Gnome XML Library Reference Manual
<<< Previous PageHomeUpNext Page >>>

HTMLparser

Name

HTMLparser —

Synopsis



typedef     htmlParserCtxt;
typedef     htmlParserCtxtPtr;
typedef     htmlParserNodeInfo;
typedef     htmlSAXHandler;
typedef     htmlSAXHandlerPtr;
typedef     htmlParserInput;
typedef     htmlParserInputPtr;
typedef     htmlDocPtr;
typedef     htmlNodePtr;
htmlElemDescPtr htmlTagLookup               (const xmlChar *tag);
htmlEntityDescPtr htmlEntityLookup          (const xmlChar *name);
htmlEntityDescPtr htmlParseEntityRef        (htmlParserCtxtPtr ctxt,
                                             xmlChar **str);
int         htmlParseCharRef                (htmlParserCtxtPtr ctxt);
void        htmlParseElement                (htmlParserCtxtPtr ctxt);
htmlDocPtr  htmlSAXParseDoc                 (xmlChar *cur,
                                             const char *encoding,
                                             htmlSAXHandlerPtr sax,
                                             void *userData);
htmlDocPtr  htmlParseDoc                    (xmlChar *cur,
                                             const char *encoding);
htmlDocPtr  htmlSAXParseFile                (const char *filename,
                                             const char *encoding,
                                             htmlSAXHandlerPtr sax,
                                             void *userData);
htmlDocPtr  htmlParseFile                   (const char *filename,
                                             const char *encoding);

Description

Details

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;

htmlTagLookup ()

htmlElemDescPtr htmlTagLookup               (const xmlChar *tag);

Lookup the HTML tag in the ElementTable

tag : The tag name
Returns :the related htmlElemDescPtr or NULL if not found.

htmlEntityLookup ()

htmlEntityDescPtr htmlEntityLookup          (const xmlChar *name);

Lookup the given entity in EntitiesTable

TODO: the linear scan is really ugly, an hash table is really needed.

name : the entity name
Returns :the associated htmlEntityDescPtr if found, NULL otherwise.

htmlParseEntityRef ()

htmlEntityDescPtr htmlParseEntityRef        (htmlParserCtxtPtr ctxt,
                                             xmlChar **str);

parse an HTML ENTITY references

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

ctxt : an HTML parser context
str : location to store the entity name
Returns :the associated htmlEntityDescPtr if found, or NULL otherwise, if non-NULL *str will have to be freed by the caller.

htmlParseCharRef ()

int         htmlParseCharRef                (htmlParserCtxtPtr ctxt);

parse Reference declarations

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

ctxt : an HTML parser context
Returns :the value parsed (as an int)

htmlParseElement ()

void        htmlParseElement                (htmlParserCtxtPtr ctxt);

parse an HTML element, this is highly recursive

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

[41] Attribute ::= Name Eq AttValue

ctxt : an HTML parser context

htmlSAXParseDoc ()

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

parse an HTML in-memory document and build a tree. It use the given SAX function block to handle the parsing callback. If sax is NULL, fallback to the default DOM tree building routines.

cur : a pointer to an array of xmlChar
encoding : a free form C string describing the HTML document encoding, or NULL
sax : the SAX handler block
userData : if using SAX, this pointer will be provided on callbacks.
Returns :the resulting document tree

htmlParseDoc ()

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

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

cur : a pointer to an array of xmlChar
encoding : a free form C string describing the HTML document encoding, or NULL
Returns :the resulting document 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.

filename : the filename
encoding : a free form C string describing the HTML document encoding, or NULL
sax : the SAX handler block
userData : if using SAX, this pointer will be provided on callbacks.
Returns :the resulting document tree

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.

filename : the filename
encoding : a free form C string describing the HTML document encoding, or NULL
Returns :the resulting document tree



<<< Previous PageHomeUpNext Page >>>
xml-errorHTMLtree