HTMLparser.h libxml/xmlversion.h libxml/parser.h /builds/GNOME/libxml2/HTMLparser.c /builds/GNOME/libxml2/HTMLtree.c /builds/GNOME/libxml2/debugXML.c /builds/GNOME/libxml2/encoding.c /builds/GNOME/libxml2/globals.c /builds/GNOME/libxml2/parser.c HTMLtree.h parserInternals.h UTF8ToHtml htmlUTF8ToHtml htmlDefaultSubelement elt elt->defaultsubelt htmlElementAllowedHereDesc parent elt htmlElementAllowedHere((parent), (elt)->name) htmlRequiredAttrs elt (elt)->attrs_req htmlParserOption HTML_PARSE_RECOVER = 1<<0 No effect as of 2.14.0. HTML_PARSE_NODEFDTD = 1<<2 Do not default to a doctype if none was found. HTML_PARSE_NOERROR = 1<<5 Disable error and warning reports to the error handlers. Errors are still accessible with xmlCtxtGetLastError(). HTML_PARSE_NOWARNING = 1<<6 Disable warning reports. HTML_PARSE_PEDANTIC = 1<<7 No effect. HTML_PARSE_NOBLANKS = 1<<8 Remove some text nodes containing only whitespace from the result document. Which nodes are removed depends on a conservative heuristic. The reindenting feature of the serialization code relies on this option to be set when parsing. Use of this option is DISCOURAGED. HTML_PARSE_NONET = 1<<11 No effect. HTML_PARSE_NOIMPLIED = 1<<13 Do not add implied html, head or body elements. HTML_PARSE_COMPACT = 1<<16 Store small strings directly in the node struct to save memory. HTML_PARSE_HUGE = 1<<19 Relax some internal limits. See XML_PARSE_HUGE in xmlParserOption. 2.14.0 Use XML_PARSE_HUGE with older versions. HTML_PARSE_IGNORE_ENC =1<<21 Ignore the encoding in the HTML declaration. This option is mostly unneeded these days. The only effect is to enforce ISO-8859-1 decoding of ASCII-like data. HTML_PARSE_BIG_LINES = 1<<22 Enable reporting of line numbers larger than 65535. 2.14.0 Use XML_PARSE_BIG_LINES with older versions. HTML_PARSE_HTML5 = 1<<26 Make the tokenizer emit a SAX callback for each token. This results in unbalanced invocations of startElement and endElement. For now, this is only usable to tokenize HTML5 with custom SAX callbacks. A tree builder isn't implemented yet. 2.14.0 This is the set of HTML parser options that can be passed to htmlReadDoc, htmlCtxtSetOptions and other functions. htmlStatus HTML_NA = 0 HTML_INVALID = 0x1 HTML_DEPRECATED = 0x2 HTML_VALID = 0x4 HTML_REQUIRED = 0xc deprecated content model xmlParserCtxt typedef xmlParserCtxt htmlParserCtxt htmlParserCtxt Same as xmlParserCtxt. xmlParserCtxtPtr typedef xmlParserCtxtPtr htmlParserCtxtPtr htmlParserCtxtPtr xmlParserNodeInfo typedef xmlParserNodeInfo htmlParserNodeInfo htmlParserNodeInfo xmlSAXHandler typedef xmlSAXHandler htmlSAXHandler htmlSAXHandler Same as xmlSAXHandler. xmlSAXHandlerPtr typedef xmlSAXHandlerPtr htmlSAXHandlerPtr htmlSAXHandlerPtr xmlParserInput typedef xmlParserInput htmlParserInput htmlParserInput Same as xmlParserInput. xmlParserInputPtr typedef xmlParserInputPtr htmlParserInputPtr htmlParserInputPtr xmlDocPtr typedef xmlDocPtr htmlDocPtr htmlDocPtr xmlNodePtr typedef xmlNodePtr htmlNodePtr htmlNodePtr void void htmlInitAutoClose (void) htmlInitAutoClose void DeprecatedThis is a no-op. const htmlElemDesc * const htmlElemDesc * htmlTagLookup (const xmlChar *tag) htmlTagLookup const xmlChar * tag Lookup the HTML tag in the ElementTable. DeprecatedOnly supports HTML 4. tag The tag name in lowercase the related htmlElemDesc or NULL if not found. const htmlEntityDesc * const htmlEntityDesc * htmlEntityLookup (const xmlChar *name) htmlEntityLookup const xmlChar * name Lookup the given entity in EntitiesTable. DeprecatedOnly supports HTML 4. TODO: the linear scan is really ugly, an hash table is really needed. name the entity name the associated htmlEntityDesc if found, NULL otherwise. const htmlEntityDesc * const htmlEntityDesc * htmlEntityValueLookup (unsigned int value) htmlEntityValueLookup unsigned int value Lookup the given entity in EntitiesTable. DeprecatedOnly supports HTML 4. TODO: the linear scan is really ugly, an hash table is really needed. value the entity's unicode value the associated htmlEntityDesc if found, NULL otherwise. int int htmlIsAutoClosed (xmlDoc *doc, xmlNode *elem) htmlIsAutoClosed xmlDoc * doc xmlNode * 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 DeprecatedInternal function, don't use. doc the HTML document elem the HTML element 1 if autoclosed, 0 otherwise int int htmlAutoCloseTag (xmlDoc *doc, const xmlChar *name, xmlNode *elem) htmlAutoCloseTag xmlDoc * doc const xmlChar * name xmlNode * 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. DeprecatedInternal function, don't use. doc the HTML document name The tag name elem the HTML element 1 if autoclose, 0 otherwise const htmlEntityDesc * const htmlEntityDesc * htmlParseEntityRef (htmlParserCtxt *ctxt, const xmlChar **str) htmlParseEntityRef htmlParserCtxt * ctxt const xmlChar ** str DeprecatedInternal function, don't use. ctxt an HTML parser context str location to store the entity name NULL. int int htmlParseCharRef (htmlParserCtxt *ctxt) htmlParseCharRef htmlParserCtxt * ctxt DeprecatedInternal function, don't use. ctxt an HTML parser context 0 void void htmlParseElement (htmlParserCtxt *ctxt) htmlParseElement htmlParserCtxt * ctxt This is kept for compatibility with previous code versions. DeprecatedInternal function, don't use. ctxt an HTML parser context htmlParserCtxt * htmlParserCtxt * htmlNewParserCtxt (void) 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 htmlNewSAXParserCtxt for custom SAX parsers. the htmlParserCtxt or NULL in case of allocation error htmlParserCtxt * htmlParserCtxt * htmlNewSAXParserCtxt (const htmlSAXHandler *sax, void *userData) 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. 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. sax SAX handler userData user data the htmlParserCtxt or NULL in case of allocation error htmlParserCtxt * htmlParserCtxt * htmlCreateMemoryParserCtxt (const char *buffer, int size) htmlCreateMemoryParserCtxt const char * buffer int size Create a parser context for an HTML in-memory document. The input buffer must not contain any terminating null bytes. DeprecatedUse htmlNewParserCtxt and htmlCtxtReadMemory. buffer a pointer to a char array size the size of the array the new parser context or NULL int int htmlParseDocument (htmlParserCtxt *ctxt) htmlParseDocument htmlParserCtxt * 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. ctxt an HTML parser context 0, -1 in case of error. xmlDoc * xmlDoc * htmlSAXParseDoc (const xmlChar *cur, const char *encoding, htmlSAXHandler *sax, void *userData) htmlSAXParseDoc const xmlChar * cur const char * encoding htmlSAXHandler * 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. DeprecatedUse htmlNewSAXParserCtxt and htmlCtxtReadDoc. 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. the resulting document tree unless SAX is NULL or the document is not well formed. xmlDoc * xmlDoc * htmlParseDoc (const xmlChar *cur, const char *encoding) htmlParseDoc const xmlChar * cur const char * encoding Parse an HTML in-memory document and build a tree. DeprecatedUse htmlReadDoc. This function uses deprecated global parser options. cur a pointer to an array of xmlChar encoding the encoding (optional) the resulting document tree htmlParserCtxt * htmlParserCtxt * htmlCreateFileParserCtxt (const char *filename, const char *encoding) htmlCreateFileParserCtxt const char * filename const char * encoding Create a parser context to read from a file. DeprecatedUse htmlNewParserCtxt and htmlCtxtReadFile. 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. filename the filename encoding optional encoding the new parser context or NULL if a memory allocation failed. xmlDoc * xmlDoc * htmlSAXParseFile (const char *filename, const char *encoding, htmlSAXHandler *sax, void *userData) htmlSAXParseFile const char * filename const char * encoding htmlSAXHandler * 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. DeprecatedUse htmlNewSAXParserCtxt and htmlCtxtReadFile. filename the filename encoding encoding (optional) sax the SAX handler block userData if using SAX, this pointer will be provided on callbacks. the resulting document tree unless SAX is NULL or the document is not well formed. xmlDoc * xmlDoc * htmlParseFile (const char *filename, const char *encoding) htmlParseFile const char * filename const char * encoding Parse an HTML file and build a tree. filename the filename encoding encoding (optional) the resulting document tree int int htmlUTF8ToHtml (unsigned char *out, int *outlen, const unsigned char *in, int *inlen) htmlUTF8ToHtml 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. DeprecatedInternal function, don't use. out a pointer to an array of bytes to store the result outlen the length of out in a pointer to an array of UTF-8 chars inlen the length of in 0 if success, -2 if the transcoding fails, or -1 otherwise The value of inlen after return is the number of octets consumed as the return value is positive, else unpredictable. The value of outlen after return is the number of octets consumed. int int htmlEncodeEntities (unsigned char *out, int *outlen, const unsigned char *in, int *inlen, int quoteChar) 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. DeprecatedOnly supports HTML 4. out a pointer to an array of bytes to store the result outlen the length of out in a pointer to an array of UTF-8 chars inlen the length of in quoteChar the quote character to escape (' or ") or zero. 0 if success, -2 if the transcoding fails, or -1 otherwise The value of inlen after return is the number of octets consumed as the return value is positive, else unpredictable. The value of outlen after return is the number of octets consumed. int int htmlIsScriptAttribute (const xmlChar *name) htmlIsScriptAttribute const xmlChar * name Check if an attribute is of content type Script. DeprecatedOnly supports HTML 4. name an attribute name 1 is the attribute is a script 0 otherwise int int htmlHandleOmittedElem (int val) htmlHandleOmittedElem int val Set and return the previous value for handling HTML omitted tags. DeprecatedUse HTML_PARSE_NOIMPLIED val int 0 or 1 the last value for 0 for no handling, 1 for auto insertion. htmlParserCtxt * htmlParserCtxt * htmlCreatePushParserCtxt (htmlSAXHandler *sax, void *user_data, const char *chunk, int size, const char *filename, xmlCharEncoding enc) htmlCreatePushParserCtxt htmlSAXHandler * 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. sax a SAX handler (optional) user_data The user data returned on SAX callbacks (optional) chunk a pointer to an array of chars (optional) size number of chars in the array filename only used for error reporting (optional) enc encoding (deprecated, pass XML_CHAR_ENCODING_NONE) the new parser context or NULL if a memory allocation failed. int int htmlParseChunk (htmlParserCtxt *ctxt, const char *chunk, int size, int terminate) htmlParseChunk htmlParserCtxt * 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. Since 2.14.0, xmlCtxtGetDocument can be used to retrieve the result document. ctxt an HTML parser context chunk chunk of memory size size of chunk in bytes terminate last chunk indicator an xmlParserErrors code (0 on success). void void htmlFreeParserCtxt (htmlParserCtxt *ctxt) htmlFreeParserCtxt htmlParserCtxt * ctxt Free all the memory used by a parser context. However the parsed document in ctxt->myDoc is not freed. ctxt an HTML parser context void void htmlCtxtReset (htmlParserCtxt *ctxt) htmlCtxtReset htmlParserCtxt * ctxt Reset a parser context. Same as xmlCtxtReset. ctxt an HTML parser context int int htmlCtxtSetOptions (htmlParserCtxt *ctxt, int options) htmlCtxtSetOptions htmlParserCtxt * ctxt int options Applies the options to the parser context. Unset options are cleared. 2.14.0 With older versions, you can use htmlCtxtUseOptions. ctxt an HTML parser context options a bitmask of htmlParserOption values 0 in case of success, the set of unknown or unimplemented options in case of error. int int htmlCtxtUseOptions (htmlParserCtxt *ctxt, int options) htmlCtxtUseOptions htmlParserCtxt * ctxt int options Applies the options to the parser context. The following options are never cleared and can only be enabled: DeprecatedUse htmlCtxtSetOptions. HTML_PARSE_NODEFDTD HTML_PARSE_NOERROR HTML_PARSE_NOWARNING HTML_PARSE_NOIMPLIED HTML_PARSE_COMPACT HTML_PARSE_HUGE HTML_PARSE_IGNORE_ENC HTML_PARSE_BIG_LINES ctxt an HTML parser context options a combination of htmlParserOption values 0 in case of success, the set of unknown or unimplemented options in case of error. xmlDoc * xmlDoc * htmlReadDoc (const xmlChar *cur, const char *URL, const char *encoding, int options) htmlReadDoc const xmlChar * cur str const char * URL url const char * encoding int options Convenience function to parse an HTML document from a zero-terminated string. See htmlCtxtReadDoc for details. str a pointer to a zero terminated string url only used for error reporting (optoinal) encoding the document encoding (optional) options a combination of htmlParserOption values the resulting document tree. xmlDoc * xmlDoc * htmlReadFile (const char *URL, const char *encoding, int options) htmlReadFile const char * URL 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. filename a file or URL encoding the document encoding (optional) options a combination of htmlParserOption values the resulting document tree. xmlDoc * xmlDoc * htmlReadMemory (const char *buffer, int size, const char *URL, const char *encoding, int options) htmlReadMemory const char * buffer int size const char * URL 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. buffer a pointer to a char array size the size of the array url only used for error reporting (optional) encoding the document encoding, or NULL options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlReadFd (int fd, const char *URL, const char *encoding, int options) htmlReadFd int fd const char * URL 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. fd an open file descriptor url only used for error reporting (optional) encoding the document encoding, or NULL options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlReadIO (xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void *ioctx, const char *URL, const char *encoding, int options) htmlReadIO xmlInputReadCallback ioread xmlInputCloseCallback ioclose void * ioctx const char * URL url const char * encoding int options Convenience function to parse an HTML document from I/O functions and context. See htmlCtxtReadIO for details. ioread an I/O read function ioclose an I/O close function (optional) ioctx an I/O handler url only used for error reporting (optional) encoding the document encoding (optional) options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlCtxtParseDocument (htmlParserCtxt *ctxt, xmlParserInput *input) htmlCtxtParseDocument htmlParserCtxt * ctxt xmlParserInput * input Parse an HTML document and return the resulting document tree. 2.13.0 ctxt an HTML parser context input parser input the resulting document tree or NULL xmlDoc * xmlDoc * htmlCtxtReadDoc (xmlParserCtxt *ctxt, const xmlChar *cur, const char *URL, const char *encoding, int options) htmlCtxtReadDoc xmlParserCtxt * ctxt const xmlChar * cur str const char * URL const char * encoding int options Parse an HTML in-memory document and build a tree. See htmlCtxtUseOptions for details. ctxt an HTML parser context str a pointer to a zero terminated string URL only used for error reporting (optional) encoding the document encoding (optional) options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlCtxtReadFile (xmlParserCtxt *ctxt, const char *filename, const char *encoding, int options) htmlCtxtReadFile xmlParserCtxt * 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 htmlCtxtUseOptions for details. ctxt an HTML parser context filename a file or URL encoding the document encoding (optional) options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlCtxtReadMemory (xmlParserCtxt *ctxt, const char *buffer, int size, const char *URL, const char *encoding, int options) htmlCtxtReadMemory xmlParserCtxt * 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. ctxt an HTML parser context buffer a pointer to a char array size the size of the array URL only used for error reporting (optional) encoding the document encoding (optinal) options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlCtxtReadFd (xmlParserCtxt *ctxt, int fd, const char *URL, const char *encoding, int options) htmlCtxtReadFd xmlParserCtxt * 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. ctxt an HTML parser context fd an open file descriptor URL only used for error reporting (optional) encoding the document encoding (optinal) options a combination of htmlParserOption values the resulting document tree xmlDoc * xmlDoc * htmlCtxtReadIO (xmlParserCtxt *ctxt, xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void *ioctx, const char *URL, const char *encoding, int options) htmlCtxtReadIO xmlParserCtxt * 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 htmlCtxtUseOptions for details. ctxt an HTML parser context ioread an I/O read function ioclose an I/O close function ioctx an I/O handler URL the base URL to use for the document encoding the document encoding, or NULL options a combination of htmlParserOption values the resulting document tree htmlStatus htmlStatus htmlAttrAllowed (const htmlElemDesc *, const xmlChar *, int) htmlAttrAllowed const htmlElemDesc * elt const xmlChar * attr int legacy DeprecatedDon't use. elt HTML element attr HTML attribute legacy whether to allow deprecated attributes HTML_VALID int int htmlElementAllowedHere (const htmlElemDesc *, const xmlChar *) htmlElementAllowedHere const htmlElemDesc * parent const xmlChar * elt DeprecatedDon't use. parent HTML parent element elt HTML element 1 htmlStatus htmlStatus htmlElementStatusHere (const htmlElemDesc *, const htmlElemDesc *) htmlElementStatusHere const htmlElemDesc * parent const htmlElemDesc * elt DeprecatedDon't use. parent HTML parent element elt HTML element HTML_VALID htmlStatus htmlStatus htmlNodeStatus (xmlNode *, int) htmlNodeStatus xmlNode * node int legacy DeprecatedDon't use. node an xmlNode in a tree legacy whether to allow deprecated elements (YES is faster here for Element nodes) HTML_VALID HTML parser, doesn't support HTML5. This module orginally implemented an HTML parser based on the (underspecified) HTML 4.0 spec. As of 2.14, the tokenizer conforms to HTML5. Tree construction still follows a custom, unspecified algorithm with many differences to HTML5. The parser defaults to ISO-8859-1, the default encoding of HTTP/1.0. See Copyright for the status of this software. Daniel Veillard