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 */
};

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.

htmlCreateMemoryParserCtxt ()

htmlParserCtxtPtr	htmlCreateMemoryParserCtxt	(const char * buffer, 
							 int size)

Create a parser context for an HTML in-memory document.

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 The value of @filename is used for fetching external entities and error/warning reports.

htmlCtxtReadDoc ()

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

parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context

htmlCtxtReadFd ()

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

parse an XML from a file descriptor and build a tree. This reuses the existing @ctxt parser context

htmlCtxtReadFile ()

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

parse an XML file from the filesystem or the network. This reuses the existing @ctxt parser context

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. This reuses the existing @ctxt parser context

htmlCtxtReadMemory ()

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

parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context

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)

Set and return the previous value for handling HTML omitted tags.

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 parser context.

htmlNodeStatus ()

htmlStatus	htmlNodeStatus		(const 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)

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

htmlParseDoc ()

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

parse an HTML in-memory document and build a tree.

htmlParseDocument ()

int	htmlParseDocument		(htmlParserCtxtPtr ctxt)

parse an HTML document (and build a tree if using the standard SAX interface).

htmlParseElement ()

void	htmlParseElement		(htmlParserCtxtPtr ctxt)

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)

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. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time.

htmlReadDoc ()

htmlDocPtr	htmlReadDoc		(const xmlChar * cur, 
					 const char * URL, 
					 const char * encoding, 
					 int options)

parse an XML in-memory document and build a tree.

htmlReadFd ()

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

parse an HTML from a file descriptor and build a tree. NOTE that the file descriptor will not be closed when the reader is closed or reset.

htmlReadFile ()

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

parse an XML file from the filesystem or the network.

htmlReadIO ()

htmlDocPtr	htmlReadIO		(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.

htmlReadMemory ()

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

parse an XML in-memory document and build a tree.

htmlSAXParseDoc ()

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

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)

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