stdex::html::parser< T, TR, AX > Class Template Reference

HTML parser. More...

Public Member Functions
	parser (const document< T, TR, AX > &document, _In_reads_or_z_opt_(num_chars) const stdex::schar_t *url=nullptr, size_t num_chars=0, bool parse_frames=false, stdex::progress< size_t > *progress=nullptr)
text_token< T, TR, AX > *	parse ()
	Parses HTML document.
token_list::const_iterator	end_tokens (std::basic_string< T, TR, AX > &source, token_list &active_tokens, const token_list &new_tokens)
	Pops ending tokens from the active token list and append their tags to the source code string.
void	append_inserted_tokens (std::basic_string< T, TR, AX > &source, inserted_token_list &inserted_tokens, size_t word_index, bool after_word, token_list &active_tokens)
	Adds matching inserted tokens before/after the given word in source code.
void	make_absolute_url (std::basic_string< T, TR, AX > &rel)
	Converts URL to absolute.
const token_vector &	tokens () const
	Returns collection of tokens.

Static Public Member Functions
static void	link (std::basic_string< T, TR, AX > &source, const text_token< T, TR, AX > *t)
	Rebuilds HTML source code from the token tree.
static void	start_tokens (std::basic_string< T, TR, AX > &source, token_list &active_tokens, const token_list &new_tokens, token_list::const_iterator from)
	Pushes tokens to the active token list and appends their tags to the source code string.
static void	merge (token_list &a, const token_list &b)
	Adds tokens from list b to list a creating an union.

Protected Member Functions
template<class T_token >
T_token *	append_token (std::unique_ptr< T_token > &&token)
	Adds token to the collection.
template<class T_token >
size_t	append_token (std::unique_ptr< T_token > &&token, std::basic_string< T, TR, AX > &source)
	Adds token to the collection and appends its tag to the source code string.
text_token< T, TR, AX > *	parse (const sequence_store::const_iterator &end, uint32_t text_type=0)
	Recursively parses HTML document.
text_token< T, TR, AX > *	parse_css (size_t start, size_t end)
	Parses CSS.

Protected Attributes
const document< T, TR, AX > &	m_document
	Document being analyzed.
const stdex::sstring	m_url
	Absolute document URL.
const bool	m_parse_frames
	Parse frames.
stdex::progress< size_t > *	m_progress
	Progress indicator.
const T *	m_source
	HTML source code.
token_vector	m_tokens
	HTML token storage.
sequence_store::const_iterator	m_offset
	Index of active section.
stdex::parser::basic_css_cdo< T >	m_css_cdo
stdex::parser::basic_css_cdc< T >	m_css_cdc
stdex::parser::basic_css_comment< T >	m_css_comment
stdex::parser::basic_css_string< T >	m_css_string
stdex::parser::basic_css_uri< T >	m_css_uri
stdex::parser::basic_css_import< T >	m_css_import
stdex::parser::basic_any_cu< T >	m_any_char

Detailed Description

template<class T, class TR, class AX>
class stdex::html::parser< T, TR, AX >

HTML parser.

Member Function Documentation

append_inserted_tokens()

template<class T , class TR , class AX >

void stdex::html::parser< T, TR, AX >::append_inserted_tokens ( std::basic_string< T, TR, AX > & source, inserted_token_list & inserted_tokens, size_t word_index, bool after_word, token_list & active_tokens )

inline

Adds matching inserted tokens before/after the given word in source code.

Parameters

[in,out]	source	Source code
[in,out]	inserted_tokens	List of tokens to insert. The tokens are removed from the list once inserted.
[in]	word_index	Word index
[in]	after_word	false if source code is before the word; true if after the word
[in,out]	active_tokens	Stack of active tokens

append_token() [1/2]

template<class T , class TR , class AX >

template<class T_token >

T_token * stdex::html::parser< T, TR, AX >::append_token ( std::unique_ptr< T_token > && token )

inlineprotected

Adds token to the collection.

Parameters

[in]

token

Token

Returns

Pointer to the token for non-owning references

append_token() [2/2]

template<class T , class TR , class AX >

template<class T_token >

size_t stdex::html::parser< T, TR, AX >::append_token ( std::unique_ptr< T_token > && token, std::basic_string< T, TR, AX > & source )

inlineprotected

Adds token to the collection and appends its tag to the source code string.

Parameters

[in]	token	Token
[in,out]	source	Source code

Returns

Number of code units appended to the source code

end_tokens()

template<class T , class TR , class AX >

token_list::const_iterator stdex::html::parser< T, TR, AX >::end_tokens ( std::basic_string< T, TR, AX > & source, token_list & active_tokens, const token_list & new_tokens )

inline

Pops ending tokens from the active token list and append their tags to the source code string.

Parameters

[in,out]	source	Source code
[in,out]	active_tokens	Stack of active tokens
[in]	new_tokens	Desired stack of active tokens

Returns

Position in new_tokens specifying where the cut was made

link()

template<class T , class TR , class AX >

static void stdex::html::parser< T, TR, AX >::link ( std::basic_string< T, TR, AX > & source, const text_token< T, TR, AX > * t )

inlinestatic

Rebuilds HTML source code from the token tree.

Parameters

[in,out]	source	String to append source code to
[in]	t	Document root token

merge()

template<class T , class TR , class AX >

static void stdex::html::parser< T, TR, AX >::merge ( token_list & a, const token_list & b )

inlinestatic

Adds tokens from list b to list a creating an union.

Parameters

[in,out]	a	Token list to merge b into
[in]	b	Token list to merge to a

parse()

template<class T , class TR , class AX >

text_token< T, TR, AX > * stdex::html::parser< T, TR, AX >::parse ( const sequence_store::const_iterator & end, uint32_t text_type = 0 )

inlineprotected

Recursively parses HTML document.

Parameters

[in]	end	Parse sequences on [m_offset, end) interval
[in]	text_type	Text flags of the sequences being parsed

Returns

Token representing sequences parsed

start_tokens()

template<class T , class TR , class AX >

static void stdex::html::parser< T, TR, AX >::start_tokens ( std::basic_string< T, TR, AX > & source, token_list & active_tokens, const token_list & new_tokens, token_list::const_iterator from )

inlinestatic

Pushes tokens to the active token list and appends their tags to the source code string.

Parameters

[in,out]	source	Source code
[in,out]	active_tokens	Stack of active tokens
[in]	new_tokens	New tokens to add
[in]	from	Token from new_tokens to start adding at

---

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

• include/stdex/html.hpp