Base class for XML-based document parsers (ODF, OOXML, etc.). More...

#include <common_xml_document_parser.h>

Inheritance diagram for docwire::common_xml_document_parser< safety_level >:

Classes
struct	comment
	Represents a comment with author, time, and text. More...

struct	relationship
	Represents a relationship, typically for hyperlinks or embedded objects. More...

class	scoped_context_stack_push
	Helper class to manage the context stack scope. Pushes a new context on construction and pops it on destruction. More...

struct	shared_string
	Represents a shared string, a common optimization in OOXML formats. More...

Public Types
enum	ODFOOXMLListStyle { number , bullet }
	Enum for list styles (e.g., numbered or bulleted).

typedef std::vector< ODFOOXMLListStyle >	ListStyleVector
	Type alias for a vector of list styles.

using	ListStyleMap = std::map< std::string, common_xml_document_parser< safety_level >::ListStyleVector >
	Type alias for a map of list style names to their definitions.

using	CommentMap = std::map< int, common_xml_document_parser< safety_level >::comment >
	Type alias for a map of comment IDs to Comment objects.

using	RelationshipMap = std::map< std::string, common_xml_document_parser< safety_level >::relationship >
	Type alias for a map of relationship IDs to Relationship objects.

using	SharedStringVector = std::vector< shared_string >
	Type alias for a vector of shared strings.

typedef std::function< void(xml::node_ref< safety_level > &xml_node, XmlParseMode mode, zip_reader *zipfile, std::string &text, bool &children_processed, std::string &level_suffix, bool first_on_level)>	CommandHandler
	Defines the function signature for an XML tag command handler.

Public Member Functions
void	registerODFOOXMLCommandHandler (const std::string &xml_tag, const CommandHandler &handler)
	Registers a handler for a specific XML tag. More...

std::string	parseXmlData (xml::children_view< safety_level > xml_nodes, XmlParseMode mode, zip_reader *zipfile)
	Parses XML data from a view of nodes. More...

std::string	parseXmlChildren (xml::node_ref< safety_level > &xml_node, XmlParseMode mode, zip_reader *zipfile)
	Parses the children of a given XML node. More...

void	extractText (std::string_view xml_contents, XmlParseMode mode, zip_reader *zipfile, std::string &text)
	Extracts text from raw XML content. More...

void	parseODFMetadata (std::string_view xml_content, attributes::metadata &metadata) const
	Parses ODF metadata from XML content. More...

const std::string	formatComment (const std::string &author, const std::string &time, const std::string &text)
	Formats a comment for output. More...

size_t &	getListDepth ()
	Returns the current nesting depth of lists.

ListStyleMap &	getListStyles ()
	Gets the map of list styles.

CommentMap &	getComments ()
	Gets the map of comments.

RelationshipMap &	getRelationships ()
	Gets the map of relationships.

SharedStringVector &	getSharedStrings ()
	Gets the vector of shared strings.

bool	disabledText () const
	Checks if text extraction is currently disabled.

xml::reader_blanks	blanks () const
	Gets the current blank node handling policy.

void	disableText (bool disable)
	Enables or disables text extraction.

void	set_blanks (xml::reader_blanks blanks)
	Sets the blank node handling policy for the XML reader.

void	activeEmittingSignals (bool flag)
	Controls whether signal emission (callbacks) is active.

	common_xml_document_parser ()
	Default constructor.

Public Member Functions inherited from docwire::chain_element
	chain_element (chain_element &&)=default

chain_element &	operator= (chain_element &&)=default

virtual continuation	operator() (message_ptr msg, const message_callbacks &emit_message)=0

virtual bool	is_leaf () const =0
	Check if chain element is a leaf (last element which doesn't produce any messages). At this moment only exporters are leafs. More...

virtual bool	is_generator () const

Additional Inherited Members
Protected Types inherited from docwire::with_pimpl< chain_element >
using	impl_type = pimpl_impl< chain_element >

Protected Types inherited from docwire::with_pimpl< common_xml_document_parser< default_safety_level > >
using	impl_type = pimpl_impl< common_xml_document_parser< default_safety_level > >

Protected Member Functions inherited from docwire::with_pimpl< chain_element >
impl_type *	create_impl (Args &&... args)

	with_pimpl (Args &&... args)

	with_pimpl (with_pimpl< chain_element > &&other) noexcept

	with_pimpl (std::nullptr_t)

with_pimpl &	operator= (with_pimpl &&other) noexcept

impl_type &	impl ()

const impl_type &	impl () const

Protected Member Functions inherited from docwire::with_pimpl< common_xml_document_parser< default_safety_level > >
impl_type *	create_impl (Args &&... args)

	with_pimpl (Args &&... args)

	with_pimpl (with_pimpl< common_xml_document_parser< default_safety_level > > &&other) noexcept

	with_pimpl (std::nullptr_t)

with_pimpl &	operator= (with_pimpl &&other) noexcept

impl_type &	impl ()

const impl_type &	impl () const

Detailed Description

template<safety_policy safety_level = default_safety_level>
class docwire::common_xml_document_parser< safety_level >

Base class for XML-based document parsers (ODF, OOXML, etc.).

This class is inherited by specific parsers (e.g., odf_ooxml_parser, odfxml_parser). It allows registering handlers for specific XML tags.

Template Parameters

safety_level The safety policy used for XML parsing operations.

See also: xml::reader; XML parsing example

Definition at line 41 of file common_xml_document_parser.h.

Member Function Documentation

◆ extractText()

template<safety_policy safety_level = default_safety_level>

void docwire::common_xml_document_parser< safety_level >::extractText	(	std::string_view	xml_contents,
		XmlParseMode	mode,
		zip_reader *	zipfile,
		std::string &	text
	)

Extracts text from raw XML content.

This is a high-level function that initializes the XML reader and calls parseXmlData.

Parameters

xml_contents	The raw XML string.
mode	The parsing mode.
zipfile	Pointer to the zip_reader if applicable.
text	Output parameter where the extracted text will be appended.

◆ formatComment()

template<safety_policy safety_level = default_safety_level>

const std::string docwire::common_xml_document_parser< safety_level >::formatComment	(	const std::string &	author,
		const std::string &	time,
		const std::string &	text
	)

Formats a comment for output.

Parameters

author	The author of the comment.
time	The timestamp of the comment.
text	The content of the comment.

Returns: The formatted comment string.

◆ parseODFMetadata()

template<safety_policy safety_level = default_safety_level>

void docwire::common_xml_document_parser< safety_level >::parseODFMetadata	(	std::string_view	xml_content,
		attributes::metadata &	metadata
	)		const

Parses ODF metadata from XML content.

Parameters

xml_content	The raw XML content of the metadata file.
metadata	The structure to populate with parsed metadata.

◆ parseXmlChildren()

template<safety_policy safety_level = default_safety_level>

std::string docwire::common_xml_document_parser< safety_level >::parseXmlChildren	(	xml::node_ref< safety_level > &	xml_node,
		XmlParseMode	mode,
		zip_reader *	zipfile
	)

Parses the children of a given XML node.

Parameters

xml_node	The parent node whose children will be parsed.
mode	The parsing mode.
zipfile	Pointer to the zip_reader if applicable.

Returns: The extracted text content from the children.

◆ parseXmlData()

template<safety_policy safety_level = default_safety_level>

std::string docwire::common_xml_document_parser< safety_level >::parseXmlData	(	xml::children_view< safety_level >	xml_nodes,
		XmlParseMode	mode,
		zip_reader *	zipfile
	)

Parses XML data from a view of nodes.

Iterates through the provided XML nodes and executes registered command handlers.

Parameters

xml_nodes	The view of XML nodes to parse.
mode	The parsing mode (e.g., PARSE_XML, STRIP_XML).
zipfile	Pointer to the zip_reader if the XML is part of a zipped archive (e.g., DOCX, ODT).

Returns: The extracted text content.

◆ registerODFOOXMLCommandHandler()

template<safety_policy safety_level = default_safety_level>

void docwire::common_xml_document_parser< safety_level >::registerODFOOXMLCommandHandler	(	const std::string &	xml_tag,
		const CommandHandler &	handler
	)

Registers a handler for a specific XML tag.

Derived classes can use this to add or override behavior for specific XML tags.

Parameters

xml_tag	The XML tag name to handle.
handler	The function to execute when the tag is encountered.

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

common_xml_document_parser.h

Classes

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

template<safety_policy safety_level = default_safety_level> class docwire::common_xml_document_parser< safety_level >

Member Function Documentation

◆ extractText()

◆ formatComment()

◆ parseODFMetadata()

◆ parseXmlChildren()

◆ parseXmlData()

◆ registerODFOOXMLCommandHandler()

template<safety_policy safety_level = default_safety_level>
class docwire::common_xml_document_parser< safety_level >