Semantic validator for mzML files. More...

#include <OpenMS/FORMAT/VALIDATORS/MzMLValidator.h>

Inheritance diagram for MzMLValidator:

Collaboration diagram for MzMLValidator:

Public Member Functions
	MzMLValidator (const CVMappings &mapping, const ControlledVocabulary &cv)
	Constructor.

	~MzMLValidator () override
	Destructor.

Public Member Functions inherited from SemanticValidator
	SemanticValidator (const CVMappings &mapping, const ControlledVocabulary &cv)
	Constructor.

	~SemanticValidator () override
	Destructor.

bool	validate (const std::string &filename, StringList &errors, StringList &warnings)
	Semantically validates an XML file.

bool	locateTerm (const std::string &path, const CVTerm &parsed_term) const
	Checks if a CVTerm is allowed in a given path.

void	setTag (const std::string &tag)
	Sets the CV parameter tag name (default: 'cvParam')

void	setAccessionAttribute (const std::string &accession)
	Sets the name of the attribute for accessions in the CV parameter tag name (default: 'accession')

void	setNameAttribute (const std::string &name)
	Sets the name of the attribute for accessions in the CV parameter tag name (default: 'name')

void	setValueAttribute (const std::string &value)
	Sets the name of the attribute for accessions in the CV parameter tag name (default: 'value')

void	setCheckTermValueTypes (bool check)
	Set if CV term value types should be check (enabled by default)

void	setCheckUnits (bool check)
	Set if CV term units should be check (disabled by default)

void	setUnitAccessionAttribute (const std::string &accession)
	Sets the name of the unit accession attribute (default: 'unitAccession')

void	setUnitNameAttribute (const std::string &name)
	Sets the name of the unit name attribute (default: 'unitName')

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

std::string	getPath_ (UInt remove_from_end=0) const override
	Returns the current element path.

void	handleTerm_ (const std::string &path, const CVTerm &parsed_term) override
	Handling of the term.

Protected Member Functions inherited from SemanticValidator
void	startElement (const XMLCh const, const XMLCh const, const XMLCh *const qname, const xercesc::Attributes &attributes) override

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

void	characters (const XMLCh *const chars, const XMLSize_t) override

virtual void	getCVTerm_ (const xercesc::Attributes &attributes, CVTerm &parsed_term)
	Parses the CV term accession (required), name (required) and value (optional) from the XML attributes.

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
std::map< std::string, std::vector< CVTerm > >	param_groups_
	CV terms which can have a value (term => value type)

std::string	current_id_
	Current referenceableParamGroup identifier.

std::string	binary_data_array_
	Binary data array name.

std::string	binary_data_type_
	Binary data array type.

Protected Attributes inherited from SemanticValidator
const CVMappings &	mapping_
	Reference to the mappings.

const ControlledVocabulary &	cv_
	Reference to the CVs.

StringList	errors_
	Validation errors.

StringList	warnings_
	Validation warnings.

StringList	open_tags_
	List of open tags.

std::map< std::string, std::vector< CVMappingRule > >	rules_
	Rules (location => rule)

std::map< std::string, std::map< std::string, std::map< std::string, UInt > > >	fulfilled_

std::string	cv_tag_

std::string	accession_att_

std::string	name_att_

std::string	value_att_

std::string	unit_accession_att_

std::string	unit_name_att_

bool	check_term_value_types_

bool	check_units_

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.

Private Member Functions
	MzMLValidator ()
	Not implemented.

	MzMLValidator (const MzMLValidator &rhs)
	Not implemented.

MzMLValidator &	operator= (const MzMLValidator &rhs)
	Not implemented.

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

Semantic validator for mzML files.

Specialises SemanticValidator with mzML-specific rules in addition to the generic CV-mapping checks:

Terms placed inside a referenceableParamGroup are remembered and re-validated wherever the group is referenced via referenceableParamGroupRef.
For each binaryDataArray, the data-array CV term and the data-type CV term are cross-checked: the value type must be listed as a valid pairing for the data array (otherwise an error is reported).
The leading indexedmzML wrapper, if present, is stripped from the reported element path so validation messages refer to the mzML body.
GO and BTO terms are skipped because they use part_of relations which the is_a-based inheritance check cannot evaluate.

Unit checking is enabled.

Constructor & Destructor Documentation

◆ MzMLValidator() [1/3]

MzMLValidator	(	const CVMappings &	mapping,
		const ControlledVocabulary &	cv
	)

Constructor.

Parameters

[in]	mapping	The mapping rules
[in]	cv	All controlled vocabularies required for the mapping

◆ ~MzMLValidator()

~MzMLValidator ( )

override

Destructor.

◆ MzMLValidator() [2/3]

MzMLValidator ( )

private

Not implemented.

◆ MzMLValidator() [3/3]

MzMLValidator ( const MzMLValidator & rhs )

private

Not implemented.

Member Function Documentation

◆ getPath_()

std::string getPath_ ( UInt remove_from_end = 0 ) const

overrideprotectedvirtual

Returns the current element path.

Reimplemented from SemanticValidator.

◆ handleTerm_()

void handleTerm_	(	const std::string &	path,
		const CVTerm &	parsed_term
	)

overrideprotectedvirtual

Handling of the term.

Reimplemented from SemanticValidator.

◆ operator=()

MzMLValidator & operator= ( const MzMLValidator & rhs )

private

Not implemented.

◆ startElement()

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

overrideprotected

Member Data Documentation

◆ binary_data_array_

std::string binary_data_array_

protected

Binary data array name.

◆ binary_data_type_

std::string binary_data_type_

protected

Binary data array type.

◆ current_id_

std::string current_id_

protected

Current referenceableParamGroup identifier.

◆ param_groups_

std::map<std::string, std::vector<CVTerm> > param_groups_

protected

CV terms which can have a value (term => value type)

Public Member Functions

Protected Member Functions

Protected Attributes

Private Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ MzMLValidator() [1/3]

◆ ~MzMLValidator()

◆ MzMLValidator() [2/3]

◆ MzMLValidator() [3/3]

Member Function Documentation

◆ getPath_()

◆ handleTerm_()

◆ operator=()

◆ startElement()

Member Data Documentation

◆ binary_data_array_

◆ binary_data_type_

◆ current_id_

◆ param_groups_