Used to load Mascot PepXML files. More...

#include <OpenMS/FORMAT/PepXMLFileMascot.h>

Inheritance diagram for PepXMLFileMascot:

Collaboration diagram for PepXMLFileMascot:

Public Member Functions
	PepXMLFileMascot ()
	Constructor.

void	load (const std::string &filename, std::map< std::string, std::vector< AASequence > > &peptides)
	Loads peptide sequences with modifications out of a PepXML file.

Public Member Functions inherited from XMLFile
	XMLFile ()
	Construct an XMLFile without schema info; `schema_location_` remains unset, so isValid cannot be used until derived-class logic initializes `schema_location_` before calling isValid.

	XMLFile (const std::string &schema_location, const std::string &version)
	Construct with a schema location for later isValid calls.

virtual	~XMLFile ()
	Virtual destructor — defaulted; allows safe deletion through a base-class pointer.

bool	isValid (const std::string &filename, std::ostream &os)
	Check if `filename` validates against the bound XML schema.

const std::string &	getVersion () const
	Return the schema version string passed to the parameterised constructor; empty for default-constructed instances.

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	matchModification_ (double mass, std::string &modification_description)

Protected Member Functions inherited from XMLHandler
void	writeUserParam_ (const std::string &tag_name, std::ostream &os, const MetaInfoInterface &meta, UInt indent) const
	Writes the content of MetaInfoInterface to the file.

Int	asInt_ (const std::string &in) const
	Conversion of a std::string to an integer value.

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

UInt	asUInt_ (const std::string &in) const
	Conversion of a std::string to an unsigned integer value.

double	asDouble_ (const std::string &in) const
	Conversion of a std::string to a double value.

float	asFloat_ (const std::string &in) const
	Conversion of a std::string to a float value.

bool	asBool_ (const std::string &in) const
	Conversion of a string to a boolean value.

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

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

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

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

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

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

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

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

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

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

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.

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.

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.

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.

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.

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.

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

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

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

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

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

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

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

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.

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.

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.

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.

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.

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.

	XMLHandler (const std::string &filename, const std::string &version)
	Default constructor.

	~XMLHandler () override
	Destructor.

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

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 std::string &msg, UInt line=0, UInt column=0) const
	Fatal error handler. Throws a ParseError exception.

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

void	warning (ActionMode mode, const std::string &msg, UInt line=0, UInt column=0) const
	Warning handler.

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

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

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

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

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

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

DataValue	cvParamToValue (const ControlledVocabulary &cv, const std::string &parent_tag, const std::string &accession, const std::string &name, const std::string &value, const std::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.

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.

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

Protected Member Functions inherited from XMLFile
void	parse_ (const std::string &filename, XMLHandler *handler)
	Parse the XML file at `filename` through `handler`.

void	parseBuffer_ (const std::string &buffer, XMLHandler *handler)
	Parse an in-memory XML buffer through `handler`.

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

void	enforceEncoding_ (const std::string &encoding)
	Set or clear the XML-encoding override applied to subsequent parse_ / parseBuffer_ calls.

	XMLFile ()
	Construct an XMLFile without schema info; `schema_location_` remains unset, so isValid cannot be used until derived-class logic initializes `schema_location_` before calling isValid.

	XMLFile (const std::string &schema_location, const std::string &version)
	Construct with a schema location for later isValid calls.

virtual	~XMLFile ()
	Virtual destructor — defaulted; allows safe deletion through a base-class pointer.

bool	isValid (const std::string &filename, std::ostream &os)
	Check if `filename` validates against the bound XML schema.

const std::string &	getVersion () const
	Return the schema version string passed to the parameterised constructor; empty for default-constructed instances.

Protected Attributes
members for loading data
std::string	actual_title_
	Pointer to fill in protein identifications.

std::string	actual_sequence_
	The sequence of the actual peptide hit.

std::vector< std::pair< std::string, UInt > >	actual_modifications_
	The modifications of the actual peptide hit (position is 1-based)

std::map< std::string, std::vector< AASequence > > *	peptides_
	The peptides together with the spectrum title.

std::vector< AASequence >	actual_aa_sequences_
	stores the actual peptide sequences

std::vector< std::string >	fixed_modifications_
	stores the fixed residue modifications

std::vector< std::pair< std::string, double > >	variable_modifications_
	stores the variable residue modifications

Protected Attributes inherited from XMLHandler
std::string	file_
	File name.

std::string	version_
	Schema version.

StringManager	sm_
	Helper class for string conversion.

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

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

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

Protected Attributes inherited from XMLFile
std::string	schema_location_
	Path of the XML schema for validation; empty when the default constructor was used (isValid then throws `NotImplemented`).

std::string	schema_version_
	Schema version string returned by getVersion.

std::string	enforced_encoding_
	Optional XML encoding override applied to the `InputSource` in parse_ and parseBuffer_; empty disables the override. Used as a workaround for XTandem output XML which carries an encoding the parser otherwise stumbles on.

Additional Inherited Members
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 }

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

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

Detailed Description

Used to load Mascot PepXML files.

A schema for this format can be found at http://www.matrixscience.com/xmlns/schema/pepXML_v18/pepXML_v18.xsd.

Constructor & Destructor Documentation

◆ PepXMLFileMascot()

PepXMLFileMascot ( )

Constructor.

Member Function Documentation

◆ endElement()

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

overrideprotected

◆ load()

void load	(	const std::string &	filename,
		std::map< std::string, std::vector< AASequence > > &	peptides
	)

Loads peptide sequences with modifications out of a PepXML file.

Exceptions

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

◆ matchModification_()

void matchModification_	(	double	mass,
		std::string &	modification_description
	)

protected

◆ startElement()

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

overrideprotected

Member Data Documentation

◆ actual_aa_sequences_

std::vector<AASequence> actual_aa_sequences_

protected

stores the actual peptide sequences

◆ actual_modifications_

std::vector<std::pair<std::string, UInt> > actual_modifications_

protected

The modifications of the actual peptide hit (position is 1-based)

◆ actual_sequence_

std::string actual_sequence_

protected

The sequence of the actual peptide hit.

◆ actual_title_

std::string actual_title_

protected

Pointer to fill in protein identifications.

The title of the actual spectrum

◆ fixed_modifications_

std::vector<std::string> fixed_modifications_

protected

stores the fixed residue modifications

◆ peptides_

std::map<std::string, std::vector<AASequence> >* peptides_

protected

The peptides together with the spectrum title.

◆ variable_modifications_

std::vector<std::pair<std::string, double> > variable_modifications_

protected

stores the variable residue modifications

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ PepXMLFileMascot()

Member Function Documentation

◆ endElement()

◆ load()

◆ matchModification_()

◆ startElement()

Member Data Documentation

◆ actual_aa_sequences_

◆ actual_modifications_

◆ actual_sequence_

◆ actual_title_

◆ fixed_modifications_

◆ peptides_

◆ variable_modifications_