Macro htmlDefaultSubelement

#define htmlDefaultSubelement(elt);

Returns the default subelement for this element

Macro htmlElementAllowedHereDesc

#define htmlElementAllowedHereDesc(parent, elt);

Checks whether an HTML element description may be a direct child of the specified element. Returns 1 if allowed; 0 otherwise.

Macro htmlRequiredAttrs

#define htmlRequiredAttrs(elt);

Returns the attributes required for the specified element.

Typedef htmlDocPtr

xmlDocPtr htmlDocPtr;

Structure htmlElemDesc

struct _htmlElemDesc {
    const char *	name	: The tag name
    char	startTag	: Whether the start tag can be implied
    char	endTag	: Whether the end tag can be implied
    char	saveEndTag	: Whether the end tag should be saved
    char	empty	: Is this an empty element ?
    char	depr	: Is this a deprecated element ?
    char	dtd	: 1: only in Loose DTD, 2: only Frameset one
    char	isinline	: is this a block 0 or inline 1 element
    const char *	desc	: the description NRK Jan.2003 * New fields encapsulating HTML structur
    const char **	subelts	: allowed sub-elements of this element
    const char *	defaultsubelt	: subelement for suggested auto-repair if necessary or NULL
    const char **	attrs_opt	: Optional Attributes
    const char **	attrs_depr	: Additional deprecated attributes
    const char **	attrs_req	: Required attributes
} htmlElemDesc;

Typedef htmlElemDescPtr

htmlElemDesc * htmlElemDescPtr;

Structure htmlEntityDesc

struct _htmlEntityDesc {
    unsigned int	value	: the UNICODE value for the character
    const char *	name	: The entity name
    const char *	desc	: the description
} htmlEntityDesc;

Typedef htmlEntityDescPtr

htmlEntityDesc * htmlEntityDescPtr;

Typedef htmlNodePtr

xmlNodePtr htmlNodePtr;

Typedef htmlParserCtxt

xmlParserCtxt htmlParserCtxt;

Typedef htmlParserCtxtPtr

xmlParserCtxtPtr htmlParserCtxtPtr;

Typedef htmlParserInput

xmlParserInput htmlParserInput;

Typedef htmlParserInputPtr

xmlParserInputPtr htmlParserInputPtr;

Typedef htmlParserNodeInfo

xmlParserNodeInfo htmlParserNodeInfo;

Enum htmlParserOption

enum htmlParserOption {
    HTML_PARSE_RECOVER = 1 /* Relaxed parsing */
    HTML_PARSE_NODEFDTD = 4 /* do not default a doctype if not found */
    HTML_PARSE_NOERROR = 32 /* suppress error reports */
    HTML_PARSE_NOWARNING = 64 /* suppress warning reports */
    HTML_PARSE_PEDANTIC = 128 /* pedantic error reporting */
    HTML_PARSE_NOBLANKS = 256 /* remove blank nodes */
    HTML_PARSE_NONET = 2048 /* Forbid network access */
    HTML_PARSE_NOIMPLIED = 8192 /* Do not add implied html/body... elements */
    HTML_PARSE_COMPACT = 65536 /* compact small text nodes */
    HTML_PARSE_IGNORE_ENC = 2097152 /*  ignore internal document encoding hint */
};

Typedef htmlSAXHandler

xmlSAXHandler htmlSAXHandler;

Typedef htmlSAXHandlerPtr

xmlSAXHandlerPtr htmlSAXHandlerPtr;

Enum htmlStatus

enum htmlStatus {
    HTML_NA = 0 /* something we don't check at all */
    HTML_INVALID = 1
    HTML_DEPRECATED = 2
    HTML_VALID = 4
    HTML_REQUIRED = 12 /*  VALID bit set so ( & HTML_VALID ) is TRUE */
};

Variable htmlDefaultSAXHandler

const xmlSAXHandlerV1 htmlDefaultSAXHandler;

DEPRECATED: This handler is unused and will be removed from future versions. Default old SAX v1 handler for HTML, builds the DOM tree

UTF8ToHtml ()

int	UTF8ToHtml			(unsigned char * out, 
					 int * outlen, 
					 const unsigned char * in, 
					 int * inlen)

Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.

htmlAttrAllowed ()

htmlStatus	htmlAttrAllowed		(const htmlElemDesc * elt, 
					 const xmlChar * attr, 
					 int legacy)

Checks whether an attribute is valid for an element Has full knowledge of Required and Deprecated attributes

htmlAutoCloseTag ()

int	htmlAutoCloseTag		(htmlDocPtr doc, 
					 const xmlChar * name, 
					 htmlNodePtr elem)

The HTML DTD allows a tag to implicitly close other tags. The list is kept in htmlStartClose array. This function checks if the element or one of it's children would autoclose the given tag.

htmlCreateFileParserCtxt ()

htmlParserCtxtPtr	htmlCreateFileParserCtxt	(const char * filename, 
							 const char * encoding)

DEPRECATED: Use htmlNewParserCtxt and htmlCtxtReadFile. Create a parser context to read from a file. A non-NULL encoding overrides encoding declarations in the document. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time.

htmlCreateMemoryParserCtxt ()

htmlParserCtxtPtr	htmlCreateMemoryParserCtxt	(const char * buffer, 
							 int size)

DEPRECATED: Use htmlNewParserCtxt and htmlCtxtReadMemory. Create a parser context for an HTML in-memory document. The input buffer must not contain any terminating null bytes.

htmlCreatePushParserCtxt ()

htmlParserCtxtPtr	htmlCreatePushParserCtxt	(htmlSAXHandlerPtr sax, 
							 void * user_data, 
							 const char * chunk, 
							 int size, 
							 const char * filename, 
							 xmlCharEncoding enc)

Create a parser context for using the HTML parser in push mode.

htmlCtxtParseDocument ()

htmlDocPtr	htmlCtxtParseDocument	(htmlParserCtxtPtr ctxt, 
					 xmlParserInputPtr input)

Parse an HTML document and return the resulting document tree. Available since 2.13.0.

htmlCtxtReadDoc ()

htmlDocPtr	htmlCtxtReadDoc		(htmlParserCtxtPtr ctxt, 
					 const xmlChar * str, 
					 const char * URL, 
					 const char * encoding, 
					 int options)

Parse an HTML in-memory document and build a tree. See htmlCtxtUseOptions for details.

htmlCtxtReadFd ()

htmlDocPtr	htmlCtxtReadFd		(htmlParserCtxtPtr ctxt, 
					 int fd, 
					 const char * URL, 
					 const char * encoding, 
					 int options)

Parse an HTML from a file descriptor and build a tree. See htmlCtxtUseOptions for details. NOTE that the file descriptor will not be closed when the context is freed or reset.

htmlCtxtReadFile ()

htmlDocPtr	htmlCtxtReadFile	(htmlParserCtxtPtr ctxt, 
					 const char * filename, 
					 const char * encoding, 
					 int options)

Parse an HTML file from the filesystem, the network or a user-defined resource loader. See xmlNewInputURL and htmlCtxtUseOptions for details.

htmlCtxtReadIO ()

htmlDocPtr	htmlCtxtReadIO		(htmlParserCtxtPtr ctxt, 
					 xmlInputReadCallback ioread, 
					 xmlInputCloseCallback ioclose, 
					 void * ioctx, 
					 const char * URL, 
					 const char * encoding, 
					 int options)

Parse an HTML document from I/O functions and source and build a tree. See xmlNewInputIO and htmlCtxtUseOptions for details.

htmlCtxtReadMemory ()

htmlDocPtr	htmlCtxtReadMemory	(htmlParserCtxtPtr ctxt, 
					 const char * buffer, 
					 int size, 
					 const char * URL, 
					 const char * encoding, 
					 int options)

Parse an HTML in-memory document and build a tree. The input buffer must not contain any terminating null bytes. See htmlCtxtUseOptions for details.

htmlCtxtReset ()

void	htmlCtxtReset			(htmlParserCtxtPtr ctxt)

Reset a parser context

htmlCtxtUseOptions ()

int	htmlCtxtUseOptions		(htmlParserCtxtPtr ctxt, 
					 int options)

Applies the options to the parser context

htmlElementAllowedHere ()

int	htmlElementAllowedHere		(const htmlElemDesc * parent, 
					 const xmlChar * elt)

Checks whether an HTML element may be a direct child of a parent element. Note - doesn't check for deprecated elements

htmlElementStatusHere ()

htmlStatus	htmlElementStatusHere	(const htmlElemDesc * parent, 
					 const htmlElemDesc * elt)

Checks whether an HTML element may be a direct child of a parent element. and if so whether it is valid or deprecated.

htmlEncodeEntities ()

int	htmlEncodeEntities		(unsigned char * out, 
					 int * outlen, 
					 const unsigned char * in, 
					 int * inlen, 
					 int quoteChar)

Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.

htmlEntityLookup ()

const htmlEntityDesc *	htmlEntityLookup	(const xmlChar * name)

Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.

htmlEntityValueLookup ()

const htmlEntityDesc *	htmlEntityValueLookup	(unsigned int value)

Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.

htmlFreeParserCtxt ()

void	htmlFreeParserCtxt		(htmlParserCtxtPtr ctxt)

Free all the memory used by a parser context. However the parsed document in ctxt->myDoc is not freed.

htmlHandleOmittedElem ()

int	htmlHandleOmittedElem		(int val)

DEPRECATED: Use HTML_PARSE_NOIMPLIED Set and return the previous value for handling HTML omitted tags.

htmlInitAutoClose ()

void	htmlInitAutoClose		(void)

DEPRECATED: This is a no-op.

htmlIsAutoClosed ()

int	htmlIsAutoClosed		(htmlDocPtr doc, 
					 htmlNodePtr elem)

The HTML DTD allows a tag to implicitly close other tags. The list is kept in htmlStartClose array. This function checks if a tag is autoclosed by one of it's child

htmlIsScriptAttribute ()

int	htmlIsScriptAttribute		(const xmlChar * name)

Check if an attribute is of content type Script

htmlNewParserCtxt ()

htmlParserCtxtPtr	htmlNewParserCtxt	(void)

Allocate and initialize a new HTML parser context. This can be used to parse HTML documents into DOM trees with functions like xmlCtxtReadFile or xmlCtxtReadMemory. See htmlCtxtUseOptions for parser options. See xmlCtxtSetErrorHandler for advanced error handling. See xmlNewInputURL, xmlNewInputMemory, xmlNewInputIO and similar functions for advanced input control. See htmlNewSAXParserCtxt for custom SAX parsers.

htmlNewSAXParserCtxt ()

htmlParserCtxtPtr	htmlNewSAXParserCtxt	(const htmlSAXHandler * sax, 
						 void * userData)

Allocate and initialize a new HTML SAX parser context. If userData is NULL, the parser context will be passed as user data. Available since 2.11.0. If you want support older versions, it's best to invoke htmlNewParserCtxt and set ctxt->sax with struct assignment. Also see htmlNewParserCtxt.

htmlNodeStatus ()

htmlStatus	htmlNodeStatus		(htmlNodePtr node, 
					 int legacy)

Checks whether the tree node is valid. Experimental (the author only uses the HTML enhancements in a SAX parser)

htmlParseCharRef ()

int	htmlParseCharRef		(htmlParserCtxtPtr ctxt)

DEPRECATED: Internal function, don't use. parse Reference declarations [66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'

htmlParseChunk ()

int	htmlParseChunk			(htmlParserCtxtPtr ctxt, 
					 const char * chunk, 
					 int size, 
					 int terminate)

Parse a chunk of memory in push parser mode. Assumes that the parser context was initialized with htmlCreatePushParserCtxt. The last chunk, which will often be empty, must be marked with the @terminate flag. With the default SAX callbacks, the resulting document will be available in ctxt->myDoc. This pointer will not be freed by the library. If the document isn't well-formed, ctxt->myDoc is set to NULL.

htmlParseDoc ()

htmlDocPtr	htmlParseDoc		(const xmlChar * cur, 
					 const char * encoding)

DEPRECATED: Use htmlReadDoc. Parse an HTML in-memory document and build a tree. This function uses deprecated global parser options.

htmlParseDocument ()

int	htmlParseDocument		(htmlParserCtxtPtr ctxt)

Parse an HTML document and invoke the SAX handlers. This is useful if you're only interested in custom SAX callbacks. If you want a document tree, use htmlCtxtParseDocument.

htmlParseElement ()

void	htmlParseElement		(htmlParserCtxtPtr ctxt)

DEPRECATED: Internal function, don't use. parse an HTML element, this is highly recursive this is kept for compatibility with previous code versions [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue

htmlParseEntityRef ()

const htmlEntityDesc *	htmlParseEntityRef	(htmlParserCtxtPtr ctxt, 
						 const xmlChar ** str)

DEPRECATED: Internal function, don't use. parse an HTML ENTITY references [68] EntityRef ::= '&' Name ';'

htmlParseFile ()

htmlDocPtr	htmlParseFile		(const char * filename, 
					 const char * encoding)

Parse an HTML file and build a tree. See xmlNewInputURL for details.

htmlReadDoc ()

htmlDocPtr	htmlReadDoc		(const xmlChar * str, 
					 const char * url, 
					 const char * encoding, 
					 int options)

Convenience function to parse an HTML document from a zero-terminated string. See htmlCtxtReadDoc for details.

htmlReadFd ()

htmlDocPtr	htmlReadFd		(int fd, 
					 const char * url, 
					 const char * encoding, 
					 int options)

Convenience function to parse an HTML document from a file descriptor. NOTE that the file descriptor will not be closed when the context is freed or reset. See htmlCtxtReadFd for details.

htmlReadFile ()

htmlDocPtr	htmlReadFile		(const char * filename, 
					 const char * encoding, 
					 int options)

Convenience function to parse an HTML file from the filesystem, the network or a global user-defined resource loader. See htmlCtxtReadFile for details.

htmlReadIO ()

htmlDocPtr	htmlReadIO		(xmlInputReadCallback ioread, 
					 xmlInputCloseCallback ioclose, 
					 void * ioctx, 
					 const char * url, 
					 const char * encoding, 
					 int options)

Convenience function to parse an HTML document from I/O functions and context. See htmlCtxtReadIO for details.

htmlReadMemory ()

htmlDocPtr	htmlReadMemory		(const char * buffer, 
					 int size, 
					 const char * url, 
					 const char * encoding, 
					 int options)

Convenience function to parse an HTML document from memory. The input buffer must not contain any terminating null bytes. See htmlCtxtReadMemory for details.

htmlSAXParseDoc ()

htmlDocPtr	htmlSAXParseDoc		(const xmlChar * cur, 
					 const char * encoding, 
					 htmlSAXHandlerPtr sax, 
					 void * userData)

DEPRECATED: Use htmlNewSAXParserCtxt and htmlCtxtReadDoc. Parse an HTML in-memory document. If sax is not NULL, use the SAX callbacks to handle parse events. If sax is NULL, fallback to the default DOM behavior and return a tree.

htmlSAXParseFile ()

htmlDocPtr	htmlSAXParseFile	(const char * filename, 
					 const char * encoding, 
					 htmlSAXHandlerPtr sax, 
					 void * userData)

DEPRECATED: Use htmlNewSAXParserCtxt and htmlCtxtReadFile. parse an HTML file and build a tree. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time. It use the given SAX function block to handle the parsing callback. If sax is NULL, fallback to the default DOM tree building routines.

htmlTagLookup ()

const htmlElemDesc *	htmlTagLookup	(const xmlChar * tag)

Lookup the HTML tag in the ElementTable