htmlParserCtxt

typedef xmlParserCtxt htmlParserCtxt;

htmlParserCtxtPtr

typedef xmlParserCtxtPtr htmlParserCtxtPtr;

htmlParserNodeInfo

typedef xmlParserNodeInfo htmlParserNodeInfo;

htmlSAXHandler

typedef xmlSAXHandler htmlSAXHandler;

htmlSAXHandlerPtr

typedef xmlSAXHandlerPtr htmlSAXHandlerPtr;

htmlParserInput

typedef xmlParserInput htmlParserInput;

htmlParserInputPtr

typedef xmlParserInputPtr htmlParserInputPtr;

htmlDocPtr

typedef xmlDocPtr htmlDocPtr;

htmlNodePtr

typedef xmlNodePtr htmlNodePtr;

struct 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 structure
 *
 * Bugs:
 *	This is a very limited representation.  It fails to tell us when
 *	an element *requires* subelements (we only have whether they're
 *	allowed or not), and it doesn't tell us where CDATA and PCDATA
 *	are allowed.  Some element relationships are not fully represented:
 *	these are flagged with the word MODIFIER
 */
    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 */
};

htmlElemDescPtr

typedef htmlElemDesc *htmlElemDescPtr;

struct htmlEntityDesc

struct htmlEntityDesc {

    unsigned int value;	/* the UNICODE value for the character */
    const char *name;	/* The entity name */
    const char *desc;   /* the description */
};

htmlEntityDescPtr

typedef htmlEntityDesc *htmlEntityDescPtr;

htmlTagLookup ()

const htmlElemDesc* htmlTagLookup           (const xmlChar *tag);

Lookup the HTML tag in the ElementTable

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.

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

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.

htmlParseEntityRef ()

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

parse an HTML ENTITY references

[68] EntityRef ::= '&' Name ';'

htmlParseCharRef ()

int         htmlParseCharRef                (htmlParserCtxtPtr ctxt);

parse Reference declarations

[66] CharRef ::= '&#' [0-9]+ ';' | '&x' [0-9a-fA-F]+ ';'

htmlParseElement ()

void        htmlParseElement                (htmlParserCtxtPtr ctxt);

parse an HTML element, this is highly recursive

[39] element ::= EmptyElemTag | STag content ETag

[41] Attribute ::= Name Eq AttValue

htmlCreateMemoryParserCtxt ()

htmlParserCtxtPtr htmlCreateMemoryParserCtxt
                                            (const char *buffer,
                                             int size);

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

htmlParseDocument ()

int         htmlParseDocument               (htmlParserCtxtPtr ctxt);

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

htmlSAXParseDoc ()

htmlDocPtr  htmlSAXParseDoc                 (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.

htmlParseDoc ()

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

parse an HTML in-memory document and build 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.

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.

UTF8ToHtml ()

int         UTF8ToHtml                      (unsigned char *out,
                                             int *outlen,
                                             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.

htmlEncodeEntities ()

int         htmlEncodeEntities              (unsigned char *out,
                                             int *outlen,
                                             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.

htmlIsScriptAttribute ()

int         htmlIsScriptAttribute           (const xmlChar *name);

Check if an attribute is of content type Script

htmlHandleOmittedElem ()

int         htmlHandleOmittedElem           (int val);

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

htmlFreeParserCtxt ()

void        htmlFreeParserCtxt              (htmlParserCtxtPtr ctxt);

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

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.

htmlParseChunk ()

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

Parse a Chunk of memory