FileHandler Class Reference

Facilitates file handling by file type recognition. More...

#include <OpenMS/FORMAT/FileHandler.h>

Public Member Functions
PeakFileOptions &	getOptions ()
	Mutable access to the options for loading/storing.
const PeakFileOptions &	getOptions () const
	Non-mutable access to the options for loading/storing.
FeatureFileOptions &	getFeatOptions ()
	Mutable access to the feature file options for loading/storing.
const FeatureFileOptions &	getFeatOptions () const
	Non-mutable access to the feature file options for loading/storing.
void	setOptions (const PeakFileOptions &)
	set options for loading/storing
void	setFeatOptions (const FeatureFileOptions &)
	set feature file options for loading/storing
void	loadExperiment (const std::string &filename, PeakMap &exp, const std::vector< FileTypes::Type > allowed_types=std::vector< FileTypes::Type >(), ProgressLogger::LogType log=ProgressLogger::NONE, const bool rewrite_source_file=false, const bool compute_hash=false)
	Loads a file into an MSExperiment.
void	transformExperiment (const std::string &filename, Interfaces::IMSDataConsumer *consumer, const std::vector< FileTypes::Type > allowed_types=std::vector< FileTypes::Type >(), ProgressLogger::LogType log=ProgressLogger::NONE, const bool rewrite_source_file=false, const bool compute_hash=false)
	Streams a file into a consumer, spectrum by spectrum, without holding the whole experiment in memory.
void	loadImagingExperiment (const std::string &filename, MSImagingExperiment &exp, const std::vector< FileTypes::Type > allowed_types=std::vector< FileTypes::Type >(), ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads a mass spectrometry imaging file into an MSImagingExperiment.
void	storeExperiment (const std::string &filename, const PeakMap &exp, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Stores an MSExperiment to a file.
void	loadSpectrum (const std::string &filename, MSSpectrum &spec, const std::vector< FileTypes::Type > allowed_types={})
	Loads a single MSSpectrum from a file.
void	storeSpectrum (const std::string &filename, MSSpectrum &spec, const std::vector< FileTypes::Type > allowed_types={})
	Stores a single MSSpectrum to a file.
void	loadFeatures (const std::string &filename, FeatureMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads a file into a FeatureMap.
void	storeFeatures (const std::string &filename, const FeatureMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Store a FeatureMap.
void	loadConsensusFeatures (const std::string &filename, ConsensusMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads a file into a ConsensusMap.
void	storeConsensusFeatures (const std::string &filename, const ConsensusMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Store a ConsensusFeatureMap.
void	loadIdentifications (const std::string &filename, std::vector< ProteinIdentification > &additional_proteins, PeptideIdentificationList &additional_peptides, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads an identification file into a proteinIdentifications and peptideIdentifications.
void	storeIdentifications (const std::string &filename, const std::vector< ProteinIdentification > &additional_proteins, const PeptideIdentificationList &additional_peptides, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Stores proteins and peptides into an Identification File.
void	loadTransitions (const std::string &filename, TargetedExperiment &library, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Load transitions of a spectral library.
void	storeTransitions (const std::string &filename, const TargetedExperiment &library, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Store transitions of a spectral library.
void	loadTransformations (const std::string &filename, TransformationDescription &map, bool fit_model=true, const std::vector< FileTypes::Type > allowed_types={})
	Loads a file into Transformations.
void	storeTransformations (const std::string &filename, const TransformationDescription &map, const std::vector< FileTypes::Type > allowed_types={})
	Store Transformations.
void	storeQC (const std::string &input_file, const std::string &filename, const MSExperiment &exp, const FeatureMap &feature_map, std::vector< ProteinIdentification > &prot_ids, PeptideIdentificationList &pep_ids, const ConsensusMap &consensus_map, const std::string &contact_name="", const std::string &contact_address="", const std::string &description="", const std::string &label="label", const bool remove_duplicate_features=false, const std::vector< FileTypes::Type > allowed_types={})
	Store QC info.

Static Public Member Functions
static FileTypes::Type	getType (const std::string &filename)
	Tries to determine the file type (by name or content)
static FileTypes::Type	getTypeByFileName (const std::string &filename)
	Try to get the file type from the filename.
static bool	hasValidExtension (const std::string &filename, const FileTypes::Type type)
	Check if filename has the extension type.
static std::string	stripExtension (const std::string &filename)
	If filename contains an extension, it will be removed (including the '.'). Special extensions, known to OpenMS, e.g. '.mzML.gz' will be recognized as well.
static std::string	swapExtension (const std::string &filename, const FileTypes::Type new_type)
	Tries to find and remove a known file extension, and append the new one.
static FileTypes::Type	getConsistentOutputfileType (const std::string &output_filename, const std::string &requested_type)
	Useful function for TOPP tools which have an 'out_type' parameter and want to know what output format to write. This function makes sure that the type derived from output_filename and requested_type are consistent, i.e. are either identical or one of them is UNKNOWN. Upon conflict, an error message is printed and the UNKNOWN type is returned.
static FileTypes::Type	getTypeByContent (const std::string &filename)
	Determines the file type of a file by parsing the first few lines.
static bool	isSupported (FileTypes::Type type)
	Returns if the file type is supported in this build of the library.
static std::string	computeFileHash (const std::string &filename)
	Computes a SHA-1 hash value for the content of the given file.

Private Member Functions
void	applyPostLoadOptions_ (MSExperiment &exp) const
	Applies the current PeakFileOptions filters to an already-loaded experiment.

Private Attributes
PeakFileOptions	options_
FeatureFileOptions	f_options_

Detailed Description

Facilitates file handling by file type recognition.

This class provides file type recognition from the file name and from the file content.

It also offer a common interface to load MSExperiment data and allows querying for supported file types.

See also

FileTypes

Member Function Documentation

applyPostLoadOptions_()

void applyPostLoadOptions_ ( MSExperiment &  exp ) const

private

Applies the current PeakFileOptions filters to an already-loaded experiment.

Used by the vendor-format paths. Bruker .d: loadExperiment() has the reader skip the MS levels, retention times and DDA precursors the options exclude, so that this data is not decoded; the filters here make the result exact (the reader's ranges are inclusive). Thermo .raw: the scan-level filters are passed to ThermoRawFile, only the per-peak filters are applied here. Filters MS level, RT range, precursor m/z range, ion mobility range, per-peak m/z and intensity ranges, and strips peak data when metadata-only is requested or fill-data is off. transformExperiment() applies the same filters to each spectrum. Calls updateRanges() at the end.

computeFileHash()

static std::string computeFileHash ( const std::string &  filename )

static

Computes a SHA-1 hash value for the content of the given file.

Returns

The SHA-1 hash of the given file.

getConsistentOutputfileType()

static FileTypes::Type getConsistentOutputfileType ( const std::string &  output_filename, const std::string &  requested_type  )

static

Useful function for TOPP tools which have an 'out_type' parameter and want to know what output format to write. This function makes sure that the type derived from output_filename and requested_type are consistent, i.e. are either identical or one of them is UNKNOWN. Upon conflict, an error message is printed and the UNKNOWN type is returned.

Parameters

[in]	output_filename	A full filename (with none, absolute or relative paths) whose type is determined using FileHandler::getTypeByFileName() internally
[in]	requested_type	A type as string, usually obtained from '-out_type', e.g. "FASTA" (case insensitive). The string can be empty (yields UNKNOWN for this type)

Returns

A consistent file type or UNKNOWN upon conflict

getFeatOptions() [1/2]

FeatureFileOptions & getFeatOptions

(

)

Mutable access to the feature file options for loading/storing.

getFeatOptions() [2/2]

const FeatureFileOptions & getFeatOptions

(

)

const

Non-mutable access to the feature file options for loading/storing.

getOptions() [1/2]

PeakFileOptions & getOptions

(

)

Mutable access to the options for loading/storing.

Referenced by MS1LabeledSpectra::load(), TOPPFLASHDeconv::main_(), and TOPPViewBase::metadataFileDialog().

getOptions() [2/2]

const PeakFileOptions & getOptions

(

)

const

Non-mutable access to the options for loading/storing.

getType()

static FileTypes::Type getType ( const std::string &  filename )

static

Tries to determine the file type (by name or content)

First tries to determine the type from the file name. If this fails, the type is determined from the file content.

Parameters

[in]

filename

the name of the file to check

Returns

A FileTypes::Type corresponding to the extension, or FileTypes::UNKNOWN if not determinable

Exceptions

Exception::FileNotFound

is thrown if the file is not present

Referenced by TOPPViewBase::addDataFile(), MS1LabeledSpectra::load(), and OpenMS::Internal::ClassTest::validateTmpFiles().

getTypeByContent()

static FileTypes::Type getTypeByContent ( const std::string &  filename )

static

Determines the file type of a file by parsing the first few lines.

Parameters

[in]

filename

The file to check

Exceptions

Exception::FileNotFound

is thrown if the file is not present

Referenced by InspectOutfile::getExperiment().

getTypeByFileName()

static FileTypes::Type getTypeByFileName ( const std::string &  filename )

static

Try to get the file type from the filename.

Parameters

[in]

filename

the name of the file to check

Returns

A FileTypes::Type corresponding to the extension, or FileTypes::UNKNOWN if not determinable

Exceptions

Exception::FileNotFound

is thrown if the file is not present

hasValidExtension()

static bool hasValidExtension ( const std::string &  filename, const FileTypes::Type  type  )

static

Check if filename has the extension type.

If the extension is not known (e.g. '.tmp') this is also allowed. However, if the extension is another one (neither type nor unknown), false is returned.

Parameters

[in]	filename	The filename to check
[in]	type	The expected file type

isSupported()

static bool isSupported ( FileTypes::Type  type )

static

Returns if the file type is supported in this build of the library.

loadConsensusFeatures()

void loadConsensusFeatures	(	const std::string &	filename,
		ConsensusMap &	map,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Loads a file into a ConsensusMap.

Parameters

[in]	filename	the file name of the file to load.
[in]	map	The ConsensusMap to load the data into.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type
[in]	log	Progress logging mode

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

Referenced by TOPPViewBase::addDataFile(), TOPPViewBase::fileChanged_(), and TOPPGNPSExport::main_().

loadExperiment()

void loadExperiment	(	const std::string &	filename,
		PeakMap &	exp,
		const std::vector< FileTypes::Type >	allowed_types = std::vector< FileTypes::Type >(),
		ProgressLogger::LogType	log = ProgressLogger::NONE,
		const bool	rewrite_source_file = false,
		const bool	compute_hash = false
	)

Loads a file into an MSExperiment.

Parameters

[out]	filename	The file name of the file to load.
[in]	exp	The experiment to load the data into.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type
[in]	log	Progress logging mode
[in]	rewrite_source_file	Set's the SourceFile name and path to the current file. Note that this looses the link to the primary MS run the file originated from.
[out]	compute_hash	If source files are rewritten, this flag triggers a recomputation of hash values. A SHA1 string gets stored in the checksum member of SourceFile.

Note

Thermo .raw files (OpenMS built with WITH_THERMO_RAW) are read with Thermo's peak picking, like FileConverter does by default, so profile scans are returned centroided. Use ThermoRawFile directly to keep the scans as they were acquired. As for mzML, SRM scans (triple quadrupoles) are converted to chromatograms. The MS level, RT range, precursor m/z range, metadata-only, fill-data and skip-chromatograms options are passed to the reader, so skipped scans are not decoded (fill-data off loads spectra without peaks, like metadata-only). The SourceFile carries no SHA-1 checksum unless rewrite_source_file and compute_hash are set. Bruker .d directories and .d.zip archives (OpenMS built with WITH_OPENTIMS): the MS levels and the RT and ion mobility ranges are passed to the reader, which selects the spectra by their RT (a DDA MS2 spectrum is built from all of its frames) and skips the DDA precursors isolated outside the ion mobility range, so the frames they exclude are not decoded; all options are then applied to the loaded spectra. The ion mobility range (PeakFileOptions::setIMRange()) is applied to the data of every format here; the format readers themselves ignore it.

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

Referenced by TOPPViewBase::addDataFile(), CachedSwathFileConsumer::ensureMapsAreFilled_(), TOPPViewBase::fileChanged_(), InspectOutfile::getExperiment(), MS1LabeledSpectra::load(), TOPPFLASHDeconv::main_(), and NucleicAcidSearchEngine::main_().

loadFeatures()

void loadFeatures	(	const std::string &	filename,
		FeatureMap &	map,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Loads a file into a FeatureMap.

Parameters

[in]	filename	the file name of the file to load.
[out]	map	The FeatureMap to load the data into.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type
[in]	log	Progress logging mode

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

Referenced by TOPPViewBase::addDataFile(), and TOPPViewBase::fileChanged_().

loadIdentifications()

void loadIdentifications	(	const std::string &	filename,
		std::vector< ProteinIdentification > &	additional_proteins,
		PeptideIdentificationList &	additional_peptides,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Loads an identification file into a proteinIdentifications and peptideIdentifications.

Parameters

[in]	filename	the file name of the file to load.
[in]	additional_proteins	The proteinIdentification vector to load the data into.
[in]	additional_peptides	The peptideIdentification vector to load the data into.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type
[in]	log	Progress logging mode

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

Referenced by TOPPViewBase::addDataFile().

loadImagingExperiment()

void loadImagingExperiment	(	const std::string &	filename,
		MSImagingExperiment &	exp,
		const std::vector< FileTypes::Type >	allowed_types = std::vector< FileTypes::Type >(),
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Loads a mass spectrometry imaging file into an MSImagingExperiment.

Imaging data is always loaded into an MSImagingExperiment. Supported here are imzML (via ImzMLFile) and Bruker timsTOF MALDI imaging .d folders and .d.zip archives (via BrukerTimsImagingFile, OpenMS built with WITH_OPENTIMS).

Parameters

[in]	filename	The file name of the file to load.
[out]	exp	The imaging experiment to load the data into; replaced (not appended).
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any imaging type that we have a handler for.
[in]	log	Progress logging mode

Exceptions

Exception::InvalidFileType	is thrown if the file is not an imaging format
Exception::ParseError	is thrown if the type is not in allowed_types
Exception::InvalidValue	is thrown for a .d folder that is not MALDI imaging

loadSpectrum()

void loadSpectrum	(	const std::string &	filename,
		MSSpectrum &	spec,
		const std::vector< FileTypes::Type >	allowed_types = {}
	)

Loads a single MSSpectrum from a file.

Parameters

[in]	filename	The file name of the file to load.
[out]	spec	The spectrum to load the data into.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

loadTransformations()

void loadTransformations	(	const std::string &	filename,
		TransformationDescription &	map,
		bool	fit_model = true,
		const std::vector< FileTypes::Type >	allowed_types = {}
	)

Loads a file into Transformations.

Parameters

[in]	filename	the file name of the file to load.
[out]	map	The Transformations to load the data into.
[in]	fit_model	Call fitModel() on the map before returning?
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

loadTransitions()

void loadTransitions	(	const std::string &	filename,
		TargetedExperiment &	library,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Load transitions of a spectral library.

Parameters

[in]	filename	the file name of the file to read.
[out]	library	The TargetedExperiment to load.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type
[in]	log	Progress logging mode

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

setFeatOptions()

void setFeatOptions

(

const FeatureFileOptions &

)

set feature file options for loading/storing

setOptions()

void setOptions

(

const PeakFileOptions &

)

set options for loading/storing

Referenced by TOPPFLASHDeconv::main_(), and NucleicAcidSearchEngine::main_().

storeConsensusFeatures()

void storeConsensusFeatures	(	const std::string &	filename,
		const ConsensusMap &	map,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Store a ConsensusFeatureMap.

Parameters

[in]	filename	the file name of the file to write.
[out]	map	The ConsensusMap to store.
[in]	allowed_types	Restricts the set of file formats this call may write. Empty: infer the format from the filename extension; if that fails, throw InvalidFileType. Size 1: if the filename's type is UNKNOWN (e.g. TOPPAS intermediate ".unknown" files), fall back to this single type. Otherwise the filename type must equal it, or InvalidFileType is thrown. Size >1: the filename type must be one of these; UNKNOWN filenames CANNOT be disambiguated and will throw InvalidFileType. TOPP tools writing through TOPPAS pipelines must therefore pass a single concrete type here (typically derived from the input file type or an out_type parameter), not the full list of formats they support.
[in]	log	Progress logging mode

Exceptions

Exception::UnableToCreateFile	is thrown if the file could not be written
Exception::InvalidFileType	is thrown if the file type cannot be determined or is not allowed

storeExperiment()

void storeExperiment	(	const std::string &	filename,
		const PeakMap &	exp,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Stores an MSExperiment to a file.

The file type to store the data in is determined by the file name. Supported formats for storing are mzML, mzXML, mzData and DTA2D. If the file format cannot be determined from the file name, the mzML format is used.

Parameters

[in]	filename	The name of the file to store the data in.
[out]	exp	The experiment to store.
[in]	allowed_types	A vector of supported filetypes. If empty we try to guess based on the filename. If that fails we throw UnableToCreateFile. If there is only one allowed type, check whether it agrees with the filename, and throw UnableToCreateFile if they disagree.
[in]	log	Progress logging mode

Exceptions

Exception::UnableToCreateFile

is thrown if the file could not be written

Referenced by NucleicAcidSearchEngine::main_().

storeFeatures()

void storeFeatures	(	const std::string &	filename,
		const FeatureMap &	map,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Store a FeatureMap.

Parameters

[in]	filename	the file name of the file to write.
[out]	map	The FeatureMap to store.
[in]	allowed_types	Restricts the set of file formats this call may write. Empty: infer the format from the filename extension; if that fails, throw InvalidFileType. Size 1: if the filename's type is UNKNOWN (e.g. TOPPAS intermediate ".unknown" files), fall back to this single type. Otherwise the filename type must equal it, or InvalidFileType is thrown. Size >1: the filename type must be one of these; UNKNOWN filenames CANNOT be disambiguated and will throw InvalidFileType. TOPP tools writing through TOPPAS pipelines must therefore pass a single concrete type here (typically derived from the input file type or an out_type parameter), not the full list of formats they support.
[in]	log	Progress logging mode

Exceptions

Exception::UnableToCreateFile	is thrown if the file could not be written
Exception::InvalidFileType	is thrown if the file type cannot be determined or is not allowed

storeIdentifications()

void storeIdentifications	(	const std::string &	filename,
		const std::vector< ProteinIdentification > &	additional_proteins,
		const PeptideIdentificationList &	additional_peptides,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Stores proteins and peptides into an Identification File.

Parameters

[in]	filename	the file name of the file to write to.
[in]	additional_proteins	The proteinIdentification vector to load the data from.
[in]	additional_peptides	The peptideIdentification vector to load the data from.
[in]	allowed_types	Restricts the set of file formats this call may write. Empty: infer the format from the filename extension; if that fails, throw InvalidFileType. Size 1: if the filename's type is UNKNOWN (e.g. TOPPAS intermediate ".unknown" files), fall back to this single type. Otherwise the filename type must equal it, or InvalidFileType is thrown. Size >1: the filename type must be one of these; UNKNOWN filenames CANNOT be disambiguated and will throw InvalidFileType. TOPP tools writing through TOPPAS pipelines must therefore pass a single concrete type here (typically derived from the input file type or an out_type parameter), not the full list of formats they support.
[in]	log	Progress logging mode

Exceptions

Exception::UnableToCreateFile	is thrown if the file could not be written
Exception::InvalidFileType	is thrown if the file type cannot be determined or is not allowed

Referenced by NucleicAcidSearchEngine::main_().

storeQC()

void storeQC	(	const std::string &	input_file,
		const std::string &	filename,
		const MSExperiment &	exp,
		const FeatureMap &	feature_map,
		std::vector< ProteinIdentification > &	prot_ids,
		PeptideIdentificationList &	pep_ids,
		const ConsensusMap &	consensus_map,
		const std::string &	contact_name = "",
		const std::string &	contact_address = "",
		const std::string &	description = "",
		const std::string &	label = "label",
		const bool	remove_duplicate_features = false,
		const std::vector< FileTypes::Type >	allowed_types = {}
	)

Store QC info.

Stores QC data in mzQC file with JSON format

Parameters

[in]	input_file	mzML input file name
[in]	filename	mzQC output file name
[in]	exp	MSExperiment to extract QC data from, prior sortSpectra() and updateRanges() required
[in]	feature_map	FeatureMap from feature file (featureXML)
[in]	prot_ids	protein identifications from ID file (idXML)
[in]	pep_ids	protein identifications from ID file (idXML)
[out]	consensus_map	an optional consensus map to store.
[in]	contact_name	name of the person creating the mzQC file
[in]	contact_address	contact address (mail/e-mail or phone) of the person creating the mzQC file
[in]	description	description and comments about the mzQC file contents
[in]	label	unique and informative label for the run
[in]	remove_duplicate_features	whether to remove duplicate features only for QCML for now
[in]	allowed_types	A vector of supported filetypes. If empty we try to guess based on the filename. If that fails we throw UnableToCreateFile. If there is only one allowed type, check whether it agrees with the filename, and throw UnableToCreateFile if they disagree.

Exceptions

Exception::UnableToCreateFile

is thrown if the file could not be written

storeSpectrum()

void storeSpectrum	(	const std::string &	filename,
		MSSpectrum &	spec,
		const std::vector< FileTypes::Type >	allowed_types = {}
	)

Stores a single MSSpectrum to a file.

Parameters

[in]	filename	The file name of the file to store.
[in]	spec	The spectrum to store the data from.
[in]	allowed_types	A vector of supported filetypes. If the vector is empty, load from any type that we have a handler for. Otherwise getType() is called internally to check the type

Exceptions

Exception::UnableToCreateFile

is thrown if the file could not be written

storeTransformations()

void storeTransformations	(	const std::string &	filename,
		const TransformationDescription &	map,
		const std::vector< FileTypes::Type >	allowed_types = {}
	)

Store Transformations.

Parameters

[out]	filename	the file name of the file to write.
[in]	map	The Transformations to store.
[in]	allowed_types	A vector of supported filetypes. If empty we try to guess based on the filename. If that fails we throw UnableToCreateFile. If there is only one allowed type, check whether it agrees with the filename, and throw UnableToCreateFile if they disagree.

Exceptions

Exception::UnableToCreateFile

is thrown if the file could not be written

storeTransitions()

void storeTransitions	(	const std::string &	filename,
		const TargetedExperiment &	library,
		const std::vector< FileTypes::Type >	allowed_types = {},
		ProgressLogger::LogType	log = ProgressLogger::NONE
	)

Store transitions of a spectral library.

Parameters

[out]	filename	the file name of the file to write.
[out]	library	The TargetedExperiment to store.
[in]	allowed_types	A vector of supported filetypes. If empty we try to guess based on the filename. If that fails we throw UnableToCreateFile. If there is only one allowed type, check whether it agrees with the filename, and throw UnableToCreateFile if they disagree.
[in]	log	Progress logging mode

Exceptions

Exception::UnableToCreateFile

is thrown if the file could not be written

stripExtension()

static std::string stripExtension ( const std::string &  filename )

static

If filename contains an extension, it will be removed (including the '.'). Special extensions, known to OpenMS, e.g. '.mzML.gz' will be recognized as well.

E.g. 'experiment.featureXML' becomes 'experiment' and 'c:\files\data.mzML.gz' becomes 'c:\files\data' If the extension is unknown, the everything in the basename of the file after the last '.' is removed. E.g. 'future.newEnding' becomes 'future' If the filename does not contain '.', but the path (if any) does, nothing is removed, e.g. '/my.dotted.dir/filename' is returned unchanged.

Parameters

[in]

filename

the name to strip

Returns

the stripped filename

swapExtension()

static std::string swapExtension ( const std::string &  filename, const FileTypes::Type  new_type  )

static

Tries to find and remove a known file extension, and append the new one.

Internally calls 'stripExtension()' and adds the new suffix to the result. E.g. 'experiment.featureXML'+ FileTypes::TRANSFORMATIONXML becomes 'experiment.trafoXML' and 'c:\files\data.mzML.gz' + FileTypes::FEATUREXML becomes 'c:\files\data.featureXML' If the existing extension is unknown, the everything after the last '.' is removed, e.g. 'exp.tmp' + FileTypes::IDXML becomes 'exp.idXML'

Parameters

[in]	filename	the original filename
[in]	new_type	the FileTypes::Types to use to set the new extension

Returns

the updated string

Referenced by TOPPViewBase::addDataFile().

transformExperiment()

void transformExperiment	(	const std::string &	filename,
		Interfaces::IMSDataConsumer *	consumer,
		const std::vector< FileTypes::Type >	allowed_types = std::vector< FileTypes::Type >(),
		ProgressLogger::LogType	log = ProgressLogger::NONE,
		const bool	rewrite_source_file = false,
		const bool	compute_hash = false
	)

Streams a file into a consumer, spectrum by spectrum, without holding the whole experiment in memory.

The consumer receives IMSDataConsumer::setExpectedSize() and IMSDataConsumer::setExperimentalSettings() first, then the spectra and chromatograms. Supported are mzML (MzMLFile::transform), mzXML (MzXMLFile::transform), Thermo .raw (ThermoRawFile::transform, OpenMS built with WITH_THERMO_RAW) and Bruker timsTOF .d directories and .d.zip archives (BrukerTimsFile::transform, OpenMS built with WITH_OPENTIMS). The PeakFileOptions are applied as by loadExperiment(); .raw files are read centroided and with the scan-level options passed to the reader, as by loadExperiment(). For .d data the reader skips the frames the options exclude, as for loadExperiment(), and every spectrum is then filtered on its way to the consumer. Bruker MALDI imaging data is rejected, as by loadExperiment(). Unlike loadExperiment(), mzML and .raw spectra that hold chromatogram data (SRM) are not converted to chromatograms. For mzML and mzXML the sizes passed to IMSDataConsumer::setExpectedSize() come from the file and ignore the selection; for .raw they are the numbers of selected spectra and chromatograms. For .d data the number of spectra is an upper bound: it is counted before any peak is read (see BrukerTimsFile::transform()), and the spectra the options exclude are not subtracted. Some Bruker configurations are loaded completely before the first spectrum is passed on (see BrukerTimsFile::transform()); the default configuration used here is not one of them.

Parameters

[in]	filename	The file to read
[in]	consumer	Receives the data (not owned)
[in]	allowed_types	Supported file types; if empty, any streamable type
[in]	log	Progress logging mode
[in]	rewrite_source_file	Set the SourceFile name and path to filename (as loadExperiment())
[in]	compute_hash	If source files are rewritten, store the SHA-1 of filename in the SourceFile

Exceptions

Exception::NullPointer	is thrown if consumer is null
Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing or the type is not in allowed_types
Exception::InvalidFileType	is thrown if the file type cannot be streamed

Member Data Documentation

f_options_

FeatureFileOptions f_options_

private

options_

PeakFileOptions options_

private