RetroSearch Browse

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

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/seq__dict_8hpp_source.html below:

NCBI C++ ToolKit: include/gui/utils/seq_dict.hpp Source File

1 #ifndef __GUI_SEQ_DICTIONARY_HPP_ 2 #define __GUI_SEQ_DICTIONARY_HPP_ 53 #ifndef __USE_BM_XOR_COMPRESSION__ 54 #define __USE_BM_XOR_COMPRESSION__ 69 'A'

'C'

'G'

'T'

'N'

'B'

'D'

'E'

'F'

'H'

'I'

'J'

'K'

70 'L'

'M'

'O'

'P'

'Q'

'R'

'S'

'U'

'V'

'W'

'X'

'Y'

'Z'

105 template

typename

Alphabet = TSeqAlphabet<true>>

120 if

(IsRegion(index) ==

false

) {

126 auto

it = m_Terms.get_const_iterator(

offset

);

127 for

(

size_t i

= 0;

len

&& it.valid(); ++

) {

139 return

x_GetOffset(index) == 0 && x_GetLen(index) > 0;

146 return len

== 0 ? 1 :

len

;

160 #ifdef __USE_BM_XOR_COMPRESSION__ 164

m_Terms.optimize(TB);

165

sv_serializer.

serialize

(m_Terms, sv_lay);

166 const unsigned char

buf

= sv_lay.

data

();

168 if

(!os.write(

reinterpret_cast<const char

>

(&sz),

sizeof

(sz)))

170 if

(sz && !os.write((

char

*)&

buf

[0], sz))

186

sv_deserializer.

deserialize

(m_Terms, (

const unsigned char

*)&

data

[pos]);

219 return

x_SetIndex(char_code, 0);

225 return

x_SetIndex(0,

len

);

251 template

typename

Alphabet = TSeqAlphabet<true>>

272 if

(seq.length() == 1) {

273

index = x_AddChar(seq[0]);

276

m_CheckSum.Reset(ncbi::CChecksum::eCRC32);

277

m_CheckSum.AddLine(seq);

278 auto crc32

= m_CheckSum.GetChecksum();

279 if

(m_SeqPos.test(

crc32

)) {

284 if

(x_FindSequence(seq, pos)) {

285

index = TSeqDict::x_SetIndex(pos + 1, seq.length());

287

index = x_AddSequence(seq);

290

m_SeqPos.set(

crc32

);

291

index = x_AddSequence(seq);

300 return

TSeqDict::x_SetIndexAsRegion(

len

);

306

unique_ptr<TSeqDict> seqdict(

new TSeqDict

());

307 auto

sz = m_SearchStr.size();

309

seqdict->m_Terms[0] = 0;

310 while

(curr_pos < sz) {

311

vector<unsigned>

buffer

(10 * 1024 * 1024 );

313 for

(;

buffer

.size() && curr_pos < sz; ++

, ++curr_pos) {

314 buffer

[

] = m_Coder[(unsigned)m_SearchStr[curr_pos]];

316

seqdict->m_Terms.import_back(&

buffer

[0],

);

325 auto

seq_sz = seq.size();

328

m_SearchStr.push_back(

'\0'

);

329 auto

ptr = strstr(&m_SearchStr[0], seq.c_str());

330

m_SearchStr.pop_back();

332

pos = ptr - &m_SearchStr[0];

341 auto code

= m_Coder[(unsigned)

];

343 throw

runtime_error(

"The sequence contains bad symbol '"

string

(1,

) +

"'"

);

344 return

TSeqDict::x_SetIndexAsChar(

code

);

350 auto

seq_size = seq.size();

354

vector<unsigned> seq_v(seq_size);

355 for

(

size_t i

= 0;

< seq_size; ++

) {

356 auto code

= m_Coder[(unsigned)seq[

]];

357 if

(

code

kBAD_CODE

)

throw

runtime_error(

"The sequence contains bad symbol '"

string

(1, seq[

]) +

"'"

);

360

idx = TSeqDict::x_SetIndex(m_CurrPos, seq_size);

361

m_CurrPos += seq_size;

362 copy

(seq.begin(), seq.end(), back_inserter(m_SearchStr));

371 size_t

m_CurrPos = 0;

Compressed bit-vector bvector<> container, set algebraic methods, traversal iterators.

#define BM_DECLARE_TEMP_BLOCK(x)

Algorithms for bit ranges and intervals.

Sparse constainer sparse_vector<> for integer types using bit-transposition transform.

Algorithms for bm::sparse_vector.

Compressed sparse container rsc_sparse_vector<> for integer types.

Serialization for sparse_vector<>

string sparse vector based on bit-transposed matrix

Checksum and hash calculation classes.

ncbi::CChecksum m_CheckSum

unique_ptr< TSeqDict > Build()

Builds the sequence dictionary from previously added sequences.

vector< unsigned > m_Coder

TIndex AddRegion(uint32_t len)

Create Region index.

TSeqDict::svector_u32 svector_u32

bool x_FindSequence(const string &seq, unsigned &pos)

TIndex x_AddSequence(const string &seq)

if necessary adds a ductionary sequence and returns its index

CSeqDictionary< Alphabet > TSeqDict

TIndex AddSequence(const string &seq)

Add sequence and returns its index.

vector< char > m_SearchStr

static bool IsRegion(TIndex index)

Checks if index references an actual sequence or it just contains a length of unaligned region.

string & GetSequence(TIndex index, string &seq) const

returns Sequence by Index

size_t Deserialize(const char *data)

Deserialization from string starting from pos returns number of deserilized bytes.

static TIndex x_SetIndexAsChar(uint32_t char_code)

static TIndex x_SetIndex(uint32_t offset, uint32_t len)

Index mask functions.

static uint32_t x_GetOffset(TIndex index)

static size_t GetSeqLength(TIndex index)

Returns the sequence length encoded in the index.

bool Serialize(ostream &os)

Serialization to ostream.

bm::sparse_vector< unsigned, bm::bvector<> > svector_u32

static uint32_t x_GetLen(TIndex index)

unsigned long long TIndex

static TIndex x_SetIndexAsRegion(uint32_t len)

sparse vector de-serializer

void deserialize(SV &sv, const unsigned char *buf, bool clear_sv=true)

Serialize sparse vector into a memory buffer(s) structure.

void serialize(const SV &sv, sparse_vector_serial_layout< SV > &sv_layout)

Serialize sparse vector into a memory buffer(s) structure.

void enable_xor_compression() noexcept

Enable XOR compression on vector serialization.

succinct sparse vector with runtime compression using bit-slicing / transposition method

@ BM_GAP

GAP compression is ON.

static const BitmapCharRec *const chars[]

void copy(Njn::Matrix< S > *matrix_, const Njn::Matrix< T > &matrix0_)

static const unsigned kBAD_CODE

layout class for serialization buffer structure

const unsigned char * data() const noexcept

Return serialization buffer pointer.

size_t size() const noexcept

return current serialized size

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