Definition at line 62 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. | |
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. | |
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 |
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. | |
![]() | |
RDataSource ()=default | |
RDataSource (const RDataSource &)=delete | |
RDataSource (RDataSource &&)=delete | |
virtual | ~RDataSource ()=default |
virtual void | FinalizeSlot (unsigned int) |
Convenience method called at the end of the data processing associated to a slot. | |
template<typename T > | |
std::vector< T ** > | GetColumnReaders (std::string_view columnName) |
Called at most once per column by RDF. | |
virtual void | InitSlot (unsigned int, ULong64_t) |
Convenience method called at the start of the data processing associated to a slot. | |
RDataSource & | operator= (const RDataSource &)=delete |
RDataSource & | operator= (RDataSource &&)=delete |
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. | |
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 |
Additional Inherited Members | |
![]() | |
using | Record_t = std::vector<void *> |
![]() | |
std::optional< std::pair< ULong64_t, ULong64_t > > | fGlobalEntryRange {} |
unsigned int | fNSlots {} |
#include <ROOT/RTTreeDS.hxx>
ROOT::Internal::RDF::RTTreeDS::RTTreeDS | ( | std::shared_ptr< TTree > | tree | ) |
Definition at line 93 of file RTTreeDS.cxx.
ROOT::Internal::RDF::RTTreeDS::RTTreeDS | ( | std::shared_ptr< TTree > | tree, |
const ROOT::TreeUtils::RFriendInfo & | friendInfo ) |
Definition at line 99 of file RTTreeDS.cxx.
ROOT::Internal::RDF::RTTreeDS::RTTreeDS | ( | std::string_view | treeName, |
TDirectory * | dirPtr ) |
Definition at line 105 of file RTTreeDS.cxx.
ROOT::Internal::RDF::RTTreeDS::RTTreeDS | ( | std::string_view | treeName, |
std::string_view | fileNameGlob ) |
Definition at line 129 of file RTTreeDS.cxx.
ROOT::Internal::RDF::RTTreeDS::RTTreeDS | ( | std::string_view | treeName, |
const std::vector< std::string > & | fileNameGlobs ) |
Definition at line 148 of file RTTreeDS.cxx.
|
delete |
|
final |
Definition at line 66 of file RTTreeDS.cxx.
|
inlinefinalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 151 of file RTTreeDS.hxx.
|
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 315 of file RTTreeDS.cxx.
|
finalprivatevirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 179 of file RTTreeDS.cxx.
|
finalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 249 of file RTTreeDS.cxx.
|
finalvirtual |
Convenience method called after concluding an event-loop.
See Initialize for more details.
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 427 of file RTTreeDS.cxx.
|
inlinefinalvirtual |
Returns a reference to the collection of the dataset's column names.
Implements ROOT::RDF::RDataSource.
Definition at line 108 of file RTTreeDS.hxx.
|
inlinefinalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 145 of file RTTreeDS.hxx.
|
inlinefinalvirtual |
If the other GetColumnReaders overload returns an empty vector, this overload will be called instead.
[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 129 of file RTTreeDS.hxx.
|
inlinefinalvirtual |
type-erased vector of pointers to pointers to column values - one per slot
Implements ROOT::RDF::RDataSource.
Definition at line 122 of file RTTreeDS.hxx.
|
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 404 of file RTTreeDS.cxx.
|
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 139 of file RTTreeDS.hxx.
|
finalvirtual |
Returns the number of files from which the dataset is constructed.
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 240 of file RTTreeDS.cxx.
|
private |
Definition at line 383 of file RTTreeDS.cxx.
|
inlinefinalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 143 of file RTTreeDS.hxx.
TTree * ROOT::Internal::RDF::RTTreeDS::GetTree | ( | ) |
Definition at line 465 of file RTTreeDS.cxx.
|
private |
Definition at line 373 of file RTTreeDS.cxx.
|
finalvirtual |
Type of a column as a string, e.g.
GetTypeName("x") == "double"
. Required for jitting e.g. df.Filter("x>0")
.
[in] | colName | The name of the column |
Implements ROOT::RDF::RDataSource.
Definition at line 360 of file RTTreeDS.cxx.
|
finalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 347 of file RTTreeDS.cxx.
|
inlinefinalvirtual |
Checks if the dataset has a certain column.
[in] | colName | The name of the column |
Implements ROOT::RDF::RDataSource.
Definition at line 110 of file RTTreeDS.hxx.
|
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 435 of file RTTreeDS.cxx.
|
finalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 449 of file RTTreeDS.cxx.
|
finalvirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 208 of file RTTreeDS.cxx.
|
finalprivatevirtual |
Reimplemented from ROOT::RDF::RDataSource.
Definition at line 456 of file RTTreeDS.cxx.
Advance the "cursors" returned by GetColumnReaders to the selected entry for a particular slot.
[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 339 of file RTTreeDS.cxx.
|
private |
Definition at line 73 of file RTTreeDS.cxx.
|
private |
Definition at line 63 of file RTTreeDS.hxx.
|
private |
Definition at line 64 of file RTTreeDS.hxx.
|
private |
Definition at line 71 of file RTTreeDS.hxx.
|
private |
Definition at line 75 of file RTTreeDS.hxx.
|
private |
Definition at line 65 of file RTTreeDS.hxx.
|
private |
Definition at line 67 of file RTTreeDS.hxx.
|
private |
Definition at line 69 of file RTTreeDS.hxx.