1
0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2026-01-17 02:02:39 +03:00
Files
libxml2/doc/html/libxml-HTMLparser.html
Daniel Veillard 2fdbd32d51 new dictionary module to keep a single instance of the names used by the
* dict.c include/libxml/dict.h Makefile.am include/libxml/Makefile.am:
  new dictionary module to keep a single instance of the names used
  by the parser
* DOCBparser.c HTMLparser.c parser.c parserInternals.c valid.c:
  switched all parsers to use the dictionary internally
* include/libxml/HTMLparser.h include/libxml/parser.h
  include/libxml/parserInternals.h include/libxml/valid.h:
  Some of the interfaces changed as a result to receive or return
  "const xmlChar *" instead of "xmlChar *", this is either
  insignificant from an user point of view or when the returning
  value changed, those function are really parser internal methods
  that no user code should really change
* doc/libxml2-api.xml doc/html/*: the API interface changed and
  the docs were regenerated
Daniel
2003-08-18 12:15:38 +00:00

371 lines
36 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<html><head><meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"><title>HTMLparser</title><meta name="generator" content="DocBook XSL Stylesheets V1.58.1"><style xmlns="http://www.w3.org/TR/xhtml1/transitional" type="text/css">
.synopsis, .classsynopsis {
background: #eeeeee;
border: solid 1px #aaaaaa;
padding: 0.5em;
}
.programlisting {
background: #eeeeff;
border: solid 1px #aaaaff;
padding: 0.5em;
}
.variablelist {
padding: 4px;
margin-left: 3em;
}
.navigation {
background: #ffeeee;
border: solid 1px #ffaaaa;
margin-top: 0.5em;
margin-bottom: 0.5em;
}
.navigation a {
color: #770000;
}
.navigation a:visited {
color: #550000;
}
.navigation .title {
font-size: 200%;
}
</style><link rel="home" href="index.html" title="Gnome XML Library Reference Manual"><link rel="up" href="libxml-lib.html" title="Libxml Library Reference"><link rel="previous" href="libxml-xmlerror.html" title="xmlerror"><link rel="next" href="libxml-HTMLtree.html" title="HTMLtree"></head><body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF"><table xmlns="http://www.w3.org/TR/xhtml1/transitional" class="navigation" width="100%" summary="Navigation header" cellpadding="2" cellspacing="2"><tr valign="middle"><td><a accesskey="p" href="libxml-xmlerror.html"><img src="left.png" width="24" height="24" border="0" alt="Prev"></img></a></td><td><a accesskey="u" href="libxml-lib.html"><img src="up.png" width="24" height="24" border="0" alt="Up"></img></a></td><td><a accesskey="h" href="index.html"><img src="home.png" width="24" height="24" border="0" alt="Home"></img></a></td><th width="100%" align="center">Gnome XML Library Reference Manual</th><td><a accesskey="n" href="libxml-HTMLtree.html"><img src="right.png" width="24" height="24" border="0" alt="Next"></img></a></td></tr></table><div class="refentry" lang="en"><a name="libxml-HTMLparser"></a><div class="titlepage"></div><div class="refnamediv"><h2>HTMLparser</h2><p>HTMLparser &#8212; </p></div><div class="refsynopsisdiv"><h2>Synopsis</h2><pre class="synopsis">
typedef <a href="libxml-HTMLparser.html#htmlParserCtxt">htmlParserCtxt</a>;
typedef <a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a>;
typedef <a href="libxml-HTMLparser.html#htmlParserNodeInfo">htmlParserNodeInfo</a>;
typedef <a href="libxml-HTMLparser.html#htmlSAXHandler">htmlSAXHandler</a>;
typedef <a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a>;
typedef <a href="libxml-HTMLparser.html#htmlParserInput">htmlParserInput</a>;
typedef <a href="libxml-HTMLparser.html#htmlParserInputPtr">htmlParserInputPtr</a>;
typedef <a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a>;
typedef <a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a>;
struct <a href="libxml-HTMLparser.html#htmlElemDesc">htmlElemDesc</a>;
typedef <a href="libxml-HTMLparser.html#htmlElemDescPtr">htmlElemDescPtr</a>;
struct <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>;
typedef <a href="libxml-HTMLparser.html#htmlEntityDescPtr">htmlEntityDescPtr</a>;
const <a href="libxml-HTMLparser.html#htmlElemDesc">htmlElemDesc</a>* <a href="libxml-HTMLparser.html#htmlTagLookup">htmlTagLookup</a> (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *tag);
const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* <a href="libxml-HTMLparser.html#htmlEntityLookup">htmlEntityLookup</a> (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name);
const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* <a href="libxml-HTMLparser.html#htmlEntityValueLookup">htmlEntityValueLookup</a> (unsigned int value);
int <a href="libxml-HTMLparser.html#htmlIsAutoClosed">htmlIsAutoClosed</a> (<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc,
<a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);
int <a href="libxml-HTMLparser.html#htmlAutoCloseTag">htmlAutoCloseTag</a> (<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc,
const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name,
<a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);
const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* <a href="libxml-HTMLparser.html#htmlParseEntityRef">htmlParseEntityRef</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt,
const <a href="libxml-tree.html#xmlChar">xmlChar</a> **str);
int <a href="libxml-HTMLparser.html#htmlParseCharRef">htmlParseCharRef</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
void <a href="libxml-HTMLparser.html#htmlParseElement">htmlParseElement</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="libxml-HTMLparser.html#htmlCreateMemoryParserCtxt">htmlCreateMemoryParserCtxt</a>
(const char *buffer,
int size);
int <a href="libxml-HTMLparser.html#htmlParseDocument">htmlParseDocument</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="libxml-HTMLparser.html#htmlSAXParseDoc">htmlSAXParseDoc</a> (<a href="libxml-tree.html#xmlChar">xmlChar</a> *cur,
const char *encoding,
<a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
void *userData);
<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="libxml-HTMLparser.html#htmlParseDoc">htmlParseDoc</a> (<a href="libxml-tree.html#xmlChar">xmlChar</a> *cur,
const char *encoding);
<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="libxml-HTMLparser.html#htmlSAXParseFile">htmlSAXParseFile</a> (const char *filename,
const char *encoding,
<a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
void *userData);
<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="libxml-HTMLparser.html#htmlParseFile">htmlParseFile</a> (const char *filename,
const char *encoding);
int <a href="libxml-HTMLparser.html#UTF8ToHtml">UTF8ToHtml</a> (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);
int <a href="libxml-HTMLparser.html#htmlEncodeEntities">htmlEncodeEntities</a> (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen,
int quoteChar);
int <a href="libxml-HTMLparser.html#htmlIsScriptAttribute">htmlIsScriptAttribute</a> (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name);
int <a href="libxml-HTMLparser.html#htmlHandleOmittedElem">htmlHandleOmittedElem</a> (int val);
void <a href="libxml-HTMLparser.html#htmlFreeParserCtxt">htmlFreeParserCtxt</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="libxml-HTMLparser.html#htmlCreatePushParserCtxt">htmlCreatePushParserCtxt</a> (<a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
void *user_data,
const char *chunk,
int size,
const char *filename,
<a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);
int <a href="libxml-HTMLparser.html#htmlParseChunk">htmlParseChunk</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt,
const char *chunk,
int size,
int terminate);
</pre></div><div class="refsect1" lang="en"><h2>Description</h2><p>
</p></div><div class="refsect1" lang="en"><h2>Details</h2><div class="refsect2" lang="en"><h3><a name="htmlParserCtxt"></a>htmlParserCtxt</h3><pre class="programlisting">typedef xmlParserCtxt htmlParserCtxt;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParserCtxtPtr"></a>htmlParserCtxtPtr</h3><pre class="programlisting">typedef xmlParserCtxtPtr htmlParserCtxtPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParserNodeInfo"></a>htmlParserNodeInfo</h3><pre class="programlisting">typedef xmlParserNodeInfo htmlParserNodeInfo;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlSAXHandler"></a>htmlSAXHandler</h3><pre class="programlisting">typedef xmlSAXHandler htmlSAXHandler;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlSAXHandlerPtr"></a>htmlSAXHandlerPtr</h3><pre class="programlisting">typedef xmlSAXHandlerPtr htmlSAXHandlerPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParserInput"></a>htmlParserInput</h3><pre class="programlisting">typedef xmlParserInput htmlParserInput;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParserInputPtr"></a>htmlParserInputPtr</h3><pre class="programlisting">typedef xmlParserInputPtr htmlParserInputPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlDocPtr"></a>htmlDocPtr</h3><pre class="programlisting">typedef xmlDocPtr htmlDocPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlNodePtr"></a>htmlNodePtr</h3><pre class="programlisting">typedef xmlNodePtr htmlNodePtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlElemDesc"></a>struct htmlElemDesc</h3><pre class="programlisting">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 */
};
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlElemDescPtr"></a>htmlElemDescPtr</h3><pre class="programlisting">typedef htmlElemDesc *htmlElemDescPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlEntityDesc"></a>struct htmlEntityDesc</h3><pre class="programlisting">struct htmlEntityDesc {
unsigned int value; /* the UNICODE value for the character */
const char *name; /* The entity name */
const char *desc; /* the description */
};
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlEntityDescPtr"></a>htmlEntityDescPtr</h3><pre class="programlisting">typedef htmlEntityDesc *htmlEntityDescPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlTagLookup"></a>htmlTagLookup ()</h3><pre class="programlisting">const <a href="libxml-HTMLparser.html#htmlElemDesc">htmlElemDesc</a>* htmlTagLookup (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *tag);</pre><p>
Lookup the HTML tag in the ElementTable</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>tag</tt></i> :</span></td><td> The tag name in lowercase
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the related htmlElemDescPtr or NULL if not found.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlEntityLookup"></a>htmlEntityLookup ()</h3><pre class="programlisting">const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* htmlEntityLookup (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name);</pre><p>
Lookup the given entity in EntitiesTable
</p><p>
TODO: the linear scan is really ugly, an hash table is really needed.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>name</tt></i> :</span></td><td> the entity name
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the associated htmlEntityDescPtr if found, NULL otherwise.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlEntityValueLookup"></a>htmlEntityValueLookup ()</h3><pre class="programlisting">const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* htmlEntityValueLookup (unsigned int value);</pre><p>
Lookup the given entity in EntitiesTable
</p><p>
TODO: the linear scan is really ugly, an hash table is really needed.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>value</tt></i> :</span></td><td> the entity's unicode value
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the associated htmlEntityDescPtr if found, NULL otherwise.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlIsAutoClosed"></a>htmlIsAutoClosed ()</h3><pre class="programlisting">int htmlIsAutoClosed (<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc,
<a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);</pre><p>
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</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>doc</tt></i> :</span></td><td> the HTML document
</td></tr><tr><td><span class="term"><i><tt>elem</tt></i> :</span></td><td> the HTML element
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>1 if autoclosed, 0 otherwise
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlAutoCloseTag"></a>htmlAutoCloseTag ()</h3><pre class="programlisting">int htmlAutoCloseTag (<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc,
const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name,
<a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);</pre><p>
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.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>doc</tt></i> :</span></td><td> the HTML document
</td></tr><tr><td><span class="term"><i><tt>name</tt></i> :</span></td><td> The tag name
</td></tr><tr><td><span class="term"><i><tt>elem</tt></i> :</span></td><td> the HTML element
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>1 if autoclose, 0 otherwise
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseEntityRef"></a>htmlParseEntityRef ()</h3><pre class="programlisting">const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* htmlParseEntityRef (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt,
const <a href="libxml-tree.html#xmlChar">xmlChar</a> **str);</pre><p>
parse an HTML ENTITY references
</p><p>
[68] EntityRef ::= '&amp;' Name ';'</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i> :</span></td><td> an HTML parser context
</td></tr><tr><td><span class="term"><i><tt>str</tt></i> :</span></td><td> location to store the entity name
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the associated htmlEntityDescPtr if found, or NULL otherwise,
if non-NULL *str will have to be freed by the caller.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseCharRef"></a>htmlParseCharRef ()</h3><pre class="programlisting">int htmlParseCharRef (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);</pre><p>
parse Reference declarations
</p><p>
[66] CharRef ::= '&amp;#' [0-9]+ ';' |
'&amp;<GTKDOCLINK xmlns="http://www.w3.org/TR/xhtml1/transitional" HREF="x">x</GTKDOCLINK>' [0-9a-fA-F]+ ';'</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i> :</span></td><td> an HTML parser context
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the value parsed (as an int)
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseElement"></a>htmlParseElement ()</h3><pre class="programlisting">void htmlParseElement (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);</pre><p>
parse an HTML element, this is highly recursive
</p><p>
[39] element ::= EmptyElemTag | STag content ETag
</p><p>
[41] Attribute ::= Name Eq AttValue</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i> :</span></td><td> an HTML parser context
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlCreateMemoryParserCtxt"></a>htmlCreateMemoryParserCtxt ()</h3><pre class="programlisting"><a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> htmlCreateMemoryParserCtxt
(const char *buffer,
int size);</pre><p>
Create a parser context for an HTML in-memory document.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>buffer</tt></i> :</span></td><td> a pointer to a char array
</td></tr><tr><td><span class="term"><i><tt>size</tt></i> :</span></td><td> the size of the array
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the new parser context or NULL
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseDocument"></a>htmlParseDocument ()</h3><pre class="programlisting">int htmlParseDocument (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);</pre><p>
parse an HTML document (and build a tree if using the standard SAX
interface).</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i> :</span></td><td> an HTML parser context
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0, -1 in case of error. the parser context is augmented
as a result of the parsing.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlSAXParseDoc"></a>htmlSAXParseDoc ()</h3><pre class="programlisting"><a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlSAXParseDoc (<a href="libxml-tree.html#xmlChar">xmlChar</a> *cur,
const char *encoding,
<a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
void *userData);</pre><p>
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.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>cur</tt></i> :</span></td><td> a pointer to an array of xmlChar
</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i> :</span></td><td> a free form C string describing the HTML document encoding, or NULL
</td></tr><tr><td><span class="term"><i><tt>sax</tt></i> :</span></td><td> the SAX handler block
</td></tr><tr><td><span class="term"><i><tt>userData</tt></i> :</span></td><td> if using SAX, this pointer will be provided on callbacks.
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the resulting document tree unless SAX is NULL or the document is
not well formed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseDoc"></a>htmlParseDoc ()</h3><pre class="programlisting"><a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlParseDoc (<a href="libxml-tree.html#xmlChar">xmlChar</a> *cur,
const char *encoding);</pre><p>
parse an HTML in-memory document and build a tree.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>cur</tt></i> :</span></td><td> a pointer to an array of xmlChar
</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i> :</span></td><td> a free form C string describing the HTML document encoding, or NULL
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the resulting document tree
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlSAXParseFile"></a>htmlSAXParseFile ()</h3><pre class="programlisting"><a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlSAXParseFile (const char *filename,
const char *encoding,
<a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
void *userData);</pre><p>
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.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>filename</tt></i> :</span></td><td> the filename
</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i> :</span></td><td> a free form C string describing the HTML document encoding, or NULL
</td></tr><tr><td><span class="term"><i><tt>sax</tt></i> :</span></td><td> the SAX handler block
</td></tr><tr><td><span class="term"><i><tt>userData</tt></i> :</span></td><td> if using SAX, this pointer will be provided on callbacks.
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the resulting document tree unless SAX is NULL or the document is
not well formed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseFile"></a>htmlParseFile ()</h3><pre class="programlisting"><a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlParseFile (const char *filename,
const char *encoding);</pre><p>
parse an HTML file and build a tree. Automatic support for ZLIB/Compress
compressed document is provided by default if found at compile-time.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>filename</tt></i> :</span></td><td> the filename
</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i> :</span></td><td> a free form C string describing the HTML document encoding, or NULL
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the resulting document tree
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="UTF8ToHtml"></a>UTF8ToHtml ()</h3><pre class="programlisting">int UTF8ToHtml (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</pre><p>
Take a block of UTF-8 chars in and try to convert it to an ASCII
plus HTML entities block of chars out.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>out</tt></i> :</span></td><td> a pointer to an array of bytes to store the result
</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i> :</span></td><td> the length of <i><tt>out</tt></i>
</td></tr><tr><td><span class="term"><i><tt>in</tt></i> :</span></td><td> a pointer to an array of UTF-8 chars
</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i> :</span></td><td> the length of <i><tt>in</tt></i>
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 if success, -2 if the transcoding fails, or -1 otherwise
The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
as the return value is positive, else unpredictable.
The value of <i><tt>outlen</tt></i> after return is the number of octets consumed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlEncodeEntities"></a>htmlEncodeEntities ()</h3><pre class="programlisting">int htmlEncodeEntities (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen,
int quoteChar);</pre><p>
Take a block of UTF-8 chars in and try to convert it to an ASCII
plus HTML entities block of chars out.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>out</tt></i> :</span></td><td> a pointer to an array of bytes to store the result
</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i> :</span></td><td> the length of <i><tt>out</tt></i>
</td></tr><tr><td><span class="term"><i><tt>in</tt></i> :</span></td><td> a pointer to an array of UTF-8 chars
</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i> :</span></td><td> the length of <i><tt>in</tt></i>
</td></tr><tr><td><span class="term"><i><tt>quoteChar</tt></i> :</span></td><td> the quote character to escape (' or ") or zero.
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 if success, -2 if the transcoding fails, or -1 otherwise
The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
as the return value is positive, else unpredictable.
The value of <i><tt>outlen</tt></i> after return is the number of octets consumed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlIsScriptAttribute"></a>htmlIsScriptAttribute ()</h3><pre class="programlisting">int htmlIsScriptAttribute (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name);</pre><p>
Check if an attribute is of content type Script</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>name</tt></i> :</span></td><td> an attribute name
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>1 is the attribute is a script 0 otherwise
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlHandleOmittedElem"></a>htmlHandleOmittedElem ()</h3><pre class="programlisting">int htmlHandleOmittedElem (int val);</pre><p>
Set and return the previous value for handling HTML omitted tags.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>val</tt></i> :</span></td><td> int 0 or 1
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the last value for 0 for no handling, 1 for auto insertion.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlFreeParserCtxt"></a>htmlFreeParserCtxt ()</h3><pre class="programlisting">void htmlFreeParserCtxt (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);</pre><p>
Free all the memory used by a parser context. However the parsed
document in ctxt-&gt;myDoc is not freed.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i> :</span></td><td> an HTML parser context
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlCreatePushParserCtxt"></a>htmlCreatePushParserCtxt ()</h3><pre class="programlisting"><a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> htmlCreatePushParserCtxt (<a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
void *user_data,
const char *chunk,
int size,
const char *filename,
<a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);</pre><p>
Create a parser context for using the HTML parser in push mode
The value of <i><tt>filename</tt></i> is used for fetching external entities
and error/warning reports.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>sax</tt></i> :</span></td><td> a SAX handler
</td></tr><tr><td><span class="term"><i><tt>user_data</tt></i> :</span></td><td> The user data returned on SAX callbacks
</td></tr><tr><td><span class="term"><i><tt>chunk</tt></i> :</span></td><td> a pointer to an array of chars
</td></tr><tr><td><span class="term"><i><tt>size</tt></i> :</span></td><td> number of chars in the array
</td></tr><tr><td><span class="term"><i><tt>filename</tt></i> :</span></td><td> an optional file name or URI
</td></tr><tr><td><span class="term"><i><tt>enc</tt></i> :</span></td><td> an optional encoding
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the new parser context or NULL
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="htmlParseChunk"></a>htmlParseChunk ()</h3><pre class="programlisting">int htmlParseChunk (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt,
const char *chunk,
int size,
int terminate);</pre><p>
Parse a Chunk of memory</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i> :</span></td><td> an XML parser context
</td></tr><tr><td><span class="term"><i><tt>chunk</tt></i> :</span></td><td> an char array
</td></tr><tr><td><span class="term"><i><tt>size</tt></i> :</span></td><td> the size in byte of the chunk
</td></tr><tr><td><span class="term"><i><tt>terminate</tt></i> :</span></td><td> last chunk indicator
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>zero if no error, the xmlParserErrors otherwise.
</td></tr></tbody></table></div></div></div></div><table xmlns="http://www.w3.org/TR/xhtml1/transitional" class="navigation" width="100%" summary="Navigation footer" cellpadding="2" cellspacing="0"><tr valign="middle"><td align="left"><a accesskey="p" href="libxml-xmlerror.html"><b>&lt;&lt; xmlerror</b></a></td><td align="right"><a accesskey="n" href="libxml-HTMLtree.html"><b>HTMLtree &gt;&gt;</b></a></td></tr></table></body></html>