Class for managing LDS2 database and related data files. More...

#include <objtools/lds2/lds2.hpp>

Inheritance diagram for CLDS2_Manager:

Collaboration diagram for CLDS2_Manager:

Public Types
enum	EDirMode { eDir_NoRecurse , eDir_Recurse }
	Directory parsing mode while indexing files. More...

enum	EGBReleaseMode { eGB_Ignore , eGB_Guess , eGB_Force }
	Control indexing of GB releases (bioseq-sets). More...

enum	EDuplicateIdMode { eDuplicate_Skip , eDuplicate_Store , eDuplicate_Throw }
	Control seq-id conflict resolving during file parsing. More...

enum	EErrorMode { eError_Silent , eError_Report , eError_Throw }
	Error handling while indexing files. 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
	CLDS2_Manager (const string &db_file)
	Create LDS2 manager for the specified db file. More...

virtual	~CLDS2_Manager (void)

const string &	GetDbFile (void) const
	Get currently selected database name. More...

CLDS2_Database *	GetDatabase (void)
	Get the current database object. More...

void	SetDbFile (const string &db_file)
	Select new database. More...

void	AddDataFile (const string &data_file)
	Add new data file to the list. More...

void	AddDataDir (const string &data_dir, EDirMode mode=eDir_Recurse)
	Add data directory. More...

void	RegisterUrlHandler (CLDS2_UrlHandler_Base *handler)
	Register a URL handler. More...

void	AddDataUrl (const string &url, const string &handler_name)
	Add a URL. More...

void	ResetData (void)
	Remove all data from the database. More...

void	UpdateData (void)
	Rescan all indexed files, check for modifications, update the database. More...

EGBReleaseMode	GetGBReleaseMode (void) const

void	SetGBReleaseMode (EGBReleaseMode mode)

EDuplicateIdMode	GetDuplicateIdMode (void) const

void	SetDuplicateIdMode (EDuplicateIdMode mode)

int	GetSeqAlignGroupSize (void) const
	Control grouping of standalone seq-aligns into bigger blobs. More...

void	SetSeqAlignGroupSize (int sz)

EErrorMode	GetErrorMode (void) const

void	SetErrorMode (EErrorMode mode)

CFastaReader::TFlags	GetFastaFlags (void) const
	Fasta reader settings. More...

void	SetFastaFlags (CFastaReader::TFlags flags)

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

Private Types
typedef CLDS2_Database::TStringSet	TFiles

typedef map< string, CRef< CLDS2_UrlHandler_Base > >	THandlers

typedef map< string, string >	THandlersByUrl

Private Member Functions
bool	x_IsGZipFile (const SLDS2_File &file_info)

CLDS2_UrlHandler_Base *	x_GetUrlHandler (const SLDS2_File &file_info)

SLDS2_File	x_GetFileInfo (const string &file_name, CRef< CLDS2_UrlHandler_Base > &handler)

void	x_ParseFile (const SLDS2_File &info, CLDS2_UrlHandler_Base &handler)

Additional Inherited Members
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)

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

Class for managing LDS2 database and related data files.

Definition at line 45 of file lds2.hpp.

Member Typedef Documentation

◆ TFiles

typedef CLDS2_Database::TStringSet CLDS2_Manager::TFiles

private

Definition at line 145 of file lds2.hpp.

◆ THandlers

typedef map<string, CRef<CLDS2_UrlHandler_Base> > CLDS2_Manager::THandlers

private

Definition at line 159 of file lds2.hpp.

◆ THandlersByUrl

typedef map<string, string> CLDS2_Manager::THandlersByUrl

private

Definition at line 161 of file lds2.hpp.

Member Enumeration Documentation

◆ EDirMode

enum CLDS2_Manager::EDirMode

Directory parsing mode while indexing files.

Enumerator
eDir_NoRecurse	Do not parse sub-dirs automatically.
eDir_Recurse	Automatically scan sub-directories (default).

Definition at line 71 of file lds2.hpp.

◆ EDuplicateIdMode

enum CLDS2_Manager::EDuplicateIdMode

Control seq-id conflict resolving during file parsing.

Enumerator

eDuplicate_Skip

Ignore bioseqs with duplicate ids, store just the first one.

eDuplicate_Store

Store all bioseqs regardless of seq-id conflicts (defalut).

The conflict may be resolved later by data loader.

eDuplicate_Throw

Throw exception on bioseqs with duplicate seq-ids.

Definition at line 109 of file lds2.hpp.

◆ EErrorMode

enum CLDS2_Manager::EErrorMode

Error handling while indexing files.

NOTE: Only a few kinds of errors can be ignored (unsupported file format or object type, broken data file etc.).

Enumerator
eError_Silent	Try to ignore errors, continue indexing.
eError_Report	Print error messages, but do not fail (default).
eError_Throw	Throw exceptions on errors.

Definition at line 131 of file lds2.hpp.

◆ EGBReleaseMode

enum CLDS2_Manager::EGBReleaseMode

Control indexing of GB releases (bioseq-sets).

Enumerator
eGB_Ignore	Do not split bioseq-sets (default)
eGB_Guess	Try to autodetect and split GB release bioseq-sets.
eGB_Force	Split all top-level bioseq-sets into seq-entries.

Definition at line 99 of file lds2.hpp.

Constructor & Destructor Documentation

◆ CLDS2_Manager()

CLDS2_Manager::CLDS2_Manager ( const string & db_file )

Create LDS2 manager for the specified db file.

If the file does not exist, it will be created only after adding at least one data file and indexing it.

Definition at line 879 of file lds2.cpp.

References RegisterUrlHandler(), and SetDbFile().

◆ ~CLDS2_Manager()

CLDS2_Manager::~CLDS2_Manager ( void )

virtual

Definition at line 897 of file lds2.cpp.

Member Function Documentation

◆ AddDataDir()

void CLDS2_Manager::AddDataDir	(	const string &	data_dir,
		EDirMode	mode = `eDir_Recurse`
	)

Add data directory.

All files in the directory are added to the list. If the mode is eDir_Recurse, also adds all subdirectories. Call UpdateData to parse and index the files.

Definition at line 930 of file lds2.cpp.

References AddDataFile(), eDir_Recurse, CDir::fIgnoreRecursive, CDir::GetEntries(), CDirEntry::GetPath(), CDirEntry::IsDir(), CDirEntry::IsFile(), and ITERATE.

Referenced by CSplignApp::Run(), CLDS2IndexerApplication::Run(), and CDemoApp::Run().

◆ AddDataFile()

void CLDS2_Manager::AddDataFile ( const string & data_file )

Add new data file to the list.

This will not parse and index the new file - call UpdateData().

Definition at line 923 of file lds2.cpp.

References CDirEntry::CreateAbsolutePath(), set< Key, Compare >::insert(), and m_Files.

Referenced by AddDataDir().

◆ AddDataUrl()

void CLDS2_Manager::AddDataUrl	(	const string &	url,
		const string &	handler_name
	)

Add a URL.

The handler is used to access the URL and must be registered in the manager before adding the URL.

Definition at line 1192 of file lds2.cpp.

References set< Key, Compare >::insert(), m_Files, and m_HandlersByUrl.

◆ GetDatabase()

CLDS2_Database* CLDS2_Manager::GetDatabase ( void )

inline

Get the current database object.

Definition at line 59 of file lds2.hpp.

Referenced by CLDS2IndexerApplication::Run().

◆ GetDbFile()

const string & CLDS2_Manager::GetDbFile ( void ) const

inline

Get currently selected database name.

Definition at line 176 of file lds2.hpp.

References _ASSERT, CLDS2_Database::GetDbFile(), and m_Db.

◆ GetDuplicateIdMode()

EDuplicateIdMode CLDS2_Manager::GetDuplicateIdMode ( void ) const

inline

Definition at line 119 of file lds2.hpp.

Referenced by CLDS2_ObjectParser::EndBlob().

◆ GetErrorMode()

EErrorMode CLDS2_Manager::GetErrorMode ( void ) const

inline

Definition at line 137 of file lds2.hpp.

◆ GetFastaFlags()

CFastaReader::TFlags CLDS2_Manager::GetFastaFlags ( void ) const

inline

Fasta reader settings.

Definition at line 141 of file lds2.hpp.

◆ GetGBReleaseMode()

EGBReleaseMode CLDS2_Manager::GetGBReleaseMode ( void ) const

inline

Definition at line 105 of file lds2.hpp.

◆ GetSeqAlignGroupSize()

int CLDS2_Manager::GetSeqAlignGroupSize ( void ) const

inline

Control grouping of standalone seq-aligns into bigger blobs.

If set to 0 or 1, no grouping is performed, each seq-align becomes a separate blob.

Definition at line 125 of file lds2.hpp.

◆ RegisterUrlHandler()

void CLDS2_Manager::RegisterUrlHandler ( CLDS2_UrlHandler_Base * handler )

Register a URL handler.

Using handlers allows to use special storage types like compressed files, ftp or http locations etc. The same handler must be registered in the data loader when using LDS2 to fetch data. The default handlers "file" and "gzipfile" for local files are registered automatically.

Definition at line 902 of file lds2.cpp.

References _ASSERT, m_Handlers, and Ref().

Referenced by CLDS2_Manager().

◆ ResetData()

void CLDS2_Manager::ResetData ( void )

Remove all data from the database.

Definition at line 916 of file lds2.cpp.

References set< Key, Compare >::clear(), CLDS2_Database::Create(), m_Db, and m_Files.

◆ SetDbFile()

void CLDS2_Manager::SetDbFile ( const string & db_file )

Select new database.

If the database does not yet exist, it is not created immediately. The list of data files is cleared.

Definition at line 909 of file lds2.cpp.

References set< Key, Compare >::clear(), m_Db, m_Files, and CRef< C, Locker >::Reset().

Referenced by CLDS2_Manager().

◆ SetDuplicateIdMode()

void CLDS2_Manager::SetDuplicateIdMode ( EDuplicateIdMode mode )

inline

Definition at line 120 of file lds2.hpp.

◆ SetErrorMode()

void CLDS2_Manager::SetErrorMode ( EErrorMode mode )

inline

Definition at line 138 of file lds2.hpp.

◆ SetFastaFlags()

void CLDS2_Manager::SetFastaFlags ( CFastaReader::TFlags flags )

inline

Definition at line 142 of file lds2.hpp.

References flags.

◆ SetGBReleaseMode()

void CLDS2_Manager::SetGBReleaseMode ( EGBReleaseMode mode )

inline

Definition at line 106 of file lds2.hpp.

Referenced by CLDS2IndexerApplication::Run().

◆ SetSeqAlignGroupSize()

void CLDS2_Manager::SetSeqAlignGroupSize ( int sz )

inline

Definition at line 126 of file lds2.hpp.

Referenced by CLDS2IndexerApplication::Run().

◆ UpdateData()

void CLDS2_Manager::UpdateData ( void )

Rescan all indexed files, check for modifications, update the database.

Definition at line 1016 of file lds2.cpp.

References _ASSERT, CLDS2_Database::AddFile(), CLDS2_Database::BeginUpdate(), CLDS2_Database::Create(), CLDS2_Database::DeleteFile(), eError_Report, eError_Throw, CLDS2_Database::EndUpdate(), ERR_POST_X, Error(), CDirEntry::Exists(), SLDS2_File::exists(), SLDS2_File::format, CLDS2_Database::GetDbFile(), CLDS2_Database::GetFileInfo(), CLDS2_Database::GetFileNames(), SLDS2_File::id, IsSupportedFormat(), ITERATE, LDS2_THROW, m_Db, m_ErrorMode, m_Files, CLDS2_Database::Open(), CLDS2_Database::UpdateFile(), x_GetFileInfo(), and x_ParseFile().

Referenced by CSplignApp::Run(), CLDS2IndexerApplication::Run(), and CDemoApp::Run().

◆ x_GetFileInfo()

SLDS2_File CLDS2_Manager::x_GetFileInfo	(	const string &	file_name,
		CRef< CLDS2_UrlHandler_Base > &	handler
	)

private

Definition at line 985 of file lds2.cpp.

References file_name, info, and x_GetUrlHandler().

Referenced by UpdateData().

◆ x_GetUrlHandler()

CLDS2_UrlHandler_Base * CLDS2_Manager::x_GetUrlHandler ( const SLDS2_File & file_info )

private

Definition at line 954 of file lds2.cpp.

References eError_Report, eError_Throw, map_checker< Container >::end(), ERR_POST_X, Error(), map_checker< Container >::find(), LDS2_THROW, m_ErrorMode, m_Handlers, m_HandlersByUrl, SLDS2_File::name, NULL, CLDS2_UrlHandler_File::s_GetHandlerName(), CLDS2_UrlHandler_GZipFile::s_GetHandlerName(), and x_IsGZipFile().

Referenced by x_GetFileInfo().

◆ x_IsGZipFile()

bool CLDS2_Manager::x_IsGZipFile ( const SLDS2_File & file_info )

private

Definition at line 946 of file lds2.cpp.

References CFormatGuess::eGZip, CFormatGuess::Format(), in(), and SLDS2_File::name.

Referenced by x_GetUrlHandler().

◆ x_ParseFile()

void CLDS2_Manager::x_ParseFile	(	const SLDS2_File &	info,
		CLDS2_UrlHandler_Base &	handler
	)

private

Member Data Documentation

◆ m_Db

CRef<CLDS2_Database> CLDS2_Manager::m_Db

private

Definition at line 163 of file lds2.hpp.

Referenced by GetDbFile(), ResetData(), SetDbFile(), UpdateData(), and x_ParseFile().

◆ m_DupIdMode

EDuplicateIdMode CLDS2_Manager::m_DupIdMode

private

Definition at line 167 of file lds2.hpp.

◆ m_ErrorMode

EErrorMode CLDS2_Manager::m_ErrorMode

private

Definition at line 168 of file lds2.hpp.

Referenced by UpdateData(), x_GetUrlHandler(), and x_ParseFile().

◆ m_FastaFlags

CFastaReader::TFlags CLDS2_Manager::m_FastaFlags

private

Definition at line 169 of file lds2.hpp.

Referenced by x_ParseFile().

◆ m_Files

TFiles CLDS2_Manager::m_Files

private

Definition at line 164 of file lds2.hpp.

Referenced by AddDataFile(), AddDataUrl(), ResetData(), SetDbFile(), and UpdateData().

◆ m_GBReleaseMode

EGBReleaseMode CLDS2_Manager::m_GBReleaseMode

private

Definition at line 166 of file lds2.hpp.

◆ m_Handlers

THandlers CLDS2_Manager::m_Handlers

private

Definition at line 170 of file lds2.hpp.

Referenced by RegisterUrlHandler(), and x_GetUrlHandler().

◆ m_HandlersByUrl

THandlersByUrl CLDS2_Manager::m_HandlersByUrl

private

Definition at line 165 of file lds2.hpp.

Referenced by AddDataUrl(), and x_GetUrlHandler().

◆ m_SeqAlignGroupSize

int CLDS2_Manager::m_SeqAlignGroupSize

private

Definition at line 171 of file lds2.hpp.

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

include/objtools/lds2/lds2.hpp
src/objtools/lds2/lds2.cpp

Private Attributes
CRef< CLDS2_Database >	m_Db

TFiles	m_Files

THandlersByUrl	m_HandlersByUrl

EGBReleaseMode	m_GBReleaseMode

EDuplicateIdMode	m_DupIdMode

EErrorMode	m_ErrorMode

CFastaReader::TFlags	m_FastaFlags

THandlers	m_Handlers

int	m_SeqAlignGroupSize

Public Types

Public Member Functions

Private Types

Private Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ TFiles

◆ THandlers

◆ THandlersByUrl

Member Enumeration Documentation

◆ EDirMode

◆ EDuplicateIdMode

◆ EErrorMode

◆ EGBReleaseMode

Constructor & Destructor Documentation

◆ CLDS2_Manager()

◆ ~CLDS2_Manager()

Member Function Documentation

◆ AddDataDir()

◆ AddDataFile()

◆ AddDataUrl()

◆ GetDatabase()

◆ GetDbFile()

◆ GetDuplicateIdMode()

◆ GetErrorMode()

◆ GetFastaFlags()

◆ GetGBReleaseMode()

◆ GetSeqAlignGroupSize()

◆ RegisterUrlHandler()

◆ ResetData()

◆ SetDbFile()

◆ SetDuplicateIdMode()

◆ SetErrorMode()

◆ SetFastaFlags()

◆ SetGBReleaseMode()

◆ SetSeqAlignGroupSize()

◆ UpdateData()

◆ x_GetFileInfo()

◆ x_GetUrlHandler()

◆ x_IsGZipFile()

◆ x_ParseFile()

Member Data Documentation

◆ m_Db

◆ m_DupIdMode

◆ m_ErrorMode

◆ m_FastaFlags

◆ m_Files

◆ m_GBReleaseMode

◆ m_Handlers

◆ m_HandlersByUrl

◆ m_SeqAlignGroupSize