#include <objtools/blast/seqdb_reader/impl/seqdbisam.hpp>

Inheritance diagram for CSeqDBIsam:

Collaboration diagram for CSeqDBIsam:

Classes
class	SIsamKey
	Stores a key for an ISAM file. More...

Public Types
enum	EIsamDbType { eNumeric = 0 , eNumericNoData = 1 , eString = 2 , eStringDatabase = 3 , eStringBin = 4 , eNumericLongId = 5 }
	Types of database this class can access. More...

typedef CSeqDBGiList::SGiOid	TGiOid
	Import the type representing one GI, OID association. More...

typedef CSeqDBAtlas::TIndx	TIndx
	Type which is large enough to span the bytes of an ISAM file. More...

typedef int	TOid
	This class works with OIDs relative to a specific volume. More...

typedef Int8	TTi
	PIG identifiers for numeric indices over protein volumes. More...

typedef Int8	TId
	Type large enough to hold any numerical ID. More...

Public Types inherited from CObject
enum	EAllocFillMode { eAllocFillNone = 1 , eAllocFillZero , eAllocFillPattern }
	Control filling of newly allocated memory. More...

typedef CObjectCounterLocker	TLockerType
	Default locker type for CRef. More...

typedef atomic< Uint8 >	TCounter
	Counter type is CAtomiCounter. More...

typedef Uint8	TCount
	Alias for value type of counter. More...

Public Member Functions
	CSeqDBIsam (CSeqDBAtlas &atlas, const string &dbname, char prot_nucl, char file_ext_char, ESeqDBIdType ident_type)
	Constructor. More...

	~CSeqDBIsam ()
	Destructor. More...

bool	PigToOid (TPig pig, TOid &oid)
	PIG translation. More...

bool	IdToOid (Int8 id, TOid &oid)
	GI or TI translation. More...

void	IdsToOids (int vol_start, int vol_end, CSeqDBGiList &ids)
	Translate Gis and Tis to Oids for the given ID list. More...

void	IdsToOids (int vol_start, int vol_end, CSeqDBNegativeList &ids)
	Compute list of included OIDs based on a negative ID list. More...

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

bool	SeqidToOid (const string &acc, TOid &oid)
	Seq-id translation. More...

void	HashToOids (unsigned hash, vector< TOid > &oids)
	Sequence hash lookup. More...

void	UnLease ()
	Return any memory held by this object to the atlas. More...

void	GetIdBounds (Int8 &low_id, Int8 &high_id, int &count)
	Get Numeric Bounds. More...

void	GetIdBounds (string &low_id, string &high_id, int &count)
	Get String Bounds. More...

Public Member Functions inherited from CObject
	CObject (void)
	Constructor. More...

	CObject (const CObject &src)
	Copy constructor. More...

virtual	~CObject (void)
	Destructor. More...

CObject &	operator= (const CObject &src) THROWS_NONE
	Assignment operator. More...

bool	CanBeDeleted (void) const THROWS_NONE
	Check if object can be deleted. More...

bool	IsAllocatedInPool (void) const THROWS_NONE
	Check if object is allocated in memory pool (not system heap) More...

bool	Referenced (void) const THROWS_NONE
	Check if object is referenced. More...

bool	ReferencedOnlyOnce (void) const THROWS_NONE
	Check if object is referenced only once. More...

void	AddReference (void) const
	Add reference to object. More...

void	RemoveReference (void) const
	Remove reference to object. More...

void	ReleaseReference (void) const
	Remove reference without deleting object. More...

virtual void	DoNotDeleteThisObject (void)
	Mark this object as not allocated in heap – do not delete this object. More...

virtual void	DoDeleteThisObject (void)
	Mark this object as allocated in heap – object can be deleted. More...

void *	operator new (size_t size)
	Define new operator for memory allocation. More...

void *	operator new[] (size_t size)
	Define new[] operator for 'array' memory allocation. More...

void	operator delete (void *ptr)
	Define delete operator for memory deallocation. More...

void	operator delete[] (void *ptr)
	Define delete[] operator for memory deallocation. More...

void *	operator new (size_t size, void *place)
	Define new operator. More...

void	operator delete (void ptr, void place)
	Define delete operator. More...

void *	operator new (size_t size, CObjectMemoryPool *place)
	Define new operator using memory pool. More...

void	operator delete (void ptr, CObjectMemoryPool place)
	Define delete operator. More...

virtual void	DebugDump (CDebugDumpContext ddc, unsigned int depth) const
	Define method for dumping debug information. More...

Public Member Functions inherited from CDebugDumpable
	CDebugDumpable (void)

virtual	~CDebugDumpable (void)

void	DebugDumpText (ostream &out, const string &bundle, unsigned int depth) const

void	DebugDumpFormat (CDebugDumpFormatter &ddf, const string &bundle, unsigned int depth) const

void	DumpToConsole (void) const

Static Public Member Functions
static bool	IndexExists (const string &dbname, char prot_nucl, char file_ext_char)
	Check if a given ISAM index exists. More...

Static Public Member Functions inherited from CObject
static NCBI_XNCBI_EXPORT void	ThrowNullPointerException (void)
	Define method to throw null pointer exception. More...

static NCBI_XNCBI_EXPORT void	ThrowNullPointerException (const type_info &type)

static EAllocFillMode	GetAllocFillMode (void)

static void	SetAllocFillMode (EAllocFillMode mode)

static void	SetAllocFillMode (const string &value)
	Set mode from configuration parameter value. More...

Static Public Member Functions inherited from CDebugDumpable
static void	EnableDebugDump (bool on)

Private Types
enum	EErrorCode { eNotFound = 1 , eNoError = 0 , eBadVersion = -10 , eBadType = -11 , eWrongFile = -12 , eInitFailed = -13 }
	Exit conditions occurring in this code. More...

Private Member Functions
template<class T >
void	x_LoadIndex (CSeqDBFileMemMap &lease, vector< T > &keys, vector< TIndx > &offs)
	Load and extract all index samples into array at once. More...

template<class T >
void	x_LoadData (CSeqDBFileMemMap &lease, vector< T > &keys, vector< int > &vals, int num_keys, TIndx begin)
	Load and extract a data page into array at once. More...

template<class T >
void	x_TranslateGiList (int vol_start, CSeqDBGiList &gis)
	GiList Translation. More...

bool	x_IdentToOid (Int8 id, TOid &oid)
	Numeric identifier lookup. More...

EErrorCode	x_SearchIndexNumeric (Int8 Number, int Data, Uint4 Index, Int4 &SampleNum, bool &done)
	Index file search. More...

void	x_SearchNegativeMulti (int vol_start, int vol_end, CSeqDBNegativeList &gis, bool use_tis)
	Negative ID List Translation. More...

void	x_SearchNegativeMultiSeq (int vol_start, int vol_end, CSeqDBNegativeList &gis)

EErrorCode	x_SearchDataNumeric (Int8 Number, int Data, Uint4 Index, Int4 SampleNum)
	Data file search. More...

EErrorCode	x_NumericSearch (Int8 Number, int Data, Uint4 Index)
	Numeric identifier lookup. More...

EErrorCode	x_StringSearch (const string &term_in, vector< string > &term_out, vector< string > &value_out, vector< TIndx > &index_out)
	String identifier lookup. More...

EErrorCode	x_InitSearch (void)
	Initialize the search object. More...

int	x_GetPageNumElements (Int4 SampleNum, Int4 *Start)
	Determine the number of elements in the data page. More...

bool	x_SparseStringToOids (const string &acc, vector< int > &oids, bool adjusted)
	Lookup a string in a sparse table. More...

int	x_DiffCharLease (const string &term_in, CSeqDBFileMemMap &lease, const string &file_name, TIndx file_length, Uint4 at_least, TIndx KeyOffset, bool ignore_case)
	Find the first character to differ in two strings. More...

int	x_DiffChar (const string &term_in, const char begin, const char end, bool ignore_case)
	Find the first character to differ in two strings. More...

void	x_ExtractData (const char key_start, const char entry_end, vector< string > &key_out, vector< string > &data_out)
	Extract the data from a key-value pair in memory. More...

TIndx	x_GetIndexKeyOffset (TIndx sample_offset, Uint4 sample_num)
	Get the offset of the specified sample. More...

void	x_GetIndexString (TIndx key_offset, int length, string &prefix, bool trim_to_null)
	Read a string from the index file. More...

int	x_DiffSample (const string &term_in, Uint4 SampleNum, TIndx &KeyOffset)
	Find the first character to differ in two strings. More...

void	x_ExtractAllData (const string &term_in, TIndx sample_index, vector< TIndx > &indices_out, vector< string > &keys_out, vector< string > &data_out)
	Find matches in the given page of a string ISAM file. More...

void	x_ExtractPageData (const string &term_in, TIndx page_index, const char beginp, const char endp, vector< TIndx > &indices_out, vector< string > &keys_out, vector< string > &data_out)
	Find matches in the given memory area of a string ISAM file. More...

void	x_LoadPage (TIndx SampleNum1, TIndx SampleNum2, const char beginp, const char endp)
	Map a page into memory. More...

int	x_TestNumericSample (CSeqDBFileMemMap &index_lease, int index, Int8 key_in, Int8 &key_out, int &data_out)
	Test a sample key value from a numeric index. More...

void	x_GetNumericSample (CSeqDBFileMemMap &index_lease, int index, Int8 &key_out, int &data_out)
	Get a sample key value from a numeric index. More...

bool	x_FindInNegativeList (CSeqDBNegativeList &ids, int &index, Int8 key, bool use_tis)
	Find ID in the negative GI list using PBS. More...

bool	x_FindInNegativeList (CSeqDBNegativeList &ids, int &index, string key)

void	x_MapDataPage (int sample_index, int &start, int &num_elements, const void **data_page_begin)
	Map a data page. More...

void	x_GetDataElement (const void *dpage, int index, Int8 &key, int &data)
	Get a particular data element from a data page. More...

void	x_GetDataElement (const void *dpage, int index, string &key, int &data)

void	x_FindIndexBounds ()
	Find the least and greatest keys in this ISAM file. More...

bool	x_OutOfBounds (Int8 key)
	Check whether a numeric key is within this volume's bounds. More...

bool	x_OutOfBounds (string key)
	Check whether a string key is within this volume's bounds. More...

Uint8	x_GetNumericKey (const void *p)

int	x_GetNumericData (const void *p)

void	x_LoadStringData (const char *begin, string &key, int &data)

template<>
void	x_LoadIndex (CSeqDBFileMemMap &lease, vector< TGi > &keys, vector< TIndx > &offs)
	Load and extract all index samples into array at once. More...

template<>
void	x_LoadData (CSeqDBFileMemMap &lease, vector< TGi > &keys, vector< int > &vals, int num_keys, TIndx begin)
	Load and extract a data page into array at once. More...

template<>
void	x_LoadIndex (CSeqDBFileMemMap &lease, vector< string > &keys, vector< TIndx > &offs)

template<>
void	x_LoadData (CSeqDBFileMemMap &lease, vector< string > &keys, vector< int > &vals, int num_keys, TIndx begin)

Static Private Member Functions
static void	x_Lower (string &s)
	Converts a string to lower case. More...

static Int8	x_GetId (CSeqDBNegativeList &ids, int index, bool use_tis)
	Fetch a GI or TI from a GI list. More...

static string	x_GetId (CSeqDBNegativeList &ids, int index)

static void	x_MakeFilenames (const string &dbname, char prot_nucl, char file_ext_char, string &index_name, string &data_name)
	Make filenames for ISAM file. More...

Private Attributes
CSeqDBAtlas &	m_Atlas
	The memory management layer. More...

ESeqDBIdType	m_IdentType
	The type of identifier this class uses. More...

CSeqDBFileMemMap	m_IndexLease
	A persistent lease on the ISAM index file. More...

CSeqDBFileMemMap	m_DataLease
	A persistent lease on the ISAM data file. More...

int	m_Type
	The format type of database files found (eNumeric or eString). More...

string	m_DataFname
	The filename of the ISAM data file. More...

string	m_IndexFname
	The filename of the ISAM index file. More...

TIndx	m_DataFileLength
	The length of the ISAM data file. More...

TIndx	m_IndexFileLength
	The length of the ISAM index file. More...

Int4	m_NumTerms
	Number of terms in database. More...

Int4	m_NumSamples
	Number of terms in ISAM index. More...

Int4	m_PageSize
	Page size of ISAM index. More...

Int4	m_MaxLineSize
	Maximum string length in the database. More...

Int4	m_IdxOption
	Options set by upper layer. More...

bool	m_Initialized
	Flag indicating whether initialization has been done. More...

TIndx	m_KeySampleOffset
	Offset of samples in index file. More...

bool	m_TestNonUnique
	Check if data for String ISAM sorted. More...

char *	m_FileStart
	Pointer to index file if no memmap. More...

Int4	m_FirstOffset
	First and last offset's of last page. More...

Int4	m_LastOffset
	First and last offset's of last page. More...

SIsamKey	m_FirstKey
	First volume key. More...

SIsamKey	m_LastKey
	Last volume key. More...

bool	m_LongId
	Use Uint8 for the key. More...

int	m_TermSize
	size of the numeric key-data pair More...

Additional Inherited Members
Static Public Attributes inherited from CObject
static const TCount	eCounterBitsCanBeDeleted = 1 << 0
	Define possible object states. More...

static const TCount	eCounterBitsInPlainHeap = 1 << 1
	Heap signature was found. More...

static const TCount	eCounterBitsPlaceMask
	Mask for 'in heap' state flags. More...

static const int	eCounterStep = 1 << 2
	Skip over the "in heap" bits. More...

static const TCount	eCounterValid = TCount(1) << (sizeof(TCount) * 8 - 2)
	Minimal value for valid objects (reference counter is zero) Must be a single bit value. More...

static const TCount	eCounterStateMask
	Valid object, and object in heap. More...

Protected Member Functions inherited from CObject
virtual void	DeleteThis (void)
	Virtual method "deleting" this object. More...

Detailed Description

CSeqDBIsam.

Manages one ISAM file, which will translate either PIGs, GIs, or Accessions to OIDs. Translation in the other direction is done in the CSeqDBVol code. Files managed by this class include those with the extensions pni, pnd, ppi, ppd, psi, psd, nsi, nsd, nni, and nnd. Each instance of this object will manage one pair of these files, including one whose name ends in 'i' and one whose name ends in 'd'.

Definition at line 127 of file seqdbisam.hpp.

Member Typedef Documentation

◆ TGiOid

typedef CSeqDBGiList::SGiOid CSeqDBIsam::TGiOid

Import the type representing one GI, OID association.

Definition at line 130 of file seqdbisam.hpp.

◆ TId

typedef Int8 CSeqDBIsam::TId

Type large enough to hold any numerical ID.

Definition at line 158 of file seqdbisam.hpp.

◆ TIndx

typedef CSeqDBAtlas::TIndx CSeqDBIsam::TIndx

Type which is large enough to span the bytes of an ISAM file.

Definition at line 143 of file seqdbisam.hpp.

◆ TOid

typedef int CSeqDBIsam::TOid

This class works with OIDs relative to a specific volume.

Definition at line 146 of file seqdbisam.hpp.

◆ TTi

typedef Int8 CSeqDBIsam::TTi

PIG identifiers for numeric indices over protein volumes.

Genomic IDs, the most common numerical identifier. Identifier type for trace databases.

Definition at line 155 of file seqdbisam.hpp.

Member Enumeration Documentation

◆ EErrorCode

enum CSeqDBIsam::EErrorCode

private

Exit conditions occurring in this code.

Enumerator
eNotFound
eNoError	The key was not found.
eBadVersion	Lookup was successful.
eBadType	The format version of the ISAM file is unsupported.
eWrongFile	The requested ISAM type did not match the file.
eInitFailed	The file was not found, or was the wrong length.

Definition at line 489 of file seqdbisam.hpp.

◆ EIsamDbType

enum CSeqDBIsam::EIsamDbType

Types of database this class can access.

Enumerator
eNumeric
eNumericNoData	Numeric database with Key/Value pairs in the index file.
eString	This type is not supported.
eStringDatabase	String database type used here.
eStringBin	This type is not supported.
eNumericLongId	This type is not supported.

Definition at line 133 of file seqdbisam.hpp.

Constructor & Destructor Documentation

◆ CSeqDBIsam()

CSeqDBIsam::CSeqDBIsam	(	CSeqDBAtlas &	atlas,
		const string &	dbname,
		char	prot_nucl,
		char	file_ext_char,
		ESeqDBIdType	ident_type
	)

Constructor.

An ISAM file object corresponds to an index file and a data file, and converts identifiers (string, GI, or PIG) into OIDs relative to a particular database volume.

Parameters

atlas	The memory management object. [in]
dbname	The name of the volume's files (minus the extension). [in]
prot_nucl	Whether the sequences are protein or nucleotide. [in]
file_ext_char	This is 's', 'n', or 'p', for string, GI, or PIG, respectively. [in]
ident_type	The type of identifiers this database translates. [in]

Definition at line 1102 of file seqdbisam.cpp.

References dbname(), DEFAULT_NISAM_SIZE, DEFAULT_SISAM_SIZE, eGiId, eHashId, eNoError, eNumeric, ePigId, eString, eStringId, eTiId, CSeqDBFileMemMap::Init(), m_DataFname, m_DataLease, m_IndexFname, m_IndexLease, m_Initialized, m_PageSize, m_Type, NCBI_THROW, x_FindIndexBounds(), x_InitSearch(), and x_MakeFilenames().

◆ ~CSeqDBIsam()

CSeqDBIsam::~CSeqDBIsam ( )

Destructor.

Releases all resources associated with this object.

Definition at line 1210 of file seqdbisam.cpp.

References UnLease().

Member Function Documentation

◆ GetIdBounds() [1/2]

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

Get Numeric Bounds.

Fetch the lowest, highest, and total number of numeric keys in the database index. If the operation fails, zero will be returned for count.

Parameters

low_id	Lowest numeric id value in database. [out]
high_id	Highest numeric id value in database. [out]
count	Number of numeric id values in database. [out]
locked	Lock holder object for this thread. [in]

Definition at line 1624 of file seqdbisam.cpp.

References CSeqDBIsam::SIsamKey::GetNumeric(), CSeqDBIsam::SIsamKey::IsSet(), m_FirstKey, m_Initialized, m_LastKey, and m_NumTerms.

Referenced by CSeqDBVol::GetGiBounds(), CSeqDBVol::GetPigBounds(), and CSeqDBVol::GetStringBounds().

◆ GetIdBounds() [2/2]

void CSeqDBIsam::GetIdBounds	(	string &	low_id,
		string &	high_id,
		int &	count
	)

Get String Bounds.

Fetch the lowest, highest, and total number of string keys in the database index. If the operation fails, zero will be returned for count.

Parameters

low_id	Lowest string id value in database. [out]
high_id	Highest string id value in database. [out]
count	Number of string id values in database. [out]
locked	Lock holder object for this thread. [in]

Definition at line 1645 of file seqdbisam.cpp.

References CSeqDBIsam::SIsamKey::GetString(), CSeqDBIsam::SIsamKey::IsSet(), m_FirstKey, m_Initialized, m_LastKey, and m_NumTerms.

◆ HashToOids()

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

Sequence hash lookup.

This methods tries to find sequences associated with a given sequence hash value. The provided value is numeric but the ISAM file uses a string format, because string searches can return multiple results per key, and there may be multiple OIDs for a given hash value due to identical sequences and collisions.

Parameters

hash	The sequence hash value to look up. [in]
oids	The returned oids. [out]
locked	The lock hold object for this thread. [in\|out]

Definition at line 1666 of file seqdbisam.cpp.

References _ASSERT, eHashId, eNoError, eNotFound, ITERATE, ncbi::grid::netcache::search::fields::key, m_IdentType, m_Initialized, NStr::UIntToString(), and x_StringSearch().

Referenced by CSeqDBVol::HashToOids().

◆ IdsToOids() [1/2]

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

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

This method iterates over a vector of Gi/OID and/or Ti/OID pairs. For each pair where the OID is -1, the GI or TI will be looked up in the ISAM file, and (if found) the correct OID will be stored (otherwise the -1 will remain). This method will normally be called once for each volume.

Parameters

vol_start	The starting OID of this volume. [in]
vol_end	The fist OID past the end of this volume. [in]
ids	The set of GI-OID or TI-OID pairs. [in\|out]
locked	The lock holder object for this thread. [in\|out]

Definition at line 1387 of file seqdbisam.cpp.

References eGiId, ePigId, eStringId, eTiId, m_IdentType, and NCBI_THROW.

Referenced by CSeqDBVol::IdsToOids().

◆ IdsToOids() [2/2]

void CSeqDBIsam::IdsToOids	(	int	vol_start,
		int	vol_end,
		CSeqDBNegativeList &	ids
	)

Compute list of included OIDs based on a negative ID list.

This method iterates over a vector of Gis or Tis, along with the corresponding ISAM file for this volume. Each OID found in the ISAM file is marked in the negative ID list. For those for which the GI or TI is not mentioned in the negative ID list, the OID will be marked as an 'included' OID in the ID list (that OID will be searched). The OIDs for IDs that are not found in the ID list will be marked as 'visible' OIDs. When this process is done for all volumes, the SeqDB object will use all OIDs that are either marked as 'included' or NOT marked as 'visible'. The 'visible' list is needed because otherwise iteration would skip IDs that are do not have GIs or TIs (whichever is being iterated). To use this method, this volume must have an ISAM file matching the negative ID list's identifier type or an exception will be thrown.

Parameters

vol_start	The starting OID of this volume. [in]
vol_end	The fist OID past the end of this volume. [in]
ids	The set of GI-OID pairs. [in\|out]
locked	The lock holder object for this thread. [in\|out]

Definition at line 1420 of file seqdbisam.cpp.

References _ASSERT, eGiId, eStringId, eTiId, CSeqDBNegativeList::GetNumGis(), CSeqDBNegativeList::GetNumSis(), CSeqDBNegativeList::GetNumTis(), CSeqDBNegativeList::InsureOrder(), m_IdentType, x_SearchNegativeMulti(), and x_SearchNegativeMultiSeq().

◆ IdToOid()

bool CSeqDBIsam::IdToOid	(	Int8	id,
		TOid &	oid
	)

inline

GI or TI translation.

A GI or TI identifier is translated to an OID. GI identifiers are used for all types of sequences. TI identifiers are used primarily for nucleotide data in the Trace DBs. Multiple GIs may indicate the same sequence of bases and the same OID, but TIs are usually unique.

Parameters

id	The GI or TI to look up. [in]
oid	The returned oid. [out]
locked	The lock hold object for this thread. [in\|out]

Returns: true if the GI was found

Definition at line 225 of file seqdbisam.hpp.

References _ASSERT, eGiId, eTiId, m_IdentType, and x_IdentToOid().

Referenced by BOOST_AUTO_TEST_CASE(), CSeqDBVol::GiToOid(), CTestThread::Main(), CSeqDBVol::TiToOid(), and CSeqDBVol::x_StringToOids().

◆ IndexExists()

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

static

Check if a given ISAM index exists.

Parameters

dbname	Base name of the database volume.
prot_nucl	'n' or 'p' for protein or nucleotide.
file_ext_char	Identifier symbol; 's' for string, etc.

Definition at line 1200 of file seqdbisam.cpp.

References dbname(), CFile::Exists(), and x_MakeFilenames().

Referenced by CSeqDBVol::GetGi(), CSeqDBVol::x_OpenGiFile(), CSeqDBVol::x_OpenHashFile(), CSeqDBVol::x_OpenPigFile(), CSeqDBVol::x_OpenStrFile(), and CSeqDBVol::x_OpenTiFile().

◆ PigToOid()

bool CSeqDBIsam::PigToOid	(	TPig	pig,
		TOid &	oid
	)

inline

PIG translation.

A PIG identifier is translated to an OID. PIG identifiers are used exclusively for protein sequences. One PIG corresponds to exactly one sequences of amino acids, and vice versa. They are also stable; the sequence a PIG points to will never be changed.

Parameters

pig	The PIG to look up. [in]
oid	The returned oid. [out]
locked	The lock hold object for this thread. [in\|out]

Returns: true if the PIG was found

Definition at line 203 of file seqdbisam.hpp.

References _ASSERT, ePigId, m_IdentType, and x_IdentToOid().

Referenced by CSeqDBVol::PigToOid(), and CSeqDBVol::x_StringToOids().

◆ SeqidToOid()

bool CSeqDBIsam::SeqidToOid	(	const string &	acc,
		TOid &	oid
	)

Seq-id translation.

A Seq-id identifier (serialized to a string) is translated into an OID. This routine will attempt to simplify the seqid so as to use the faster numeric lookup techniques whenever possible.

Parameters

acc	A string containing the Seq-id. [in]
oid	The returned oid. [out]
locked	The lock hold object for this thread. [in\|out]

◆ StringToOids()

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

String translation.

A string id is translated to one or more OIDs. String ids are used by some groups which produce sequence data. In some cases, the string may correspond to more than one OID. For this reason, the OIDs are returned in a vector. The string provided is looked up in several ways. If it contains a pipe character ("|") the data will be interpreted as a SeqID. This routine can use faster lookup mechanisms if the simplification routines were able to recognize the sequence as one of several types that have numerical indices. The version_check flag is needed to support sparse indexing. If version_check is true, and the string has a version, and the lookup fails, this method will try to remove the version and search again. On return from this method version_check will be set to true if and only if the first search failed and the versionless search succeeded. CSeqDBVol::x_CheckVersions() can then be called to verify the OIDs; see that method for more information about this scenario.

Parameters

acc	The string to look up. [in]
oids	The returned oids. [out]
adjusted	Whether the simplification adjusted the string. [in\|out]
version_check	If the version can be stripped [in] and if it was [out].
locked	The lock hold object for this thread. [in\|out]

Definition at line 1235 of file seqdbisam.cpp.

References _ASSERT, CSeq_id::AsFastaString(), eNoError, eNotFound, eStringId, CSeq_id::fParse_AnyLocal, CSeq_id::fParse_RawText, isdigit(), ITERATE, m_IdentType, m_Initialized, ncbi::grid::netcache::search::fields::size, and x_StringSearch().

Referenced by CSeqDBVol::x_StringToOids().

◆ UnLease()

void CSeqDBIsam::UnLease ( )

Return any memory held by this object to the atlas.

Definition at line 1215 of file seqdbisam.cpp.

References CSeqDBFileMemMap::Clear(), m_DataLease, and m_IndexLease.

Referenced by BOOST_AUTO_TEST_CASE(), CSeqDBVol::UnLease(), and ~CSeqDBIsam().

◆ x_DiffChar()

Int4 CSeqDBIsam::x_DiffChar	(	const string &	term_in,
		const char *	begin,
		const char *	end,
		bool	ignore_case
	)

private

Find the first character to differ in two strings.

This finds the index of the first character to differ in meaningful way between two strings. One of the strings is a term that is passed in; the other is a range of memory represented by two pointers.

Parameters

term_in	The key string to compare against.
begin	A pointer to the start of the second string.
end	A pointer to the end of the second string.
ignore_case	Whether to treat the search as case-sensitive

Returns: The position of the first difference.

Definition at line 589 of file seqdbisam.cpp.

References ch1, ch2, ENDS_ISAM_KEY(), i, int, result, s_SeqDBIsam_NullifyEOLs(), and toupper().

Referenced by x_DiffCharLease(), x_ExtractAllData(), and x_ExtractPageData().

◆ x_DiffCharLease()

int CSeqDBIsam::x_DiffCharLease	(	const string &	term_in,
		CSeqDBFileMemMap &	lease,
		const string &	file_name,
		TIndx	file_length,
		Uint4	at_least,
		TIndx	KeyOffset,
		bool	ignore_case
	)

private

Find the first character to differ in two strings.

This finds the index of the first character to differ in meaningful way between two strings. One of the strings is a term that is passed in; the other is assumed to be located in the ISAM table, a lease to which is passed to this function.

Parameters

term_in	The key string to compare against.
lease	A lease to hold the data in the ISAM table file.
file_name	The name of the ISAM file to work with.
file_length	The length of the file named by file_name.
at_least	Try to get at least this many bytes.
KeyOffset	The location of the key in the leased file.
ignore_case	Whether to treat the search as case-sensitive
locked	The lock holder object for this thread.

Returns: The position of the first difference.

Definition at line 516 of file seqdbisam.cpp.

References file_name, CSeqDBFileMemMap::GetFileDataPtr(), int, result, and x_DiffChar().

Referenced by x_DiffSample().

◆ x_DiffSample()

int CSeqDBIsam::x_DiffSample	(	const string &	term_in,
		Uint4	SampleNum,
		TIndx &	KeyOffset
	)

private

Find the first character to differ in two strings.

This finds the index of the first character to differ between two strings. The first string is provided, the second is one of the sample strings, indicated by the index of that sample value.

Parameters

term_in	The key string to compare against.
SampleNum	Selects which sample to compare with.
KeyOffset	The returned offset of the key that was used.
locked	This thread's lock holder object.

Definition at line 863 of file seqdbisam.cpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_IndexFileLength, m_IndexFname, m_IndexLease, m_KeySampleOffset, m_MaxLineSize, m_NumSamples, m_PageSize, MEMORY_ONLY_PAGE_SIZE, SeqDB_GetStdOrd(), and x_DiffCharLease().

Referenced by x_StringSearch().

◆ x_ExtractAllData()

void CSeqDBIsam::x_ExtractAllData	(	const string &	term_in,
		TIndx	sample_index,
		vector< TIndx > &	indices_out,
		vector< string > &	keys_out,
		vector< string > &	data_out
	)

private

Find matches in the given page of a string ISAM file.

This searches the area around a specific page of the data file to find all matches to term_in. The results are returned in vectors. This method may search multiple pages.

Parameters

term_in	The key string to compare against.
sample_index	Selects which page to search.
indices_out	The index of each match.
keys_out	The key of each match.
data_out	The value of each match.
locked	This thread's lock holder object.

Definition at line 688 of file seqdbisam.cpp.

References m_NumSamples, m_PageSize, s_SeqDBIsam_NullifyEOLs(), x_DiffChar(), x_ExtractPageData(), and x_LoadPage().

Referenced by x_StringSearch().

◆ x_ExtractData()

void CSeqDBIsam::x_ExtractData	(	const char *	key_start,
		const char *	entry_end,
		vector< string > &	key_out,
		vector< string > &	data_out
	)

private

Extract the data from a key-value pair in memory.

Given pointers to a location in mapped memory, and the end of the mapped data, this finds the key and data values for the object at that location.

Parameters

key_start	A pointer to the beginning of the key-value pair in memory.
entry_end	A pointer to the end of the mapped area of memory.
key_out	A string holding the ISAM entry's key
data_out	A string holding the ISAM entry's value

Definition at line 793 of file seqdbisam.cpp.

References ISAM_DATA_CHAR, and s_SeqDBIsam_NullifyEOLs().

Referenced by x_ExtractPageData(), and x_FindIndexBounds().

◆ x_ExtractPageData()

void CSeqDBIsam::x_ExtractPageData	(	const string &	term_in,
		TIndx	page_index,
		const char *	beginp,
		const char *	endp,
		vector< TIndx > &	indices_out,
		vector< string > &	keys_out,
		vector< string > &	data_out
	)

private

Find matches in the given memory area of a string ISAM file.

This searches the specified section of memory to find all matches to term_in. The results are returned in vectors.

Parameters

term_in	The key string to compare against.
page_index	Selects which page to search.
beginp	Pointer to the start of the memory area
endp	Pointer to the end of the memory area
indices_out	The index of each match.
keys_out	The key of each match.
data_out	The value of each match.

Definition at line 634 of file seqdbisam.cpp.

References s_SeqDBIsam_NullifyEOLs(), x_DiffChar(), and x_ExtractData().

Referenced by x_ExtractAllData(), and x_StringSearch().

◆ x_FindIndexBounds()

void CSeqDBIsam::x_FindIndexBounds ( )

private

Find the least and greatest keys in this ISAM file.

Definition at line 1460 of file seqdbisam.cpp.

References _ASSERT, eNumeric, m_FirstKey, m_LastKey, m_NumSamples, m_Type, s_SeqDBIsam_NullifyEOLs(), CSeqDBIsam::SIsamKey::SetNumeric(), CSeqDBIsam::SIsamKey::SetString(), x_ExtractData(), x_GetDataElement(), x_LoadPage(), x_Lower(), and x_MapDataPage().

Referenced by CSeqDBIsam().

◆ x_FindInNegativeList() [1/2]

bool CSeqDBIsam::x_FindInNegativeList	(	CSeqDBNegativeList &	ids,
		int &	index,
		Int8	key,
		bool	use_tis
	)

inlineprivate

Find ID in the negative GI list using PBS.

Use parabolic binary search to find the specified ID in the negative ID list. The 'index' value is the index to start the search at (this must refer to an index at or before the target data if the search is to succeed). Whether the search was successful or not, the index will be moved forward past any elements with values less than 'key'.

Parameters

ids	Negative ID list. [in\|out]
index	Index into negative ID list. [in\|out]
key	Key for which to search. [in]
use_tis	If true, search for a TI, else for a GI. [in]

Returns: True if the search found the ID.

Definition at line 1428 of file seqdbisam.hpp.

References ncbi::grid::netcache::search::fields::key, CSeqDBNegativeList::ListSize(), and x_GetId().

Referenced by x_SearchNegativeMulti(), and x_SearchNegativeMultiSeq().

◆ x_FindInNegativeList() [2/2]

bool CSeqDBIsam::x_FindInNegativeList	(	CSeqDBNegativeList &	ids,
		int &	index,
		string	key
	)

inlineprivate

Definition at line 1461 of file seqdbisam.hpp.

References ncbi::grid::netcache::search::fields::key, CSeqDBNegativeList::ListSize(), and x_GetId().

◆ x_GetDataElement() [1/2]

void CSeqDBIsam::x_GetDataElement	(	const void *	dpage,
		int	index,
		Int8 &	key,
		int &	data
	)

inlineprivate

Get a particular data element from a data page.

Parameters

dpage	A pointer to that page in memory. [in]
index	The index of the element to fetch. [in]
key	The returned key. [out]
data	The returned value. [out]

Definition at line 1509 of file seqdbisam.hpp.

References ncbi::grid::netcache::search::fields::key, m_TermSize, x_GetNumericData(), and x_GetNumericKey().

Referenced by x_FindIndexBounds(), and x_SearchNegativeMulti().

◆ x_GetDataElement() [2/2]

void CSeqDBIsam::x_GetDataElement	(	const void *	dpage,
		int	index,
		string &	key,
		int &	data
	)

inlineprivate

Definition at line 1519 of file seqdbisam.hpp.

References ncbi::grid::netcache::search::fields::key, m_TermSize, and x_LoadStringData().

◆ x_GetId() [1/2]

static string CSeqDBIsam::x_GetId	(	CSeqDBNegativeList &	ids,
		int	index
	)

inlinestaticprivate

Definition at line 1158 of file seqdbisam.hpp.

References CSeqDBNegativeList::GetSi().

◆ x_GetId() [2/2]

static Int8 CSeqDBIsam::x_GetId	(	CSeqDBNegativeList &	ids,
		int	index,
		bool	use_tis
	)

inlinestaticprivate

Fetch a GI or TI from a GI list.

Definition at line 1151 of file seqdbisam.hpp.

References CSeqDBNegativeList::GetGi(), CSeqDBNegativeList::GetTi(), and GI_TO.

Referenced by x_FindInNegativeList().

◆ x_GetIndexKeyOffset()

CSeqDBIsam::TIndx CSeqDBIsam::x_GetIndexKeyOffset	(	TIndx	sample_offset,
		Uint4	sample_num
	)

private

Get the offset of the specified sample.

For string ISAM indices, the index file contains a table of offsets of the index file samples. This function gets the offset of the specified sample in the index file's table.

Parameters

sample_offset	The offset into the file of the set of samples.
sample_num	The index of the sample to get.
locked	This thread's lock holder object.

Returns: The offset of the sample in the index file.

Definition at line 823 of file seqdbisam.cpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_IndexLease, and SeqDB_GetStdOrd().

Referenced by x_StringSearch().

◆ x_GetIndexString()

void CSeqDBIsam::x_GetIndexString	(	TIndx	key_offset,
		int	length,
		string &	prefix,
		bool	trim_to_null
	)

private

Read a string from the index file.

Given an offset into the index file, and a maximum length, this function returns the bytes in a string object.

Parameters

key_offset	The offset into the file of the first byte.
length	The maximum number of bytes to get.
prefix	The string in which to return the data.
trim_to_null	Whether to search for a null and return only that much data.
locked	This thread's lock holder object.

Definition at line 836 of file seqdbisam.cpp.

References CSeqDBFileMemMap::GetFileDataPtr(), i, m_IndexLease, and str().

Referenced by x_StringSearch().

◆ x_GetNumericData()

int CSeqDBIsam::x_GetNumericData ( const void * p )

inlineprivate

Definition at line 1260 of file seqdbisam.hpp.

References m_LongId, and SeqDB_GetStdOrd().

Referenced by x_GetDataElement(), x_GetNumericSample(), x_LoadData(), x_SearchDataNumeric(), x_SearchIndexNumeric(), and x_TestNumericSample().

◆ x_GetNumericKey()

Uint8 CSeqDBIsam::x_GetNumericKey ( const void * p )

inlineprivate

Definition at line 1253 of file seqdbisam.hpp.

References m_LongId, and SeqDB_GetStdOrd().

Referenced by x_GetDataElement(), x_GetNumericSample(), x_LoadData(), x_LoadIndex(), x_SearchDataNumeric(), x_SearchIndexNumeric(), and x_TestNumericSample().

◆ x_GetNumericSample()

void CSeqDBIsam::x_GetNumericSample	(	CSeqDBFileMemMap &	index_lease,
		int	index,
		Int8 &	key_out,
		int &	data_out
	)

inlineprivate

Get a sample key value from a numeric index.

Given the index of a sample value, this code will get the key. If data values are stored in the index file, the corresponding data value will also be returned. The offset of the data block is computed and returned as well.

Parameters

index_lease	The memory lease to use with the index file.
index	The index of the sample to get.
key_out	The key found will be returned here.
data_out	If an exact match, the data found will be returned here.

Definition at line 1315 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_KeySampleOffset, m_TermSize, x_GetNumericData(), and x_GetNumericKey().

◆ x_GetPageNumElements()

Int4 CSeqDBIsam::x_GetPageNumElements	(	Int4	SampleNum,
		Int4 *	Start
	)

private

Determine the number of elements in the data page.

The number of elements is determined based on whether this is the last page and the configured page size.

Parameters

SampleNum	Which data page will be searched.
Start	The returned index of the start of the page.

Returns: The number of elements in this data page.

Definition at line 123 of file seqdbisam.cpp.

References m_NumSamples, m_NumTerms, and m_PageSize.

Referenced by x_MapDataPage(), and x_SearchDataNumeric().

◆ x_IdentToOid()

bool CSeqDBIsam::x_IdentToOid	(	Int8	id,
		TOid &	oid
	)

private

Numeric identifier lookup.

Given a numeric identifier, this routine finds the OID.

Parameters

id	The GI or PIG identifier to look up.
oid	The returned oid.
locked	The lock holder object for this thread.

Returns: true if the identifier was found.

Definition at line 1221 of file seqdbisam.cpp.

References eNoError, and x_NumericSearch().

Referenced by IdToOid(), and PigToOid().

◆ x_InitSearch()

CSeqDBIsam::EErrorCode CSeqDBIsam::x_InitSearch ( void )

private

Initialize the search object.

The first identifier search sets up the object by calling this function, which reads the metadata from the index file and sets all the fields needed for ISAM lookups.

Parameters

locked The lock holder object for this thread.

Returns: A non-zero error on failure, or eNoError on success.

Definition at line 59 of file seqdbisam.cpp.

References eBadType, eBadVersion, eNoError, eNumeric, eNumericLongId, eWrongFile, CSeqDBFileMemMap::GetFileDataPtr(), CSeqDBAtlas::GetFileSizeL(), ISAM_VERSION, m_Atlas, m_DataFileLength, m_DataFname, m_IdxOption, m_IndexFileLength, m_IndexFname, m_IndexLease, m_Initialized, m_KeySampleOffset, m_LongId, m_MaxLineSize, m_NumSamples, m_NumTerms, m_PageSize, m_TermSize, m_Type, MEMORY_ONLY_PAGE_SIZE, and SeqDB_GetStdOrd().

Referenced by CSeqDBIsam().

◆ x_LoadData() [1/3]

template<>

void CSeqDBIsam::x_LoadData	(	CSeqDBFileMemMap &	lease,
		vector< string > &	keys,
		vector< int > &	vals,
		int	num_keys,
		TIndx	begin
	)

inlineprivate

Definition at line 1406 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), and NStr::StringToUInt().

◆ x_LoadData() [2/3]

template<class T >

void CSeqDBIsam::x_LoadData	(	CSeqDBFileMemMap &	lease,
		vector< T > &	keys,
		vector< int > &	vals,
		int	num_keys,
		TIndx	begin
	)

inlineprivate

Load and extract a data page into array at once.

Definition at line 519 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_TermSize, T, x_GetNumericData(), and x_GetNumericKey().

Referenced by x_SearchNegativeMultiSeq(), and x_TranslateGiList().

◆ x_LoadData() [3/3]

template<>

void CSeqDBIsam::x_LoadData	(	CSeqDBFileMemMap &	lease,
		vector< TGi > &	keys,
		vector< int > &	vals,
		int	num_keys,
		TIndx	begin
	)

inlineprivate

Load and extract a data page into array at once.

Definition at line 1353 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), GI_FROM, m_TermSize, x_GetNumericData(), and x_GetNumericKey().

◆ x_LoadIndex() [1/3]

template<>

void CSeqDBIsam::x_LoadIndex	(	CSeqDBFileMemMap &	lease,
		vector< string > &	keys,
		vector< TIndx > &	offs
	)

inlineprivate

Definition at line 1371 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_KeySampleOffset, m_NumSamples, offset, and SeqDB_GetStdOrd().

◆ x_LoadIndex() [2/3]

template<class T >

void CSeqDBIsam::x_LoadIndex	(	CSeqDBFileMemMap &	lease,
		vector< T > &	keys,
		vector< TIndx > &	offs
	)

inlineprivate

Load and extract all index samples into array at once.

Definition at line 500 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_KeySampleOffset, m_NumSamples, m_NumTerms, m_PageSize, m_TermSize, T, and x_GetNumericKey().

Referenced by x_SearchNegativeMultiSeq(), and x_TranslateGiList().

◆ x_LoadIndex() [3/3]

template<>

void CSeqDBIsam::x_LoadIndex	(	CSeqDBFileMemMap &	lease,
		vector< TGi > &	keys,
		vector< TIndx > &	offs
	)

inlineprivate

Load and extract all index samples into array at once.

Definition at line 1333 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), GI_FROM, m_KeySampleOffset, m_NumSamples, m_NumTerms, m_PageSize, m_TermSize, and x_GetNumericKey().

◆ x_LoadPage()

void CSeqDBIsam::x_LoadPage	(	TIndx	SampleNum1,
		TIndx	SampleNum2,
		const char **	beginp,
		const char **	endp
	)

private

Map a page into memory.

Given two indices, this method maps into memory the area starting at the beginning of the first index and extending to the end of the other. (If the indices are equal, only one page would be mapped.)

Parameters

SampleNum1	The first page index.
SampleNum2	The second page index.
beginp	The returned starting offset of the mapped area.
endp	The returned ending offset of the mapped area.
locked	This thread's lock holder object.

Definition at line 899 of file seqdbisam.cpp.

References _ASSERT, CSeqDBFileMemMap::GetFileDataPtr(), m_DataFname, m_DataLease, m_IndexLease, m_KeySampleOffset, and SeqDB_GetStdOrd().

Referenced by x_ExtractAllData(), x_FindIndexBounds(), and x_StringSearch().

◆ x_LoadStringData()

void CSeqDBIsam::x_LoadStringData	(	const char *	begin,
		string &	key,
		int &	data
	)

inlineprivate

Definition at line 1267 of file seqdbisam.hpp.

References ncbi::grid::netcache::search::fields::key, string, and NStr::StringToUInt().

Referenced by x_GetDataElement().

◆ x_Lower()

static void CSeqDBIsam::x_Lower ( string & s )

inlinestaticprivate

Converts a string to lower case.

Definition at line 1143 of file seqdbisam.hpp.

References i, and tolower().

Referenced by x_FindIndexBounds(), and x_OutOfBounds().

◆ x_MakeFilenames()

void CSeqDBIsam::x_MakeFilenames	(	const string &	dbname,
		char	prot_nucl,
		char	file_ext_char,
		string &	index_name,
		string &	data_name
	)

staticprivate

Make filenames for ISAM file.

Parameters

dbname	Base name of the database volume. [in]
prot_nucl	'n' or 'p' for protein or nucleotide. [in]
file_ext_char	Identifier symbol; 's' for string, etc. [in]
index_name	Filename of ISAM index file. [out]
data_name	Filename of ISAM data file. [out]

Definition at line 1172 of file seqdbisam.cpp.

References dbname(), isalpha(), and NCBI_THROW.

Referenced by CSeqDBIsam(), and IndexExists().

◆ x_MapDataPage()

void CSeqDBIsam::x_MapDataPage	(	int	sample_index,
		int &	start,
		int &	num_elements,
		const void **	data_page_begin
	)

inlineprivate

Map a data page.

The caller provides an index into the sample file. The page of data is mapped, and a pointer is returned. In addition, the starting index (start) of the data is returned, along with the number of elements in that page.

Parameters

sample_index	Index into the index (i.e. pni) file. [in]
start	Index of first element of the page. [out]
num_elements	Number of elements in the page. [out]
data_page_begin	Pointer to the returned data. [out]
locked	The lock holder object for this thread. [out]

Definition at line 1493 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_DataFname, m_DataLease, m_TermSize, and x_GetPageNumElements().

Referenced by x_FindIndexBounds(), and x_SearchNegativeMulti().

◆ x_NumericSearch()

CSeqDBIsam::EErrorCode CSeqDBIsam::x_NumericSearch	(	Int8	Number,
		int *	Data,
		Uint4 *	Index
	)

private

Numeric identifier lookup.

Given a numeric identifier, this routine finds the OID.

Parameters

Number	The GI or PIG identifier to look up.
Data	The returned OID.
Index	The returned location in the ISAM table, or NULL.
locked	The lock holder object for this thread.

Returns: A non-zero error on failure, or eNoError on success.

Definition at line 498 of file seqdbisam.cpp.

References done, x_SearchDataNumeric(), and x_SearchIndexNumeric().

Referenced by x_IdentToOid().

◆ x_OutOfBounds() [1/2]

bool CSeqDBIsam::x_OutOfBounds ( Int8 key )

private

Check whether a numeric key is within this volume's bounds.

Parameters

key	The key for which to do the check.
locked	The lock holder object for this thread.

Definition at line 1584 of file seqdbisam.cpp.

References _ASSERT, eNumeric, CSeqDBIsam::SIsamKey::IsSet(), ncbi::grid::netcache::search::fields::key, m_FirstKey, m_LastKey, m_Type, CSeqDBIsam::SIsamKey::OutsideFirstBound(), and CSeqDBIsam::SIsamKey::OutsideLastBound().

Referenced by x_SearchIndexNumeric(), and x_StringSearch().

◆ x_OutOfBounds() [2/2]

bool CSeqDBIsam::x_OutOfBounds ( string key )

private

Check whether a string key is within this volume's bounds.

Parameters

key	The key for which to do the check.
locked	The lock holder object for this thread.

Definition at line 1603 of file seqdbisam.cpp.

References _ASSERT, eString, CSeqDBIsam::SIsamKey::IsSet(), ncbi::grid::netcache::search::fields::key, m_FirstKey, m_LastKey, m_Type, CSeqDBIsam::SIsamKey::OutsideFirstBound(), CSeqDBIsam::SIsamKey::OutsideLastBound(), and x_Lower().

◆ x_SearchDataNumeric()

CSeqDBIsam::EErrorCode CSeqDBIsam::x_SearchDataNumeric	(	Int8	Number,
		int *	Data,
		Uint4 *	Index,
		Int4	SampleNum
	)

private

Data file search.

Given a numeric identifier, this routine finds the OID in the data file.

Parameters

Number	The GI or PIG identifier to look up.
Data	The returned OID.
Index	The returned location in the ISAM table, or NULL.
SampleNum	The location of the page in the data file to search.
locked	The lock holder object for this thread.

Returns: A non-zero error on failure, or eNoError on success.

Definition at line 421 of file seqdbisam.cpp.

References _ASSERT, eNoError, eNotFound, eNumericNoData, first(), CSeqDBFileMemMap::GetFileDataPtr(), last(), m_DataFname, m_DataLease, m_TermSize, m_Type, NULL, x_GetNumericData(), x_GetNumericKey(), and x_GetPageNumElements().

Referenced by x_NumericSearch().

◆ x_SearchIndexNumeric()

CSeqDBIsam::EErrorCode CSeqDBIsam::x_SearchIndexNumeric	(	Int8	Number,
		int *	Data,
		Uint4 *	Index,
		Int4 &	SampleNum,
		bool &	done
	)

private

Index file search.

Given a numeric identifier, this routine finds the OID or the page in the data file where the OID can be found.

Parameters

Number	The GI or PIG identifier to look up.
Data	The returned OID.
Index	The returned location in the ISAM table, or NULL.
SampleNum	The returned location in the data file if not done.
done	true if the OID was found.
locked

Returns: A non-zero error on failure, or eNoError on success.

Definition at line 140 of file seqdbisam.cpp.

References _ASSERT, done, eInitFailed, eNoError, eNotFound, eNumericNoData, CSeqDBFileMemMap::GetFileDataPtr(), m_IndexFname, m_IndexLease, m_Initialized, m_KeySampleOffset, m_NumSamples, m_PageSize, m_TermSize, m_Type, NULL, x_GetNumericData(), x_GetNumericKey(), and x_OutOfBounds().

Referenced by x_NumericSearch().

◆ x_SearchNegativeMulti()

void CSeqDBIsam::x_SearchNegativeMulti	(	int	vol_start,
		int	vol_end,
		CSeqDBNegativeList &	gis,
		bool	use_tis
	)

private

Negative ID List Translation.

Given a Negative ID list, this routine turns on the bits for the OIDs found in the volume but not in the negated ID list.

Parameters

vol_start	The starting OID for this ISAM file's database volume.
vol_end	The ending OID for this ISAM file's database volume.
gis	The Negative ID list to translate.
use_tis	Iterate over TIs if true (GIs otherwise).
locked	The lock holder object for this thread.

Definition at line 219 of file seqdbisam.cpp.

References _ASSERT, CSeqDBNegativeList::AddIncludedOid(), CSeqDBNegativeList::AddVisibleOid(), eNumericNoData, CSeqDBNegativeList::GetNumGis(), CSeqDBNegativeList::GetNumTis(), i, m_Initialized, m_NumSamples, m_Type, NCBI_THROW, x_FindInNegativeList(), x_GetDataElement(), and x_MapDataPage().

Referenced by IdsToOids().

◆ x_SearchNegativeMultiSeq()

void CSeqDBIsam::x_SearchNegativeMultiSeq	(	int	vol_start,
		int	vol_end,
		CSeqDBNegativeList &	gis
	)

private

Definition at line 333 of file seqdbisam.cpp.

References CSeqDBNegativeList::AddIncludedOid(), CSeqDBNegativeList::AddVisibleOid(), i, CSeqDBNegativeList::ListSize(), m_DataLease, m_IndexLease, m_Initialized, m_NumSamples, m_NumTerms, m_PageSize, NCBI_THROW, s_IsSameAccession(), x_FindInNegativeList(), x_LoadData(), and x_LoadIndex().

Referenced by IdsToOids().

◆ x_SparseStringToOids()

bool CSeqDBIsam::x_SparseStringToOids	(	const string &	acc,
		vector< int > &	oids,
		bool	adjusted
	)

private

Lookup a string in a sparse table.

This does string lookup in a sparse string table. There is no support (code) for this since there are currently no examples of this kind of table to test against.

Parameters

acc	The string to look up.
oids	The returned oids found by the search.
adjusted	Whether the key was changed by the identifier simplification logic.
locked	The lock holder object for this thread.

Returns: true if results were found

Definition at line 1377 of file seqdbisam.cpp.

References _TROUBLE.

◆ x_StringSearch()

CSeqDBIsam::EErrorCode CSeqDBIsam::x_StringSearch	(	const string &	term_in,
		vector< string > &	term_out,
		vector< string > &	value_out,
		vector< TIndx > &	index_out
	)

private

String identifier lookup.

Given a string identifier, this routine finds the OID(s).

Parameters

term_in	The string identifier to look up.
term_out	The returned keys (as strings).
value_out	The returned oids (as strings).
index_out	The locations where the matches were found.
locked	The lock holder object for this thread.

Returns: A non-zero error on failure, or eNoError on success.

Definition at line 934 of file seqdbisam.cpp.

References NStr::CompareNocase(), eInitFailed, eNoError, eNotFound, CSeqDBFileMemMap::GetFileDataPtr(), int, m_IndexFileLength, m_IndexLease, m_Initialized, m_KeySampleOffset, m_MaxLineSize, m_NumSamples, m_PageSize, MEMORY_ONLY_PAGE_SIZE, prefix, tolower(), x_DiffSample(), x_ExtractAllData(), x_ExtractPageData(), x_GetIndexKeyOffset(), x_GetIndexString(), x_LoadPage(), and x_OutOfBounds().

Referenced by HashToOids(), and StringToOids().

◆ x_TestNumericSample()

int CSeqDBIsam::x_TestNumericSample	(	CSeqDBFileMemMap &	index_lease,
		int	index,
		Int8	key_in,
		Int8 &	key_out,
		int &	data_out
	)

inlineprivate

Test a sample key value from a numeric index.

This method reads the key value of an index file sample element from a numeric index file. The calling code should insure that the data is mapped in, and that the file type is correct. The key value found will be compared to the search key. This method will return 0 for an exact match, -1 if the key is less than the sample, or 1 if the key is greater. If the match is exact, it will also return the data in data_out.

Parameters

index_lease	The memory lease to use with the index file.
index	The index of the sample to get.
key_in	The key for which the user is searching.
key_out	The key found will be returned here.
data_out	If an exact match, the data found will be returned here.

Returns: -1, 0 or 1 when key_in is less, equal greater than key_out.

Definition at line 1284 of file seqdbisam.hpp.

References CSeqDBFileMemMap::GetFileDataPtr(), m_KeySampleOffset, m_TermSize, x_GetNumericData(), and x_GetNumericKey().

◆ x_TranslateGiList()

template<class T >

void CSeqDBIsam::x_TranslateGiList	(	int	vol_start,
		CSeqDBGiList &	gis
	)

inlineprivate

GiList Translation.

Given a GI list, this routine finds the OID for each ID in the list not already having a translation.

Parameters

vol_start	The starting OID for this ISAM file's database volume.
gis	The GI list to translate.
locked	The lock holder object for this thread.

Definition at line 549 of file seqdbisam.hpp.

References CSeqDBGiList::eGi, CSeqDBGiList::GetKey(), CSeqDBGiList::GetSize(), CSeqDBGiList::InsureOrder(), m_DataLease, m_IndexLease, m_Initialized, m_NumSamples, m_NumTerms, m_PageSize, NCBI_THROW, T, x_LoadData(), and x_LoadIndex().

Member Data Documentation

◆ m_Atlas

CSeqDBAtlas& CSeqDBIsam::m_Atlas

private

The memory management layer.

Definition at line 1180 of file seqdbisam.hpp.

Referenced by x_InitSearch().

◆ m_DataFileLength

TIndx CSeqDBIsam::m_DataFileLength

private

The length of the ISAM data file.

Definition at line 1203 of file seqdbisam.hpp.

Referenced by x_InitSearch().

◆ m_DataFname

string CSeqDBIsam::m_DataFname

private

The filename of the ISAM data file.

Definition at line 1197 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), x_InitSearch(), x_LoadPage(), x_MapDataPage(), and x_SearchDataNumeric().

◆ m_DataLease

CSeqDBFileMemMap CSeqDBIsam::m_DataLease

private

A persistent lease on the ISAM data file.

Definition at line 1190 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), UnLease(), x_LoadPage(), x_MapDataPage(), x_SearchDataNumeric(), x_SearchNegativeMultiSeq(), and x_TranslateGiList().

◆ m_FileStart

char* CSeqDBIsam::m_FileStart

private

Pointer to index file if no memmap.

Definition at line 1233 of file seqdbisam.hpp.

◆ m_FirstKey

SIsamKey CSeqDBIsam::m_FirstKey

private

First volume key.

Definition at line 1242 of file seqdbisam.hpp.

Referenced by GetIdBounds(), x_FindIndexBounds(), and x_OutOfBounds().

◆ m_FirstOffset

Int4 CSeqDBIsam::m_FirstOffset

private

First and last offset's of last page.

Definition at line 1236 of file seqdbisam.hpp.

◆ m_IdentType

ESeqDBIdType CSeqDBIsam::m_IdentType

private

The type of identifier this class uses.

Definition at line 1183 of file seqdbisam.hpp.

Referenced by HashToOids(), IdsToOids(), IdToOid(), PigToOid(), and StringToOids().

◆ m_IdxOption

Int4 CSeqDBIsam::m_IdxOption

private

Options set by upper layer.

Definition at line 1221 of file seqdbisam.hpp.

Referenced by x_InitSearch().

◆ m_IndexFileLength

TIndx CSeqDBIsam::m_IndexFileLength

private

The length of the ISAM index file.

Definition at line 1206 of file seqdbisam.hpp.

Referenced by x_DiffSample(), x_InitSearch(), and x_StringSearch().

◆ m_IndexFname

string CSeqDBIsam::m_IndexFname

private

The filename of the ISAM index file.

Definition at line 1200 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), x_DiffSample(), x_InitSearch(), and x_SearchIndexNumeric().

◆ m_IndexLease

CSeqDBFileMemMap CSeqDBIsam::m_IndexLease

private

A persistent lease on the ISAM index file.

Definition at line 1186 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), UnLease(), x_DiffSample(), x_GetIndexKeyOffset(), x_GetIndexString(), x_InitSearch(), x_LoadPage(), x_SearchIndexNumeric(), x_SearchNegativeMultiSeq(), x_StringSearch(), and x_TranslateGiList().

◆ m_Initialized

bool CSeqDBIsam::m_Initialized

private

Flag indicating whether initialization has been done.

Definition at line 1224 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), GetIdBounds(), HashToOids(), StringToOids(), x_InitSearch(), x_SearchIndexNumeric(), x_SearchNegativeMulti(), x_SearchNegativeMultiSeq(), x_StringSearch(), and x_TranslateGiList().

◆ m_KeySampleOffset

TIndx CSeqDBIsam::m_KeySampleOffset

private

Offset of samples in index file.

Definition at line 1227 of file seqdbisam.hpp.

Referenced by x_DiffSample(), x_GetNumericSample(), x_InitSearch(), x_LoadIndex(), x_LoadPage(), x_SearchIndexNumeric(), x_StringSearch(), and x_TestNumericSample().

◆ m_LastKey

SIsamKey CSeqDBIsam::m_LastKey

private

Last volume key.

Definition at line 1245 of file seqdbisam.hpp.

Referenced by GetIdBounds(), x_FindIndexBounds(), and x_OutOfBounds().

◆ m_LastOffset

Int4 CSeqDBIsam::m_LastOffset

private

First and last offset's of last page.

Definition at line 1239 of file seqdbisam.hpp.

◆ m_LongId

bool CSeqDBIsam::m_LongId

private

Use Uint8 for the key.

Definition at line 1248 of file seqdbisam.hpp.

Referenced by x_GetNumericData(), x_GetNumericKey(), and x_InitSearch().

◆ m_MaxLineSize

Int4 CSeqDBIsam::m_MaxLineSize

private

Maximum string length in the database.

Definition at line 1218 of file seqdbisam.hpp.

Referenced by x_DiffSample(), x_InitSearch(), and x_StringSearch().

◆ m_NumSamples

Int4 CSeqDBIsam::m_NumSamples

private

Number of terms in ISAM index.

Definition at line 1212 of file seqdbisam.hpp.

Referenced by x_DiffSample(), x_ExtractAllData(), x_FindIndexBounds(), x_GetPageNumElements(), x_InitSearch(), x_LoadIndex(), x_SearchIndexNumeric(), x_SearchNegativeMulti(), x_SearchNegativeMultiSeq(), x_StringSearch(), and x_TranslateGiList().

◆ m_NumTerms

Int4 CSeqDBIsam::m_NumTerms

private

Number of terms in database.

Definition at line 1209 of file seqdbisam.hpp.

Referenced by GetIdBounds(), x_GetPageNumElements(), x_InitSearch(), x_LoadIndex(), x_SearchNegativeMultiSeq(), and x_TranslateGiList().

◆ m_PageSize

Int4 CSeqDBIsam::m_PageSize

private

Page size of ISAM index.

Definition at line 1215 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), x_DiffSample(), x_ExtractAllData(), x_GetPageNumElements(), x_InitSearch(), x_LoadIndex(), x_SearchIndexNumeric(), x_SearchNegativeMultiSeq(), x_StringSearch(), and x_TranslateGiList().

◆ m_TermSize

int CSeqDBIsam::m_TermSize

private

size of the numeric key-data pair

Definition at line 1251 of file seqdbisam.hpp.

Referenced by x_GetDataElement(), x_GetNumericSample(), x_InitSearch(), x_LoadData(), x_LoadIndex(), x_MapDataPage(), x_SearchDataNumeric(), x_SearchIndexNumeric(), and x_TestNumericSample().

◆ m_TestNonUnique

bool CSeqDBIsam::m_TestNonUnique

private

Check if data for String ISAM sorted.

Definition at line 1230 of file seqdbisam.hpp.

◆ m_Type

int CSeqDBIsam::m_Type

private

The format type of database files found (eNumeric or eString).

Definition at line 1194 of file seqdbisam.hpp.

Referenced by CSeqDBIsam(), x_FindIndexBounds(), x_InitSearch(), x_OutOfBounds(), x_SearchDataNumeric(), x_SearchIndexNumeric(), and x_SearchNegativeMulti().

The documentation for this class was generated from the following files:

include/objtools/blast/seqdb_reader/impl/seqdbisam.hpp
src/objtools/blast/seqdb_reader/seqdbisam.cpp

Classes

Public Types

Public Member Functions

Static Public Member Functions

Private Types

Private Member Functions

Static Private Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ TGiOid

◆ TId

◆ TIndx

◆ TOid

◆ TTi

Member Enumeration Documentation

◆ EErrorCode

◆ EIsamDbType

Constructor & Destructor Documentation

◆ CSeqDBIsam()

◆ ~CSeqDBIsam()

Member Function Documentation

◆ GetIdBounds() [1/2]

◆ GetIdBounds() [2/2]

◆ HashToOids()

◆ IdsToOids() [1/2]

◆ IdsToOids() [2/2]

◆ IdToOid()

◆ IndexExists()

◆ PigToOid()

◆ SeqidToOid()

◆ StringToOids()

◆ UnLease()

◆ x_DiffChar()

◆ x_DiffCharLease()

◆ x_DiffSample()

◆ x_ExtractAllData()

◆ x_ExtractData()

◆ x_ExtractPageData()

◆ x_FindIndexBounds()

◆ x_FindInNegativeList() [1/2]

◆ x_FindInNegativeList() [2/2]

◆ x_GetDataElement() [1/2]

◆ x_GetDataElement() [2/2]

◆ x_GetId() [1/2]

◆ x_GetId() [2/2]

◆ x_GetIndexKeyOffset()

◆ x_GetIndexString()

◆ x_GetNumericData()

◆ x_GetNumericKey()

◆ x_GetNumericSample()

◆ x_GetPageNumElements()

◆ x_IdentToOid()

◆ x_InitSearch()

◆ x_LoadData() [1/3]

◆ x_LoadData() [2/3]

◆ x_LoadData() [3/3]

◆ x_LoadIndex() [1/3]

◆ x_LoadIndex() [2/3]

◆ x_LoadIndex() [3/3]

◆ x_LoadPage()

◆ x_LoadStringData()

◆ x_Lower()

◆ x_MakeFilenames()

◆ x_MapDataPage()

◆ x_NumericSearch()

◆ x_OutOfBounds() [1/2]

◆ x_OutOfBounds() [2/2]

◆ x_SearchDataNumeric()

◆ x_SearchIndexNumeric()

◆ x_SearchNegativeMulti()

◆ x_SearchNegativeMultiSeq()

◆ x_SparseStringToOids()

◆ x_StringSearch()

◆ x_TestNumericSample()

◆ x_TranslateGiList()

Member Data Documentation

◆ m_Atlas

◆ m_DataFileLength