ArrowIOHelpers.h File Reference

#include <OpenMS/config.h>
#include <OpenMS/CONCEPT/Types.h>
#include <OpenMS/DATASTRUCTURES/StringUtils.h>
#include <OpenMS/FORMAT/MSExperimentArrowExport.h>
#include <cstdint>
#include <map>
#include <memory>
#include <string>
#include <utility>
#include <unordered_set>
#include <vector>

Go to the source code of this file.

Classes
struct	QPXRunFileNameKeys
	MetaInfo indices qpxPsmRunFileName() consults, resolved once. More...

Namespaces
namespace	arrow
namespace	OpenMS
	Main OpenMS namespace.
namespace	OpenMS::MS1LabelState
	The label state of an identification in MS1-labeled (SILAC, Dimethyl, ...) data.
namespace	OpenMS::ArrowIOHelpers
	Public helpers for writing and concatenating Arrow tables to Parquet files.

Functions
std::string	generateUuidV4 ()
	Generate a lowercase hyphenated RFC 4122 version-4 UUID string.
Size	tableRowCount (const std::shared_ptr< arrow::Table > &table)
	Number of rows in an Arrow table, or 0 when it is null.
bool	writeTableToParquet (const std::shared_ptr< arrow::Table > &table, const std::string &filename, const ParquetWriteConfig &config=ParquetWriteConfig{})
	Write an Arrow table to a Parquet file.
bool	concatenateAndWriteToParquet (const std::vector< std::shared_ptr< arrow::Table > > &tables, const std::string &filename, const ParquetWriteConfig &config=ParquetWriteConfig{}, const std::shared_ptr< const arrow::KeyValueMetadata > &metadata=nullptr)
	Concatenate a vector of Arrow tables and write the result to a Parquet file.
std::shared_ptr< const arrow::KeyValueMetadata >	qpxFileMetadata (const std::string &file_type, const ParquetWriteConfig &config=ParquetWriteConfig{}, const std::map< std::string, std::string > &extra={})
	Build the canonical QPX file-level key-value metadata.
std::string	qpxScanFormat (const std::string &native_id)
	Classify a spectrum native ID into a QPX scan_format token.
std::string	qpxScanFormat (const std::vector< std::string > &native_ids)
	Derive a single QPX scan_format token for a set of native IDs.
std::string	qpxRunFileName (const std::string &ms_run_path)
	Reduce an MS run path to the QPX run_file_name form.
std::vector< Int32 >	qpxScanComponents (const std::string &spectrum_reference)
	The QPX scan column value for one spectrum reference.
std::string	qpxPsmRunFileName (const MetaInfoInterface &hit, const MetaInfoInterface &identification, const std::string &resolved_run_file, const QPXRunFileNameKeys &keys)
	The QPX run_file_name the psm view writes for one identification and hit.
bool	qpxWarnOnRunNameCollisions (const std::string &context, const std::vector< std::string > &ms_run_paths)
	Warn once per export about source files that collapse onto one run_file_name.
std::string	qpxIntensityLabel (const std::string &column_label, const std::string &channel_name)
	QPX intensities[].label for a ConsensusMap column header.
std::map< std::uint64_t, std::string >	qpxIntensityLabels (const ConsensusMap &cmap)
	Derive canonical QPX intensity labels for every ConsensusMap column.
bool	qpxIsCanonicalIntensityLabel (const std::string &label)
	Test whether a string is in the canonical SDRF/QPX intensity-label vocabulary.
std::vector< std::pair< std::string, std::string > >	qpxCvParams (const MetaInfoInterface &hit)
	The meta values of an identification that QPX carries as cv_params.
std::vector< std::pair< std::string, std::string > >	qpxCvParams (const MetaInfoInterface &hit, const MS1LabelState::Keys &keys)
	qpxCvParams() with the registry indices resolved once (MS1LabelState::Keys), for a loop over many hits
std::shared_ptr< arrow::Array >	getColumn (const std::shared_ptr< arrow::Table > &table, const std::string &name, bool required=true)
	Fetch a named column from a table, combining chunks if needed.
std::string	getStringValue (const std::shared_ptr< arrow::Array > &array, int64_t row)
	Read a string at row, or "" if null/out-of-bounds.
double	getDoubleValue (const std::shared_ptr< arrow::Array > &array, int64_t row, double default_val=0.0)
	Read a double at row, or default_val if null.
float	getFloatValue (const std::shared_ptr< arrow::Array > &array, int64_t row, float default_val=0.0f)
	Read a float at row, or default_val if null.
int32_t	getInt32Value (const std::shared_ptr< arrow::Array > &array, int64_t row, int32_t default_val=0)
	Read an int32 at row, or default_val if null.
int64_t	getInt64Value (const std::shared_ptr< arrow::Array > &array, int64_t row, int64_t default_val=0)
	Read an int64 at row, or default_val if null.
bool	getBoolValue (const std::shared_ptr< arrow::Array > &array, int64_t row, bool default_val=false)
	Read a bool at row, or default_val if null.
bool	isNull (const std::shared_ptr< arrow::Array > &array, int64_t row)
	Whether array is null at row (or unset)
void	readMetaValues (const std::shared_ptr< arrow::Array > &array, int64_t row, MetaInfoInterface &target, const std::unordered_set< std::string > &excluded_keys={})
	Read metavalues from a list<struct{name,value,value_type}> column.