Public helpers for writing and concatenating Arrow tables to Parquet files. More...

Functions
std::string	generateUuidV4 ()
	Generate a lowercase hyphenated RFC 4122 version-4 UUID string.

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{})
	Concatenate a vector of Arrow tables and write the result to a Parquet file.

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.

Detailed Description

Public helpers for writing and concatenating Arrow tables to Parquet files.

TOPP tools link against libOpenMS (which exports these helpers) but not directly against Arrow/Parquet. These wrappers keep all Arrow/Parquet API calls inside libOpenMS so downstream binaries don't need to import Arrow symbols.

Function Documentation

◆ concatenateAndWriteToParquet()

bool concatenateAndWriteToParquet	(	const std::vector< std::shared_ptr< arrow::Table > > &	tables,
		const std::string &	filename,
		const ParquetWriteConfig &	config = `ParquetWriteConfig{}`
	)

Concatenate a vector of Arrow tables and write the result to a Parquet file.

All tables must share the same schema. An empty input vector is a no-op (returns true without writing).

Parameters

[in]	tables	Vector of Arrow tables to concatenate (must share schema)
[in]	filename	Output file path
[in]	config	Parquet writer configuration

Returns: true on success (or if tables is empty), false on error

◆ generateUuidV4()

std::string generateUuidV4 ( )

Generate a lowercase hyphenated RFC 4122 version-4 UUID string.

Used by QPX Parquet exporters when attaching file metadata.

Returns: UUID string, e.g. "550e8400-e29b-41d4-a716-446655440000"

◆ getBoolValue()

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.

◆ getColumn()

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.

Returns nullptr if the column is missing or contains no chunks. When required is true, missing columns are logged as errors.

◆ getDoubleValue()

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.

◆ getFloatValue()

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.

◆ getInt32Value()

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.

◆ getInt64Value()

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.

◆ getStringValue()

std::string getStringValue	(	const std::shared_ptr< arrow::Array > &	array,
		int64_t	row
	)

Read a string at row, or "" if null/out-of-bounds.

◆ isNull()

bool isNull	(	const std::shared_ptr< arrow::Array > &	array,
		int64_t	row
	)

Whether array is null at row (or unset)

◆ readMetaValues()

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.

Decodes typed entries (int, double/float, *_list, string) and assigns them to target. Keys in excluded_keys are skipped.

◆ writeTableToParquet()

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.