Definition at line 42 of file RNTupleProcessorDS.hxx.

Classes
struct	RFieldInfo
	Holds useful information about fields added to the RNTupleProcessorDS. More...

Public Member Functions
	RNTupleProcessorDS (const RNTupleProcessorDS &)=delete

	RNTupleProcessorDS (RNTupleProcessorDS &&)=delete

	RNTupleProcessorDS (std::unique_ptr< ROOT::Experimental::RNTupleProcessor > processor)

	~RNTupleProcessorDS () final

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

void	Finalize () final
	Convenience method called after concluding an event-loop.

void	FinalizeSlot (unsigned int slot) final
	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 name, const std::type_info &) 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.

std::size_t	GetNFiles () const final
	Returns the number of files from which the dataset is constructed.

std::string	GetTypeName (std::string_view colName) 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.

void	InitSlot (unsigned int slot, ULong64_t firstEntry) final
	Convenience method called at the start of the data processing associated to a slot.

RNTupleProcessorDS &	operator= (const RNTupleProcessorDS &)=delete

RNTupleProcessorDS &	operator= (RNTupleProcessorDS &&)=delete

bool	SetEntry (unsigned int, ULong64_t) 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
virtual std::string	AsString ()

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 std::string	DescribeDataset ()

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

Record_t	GetColumnReadersImpl (std::string_view name, const std::type_info &) final
	type-erased vector of pointers to pointers to column values - one per slot

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
void	AddField (const ROOT::RFieldBase &field, std::string_view colName, Internal::RNTupleProcessorProvenance procProvenance, std::deque< RFieldInfo > &fieldInfos, bool convertToRVec=true)
	Provides the RDF column "colName" given the field.

Private Attributes
std::vector< std::string >	fColumnNames

std::vector< ROOT::Experimental::Internal::RDF::RNTupleProcessorColumnReader * >	fColumnReaders

std::vector< std::string >	fColumnTypes

std::vector< std::pair< ULong64_t, ULong64_t > >	fCurrentRanges

RNTupleProcessor::REntryMapping	fEntryMapping

std::unique_ptr< RNTupleProcessor >	fProcessor

#include <ROOT/RNTupleProcessorDS.hxx>

Inheritance diagram for ROOT::Experimental::Internal::RDF::RNTupleProcessorDS:

[legend]

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

◆ RNTupleProcessorDS() [1/3]

ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::RNTupleProcessorDS ( std::unique_ptr< ROOT::Experimental::RNTupleProcessor > processor )

Definition at line 231 of file RNTupleProcessorDS.cxx.

◆ RNTupleProcessorDS() [2/3]

ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::RNTupleProcessorDS ( const RNTupleProcessorDS & )

delete

◆ RNTupleProcessorDS() [3/3]

ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::RNTupleProcessorDS ( RNTupleProcessorDS && )

delete

◆ ~RNTupleProcessorDS()

ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::~RNTupleProcessorDS ( )

finaldefault

Member Function Documentation

◆ AddField()

void ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::AddField	(	const ROOT::RFieldBase &	field,
		std::string_view	colName,
		Internal::RNTupleProcessorProvenance	procProvenance,
		std::deque< RFieldInfo > &	fieldInfos,
		bool	convertToRVec = true )

private

Provides the RDF column "colName" given the field.

Parameters

[in]	field	Field to add.
[in]	colName	RDF column name corresponding to the field.
[in]	procProvenance	Processor provenance of the field to add.
[in]	fieldInfos	Additional information about the field's outer collections.
[in]	convertToRVec	Whether to add collections (`std::vector` or `std::array`) as ROOT::VecOps::RVec (enabled by default).

For records and collections, AddField recurses into the subfields. For instance, if the provided field refers to an std::vector<Jet>, with

struct Jet {
   float pt;
   float eta;
};

AddField will recurse into Jet.pt and Jet.eta and provide the two inner fields as ROOT::VecOps::RVec<float> each.

When convertToRVec is true, the field's corresponding column is added as a ROOT::VecOps::RVec. Otherwise, the collection field's on-disk type is used. Note, however, that inner record members of such collections will still be added as ROOT::VecOps::RVec (e.g., std::set<Jet> will be added as astd::set, butJet.[pt|eta] will be added as `ROOTVecOps::RVec<float>).

Definition at line 51 of file RNTupleProcessorDS.cxx.

◆ AsString()

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

inlineprotectedvirtualinherited

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

Definition at line 145 of file RDataSource.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::Experimental::Internal::RDF::RNTupleProcessorDS::CreateSampleInfo	(	unsigned int	,
		const std::unordered_map< std::string, ROOT::RDF::Experimental::RSample * > &	sampleMap ) const

finalvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 411 of file RNTupleProcessorDS.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()

void ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::Finalize ( )

finalvirtual

Convenience method called after concluding an event-loop.

See Initialize for more details.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 382 of file RNTupleProcessorDS.cxx.

◆ FinalizeSlot()

void ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::FinalizeSlot ( unsigned int )

finalvirtual

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 from ROOT::RDF::RDataSource.

Definition at line 352 of file RNTupleProcessorDS.cxx.

◆ GetColumnNames()

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

inlinefinalvirtual

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

Implements ROOT::RDF::RDataSource.

Definition at line 109 of file RNTupleProcessorDS.hxx.

◆ 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::Experimental::Internal::RDF::RNTupleProcessorDS::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 252 of file RNTupleProcessorDS.cxx.

◆ GetColumnReadersImpl()

ROOT::RDF::RDataSource::Record_t ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::GetColumnReadersImpl	(	std::string_view	name,
		const std::type_info &	)

finalprotectedvirtual

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

Implements ROOT::RDF::RDataSource.

Definition at line 245 of file RNTupleProcessorDS.cxx.

◆ GetEntryRanges()

std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::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 338 of file RNTupleProcessorDS.cxx.

◆ GetLabel()

std::string ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::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 113 of file RNTupleProcessorDS.hxx.

◆ GetNFiles()

std::size_t ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::GetNFiles ( ) const

inlinefinalvirtual

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

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 108 of file RNTupleProcessorDS.hxx.

◆ GetTopLevelFieldNames()

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

inlineprotectedvirtualinherited

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

Definition at line 155 of file RDataSource.hxx.

◆ GetTypeName()

std::string ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::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 357 of file RNTupleProcessorDS.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::Experimental::Internal::RDF::RNTupleProcessorDS::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 370 of file RNTupleProcessorDS.cxx.

◆ Initialize()

void ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::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 375 of file RNTupleProcessorDS.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()

void ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::InitSlot	(	unsigned int	,
		ULong64_t	)

finalvirtual

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 from ROOT::RDF::RDataSource.

Definition at line 347 of file RNTupleProcessorDS.cxx.

◆ operator=() [1/2]

RNTupleProcessorDS & ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::operator= ( const RNTupleProcessorDS & )

delete

◆ operator=() [2/2]

RNTupleProcessorDS & ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::operator= ( RNTupleProcessorDS && )

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::Experimental::Internal::RDF::RNTupleProcessorDS::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 396 of file RNTupleProcessorDS.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::Experimental::Internal::RDF::RNTupleProcessorDS::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 387 of file RNTupleProcessorDS.cxx.

Member Data Documentation

◆ fColumnNames

std::vector<std::string> ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::fColumnNames

private

Definition at line 47 of file RNTupleProcessorDS.hxx.

◆ fColumnReaders

std::vector<ROOT::Experimental::Internal::RDF::RNTupleProcessorColumnReader *> ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::fColumnReaders

private

Definition at line 50 of file RNTupleProcessorDS.hxx.

◆ fColumnTypes

std::vector<std::string> ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::fColumnTypes

private

Definition at line 48 of file RNTupleProcessorDS.hxx.

◆ fCurrentRanges

std::vector<std::pair<ULong64_t, ULong64_t> > ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::fCurrentRanges

private

Definition at line 52 of file RNTupleProcessorDS.hxx.

◆ fEntryMapping

RNTupleProcessor::REntryMapping ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::fEntryMapping

private

Definition at line 45 of file RNTupleProcessorDS.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.

◆ fProcessor

std::unique_ptr<RNTupleProcessor> ROOT::Experimental::Internal::RDF::RNTupleProcessorDS::fProcessor

private

Definition at line 44 of file RNTupleProcessorDS.hxx.

Libraries for ROOT::Experimental::Internal::RDF::RNTupleProcessorDS:

[legend]

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

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

Classes

Public Member Functions

Protected Types

Protected Member Functions

Protected Attributes

Private Member Functions

Private Attributes

Member Typedef Documentation

◆ Record_t

Constructor & Destructor Documentation

◆ RNTupleProcessorDS() [1/3]

◆ RNTupleProcessorDS() [2/3]

◆ RNTupleProcessorDS() [3/3]

◆ ~RNTupleProcessorDS()

Member Function Documentation

◆ AddField()

◆ 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

◆ fColumnNames

◆ fColumnReaders

◆ fColumnTypes

◆ fCurrentRanges

◆ fEntryMapping

◆ fGlobalEntryRange

◆ fNSlots

◆ fProcessor