Consumer class that writes MS data to disk using the mzML format. More...

#include <OpenMS/FORMAT/DATAACCESS/MSDataWritingConsumer.h>

Inheritance diagram for MSDataWritingConsumer:

Public Types
typedef PeakMap	MapType

typedef MapType::SpectrumType	SpectrumType

typedef MapType::ChromatogramType	ChromatogramType

Public Types inherited from XMLHandler
enum	ActionMode { LOAD, STORE }
	Action to set the current mode (for error messages) More...

Public Types inherited from IMSDataConsumer
typedef MSSpectrum	SpectrumType

typedef MSChromatogram	ChromatogramType

Public Member Functions
	MSDataWritingConsumer (String filename)
	Constructor. More...

virtual	~MSDataWritingConsumer ()
	Destructor. More...

virtual void	addDataProcessing (DataProcessing d)
	Optionally add a data processing method to each chromatogram and spectrum. More...

virtual Size	getNrSpectraWritten ()
	Return the number of spectra written. More...

virtual Size	getNrChromatogramsWritten ()
	Return the number of chromatograms written. More...

IMSDataConsumer interface
virtual void	setExperimentalSettings (const ExperimentalSettings &exp)
	Set experimental settings for the whole file. More...

virtual void	setExpectedSize (Size expectedSpectra, Size expectedChromatograms)
	Set expected size of spectra and chromatograms to be written. More...

virtual void	consumeSpectrum (SpectrumType &s)
	Consume a spectrum. More...

virtual void	consumeChromatogram (ChromatogramType &c)
	Consume a chromatogram. More...

Public Member Functions inherited from MzMLHandler
void	getCounts (Size &spectra_counts, Size &chromatogram_counts)
	Get the spectra and chromatogram counts of a file. More...

void	setMSDataConsumer (Interfaces::IMSDataConsumer *consumer)
	Set the IMSDataConsumer consumer which will consume the read data. More...

	MzMLHandler (MapType &exp, const String &filename, const String &version, ProgressLogger &logger)
	Constructor for a read-only handler. More...

	MzMLHandler (const MapType &exp, const String &filename, const String &version, const ProgressLogger &logger)
	Constructor for a write-only handler. More...

virtual	~MzMLHandler ()
	Destructor. More...

virtual void	endElement (const XMLCh const, const XMLCh const, const XMLCh *const qname)
	Parsing method for closing tags. More...

virtual void	startElement (const XMLCh const, const XMLCh const, const XMLCh *const qname, const xercesc::Attributes &attributes)
	Parsing method for opening tags. More...

virtual void	characters (const XMLCh *const chars, const XMLSize_t length)
	Parsing method for character data. More...

virtual void	writeTo (std::ostream &os)
	Writes the contents to a stream. More...

void	setOptions (const PeakFileOptions &opt)
	Set the peak file options. More...

PeakFileOptions &	getOptions ()
	Get the peak file options. More...

Public Member Functions inherited from XMLHandler
	XMLHandler (const String &filename, const String &version)
	Default constructor. More...

virtual	~XMLHandler ()
	Destructor. More...

void	reset ()
	Release internal memory used for parsing (call. More...

void	fatalError (ActionMode mode, const String &msg, UInt line=0, UInt column=0) const
	Fatal error handler. Throws a ParseError exception. More...

void	error (ActionMode mode, const String &msg, UInt line=0, UInt column=0) const
	Error handler for recoverable errors. More...

void	warning (ActionMode mode, const String &msg, UInt line=0, UInt column=0) const
	Warning handler. More...

String	errorString ()
	Returns the last error description. More...

void	fatalError (const xercesc::SAXParseException &exception)

void	error (const xercesc::SAXParseException &exception)

void	warning (const xercesc::SAXParseException &exception)

Public Member Functions inherited from IMSDataConsumer
virtual	~IMSDataConsumer ()

Protected Attributes
std::ofstream	ofs_
	File stream (to write mzML) More...

bool	started_writing_
	Stores whether we have already started writing any data. More...

bool	writing_spectra_
	Stores whether we are currently writing spectra. More...

bool	writing_chromatograms_
	Stores whether we are currently writing chromatograms. More...

Size	spectra_written_
	Number of spectra written. More...

Size	chromatograms_written_
	Number of chromatograms written. More...

Size	spectra_expected_
	Number of spectra expected. More...

Size	chromatograms_expected_
	Number of chromatograms expected. More...

bool	add_dataprocessing_
	Whether to add dataprocessing term to the data before writing. More...

Internal::MzMLValidator *	validator_
	Validator that knows about CV terms. More...

ExperimentalSettings	settings_
	Experimental settings to use for the whole file. More...

std::vector< std::vector< ConstDataProcessingPtr > >	dps_
	Vector of data processing objects -> will be filled by writeHeader_. More...

DataProcessingPtr	additional_dataprocessing_
	The dataprocessing to be added to each spectrum/chromatogram. More...

Protected Attributes inherited from MzMLHandler
MapType *	exp_
	map pointer for reading More...

const MapType *	cexp_
	map pointer for writing More...

PeakFileOptions	options_
	Options that can be set for loading/storing. More...

Base64	decoder_
	Decoder/Encoder for Base64-data in MzML. More...

const ProgressLogger &	logger_
	Progress logger. More...

Interfaces::IMSDataConsumer *	consumer_
	Consumer class to work on spectra. More...

UInt	scan_count
	Counting spectra and chromatograms. More...

UInt	chromatogram_count

bool	skip_chromatogram_
	Flag that indicates whether this spectrum should be skipped (due to options) More...

bool	skip_spectrum_

bool	rt_set_

ControlledVocabulary	cv_
	Controlled vocabulary (psi-ms from OpenMS/share/OpenMS/CV/psi-ms.obo) More...

CVMappings	mapping_

UInt	selected_ion_count_
	Count of selected ions. More...

SpectrumType	spec_
	The current spectrum. More...

ChromatogramType	chromatogram_
	The current chromatogram. More...

std::vector< BinaryData >	data_
	The spectrum data (or chromatogram data) More...

Size	default_array_length_
	The default number of peaks in the current spectrum. More...

bool	in_spectrum_list_
	Flag that indicates that we're inside a spectrum (in contrast to a chromatogram) More...

String	current_id_
	Id of the current list. Used for referencing param group, source file, sample, software, ... More...

Map< String, std::vector< SemanticValidator::CVTerm > >	ref_param_
	The referencing param groups: id => array (accession, value) More...

Map< String, SourceFile >	source_files_
	The source files: id => SourceFile. More...

Map< String, Sample >	samples_
	The sample list: id => Sample. More...

Map< String, Software >	software_
	The software list: id => Software. More...

Map< String, Instrument >	instruments_
	The data processing list: id => Instrument. More...

Map< String, std::vector< DataProcessingPtr > >	processing_
	The data processing list: id => Instrument. More...

String	default_processing_
	id of the default data processing (used when no processing is defined) More...

std::vector< SpectrumData >	spectrum_data_
	Vector of spectrum data stored for later parallel processing. More...

std::vector< ChromatogramData >	chromatogram_data_
	Vector of chromatogram data stored for later parallel processing. More...

std::vector< std::pair< std::string, long > >	spectra_offsets

std::vector< std::pair< std::string, long > >	chromatograms_offsets

Protected Attributes inherited from XMLHandler
String	error_message_
	Error message of the last error. More...

String	file_
	File name. More...

String	version_
	Schema version. More...

StringManager	sm_
	Helper class for string conversion. More...

std::vector< String >	open_tags_
	Stack of open XML tags. More...

std::vector< std::vector< String > >	cv_terms_
	Array of CV term lists (one sublist denotes one term and it's children) More...

Private Member Functions
virtual void	doCleanup_ ()
	Cleanup function called by the destructor. More...

Data Processing using the template method pattern
virtual void	processSpectrum_ (SpectrumType &s)=0
	Process a spectrum before storing to disk. More...

virtual void	processChromatogram_ (ChromatogramType &c)=0
	Process a chromatogram before storing to disk. More...

Additional Inherited Members
Static Public Member Functions inherited from XMLHandler
static String	writeXMLEscape (const String &to_escape)
	Escapes a string and returns the escaped string. More...

Protected Types inherited from MzMLHandler
typedef MapType::PeakType	PeakType
	Peak type. More...

typedef MapType::ChromatogramPeakType	ChromatogramPeakType
	Chromatogram peak type. More...

typedef MSSpectrum	SpectrumType
	Spectrum type. More...

typedef MSChromatogram	ChromatogramType
	Spectrum type. More...

typedef MzMLHandlerHelper::BinaryData	BinaryData

Protected Member Functions inherited from MzMLHandler
void	writeSpectrum_ (std::ostream &os, const SpectrumType &spec, Size s, Internal::MzMLValidator &validator, bool renew_native_ids, std::vector< std::vector< ConstDataProcessingPtr > > &dps)

void	writeChromatogram_ (std::ostream &os, const ChromatogramType &chromatogram, Size c, Internal::MzMLValidator &validator)

template<typename ContainerT >
void	writeContainerData (std::ostream &os, const PeakFileOptions &pf_options_, const ContainerT &container, String array_type)

void	populateSpectraWithData ()
	Populate all spectra on the stack with data from input. More...

void	populateChromatogramsWithData ()
	Populate all chromatograms on the stack with data from input. More...

void	addSpectrumMetaData_ (const std::vector< MzMLHandlerHelper::BinaryData > &input_data, const Size n, SpectrumType &spectrum) const

void	populateSpectraWithData_ (std::vector< MzMLHandlerHelper::BinaryData > &input_data, Size &default_arr_length, const PeakFileOptions &peak_file_options, SpectrumType &spectrum)
	Fill a single spectrum with data from input. More...

void	populateChromatogramsWithData_ (std::vector< MzMLHandlerHelper::BinaryData > &input_data, Size &default_arr_length, const PeakFileOptions &peak_file_options, ChromatogramType &inp_chromatogram)
	Fill a single chromatogram with data from input. More...

template<typename DataType >
void	writeBinaryDataArray (std::ostream &os, const PeakFileOptions &pf_options_, std::vector< DataType > data_to_encode, bool is32bit, String array_type)

void	writeHeader_ (std::ostream &os, const MapType &exp, std::vector< std::vector< ConstDataProcessingPtr > > &dps, Internal::MzMLValidator &validator)

void	fillChromatogramData_ ()
	Fills the current chromatogram with data points and meta data. More...

void	handleCVParam_ (const String &parent_parent_tag, const String &parent_tag, const String &accession, const String &name, const String &value, const String &unit_accession="")
	Handles CV terms. More...

void	handleUserParam_ (const String &parent_parent_tag, const String &parent_tag, const String &name, const String &type, const String &value)
	Handles user terms. More...

void	writeUserParam_ (std::ostream &os, const MetaInfoInterface &meta, UInt indent, String path, Internal::MzMLValidator &validator) const
	Writes user terms. More...

ControlledVocabulary::CVTerm	getChildWithName_ (const String &parent_accession, const String &name) const
	Looks up a child CV term of `parent_accession` with the name `name`. If no such term is found, an empty term is returned. More...

void	writeSoftware_ (std::ostream &os, const String &id, const Software &software, Internal::MzMLValidator &validator)
	Helper method that writes a software. More...

void	writeSourceFile_ (std::ostream &os, const String &id, const SourceFile &software, Internal::MzMLValidator &validator)
	Helper method that writes a source file. More...

void	writeDataProcessing_ (std::ostream &os, const String &id, const std::vector< ConstDataProcessingPtr > &dps, Internal::MzMLValidator &validator)
	Helper method that writes a data processing list. More...

void	writePrecursor_ (std::ostream &os, const Precursor &precursor, Internal::MzMLValidator &validator)
	Helper method that write precursor information from spectra and chromatograms. More...

void	writeProduct_ (std::ostream &os, const Product &product, Internal::MzMLValidator &validator)
	Helper method that write precursor information from spectra and chromatograms. More...

String	writeCV_ (const ControlledVocabulary::CVTerm &c, const DataValue &metaValue) const
	Helper method to write an CV based on a meta value. More...

bool	validateCV_ (const ControlledVocabulary::CVTerm &c, const String &path, const Internal::MzMLValidator &validator) const
	Helper method to validate if the given CV is allowed in the current location (path) More...

Protected Member Functions inherited from XMLHandler
bool	equal_ (const XMLCh a, const XMLCh b) const
	Returns if two Xerces strings are equal. More...

void	writeUserParam_ (const String &tag_name, std::ostream &os, const MetaInfoInterface &meta, UInt indent) const
	Writes the content of MetaInfoInterface to the file. More...

Int	asInt_ (const String &in)
	Conversion of a String to an integer value. More...

Int	asInt_ (const XMLCh *in)
	Conversion of a Xerces string to an integer value. More...

UInt	asUInt_ (const String &in)
	Conversion of a String to an unsigned integer value. More...

double	asDouble_ (const String &in)
	Conversion of a String to a double value. More...

float	asFloat_ (const String &in)
	Conversion of a String to a float value. More...

bool	asBool_ (const String &in)
	Conversion of a string to a boolean value. More...

DateTime	asDateTime_ (String date_string)
	Conversion of a xs:datetime string to a DateTime value. More...

char *	attributeAsString_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a String. More...

Int	attributeAsInt_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a Int. More...

double	attributeAsDouble_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a double. More...

DoubleList	attributeAsDoubleList_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a DoubleList. More...

IntList	attributeAsIntList_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to an IntList. More...

StringList	attributeAsStringList_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to an StringList. More...

bool	optionalAttributeAsString_ (String &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the String value if the attribute is present. More...

bool	optionalAttributeAsInt_ (Int &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the Int value if the attribute is present. More...

bool	optionalAttributeAsUInt_ (UInt &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the UInt value if the attribute is present. More...

bool	optionalAttributeAsDouble_ (double &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the double value if the attribute is present. More...

bool	optionalAttributeAsDoubleList_ (DoubleList &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the DoubleList value if the attribute is present. More...

bool	optionalAttributeAsStringList_ (StringList &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the StringList value if the attribute is present. More...

bool	optionalAttributeAsIntList_ (IntList &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the IntList value if the attribute is present. More...

char *	attributeAsString_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a String. More...

Int	attributeAsInt_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a Int. More...

double	attributeAsDouble_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a double. More...

DoubleList	attributeAsDoubleList_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a DoubleList. More...

IntList	attributeAsIntList_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a IntList. More...

StringList	attributeAsStringList_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a StringList. More...

bool	optionalAttributeAsString_ (String &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the String value if the attribute is present. More...

bool	optionalAttributeAsInt_ (Int &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the Int value if the attribute is present. More...

bool	optionalAttributeAsUInt_ (UInt &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the UInt value if the attribute is present. More...

bool	optionalAttributeAsDouble_ (double &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the double value if the attribute is present. More...

bool	optionalAttributeAsDoubleList_ (DoubleList &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the DoubleList value if the attribute is present. More...

bool	optionalAttributeAsIntList_ (IntList &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the IntList value if the attribute is present. More...

bool	optionalAttributeAsStringList_ (StringList &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the StringList value if the attribute is present. More...

SignedSize	cvStringToEnum_ (const Size section, const String &term, const char *message, const SignedSize result_on_error=0)

Detailed Description

Consumer class that writes MS data to disk using the mzML format.

The MSDataWritingConsumer is able to write spectra and chromatograms to disk on the fly (as soon as they are consumed). This class is abstract and allows the derived class to define how spectra and chromatograms are processed before being written to disk.

If you are looking for class that simply takes spectra and chromatograms and writes them to disk, please use the PlainMSDataWritingConsumer.

Example usage:

MSDataWritingConsumer * consumer = new MSDataWritingConsumer(outfile); // some implementation
consumer->setExpectedSize(specsize, chromsize);
consumer->setExperimentalSettings(exp_settings);
consumer->addDataProcessing(dp); // optional, will be added to all spectra and chromatograms
[...]
// multiple times ... 
consumer->consumeSpectrum(spec);
consumer->consumeChromatogram(chrom);
[...]
delete consumer;

Note: The first usage of consumeChromatogram or consumeSpectrum will start writing of the mzML header to disk (and the first element).; Currently it is not possible to add spectra after having already added chromatograms since this could lead to a situation with multiple spectrumList tags appear in an mzML file.; The expected size will not be enforced but it will lead to an inconsistent mzML if the count attribute of spectrumList or chromatogramList is incorrect.

Member Typedef Documentation

◆ ChromatogramType

typedef MapType::ChromatogramType ChromatogramType

◆ MapType

typedef PeakMap MapType

◆ SpectrumType

typedef MapType::SpectrumType SpectrumType

Constructor & Destructor Documentation

◆ MSDataWritingConsumer()

MSDataWritingConsumer ( String filename )

explicit

Constructor.

Parameters

filename Filename for the output mzML

◆ ~MSDataWritingConsumer()

virtual ~MSDataWritingConsumer ( )

virtual

Destructor.

Member Function Documentation

◆ addDataProcessing()

virtual void addDataProcessing ( DataProcessing d )

virtual

Optionally add a data processing method to each chromatogram and spectrum.

The provided DataProcessing object will be added to each chromatogram and spectrum written to to the mzML file.

Parameters

d	The DataProcessing object to be added

Referenced by extractCachedMetaFilename(), and SortPairDoubleByFirst().

◆ consumeChromatogram()

virtual void consumeChromatogram ( ChromatogramType & c )

virtual

Consume a chromatogram.

The chromatogram will be processed using the processChromatogram_ method of the current implementation and then written to the mzML file.

Parameters

c	The chromatogram to be written to mzML

Implements IMSDataConsumer.

Reimplemented in NoopMSDataWritingConsumer.

Referenced by IndexedMzMLFileLoader::store().

◆ consumeSpectrum()

virtual void consumeSpectrum ( SpectrumType & s )

virtual

Consume a spectrum.

The spectrum will be processed using the processSpectrum_ method of the current implementation and then written to the mzML file.

Parameters

s	The spectrum to be written to mzML

Implements IMSDataConsumer.

Reimplemented in NoopMSDataWritingConsumer.

Referenced by IndexedMzMLFileLoader::store().

◆ doCleanup_()

virtual void doCleanup_ ( )

privatevirtual

Cleanup function called by the destructor.

Will write the last tags to the file and close the file stream.

Reimplemented in NoopMSDataWritingConsumer.

◆ getNrChromatogramsWritten()

virtual Size getNrChromatogramsWritten ( )

virtual

Return the number of chromatograms written.

◆ getNrSpectraWritten()

virtual Size getNrSpectraWritten ( )

virtual

Return the number of spectra written.

◆ processChromatogram_()

virtual void processChromatogram_ ( ChromatogramType & c )

privatepure virtual

Process a chromatogram before storing to disk.

Redefine this function to determine chromatogram processing before writing to disk.

Implemented in NoopMSDataWritingConsumer, and PlainMSDataWritingConsumer.

◆ processSpectrum_()

virtual void processSpectrum_ ( SpectrumType & s )

privatepure virtual

Process a spectrum before storing to disk.

Redefine this function to determine spectra processing before writing to disk.

Implemented in NoopMSDataWritingConsumer, and PlainMSDataWritingConsumer.

◆ setExpectedSize()

virtual void setExpectedSize	(	Size	expectedSpectra,
		Size	expectedChromatograms
	)

virtual

Set expected size of spectra and chromatograms to be written.

These numbers will be written in the spectrumList and chromatogramList tag in the mzML file. Therefore, these will contain wrong numbers if the expected size is not set correctly.

Parameters

expectedSpectra	Number of spectra expected
expectedChromatograms	Number of chromatograms expected

Implements IMSDataConsumer.

Referenced by SortPairDoubleByFirst(), and IndexedMzMLFileLoader::store().

◆ setExperimentalSettings()

virtual void setExperimentalSettings ( const ExperimentalSettings & exp )

virtual

Set experimental settings for the whole file.

Parameters

exp	Experimental settings to be used for this file (from this and the first spectrum/chromatogram, the class will deduce most of the header of the mzML file)

Implements IMSDataConsumer.

Reimplemented in NoopMSDataWritingConsumer.

Referenced by SortPairDoubleByFirst(), and IndexedMzMLFileLoader::store().

Member Data Documentation

◆ add_dataprocessing_

bool add_dataprocessing_

protected

Whether to add dataprocessing term to the data before writing.

◆ additional_dataprocessing_

DataProcessingPtr additional_dataprocessing_

protected

The dataprocessing to be added to each spectrum/chromatogram.

◆ chromatograms_expected_

Size chromatograms_expected_

protected

Number of chromatograms expected.

◆ chromatograms_written_

Size chromatograms_written_

protected

Number of chromatograms written.

◆ dps_

std::vector<std::vector< ConstDataProcessingPtr > > dps_

protected

Vector of data processing objects -> will be filled by writeHeader_.

◆ ofs_

std::ofstream ofs_

protected

File stream (to write mzML)

◆ settings_

ExperimentalSettings settings_

protected

Experimental settings to use for the whole file.

◆ spectra_expected_

Size spectra_expected_

protected

Number of spectra expected.

◆ spectra_written_

Size spectra_written_

protected

Number of spectra written.

◆ started_writing_

bool started_writing_

protected

Stores whether we have already started writing any data.

◆ validator_

Internal::MzMLValidator* validator_

protected

Validator that knows about CV terms.

◆ writing_chromatograms_

bool writing_chromatograms_

protected

Stores whether we are currently writing chromatograms.

◆ writing_spectra_

bool writing_spectra_

protected

Stores whether we are currently writing spectra.

Public Types

Public Member Functions

Protected Attributes

Private Member Functions

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ ChromatogramType

◆ MapType

◆ SpectrumType

Constructor & Destructor Documentation

◆ MSDataWritingConsumer()

◆ ~MSDataWritingConsumer()

Member Function Documentation

◆ addDataProcessing()

◆ consumeChromatogram()

◆ consumeSpectrum()

◆ doCleanup_()

◆ getNrChromatogramsWritten()

◆ getNrSpectraWritten()

◆ processChromatogram_()

◆ processSpectrum_()

◆ setExpectedSize()

◆ setExperimentalSettings()

Member Data Documentation

◆ add_dataprocessing_

◆ additional_dataprocessing_

◆ chromatograms_expected_

◆ chromatograms_written_

◆ dps_

◆ ofs_

◆ settings_

◆ spectra_expected_

◆ spectra_written_

◆ started_writing_

◆ validator_

◆ writing_chromatograms_

◆ writing_spectra_