File DataSource.h

namespace podio

Functions

ROOT::RDataFrame CreateDataFrame(const std::vector<std::string> &filePathList)

Create RDataFrame from multiple Podio files.

Parameters:: filePathList – [in] List of file paths from which the RDataFrame will be created.
Returns:: RDataFrame created from input file list.

ROOT::RDataFrame CreateDataFrame(const std::string &filePath)

Create RDataFrame from a Podio file.

Parameters:: filePath – [in] File path from which the RDataFrame will be created.
Returns:: RDataFrame created from input file list.

class DataSource : public ROOT::RDF::RDataSource

#include <podio/DataSource.h>

Public Functions

explicit DataSource(const std::string &filePath, int nEvents = -1): Construct the podio::DataSource from the provided file.

explicit DataSource(const std::vector<std::string> &filePathList, int nEvents = -1): Construct the podio::DataSource from the provided file list.

void SetNSlots(unsigned int nSlots) override: Inform the podio::DataSource of the desired level of parallelism.

void Initialize() override: Inform podio::DataSource that an event-loop is about to start.

std::vector<std::pair<ULong64_t, ULong64_t>> GetEntryRanges() override: Retrieve from podio::DataSource a set of ranges of entries that can be processed concurrently.

void InitSlot(unsigned int slot, ULong64_t firstEntry) override: Inform podio::DataSource that a certain thread is about to start working on a certain range of entries.

bool SetEntry(unsigned int slot, ULong64_t entry) override: Inform podio::DataSource that a certain thread is about to start working on a certain entry.

void FinalizeSlot(unsigned int slot) override: Inform podio::DataSource that a certain thread finished working on a certain range of entries.

void Finalize() override: Inform podio::DataSource that an event-loop finished.

const std::vector<std::string> &GetColumnNames() const override: Returns a reference to the collection of the dataset’s column names.

bool HasColumn(std::string_view columnName) const override: Checks if the dataset has a certain column.

std::string GetTypeName(std::string_view columnName) const override

Type of a column as a string.

Required for JITting.

inline std::string GetLabel() override

Protected Functions

std::vector<void*> GetColumnReadersImpl(std::string_view name, const std::type_info &typeInfo) override: Type-erased vector of pointers to pointers to column values — one per slot.

inline std::string AsString() override

Private Functions

void SetupInput(int nEvents)

Setup input for the podio::DataSource.

Parameters:: nEvents – [in] Number of events.

Private Members

unsigned int m_nSlots = 1: Number of slots/threads.

std::vector<std::string> m_filePathList = {}: Input filename.

ULong64_t m_nEvents = 0: Total number of events.

std::vector<std::pair<ULong64_t, ULong64_t>> m_rangesAvailable = {}: Ranges of events available to be processed.

std::vector<std::pair<ULong64_t, ULong64_t>> m_rangesAll = {}: Ranges of events available ever created.

std::vector<std::string> m_columnNames = {}: Column names.

std::vector<std::string> m_columnTypes = {}: Column types.

std::vector<std::vector<const podio::CollectionBase*>> m_Collections = {}: Collections, m_Collections[columnIndex][slotIndex].

std::vector<unsigned int> m_activeCollections = {}: Active collections.

std::vector<std::unique_ptr<podio::Reader>> m_podioReaders = {}: Root podio readers.

std::vector<std::unique_ptr<podio::Frame>> m_frames = {}: Podio frames.