32_t Uint4

4-byte (32-bit) unsigned integer

uint64_t Uint8

8-byte (64-bit) unsigned integer

#define END_NCBI_SCOPE

End previously defined NCBI scope.

#define END_SCOPE(ns)

End the previously defined scope.

#define BEGIN_NCBI_SCOPE

Define ncbi namespace.

#define BEGIN_SCOPE(ns)

Define a new scope.

IO_PREFIX::ofstream CNcbiOfstream

Portable alias for ofstream.

IO_PREFIX::ostream CNcbiOstream

Portable alias for ostream.

static void hex(unsigned char c)

double value_type

The numeric datatype used by the parser.

#define ASSERT

macro for assert.

std::istream & in(std::istream &in_, double &x_)

double r(size_t dimension_, const Int4 *score_, const double *prob_, double theta_)

CSequenceIStream::TSeqData TSeqData

Simple record type used to specify index creation parameters.

bool legacy

Indicator of the legacy index format.

unsigned long max_index_size

Maximum index size in megabytes.

unsigned long chunk_size

Long sequences are split into chunks of this size.

std::string stat_file_name

File to write index statistics into.

unsigned long ws_hint

Most likely word size to use for searches.

bool idmap

Indicator of the index map creation.

unsigned long hkey_width

Width of the hash key in bits.

unsigned long stride

Stride to use for stored database locations.

TWord data[DATA_UNIT_SIZE]

Type containing the sequence itself along with the masking information.

CRef< objects::CSeq_entry > seq_entry_

Sequence data.

TMask mask_locs_

Masked portion of the sequence.

Element of mapping of local sequence ids to chunks.

TSeqNum start_

First chunk.

TSeqPos seq_start_

Start of the combined sequence in seq_store.

TSeqNum end_

One past the last chunk.

TSeqPos seq_end_

End of the combined sequence in seq_store.

Type used to store a masked segment internally.

TSeqPos stop_

One past the end of the segment.

SSeqSeg(TSeqPos start, TSeqPos stop=0)

Object constructor.

TSeqPos start_

Start of the segment.

Information about the sequence chunk.

SSeqInfo(TWord start=0, TWord len=0, const TSegs &segs=TSegs())

Object constructor.

TSegs segs_

Valid intervals, i.e.

TWord seq_start_

Start of the compressed sequence data.

TWord len_

Sequence length.

std::vector< SSeqSeg > TSegs

Type containing the valid intervals.

static Uint4 letter(char c)

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