Used to load and store idXML files. More...

#include <OpenMS/FORMAT/IdXMLFile.h>

Inheritance diagram for IdXMLFile:

Collaboration diagram for IdXMLFile:

Public Member Functions
	IdXMLFile ()
	Constructor. More...

void	load (const String &filename, std::vector< ProteinIdentification > &protein_ids, std::vector< PeptideIdentification > &peptide_ids)
	Loads the identifications of an idXML file without identifier. More...

void	load (const String &filename, std::vector< ProteinIdentification > &protein_ids, std::vector< PeptideIdentification > &peptide_ids, String &document_id)
	Loads the identifications of an idXML file. More...

void	store (const String &filename, const std::vector< ProteinIdentification > &protein_ids, const std::vector< PeptideIdentification > &peptide_ids, const String &document_id="")
	Stores the data in an idXML file. More...

Public Member Functions inherited from XMLFile
	XMLFile ()
	Default constructor. More...

	XMLFile (const String &schema_location, const String &version)
	Constructor that sets the schema location. More...

virtual	~XMLFile ()
	Destructor. More...

bool	isValid (const String &filename, std::ostream &os)
	Checks if a file validates against the XML schema. More...

const String &	getVersion () const
	return the version of the schema More...

Public Member Functions inherited from ProgressLogger
	ProgressLogger ()
	Constructor. More...

virtual	~ProgressLogger ()
	Destructor. More...

	ProgressLogger (const ProgressLogger &other)
	Copy constructor. More...

ProgressLogger &	operator= (const ProgressLogger &other)
	Assignment Operator. More...

void	setLogType (LogType type) const
	Sets the progress log that should be used. The default type is NONE! More...

LogType	getLogType () const
	Returns the type of progress log being used. More...

void	setLogger (ProgressLoggerImpl *logger)
	Sets the logger to be used for progress logging. More...

void	startProgress (SignedSize begin, SignedSize end, const String &label) const
	Initializes the progress display. More...

void	setProgress (SignedSize value) const
	Sets the current progress. More...

void	endProgress (UInt64 bytes_processed=0) const

void	nextProgress () const
	increment progress by 1 (according to range begin-end) More...

Protected Member Functions
void	endElement (const XMLCh const, const XMLCh const, const XMLCh *const qname) override

void	startElement (const XMLCh const, const XMLCh const, const XMLCh *const qname, const xercesc::Attributes &attributes) override

void	addProteinGroups_ (MetaInfoInterface &meta, const std::vector< ProteinIdentification::ProteinGroup > &groups, const String &group_name, const std::unordered_map< std::string, UInt > &accession_to_id, XMLHandler::ActionMode mode)

void	getProteinGroups_ (std::vector< ProteinIdentification::ProteinGroup > &groups, const String &group_name)
	Read and store ProteinGroup data. More...

Protected Member Functions inherited from XMLHandler
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) const
	Conversion of a String to an integer value. More...

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

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

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

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

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

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

bool	equal_ (const XMLCh a, const XMLCh b) const
	Returns if two Xerces strings are equal. More...

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

String	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...

String	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...

	XMLHandler (const String &filename, const String &version)
	Default constructor. More...

	~XMLHandler () override
	Destructor. More...

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

void	fatalError (const xercesc::SAXParseException &exception) override

void	error (const xercesc::SAXParseException &exception) override

void	warning (const xercesc::SAXParseException &exception) override

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...

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

void	startElement (const XMLCh const uri, const XMLCh const localname, const XMLCh *const qname, const xercesc::Attributes &attrs) override
	Parsing method for opening tags. More...

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

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

virtual LOADDETAIL	getLoadDetail () const
	handler which support partial loading, implement this method More...

virtual void	setLoadDetail (const LOADDETAIL d)
	handler which support partial loading, implement this method More...

DataValue	cvParamToValue (const ControlledVocabulary &cv, const String &parent_tag, const String &accession, const String &name, const String &value, const String &unit_accession) const
	Convert the value of a <cvParam value=.> (as commonly found in PSI schemata) to the DataValue with the correct type (e.g. int) according to the type stored in the CV (usually PSI-MS CV), as well as set its unit. More...

DataValue	cvParamToValue (const ControlledVocabulary &cv, const CVTerm &raw_term) const
	Convert the value of a <cvParam value=.> (as commonly found in PSI schemata) to the DataValue with the correct type (e.g. int) according to the type stored in the CV (usually PSI-MS CV), as well as set its unit. More...

void	checkUniqueIdentifiers_ (const std::vector< ProteinIdentification > &prot_ids) const

Protected Member Functions inherited from XMLFile
void	parse_ (const String &filename, XMLHandler *handler)
	Parses the XML file given by `filename` using the handler given by `handler`. More...

void	parseBuffer_ (const std::string &buffer, XMLHandler *handler)
	Parses the in-memory buffer given by `buffer` using the handler given by `handler`. More...

void	save_ (const String &filename, XMLHandler *handler) const
	Stores the contents of the XML handler given by `handler` in the file given by `filename`. More...

void	enforceEncoding_ (const String &encoding)

	XMLFile ()
	Default constructor. More...

	XMLFile (const String &schema_location, const String &version)
	Constructor that sets the schema location. More...

virtual	~XMLFile ()
	Destructor. More...

bool	isValid (const String &filename, std::ostream &os)
	Checks if a file validates against the XML schema. More...

const String &	getVersion () const
	return the version of the schema More...

Protected Member Functions inherited from ProgressLogger
	ProgressLogger ()
	Constructor. More...

virtual	~ProgressLogger ()
	Destructor. More...

	ProgressLogger (const ProgressLogger &other)
	Copy constructor. More...

ProgressLogger &	operator= (const ProgressLogger &other)
	Assignment Operator. More...

void	setLogType (LogType type) const
	Sets the progress log that should be used. The default type is NONE! More...

LogType	getLogType () const
	Returns the type of progress log being used. More...

void	setLogger (ProgressLoggerImpl *logger)
	Sets the logger to be used for progress logging. More...

void	startProgress (SignedSize begin, SignedSize end, const String &label) const
	Initializes the progress display. More...

void	setProgress (SignedSize value) const
	Sets the current progress. More...

void	endProgress (UInt64 bytes_processed=0) const

void	nextProgress () const
	increment progress by 1 (according to range begin-end) More...

Static Protected Member Functions
static std::ostream &	createFlankingAAXMLString_ (const std::vector< PeptideEvidence > &pes, std::ostream &os)

static std::ostream &	createPositionXMLString_ (const std::vector< PeptideEvidence > &pes, std::ostream &os)

static void	writeFragmentAnnotations_ (const String &tag_name, std::ostream &os, const std::vector< PeptideHit::PeakAnnotation > &annotations, UInt indent)

static void	parseFragmentAnnotation_ (const String &s, std::vector< PeptideHit::PeakAnnotation > &annotations)

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

static DataValue	fromXSDString (const String &type, const String &value)
	Convert an XSD type (e.g. 'xsd:double') to a DataValue. More...

Protected Attributes
members for loading data
std::vector< ProteinIdentification > *	prot_ids_
	Pointer to fill in protein identifications. More...

std::vector< PeptideIdentification > *	pep_ids_
	Pointer to fill in peptide identifications. More...

MetaInfoInterface *	last_meta_
	Pointer to last read object with MetaInfoInterface. More...

std::map< String, ProteinIdentification::SearchParameters >	parameters_
	Search parameters map (key is the "id") More...

ProteinIdentification::SearchParameters	param_
	Temporary search parameters variable. More...

String	id_
	Temporary id. More...

ProteinIdentification	prot_id_
	Temporary protein ProteinIdentification. More...

PeptideIdentification	pep_id_
	Temporary peptide ProteinIdentification. More...

ProteinHit	prot_hit_
	Temporary protein hit. More...

PeptideHit	pep_hit_
	Temporary peptide hit. More...

PeptideHit::PepXMLAnalysisResult	current_analysis_result_
	Temporary analysis result instance. More...

std::vector< PeptideEvidence >	peptide_evidences_
	Temporary peptide evidences. More...

std::unordered_map< std::string, String >	proteinid_to_accession_
	Map from protein id to accession. More...

String *	document_id_
	Document identifier. More...

bool	prot_id_in_run_
	true if a prot id is contained in the current run More...

Protected Attributes inherited from XMLHandler
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...

LOADDETAIL	load_detail_
	parse only until total number of scans and chroms have been determined from attributes More...

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

Protected Attributes inherited from XMLFile
String	schema_location_
	XML schema file location. More...

String	schema_version_
	Version string. More...

String	enforced_encoding_
	Encoding string that replaces the encoding (system dependent or specified in the XML). Disabled if empty. Used as a workaround for XTandem output xml. More...

Protected Attributes inherited from ProgressLogger
LogType	type_

time_t	last_invoke_

ProgressLoggerImpl *	current_logger_

Friends
class	Internal::ConsensusXMLHandler

class	Internal::FeatureXMLHandler

Additional Inherited Members
Public Types inherited from ProgressLogger
enum	LogType { CMD , GUI , NONE }
	Possible log types. More...

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

enum	LOADDETAIL { LD_ALLDATA , LD_RAWCOUNTS , LD_COUNTS_WITHOPTIONS }

Protected Types inherited from ProgressLogger
enum	LogType { CMD , GUI , NONE }
	Possible log types. More...

Static Protected Attributes inherited from ProgressLogger
static int	recursion_depth_

Detailed Description

Used to load and store idXML files.

This class is used to load and store documents that implement the schema of idXML files.

A documented schema for this format can be found at https://github.com/OpenMS/OpenMS/tree/develop/share/OpenMS/SCHEMAS

One file can contain several ProteinIdentification runs. Each run consists of peptide hits stored in PeptideIdentification and (optional) protein hits stored in Identification. Peptide and protein hits are connected via a string identifier. We use the search engine and the date as identifier.

Constructor & Destructor Documentation

◆ IdXMLFile()

IdXMLFile ( )

Constructor.

Member Function Documentation

◆ addProteinGroups_()

void addProteinGroups_	(	MetaInfoInterface &	meta,
		const std::vector< ProteinIdentification::ProteinGroup > &	groups,
		const String &	group_name,
		const std::unordered_map< std::string, UInt > &	accession_to_id,
		XMLHandler::ActionMode	mode
	)

protected

Add data from ProteinGroups to a MetaInfoInterface Since it can be used during load and store, it needs to take a param for the current mode (LOAD/STORE) to throw appropriate warnings/errors

◆ createFlankingAAXMLString_()

static std::ostream& createFlankingAAXMLString_	(	const std::vector< PeptideEvidence > &	pes,
		std::ostream &	os
	)

staticprotected

Helper function to create the XML string for the amino acids before and after the peptide position in a protein. Can be reused by e.g. ConsensusXML, FeatureXML to write PeptideHit elements

◆ createPositionXMLString_()

static std::ostream& createPositionXMLString_	(	const std::vector< PeptideEvidence > &	pes,
		std::ostream &	os
	)

staticprotected

Helper function to create the XML string for the position of the peptide in a protein. Can be reused by e.g. ConsensusXML, FeatureXML to write PeptideHit elements

◆ endElement()

void endElement	(	const XMLCh * const	,
		const XMLCh * const	,
		const XMLCh *const	qname
	)

overrideprotected

◆ getProteinGroups_()

void getProteinGroups_	(	std::vector< ProteinIdentification::ProteinGroup > &	groups,
		const String &	group_name
	)

protected

Read and store ProteinGroup data.

◆ load() [1/2]

void load	(	const String &	filename,
		std::vector< ProteinIdentification > &	protein_ids,
		std::vector< PeptideIdentification > &	peptide_ids
	)

Loads the identifications of an idXML file without identifier.

The information is read in and the information is stored in the corresponding variables

Exceptions

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

◆ load() [2/2]

void load	(	const String &	filename,
		std::vector< ProteinIdentification > &	protein_ids,
		std::vector< PeptideIdentification > &	peptide_ids,
		String &	document_id
	)

Loads the identifications of an idXML file.

The information is read in and the information is stored in the corresponding variables

Exceptions

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

◆ parseFragmentAnnotation_()

static void parseFragmentAnnotation_	(	const String &	s,
		std::vector< PeptideHit::PeakAnnotation > &	annotations
	)

staticprotected

Helper function to parse fragment annotations from string

◆ startElement()

void startElement	(	const XMLCh * const	,
		const XMLCh * const	,
		const XMLCh *const	qname,
		const xercesc::Attributes &	attributes
	)

overrideprotected

◆ store()

void store	(	const String &	filename,
		const std::vector< ProteinIdentification > &	protein_ids,
		const std::vector< PeptideIdentification > &	peptide_ids,
		const String &	document_id = `""`
	)

Stores the data in an idXML file.

The data is read in and stored in the file 'filename'. PeptideHits are sorted by score. Note that ranks are not stored and need to be reassigned after loading.

Exceptions

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

◆ writeFragmentAnnotations_()

static void writeFragmentAnnotations_	(	const String &	tag_name,
		std::ostream &	os,
		const std::vector< PeptideHit::PeakAnnotation > &	annotations,
		UInt	indent
	)

staticprotected

Helper function to write out fragment annotations as user param fragment_annotation

Friends And Related Function Documentation

◆ Internal::ConsensusXMLHandler

friend class Internal::ConsensusXMLHandler

friend

◆ Internal::FeatureXMLHandler

friend class Internal::FeatureXMLHandler

friend

Member Data Documentation

◆ current_analysis_result_

PeptideHit::PepXMLAnalysisResult current_analysis_result_

protected

Temporary analysis result instance.

◆ document_id_

String* document_id_

protected

Document identifier.

◆ id_

String id_

protected

Temporary id.

◆ last_meta_

MetaInfoInterface* last_meta_

protected

Pointer to last read object with MetaInfoInterface.

◆ param_

ProteinIdentification::SearchParameters param_

protected

Temporary search parameters variable.

◆ parameters_

std::map<String, ProteinIdentification::SearchParameters> parameters_

protected

Search parameters map (key is the "id")

◆ pep_hit_

PeptideHit pep_hit_

protected

Temporary peptide hit.

◆ pep_id_

PeptideIdentification pep_id_

protected

Temporary peptide ProteinIdentification.

◆ pep_ids_

std::vector<PeptideIdentification>* pep_ids_

protected

Pointer to fill in peptide identifications.

◆ peptide_evidences_

std::vector<PeptideEvidence> peptide_evidences_

protected

Temporary peptide evidences.

◆ prot_hit_

ProteinHit prot_hit_

protected

Temporary protein hit.

◆ prot_id_

ProteinIdentification prot_id_

protected

Temporary protein ProteinIdentification.

◆ prot_id_in_run_

bool prot_id_in_run_

protected

true if a prot id is contained in the current run

◆ prot_ids_

std::vector<ProteinIdentification>* prot_ids_

protected

Pointer to fill in protein identifications.

◆ proteinid_to_accession_

std::unordered_map<std::string, String> proteinid_to_accession_

protected

Map from protein id to accession.

Public Member Functions

Protected Member Functions

Static Protected Member Functions

Protected Attributes

Friends

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ IdXMLFile()

Member Function Documentation

◆ addProteinGroups_()

◆ createFlankingAAXMLString_()

◆ createPositionXMLString_()

◆ endElement()

◆ getProteinGroups_()

◆ load() [1/2]

◆ load() [2/2]

◆ parseFragmentAnnotation_()

◆ startElement()

◆ store()

◆ writeFragmentAnnotations_()

Friends And Related Function Documentation

◆ Internal::ConsensusXMLHandler

◆ Internal::FeatureXMLHandler

Member Data Documentation

◆ current_analysis_result_

◆ document_id_

◆ id_

◆ last_meta_

◆ param_

◆ parameters_

◆ pep_hit_

◆ pep_id_

◆ pep_ids_

◆ peptide_evidences_

◆ prot_hit_

◆ prot_id_

◆ prot_id_in_run_

◆ prot_ids_

◆ proteinid_to_accession_