#include <linguisticProcessing/core/AnalysisDumpers/GenericXmlDumper.h>

Inheritance diagram for Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper:

Public Member Functions
	GenericXmlDumper ()

virtual	~GenericXmlDumper ()

virtual void	init (Common::XMLConfigurationFiles::GroupConfigurationStructure &unitConfiguration, Manager *manager) override
	initialize with parameters from configuration file.

virtual LimaStatusCode	process (AnalysisContent &analysis) const override
	Process on data in analysisContent.

Public Member Functions inherited from Lima::LinguisticProcessing::AbstractTextualAnalysisDumper
	AbstractTextualAnalysisDumper ()

virtual	~AbstractTextualAnalysisDumper ()

std::shared_ptr< DumperStream >	initialize (AnalysisContent &analysis) const

Public Member Functions inherited from Lima::InitializableObject< Base, InitializationParameters >
	InitializableObject ()

	InitializableObject (const InitializableObject &object)

InitializableObject &	operator= (const InitializableObject &object)

virtual	~InitializableObject ()

const std::string &	getId () const
	get the object id

void	setId (const std::string &id)
	set the object id

Protected Member Functions
void	clearFeatures ()

void	initializeFeatures (const std::map< std::string, std::string > &features, const std::deque< std::string > &featureOrder=std::deque< std::string >())

void	xmlOutput (std::ostream &out, AnalysisContent &analysis, LinguisticAnalysisStructure::AnalysisGraph anagraph, LinguisticAnalysisStructure::AnalysisGraph posgraph, const Common::AnnotationGraphs::AnnotationData annotationData, const SyntacticAnalysis::SyntacticData syntacticData) const

void	xmlOutputVertices (std::ostream &out, AnalysisContent &analysis, LinguisticAnalysisStructure::AnalysisGraph anagraph, LinguisticAnalysisStructure::AnalysisGraph posgraph, const Common::AnnotationGraphs::AnnotationData annotationData, const SyntacticAnalysis::SyntacticData syntacticData, const LinguisticGraphVertex begin, const LinguisticGraphVertex end, const FsaStringsPool &sp, const uint64_t offset) const

void	xmlOutputVertex (std::ostream &out, AnalysisContent &analysis, LinguisticGraphVertex v, LinguisticAnalysisStructure::AnalysisGraph anagraph, LinguisticAnalysisStructure::AnalysisGraph posgraph, const Common::AnnotationGraphs::AnnotationData annotationData, const SyntacticAnalysis::SyntacticData syntacticData, const FsaStringsPool &sp, uint64_t offset, std::set< LinguisticGraphVertex > &visited, std::set< LinguisticGraphVertex > &alreadyStoredVertices) const

void	xmlOutputVertexInfos (std::ostream &out, Lima::AnalysisContent &analysis, LinguisticGraphVertex v, Lima::LinguisticProcessing::LinguisticAnalysisStructure::AnalysisGraph *graph, uint64_t offset) const

void	xmlOutputBoWInfos (std::ostream &out, Common::BagOfWords::AbstractBoWElement *token, uint64_t offset) const

std::pair< const SpecificEntities::SpecificEntityAnnotation , LinguisticAnalysisStructure::AnalysisGraph >	checkSpecificEntity (LinguisticGraphVertex v, LinguisticAnalysisStructure::AnalysisGraph anagraph, LinguisticAnalysisStructure::AnalysisGraph posgraph, const Common::AnnotationGraphs::AnnotationData *annotationData) const
	check if a vertex is a specific entity: returns the specific entity annotation if it is the case, along with the graph in which this entity has been found (can be analysis graph or pos graph).

bool	xmlOutputSpecificEntity (std::ostream &out, AnalysisContent &analysis, const SpecificEntities::SpecificEntityAnnotation se, LinguisticAnalysisStructure::AnalysisGraph anagraph, const FsaStringsPool &sp, uint64_t offset) const

std::string	specificEntityFeature (const SpecificEntities::SpecificEntityAnnotation *se, const std::string &featureName, const FsaStringsPool &sp, uint64_t offset) const

std::vector< boost::shared_ptr< Common::BagOfWords::BoWToken > >	checkCompound (LinguisticGraphVertex v, LinguisticAnalysisStructure::AnalysisGraph anagraph, LinguisticAnalysisStructure::AnalysisGraph posgraph, const Common::AnnotationGraphs::AnnotationData annotationData, const SyntacticAnalysis::SyntacticData syntacticData, uint64_t offset, std::set< LinguisticGraphVertex > &visited) const

void	xmlOutputCompound (std::ostream &out, AnalysisContent &analysis, boost::shared_ptr< Lima::Common::BagOfWords::AbstractBoWElement > token, Lima::LinguisticProcessing::LinguisticAnalysisStructure::AnalysisGraph anagraph, Lima::LinguisticProcessing::LinguisticAnalysisStructure::AnalysisGraph posgraph, const Lima::Common::AnnotationGraphs::AnnotationData *annotationData, const Lima::FsaStringsPool &sp, uint64_t offset) const

std::string	xmlString (const std::string &str) const

void	replace (std::string &str, const std::string &toReplace, const std::string &newValue) const

Protected Attributes
std::string	m_graph

WordFeatures	m_features
	use dedicated class for feature storage (easy initialization functions)

BoWFeatures	m_bowFeatures
	use dedicated class for feature storage (easy initialization functions)

std::deque< std::string >	m_featureNames
	use additional vector (aligned) to store feature names

std::vector< std::string >	m_featureTags
	use additional vector (aligned) to store associated XML tags

std::map< std::string, std::string >	m_defaultFeatures

bool	m_outputWords
	output simple words

bool	m_outputSentenceBoundaries
	output sentence boundaries (enclosing sentence tags)

bool	m_outputSpecificEntities
	output specific entities

bool	m_outputSpecificEntityParts
	output parts of specific entities

bool	m_outputCompounds
	output compounds

bool	m_outputCompoundParts
	output also compound parts

bool	m_outputAllCompounds
	output all partial compounds (created using BoWToken iterator)

std::string	m_wordTag

std::string	m_sentenceBoundaryTag

std::string	m_specificEntityTag

std::string	m_compoundTag

Compounds::BowGenerator *	m_bowGenerator

Protected Attributes inherited from Lima::LinguisticProcessing::AbstractTextualAnalysisDumper
MediaId	m_language

std::ostream *	m_out

std::string	m_handlerName

std::string	m_outputFile

std::string	m_outputSuffix

bool	m_stripInputSuffix

bool	m_append

QString	m_temporaryFileMetadata

Protected Attributes inherited from Lima::InitializableObject< Base, InitializationParameters >
std::string	m_id

Additional Inherited Members
Public Types inherited from Lima::InitializableObject< Base, InitializationParameters >
typedef InitializableObjectManager< Base, InitializationParameters >	Manager
	Manager is the type of the Manager associated to the initializableObject.

typedef InitializableObjectFactory< Base >	Factory
	Factory is the type of the Factory associated to the initializableObject.

Detailed Description

Author: Romaric Besancon

Definition at line 39 of file GenericXmlDumper.h.

Constructor & Destructor Documentation

◆ GenericXmlDumper()

Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::GenericXmlDumper ( )

Definition at line 55 of file GenericXmlDumper.cpp.

◆ ~GenericXmlDumper()

Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::~GenericXmlDumper ( )

virtual

Definition at line 85 of file GenericXmlDumper.cpp.

Member Function Documentation

◆ checkCompound()

std::vector< boost::shared_ptr< BoWToken > > Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::checkCompound	(	LinguisticGraphVertex	v,
		LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		LinguisticAnalysisStructure::AnalysisGraph *	posgraph,
		const Common::AnnotationGraphs::AnnotationData *	annotationData,
		const SyntacticAnalysis::SyntacticData *	syntacticData,
		uint64_t	offset,
		std::set< LinguisticGraphVertex > &	visited
	)		const

protected

Definition at line 676 of file GenericXmlDumper.cpp.

◆ checkSpecificEntity()

std::pair< const SpecificEntityAnnotation , AnalysisGraph > Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::checkSpecificEntity	(	LinguisticGraphVertex	v,
		LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		LinguisticAnalysisStructure::AnalysisGraph *	posgraph,
		const Common::AnnotationGraphs::AnnotationData *	annotationData
	)		const

protected

check if a vertex is a specific entity: returns the specific entity annotation if it is the case, along with the graph in which this entity has been found (can be analysis graph or pos graph).

Returns (0,0) if not a specific entity

Definition at line 570 of file GenericXmlDumper.cpp.

◆ clearFeatures()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::clearFeatures ( )

protected

Definition at line 94 of file GenericXmlDumper.cpp.

◆ init()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::init	(	Common::XMLConfigurationFiles::GroupConfigurationStructure &	unitConfiguration,
		Manager *	manager
	)

overridevirtual

initialize with parameters from configuration file.

Parameters

unitConfiguration	@IN : <group> tag in xml configuration file that contains parameters to initialize the object.
manager	@IN : manager that asked for initialization and carries init params Use it to initialize other objects of same kind.

Exceptions

InvalidConfiguration when parameters are invalids.

Reimplemented from Lima::LinguisticProcessing::AbstractTextualAnalysisDumper.

Definition at line 105 of file GenericXmlDumper.cpp.

◆ initializeFeatures()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::initializeFeatures	(	const std::map< std::string, std::string > &	features,
		const std::deque< std::string > &	featureOrder = `std::deque<std::string>()`
	)

protected

Definition at line 235 of file GenericXmlDumper.cpp.

◆ process()

LimaStatusCode Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::process ( AnalysisContent & analysis ) const

overridevirtual

Process on data in analysisContent.

This method should not return any exception

Parameters

analysis AnalysisContent object on which to process

Exceptions

UndefinedMethod if this method hasn't been specialized

Implements Lima::LinguisticProcessing::AbstractTextualAnalysisDumper.

Definition at line 282 of file GenericXmlDumper.cpp.

◆ replace()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::replace	(	std::string &	str,
		const std::string &	toReplace,
		const std::string &	newValue
	)		const

protected

Definition at line 916 of file GenericXmlDumper.cpp.

◆ specificEntityFeature()

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::specificEntityFeature	(	const SpecificEntities::SpecificEntityAnnotation *	se,
		const std::string &	featureName,
		const FsaStringsPool &	sp,
		uint64_t	offset
	)		const

protected

Definition at line 865 of file GenericXmlDumper.cpp.

◆ xmlOutput()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutput	(	std::ostream &	out,
		AnalysisContent &	analysis,
		LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		LinguisticAnalysisStructure::AnalysisGraph *	posgraph,
		const Common::AnnotationGraphs::AnnotationData *	annotationData,
		const SyntacticAnalysis::SyntacticData *	syntacticData
	)		const

protected

Definition at line 332 of file GenericXmlDumper.cpp.

◆ xmlOutputBoWInfos()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutputBoWInfos	(	std::ostream &	out,
		Common::BagOfWords::AbstractBoWElement *	token,
		uint64_t	offset
	)		const

protected

Definition at line 846 of file GenericXmlDumper.cpp.

◆ xmlOutputCompound()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutputCompound	(	std::ostream &	out,
		AnalysisContent &	analysis,
		boost::shared_ptr< Lima::Common::BagOfWords::AbstractBoWElement >	token,
		Lima::LinguisticProcessing::LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		Lima::LinguisticProcessing::LinguisticAnalysisStructure::AnalysisGraph *	posgraph,
		const Lima::Common::AnnotationGraphs::AnnotationData *	annotationData,
		const Lima::FsaStringsPool &	sp,
		uint64_t	offset
	)		const

protected

Definition at line 725 of file GenericXmlDumper.cpp.

◆ xmlOutputSpecificEntity()

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutputSpecificEntity	(	std::ostream &	out,
		AnalysisContent &	analysis,
		const SpecificEntities::SpecificEntityAnnotation *	se,
		LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		const FsaStringsPool &	sp,
		uint64_t	offset
	)		const

protected

Definition at line 614 of file GenericXmlDumper.cpp.

◆ xmlOutputVertex()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutputVertex	(	std::ostream &	out,
		AnalysisContent &	analysis,
		LinguisticGraphVertex	v,
		LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		LinguisticAnalysisStructure::AnalysisGraph *	posgraph,
		const Common::AnnotationGraphs::AnnotationData *	annotationData,
		const SyntacticAnalysis::SyntacticData *	syntacticData,
		const FsaStringsPool &	sp,
		uint64_t	offset,
		std::set< LinguisticGraphVertex > &	visited,
		std::set< LinguisticGraphVertex > &	alreadyStoredVertices
	)		const

protected

Definition at line 517 of file GenericXmlDumper.cpp.

◆ xmlOutputVertexInfos()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutputVertexInfos	(	std::ostream &	out,
		Lima::AnalysisContent &	analysis,
		LinguisticGraphVertex	v,
		Lima::LinguisticProcessing::LinguisticAnalysisStructure::AnalysisGraph *	graph,
		uint64_t	offset
	)		const

protected

Definition at line 821 of file GenericXmlDumper.cpp.

◆ xmlOutputVertices()

void Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlOutputVertices	(	std::ostream &	out,
		AnalysisContent &	analysis,
		LinguisticAnalysisStructure::AnalysisGraph *	anagraph,
		LinguisticAnalysisStructure::AnalysisGraph *	posgraph,
		const Common::AnnotationGraphs::AnnotationData *	annotationData,
		const SyntacticAnalysis::SyntacticData *	syntacticData,
		const LinguisticGraphVertex	begin,
		const LinguisticGraphVertex	end,
		const FsaStringsPool &	sp,
		const uint64_t	offset
	)		const

protected

Definition at line 414 of file GenericXmlDumper.cpp.

◆ xmlString()

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::xmlString ( const std::string & str ) const

protected

Definition at line 904 of file GenericXmlDumper.cpp.

Member Data Documentation

◆ m_bowFeatures

BoWFeatures Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_bowFeatures

protected

use dedicated class for feature storage (easy initialization functions)

Definition at line 55 of file GenericXmlDumper.h.

◆ m_bowGenerator

Compounds::BowGenerator* Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_bowGenerator

protected

Definition at line 70 of file GenericXmlDumper.h.

◆ m_compoundTag

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_compoundTag

protected

Definition at line 69 of file GenericXmlDumper.h.

◆ m_defaultFeatures

std::map<std::string,std::string> Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_defaultFeatures

protected

Definition at line 58 of file GenericXmlDumper.h.

◆ m_featureNames

std::deque<std::string> Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_featureNames

protected

use additional vector (aligned) to store feature names

Definition at line 56 of file GenericXmlDumper.h.

◆ m_features

WordFeatures Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_features

protected

use dedicated class for feature storage (easy initialization functions)

Definition at line 54 of file GenericXmlDumper.h.

◆ m_featureTags

std::vector<std::string> Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_featureTags

protected

use additional vector (aligned) to store associated XML tags

Definition at line 57 of file GenericXmlDumper.h.

◆ m_graph

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_graph

protected

Definition at line 53 of file GenericXmlDumper.h.

◆ m_outputAllCompounds

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputAllCompounds

protected

output all partial compounds (created using BoWToken iterator)

Definition at line 65 of file GenericXmlDumper.h.

◆ m_outputCompoundParts

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputCompoundParts

protected

output also compound parts

Definition at line 64 of file GenericXmlDumper.h.

◆ m_outputCompounds

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputCompounds

protected

output compounds

Definition at line 63 of file GenericXmlDumper.h.

◆ m_outputSentenceBoundaries

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputSentenceBoundaries

protected

output sentence boundaries (enclosing sentence tags)

Definition at line 60 of file GenericXmlDumper.h.

◆ m_outputSpecificEntities

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputSpecificEntities

protected

output specific entities

Definition at line 61 of file GenericXmlDumper.h.

◆ m_outputSpecificEntityParts

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputSpecificEntityParts

protected

output parts of specific entities

Definition at line 62 of file GenericXmlDumper.h.

◆ m_outputWords

bool Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_outputWords

protected

output simple words

Definition at line 59 of file GenericXmlDumper.h.

◆ m_sentenceBoundaryTag

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_sentenceBoundaryTag

protected

Definition at line 67 of file GenericXmlDumper.h.

◆ m_specificEntityTag

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_specificEntityTag

protected

Definition at line 68 of file GenericXmlDumper.h.

◆ m_wordTag

std::string Lima::LinguisticProcessing::AnalysisDumpers::GenericXmlDumper::m_wordTag

protected

Definition at line 66 of file GenericXmlDumper.h.

The documentation for this class was generated from the following files:

lima_linguisticprocessing/src/linguisticProcessing/core/AnalysisDumpers/GenericXmlDumper.h
lima_linguisticprocessing/src/linguisticProcessing/core/AnalysisDumpers/GenericXmlDumper.cpp

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ GenericXmlDumper()

◆ ~GenericXmlDumper()

Member Function Documentation

◆ checkCompound()

◆ checkSpecificEntity()

◆ clearFeatures()

◆ init()

◆ initializeFeatures()

◆ process()

◆ replace()

◆ specificEntityFeature()

◆ xmlOutput()

◆ xmlOutputBoWInfos()

◆ xmlOutputCompound()

◆ xmlOutputSpecificEntity()

◆ xmlOutputVertex()

◆ xmlOutputVertexInfos()

◆ xmlOutputVertices()

◆ xmlString()

Member Data Documentation

◆ m_bowFeatures

◆ m_bowGenerator

◆ m_compoundTag

◆ m_defaultFeatures

◆ m_featureNames

◆ m_features

◆ m_featureTags

◆ m_graph

◆ m_outputAllCompounds

◆ m_outputCompoundParts

◆ m_outputCompounds

◆ m_outputSentenceBoundaries

◆ m_outputSpecificEntities

◆ m_outputSpecificEntityParts

◆ m_outputWords

◆ m_sentenceBoundaryTag

◆ m_specificEntityTag

◆ m_wordTag