Defines exception class and several constants for SeqDB. More...

#include <ncbiconf.h>
#include <corelib/ncbiobj.hpp>
#include <objects/seqloc/Seq_id.hpp>

Include dependency graph for seqdbcommon.hpp:

This graph shows which files directly or indirectly include this file:

Classes
class	CSeqDBException
	CSeqDBException. More...

struct	SBlastSeqIdListInfo
	Blast DB v5 seqid list info. More...

class	CSeqDBGiList
	CSeqDBGiList. More...

struct	CSeqDBGiList::SGiOid
	Structure that holds GI,OID pairs. More...

struct	CSeqDBGiList::STiOid
	Structure that holds TI,OID pairs. More...

struct	CSeqDBGiList::SSiOid
	Structure that holds Seq-id,OID pairs. More...

struct	CSeqDBGiList::STaxIdsOids

struct	CSeqDBGiList::SPigOid

class	CSeqDBBitVector
	CSeqDBBitVector. More...

class	CSeqDBNegativeList
	CSeqDBNegativeList. More...

class	CSeqDBFileGiList
	CSeqDBFileGiList. More...

class	CIntersectionGiList
	GI list containing the intersection of two other lists of GIs. More...

class	CSeqDBIdSet_Vector
	Helper class to allow copy-on-write semantics for CSeqDBIdSet. More...

class	CSeqDBIdSet
	SeqDB ID list for performing boolean set operations. More...

struct	SSeqDBTaxInfo
	SSeqDBTaxInfo. More...

Typedefs
typedef Int4	TOid
	Ordinal ID in BLAST databases. More...

typedef Uint8	TTi

typedef Uint4	TPig

typedef map< string, string >	TSeqDBAliasFileInstance
	Set of values found in one instance of one alias file. More...

typedef vector< TSeqDBAliasFileInstance >	TSeqDBAliasFileVersions
	Contents of all instances of a particular alias file pathname. More...

typedef map< string, TSeqDBAliasFileVersions >	TSeqDBAliasFileValues
	Contents of all alias file are returned in this type of container. More...

Enumerations
enum	EBlastDbVersion { eBDB_Version4 = 4 , eBDB_Version5 = 5 }
	BLAST database version. More...

enum	ESeqDBAllocType { eAtlas = 0 , eMalloc , eNew }
	Certain methods have an "Alloc" version. More...

enum	EOidMaskType { fNone = 0x0 , fExcludeModel = 0x01 }

enum	ESeqDBIdType { eGiId , eTiId , ePigId , eStringId , eHashId , eOID }
	Various identifier formats used in Id lookup. More...

Functions
	USING_SCOPE (objects)
	Include definitions from the objects namespace. More...

void	SeqDB_ReadBinaryGiList (const string &name, vector< TGi > &gis)
	Read a binary-format GI list from a file. More...

void	SeqDB_ReadMemoryGiList (const char fbeginp, const char fendp, vector< CSeqDBGiList::SGiOid > &gis, bool *in_order=0)
	Read a text or binary GI list from an area of memory. More...

void	SeqDB_ReadMemoryTiList (const char fbeginp, const char fendp, vector< CSeqDBGiList::STiOid > &tis, bool *in_order=0)
	Read a text or binary TI list from an area of memory. More...

void	SeqDB_ReadMemorySiList (const char fbeginp, const char fendp, vector< CSeqDBGiList::SSiOid > &sis, bool *in_order=0)
	Read a text SeqID list from an area of memory. More...

void	SeqDB_ReadMemoryMixList (const char fbeginp, const char fendp, vector< CSeqDBGiList::SGiOid > &gis, vector< CSeqDBGiList::STiOid > &tis, vector< CSeqDBGiList::SSiOid > &sis, bool *in_order)
	Read an ID list (mixed type) from an area of memory. More...

void	SeqDB_ReadMemoryPigList (const char fbeginp, const char fendp, vector< CSeqDBGiList::SPigOid > &pigs, bool *in_order=0)

void	SeqDB_CombineAndQuote (const vector< string > &dbs, string &dbname)
	Combine and quote a list of database names. More...

void	SeqDB_SplitQuoted (const string &dbname, vector< CTempString > &dbs, bool keep_quote=false)
	Split a (possibly) quoted list of database names into pieces. More...

void	SeqDB_ReadGiList (const string &fname, vector< CSeqDBGiList::SGiOid > &gis, bool *in_order=0)
	Read a text or binary GI list from a file. More...

void	SeqDB_ReadTiList (const string &fname, vector< CSeqDBGiList::STiOid > &tis, bool *in_order=0)
	Read a text or binary TI list from a file. More...

void	SeqDB_ReadSiList (const string &fname, vector< CSeqDBGiList::SSiOid > &sis, bool *in_order, SBlastSeqIdListInfo &db_info)
	Read a text SeqId list from a file. More...

void	SeqDB_ReadMixList (const string &fname, vector< CSeqDBGiList::SGiOid > &gis, vector< CSeqDBGiList::STiOid > &tis, vector< CSeqDBGiList::SSiOid > &sis, bool *in_order)
	Read a text SeqId list from a file. More...

void	SeqDB_ReadPigList (const string &fname, vector< CSeqDBGiList::SPigOid > &pigs, bool *in_order=0)

void	SeqDB_ReadGiList (const string &fname, vector< TGi > &gis, bool *in_order=0)
	Read a text or binary GI list from a file. More...

bool	SeqDB_IsBinaryGiList (const string &fname)
	Read a text or binary SeqId list from a file. More...

bool	SeqDB_IsBinaryTiList (const string &fname)
	Returns true if the file name passed contains a binary TI list. More...

string	SeqDB_ResolveDbPath (const string &filename)
	Resolve a file path using SeqDB's path algorithms. More...

string	SeqDB_ResolveDbPathNoExtension (const string &filename, char dbtype='-')
	Resolve a file path using SeqDB's path algorithms. More...

string	SeqDB_ResolveDbPathForLinkoutDB (const string &filename)
	Resolve a file path using SeqDB's path algorithms. More...

bool	SeqDB_CompareVolume (const string &volpath1, const string &volpath2)
	Compares two volume file names and determine the volume order. More...

unsigned	SeqDB_SequenceHash (const char *sequence, int length)
	Returns a path minus filename. More...

unsigned	SeqDB_SequenceHash (const CBioseq &sequence)
	Sequence Hashing For a CBioseq. More...

ESeqDBIdType	SeqDB_SimplifySeqid (CSeq_id &bestid, const string *acc, Int8 &num_id, string &str_id, bool &simpler)
	Seq-id simplification. More...

ESeqDBIdType	SeqDB_SimplifyAccession (const string &acc, Int8 &num_id, string &str_id, bool &simpler)
	String id simplification. More...

const string	SeqDB_SimplifyAccession (const string &acc)
	String id simplification. More...

void	SeqDB_GetFileExtensions (bool db_is_protein, vector< string > &extensions, EBlastDbVersion dbver=eBDB_Version4)
	Retrieves a list of all supported file extensions for BLAST databases. More...

void	SeqDB_GetLMDBFileExtensions (bool db_is_protein, vector< string > &extn)
	Retrieves file extensions for BLAST LMDB files. More...

void	SeqDB_GetMetadataFileExtension (bool db_is_protein, string &extn)

bool	IsStringId (const CSeq_id &id)
	Determine if id is srting id. More...

string	GetBlastSeqIdString (const CSeq_id &seqid, bool version)
	Return ID string as stored in lmdb. More...

const string	SeqDB_GetOidMaskFileExt (bool db_is_protein, EOidMaskType t)

Variables
const string	kSeqDBGroupAliasFileName
	The name of the group alias file name expected at each directory For more documentation, see "Group Alias Files" in source/src/objtools/blast/seqdb_reader/alias_files.txt. More...

const int	kSeqDBNuclNcbiNA8 = 0
	Used to request ambiguities in Ncbi/NA8 format. More...

const int	kSeqDBNuclBlastNA8 = 1
	Used to request ambiguities in BLAST/NA8 format. More...

const blastdb::TOid	kSeqDBEntryNotFound = -1

const blastdb::TOid	kSeqDBEntryDuplicate = -2

Detailed Description

Defines exception class and several constants for SeqDB.

Defines classes: CSeqDBException

Implemented for: UNIX, MS-Windows

Definition in file seqdbcommon.hpp.

Typedef Documentation

◆ TOid

typedef Int4 TOid

Ordinal ID in BLAST databases.

Definition at line 58 of file seqdbcommon.hpp.

◆ TPig

typedef Uint4 TPig

Definition at line 142 of file seqdbcommon.hpp.

◆ TSeqDBAliasFileInstance

typedef map<string, string> TSeqDBAliasFileInstance

Set of values found in one instance of one alias file.

Definition at line 1838 of file seqdbcommon.hpp.

◆ TSeqDBAliasFileValues

typedef map< string, TSeqDBAliasFileVersions > TSeqDBAliasFileValues

Contents of all alias file are returned in this type of container.

Definition at line 1844 of file seqdbcommon.hpp.

◆ TSeqDBAliasFileVersions

typedef vector< TSeqDBAliasFileInstance > TSeqDBAliasFileVersions

Contents of all instances of a particular alias file pathname.

Definition at line 1841 of file seqdbcommon.hpp.

◆ TTi

typedef Uint8 TTi

Definition at line 140 of file seqdbcommon.hpp.

Enumeration Type Documentation

◆ EBlastDbVersion

enum EBlastDbVersion

BLAST database version.

Enumerator
eBDB_Version4
eBDB_Version5

Definition at line 51 of file seqdbcommon.hpp.

◆ EOidMaskType

enum EOidMaskType

Enumerator
fNone
fExcludeModel

Definition at line 159 of file seqdbcommon.hpp.

◆ ESeqDBAllocType

enum ESeqDBAllocType

Certain methods have an "Alloc" version.

When these methods are used, the following constants can be specified to indicate which libraries to use to allocate returned data, so the corresponding calls (delete[] vs. free()) can be used to delete the data.

Enumerator
eAtlas
eMalloc
eNew

Definition at line 133 of file seqdbcommon.hpp.

◆ ESeqDBIdType

enum ESeqDBIdType

Various identifier formats used in Id lookup.

Enumerator
eGiId
eTiId	Genomic ID is a relatively stable numeric identifier for sequences.
ePigId	Trace ID is a numeric identifier for Trace sequences.
eStringId	Each PIG identifier refers to exactly one protein sequence.
eHashId	Some sequence sources uses string identifiers.
eOID	Lookup from sequence hash values to OIDs. The ordinal id indicates the order of the data in the volume's index file.

Definition at line 1963 of file seqdbcommon.hpp.

Function Documentation

◆ GetBlastSeqIdString()

string GetBlastSeqIdString	(	const CSeq_id &	seqid,
		bool	version
	)

Return ID string as stored in lmdb.

Definition at line 2697 of file seqdbcommon.cpp.

References CSeq_id::AsFastaString(), CSeq_id::GetSeqIdString(), CSeq_id_Base::IsPir(), CSeq_id_Base::IsPrf(), and dtl::version.

Referenced by CSeqDBGiList::FindId(), and CSeqDBNegativeList::FindId().

◆ IsStringId()

bool IsStringId ( const CSeq_id & id )

Determine if id is srting id.

Parameters

id	input id for check

Returns: Return true if id is not of type gi, ti or pig

Definition at line 2678 of file seqdbcommon.cpp.

References CDbtag_Base::CanGetDb(), CSeq_id_Base::e_General, CSeq_id_Base::e_Gi, and CDbtag_Base::GetDb().

Referenced by CSeqDBImpl::SeqidToOids(), and CBlastDBExtractor::SetSeqId().

◆ SeqDB_CombineAndQuote()

void SeqDB_CombineAndQuote	(	const vector< string > &	dbs,
		string &	dbname
	)

Combine and quote a list of database names.

SeqDB permits multiple databases to be opened by a single CSeqDB instance, by passing the database names as a space-delimited list to the CSeqDB constructor. To support paths and filenames with embedded spaces, surround any space-containing names with double quotes ('"'). Filenames not containing spaces may be quoted safely with no effect. (This solution prevents the use of names containing embedded double quotes.)

This method combines a list of database names into a string encoded in this way.

Parameters

dbname	Combined database name.
dbs	Database names to combine.

Combine and quote a list of database names.

Parameters

dbs	Database names to combine.
dbname	Combined database name.

Definition at line 1717 of file seqdbcommon.cpp.

References dbname(), i, int, and ncbi::grid::netcache::search::fields::size.

◆ SeqDB_CompareVolume()

bool SeqDB_CompareVolume	(	const string &	volpath1,
		const string &	volpath2
	)

Compares two volume file names and determine the volume order.

Parameters

volpath1	The 1st volume path
volpath2	The 2nd volume path

Returns: true if vol1 should appear before vol2

Definition at line 190 of file seqdbcommon.cpp.

References CSeqDB_Path::FindBaseName(), and CSeqDB_Substring::GetString().

Referenced by CIndexedDb_Old::CIndexedDb_Old(), and CSeqDBAliasNode::FindVolumePaths().

◆ SeqDB_GetFileExtensions()

void SeqDB_GetFileExtensions	(	bool	db_is_protein,
		vector< string > &	extensions,
		EBlastDbVersion	dbver = `eBDB_Version4`
	)

Retrieves a list of all supported file extensions for BLAST databases.

Parameters

db_is_protein	set to true if the database is protein else false [in]
extensions	where the return value will be stored [in\|out]
dbver	BLASTDB version to use [in]

Definition at line 2620 of file seqdbcommon.cpp.

References eBDB_Version4, eBDB_Version5, and SeqDB_GetLMDBFileExtensions().

Referenced by DeleteBlastDb(), CSeqDB::GetDiskUsage(), CBlastdbConvertApp::Run(), and CSeqDB::x_GetDBFilesMetaData().

◆ SeqDB_GetLMDBFileExtensions()

void SeqDB_GetLMDBFileExtensions	(	bool	db_is_protein,
		vector< string > &	extn
	)

Retrieves file extensions for BLAST LMDB files.

Parameters

db_is_protein	set to true if the database is protein else false [in]
extensions	where the return value will be stored [in\|out]

Definition at line 2659 of file seqdbcommon.cpp.

References NULL.

Referenced by DeleteBlastDb(), DeleteLMDBFiles(), and SeqDB_GetFileExtensions().

◆ SeqDB_GetMetadataFileExtension()

void SeqDB_GetMetadataFileExtension	(	bool	db_is_protein,
		string &	extn
	)

Definition at line 2671 of file seqdbcommon.cpp.

Referenced by CMakeBlastDBApp::x_BuildDatabase(), and CMakeClusterDBApp::x_BuildDatabase().

◆ SeqDB_GetOidMaskFileExt()

const string SeqDB_GetOidMaskFileExt	(	bool	db_is_protein,
		EOidMaskType	t
	)

Definition at line 2706 of file seqdbcommon.cpp.

References fExcludeModel, NCBI_THROW, and t.

Referenced by CWriteDB_CreateOidMaskDB(), and CSeqDBOIDList::x_ComputeFilters().

◆ SeqDB_IsBinaryGiList()

bool SeqDB_IsBinaryGiList ( const string & fname )

Read a text or binary SeqId list from a file.

The SeqIds in a file are read into the provided vector<string>. If the in_order parameter is not null, the function will test the SeqIds for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fname	The name of the SeqId list file. [in]
sis	The SeqIds returned by this function. [out]
in_order	If non-null, returns true iff the SeqIds were in order. [out]

void SeqDB_ReadSeqIdList(const string & fname, vector<string> & sis, bool * in_order = 0); Returns true if the file name passed contains a binary gi list

Parameters

fname The name of the GI list file. [in]

Exceptions

CSeqDBException if file is invalid or empty

Definition at line 1400 of file seqdbcommon.cpp.

References CSeqDBFileGiList::eGiList, and s_ContainsBinaryNumericIdList().

Referenced by BOOST_AUTO_TEST_CASE(), and CBlastDBAliasApp::CreateAliasFile().

◆ SeqDB_IsBinaryTiList()

bool SeqDB_IsBinaryTiList ( const string & fname )

Returns true if the file name passed contains a binary TI list.

Parameters

fname The name of the TI list file. [in]

Exceptions

CSeqDBException if file is invalid or empty

Definition at line 1395 of file seqdbcommon.cpp.

References CSeqDBFileGiList::eTiList, and s_ContainsBinaryNumericIdList().

Referenced by CBlastDBAliasApp::CreateAliasFile().

◆ SeqDB_ReadBinaryGiList()

void SeqDB_ReadBinaryGiList	(	const string &	name,
		vector< TGi > &	gis
	)

Read a binary-format GI list from a file.

Parameters

name	The name of the file containing GIs. [in]
gis	The GIs returned by this function. [out]

Definition at line 819 of file seqdbcommon.cpp.

References CMemoryFile::GetPtr(), CMemoryFile::GetSize(), GI_FROM, NCBI_THROW, SeqDB_GetStdOrd(), and SeqDB_MakeOSPath().

◆ SeqDB_ReadGiList() [1/2]

void SeqDB_ReadGiList	(	const string &	fname,
		vector< CSeqDBGiList::SGiOid > &	gis,
		bool *	in_order = `0`
	)

Read a text or binary GI list from a file.

The GIs in a file are read into the provided SGiOid vector. The GI half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the GIs for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fname	The name of the GI list file. [in]
gis	The GIs returned by this function. [out]
in_order	If non-null, returns true iff the GIs were in order. [out]

Definition at line 1405 of file seqdbcommon.cpp.

References CMemoryFile::GetPtr(), CMemoryFile::GetSize(), SeqDB_MakeOSPath(), and SeqDB_ReadMemoryGiList().

Referenced by CSeqDBFileGiList::CSeqDBFileGiList(), and SeqDB_ReadGiList().

◆ SeqDB_ReadGiList() [2/2]

void SeqDB_ReadGiList	(	const string &	fname,
		vector< TGi > &	gis,
		bool *	in_order = `0`
	)

Read a text or binary GI list from a file.

The GIs in a file are read into the provided vector<int>. If the in_order parameter is not null, the function will test the GIs for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fname	The name of the GI list file. [in]
gis	The GIs returned by this function. [out]
in_order	If non-null, returns true iff the GIs were in order. [out]

Definition at line 1462 of file seqdbcommon.cpp.

References ITERATE, and SeqDB_ReadGiList().

◆ SeqDB_ReadMemoryGiList()

void SeqDB_ReadMemoryGiList	(	const char *	fbeginp,
		const char *	fendp,
		vector< CSeqDBGiList::SGiOid > &	gis,
		bool *	in_order = `0`
	)

Read a text or binary GI list from an area of memory.

The GIs in a memory region are read into the provided SGiOid vector. The GI half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the GIs for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fbeginp	The start of the memory region holding the GI list. [in]
fendp	The end of the memory region holding the GI list. [in]
gis	The GIs returned by this function. [out]
in_order	If non-null, returns true iff the GIs were in order. [out]

Definition at line 925 of file seqdbcommon.cpp.

References _ASSERT, GI_FROM, NCBI_THROW, s_ReadDigit(), s_SeqDB_IsBinaryNumericList(), SeqDB_GetStdOrd(), and ZERO_GI.

Referenced by CSeqDBNodeFileIdList::CSeqDBNodeFileIdList(), and SeqDB_ReadGiList().

◆ SeqDB_ReadMemoryMixList()

void SeqDB_ReadMemoryMixList	(	const char *	fbeginp,
		const char *	fendp,
		vector< CSeqDBGiList::SGiOid > &	gis,
		vector< CSeqDBGiList::STiOid > &	tis,
		vector< CSeqDBGiList::SSiOid > &	sis,
		bool *	in_order
	)

Read an ID list (mixed type) from an area of memory.

The Seq ids in a memory region are read into the provided SSeqIdOid vector. The gi, ti or seqid half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the SeqIds for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fbeginp	The start of the memory region holding the SeqId list. [in]
fendp	The end of the memory region holding the SeqId list. [in]
gis	The gis returned by this function. [out]
tis	The tis returned by this function. [out]
sis	The seqids returned by this function. [out]
in_order	If non-null, returns true iff the seqids were in order. [out]

Definition at line 1324 of file seqdbcommon.cpp.

References eGiId, eStringId, eTiId, GI_FROM, head, SeqDB_SimplifyAccession(), and NStr::ToLower().

Referenced by SeqDB_ReadMixList().

◆ SeqDB_ReadMemoryPigList()

void SeqDB_ReadMemoryPigList	(	const char *	fbeginp,
		const char *	fendp,
		vector< CSeqDBGiList::SPigOid > &	pigs,
		bool *	in_order = `0`
	)

Definition at line 1005 of file seqdbcommon.cpp.

References NCBI_THROW, s_ReadDigit(), s_SeqDB_IsBinaryNumericList(), and SeqDB_GetStdOrd().

Referenced by CSeqDBNodeFileIdList::CSeqDBNodeFileIdList(), and SeqDB_ReadPigList().

◆ SeqDB_ReadMemorySiList()

void SeqDB_ReadMemorySiList	(	const char *	fbeginp,
		const char *	fendp,
		vector< CSeqDBGiList::SSiOid > &	sis,
		bool *	in_order = `0`
	)

Read a text SeqID list from an area of memory.

The Seqids in a memory region are read into the provided SSeqIdOid vector. The SeqId half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the SeqIds for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fbeginp	The start of the memory region holding the SeqId list. [in]
fendp	The end of the memory region holding the SeqId list. [in]
seqids	The SeqId returned by this function. [out]
in_order	If non-null, returns true iff the seqids were in order. [out]

Definition at line 1284 of file seqdbcommon.cpp.

References NStr::eTrunc_Both, head, and NStr::TruncateSpaces().

Referenced by CSeqDBNodeFileIdList::CSeqDBNodeFileIdList(), and SeqDB_ReadSiList().

◆ SeqDB_ReadMemoryTiList()

void SeqDB_ReadMemoryTiList	(	const char *	fbeginp,
		const char *	fendp,
		vector< CSeqDBGiList::STiOid > &	tis,
		bool *	in_order = `0`
	)

Read a text or binary TI list from an area of memory.

The TIs in a memory region are read into the provided STiOid vector. The TI half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the TIs for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fbeginp	The start of the memory region holding the TI list. [in]
fendp	The end of the memory region holding the TI list. [in]
tis	The TIs returned by this function. [out]
in_order	If non-null, returns true iff the TIs were in order. [out]

Definition at line 1149 of file seqdbcommon.cpp.

References int, NCBI_THROW, s_ReadDigit(), s_SeqDB_IsBinaryNumericList(), and SeqDB_GetStdOrd().

Referenced by CSeqDBNodeFileIdList::CSeqDBNodeFileIdList(), and SeqDB_ReadTiList().

◆ SeqDB_ReadMixList()

void SeqDB_ReadMixList	(	const string &	fname,
		vector< CSeqDBGiList::SGiOid > &	gis,
		vector< CSeqDBGiList::STiOid > &	tis,
		vector< CSeqDBGiList::SSiOid > &	sis,
		bool *	in_order
	)

Read a text SeqId list from a file.

The Seqids in a file are read into the provided SSeqIdOid vector. The Gi/Ti/Si half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the SeqIds for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fname	The name of the SeqId list file. [in]
tis	The TIs returned by this function. [out]
sis	The SeqIds returned by this function. [out]
in_order	If non-null, returns true iff the SeqIds were in order. [out]

Definition at line 1428 of file seqdbcommon.cpp.

References CMemoryFile::GetPtr(), CMemoryFile::GetSize(), SeqDB_MakeOSPath(), and SeqDB_ReadMemoryMixList().

Referenced by CSeqDBFileGiList::CSeqDBFileGiList().

◆ SeqDB_ReadPigList()

void SeqDB_ReadPigList	(	const string &	fname,
		vector< CSeqDBGiList::SPigOid > &	pigs,
		bool *	in_order = `0`
	)

Definition at line 1440 of file seqdbcommon.cpp.

References CMemoryFile::GetPtr(), CMemoryFile::GetSize(), SeqDB_MakeOSPath(), and SeqDB_ReadMemoryPigList().

Referenced by CSeqDBFileGiList::CSeqDBFileGiList().

◆ SeqDB_ReadSiList()

void SeqDB_ReadSiList	(	const string &	fname,
		vector< CSeqDBGiList::SSiOid > &	sis,
		bool *	in_order,
		SBlastSeqIdListInfo &	db_info
	)

Read a text SeqId list from a file.

The Seqids in a file are read into the provided SSeqIdOid vector. The SeqId half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the SeqIds for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fname	The name of the SeqId list file. [in]
gis	The GIs returned by this function. [out]
sis	The SeqIds returned by this function. [out]
in_order	If non-null, returns true iff the SeqIds were in order. [out]

Definition at line 1476 of file seqdbcommon.cpp.

References CMemoryFile::GetPtr(), CBlastSeqidlistFile::GetSeqidlist(), CMemoryFile::GetSize(), SeqDB_MakeOSPath(), and SeqDB_ReadMemorySiList().

Referenced by CSeqDBFileGiList::CSeqDBFileGiList().

◆ SeqDB_ReadTiList()

void SeqDB_ReadTiList	(	const string &	fname,
		vector< CSeqDBGiList::STiOid > &	tis,
		bool *	in_order = `0`
	)

Read a text or binary TI list from a file.

The TIs in a file are read into the provided STiOid vector. The TI half of each element of the vector is assigned, but the OID half will be left as -1. If the in_order parameter is not null, the function will test the TIs for orderedness. It will set the bool to which in_order points to true if so, false if not.

Parameters

fname	The name of the TI list file. [in]
tis	The TIs returned by this function. [out]
in_order	If non-null, returns true iff the TIs were in order. [out]

Definition at line 1417 of file seqdbcommon.cpp.

References CMemoryFile::GetPtr(), CMemoryFile::GetSize(), SeqDB_MakeOSPath(), and SeqDB_ReadMemoryTiList().

Referenced by CSeqDBFileGiList::CSeqDBFileGiList().

◆ SeqDB_ResolveDbPath()

string SeqDB_ResolveDbPath ( const string & filename )

Resolve a file path using SeqDB's path algorithms.

This finds a file using the same algorithm used by SeqDB to find blast database filenames. The filename must include the extension if any. Paths which start with '/', '\', or a drive letter (depending on operating system) will be treated as absolute paths. If the file is not found an empty string will be returned.

Parameters

filename Name of file to find.

Returns: Resolved path or empty string if not found.

Definition at line 453 of file seqdbcommon.cpp.

References s_SeqDB_FindBlastDBPath().

Referenced by CIndexedDb_New::AddIndexInfo(), BOOST_AUTO_TEST_CASE(), CIgAnnotationInfo::CIgAnnotationInfo(), CIndexedDb_Old::CIndexedDb_Old(), CTaxDBFileInfo::CTaxDBFileInfo(), CTaxonomy4BlastSQLite::CTaxonomy4BlastSQLite(), CBlastDatabaseArgs::ExtractAlgorithmOptions(), CIgBlastArgs::ExtractAlgorithmOptions(), CBlastSeqidlistFile::GetSeqidlistInfo(), s_GetTaxIDList(), CBlastTabularInfo::x_CheckTaxDB(), CCmdLineBlastXML2ReportData::x_InitCommon(), CSeqDBGiMask::x_Open(), CVDBAliasNode::x_ResolveDBList(), and CVDBAliasNode::x_ResolveVDBList().

◆ SeqDB_ResolveDbPathForLinkoutDB()

string SeqDB_ResolveDbPathForLinkoutDB ( const string & filename )

Resolve a file path using SeqDB's path algorithms.

Identical to SeqDB_ResolveDbPathNoExtension with the exception that this function searches for ISAM or SQLite files, specifically those storing numeric and string data (for LinkoutDB; i.e.: '.sqlite3'). This is intended to check whether the files used in LinkoutDB exist or not.

Parameters

filename Name of file to find.

Returns: Resolved path or empty string if not found.

Definition at line 472 of file seqdbcommon.cpp.

References CSeqDBAtlas::GenerateSearchPath(), and s_SeqDB_TryPaths().

◆ SeqDB_ResolveDbPathNoExtension()

string SeqDB_ResolveDbPathNoExtension	(	const string &	filename,
		char	dbtype = `'-'`
	)

Resolve a file path using SeqDB's path algorithms.

Identical to SeqDB_ResolveDbPath with the exception that this function does not require the extension to be provided. This is intended to check whether a BLAST DB exists or not.

Parameters

filename	Name of file to find.
dbtype	Determines whether the BLAST DB is protein ('p'), nucleotide ('n'), or whether the algorithm should guess it ('-')

Returns: Resolved path or empty string if not found.

Definition at line 464 of file seqdbcommon.cpp.

References s_SeqDB_FindBlastDBPath().

Referenced by CBlastDBCmdApp::Run(), s_DoesBlastDbExist(), and CVDBAliasNode::x_ResolveDBList().

◆ SeqDB_SequenceHash() [1/2]

unsigned SeqDB_SequenceHash ( const CBioseq & bs )

Sequence Hashing For a CBioseq.

This computes a hash of a sequence expressed as a CBioseq.

Parameters

sequence The sequence. [in]

Returns: The 32 bit hash value.

Sequence Hashing For a CBioseq.

Parameters

bs	The Bioseq containing the sequence.

Returns: The hash value of the sequence data.

Definition at line 156 of file seqdbobj.cpp.

References SeqDB_ComputeSequenceHash().

◆ SeqDB_SequenceHash() [2/2]

unsigned SeqDB_SequenceHash	(	const char *	sequence,
		int	length
	)

Returns a path minus filename.

Substring version of the above. This returns the part of a file Sequence Hashing

This computes a hash of a sequence. The sequence is expected to be in either ncbistdaa format (for protein) or ncbi8na format (for nucleotide). These formats are produced by CSeqDB::GetAmbigSeq() if the kSeqDBNuclNcbiNA8 encoding is selected.

Parameters

sequence	A pointer to the sequence data. [in]
length	The length of the sequence in bases. [in]

Returns: The 32 bit hash value.

Returns a path minus filename.

Parameters

sequence	A sequence in ncbi8na format.
length	Length of the sequence in bases (== bytes).

Returns: The hash value of the sequence data.

Definition at line 146 of file seqdbobj.cpp.

References SeqDB_ComputeSequenceHash().

Referenced by BOOST_AUTO_TEST_CASE(), CSeqDBImpl::GetSequenceHash(), and CWriteDB_Impl::x_ComputeHash().

◆ SeqDB_SimplifyAccession() [1/2]

const string SeqDB_SimplifyAccession ( const string & acc )

String id simplification.

This simpler version will convert string id to the standard ISAM form, and return "" if the conversion fails.

Parameters

acc	The string to look up. [in]

Returns: The resulting converted id.

Definition at line 2610 of file seqdbcommon.cpp.

References eStringId, result, and SeqDB_SimplifyAccession().

◆ SeqDB_SimplifyAccession() [2/2]

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

String id simplification.

This routine tries to produce a numerical type from a string identifier. SeqDB can use faster lookup mechanisms if a PIG, GI, or OID type can be recognized in the string, for example. Even when the output is a string, it may be better formed for the purpose of lookup in the string ISAM file.

Parameters

acc	The string to look up. [in]
num_id	The returned identifier, if numeric. [out]
str_id	The returned identifier, if a string. [out]
simpler	Whether an adjustment was done at all. [out]

Returns: The resulting identifier type.

Definition at line 2535 of file seqdbcommon.cpp.

References CSeq_id::BestRank(), NStr::EqualNocase(), eStringId, NStr::fConvErr_NoThrow, FindBestChoice(), NULL, CSeq_id::ParseFastaIds(), result, s_SeqDB_ParseSeqIDs(), SeqDB_SimplifySeqid(), NStr::SplitInTwo(), and NStr::ToLower().

Referenced by CSeqDBVol::AccessionToOids(), CInputGiList::AppendSi(), BOOST_AUTO_TEST_CASE(), CSeqDBGiList::PreprocessIdsForISAMSiLookup(), CSeqDBNegativeList::PreprocessIdsForISAMSiLookup(), SeqDB_ReadMemoryMixList(), and SeqDB_SimplifyAccession().

◆ SeqDB_SimplifySeqid()

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

Seq-id simplification.

Given a Seq-id, this routine devolves it to a GI or PIG if possible. If not, it formats the Seq-id into a canonical form for lookup in the string ISAM files. If the Seq-id was parsed from an accession, it can be provided in the "acc" parameter, and it will be used if the Seq-id is not in a form this code can recognize. In the case that new Seq-id types are added, support for which has not been added to this code, this mechanism will try to use the original string.

Parameters

bestid	The Seq-id to look up. [in]
acc	The original string the Seq-id was created from (or NULL). [in]
num_id	The returned identifier, if numeric. [out]
str_id	The returned identifier, if a string. [out]
simpler	Whether an adjustment was done at all. [out]

Returns: The resulting identifier type.

Definition at line 2264 of file seqdbcommon.cpp.

References CSeq_id::AsFastaString(), CTextseq_id_Base::CanGetAccession(), CDbtag_Base::CanGetDb(), CTextseq_id_Base::CanGetName(), CDbtag_Base::CanGetTag(), CTextseq_id_Base::CanGetVersion(), NStr::CompareNocase(), CSeq_id_Base::e_Ddbj, CSeq_id_Base::e_Embl, CSeq_id_Base::e_Genbank, CSeq_id_Base::e_General, CSeq_id_Base::e_Gi, CSeq_id_Base::e_Gibbsq, CSeq_id_Base::e_Gpipe, CSeq_id_Base::e_Local, CSeq_id_Base::e_Other, CSeq_id_Base::e_Pir, CSeq_id_Base::e_Prf, CSeq_id_Base::e_Swissprot, CSeq_id_Base::e_Tpd, CSeq_id_Base::e_Tpe, CSeq_id_Base::e_Tpg, CSeq_id::eFasta, eGiId, eOID, ePigId, eStringId, eTiId, CSeq_id::fLabel_GeneralDbIsContent, CSeq_id::fLabel_Version, CTextseq_id_Base::GetAccession(), CDbtag_Base::GetDb(), CSeq_id_Base::GetGeneral(), CSeq_id_Base::GetGi(), CSeq_id_Base::GetGibbsq(), CObject_id_Base::GetId(), CSeq_id::GetLabel(), CSeq_id_Base::GetLocal(), CTextseq_id_Base::GetName(), CObject_id_Base::GetStr(), CDbtag_Base::GetTag(), CSeq_id::GetTextseq_Id(), CTextseq_id_Base::GetVersion(), GI_TO, NStr::IntToString(), CObject_id_Base::IsStr(), result, NStr::StringToInt8(), NStr::ToLower(), NStr::UIntToString(), and CSeq_id_Base::Which().

Referenced by CSeqDBGiList::FindId(), CSeqDBNegativeList::FindId(), SeqDB_SimplifyAccession(), CSeqDBVol::SeqidToOids(), and CBlastDB_BioseqFormatter::Write().

◆ SeqDB_SplitQuoted()

void SeqDB_SplitQuoted	(	const string &	dbname,
		vector< CTempString > &	dbs,
		bool	keep_quote = `false`
	)

Split a (possibly) quoted list of database names into pieces.

SeqDB permits multiple databases to be opened by a single CSeqDB instance, by passing the database names as a space-delimited list to the CSeqDB constructor. To support paths and filenames with embedded spaces, surround any space-containing names with double quotes ('"'). Filenames not containing spaces may be quoted safely with no effect. (This solution prevents the use of names containing embedded double quotes.)

This method splits a string encoded in this way into individual database names. Note that the resulting vector's objects are CTempString "slice" objects, and are only valid while the original (encoded) string is unchanged.

Parameters

dbname	Combined database name.
dbs	Database names to combine.

Definition at line 1744 of file seqdbcommon.cpp.

References dbname(), ITERATE, and tmp.

◆ USING_SCOPE()

USING_SCOPE ( objects )

Include definitions from the objects namespace.

Variable Documentation

◆ kSeqDBEntryDuplicate

const blastdb::TOid kSeqDBEntryDuplicate = -2

Definition at line 126 of file seqdbcommon.hpp.

◆ kSeqDBEntryNotFound

const blastdb::TOid kSeqDBEntryNotFound = -1

Definition at line 125 of file seqdbcommon.hpp.

Referenced by CSeqDBImpl::AccessionsToOids(), CSeqDBLMDBSet::AccessionsToOids(), BOOST_AUTO_TEST_CASE(), CSeqDBLMDB::GetOids(), CSeqDBLMDB::NegativeSeqIdsToOids(), s_ProcessSeqIdFilters(), WriteBlastSeqidlistFile(), CSeqDBLMDBEntry::x_AdjustOidsOffset(), and CBlastDBCmdApp::x_ProcessBatchEntry_NoDup().

◆ kSeqDBGroupAliasFileName

const string kSeqDBGroupAliasFileName

extern

The name of the group alias file name expected at each directory For more documentation, see "Group Alias Files" in source/src/objtools/blast/seqdb_reader/alias_files.txt.

Referenced by CWriteDB_ConsolidateAliasFiles(), and CSeqDBAliasSets::x_DbToIndexName().

◆ kSeqDBNuclBlastNA8

const int kSeqDBNuclBlastNA8 = 1

Used to request ambiguities in BLAST/NA8 format.

Definition at line 123 of file seqdbcommon.hpp.

Referenced by BOOST_AUTO_TEST_CASE(), CSeqDBVol::GetAmbigPartialSeq(), and CSeqDBVol::x_GetAmbigSeq().

◆ kSeqDBNuclNcbiNA8

const int kSeqDBNuclNcbiNA8 = 0

Used to request ambiguities in Ncbi/NA8 format.

Definition at line 120 of file seqdbcommon.hpp.

Referenced by BOOST_AUTO_TEST_CASE(), CSeqDBVol::GetSeqData(), CLocalBlastDbAdapter::GetSequence(), CSeqDB::GetSequenceAsString(), CSeqDBImpl::GetSequenceHash(), s_TestPartialAmbigRange(), and CSeqDBDemo_Thread::x_UseOID().

Classes

Typedefs

Enumerations

Functions

Variables

Detailed Description

Typedef Documentation

◆ TOid

◆ TPig

◆ TSeqDBAliasFileInstance

◆ TSeqDBAliasFileValues

◆ TSeqDBAliasFileVersions

◆ TTi

Enumeration Type Documentation

◆ EBlastDbVersion

◆ EOidMaskType

◆ ESeqDBAllocType

◆ ESeqDBIdType

Function Documentation

◆ GetBlastSeqIdString()

◆ IsStringId()

◆ SeqDB_CombineAndQuote()

◆ SeqDB_CompareVolume()

◆ SeqDB_GetFileExtensions()

◆ SeqDB_GetLMDBFileExtensions()

◆ SeqDB_GetMetadataFileExtension()

◆ SeqDB_GetOidMaskFileExt()

◆ SeqDB_IsBinaryGiList()

◆ SeqDB_IsBinaryTiList()

◆ SeqDB_ReadBinaryGiList()

◆ SeqDB_ReadGiList() [1/2]

◆ SeqDB_ReadGiList() [2/2]

◆ SeqDB_ReadMemoryGiList()

◆ SeqDB_ReadMemoryMixList()

◆ SeqDB_ReadMemoryPigList()

◆ SeqDB_ReadMemorySiList()

◆ SeqDB_ReadMemoryTiList()

◆ SeqDB_ReadMixList()

◆ SeqDB_ReadPigList()

◆ SeqDB_ReadSiList()

◆ SeqDB_ReadTiList()

◆ SeqDB_ResolveDbPath()

◆ SeqDB_ResolveDbPathForLinkoutDB()

◆ SeqDB_ResolveDbPathNoExtension()

◆ SeqDB_SequenceHash() [1/2]

◆ SeqDB_SequenceHash() [2/2]

◆ SeqDB_SimplifyAccession() [1/2]

◆ SeqDB_SimplifyAccession() [2/2]

◆ SeqDB_SimplifySeqid()

◆ SeqDB_SplitQuoted()

◆ USING_SCOPE()

Variable Documentation

◆ kSeqDBEntryDuplicate

◆ kSeqDBEntryNotFound

◆ kSeqDBGroupAliasFileName

◆ kSeqDBNuclBlastNA8

◆ kSeqDBNuclNcbiNA8