A simple data-source implementation, for demo purposes.

Constructing an RDataFrame as RDataFrame(nEntries) is a superior alternative. If size is std::numeric_limits<ULong64_t>::max(), this acts as an infinite data-source: it returns entries from GetEntryRanges forever or until a Range stops the event loop (for test purposes).

Definition at line 36 of file RTrivialDS.hxx.

Public Member Functions
	RTrivialDS ()
	This ctor produces a data-source that returns infinite entries.
	RTrivialDS (const RTrivialDS &)=delete
	RTrivialDS (RTrivialDS &&)=delete
	RTrivialDS (ULong64_t size, bool skipEvenEntries=false)
	~RTrivialDS () final=default
virtual void	Finalize ()
	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.
template<typename T>
std::vector< T ** >	GetColumnReaders (std::string_view columnName)
	Called at most once per column by RDF.
std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase >	GetColumnReaders (unsigned int slot, std::string_view colName, const std::type_info &tid) final
	If the other GetColumnReaders overload returns an empty vector, this overload will be called instead.
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.
virtual std::size_t	GetNFiles () const
	Returns the number of files from which the dataset is constructed.
std::string	GetTypeName (std::string_view) const final
	Type of a column as a string, e.g.
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.
virtual void	InitSlot (unsigned int, ULong64_t)
	Convenience method called at the start of the data processing associated to a slot.
RTrivialDS &	operator= (const RTrivialDS &)=delete
RTrivialDS &	operator= (RTrivialDS &&)=delete
bool	SetEntry (unsigned int slot, 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.
void	SetNSlots (unsigned int nSlots) final
	Inform RDataSource of the number of processing slots (i.e.

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

Protected Member Functions
std::string	AsString () final
virtual std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase >	CreateColumnReader (unsigned int slot, std::string_view col, const std::type_info &tid, TTreeReader *)
	Creates a column reader for the requested column.
virtual ROOT::RDF::RSampleInfo	CreateSampleInfo (unsigned int, const std::unordered_map< std::string, ROOT::RDF::Experimental::RSample * > &) const
virtual std::string	DescribeDataset ()
virtual const std::vector< std::string > &	GetColumnNamesNoDuplicates () const
virtual const std::vector< std::string > &	GetTopLevelFieldNames () const
virtual std::string	GetTypeNameWithOpts (std::string_view colName, bool) const
virtual void	InitializeWithOpts (const std::set< std::string > &)
virtual void	ProcessMT (ROOT::Detail::RDF::RLoopManager &)
virtual void	RunFinalChecks (bool) const

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

Private Member Functions
std::vector< void * >	GetColumnReadersImpl (std::string_view name, const std::type_info &) final
	type-erased vector of pointers to pointers to column values - one per slot

Private Attributes
std::vector< std::string >	fColNames {"col0"}
std::vector< ULong64_t >	fCounter
std::vector< ULong64_t * >	fCounterAddr
std::vector< std::pair< ULong64_t, ULong64_t > >	fEntryRanges
ULong64_t	fSize = 0ULL
bool	fSkipEvenEntries = false

#include <ROOT/RTrivialDS.hxx>

Inheritance diagram for ROOT::RDF::RTrivialDS:

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

◆ RTrivialDS() [1/4]

ROOT::RDF::RTrivialDS::RTrivialDS	(	ULong64_t	size,
		bool	skipEvenEntries = false )

Definition at line 25 of file RTrivialDS.cxx.

◆ RTrivialDS() [2/4]

ROOT::RDF::RTrivialDS::RTrivialDS ( )

This ctor produces a data-source that returns infinite entries.

Definition at line 29 of file RTrivialDS.cxx.

◆ RTrivialDS() [3/4]

ROOT::RDF::RTrivialDS::RTrivialDS ( const RTrivialDS & )

delete

◆ RTrivialDS() [4/4]

ROOT::RDF::RTrivialDS::RTrivialDS ( RTrivialDS && )

delete

◆ ~RTrivialDS()

ROOT::RDF::RTrivialDS::~RTrivialDS ( )

finaldefault

Member Function Documentation

◆ AsString()

std::string ROOT::RDF::RTrivialDS::AsString ( )

inlinefinalprotectedvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 47 of file RTrivialDS.hxx.

◆ CreateColumnReader()

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

inlineprotectedvirtualinherited

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 in ROOT::Internal::RDF::RTTreeDS.

Definition at line 195 of file RDataSource.hxx.

◆ CreateSampleInfo()

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

protectedvirtualinherited

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

Definition at line 11 of file RDataSource.cxx.

◆ DescribeDataset()

virtual std::string ROOT::RDF::RDataSource::DescribeDataset ( )

inlineprotectedvirtualinherited

Reimplemented in ROOT::Internal::RDF::RTTreeDS.

Definition at line 165 of file RDataSource.hxx.

◆ Finalize()

virtual void ROOT::RDF::RDataSource::Finalize ( )

inlinevirtualinherited

Convenience method called after concluding an event-loop.

See Initialize for more details.

Reimplemented in ROOT::Internal::RDF::RTTreeDS, ROOT::RDF::RCsvDS, and ROOT::RDF::RNTupleDS.

Definition at line 317 of file RDataSource.hxx.

◆ 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::RDF::RTrivialDS::GetColumnNames ( ) const

finalvirtual

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

Implements ROOT::RDF::RDataSource.

Definition at line 33 of file RTrivialDS.cxx.

◆ GetColumnNamesNoDuplicates()

virtual const std::vector< std::string > & ROOT::RDF::RDataSource::GetColumnNamesNoDuplicates ( ) const

inlineprotectedvirtualinherited

Reimplemented in ROOT::Internal::RDF::RTTreeDS.

Definition at line 159 of file RDataSource.hxx.

◆ GetColumnReaders() [1/2]

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.

◆ GetColumnReaders() [2/2]

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

finalvirtual

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 RTrivialDS.cxx.

◆ GetColumnReadersImpl()

std::vector< void * > ROOT::RDF::RTrivialDS::GetColumnReadersImpl	(	std::string_view	name,
		const std::type_info &	)

finalprivatevirtual

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

Implements ROOT::RDF::RDataSource.

Definition at line 20 of file RTrivialDS.cxx.

◆ GetEntryRanges()

std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::RDF::RTrivialDS::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 48 of file RTrivialDS.cxx.

◆ GetLabel()

std::string ROOT::RDF::RTrivialDS::GetLabel ( )

finalvirtual

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 105 of file RTrivialDS.cxx.

◆ GetNFiles()

virtual std::size_t ROOT::RDF::RDataSource::GetNFiles ( ) const

inlinevirtualinherited

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

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

Definition at line 222 of file RDataSource.hxx.

◆ GetTopLevelFieldNames()

virtual const std::vector< std::string > & ROOT::RDF::RDataSource::GetTopLevelFieldNames ( ) const

inlineprotectedvirtualinherited

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

Definition at line 155 of file RDataSource.hxx.

◆ GetTypeName()

std::string ROOT::RDF::RTrivialDS::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 43 of file RTrivialDS.cxx.

◆ GetTypeNameWithOpts()

virtual std::string ROOT::RDF::RDataSource::GetTypeNameWithOpts	(	std::string_view	colName,
		bool	) const

inlineprotectedvirtualinherited

Reimplemented in ROOT::Internal::RDF::RTTreeDS.

Definition at line 152 of file RDataSource.hxx.

◆ HasColumn()

bool ROOT::RDF::RTrivialDS::HasColumn ( std::string_view colName ) const

finalvirtual

Checks if the dataset has a certain column.

Parameters

[in] colName The name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 38 of file RTrivialDS.cxx.

◆ Initialize()

void ROOT::RDF::RTrivialDS::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 84 of file RTrivialDS.cxx.

◆ InitializeWithOpts()

virtual void ROOT::RDF::RDataSource::InitializeWithOpts ( const std::set< std::string > & )

inlineprotectedvirtualinherited

Reimplemented in ROOT::Internal::RDF::RTTreeDS.

Definition at line 162 of file RDataSource.hxx.

◆ 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]

RTrivialDS & ROOT::RDF::RTrivialDS::operator= ( const RTrivialDS & )

delete

◆ operator=() [2/2]

RTrivialDS & ROOT::RDF::RTrivialDS::operator= ( RTrivialDS && )

delete

◆ ProcessMT()

void ROOT::RDF::RDataSource::ProcessMT ( ROOT::Detail::RDF::RLoopManager & lm )

protectedvirtualinherited

Reimplemented in ROOT::Internal::RDF::RTTreeDS.

Definition at line 17 of file RDataSource.cxx.

◆ RunFinalChecks()

virtual void ROOT::RDF::RDataSource::RunFinalChecks ( bool ) const

inlineprotectedvirtualinherited

Reimplemented in ROOT::Internal::RDF::RTTreeDS.

Definition at line 174 of file RDataSource.hxx.

◆ SetEntry()

bool ROOT::RDF::RTrivialDS::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 66 of file RTrivialDS.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()

void ROOT::RDF::RTrivialDS::SetNSlots ( unsigned int nSlots )

finalvirtual

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 from ROOT::RDF::RDataSource.

Definition at line 75 of file RTrivialDS.cxx.

Member Data Documentation

◆ fColNames

std::vector<std::string> ROOT::RDF::RTrivialDS::fColNames {"col0"}

private

Definition at line 41 of file RTrivialDS.hxx.

◆ fCounter

std::vector<ULong64_t> ROOT::RDF::RTrivialDS::fCounter

private

Definition at line 42 of file RTrivialDS.hxx.

◆ fCounterAddr

std::vector<ULong64_t *> ROOT::RDF::RTrivialDS::fCounterAddr

private

Definition at line 43 of file RTrivialDS.hxx.

◆ fEntryRanges

std::vector<std::pair<ULong64_t, ULong64_t> > ROOT::RDF::RTrivialDS::fEntryRanges

private

Definition at line 40 of file RTrivialDS.hxx.

◆ fGlobalEntryRange

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

protectedinherited

Definition at line 149 of file RDataSource.hxx.

◆ fNSlots

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

protectedinherited

Definition at line 147 of file RDataSource.hxx.

◆ fSize

ULong64_t ROOT::RDF::RTrivialDS::fSize = 0ULL

private

Definition at line 38 of file RTrivialDS.hxx.

◆ fSkipEvenEntries

bool ROOT::RDF::RTrivialDS::fSkipEvenEntries = false

private

Definition at line 39 of file RTrivialDS.hxx.

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

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

Public Member Functions

Protected Types

Protected Member Functions

Protected Attributes

Private Member Functions

Private Attributes

Member Typedef Documentation

◆ Record_t

Constructor & Destructor Documentation

◆ RTrivialDS() [1/4]

◆ RTrivialDS() [2/4]

◆ RTrivialDS() [3/4]

◆ RTrivialDS() [4/4]

◆ ~RTrivialDS()

Member Function Documentation

◆ AsString()

◆ CreateColumnReader()

◆ CreateSampleInfo()

◆ DescribeDataset()

◆ Finalize()

◆ FinalizeSlot()

◆ GetColumnNames()

◆ GetColumnNamesNoDuplicates()

◆ GetColumnReaders() [1/2]

◆ GetColumnReaders() [2/2]

◆ GetColumnReadersImpl()

◆ GetEntryRanges()

◆ GetLabel()

◆ GetNFiles()

◆ GetTopLevelFieldNames()

◆ GetTypeName()

◆ GetTypeNameWithOpts()

◆ HasColumn()

◆ Initialize()

◆ InitializeWithOpts()

◆ InitSlot()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ ProcessMT()

◆ RunFinalChecks()

◆ SetEntry()

◆ SetGlobalEntryRange()

◆ SetNSlots()

Member Data Documentation

◆ fColNames

◆ fCounter

◆ fCounterAddr

◆ fEntryRanges

◆ fGlobalEntryRange

◆ fNSlots

◆ fSize

◆ fSkipEvenEntries