|
Packit Service |
a31ea6 |
|
|
Packit Service |
a31ea6 |
|
|
Packit Service |
a31ea6 |
<html xmlns="http://www.w3.org/1999/xhtml"><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /><link rel="SHORTCUT ICON" href="/favicon.ico" /><style type="text/css">
|
|
Packit Service |
a31ea6 |
TD {font-family: Verdana,Arial,Helvetica}
|
|
Packit Service |
a31ea6 |
BODY {font-family: Verdana,Arial,Helvetica; margin-top: 2em; margin-left: 0em; margin-right: 0em}
|
|
Packit Service |
a31ea6 |
H1 {font-family: Verdana,Arial,Helvetica}
|
|
Packit Service |
a31ea6 |
H2 {font-family: Verdana,Arial,Helvetica}
|
|
Packit Service |
a31ea6 |
H3 {font-family: Verdana,Arial,Helvetica}
|
|
Packit Service |
a31ea6 |
A:link, A:visited, A:active { text-decoration: underline }
|
|
Packit Service |
a31ea6 |
</style><style type="text/css">
|
|
Packit Service |
a31ea6 |
div.deprecated pre.programlisting {border-style: double;border-color:red}
|
|
Packit Service |
a31ea6 |
pre.programlisting {border-style: double;background: #EECFA1}
|
|
Packit Service |
a31ea6 |
</style><title>Module HTMLparser from libxml2</title></head><body bgcolor="#8b7765" text="#000000" link="#a06060" vlink="#000000">![Action against software patents](../epatents.png) | ![Gnome2 Logo](../gnome2.png) ![W3C Logo](../w3c.png) ![Red Hat Logo](../redhat.gif) | Module HTMLparser from libxml2 |
|
|
<center>API Menu</center> | <form action="../search.php" enctype="application/x-www-form-urlencoded" method="get"><input name="query" type="text" size="20" value="" /><input name="submit" type="submit" value="Search ..." /></form> |
<center>API Indexes</center> | |
<center>Related links</center> | |
|
| |
|
|
|
Packit Service |
a31ea6 |
Structure htmlElemDesc struct _htmlElemDesc
|
|
Packit Service |
a31ea6 |
Typedef htmlElemDesc * htmlElemDescPtr
|
|
Packit Service |
a31ea6 |
Structure htmlEntityDesc struct _htmlEntityDesc
|
|
Packit Service |
a31ea6 |
Typedef htmlEntityDesc * htmlEntityDescPtr
|
|
Packit Service |
a31ea6 |
Typedef xmlNodePtr htmlNodePtr
|
|
Packit Service |
a31ea6 |
Typedef xmlParserCtxt htmlParserCtxt
|
|
Packit Service |
a31ea6 |
Typedef xmlParserCtxtPtr htmlParserCtxtPtr
|
|
Packit Service |
a31ea6 |
Typedef xmlParserInput htmlParserInput
|
|
Packit Service |
a31ea6 |
Typedef xmlParserInputPtr htmlParserInputPtr
|
|
Packit Service |
a31ea6 |
Typedef xmlParserNodeInfo htmlParserNodeInfo
|
|
Packit Service |
a31ea6 |
Enum htmlParserOption
|
|
Packit Service |
a31ea6 |
Typedef xmlSAXHandler htmlSAXHandler
|
|
Packit Service |
a31ea6 |
Typedef xmlSAXHandlerPtr htmlSAXHandlerPtr
|
|
Packit Service |
a31ea6 |
Enum htmlStatus
|
|
Packit Service |
a31ea6 |
int UTF8ToHtml (unsigned char * out, int * outlen, const unsigned char * in, int * inlen)
|
|
Packit Service |
a31ea6 |
htmlStatus htmlAttrAllowed (const htmlElemDesc * elt, const xmlChar * attr, int legacy)
|
|
Packit Service |
a31ea6 |
int htmlAutoCloseTag (htmlDocPtr doc, const xmlChar * name, htmlNodePtr elem)
|
|
Packit Service |
a31ea6 |
htmlParserCtxtPtr htmlCreateMemoryParserCtxt (const char * buffer, int size)
|
|
Packit Service |
a31ea6 |
htmlParserCtxtPtr htmlCreatePushParserCtxt (htmlSAXHandlerPtr sax, void * user_data, const char * chunk, int size, const char * filename, xmlCharEncoding enc)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlCtxtReadDoc (htmlParserCtxtPtr ctxt, const xmlChar * cur, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlCtxtReadFd (htmlParserCtxtPtr ctxt, int fd, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlCtxtReadFile (htmlParserCtxtPtr ctxt, const char * filename, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlCtxtReadIO (htmlParserCtxtPtr ctxt, xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void * ioctx, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlCtxtReadMemory (htmlParserCtxtPtr ctxt, const char * buffer, int size, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
void htmlCtxtReset (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
int htmlCtxtUseOptions (htmlParserCtxtPtr ctxt, int options)
|
|
Packit Service |
a31ea6 |
int htmlElementAllowedHere (const htmlElemDesc * parent, const xmlChar * elt)
|
|
Packit Service |
a31ea6 |
htmlStatus htmlElementStatusHere (const htmlElemDesc * parent, const htmlElemDesc * elt)
|
|
Packit Service |
a31ea6 |
int htmlEncodeEntities (unsigned char * out, int * outlen, const unsigned char * in, int * inlen, int quoteChar)
|
|
Packit Service |
a31ea6 |
const htmlEntityDesc * htmlEntityLookup (const xmlChar * name)
|
|
Packit Service |
a31ea6 |
const htmlEntityDesc * htmlEntityValueLookup (unsigned int value)
|
|
Packit Service |
a31ea6 |
void htmlFreeParserCtxt (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
int htmlHandleOmittedElem (int val)
|
|
Packit Service |
a31ea6 |
int htmlIsAutoClosed (htmlDocPtr doc, htmlNodePtr elem)
|
|
Packit Service |
a31ea6 |
int htmlIsScriptAttribute (const xmlChar * name)
|
|
Packit Service |
a31ea6 |
htmlParserCtxtPtr htmlNewParserCtxt (void)
|
|
Packit Service |
a31ea6 |
htmlStatus htmlNodeStatus (const htmlNodePtr node, int legacy)
|
|
Packit Service |
a31ea6 |
int htmlParseCharRef (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
int htmlParseChunk (htmlParserCtxtPtr ctxt, const char * chunk, int size, int terminate)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlParseDoc (const xmlChar * cur, const char * encoding)
|
|
Packit Service |
a31ea6 |
int htmlParseDocument (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
void htmlParseElement (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
const htmlEntityDesc * htmlParseEntityRef (htmlParserCtxtPtr ctxt, const xmlChar ** str)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlParseFile (const char * filename, const char * encoding)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlReadDoc (const xmlChar * cur, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlReadFd (int fd, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlReadFile (const char * filename, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlReadIO (xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void * ioctx, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlReadMemory (const char * buffer, int size, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlSAXParseDoc (const xmlChar * cur, const char * encoding, htmlSAXHandlerPtr sax, void * userData)
|
|
Packit Service |
a31ea6 |
htmlDocPtr htmlSAXParseFile (const char * filename, const char * encoding, htmlSAXHandlerPtr sax, void * userData)
|
|
Packit Service |
a31ea6 |
const htmlElemDesc * htmlTagLookup (const xmlChar * tag)
|
|
Packit Service |
a31ea6 |
Description
|
|
Packit Service |
a31ea6 |
Macro: htmlDefaultSubelement#define htmlDefaultSubelement Returns the default subelement for this element
|
|
Packit Service |
a31ea6 |
Macro: htmlElementAllowedHereDesc#define htmlElementAllowedHereDesc Checks whether an HTML element description may be a direct child of the specified element. Returns 1 if allowed; 0 otherwise.
|
|
Packit Service |
a31ea6 |
Macro: htmlRequiredAttrs#define htmlRequiredAttrs Returns the attributes required for the specified element.
|
|
Packit Service |
a31ea6 |
Structure htmlElemDesc struct _htmlElemDesc {
|
|
Packit Service |
a31ea6 |
const char * name : The tag name
|
|
Packit Service |
a31ea6 |
char startTag : Whether the start tag can be implied
|
|
Packit Service |
a31ea6 |
char endTag : Whether the end tag can be implied
|
|
Packit Service |
a31ea6 |
char saveEndTag : Whether the end tag should be saved
|
|
Packit Service |
a31ea6 |
char empty : Is this an empty element ?
|
|
Packit Service |
a31ea6 |
char depr : Is this a deprecated element ?
|
|
Packit Service |
a31ea6 |
char dtd : 1: only in Loose DTD, 2: only Frameset
|
|
Packit Service |
a31ea6 |
char isinline : is this a block 0 or inline 1 element
|
|
Packit Service |
a31ea6 |
const char * desc : the description NRK Jan.2003 * New fiel
|
|
Packit Service |
a31ea6 |
const char ** subelts : allowed sub-elements of this element
|
|
Packit Service |
a31ea6 |
const char * defaultsubelt : subelement for suggested auto-repair if
|
|
Packit Service |
a31ea6 |
const char ** attrs_opt : Optional Attributes
|
|
Packit Service |
a31ea6 |
const char ** attrs_depr : Additional deprecated attributes
|
|
Packit Service |
a31ea6 |
const char ** attrs_req : Required attributes
|
|
Packit Service |
a31ea6 |
}Structure htmlEntityDesc struct _htmlEntityDesc {
|
|
Packit Service |
a31ea6 |
unsigned int value : the UNICODE value for the character
|
|
Packit Service |
a31ea6 |
const char * name : The entity name
|
|
Packit Service |
a31ea6 |
const char * desc : the description
|
|
Packit Service |
a31ea6 |
}Enum htmlParserOption {
|
|
Packit Service |
a31ea6 |
HTML_PARSE_RECOVER = 1 : Relaxed parsing
|
|
Packit Service |
a31ea6 |
HTML_PARSE_NODEFDTD = 4 : do not default a doctype if not found
|
|
Packit Service |
a31ea6 |
HTML_PARSE_NOERROR = 32 : suppress error reports
|
|
Packit Service |
a31ea6 |
HTML_PARSE_NOWARNING = 64 : suppress warning reports
|
|
Packit Service |
a31ea6 |
HTML_PARSE_PEDANTIC = 128 : pedantic error reporting
|
|
Packit Service |
a31ea6 |
HTML_PARSE_NOBLANKS = 256 : remove blank nodes
|
|
Packit Service |
a31ea6 |
HTML_PARSE_NONET = 2048 : Forbid network access
|
|
Packit Service |
a31ea6 |
HTML_PARSE_NOIMPLIED = 8192 : Do not add implied html/body... elements
|
|
Packit Service |
a31ea6 |
HTML_PARSE_COMPACT = 65536 : compact small text nodes
|
|
Packit Service |
a31ea6 |
HTML_PARSE_IGNORE_ENC = 2097152 : ignore internal document encoding hint
|
|
Packit Service |
a31ea6 |
}
|
|
Packit Service |
a31ea6 |
Enum htmlStatus {
|
|
Packit Service |
a31ea6 |
HTML_NA = 0 : something we don't check at all
|
|
Packit Service |
a31ea6 |
HTML_INVALID = 1
|
|
Packit Service |
a31ea6 |
HTML_DEPRECATED = 2
|
|
Packit Service |
a31ea6 |
HTML_VALID = 4
|
|
Packit Service |
a31ea6 |
HTML_REQUIRED = 12 : VALID bit set so ( & HTML_VALID ) is TRUE
|
|
Packit Service |
a31ea6 |
}
|
|
Packit Service |
a31ea6 |
Function: UTF8ToHtmlint UTF8ToHtml (unsigned char * out, int * outlen, const unsigned char * in, int * inlen)
|
|
Packit Service |
a31ea6 |
Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.
|
|
Packit Service |
a31ea6 |
<tt>out</tt>: | a pointer to an array of bytes to store the result | <tt>outlen</tt>: | the length of @out | <tt>in</tt>: | a pointer to an array of UTF-8 chars | <tt>inlen</tt>: | the length of @in | <tt>Returns</tt>: | 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. |
Function: htmlAttrAllowedhtmlStatus htmlAttrAllowed (const htmlElemDesc * elt, const xmlChar * attr, int legacy)
|
|
Packit Service |
a31ea6 |
Checks whether an attribute is valid for an element Has full knowledge of Required and Deprecated attributes
|
|
Packit Service |
a31ea6 |
<tt>elt</tt>: | HTML element | <tt>attr</tt>: | HTML attribute | <tt>legacy</tt>: | whether to allow deprecated attributes | <tt>Returns</tt>: | one of HTML_REQUIRED, HTML_VALID, HTML_DEPRECATED, HTML_INVALID |
Function: htmlAutoCloseTagint htmlAutoCloseTag (htmlDocPtr doc, const xmlChar * name, htmlNodePtr elem)
|
|
Packit Service |
a31ea6 |
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.
|
|
Packit Service |
a31ea6 |
<tt>doc</tt>: | the HTML document | <tt>name</tt>: | The tag name | <tt>elem</tt>: | the HTML element | <tt>Returns</tt>: | 1 if autoclose, 0 otherwise |
Function: htmlCreateMemoryParserCtxthtmlParserCtxtPtr htmlCreateMemoryParserCtxt (const char * buffer, int size)
|
|
Packit Service |
a31ea6 |
Create a parser context for an HTML in-memory document.
|
|
Packit Service |
a31ea6 |
<tt>buffer</tt>: | a pointer to a char array | <tt>size</tt>: | the size of the array | <tt>Returns</tt>: | the new parser context or NULL |
Function: htmlCreatePushParserCtxthtmlParserCtxtPtr htmlCreatePushParserCtxt (htmlSAXHandlerPtr sax, void * user_data, const char * chunk, int size, const char * filename, xmlCharEncoding enc)
|
|
Packit Service |
a31ea6 |
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.
|
|
Packit Service |
a31ea6 |
<tt>sax</tt>: | a SAX handler | <tt>user_data</tt>: | The user data returned on SAX callbacks | <tt>chunk</tt>: | a pointer to an array of chars | <tt>size</tt>: | number of chars in the array | <tt>filename</tt>: | an optional file name or URI | <tt>enc</tt>: | an optional encoding | <tt>Returns</tt>: | the new parser context or NULL |
Function: htmlCtxtReadDochtmlDocPtr htmlCtxtReadDoc (htmlParserCtxtPtr ctxt, const xmlChar * cur, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>cur</tt>: | a pointer to a zero terminated string | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlCtxtReadFdhtmlDocPtr htmlCtxtReadFd (htmlParserCtxtPtr ctxt, int fd, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML from a file descriptor and build a tree. This reuses the existing @ctxt parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>fd</tt>: | an open file descriptor | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlCtxtReadFilehtmlDocPtr htmlCtxtReadFile (htmlParserCtxtPtr ctxt, const char * filename, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML file from the filesystem or the network. This reuses the existing @ctxt parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>filename</tt>: | a file or URL | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlCtxtReadIOhtmlDocPtr htmlCtxtReadIO (htmlParserCtxtPtr ctxt, xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void * ioctx, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an HTML document from I/O functions and source and build a tree. This reuses the existing @ctxt parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>ioread</tt>: | an I/O read function | <tt>ioclose</tt>: | an I/O close function | <tt>ioctx</tt>: | an I/O handler | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlCtxtReadMemoryhtmlDocPtr htmlCtxtReadMemory (htmlParserCtxtPtr ctxt, const char * buffer, int size, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>buffer</tt>: | a pointer to a char array | <tt>size</tt>: | the size of the array | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlCtxtResetvoid htmlCtxtReset (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
Reset a parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context |
Function: htmlCtxtUseOptionsint htmlCtxtUseOptions (htmlParserCtxtPtr ctxt, int options)
|
|
Packit Service |
a31ea6 |
Applies the options to the parser context
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | 0 in case of success, the set of unknown or unimplemented options in case of error. |
Function: htmlElementAllowedHereint htmlElementAllowedHere (const htmlElemDesc * parent, const xmlChar * elt)
|
|
Packit Service |
a31ea6 |
Checks whether an HTML element may be a direct child of a parent element. Note - doesn't check for deprecated elements
|
|
Packit Service |
a31ea6 |
<tt>parent</tt>: | HTML parent element | <tt>elt</tt>: | HTML element | <tt>Returns</tt>: | 1 if allowed; 0 otherwise. |
Function: htmlElementStatusHerehtmlStatus htmlElementStatusHere (const htmlElemDesc * parent, const htmlElemDesc * elt)
|
|
Packit Service |
a31ea6 |
Checks whether an HTML element may be a direct child of a parent element. and if so whether it is valid or deprecated.
|
|
Packit Service |
a31ea6 |
<tt>parent</tt>: | HTML parent element | <tt>elt</tt>: | HTML element | <tt>Returns</tt>: | one of HTML_VALID, HTML_DEPRECATED, HTML_INVALID |
Function: htmlEncodeEntitiesint htmlEncodeEntities (unsigned char * out, int * outlen, const unsigned char * in, int * inlen, int quoteChar)
|
|
Packit Service |
a31ea6 |
Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.
|
|
Packit Service |
a31ea6 |
<tt>out</tt>: | a pointer to an array of bytes to store the result | <tt>outlen</tt>: | the length of @out | <tt>in</tt>: | a pointer to an array of UTF-8 chars | <tt>inlen</tt>: | the length of @in | <tt>quoteChar</tt>: | the quote character to escape (' or ") or zero. | <tt>Returns</tt>: | 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. |
Function: htmlEntityLookupconst htmlEntityDesc * htmlEntityLookup (const xmlChar * name)
|
|
Packit Service |
a31ea6 |
Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.
|
|
Packit Service |
a31ea6 |
<tt>name</tt>: | the entity name | <tt>Returns</tt>: | the associated htmlEntityDescPtr if found, NULL otherwise. |
Function: htmlEntityValueLookupconst htmlEntityDesc * htmlEntityValueLookup (unsigned int value)
|
|
Packit Service |
a31ea6 |
Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.
|
|
Packit Service |
a31ea6 |
<tt>value</tt>: | the entity's unicode value | <tt>Returns</tt>: | the associated htmlEntityDescPtr if found, NULL otherwise. |
Function: htmlFreeParserCtxtvoid htmlFreeParserCtxt (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
Free all the memory used by a parser context. However the parsed document in ctxt->myDoc is not freed.
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context |
Function: htmlHandleOmittedElemint htmlHandleOmittedElem (int val)
|
|
Packit Service |
a31ea6 |
Set and return the previous value for handling HTML omitted tags.
|
|
Packit Service |
a31ea6 |
<tt>val</tt>: | int 0 or 1 | <tt>Returns</tt>: | the last value for 0 for no handling, 1 for auto insertion. |
Function: htmlIsAutoClosedint htmlIsAutoClosed (htmlDocPtr doc, htmlNodePtr elem)
|
|
Packit Service |
a31ea6 |
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
|
|
Packit Service |
a31ea6 |
<tt>doc</tt>: | the HTML document | <tt>elem</tt>: | the HTML element | <tt>Returns</tt>: | 1 if autoclosed, 0 otherwise |
Function: htmlIsScriptAttributeint htmlIsScriptAttribute (const xmlChar * name)
|
|
Packit Service |
a31ea6 |
Check if an attribute is of content type Script
|
|
Packit Service |
a31ea6 |
<tt>name</tt>: | an attribute name | <tt>Returns</tt>: | 1 is the attribute is a script 0 otherwise |
Function: htmlNewParserCtxthtmlParserCtxtPtr htmlNewParserCtxt (void)
|
|
Packit Service |
a31ea6 |
Allocate and initialize a new parser context.
|
|
Packit Service |
a31ea6 |
Function: htmlNodeStatushtmlStatus htmlNodeStatus (const htmlNodePtr node, int legacy)
|
|
Packit Service |
a31ea6 |
Checks whether the tree node is valid. Experimental (the author only uses the HTML enhancements in a SAX parser)
|
|
Packit Service |
a31ea6 |
Function: htmlParseCharRefint htmlParseCharRef (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
parse Reference declarations [66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>Returns</tt>: | the value parsed (as an int) |
Function: htmlParseChunkint htmlParseChunk (htmlParserCtxtPtr ctxt, const char * chunk, int size, int terminate)
|
|
Packit Service |
a31ea6 |
Parse a Chunk of memory
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>chunk</tt>: | an char array | <tt>size</tt>: | the size in byte of the chunk | <tt>terminate</tt>: | last chunk indicator | <tt>Returns</tt>: | zero if no error, the xmlParserErrors otherwise. |
Function: htmlParseDochtmlDocPtr htmlParseDoc (const xmlChar * cur, const char * encoding)
|
|
Packit Service |
a31ea6 |
parse an HTML in-memory document and build a tree.
|
|
Packit Service |
a31ea6 |
<tt>cur</tt>: | a pointer to an array of xmlChar | <tt>encoding</tt>: | a free form C string describing the HTML document encoding, or NULL | <tt>Returns</tt>: | the resulting document tree |
Function: htmlParseDocumentint htmlParseDocument (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
parse an HTML document (and build a tree if using the standard SAX interface).
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>Returns</tt>: | 0, -1 in case of error. the parser context is augmented as a result of the parsing. |
Function: htmlParseElementvoid htmlParseElement (htmlParserCtxtPtr ctxt)
|
|
Packit Service |
a31ea6 |
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
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context |
Function: htmlParseEntityRefconst htmlEntityDesc * htmlParseEntityRef (htmlParserCtxtPtr ctxt, const xmlChar ** str)
|
|
Packit Service |
a31ea6 |
parse an HTML ENTITY references [68] EntityRef ::= '&' Name ';'
|
|
Packit Service |
a31ea6 |
<tt>ctxt</tt>: | an HTML parser context | <tt>str</tt>: | location to store the entity name | <tt>Returns</tt>: | the associated htmlEntityDescPtr if found, or NULL otherwise, if non-NULL *str will have to be freed by the caller. |
Function: htmlParseFilehtmlDocPtr htmlParseFile (const char * filename, const char * encoding)
|
|
Packit Service |
a31ea6 |
parse an HTML file and build a tree. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time.
|
|
Packit Service |
a31ea6 |
<tt>filename</tt>: | the filename | <tt>encoding</tt>: | a free form C string describing the HTML document encoding, or NULL | <tt>Returns</tt>: | the resulting document tree |
Function: htmlReadDochtmlDocPtr htmlReadDoc (const xmlChar * cur, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML in-memory document and build a tree.
|
|
Packit Service |
a31ea6 |
<tt>cur</tt>: | a pointer to a zero terminated string | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlReadFdhtmlDocPtr htmlReadFd (int fd, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML from a file descriptor and build a tree.
|
|
Packit Service |
a31ea6 |
<tt>fd</tt>: | an open file descriptor | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlReadFilehtmlDocPtr htmlReadFile (const char * filename, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML file from the filesystem or the network.
|
|
Packit Service |
a31ea6 |
<tt>filename</tt>: | a file or URL | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlReadIOhtmlDocPtr htmlReadIO (xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void * ioctx, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an HTML document from I/O functions and source and build a tree.
|
|
Packit Service |
a31ea6 |
<tt>ioread</tt>: | an I/O read function | <tt>ioclose</tt>: | an I/O close function | <tt>ioctx</tt>: | an I/O handler | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlReadMemoryhtmlDocPtr htmlReadMemory (const char * buffer, int size, const char * URL, const char * encoding, int options)
|
|
Packit Service |
a31ea6 |
parse an XML in-memory document and build a tree.
|
|
Packit Service |
a31ea6 |
<tt>buffer</tt>: | a pointer to a char array | <tt>size</tt>: | the size of the array | <tt>URL</tt>: | the base URL to use for the document | <tt>encoding</tt>: | the document encoding, or NULL | <tt>options</tt>: | a combination of htmlParserOption(s) | <tt>Returns</tt>: | the resulting document tree |
Function: htmlSAXParseDochtmlDocPtr htmlSAXParseDoc (const xmlChar * cur, const char * encoding, htmlSAXHandlerPtr sax, void * userData)
|
|
Packit Service |
a31ea6 |
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.
|
|
Packit Service |
a31ea6 |
<tt>cur</tt>: | a pointer to an array of xmlChar | <tt>encoding</tt>: | a free form C string describing the HTML document encoding, or NULL | <tt>sax</tt>: | the SAX handler block | <tt>userData</tt>: | if using SAX, this pointer will be provided on callbacks. | <tt>Returns</tt>: | the resulting document tree unless SAX is NULL or the document is not well formed. |
Function: htmlSAXParseFilehtmlDocPtr htmlSAXParseFile (const char * filename, const char * encoding, htmlSAXHandlerPtr sax, void * userData)
|
|
Packit Service |
a31ea6 |
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.
|
|
Packit Service |
a31ea6 |
<tt>filename</tt>: | the filename | <tt>encoding</tt>: | a free form C string describing the HTML document encoding, or NULL | <tt>sax</tt>: | the SAX handler block | <tt>userData</tt>: | if using SAX, this pointer will be provided on callbacks. | <tt>Returns</tt>: | the resulting document tree unless SAX is NULL or the document is not well formed. |
Function: htmlTagLookupconst htmlElemDesc * htmlTagLookup (const xmlChar * tag)
|
|
Packit Service |
a31ea6 |
Lookup the HTML tag in the ElementTable
|
|
Packit Service |
a31ea6 |
<tt>tag</tt>: | The tag name in lowercase | <tt>Returns</tt>: | the related htmlElemDescPtr or NULL if not found. |
Daniel Veillard </body></html>
|