1
<?xml version="1.0" encoding="UTF-8"?>
4
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
5
<title>HTMLparser: interface for an HTML 4.0 non-verifying parser</title>
6
<meta name="generator" content="Libxml2 devhelp stylesheet"/>
7
<link rel="start" href="index.html" title="libxml2 Reference Manual"/>
8
<link rel="up" href="general.html" title="API"/>
9
<link rel="stylesheet" href="style.css" type="text/css"/>
10
<link rel="chapter" href="general.html" title="API"/>
12
<body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
13
<table class="navigation" width="100%" summary="Navigation header" cellpadding="2" cellspacing="2">
16
<a accesskey="p" href="libxml2-DOCBparser.html">
17
<img src="left.png" width="24" height="24" border="0" alt="Prev"/>
21
<a accesskey="u" href="general.html">
22
<img src="up.png" width="24" height="24" border="0" alt="Up"/>
26
<a accesskey="h" href="index.html">
27
<img src="home.png" width="24" height="24" border="0" alt="Home"/>
31
<a accesskey="n" href="libxml2-HTMLtree.html">
32
<img src="right.png" width="24" height="24" border="0" alt="Next"/>
35
<th width="100%" align="center">libxml2 Reference Manual</th>
39
<span class="refentrytitle">HTMLparser</span>
41
<p>HTMLparser - interface for an HTML 4.0 non-verifying parser</p>
42
<p>this module implements an HTML 4.0 non-verifying parser with API compatible with the XML parser ones. It should be able to parse "real world" HTML, even if severely broken from a specification point of view. </p>
43
<p>Author(s): Daniel Veillard </p>
44
<div class="refsynopsisdiv">
46
<pre class="synopsis">#define <a href="#htmlDefaultSubelement">htmlDefaultSubelement</a>(elt);
47
#define <a href="#htmlElementAllowedHereDesc">htmlElementAllowedHereDesc</a>(parent, elt);
48
#define <a href="#htmlRequiredAttrs">htmlRequiredAttrs</a>(elt);
49
typedef <a href="libxml2-parser.html#xmlParserNodeInfo">xmlParserNodeInfo</a> <a href="#htmlParserNodeInfo">htmlParserNodeInfo</a>;
50
typedef <a href="libxml2-tree.html#xmlParserInput">xmlParserInput</a> <a href="#htmlParserInput">htmlParserInput</a>;
51
typedef <a href="libxml2-tree.html#xmlParserCtxtPtr">xmlParserCtxtPtr</a> <a href="#htmlParserCtxtPtr">htmlParserCtxtPtr</a>;
52
typedef struct _htmlEntityDesc <a href="#htmlEntityDesc">htmlEntityDesc</a>;
53
typedef <a href="libxml2-tree.html#xmlDocPtr">xmlDocPtr</a> <a href="#htmlDocPtr">htmlDocPtr</a>;
54
typedef <a href="libxml2-tree.html#xmlSAXHandlerPtr">xmlSAXHandlerPtr</a> <a href="#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a>;
55
typedef enum <a href="#htmlStatus">htmlStatus</a>;
56
typedef <a href="libxml2-tree.html#xmlNodePtr">xmlNodePtr</a> <a href="#htmlNodePtr">htmlNodePtr</a>;
57
typedef <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * <a href="#htmlElemDescPtr">htmlElemDescPtr</a>;
58
typedef struct _htmlElemDesc <a href="#htmlElemDesc">htmlElemDesc</a>;
59
typedef <a href="libxml2-tree.html#xmlSAXHandler">xmlSAXHandler</a> <a href="#htmlSAXHandler">htmlSAXHandler</a>;
60
typedef <a href="libxml2-tree.html#xmlParserInputPtr">xmlParserInputPtr</a> <a href="#htmlParserInputPtr">htmlParserInputPtr</a>;
61
typedef enum <a href="#htmlParserOption">htmlParserOption</a>;
62
typedef <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityDescPtr">htmlEntityDescPtr</a>;
63
typedef <a href="libxml2-tree.html#xmlParserCtxt">xmlParserCtxt</a> <a href="#htmlParserCtxt">htmlParserCtxt</a>;
64
int <a href="#htmlIsScriptAttribute">htmlIsScriptAttribute</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name);
65
int <a href="#htmlHandleOmittedElem">htmlHandleOmittedElem</a> (int val);
66
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadFd">htmlReadFd</a> (int fd, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
67
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadIO">htmlReadIO</a> (<a href="libxml2-xmlIO.html#xmlInputReadCallback">xmlInputReadCallback</a> ioread, <br/> <a href="libxml2-xmlIO.html#xmlInputCloseCallback">xmlInputCloseCallback</a> ioclose, <br/> void * ioctx, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
68
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlParseFile">htmlParseFile</a> (const char * filename, <br/> const char * encoding);
69
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadDoc">htmlCtxtReadDoc</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
70
int <a href="#htmlAutoCloseTag">htmlAutoCloseTag</a> (<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name, <br/> <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);
71
int <a href="#htmlParseChunk">htmlParseChunk</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * chunk, <br/> int size, <br/> int terminate);
72
const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * <a href="#htmlTagLookup">htmlTagLookup</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * tag);
73
<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="#htmlCreateMemoryParserCtxt">htmlCreateMemoryParserCtxt</a> (const char * buffer, <br/> int size);
74
void <a href="#htmlCtxtReset">htmlCtxtReset</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
75
int <a href="#htmlElementAllowedHere">htmlElementAllowedHere</a> (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * parent, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * elt);
76
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadIO">htmlCtxtReadIO</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> <a href="libxml2-xmlIO.html#xmlInputReadCallback">xmlInputReadCallback</a> ioread, <br/> <a href="libxml2-xmlIO.html#xmlInputCloseCallback">xmlInputCloseCallback</a> ioclose, <br/> void * ioctx, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
77
<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="#htmlCreatePushParserCtxt">htmlCreatePushParserCtxt</a> (<a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * user_data, <br/> const char * chunk, <br/> int size, <br/> const char * filename, <br/> <a href="libxml2-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);
78
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadMemory">htmlReadMemory</a> (const char * buffer, <br/> int size, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
79
int <a href="#htmlIsAutoClosed">htmlIsAutoClosed</a> (<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc, <br/> <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);
80
int <a href="#htmlParseCharRef">htmlParseCharRef</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
81
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadDoc">htmlReadDoc</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
82
int <a href="#htmlEncodeEntities">htmlEncodeEntities</a> (unsigned char * out, <br/> int * outlen, <br/> const unsigned char * in, <br/> int * inlen, <br/> int quoteChar);
83
<a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> <a href="#htmlNodeStatus">htmlNodeStatus</a> (const <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> node, <br/> int legacy);
84
<a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> <a href="#htmlAttrAllowed">htmlAttrAllowed</a> (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * elt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * attr, <br/> int legacy);
85
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlSAXParseFile">htmlSAXParseFile</a> (const char * filename, <br/> const char * encoding, <br/> <a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * userData);
86
const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlParseEntityRef">htmlParseEntityRef</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> ** str);
87
<a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> <a href="#htmlElementStatusHere">htmlElementStatusHere</a> (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * parent, <br/> const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * elt);
88
const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityValueLookup">htmlEntityValueLookup</a> (unsigned int value);
89
void <a href="#htmlParseElement">htmlParseElement</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
90
int <a href="#UTF8ToHtml">UTF8ToHtml</a> (unsigned char * out, <br/> int * outlen, <br/> const unsigned char * in, <br/> int * inlen);
91
const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityLookup">htmlEntityLookup</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name);
92
void <a href="#htmlFreeParserCtxt">htmlFreeParserCtxt</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
93
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadMemory">htmlCtxtReadMemory</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * buffer, <br/> int size, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
94
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadFd">htmlCtxtReadFd</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> int fd, <br/> const char * URL, <br/> const char * encoding, <br/> int options);
95
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadFile">htmlReadFile</a> (const char * filename, <br/> const char * encoding, <br/> int options);
96
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadFile">htmlCtxtReadFile</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * filename, <br/> const char * encoding, <br/> int options);
97
int <a href="#htmlParseDocument">htmlParseDocument</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
98
<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="#htmlNewParserCtxt">htmlNewParserCtxt</a> (void);
99
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlSAXParseDoc">htmlSAXParseDoc</a> (<a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * encoding, <br/> <a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * userData);
100
int <a href="#htmlCtxtUseOptions">htmlCtxtUseOptions</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> int options);
101
<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlParseDoc">htmlParseDoc</a> (<a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * encoding);
104
<div class="refsect1" lang="en">
107
<div class="refsect1" lang="en">
109
<div class="refsect2" lang="en">
110
<div class="refsect2" lang="en"><h3><a name="htmlDefaultSubelement">Macro </a>htmlDefaultSubelement</h3><pre class="programlisting">#define <a href="#htmlDefaultSubelement">htmlDefaultSubelement</a>(elt);
111
</pre><p>Returns the default subelement for this element</p><div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>elt</tt></i>:</span></td><td>HTML element</td></tr></tbody></table></div>
114
<div class="refsect2" lang="en"><h3><a name="htmlElementAllowedHereDesc">Macro </a>htmlElementAllowedHereDesc</h3><pre class="programlisting">#define <a href="#htmlElementAllowedHereDesc">htmlElementAllowedHereDesc</a>(parent, elt);
115
</pre><p>Checks whether an HTML element description may be a direct child of the specified element. Returns 1 if allowed; 0 otherwise.</p><div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>parent</tt></i>:</span></td><td>HTML parent element</td></tr><tr><td><span class="term"><i><tt>elt</tt></i>:</span></td><td>HTML element</td></tr></tbody></table></div>
118
<div class="refsect2" lang="en"><h3><a name="htmlRequiredAttrs">Macro </a>htmlRequiredAttrs</h3><pre class="programlisting">#define <a href="#htmlRequiredAttrs">htmlRequiredAttrs</a>(elt);
119
</pre><p>Returns the attributes required for the specified element.</p><div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>elt</tt></i>:</span></td><td>HTML element</td></tr></tbody></table></div>
122
<div class="refsect2" lang="en"><h3><a name="htmlDocPtr">Typedef </a>htmlDocPtr</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlDocPtr">xmlDocPtr</a> htmlDocPtr;
126
<div class="refsect2" lang="en"><h3><a name="htmlElemDesc">Structure </a>htmlElemDesc</h3><pre class="programlisting">struct _htmlElemDesc {
127
const char * name : The tag name
128
char startTag : Whether the start tag can be implied
129
char endTag : Whether the end tag can be implied
130
char saveEndTag : Whether the end tag should be saved
131
char empty : Is this an empty element ?
132
char depr : Is this a deprecated element ?
133
char dtd : 1: only in Loose DTD, 2: only Frameset one
134
char isinline : is this a block 0 or inline 1 element
135
const char * desc : the description NRK Jan.2003 * New fields encapsulating HTML structur
136
const char ** subelts : allowed sub-elements of this element
137
const char * defaultsubelt : subelement for suggested auto-repair if necessary or NULL
138
const char ** attrs_opt : Optional Attributes
139
const char ** attrs_depr : Additional deprecated attributes
140
const char ** attrs_req : Required attributes
145
<div class="refsect2" lang="en"><h3><a name="htmlElemDescPtr">Typedef </a>htmlElemDescPtr</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * htmlElemDescPtr;
149
<div class="refsect2" lang="en"><h3><a name="htmlEntityDesc">Structure </a>htmlEntityDesc</h3><pre class="programlisting">struct _htmlEntityDesc {
150
unsigned int value : the UNICODE value for the character
151
const char * name : The entity name
152
const char * desc : the description
157
<div class="refsect2" lang="en"><h3><a name="htmlEntityDescPtr">Typedef </a>htmlEntityDescPtr</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * htmlEntityDescPtr;
161
<div class="refsect2" lang="en"><h3><a name="htmlNodePtr">Typedef </a>htmlNodePtr</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlNodePtr">xmlNodePtr</a> htmlNodePtr;
165
<div class="refsect2" lang="en"><h3><a name="htmlParserCtxt">Typedef </a>htmlParserCtxt</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlParserCtxt">xmlParserCtxt</a> htmlParserCtxt;
169
<div class="refsect2" lang="en"><h3><a name="htmlParserCtxtPtr">Typedef </a>htmlParserCtxtPtr</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlParserCtxtPtr">xmlParserCtxtPtr</a> htmlParserCtxtPtr;
173
<div class="refsect2" lang="en"><h3><a name="htmlParserInput">Typedef </a>htmlParserInput</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlParserInput">xmlParserInput</a> htmlParserInput;
177
<div class="refsect2" lang="en"><h3><a name="htmlParserInputPtr">Typedef </a>htmlParserInputPtr</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlParserInputPtr">xmlParserInputPtr</a> htmlParserInputPtr;
181
<div class="refsect2" lang="en"><h3><a name="htmlParserNodeInfo">Typedef </a>htmlParserNodeInfo</h3><pre class="programlisting"><a href="libxml2-parser.html#xmlParserNodeInfo">xmlParserNodeInfo</a> htmlParserNodeInfo;
185
<div class="refsect2" lang="en"><h3><a name="htmlParserOption">Enum </a>htmlParserOption</h3><pre class="programlisting">enum <a href="#htmlParserOption">htmlParserOption</a> {
186
<a name="HTML_PARSE_RECOVER">HTML_PARSE_RECOVER</a> = 1 /* Relaxed parsing */
187
<a name="HTML_PARSE_NOERROR">HTML_PARSE_NOERROR</a> = 32 /* suppress error reports */
188
<a name="HTML_PARSE_NOWARNING">HTML_PARSE_NOWARNING</a> = 64 /* suppress warning reports */
189
<a name="HTML_PARSE_PEDANTIC">HTML_PARSE_PEDANTIC</a> = 128 /* pedantic error reporting */
190
<a name="HTML_PARSE_NOBLANKS">HTML_PARSE_NOBLANKS</a> = 256 /* remove blank nodes */
191
<a name="HTML_PARSE_NONET">HTML_PARSE_NONET</a> = 2048 /* Forbid network access */
192
<a name="HTML_PARSE_COMPACT">HTML_PARSE_COMPACT</a> = 65536 /* compact small text nodes */
197
<div class="refsect2" lang="en"><h3><a name="htmlSAXHandler">Typedef </a>htmlSAXHandler</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlSAXHandler">xmlSAXHandler</a> htmlSAXHandler;
201
<div class="refsect2" lang="en"><h3><a name="htmlSAXHandlerPtr">Typedef </a>htmlSAXHandlerPtr</h3><pre class="programlisting"><a href="libxml2-tree.html#xmlSAXHandlerPtr">xmlSAXHandlerPtr</a> htmlSAXHandlerPtr;
205
<div class="refsect2" lang="en"><h3><a name="htmlStatus">Enum </a>htmlStatus</h3><pre class="programlisting">enum <a href="#htmlStatus">htmlStatus</a> {
206
<a name="HTML_NA">HTML_NA</a> = 0 /* something we don't check at all */
207
<a name="HTML_INVALID">HTML_INVALID</a> = 1
208
<a name="HTML_DEPRECATED">HTML_DEPRECATED</a> = 2
209
<a name="HTML_VALID">HTML_VALID</a> = 4
210
<a name="HTML_REQUIRED">HTML_REQUIRED</a> = 12 /* VALID bit set so ( & HTML_VALID ) is TRUE */
215
<div class="refsect2" lang="en"><h3><a name="UTF8ToHtml"/>UTF8ToHtml ()</h3><pre class="programlisting">int UTF8ToHtml (unsigned char * out, <br/> int * outlen, <br/> const unsigned char * in, <br/> int * inlen)<br/>
216
</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>
217
<div class="variablelist"><table border="0"><col align="left"/><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 @out</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 @in</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>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.</td></tr></tbody></table></div></div>
219
<div class="refsect2" lang="en"><h3><a name="htmlAttrAllowed"/>htmlAttrAllowed ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> htmlAttrAllowed (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * elt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * attr, <br/> int legacy)<br/>
220
</pre><p>Checks whether an <a href="libxml2-SAX.html#attribute">attribute</a> is valid for an element Has full knowledge of Required and Deprecated attributes</p>
221
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>elt</tt></i>:</span></td><td>HTML element</td></tr><tr><td><span class="term"><i><tt>attr</tt></i>:</span></td><td>HTML <a href="libxml2-SAX.html#attribute">attribute</a></td></tr><tr><td><span class="term"><i><tt>legacy</tt></i>:</span></td><td>whether to allow deprecated attributes</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>one of HTML_REQUIRED, HTML_VALID, HTML_DEPRECATED, <a href="libxml2-HTMLparser.html#HTML_INVALID">HTML_INVALID</a></td></tr></tbody></table></div></div>
223
<div class="refsect2" lang="en"><h3><a name="htmlAutoCloseTag"/>htmlAutoCloseTag ()</h3><pre class="programlisting">int htmlAutoCloseTag (<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name, <br/> <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem)<br/>
224
</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>
225
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>1 if autoclose, 0 otherwise</td></tr></tbody></table></div></div>
227
<div class="refsect2" lang="en"><h3><a name="htmlCreateMemoryParserCtxt"/>htmlCreateMemoryParserCtxt ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> htmlCreateMemoryParserCtxt (const char * buffer, <br/> int size)<br/>
228
</pre><p>Create a parser context for an HTML in-memory document.</p>
229
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the new parser context or NULL</td></tr></tbody></table></div></div>
231
<div class="refsect2" lang="en"><h3><a name="htmlCreatePushParserCtxt"/>htmlCreatePushParserCtxt ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> htmlCreatePushParserCtxt (<a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * user_data, <br/> const char * chunk, <br/> int size, <br/> const char * filename, <br/> <a href="libxml2-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc)<br/>
232
</pre><p>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.</p>
233
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the new parser context or NULL</td></tr></tbody></table></div></div>
235
<div class="refsect2" lang="en"><h3><a name="htmlCtxtReadDoc"/>htmlCtxtReadDoc ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlCtxtReadDoc (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
236
</pre><p>parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context</p>
237
<div class="variablelist"><table border="0"><col align="left"/><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>cur</tt></i>:</span></td><td>a pointer to a zero terminated string</td></tr><tr><td><span class="term"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
239
<div class="refsect2" lang="en"><h3><a name="htmlCtxtReadFd"/>htmlCtxtReadFd ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlCtxtReadFd (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> int fd, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
240
</pre><p>parse an XML from a file descriptor and build a tree. This reuses the existing @ctxt parser context</p>
241
<div class="variablelist"><table border="0"><col align="left"/><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>fd</tt></i>:</span></td><td>an open file descriptor</td></tr><tr><td><span class="term"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
243
<div class="refsect2" lang="en"><h3><a name="htmlCtxtReadFile"/>htmlCtxtReadFile ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlCtxtReadFile (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * filename, <br/> const char * encoding, <br/> int options)<br/>
244
</pre><p>parse an XML file from the filesystem or the network. This reuses the existing @ctxt parser context</p>
245
<div class="variablelist"><table border="0"><col align="left"/><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>filename</tt></i>:</span></td><td>a file or URL</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
247
<div class="refsect2" lang="en"><h3><a name="htmlCtxtReadIO"/>htmlCtxtReadIO ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlCtxtReadIO (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> <a href="libxml2-xmlIO.html#xmlInputReadCallback">xmlInputReadCallback</a> ioread, <br/> <a href="libxml2-xmlIO.html#xmlInputCloseCallback">xmlInputCloseCallback</a> ioclose, <br/> void * ioctx, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
248
</pre><p>parse an HTML document from I/O functions and source and build a tree. This reuses the existing @ctxt parser context</p>
249
<div class="variablelist"><table border="0"><col align="left"/><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>ioread</tt></i>:</span></td><td>an I/O read function</td></tr><tr><td><span class="term"><i><tt>ioclose</tt></i>:</span></td><td>an I/O close function</td></tr><tr><td><span class="term"><i><tt>ioctx</tt></i>:</span></td><td>an I/O handler</td></tr><tr><td><span class="term"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
251
<div class="refsect2" lang="en"><h3><a name="htmlCtxtReadMemory"/>htmlCtxtReadMemory ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlCtxtReadMemory (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * buffer, <br/> int size, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
252
</pre><p>parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context</p>
253
<div class="variablelist"><table border="0"><col align="left"/><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>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"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
255
<div class="refsect2" lang="en"><h3><a name="htmlCtxtReset"/>htmlCtxtReset ()</h3><pre class="programlisting">void htmlCtxtReset (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt)<br/>
256
</pre><p>Reset a parser context</p>
257
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i>:</span></td><td>an HTML parser context</td></tr></tbody></table></div></div>
259
<div class="refsect2" lang="en"><h3><a name="htmlCtxtUseOptions"/>htmlCtxtUseOptions ()</h3><pre class="programlisting">int htmlCtxtUseOptions (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> int options)<br/>
260
</pre><p>Applies the options to the parser context</p>
261
<div class="variablelist"><table border="0"><col align="left"/><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>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>0 in case of success, the set of unknown or unimplemented options in case of error.</td></tr></tbody></table></div></div>
263
<div class="refsect2" lang="en"><h3><a name="htmlElementAllowedHere"/>htmlElementAllowedHere ()</h3><pre class="programlisting">int htmlElementAllowedHere (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * parent, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * elt)<br/>
264
</pre><p>Checks whether an HTML element may be a direct child of a parent element. Note - doesn't check for deprecated elements</p>
265
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>parent</tt></i>:</span></td><td>HTML parent element</td></tr><tr><td><span class="term"><i><tt>elt</tt></i>:</span></td><td>HTML element</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>1 if allowed; 0 otherwise.</td></tr></tbody></table></div></div>
267
<div class="refsect2" lang="en"><h3><a name="htmlElementStatusHere"/>htmlElementStatusHere ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> htmlElementStatusHere (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * parent, <br/> const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * elt)<br/>
268
</pre><p>Checks whether an HTML element may be a direct child of a parent element. and if so whether it is valid or deprecated.</p>
269
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>parent</tt></i>:</span></td><td>HTML parent element</td></tr><tr><td><span class="term"><i><tt>elt</tt></i>:</span></td><td>HTML element</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>one of HTML_VALID, HTML_DEPRECATED, <a href="libxml2-HTMLparser.html#HTML_INVALID">HTML_INVALID</a></td></tr></tbody></table></div></div>
271
<div class="refsect2" lang="en"><h3><a name="htmlEncodeEntities"/>htmlEncodeEntities ()</h3><pre class="programlisting">int htmlEncodeEntities (unsigned char * out, <br/> int * outlen, <br/> const unsigned char * in, <br/> int * inlen, <br/> int quoteChar)<br/>
272
</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>
273
<div class="variablelist"><table border="0"><col align="left"/><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 @out</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 @in</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"><i><tt>Returns</tt></i>:</span></td><td>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.</td></tr></tbody></table></div></div>
275
<div class="refsect2" lang="en"><h3><a name="htmlEntityLookup"/>htmlEntityLookup ()</h3><pre class="programlisting">const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * htmlEntityLookup (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name)<br/>
276
</pre><p>Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.</p>
277
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>name</tt></i>:</span></td><td>the entity name</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the associated <a href="libxml2-HTMLparser.html#htmlEntityDescPtr">htmlEntityDescPtr</a> if found, NULL otherwise.</td></tr></tbody></table></div></div>
279
<div class="refsect2" lang="en"><h3><a name="htmlEntityValueLookup"/>htmlEntityValueLookup ()</h3><pre class="programlisting">const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * htmlEntityValueLookup (unsigned int value)<br/>
280
</pre><p>Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.</p>
281
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the associated <a href="libxml2-HTMLparser.html#htmlEntityDescPtr">htmlEntityDescPtr</a> if found, NULL otherwise.</td></tr></tbody></table></div></div>
283
<div class="refsect2" lang="en"><h3><a name="htmlFreeParserCtxt"/>htmlFreeParserCtxt ()</h3><pre class="programlisting">void htmlFreeParserCtxt (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt)<br/>
284
</pre><p>Free all the memory used by a parser context. However the parsed document in ctxt->myDoc is not freed.</p>
285
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i>:</span></td><td>an HTML parser context</td></tr></tbody></table></div></div>
287
<div class="refsect2" lang="en"><h3><a name="htmlHandleOmittedElem"/>htmlHandleOmittedElem ()</h3><pre class="programlisting">int htmlHandleOmittedElem (int val)<br/>
288
</pre><p>Set and return the previous value for handling HTML omitted tags.</p>
289
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the last value for 0 for no handling, 1 for auto insertion.</td></tr></tbody></table></div></div>
291
<div class="refsect2" lang="en"><h3><a name="htmlIsAutoClosed"/>htmlIsAutoClosed ()</h3><pre class="programlisting">int htmlIsAutoClosed (<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc, <br/> <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem)<br/>
292
</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>
293
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>1 if autoclosed, 0 otherwise</td></tr></tbody></table></div></div>
295
<div class="refsect2" lang="en"><h3><a name="htmlIsScriptAttribute"/>htmlIsScriptAttribute ()</h3><pre class="programlisting">int htmlIsScriptAttribute (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name)<br/>
296
</pre><p>Check if an <a href="libxml2-SAX.html#attribute">attribute</a> is of content type Script</p>
297
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>name</tt></i>:</span></td><td>an <a href="libxml2-SAX.html#attribute">attribute</a> name</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>1 is the <a href="libxml2-SAX.html#attribute">attribute</a> is a script 0 otherwise</td></tr></tbody></table></div></div>
299
<div class="refsect2" lang="en"><h3><a name="htmlNewParserCtxt"/>htmlNewParserCtxt ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> htmlNewParserCtxt (void)<br/>
300
</pre><p>Allocate and initialize a new parser context.</p>
301
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the <a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> or NULL in case of allocation error</td></tr></tbody></table></div></div>
303
<div class="refsect2" lang="en"><h3><a name="htmlNodeStatus"/>htmlNodeStatus ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> htmlNodeStatus (const <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> node, <br/> int legacy)<br/>
304
</pre><p>Checks whether the tree node is valid. Experimental (the author only uses the HTML enhancements in a SAX parser)</p>
305
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>node</tt></i>:</span></td><td>an <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> in a tree</td></tr><tr><td><span class="term"><i><tt>legacy</tt></i>:</span></td><td>whether to allow deprecated elements (YES is faster here for Element nodes)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>for Element nodes, a return from <a href="libxml2-HTMLparser.html#htmlElementAllowedHere">htmlElementAllowedHere</a> (if legacy allowed) or <a href="libxml2-HTMLparser.html#htmlElementStatusHere">htmlElementStatusHere</a> (otherwise). for Attribute nodes, a return from <a href="libxml2-HTMLparser.html#htmlAttrAllowed">htmlAttrAllowed</a> for other nodes, <a href="libxml2-HTMLparser.html#HTML_NA">HTML_NA</a> (no checks performed)</td></tr></tbody></table></div></div>
307
<div class="refsect2" lang="en"><h3><a name="htmlParseCharRef"/>htmlParseCharRef ()</h3><pre class="programlisting">int htmlParseCharRef (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt)<br/>
308
</pre><p>parse Reference declarations [66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'</p>
309
<div class="variablelist"><table border="0"><col align="left"/><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>Returns</tt></i>:</span></td><td>the value parsed (as an int)</td></tr></tbody></table></div></div>
311
<div class="refsect2" lang="en"><h3><a name="htmlParseChunk"/>htmlParseChunk ()</h3><pre class="programlisting">int htmlParseChunk (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * chunk, <br/> int size, <br/> int terminate)<br/>
312
</pre><p>Parse a Chunk of memory</p>
313
<div class="variablelist"><table border="0"><col align="left"/><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>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"><i><tt>Returns</tt></i>:</span></td><td>zero if no error, the <a href="libxml2-xmlerror.html#xmlParserErrors">xmlParserErrors</a> otherwise.</td></tr></tbody></table></div></div>
315
<div class="refsect2" lang="en"><h3><a name="htmlParseDoc"/>htmlParseDoc ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlParseDoc (<a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * encoding)<br/>
316
</pre><p>parse an HTML in-memory document and build a tree.</p>
317
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>cur</tt></i>:</span></td><td>a pointer to an array of <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a></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>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
319
<div class="refsect2" lang="en"><h3><a name="htmlParseDocument"/>htmlParseDocument ()</h3><pre class="programlisting">int htmlParseDocument (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt)<br/>
320
</pre><p>parse an HTML document (and build a tree if using the standard SAX interface).</p>
321
<div class="variablelist"><table border="0"><col align="left"/><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>Returns</tt></i>:</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>
323
<div class="refsect2" lang="en"><h3><a name="htmlParseElement"/>htmlParseElement ()</h3><pre class="programlisting">void htmlParseElement (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt)<br/>
324
</pre><p>parse an HTML element, this is highly recursive [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue</p>
325
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>ctxt</tt></i>:</span></td><td>an HTML parser context</td></tr></tbody></table></div></div>
327
<div class="refsect2" lang="en"><h3><a name="htmlParseEntityRef"/>htmlParseEntityRef ()</h3><pre class="programlisting">const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * htmlParseEntityRef (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> ** str)<br/>
328
</pre><p>parse an HTML ENTITY references [68] EntityRef ::= '&' Name ';'</p>
329
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the associated <a href="libxml2-HTMLparser.html#htmlEntityDescPtr">htmlEntityDescPtr</a> if found, or NULL otherwise, if non-NULL *str will have to be freed by the caller.</td></tr></tbody></table></div></div>
331
<div class="refsect2" lang="en"><h3><a name="htmlParseFile"/>htmlParseFile ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlParseFile (const char * filename, <br/> const char * encoding)<br/>
332
</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>
333
<div class="variablelist"><table border="0"><col align="left"/><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>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
335
<div class="refsect2" lang="en"><h3><a name="htmlReadDoc"/>htmlReadDoc ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlReadDoc (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
336
</pre><p>parse an XML in-memory document and build a tree.</p>
337
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>cur</tt></i>:</span></td><td>a pointer to a zero terminated string</td></tr><tr><td><span class="term"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
339
<div class="refsect2" lang="en"><h3><a name="htmlReadFd"/>htmlReadFd ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlReadFd (int fd, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
340
</pre><p>parse an XML from a file descriptor and build a tree.</p>
341
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>fd</tt></i>:</span></td><td>an open file descriptor</td></tr><tr><td><span class="term"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
343
<div class="refsect2" lang="en"><h3><a name="htmlReadFile"/>htmlReadFile ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlReadFile (const char * filename, <br/> const char * encoding, <br/> int options)<br/>
344
</pre><p>parse an XML file from the filesystem or the network.</p>
345
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>filename</tt></i>:</span></td><td>a file or URL</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
347
<div class="refsect2" lang="en"><h3><a name="htmlReadIO"/>htmlReadIO ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlReadIO (<a href="libxml2-xmlIO.html#xmlInputReadCallback">xmlInputReadCallback</a> ioread, <br/> <a href="libxml2-xmlIO.html#xmlInputCloseCallback">xmlInputCloseCallback</a> ioclose, <br/> void * ioctx, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
348
</pre><p>parse an HTML document from I/O functions and source and build a tree.</p>
349
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>ioread</tt></i>:</span></td><td>an I/O read function</td></tr><tr><td><span class="term"><i><tt>ioclose</tt></i>:</span></td><td>an I/O close function</td></tr><tr><td><span class="term"><i><tt>ioctx</tt></i>:</span></td><td>an I/O handler</td></tr><tr><td><span class="term"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
351
<div class="refsect2" lang="en"><h3><a name="htmlReadMemory"/>htmlReadMemory ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlReadMemory (const char * buffer, <br/> int size, <br/> const char * URL, <br/> const char * encoding, <br/> int options)<br/>
352
</pre><p>parse an XML in-memory document and build a tree.</p>
353
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>URL</tt></i>:</span></td><td>the base URL to use for the document</td></tr><tr><td><span class="term"><i><tt>encoding</tt></i>:</span></td><td>the document encoding, or NULL</td></tr><tr><td><span class="term"><i><tt>options</tt></i>:</span></td><td>a combination of htmlParserOption(s)</td></tr><tr><td><span class="term"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree</td></tr></tbody></table></div></div>
355
<div class="refsect2" lang="en"><h3><a name="htmlSAXParseDoc"/>htmlSAXParseDoc ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlSAXParseDoc (<a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * encoding, <br/> <a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * userData)<br/>
356
</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>
357
<div class="variablelist"><table border="0"><col align="left"/><tbody><tr><td><span class="term"><i><tt>cur</tt></i>:</span></td><td>a pointer to an array of <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a></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"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree unless SAX is NULL or the document is not well formed.</td></tr></tbody></table></div></div>
359
<div class="refsect2" lang="en"><h3><a name="htmlSAXParseFile"/>htmlSAXParseFile ()</h3><pre class="programlisting"><a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> htmlSAXParseFile (const char * filename, <br/> const char * encoding, <br/> <a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * userData)<br/>
360
</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>
361
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the resulting document tree unless SAX is NULL or the document is not well formed.</td></tr></tbody></table></div></div>
363
<div class="refsect2" lang="en"><h3><a name="htmlTagLookup"/>htmlTagLookup ()</h3><pre class="programlisting">const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * htmlTagLookup (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * tag)<br/>
364
</pre><p>Lookup the HTML tag in the ElementTable</p>
365
<div class="variablelist"><table border="0"><col align="left"/><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"><i><tt>Returns</tt></i>:</span></td><td>the related <a href="libxml2-HTMLparser.html#htmlElemDescPtr">htmlElemDescPtr</a> or NULL if not found.</td></tr></tbody></table></div></div>