SAX handler for UniProtKB XML <entry> documents. More...

#include <OpenMS/FORMAT/HANDLERS/UniProtXMLHandler.h>

Inheritance diagram for UniProtXMLHandler:

Collaboration diagram for UniProtXMLHandler:

Public Types
enum class	CaptureTarget { None , Accession , EntryName , FullName , PrimaryGene , TaxName , Sequence , FeatureOriginal , FeatureVariation }

using	EntryCallback = std::function< void(UniProtEntry &&)>

Public 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 }

Public Member Functions
	UniProtXMLHandler (const std::string &filename, EntryCallback callback)
	Build a handler that delivers each parsed UniProtEntry to `callback`.

	~UniProtXMLHandler () override
	Destructor.

void	startElement (const XMLCh const uri, const XMLCh const local_name, const XMLCh *const qname, const xercesc::Attributes &attrs) override

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

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

Public Member Functions inherited from XMLHandler
	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

Private Member Functions
void	resetEntry_ ()
	Clear all per-entry state so the next <entry> starts fresh.

void	resetFeature_ ()
	Clear all per-feature state so the next <feature> starts fresh.

Static Private Member Functions
static int	parsePosition_ (const std::string &attr)

Private Attributes
EntryCallback	callback_

UniProtEntry	current_entry_

int	depth_ {0}
	Depth of the most recent element start, used to scope subtree handling.

int	entry_depth_ {0}
	<entry>

int	recommended_name_depth_ {0}
	<protein>/<recommendedName>

int	gene_depth_ {0}
	<gene>

int	organism_depth_ {0}
	<organism>

int	alt_products_depth_ {0}
	<comment type="alternative products"> (whole subtree skipped)

int	feature_depth_ {0}
	<feature>

int	sequence_depth_ {0}
	<sequence length="..."> (only the canonical sequence; isoform <sequence> ignored)

bool	full_name_captured_ {false}

std::string	char_buf_
	Buffer for character data; appended-to in characters(), consumed in endElement().

CaptureTarget	capture_ {CaptureTarget::None}
	Destination for the next buffered run of character data (None == not capturing).

UniProtFeature	current_feature_
	Per-feature working state (used between startElement("feature") and endElement("feature")).

bool	gene_name_is_primary_ {false}
	Whether the next <name> encountered inside the current <gene> subtree is a primary name.

bool	organism_name_is_scientific_ {false}
	Whether the next <name> encountered inside the current <organism> subtree is the scientific name.

Additional Inherited Members
Static Public 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.

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.

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)

Detailed Description

SAX handler for UniProtKB XML <entry> documents.

Streams individual <entry> elements into UniProtEntry POD instances and delivers each via a callback at </entry>. Implements the same scoping rules as the upstream C# UniPEFF tool: isoform sequences (missing the "length" attribute on <sequence>) and the <comment type="alternative products"> subtree are skipped, <gene> and <organism> are scanned via bounded depth tracking so their inner <name> elements never leak into the top-level "entry mnemonic" capture, and <feature> contents are buffered and classified at the closing tag rather than incrementally.

Member Typedef Documentation

◆ EntryCallback

using EntryCallback = std::function<void(UniProtEntry&&)>

Callback invoked once per </entry>: receives ownership of the populated UniProtEntry. The handler resets its working state immediately after, so the callback is the only place the entry is reachable.

Member Enumeration Documentation

◆ CaptureTarget

enum class CaptureTarget

strong

Where the next character-data run, if buffered, should be deposited at the closing tag of its enclosing element.

Enumerator
None
Accession
EntryName
FullName
PrimaryGene
TaxName
Sequence
FeatureOriginal
FeatureVariation

Constructor & Destructor Documentation

◆ UniProtXMLHandler()

UniProtXMLHandler	(	const std::string &	filename,
		EntryCallback	callback
	)

Build a handler that delivers each parsed UniProtEntry to callback.

◆ ~UniProtXMLHandler()

~UniProtXMLHandler ( )

override

Destructor.

Member Function Documentation

◆ characters()

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

override

◆ endElement()

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

override

◆ parsePosition_()

static int parsePosition_ ( const std::string & attr )

staticprivate

Parse a UniProt position attribute string; returns 0 when the attribute is absent or non-numeric (UniProt encodes "unknown" by omitting the attribute).

◆ resetEntry_()

void resetEntry_ ( )

private

Clear all per-entry state so the next <entry> starts fresh.

◆ resetFeature_()

void resetFeature_ ( )

private

Clear all per-feature state so the next <feature> starts fresh.

◆ startElement()

void startElement	(	const XMLCh *const	uri,
		const XMLCh *const	local_name,
		const XMLCh *const	qname,
		const xercesc::Attributes &	attrs
	)

override

Member Data Documentation

◆ alt_products_depth_

int alt_products_depth_ {0}

private

<comment type="alternative products"> (whole subtree skipped)

◆ callback_

EntryCallback callback_

private

◆ capture_

CaptureTarget capture_ {CaptureTarget::None}

private

Destination for the next buffered run of character data (None == not capturing).

◆ char_buf_

std::string char_buf_

private

Buffer for character data; appended-to in characters(), consumed in endElement().

◆ current_entry_

UniProtEntry current_entry_

private

◆ current_feature_

UniProtFeature current_feature_

private

Per-feature working state (used between startElement("feature") and endElement("feature")).

◆ depth_

int depth_ {0}

private

Depth of the most recent element start, used to scope subtree handling.

◆ entry_depth_

int entry_depth_ {0}

private

<entry>

Subtree gates. Each holds the depth at which the corresponding element opened so we know when its closing tag fires (depth_ == gate value during endElement). 0 means "not currently inside this subtree".

◆ feature_depth_

int feature_depth_ {0}

private

◆ full_name_captured_

bool full_name_captured_ {false}

private

Captures the <fullName> the first time we encounter it inside <protein>/<recommendedName>; later <fullName> elements (e.g. alternative names) are skipped.

◆ gene_depth_

int gene_depth_ {0}

private

<gene>

◆ gene_name_is_primary_

bool gene_name_is_primary_ {false}

private

Whether the next <name> encountered inside the current <gene> subtree is a primary name.

◆ organism_depth_

int organism_depth_ {0}

private

◆ organism_name_is_scientific_

bool organism_name_is_scientific_ {false}

private

Whether the next <name> encountered inside the current <organism> subtree is the scientific name.

◆ recommended_name_depth_

int recommended_name_depth_ {0}

private

◆ sequence_depth_

int sequence_depth_ {0}

private

<sequence length="..."> (only the canonical sequence; isoform <sequence> ignored)

Public Types

Public Member Functions

Private Member Functions

Static Private Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ EntryCallback

Member Enumeration Documentation

◆ CaptureTarget

Constructor & Destructor Documentation

◆ UniProtXMLHandler()

◆ ~UniProtXMLHandler()

Member Function Documentation

◆ characters()

◆ endElement()

◆ parsePosition_()

◆ resetEntry_()

◆ resetFeature_()

◆ startElement()

Member Data Documentation

◆ alt_products_depth_

◆ callback_

◆ capture_

◆ char_buf_

◆ current_entry_

◆ current_feature_

◆ depth_

◆ entry_depth_

◆ feature_depth_

◆ full_name_captured_

◆ gene_depth_

◆ gene_name_is_primary_

◆ organism_depth_

◆ organism_name_is_scientific_

◆ recommended_name_depth_

◆ sequence_depth_