blob: cf22ca1bb715d1819e63a78361c4ad0640be40be [file] [log] [blame]
Daniel Veillardd4330462003-04-29 12:40:16 +00001<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
2<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">
3 .synopsis, .classsynopsis {
4 background: #eeeeee;
5 border: solid 1px #aaaaaa;
6 padding: 0.5em;
7 }
8 .programlisting {
9 background: #eeeeff;
10 border: solid 1px #aaaaff;
11 padding: 0.5em;
12 }
13 .variablelist {
14 padding: 4px;
15 margin-left: 3em;
16 }
17 .navigation {
18 background: #ffeeee;
19 border: solid 1px #ffaaaa;
20 margin-top: 0.5em;
21 margin-bottom: 0.5em;
22 }
23 .navigation a {
24 color: #770000;
25 }
26 .navigation a:visited {
27 color: #550000;
28 }
29 .navigation .title {
30 font-size: 200%;
31 }
32 </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">
33
34
35
36typedef <a href="libxml-HTMLparser.html#htmlParserCtxt">htmlParserCtxt</a>;
37typedef <a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a>;
38typedef <a href="libxml-HTMLparser.html#htmlParserNodeInfo">htmlParserNodeInfo</a>;
39typedef <a href="libxml-HTMLparser.html#htmlSAXHandler">htmlSAXHandler</a>;
40typedef <a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a>;
41typedef <a href="libxml-HTMLparser.html#htmlParserInput">htmlParserInput</a>;
42typedef <a href="libxml-HTMLparser.html#htmlParserInputPtr">htmlParserInputPtr</a>;
43typedef <a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a>;
44typedef <a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a>;
45struct <a href="libxml-HTMLparser.html#htmlElemDesc">htmlElemDesc</a>;
46typedef <a href="libxml-HTMLparser.html#htmlElemDescPtr">htmlElemDescPtr</a>;
47struct <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>;
48typedef <a href="libxml-HTMLparser.html#htmlEntityDescPtr">htmlEntityDescPtr</a>;
49const <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);
50const <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);
51const <a href="libxml-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a>* <a href="libxml-HTMLparser.html#htmlEntityValueLookup">htmlEntityValueLookup</a> (unsigned int value);
52int <a href="libxml-HTMLparser.html#htmlIsAutoClosed">htmlIsAutoClosed</a> (<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc,
53 <a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);
54int <a href="libxml-HTMLparser.html#htmlAutoCloseTag">htmlAutoCloseTag</a> (<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc,
55 const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name,
56 <a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);
57const <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,
58 <a href="libxml-tree.html#xmlChar">xmlChar</a> **str);
59int <a href="libxml-HTMLparser.html#htmlParseCharRef">htmlParseCharRef</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
60void <a href="libxml-HTMLparser.html#htmlParseElement">htmlParseElement</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
61<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="libxml-HTMLparser.html#htmlCreateMemoryParserCtxt">htmlCreateMemoryParserCtxt</a>
62 (const char *buffer,
63 int size);
64int <a href="libxml-HTMLparser.html#htmlParseDocument">htmlParseDocument</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
65<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,
66 const char *encoding,
67 <a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
68 void *userData);
69<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,
70 const char *encoding);
71<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="libxml-HTMLparser.html#htmlSAXParseFile">htmlSAXParseFile</a> (const char *filename,
72 const char *encoding,
73 <a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
74 void *userData);
75<a href="libxml-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="libxml-HTMLparser.html#htmlParseFile">htmlParseFile</a> (const char *filename,
76 const char *encoding);
77int <a href="libxml-HTMLparser.html#UTF8ToHtml">UTF8ToHtml</a> (unsigned char *out,
78 int *outlen,
79 unsigned char *in,
80 int *inlen);
81int <a href="libxml-HTMLparser.html#htmlEncodeEntities">htmlEncodeEntities</a> (unsigned char *out,
82 int *outlen,
83 unsigned char *in,
84 int *inlen,
85 int quoteChar);
86int <a href="libxml-HTMLparser.html#htmlIsScriptAttribute">htmlIsScriptAttribute</a> (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name);
87int <a href="libxml-HTMLparser.html#htmlHandleOmittedElem">htmlHandleOmittedElem</a> (int val);
88void <a href="libxml-HTMLparser.html#htmlFreeParserCtxt">htmlFreeParserCtxt</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
89<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,
90 void *user_data,
91 const char *chunk,
92 int size,
93 const char *filename,
94 <a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);
95int <a href="libxml-HTMLparser.html#htmlParseChunk">htmlParseChunk</a> (<a href="libxml-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt,
96 const char *chunk,
97 int size,
98 int terminate);
99</pre></div><div class="refsect1" lang="en"><h2>Description</h2><p>
100
101</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;
102</pre><p>
103
104</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;
105</pre><p>
106
107</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;
108</pre><p>
109
110</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;
111</pre><p>
112
113</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;
114</pre><p>
115
116</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;
117</pre><p>
118
119</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;
120</pre><p>
121
122</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;
123</pre><p>
124
125</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;
126</pre><p>
127
128</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 {
129 const char *name; /* The tag name */
130 char startTag; /* Whether the start tag can be implied */
131 char endTag; /* Whether the end tag can be implied */
132 char saveEndTag; /* Whether the end tag should be saved */
133 char empty; /* Is this an empty element ? */
134 char depr; /* Is this a deprecated element ? */
135 char dtd; /* 1: only in Loose DTD, 2: only Frameset one */
136 char isinline; /* is this a block 0 or inline 1 element */
137 const char *desc; /* the description */
138
139/* NRK Jan.2003
140 * New fields encapsulating HTML structure
141 *
142 * Bugs:
143 * This is a very limited representation. It fails to tell us when
144 * an element *requires* subelements (we only have whether they're
145 * allowed or not), and it doesn't tell us where CDATA and PCDATA
146 * are allowed. Some element relationships are not fully represented:
147 * these are flagged with the word MODIFIER
148 */
149 const char** subelts; /* allowed sub-elements of this element */
150 const char* defaultsubelt; /* subelement for suggested auto-repair
151 if necessary or NULL */
152 const char** attrs_opt; /* Optional Attributes */
153 const char** attrs_depr; /* Additional deprecated attributes */
154 const char** attrs_req; /* Required attributes */
155};
156</pre><p>
157
158</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;
159</pre><p>
160
161</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 {
162 unsigned int value; /* the UNICODE value for the character */
163 const char *name; /* The entity name */
164 const char *desc; /* the description */
165};
166</pre><p>
167
168</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;
169</pre><p>
170
171</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>
172Lookup the HTML tag in the ElementTable</p><p>
173
174</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
175</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.
176</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>
177Lookup the given entity in EntitiesTable
178</p><p>
179TODO: the linear scan is really ugly, an hash table is really needed.</p><p>
180
181</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
182</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the associated htmlEntityDescPtr if found, NULL otherwise.
183</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>
184Lookup the given entity in EntitiesTable
185</p><p>
186TODO: the linear scan is really ugly, an hash table is really needed.</p><p>
187
188</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
189</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the associated htmlEntityDescPtr if found, NULL otherwise.
190</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,
191 <a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);</pre><p>
192The HTML DTD allows a tag to implicitly close other tags.
193The list is kept in htmlStartClose array. This function checks
194if a tag is autoclosed by one of it's child</p><p>
195
196</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
197</td></tr><tr><td><span class="term"><i><tt>elem</tt></i> :</span></td><td> the HTML element
198</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>1 if autoclosed, 0 otherwise
199</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,
200 const <a href="libxml-tree.html#xmlChar">xmlChar</a> *name,
201 <a href="libxml-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);</pre><p>
202The HTML DTD allows a tag to implicitly close other tags.
203The list is kept in htmlStartClose array. This function checks
204if the element or one of it's children would autoclose the
205given tag.</p><p>
206
207</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
208</td></tr><tr><td><span class="term"><i><tt>name</tt></i> :</span></td><td> The tag name
209</td></tr><tr><td><span class="term"><i><tt>elem</tt></i> :</span></td><td> the HTML element
210</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>1 if autoclose, 0 otherwise
211</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,
212 <a href="libxml-tree.html#xmlChar">xmlChar</a> **str);</pre><p>
213parse an HTML ENTITY references
214</p><p>
215[68] EntityRef ::= '&amp;' Name ';'</p><p>
216
217</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
218</td></tr><tr><td><span class="term"><i><tt>str</tt></i> :</span></td><td> location to store the entity name
219</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,
220 if non-NULL *str will have to be freed by the caller.
221</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>
222parse Reference declarations
223</p><p>
224[66] CharRef ::= '&amp;#' [0-9]+ ';' |
225 '&amp;<GTKDOCLINK xmlns="http://www.w3.org/TR/xhtml1/transitional" HREF="x">x</GTKDOCLINK>' [0-9a-fA-F]+ ';'</p><p>
226
227</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
228</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the value parsed (as an int)
229</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>
230parse an HTML element, this is highly recursive
231</p><p>
232[39] element ::= EmptyElemTag | STag content ETag
233</p><p>
234[41] Attribute ::= Name Eq AttValue</p><p>
235
236</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
237</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
238 (const char *buffer,
239 int size);</pre><p>
240Create a parser context for an HTML in-memory document.</p><p>
241
242</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
243</td></tr><tr><td><span class="term"><i><tt>size</tt></i> :</span></td><td> the size of the array
244</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the new parser context or NULL
245</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>
246parse an HTML document (and build a tree if using the standard SAX
247interface).</p><p>
248
249</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
250</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
251 as a result of the parsing.
252</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,
253 const char *encoding,
254 <a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
255 void *userData);</pre><p>
256Parse an HTML in-memory document. If sax is not NULL, use the SAX callbacks
257to handle parse events. If sax is NULL, fallback to the default DOM
258behavior and return a tree.</p><p>
259
260</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
261</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
262</td></tr><tr><td><span class="term"><i><tt>sax</tt></i> :</span></td><td> the SAX handler block
263</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.
264</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
265 not well formed.
266</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,
267 const char *encoding);</pre><p>
268parse an HTML in-memory document and build a tree.</p><p>
269
270</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
271</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
272</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the resulting document tree
273</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,
274 const char *encoding,
275 <a href="libxml-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax,
276 void *userData);</pre><p>
277parse an HTML file and build a tree. Automatic support for ZLIB/Compress
278compressed document is provided by default if found at compile-time.
279It use the given SAX function block to handle the parsing callback.
280If sax is NULL, fallback to the default DOM tree building routines.</p><p>
281
282</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
283</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
284</td></tr><tr><td><span class="term"><i><tt>sax</tt></i> :</span></td><td> the SAX handler block
285</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.
286</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
287 not well formed.
288</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,
289 const char *encoding);</pre><p>
290parse an HTML file and build a tree. Automatic support for ZLIB/Compress
291compressed document is provided by default if found at compile-time.</p><p>
292
293</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
294</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
295</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the resulting document tree
296</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,
297 int *outlen,
298 unsigned char *in,
299 int *inlen);</pre><p>
300Take a block of UTF-8 chars in and try to convert it to an ASCII
301plus HTML entities block of chars out.</p><p>
302
303</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
304</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i> :</span></td><td> the length of <i><tt>out</tt></i>
305</td></tr><tr><td><span class="term"><i><tt>in</tt></i> :</span></td><td> a pointer to an array of UTF-8 chars
306</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i> :</span></td><td> the length of <i><tt>in</tt></i>
307</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
308The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
309 as the return value is positive, else unpredictable.
310The value of <i><tt>outlen</tt></i> after return is the number of octets consumed.
311</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,
312 int *outlen,
313 unsigned char *in,
314 int *inlen,
315 int quoteChar);</pre><p>
316Take a block of UTF-8 chars in and try to convert it to an ASCII
317plus HTML entities block of chars out.</p><p>
318
319</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
320</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i> :</span></td><td> the length of <i><tt>out</tt></i>
321</td></tr><tr><td><span class="term"><i><tt>in</tt></i> :</span></td><td> a pointer to an array of UTF-8 chars
322</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i> :</span></td><td> the length of <i><tt>in</tt></i>
323</td></tr><tr><td><span class="term"><i><tt>quoteChar</tt></i> :</span></td><td> the quote character to escape (' or &quot;) or zero.
324</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
325The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
326 as the return value is positive, else unpredictable.
327The value of <i><tt>outlen</tt></i> after return is the number of octets consumed.
328</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>
329Check if an attribute is of content type Script</p><p>
330
331</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
332</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
333</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>
334Set and return the previous value for handling HTML omitted tags.</p><p>
335
336</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
337</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.
338</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>
339Free all the memory used by a parser context. However the parsed
340document in ctxt-&gt;myDoc is not freed.</p><p>
341
342</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
343</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,
344 void *user_data,
345 const char *chunk,
346 int size,
347 const char *filename,
348 <a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);</pre><p>
349Create a parser context for using the HTML parser in push mode
350The value of <i><tt>filename</tt></i> is used for fetching external entities
351and error/warning reports.</p><p>
352
353</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
354</td></tr><tr><td><span class="term"><i><tt>user_data</tt></i> :</span></td><td> The user data returned on SAX callbacks
355</td></tr><tr><td><span class="term"><i><tt>chunk</tt></i> :</span></td><td> a pointer to an array of chars
356</td></tr><tr><td><span class="term"><i><tt>size</tt></i> :</span></td><td> number of chars in the array
357</td></tr><tr><td><span class="term"><i><tt>filename</tt></i> :</span></td><td> an optional file name or URI
358</td></tr><tr><td><span class="term"><i><tt>enc</tt></i> :</span></td><td> an optional encoding
359</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the new parser context or NULL
360</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,
361 const char *chunk,
362 int size,
363 int terminate);</pre><p>
364Parse a Chunk of memory</p><p>
365
366</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
367</td></tr><tr><td><span class="term"><i><tt>chunk</tt></i> :</span></td><td> an char array
368</td></tr><tr><td><span class="term"><i><tt>size</tt></i> :</span></td><td> the size in byte of the chunk
369</td></tr><tr><td><span class="term"><i><tt>terminate</tt></i> :</span></td><td> last chunk indicator
370</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>zero if no error, the xmlParserErrors otherwise.
371</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>