Definition at line 61 of file RTTreeDS.hxx.

Public Member Functions
	RTTreeDS (const RTTreeDS &)=delete
	RTTreeDS (RTTreeDS &&)=delete
	RTTreeDS (std::shared_ptr< TTree > tree)
	RTTreeDS (std::shared_ptr< TTree > tree, const ROOT::TreeUtils::RFriendInfo &friendInfo)
	RTTreeDS (std::string_view treeName, const std::vector< std::string > &fileNameGlobs)
	RTTreeDS (std::string_view treeName, std::string_view fileNameGlob)
	RTTreeDS (std::string_view treeName, TDirectory *dirPtr)
	~RTTreeDS () final
std::string	AsString () final
std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase >	CreateColumnReader (unsigned int slot, std::string_view col, const std::type_info &tid, TTreeReader *treeReader) final
	Creates a column reader for the requested column.
std::string	DescribeDataset () final
void	Finalize () final
	Convenience method called after concluding an event-loop.
virtual void	FinalizeSlot (unsigned int)
	Convenience method called at the end of the data processing associated to a slot.
const std::vector< std::string > &	GetColumnNames () const final
	Returns a reference to the collection of the dataset's column names.
const std::vector< std::string > &	GetColumnNamesNoDuplicates () const final
std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase >	GetColumnReaders (unsigned int, std::string_view, const std::type_info &) final
	If the other GetColumnReaders overload returns an empty vector, this overload will be called instead.
template<typename T>
std::vector< T ** >	GetColumnReaders (std::string_view columnName)
	Called at most once per column by RDF.
Record_t	GetColumnReadersImpl (std::string_view, const std::type_info &) final
	type-erased vector of pointers to pointers to column values - one per slot
std::vector< std::pair< ULong64_t, ULong64_t > >	GetEntryRanges () final
	Return ranges of entries to distribute to tasks.
std::string	GetLabel () final
	Return a string representation of the datasource type.
std::size_t	GetNFiles () const final
	Returns the number of files from which the dataset is constructed.
const std::vector< std::string > &	GetTopLevelFieldNames () const final
TTree *	GetTree ()
std::string	GetTypeName (std::string_view colName) const final
	Type of a column as a string, e.g.
std::string	GetTypeNameWithOpts (std::string_view colName, bool vector2RVec) const final
bool	HasColumn (std::string_view colName) const final
	Checks if the dataset has a certain column.
void	Initialize () final
	Convenience method called before starting an event-loop.
void	InitializeWithOpts (const std::set< std::string > &suppressErrorsForMissingBranches) final
virtual void	InitSlot (unsigned int, ULong64_t)
	Convenience method called at the start of the data processing associated to a slot.
RTTreeDS &	operator= (const RTTreeDS &)=delete
RTTreeDS &	operator= (RTTreeDS &&)=delete
void	ProcessMT (ROOT::Detail::RDF::RLoopManager &lm) final
bool	SetEntry (unsigned int, ULong64_t entry) final
	Advance the "cursors" returned by GetColumnReaders to the selected entry for a particular slot.
virtual void	SetGlobalEntryRange (std::pair< ULong64_t, ULong64_t > entryRange)
	Restrict processing to a [begin, end) range of entries.
virtual void	SetNSlots (unsigned int nSlots)
	Inform RDataSource of the number of processing slots (i.e.

Protected Types
using	Record_t = std::vector<void *>

Protected Attributes
std::optional< std::pair< ULong64_t, ULong64_t > >	fGlobalEntryRange {}
unsigned int	fNSlots {}

Private Member Functions
ROOT::RDF::RSampleInfo	CreateSampleInfo (unsigned int, const std::unordered_map< std::string, ROOT::RDF::Experimental::RSample * > &sampleMap) const final
std::vector< std::pair< ULong64_t, ULong64_t > >	GetTChainEntryRange (TChain &chain)
std::vector< std::pair< ULong64_t, ULong64_t > >	GetTTreeEntryRange (TTree &tree)
void	RunFinalChecks (bool nodesLeftNotRun) const final
void	Setup (std::shared_ptr< TTree > &&tree, const ROOT::TreeUtils::RFriendInfo *friendInfo=nullptr)

Private Attributes
std::vector< std::string >	fBranchNamesWithDuplicates {}
std::vector< std::string >	fBranchNamesWithoutDuplicates {}
std::vector< std::unique_ptr< TChain > >	fFriends
std::unique_ptr< ROOT::Internal::TreeUtils::RNoCleanupNotifier >	fNoCleanupNotifier
std::vector< std::string >	fTopLevelBranchNames {}
std::shared_ptr< TTree >	fTree
std::unique_ptr< TTreeReader >	fTreeReader

#include <ROOT/RTTreeDS.hxx>

Inheritance diagram for ROOT::Internal::RDF::RTTreeDS:

Member Typedef Documentation

◆ Record_t

using ROOT::RDF::RDataSource::Record_t = std::vector<void *>

protectedinherited

Definition at line 142 of file RDataSource.hxx.

Constructor & Destructor Documentation

◆ RTTreeDS() [1/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS ( std::shared_ptr< TTree > tree )

Definition at line 282 of file RTTreeDS.cxx.

◆ RTTreeDS() [2/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS	(	std::shared_ptr< TTree >	tree,
		const ROOT::TreeUtils::RFriendInfo &	friendInfo )

Definition at line 288 of file RTTreeDS.cxx.

◆ RTTreeDS() [3/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS	(	std::string_view	treeName,
		TDirectory *	dirPtr )

Definition at line 294 of file RTTreeDS.cxx.

◆ RTTreeDS() [4/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS	(	std::string_view	treeName,
		std::string_view	fileNameGlob )

Definition at line 318 of file RTTreeDS.cxx.

◆ RTTreeDS() [5/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS	(	std::string_view	treeName,
		const std::vector< std::string > &	fileNameGlobs )

Definition at line 337 of file RTTreeDS.cxx.

◆ RTTreeDS() [6/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS ( const RTTreeDS & )

delete

◆ RTTreeDS() [7/7]

ROOT::Internal::RDF::RTTreeDS::RTTreeDS ( RTTreeDS && )

delete

◆ ~RTTreeDS()

ROOT::Internal::RDF::RTTreeDS::~RTTreeDS ( )

final

Definition at line 255 of file RTTreeDS.cxx.

Member Function Documentation

◆ AsString()

std::string ROOT::Internal::RDF::RTTreeDS::AsString ( )

inlinefinalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 150 of file RTTreeDS.hxx.

◆ CreateColumnReader()

std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase > ROOT::Internal::RDF::RTTreeDS::CreateColumnReader	(	unsigned int	slot,
		std::string_view	col,
		const std::type_info &	tid,
		TTreeReader *	)

finalvirtual

Creates a column reader for the requested column.

In the general case, this is just a redirect to the right GetColumnReaders overload. The signature notably also has a TTreeReader * parameter. This is currently necessary to still allow the TTree-based MT scheduling via TTreeProcessorMT. We use the TTreeProcessorMT::Process method to launch the same kernel across all threads. In each thread task, TTreeProcessorMT creates a thread-local instance of a TTreeReader which is going to read the range of events assigned to that task. That TTreeReader instance is what is passed to this method whenever a column reader needs to be created in a thread task. In the future this method might be removed by either allowing to request a handle to the thread-local TTreeReader instance programmatically from the TTreeProcessorMT, or refactoring the TTreeProcessorMT scheduling into RTTreeDS altogether.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 504 of file RTTreeDS.cxx.

◆ CreateSampleInfo()

ROOT::RDF::RSampleInfo ROOT::Internal::RDF::RTTreeDS::CreateSampleInfo	(	unsigned int	,
		const std::unordered_map< std::string, ROOT::RDF::Experimental::RSample * > &	sampleMap ) const

finalprivatevirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 368 of file RTTreeDS.cxx.

◆ DescribeDataset()

std::string ROOT::Internal::RDF::RTTreeDS::DescribeDataset ( )

finalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 438 of file RTTreeDS.cxx.

◆ Finalize()

void ROOT::Internal::RDF::RTTreeDS::Finalize ( )

finalvirtual

Convenience method called after concluding an event-loop.

See Initialize for more details.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 633 of file RTTreeDS.cxx.

◆ FinalizeSlot()

virtual void ROOT::RDF::RDataSource::FinalizeSlot ( unsigned int )

inlinevirtualinherited

Convenience method called at the end of the data processing associated to a slot.

Parameters

[in] slot The data processing slot wihch needs to be finalized This method might be called multiple times per thread per event-loop.

Reimplemented in ROOT::Internal::RDF::RRootDS, and ROOT::RDF::RNTupleDS.

Definition at line 311 of file RDataSource.hxx.

◆ GetColumnNames()

const std::vector< std::string > & ROOT::Internal::RDF::RTTreeDS::GetColumnNames ( ) const

inlinefinalvirtual

Returns a reference to the collection of the dataset's column names.

Implements ROOT::RDF::RDataSource.

Definition at line 107 of file RTTreeDS.hxx.

◆ GetColumnNamesNoDuplicates()

const std::vector< std::string > & ROOT::Internal::RDF::RTTreeDS::GetColumnNamesNoDuplicates ( ) const

inlinefinalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 144 of file RTTreeDS.hxx.

◆ GetColumnReaders() [1/2]

std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase > ROOT::Internal::RDF::RTTreeDS::GetColumnReaders	(	unsigned int	,
		std::string_view	,
		const std::type_info &	)

inlinefinalvirtual

If the other GetColumnReaders overload returns an empty vector, this overload will be called instead.

Parameters

[in]	slot	The data processing slot that needs to be considered
[in]	name	The name of the column for which a column reader needs to be returned
[in]	tid	A type_info At least one of the two must return a non-empty/non-null value.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 128 of file RTTreeDS.hxx.

◆ GetColumnReaders() [2/2]

template<typename T>

std::vector< T ** > ROOT::RDF::RDataSource::GetColumnReaders ( std::string_view columnName )

inlineinherited

Called at most once per column by RDF.

Return vector of pointers to pointers to column values - one per slot.

Template Parameters

T	The type of the data stored in the column

Parameters

[in] columnName The name of the column

These pointers are veritable cursors: it's a responsibility of the RDataSource implementation that they point to the "right" memory region.

Definition at line 248 of file RDataSource.hxx.

◆ GetColumnReadersImpl()

Record_t ROOT::Internal::RDF::RTTreeDS::GetColumnReadersImpl	(	std::string_view	name,
		const std::type_info &	)

inlinefinalvirtual

type-erased vector of pointers to pointers to column values - one per slot

Implements ROOT::RDF::RDataSource.

Definition at line 121 of file RTTreeDS.hxx.

◆ GetEntryRanges()

std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::Internal::RDF::RTTreeDS::GetEntryRanges ( )

finalvirtual

Return ranges of entries to distribute to tasks.

They are required to be contiguous intervals with no entries skipped. Supposing a dataset with nEntries, the intervals must start at 0 and end at nEntries, e.g. [0-5],[5-10] for 10 entries. This function will be invoked repeatedly by RDataFrame as it needs additional entries to process. The same entry range should not be returned more than once. Returning an empty collection of ranges signals to RDataFrame that the processing can stop.

Implements ROOT::RDF::RDataSource.

Definition at line 610 of file RTTreeDS.cxx.

◆ GetLabel()

std::string ROOT::Internal::RDF::RTTreeDS::GetLabel ( )

inlinefinalvirtual

Return a string representation of the datasource type.

The returned string will be used by ROOT::RDF::SaveGraph() to represent the datasource in the visualization of the computation graph. Concrete datasources can override the default implementation.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 138 of file RTTreeDS.hxx.

◆ GetNFiles()

std::size_t ROOT::Internal::RDF::RTTreeDS::GetNFiles ( ) const

finalvirtual

Returns the number of files from which the dataset is constructed.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 429 of file RTTreeDS.cxx.

◆ GetTChainEntryRange()

std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::Internal::RDF::RTTreeDS::GetTChainEntryRange ( TChain & chain )

private

Definition at line 589 of file RTTreeDS.cxx.

◆ GetTopLevelFieldNames()

const std::vector< std::string > & ROOT::Internal::RDF::RTTreeDS::GetTopLevelFieldNames ( ) const

inlinefinalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 142 of file RTTreeDS.hxx.

◆ GetTree()

TTree * ROOT::Internal::RDF::RTTreeDS::GetTree ( )

Definition at line 670 of file RTTreeDS.cxx.

◆ GetTTreeEntryRange()

std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::Internal::RDF::RTTreeDS::GetTTreeEntryRange ( TTree & tree )

private

Definition at line 579 of file RTTreeDS.cxx.

◆ GetTypeName()

std::string ROOT::Internal::RDF::RTTreeDS::GetTypeName ( std::string_view colName ) const

finalvirtual

Type of a column as a string, e.g.

GetTypeName("x") == "double". Required for jitting e.g. df.Filter("x>0").

Parameters

[in] colName The name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 566 of file RTTreeDS.cxx.

◆ GetTypeNameWithOpts()

std::string ROOT::Internal::RDF::RTTreeDS::GetTypeNameWithOpts	(	std::string_view	colName,
		bool	vector2RVec ) const

finalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 553 of file RTTreeDS.cxx.

◆ HasColumn()

bool ROOT::Internal::RDF::RTTreeDS::HasColumn ( std::string_view colName ) const

inlinefinalvirtual

Checks if the dataset has a certain column.

Parameters

[in] colName The name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 109 of file RTTreeDS.hxx.

◆ Initialize()

void ROOT::Internal::RDF::RTTreeDS::Initialize ( )

finalvirtual

Convenience method called before starting an event-loop.

This method might be called multiple times over the lifetime of a RDataSource, since users can run multiple event-loops with the same RDataFrame. Ideally, Initialize should set the state of the RDataSource so that multiple identical event-loops will produce identical results.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 641 of file RTTreeDS.cxx.

◆ InitializeWithOpts()

void ROOT::Internal::RDF::RTTreeDS::InitializeWithOpts ( const std::set< std::string > & suppressErrorsForMissingBranches )

finalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 654 of file RTTreeDS.cxx.

◆ InitSlot()

virtual void ROOT::RDF::RDataSource::InitSlot	(	unsigned int	,
		ULong64_t	)

inlinevirtualinherited

Convenience method called at the start of the data processing associated to a slot.

Parameters

[in]	slot	The data processing slot wihch needs to be initialized
[in]	firstEntry	The first entry of the range that the task will process. This method might be called multiple times per thread per event-loop.

Reimplemented in ROOT::Internal::RDF::RRootDS, ROOT::RDF::RArrowDS, and ROOT::RDF::RNTupleDS.

Definition at line 304 of file RDataSource.hxx.

◆ operator=() [1/2]

RTTreeDS & ROOT::Internal::RDF::RTTreeDS::operator= ( const RTTreeDS & )

delete

◆ operator=() [2/2]

RTTreeDS & ROOT::Internal::RDF::RTTreeDS::operator= ( RTTreeDS && )

delete

◆ ProcessMT()

void ROOT::Internal::RDF::RTTreeDS::ProcessMT ( ROOT::Detail::RDF::RLoopManager & lm )

finalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 397 of file RTTreeDS.cxx.

◆ RunFinalChecks()

void ROOT::Internal::RDF::RTTreeDS::RunFinalChecks ( bool nodesLeftNotRun ) const

finalprivatevirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 661 of file RTTreeDS.cxx.

◆ SetEntry()

bool ROOT::Internal::RDF::RTTreeDS::SetEntry	(	unsigned int	slot,
		ULong64_t	entry )

finalvirtual

Advance the "cursors" returned by GetColumnReaders to the selected entry for a particular slot.

Parameters

[in]	slot	The data processing slot that needs to be considered
[in]	entry	The entry which needs to be pointed to by the reader pointers Slots are adopted to accommodate parallel data processing. Different workers will loop over different ranges and will be labelled by different "slot" values. Returns true if the entry has to be processed, false otherwise.

Implements ROOT::RDF::RDataSource.

Definition at line 545 of file RTTreeDS.cxx.

◆ SetGlobalEntryRange()

virtual void ROOT::RDF::RDataSource::SetGlobalEntryRange ( std::pair< ULong64_t, ULong64_t > entryRange )

inlinevirtualinherited

Restrict processing to a [begin, end) range of entries.

Parameters

entryRange The range of entries to process.

Definition at line 327 of file RDataSource.hxx.

◆ SetNSlots()

virtual void ROOT::RDF::RDataSource::SetNSlots ( unsigned int nSlots )

inlinevirtualinherited

Inform RDataSource of the number of processing slots (i.e.

worker threads) used by the associated RDataFrame. Slots numbers are used to simplify parallel execution: RDataFrame guarantees that different threads will always pass different slot values when calling methods concurrently.

Reimplemented in ROOT::Internal::RDF::RRootDS, ROOT::Internal::RDF::RVecDS< ColumnTypes >, ROOT::RDF::RArrowDS, ROOT::RDF::RCsvDS, ROOT::RDF::RLazyDS< ColumnTypes >, ROOT::RDF::RNTupleDS, ROOT::RDF::RSqliteDS, and ROOT::RDF::RTrivialDS.

Definition at line 214 of file RDataSource.hxx.

◆ Setup()

void ROOT::Internal::RDF::RTTreeDS::Setup	(	std::shared_ptr< TTree > &&	tree,
		const ROOT::TreeUtils::RFriendInfo *	friendInfo = nullptr )

private

Definition at line 262 of file RTTreeDS.cxx.

Member Data Documentation

◆ fBranchNamesWithDuplicates

std::vector<std::string> ROOT::Internal::RDF::RTTreeDS::fBranchNamesWithDuplicates {}

private

Definition at line 62 of file RTTreeDS.hxx.

◆ fBranchNamesWithoutDuplicates

std::vector<std::string> ROOT::Internal::RDF::RTTreeDS::fBranchNamesWithoutDuplicates {}

private

Definition at line 63 of file RTTreeDS.hxx.

◆ fFriends

std::vector<std::unique_ptr<TChain> > ROOT::Internal::RDF::RTTreeDS::fFriends

private

Definition at line 70 of file RTTreeDS.hxx.

◆ fGlobalEntryRange

std::optional<std::pair<ULong64_t, ULong64_t> > ROOT::RDF::RDataSource::fGlobalEntryRange {}

protectedinherited

Definition at line 149 of file RDataSource.hxx.

◆ fNoCleanupNotifier

std::unique_ptr<ROOT::Internal::TreeUtils::RNoCleanupNotifier> ROOT::Internal::RDF::RTTreeDS::fNoCleanupNotifier

private

Definition at line 74 of file RTTreeDS.hxx.

◆ fNSlots

unsigned int ROOT::RDF::RDataSource::fNSlots {}

protectedinherited

Definition at line 147 of file RDataSource.hxx.

◆ fTopLevelBranchNames

std::vector<std::string> ROOT::Internal::RDF::RTTreeDS::fTopLevelBranchNames {}

private

Definition at line 64 of file RTTreeDS.hxx.

◆ fTree

std::shared_ptr<TTree> ROOT::Internal::RDF::RTTreeDS::fTree

private

Definition at line 66 of file RTTreeDS.hxx.

◆ fTreeReader

std::unique_ptr<TTreeReader> ROOT::Internal::RDF::RTTreeDS::fTreeReader

private

Definition at line 68 of file RTTreeDS.hxx.

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

tree/dataframe/inc/ROOT/RTTreeDS.hxx
tree/dataframe/src/RTTreeDS.cxx

Public Member Functions

Protected Types

Protected Attributes

Private Member Functions

Private Attributes

Member Typedef Documentation

◆ Record_t

Constructor & Destructor Documentation

◆ RTTreeDS() [1/7]

◆ RTTreeDS() [2/7]

◆ RTTreeDS() [3/7]

◆ RTTreeDS() [4/7]

◆ RTTreeDS() [5/7]

◆ RTTreeDS() [6/7]

◆ RTTreeDS() [7/7]

◆ ~RTTreeDS()

Member Function Documentation

◆ AsString()

◆ CreateColumnReader()

◆ CreateSampleInfo()

◆ DescribeDataset()

◆ Finalize()

◆ FinalizeSlot()

◆ GetColumnNames()

◆ GetColumnNamesNoDuplicates()

◆ GetColumnReaders() [1/2]

◆ GetColumnReaders() [2/2]

◆ GetColumnReadersImpl()

◆ GetEntryRanges()

◆ GetLabel()

◆ GetNFiles()

◆ GetTChainEntryRange()

◆ GetTopLevelFieldNames()

◆ GetTree()

◆ GetTTreeEntryRange()

◆ GetTypeName()

◆ GetTypeNameWithOpts()

◆ HasColumn()

◆ Initialize()

◆ InitializeWithOpts()

◆ InitSlot()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ ProcessMT()

◆ RunFinalChecks()

◆ SetEntry()

◆ SetGlobalEntryRange()

◆ SetNSlots()

◆ Setup()

Member Data Documentation

◆ fBranchNamesWithDuplicates

◆ fBranchNamesWithoutDuplicates

◆ fFriends

◆ fGlobalEntryRange

◆ fNoCleanupNotifier

◆ fNSlots

◆ fTopLevelBranchNames

◆ fTree

◆ fTreeReader