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

#include <OpenMS/FORMAT/FileHandler.h>

Collaboration diagram for FileHandler:

Public Member Functions
PeakFileOptions &	getOptions ()
	Mutable access to the options for loading/storing. More...

const PeakFileOptions &	getOptions () const
	Non-mutable access to the options for loading/storing. More...

FeatureFileOptions &	getFeatOptions ()
	Mutable access to the feature file options for loading/storing. More...

const FeatureFileOptions &	getFeatOptions () const
	Non-mutable access to the feature file options for loading/storing. More...

void	setOptions (const PeakFileOptions &)
	set options for loading/storing More...

void	setFeatOptions (const FeatureFileOptions &)
	set feature file options for loading/storing More...

void	loadExperiment (const 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. More...

void	storeExperiment (const String &filename, const PeakMap &exp, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Stores an MSExperiment to a file. More...

void	loadSpectrum (const String &filename, MSSpectrum &spec, const std::vector< FileTypes::Type > allowed_types={})
	Loads a single MSSpectrum from a file. More...

void	storeSpectrum (const String &filename, MSSpectrum &spec, const std::vector< FileTypes::Type > allowed_types={})
	Stores a single MSSpectrum to a file. More...

void	loadFeatures (const String &filename, FeatureMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads a file into a FeatureMap. More...

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

void	loadConsensusFeatures (const String &filename, ConsensusMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads a file into a ConsensusMap. More...

void	storeConsensusFeatures (const String &filename, const ConsensusMap &map, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Store a ConsensusFeatureMap. More...

void	loadIdentifications (const String &filename, std::vector< ProteinIdentification > &additional_proteins, std::vector< PeptideIdentification > &additional_peptides, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Loads an identification file into a proteinIdentifications and peptideIdentifications. More...

void	storeIdentifications (const String &filename, const std::vector< ProteinIdentification > &additional_proteins, const std::vector< PeptideIdentification > &additional_peptides, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Stores proteins and peptides into an Identification File. More...

void	loadTransitions (const String &filename, TargetedExperiment &library, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Load transitions of a spectral library. More...

void	storeTransitions (const String &filename, const TargetedExperiment &library, const std::vector< FileTypes::Type > allowed_types={}, ProgressLogger::LogType log=ProgressLogger::NONE)
	Store transitions of a spectral library. More...

void	loadTransformations (const String &filename, TransformationDescription &map, bool fit_model=true, const std::vector< FileTypes::Type > allowed_types={})
	Loads a file into Transformations. More...

void	storeTransformations (const String &filename, const TransformationDescription &map, const std::vector< FileTypes::Type > allowed_types={})
	Store Transformations. More...

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

Static Public Member Functions
static FileTypes::Type	getType (const String &filename)
	Tries to determine the file type (by name or content) More...

static FileTypes::Type	getTypeByFileName (const String &filename)
	Try to get the file type from the filename. More...

static bool	hasValidExtension (const String &filename, const FileTypes::Type type)
	Check if `filename` has the extension `type`. More...

static String	stripExtension (const 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. More...

static String	swapExtension (const String &filename, const FileTypes::Type new_type)
	Tries to find and remove a known file extension, and append the new one. More...

static FileTypes::Type	getConsistentOutputfileType (const String &output_filename, const 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. More...

static FileTypes::Type	getTypeByContent (const String &filename)
	Determines the file type of a file by parsing the first few lines. More...

static bool	isSupported (FileTypes::Type type)
	Returns if the file type is supported in this build of the library. More...

static String	computeFileHash (const String &filename)
	Computes a SHA-1 hash value for the content of the given file. More...

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

◆ computeFileHash()

static String computeFileHash ( const 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 String &	output_filename,
		const 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

output_filename	A full filename (with none, absolute or relative paths) whose type is determined using FileHandler::getTypeByFileName() internally
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 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 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

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(), and TOPPOpenSwathBase::performCalibration().

◆ getTypeByContent()

static FileTypes::Type getTypeByContent ( const String & filename )

static

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

Exceptions

Exception::FileNotFound is thrown if the file is not present

Referenced by InspectOutfile::getExperiment().

◆ getTypeByFileName()

static FileTypes::Type getTypeByFileName ( const String & filename )

static

Try to get the file type from the filename.

Parameters

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 TOPPOpenSwathBase::loadSwathFiles_().

◆ hasValidExtension()

static bool hasValidExtension	(	const 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.

◆ 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 String &	filename,
		ConsensusMap &	map,
		const std::vector< FileTypes::Type >	allowed_types = `{}`,
		ProgressLogger::LogType	log = `ProgressLogger::NONE`
	)

Loads a file into a ConsensusMap.

Parameters

filename	the file name of the file to load.
map	The ConsensusMap to load the data into.
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
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 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

filename	The file name of the file to load.
exp	The experiment to load the data into.
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
log	Progress logging mode
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.
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.

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

◆ loadFeatures()

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

Loads a file into a FeatureMap.

Parameters

filename	the file name of the file to load.
map	The FeatureMap to load the data into.
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
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 String &	filename,
		std::vector< ProteinIdentification > &	additional_proteins,
		std::vector< PeptideIdentification > &	additional_peptides,
		const std::vector< FileTypes::Type >	allowed_types = `{}`,
		ProgressLogger::LogType	log = `ProgressLogger::NONE`
	)

Loads an identification file into a proteinIdentifications and peptideIdentifications.

Parameters

filename	the file name of the file to load.
additional_proteins	The proteinIdentification vector to load the data into.
additional_peptides	The peptideIdentification vector to load the data into.
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
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().

◆ loadSpectrum()

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

Loads a single MSSpectrum from a file.

Parameters

filename	The file name of the file to load.
spec	The spectrum to load the data into.
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 String &	filename,
		TransformationDescription &	map,
		bool	fit_model = `true`,
		const std::vector< FileTypes::Type >	allowed_types = `{}`
	)

Loads a file into Transformations.

Parameters

	filename	the file name of the file to load.
[out]	map	The Transformations to load the data into.
	fit_model	Call fitModel() on the `map` before returning?
	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

Referenced by TOPPOpenSwathBase::performCalibration().

◆ loadTransitions()

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

Load transitions of a spectral library.

Parameters

filename	the file name of the file to read.
library	The TargetedExperiment to load.
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
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 TOPPOpenSwathBase::loadTransitionList().

◆ 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 String &	filename,
		const ConsensusMap &	map,
		const std::vector< FileTypes::Type >	allowed_types = `{}`,
		ProgressLogger::LogType	log = `ProgressLogger::NONE`
	)

Store a ConsensusFeatureMap.

Parameters

filename	the file name of the file to write.
map	The ConsensusMap to store.
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.
log	Progress logging mode

Exceptions

Exception::UnableToCreateFile is thrown if the file could not be written

◆ storeExperiment()

void storeExperiment	(	const 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

filename	The name of the file to store the data in.
exp	The experiment to store.
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.
log	Progress logging mode

Exceptions

Exception::UnableToCreateFile is thrown if the file could not be written

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

◆ storeFeatures()

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

Store a FeatureMap.

Parameters

filename	the file name of the file to write.
map	The FeatureMap to store.
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.
log	Progress logging mode

Exceptions

Exception::UnableToCreateFile is thrown if the file could not be written

◆ storeIdentifications()

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

Stores proteins and peptides into an Identification File.

Parameters

filename	the file name of the file to write to.
additional_proteins	The proteinIdentification vector to load the data from.
additional_peptides	The peptideIdentification vector to load the data from.
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.
log	Progress logging mode

Exceptions

Exception::UnableToCreateFile is thrown if the file could not be written

Referenced by NucleicAcidSearchEngine::main_().

◆ storeQC()

void storeQC	(	const String &	input_file,
		const String &	filename,
		const MSExperiment &	exp,
		const FeatureMap &	feature_map,
		std::vector< ProteinIdentification > &	prot_ids,
		std::vector< PeptideIdentification > &	pep_ids,
		const ConsensusMap &	consensus_map = `ConsensusMap()`,
		const String &	contact_name = `""`,
		const String &	contact_address = `""`,
		const String &	description = `""`,
		const 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

input_file	mzML input file name
filename	mzQC output file name
exp	MSExperiment to extract QC data from, prior sortSpectra() and updateRanges() required
feature_map	FeatureMap from feature file (featureXML)
prot_ids	protein identifications from ID file (idXML)
pep_ids	protein identifications from ID file (idXML)
consensus_map	an optional consensus map to store.
contact_name	name of the person creating the mzQC file
contact_address	contact address (mail/e-mail or phone) of the person creating the mzQC file
description	description and comments about the mzQC file contents
label	unique and informative label for the run
remove_duplicate_features	whether to remove duplicate features only for QCML for now
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 String &	filename,
		MSSpectrum &	spec,
		const std::vector< FileTypes::Type >	allowed_types = `{}`
	)

Stores a single MSSpectrum to a file.

Parameters

filename	The file name of the file to store.
spec	The spectrum to store the data from.
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 String &	filename,
		const TransformationDescription &	map,
		const std::vector< FileTypes::Type >	allowed_types = `{}`
	)

Store Transformations.

Parameters

filename	the file name of the file to write.
map	The Transformations to store.
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

Referenced by TOPPOpenSwathBase::performCalibration().

◆ storeTransitions()

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

Store transitions of a spectral library.

Parameters

filename	the file name of the file to write.
library	The TargetedExperiment to store.
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.
log	Progress logging mode

Exceptions

Exception::UnableToCreateFile is thrown if the file could not be written

◆ stripExtension()

static String stripExtension ( const 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

filename the name to strip

Returns: the stripped filename

Referenced by TOPPViewBase::addDataFile().

◆ swapExtension()

static String swapExtension	(	const 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

filename	the original `filename`
new_type	the `FileTypes::Types` to use to set the new extension

Returns: the updated string

Referenced by TOPPViewBase::addDataFile().

Member Data Documentation

◆ f_options_

FeatureFileOptions f_options_

private

◆ options_

PeakFileOptions options_

private

Public Member Functions

Static Public Member Functions

Private Attributes

Detailed Description

Member Function Documentation

◆ computeFileHash()

◆ getConsistentOutputfileType()

◆ getFeatOptions() [1/2]

◆ getFeatOptions() [2/2]

◆ getOptions() [1/2]

◆ getOptions() [2/2]

◆ getType()

◆ getTypeByContent()

◆ getTypeByFileName()

◆ hasValidExtension()

◆ isSupported()

◆ loadConsensusFeatures()

◆ loadExperiment()

◆ loadFeatures()

◆ loadIdentifications()

◆ loadSpectrum()

◆ loadTransformations()

◆ loadTransitions()

◆ setFeatOptions()

◆ setOptions()

◆ storeConsensusFeatures()

◆ storeExperiment()

◆ storeFeatures()

◆ storeIdentifications()

◆ storeQC()

◆ storeSpectrum()

◆ storeTransformations()

◆ storeTransitions()

◆ stripExtension()

◆ swapExtension()

Member Data Documentation

◆ f_options_

◆ options_