Ana Sayfa Keşfet Yardım
Giriş Yap
jmcaricand
/
libopc
1
0
Çatalla 0
Dosyalar Sorunlar 0 Değişiklik İstekleri 0 Wiki
Dal: master
Dallar Biçim İmleri
libopc
/
third_party
/
libxml2-2.7.7
/
doc
/
devhelp
/
libxml2-HTMLparser.html

libxml2-HTMLparser.html 57 KB
Kalıcı Bağlantı Geçmiş Ham

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371 
  1. <?xml version="1.0" encoding="UTF-8"?>
    2. 

  2. <html>
    3. 

  3.   <head>
    4. 

  4.     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
    5. 

  5.     <title>HTMLparser: interface for an HTML 4.0 non-verifying parser</title>
    6. 

  6.     <meta name="generator" content="Libxml2 devhelp stylesheet"/>
    7. 

  7.     <link rel="start" href="index.html" title="libxml2 Reference Manual"/>
    8. 

  8.     <link rel="up" href="general.html" title="API"/>
    9. 

  9.     <link rel="stylesheet" href="style.css" type="text/css"/>
    10. 

  10.     <link rel="chapter" href="general.html" title="API"/>
    11. 

  11.   </head>
    12. 

  12.   <body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
    13. 

  13.     <table class="navigation" width="100%" summary="Navigation header" cellpadding="2" cellspacing="2">
    14. 

  14.       <tr valign="middle">
    15. 

  15.         <td>
    16. 

  16.           <a accesskey="p" href="libxml2-DOCBparser.html">
    17. 

  17.             <img src="left.png" width="24" height="24" border="0" alt="Prev"/>
    18. 

  18.           </a>
    19. 

  19.         </td>
    20. 

  20.         <td>
    21. 

  21.           <a accesskey="u" href="general.html">
    22. 

  22.             <img src="up.png" width="24" height="24" border="0" alt="Up"/>
    23. 

  23.           </a>
    24. 

  24.         </td>
    25. 

  25.         <td>
    26. 

  26.           <a accesskey="h" href="index.html">
    27. 

  27.             <img src="home.png" width="24" height="24" border="0" alt="Home"/>
    28. 

  28.           </a>
    29. 

  29.         </td>
    30. 

  30.         <td>
    31. 

  31.           <a accesskey="n" href="libxml2-HTMLtree.html">
    32. 

  32.             <img src="right.png" width="24" height="24" border="0" alt="Next"/>
    33. 

  33.           </a>
    34. 

  34.         </td>
    35. 

  35.         <th width="100%" align="center">libxml2 Reference Manual</th>
    36. 

  36.       </tr>
    37. 

  37.     </table>
    38. 

  38.     <h2>
    39. 

  39.       <span class="refentrytitle">HTMLparser</span>
    40. 

  40.     </h2>
    41. 

  41.     <p>HTMLparser - interface for an HTML 4.0 non-verifying parser</p>
    42. 

  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. 

  43.     <p>Author(s): Daniel Veillard </p>
    44. 

  44.     <div class="refsynopsisdiv">
    45. 

  45.       <h2>Synopsis</h2>
    46. 

  46.       <pre class="synopsis">#define <a href="#htmlDefaultSubelement">htmlDefaultSubelement</a>(elt);
    47. 

  47. #define <a href="#htmlElementAllowedHereDesc">htmlElementAllowedHereDesc</a>(parent, elt);
    48. 

  48. #define <a href="#htmlRequiredAttrs">htmlRequiredAttrs</a>(elt);
    49. 

  49. typedef <a href="libxml2-parser.html#xmlParserNodeInfo">xmlParserNodeInfo</a> <a href="#htmlParserNodeInfo">htmlParserNodeInfo</a>;
    50. 

  50. typedef <a href="libxml2-tree.html#xmlParserInput">xmlParserInput</a> <a href="#htmlParserInput">htmlParserInput</a>;
    51. 

  51. typedef <a href="libxml2-tree.html#xmlParserCtxtPtr">xmlParserCtxtPtr</a> <a href="#htmlParserCtxtPtr">htmlParserCtxtPtr</a>;
    52. 

  52. typedef struct _htmlEntityDesc <a href="#htmlEntityDesc">htmlEntityDesc</a>;
    53. 

  53. typedef <a href="libxml2-tree.html#xmlDocPtr">xmlDocPtr</a> <a href="#htmlDocPtr">htmlDocPtr</a>;
    54. 

  54. typedef <a href="libxml2-tree.html#xmlSAXHandlerPtr">xmlSAXHandlerPtr</a> <a href="#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a>;
    55. 

  55. typedef enum <a href="#htmlStatus">htmlStatus</a>;
    56. 

  56. typedef <a href="libxml2-tree.html#xmlNodePtr">xmlNodePtr</a> <a href="#htmlNodePtr">htmlNodePtr</a>;
    57. 

  57. typedef <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * <a href="#htmlElemDescPtr">htmlElemDescPtr</a>;
    58. 

  58. typedef struct _htmlElemDesc <a href="#htmlElemDesc">htmlElemDesc</a>;
    59. 

  59. typedef <a href="libxml2-tree.html#xmlSAXHandler">xmlSAXHandler</a> <a href="#htmlSAXHandler">htmlSAXHandler</a>;
    60. 

  60. typedef <a href="libxml2-tree.html#xmlParserInputPtr">xmlParserInputPtr</a> <a href="#htmlParserInputPtr">htmlParserInputPtr</a>;
    61. 

  61. typedef enum <a href="#htmlParserOption">htmlParserOption</a>;
    62. 

  62. typedef <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityDescPtr">htmlEntityDescPtr</a>;
    63. 

  63. typedef <a href="libxml2-tree.html#xmlParserCtxt">xmlParserCtxt</a> <a href="#htmlParserCtxt">htmlParserCtxt</a>;
    64. 

  64. int	<a href="#htmlIsScriptAttribute">htmlIsScriptAttribute</a>		(const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name);
    65. 

  65. int	<a href="#htmlHandleOmittedElem">htmlHandleOmittedElem</a>		(int val);
    66. 

  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. 

  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. 

  68. <a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a>	<a href="#htmlParseFile">htmlParseFile</a>		(const char * filename, <br/>					 const char * encoding);
    69. 

  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. 

  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. 

  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. 

  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. 

  73. <a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a>	<a href="#htmlCreateMemoryParserCtxt">htmlCreateMemoryParserCtxt</a>	(const char * buffer, <br/>							 int size);
    74. 

  74. void	<a href="#htmlCtxtReset">htmlCtxtReset</a>			(<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
    75. 

  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. 

  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. 

  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. 

  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. 

  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. 

  80. int	<a href="#htmlParseCharRef">htmlParseCharRef</a>		(<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
    81. 

  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. 

  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. 

  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. 

  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. 

  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. 

  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. 

  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. 

  88. const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> *	<a href="#htmlEntityValueLookup">htmlEntityValueLookup</a>	(unsigned int value);
    89. 

  89. void	<a href="#htmlParseElement">htmlParseElement</a>		(<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
    90. 

  90. int	<a href="#UTF8ToHtml">UTF8ToHtml</a>			(unsigned char * out, <br/>					 int * outlen, <br/>					 const unsigned char * in, <br/>					 int * inlen);
    91. 

  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. 

  92. void	<a href="#htmlFreeParserCtxt">htmlFreeParserCtxt</a>		(<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
    93. 

  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. 

  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. 

  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. 

  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. 

  97. int	<a href="#htmlParseDocument">htmlParseDocument</a>		(<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);
    98. 

  98. <a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a>	<a href="#htmlNewParserCtxt">htmlNewParserCtxt</a>	(void);
    99. 

  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. 

  100. int	<a href="#htmlCtxtUseOptions">htmlCtxtUseOptions</a>		(<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/>					 int options);
    101. 

  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);
    102. 

  102. </pre>
    103. 

  103.     </div>
    104. 

  104.     <div class="refsect1" lang="en">
    105. 

  105.       <h2>Description</h2>
    106. 

  106.     </div>
    107. 

  107.     <div class="refsect1" lang="en">
    108. 

  108.       <h2>Details</h2>
    109. 

  109.       <div class="refsect2" lang="en">
    110. 

  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. 

  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>
    112. 

  112. </div>
    113. 

  113.         <hr/>
    114. 

  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. 

  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>
    116. 

  116. </div>
    117. 

  117.         <hr/>
    118. 

  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. 

  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>
    120. 

  120. </div>
    121. 

  121.         <hr/>
    122. 

  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;
    123. 

  123. </pre><p/>
    124. 

  124. </div>
    125. 

  125.         <hr/>
    126. 

  126.         <div class="refsect2" lang="en"><h3><a name="htmlElemDesc">Structure </a>htmlElemDesc</h3><pre class="programlisting">struct _htmlElemDesc {
    127. 

  127.     const char *	name	: The tag name
    128. 

  128.     char	startTag	: Whether the start tag can be implied
    129. 

  129.     char	endTag	: Whether the end tag can be implied
    130. 

  130.     char	saveEndTag	: Whether the end tag should be saved
    131. 

  131.     char	empty	: Is this an empty element ?
    132. 

  132.     char	depr	: Is this a deprecated element ?
    133. 

  133.     char	dtd	: 1: only in Loose DTD, 2: only Frameset one
    134. 

  134.     char	isinline	: is this a block 0 or inline 1 element
    135. 

  135.     const char *	desc	: the description NRK Jan.2003 * New fields encapsulating HTML structur
    136. 

  136.     const char **	subelts	: allowed sub-elements of this element
    137. 

  137.     const char *	defaultsubelt	: subelement for suggested auto-repair if necessary or NULL
    138. 

  138.     const char **	attrs_opt	: Optional Attributes
    139. 

  139.     const char **	attrs_depr	: Additional deprecated attributes
    140. 

  140.     const char **	attrs_req	: Required attributes
    141. 

  141. } htmlElemDesc;
    142. 

  142. </pre><p/>
    143. 

  143. </div>
    144. 

  144.         <hr/>
    145. 

  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;
    146. 

  146. </pre><p/>
    147. 

  147. </div>
    148. 

  148.         <hr/>
    149. 

  149.         <div class="refsect2" lang="en"><h3><a name="htmlEntityDesc">Structure </a>htmlEntityDesc</h3><pre class="programlisting">struct _htmlEntityDesc {
    150. 

  150.     unsigned int	value	: the UNICODE value for the character
    151. 

  151.     const char *	name	: The entity name
    152. 

  152.     const char *	desc	: the description
    153. 

  153. } htmlEntityDesc;
    154. 

  154. </pre><p/>
    155. 

  155. </div>
    156. 

  156.         <hr/>
    157. 

  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;
    158. 

  158. </pre><p/>
    159. 

  159. </div>
    160. 

  160.         <hr/>
    161. 

  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;
    162. 

  162. </pre><p/>
    163. 

  163. </div>
    164. 

  164.         <hr/>
    165. 

  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;
    166. 

  166. </pre><p/>
    167. 

  167. </div>
    168. 

  168.         <hr/>
    169. 

  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;
    170. 

  170. </pre><p/>
    171. 

  171. </div>
    172. 

  172.         <hr/>
    173. 

  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;
    174. 

  174. </pre><p/>
    175. 

  175. </div>
    176. 

  176.         <hr/>
    177. 

  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;
    178. 

  178. </pre><p/>
    179. 

  179. </div>
    180. 

  180.         <hr/>
    181. 

  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;
    182. 

  182. </pre><p/>
    183. 

  183. </div>
    184. 

  184.         <hr/>
    185. 

  185.         <div class="refsect2" lang="en"><h3><a name="htmlParserOption">Enum </a>htmlParserOption</h3><pre class="programlisting">enum <a href="#htmlParserOption">htmlParserOption</a> {
    186. 

  186.     <a name="HTML_PARSE_RECOVER">HTML_PARSE_RECOVER</a> = 1 /* Relaxed parsing */
    187. 

  187.     <a name="HTML_PARSE_NOERROR">HTML_PARSE_NOERROR</a> = 32 /* suppress error reports */
    188. 

  188.     <a name="HTML_PARSE_NOWARNING">HTML_PARSE_NOWARNING</a> = 64 /* suppress warning reports */
    189. 

  189.     <a name="HTML_PARSE_PEDANTIC">HTML_PARSE_PEDANTIC</a> = 128 /* pedantic error reporting */
    190. 

  190.     <a name="HTML_PARSE_NOBLANKS">HTML_PARSE_NOBLANKS</a> = 256 /* remove blank nodes */
    191. 

  191.     <a name="HTML_PARSE_NONET">HTML_PARSE_NONET</a> = 2048 /* Forbid network access */
    192. 

  192.     <a name="HTML_PARSE_NOIMPLIED">HTML_PARSE_NOIMPLIED</a> = 8192 /* Do not add implied html/body... elements */
    193. 

  193.     <a name="HTML_PARSE_COMPACT">HTML_PARSE_COMPACT</a> = 65536 /*  compact small text nodes */
    194. 

  194. };
    195. 

  195. </pre><p/>
    196. 

  196. </div>
    197. 

  197.         <hr/>
    198. 

  198.         <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;
    199. 

  199. </pre><p/>
    200. 

  200. </div>
    201. 

  201.         <hr/>
    202. 

  202.         <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;
    203. 

  203. </pre><p/>
    204. 

  204. </div>
    205. 

  205.         <hr/>
    206. 

  206.         <div class="refsect2" lang="en"><h3><a name="htmlStatus">Enum </a>htmlStatus</h3><pre class="programlisting">enum <a href="#htmlStatus">htmlStatus</a> {
    207. 

  207.     <a name="HTML_NA">HTML_NA</a> = 0 /* something we don't check at all */
    208. 

  208.     <a name="HTML_INVALID">HTML_INVALID</a> = 1
    209. 

  209.     <a name="HTML_DEPRECATED">HTML_DEPRECATED</a> = 2
    210. 

  210.     <a name="HTML_VALID">HTML_VALID</a> = 4
    211. 

  211.     <a name="HTML_REQUIRED">HTML_REQUIRED</a> = 12 /*  VALID bit set so ( &amp; HTML_VALID ) is TRUE */
    212. 

  212. };
    213. 

  213. </pre><p/>
    214. 

  214. </div>
    215. 

  215.         <hr/>
    216. 

  216.         <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/>
    217. 

  217. </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>
    218. 

  218. <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. 

  219.         <hr/>
    220. 

  220.         <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/>
    221. 

  221. </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>
    222. 

  222. <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. 

  223.         <hr/>
    224. 

  224.         <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/>
    225. 

  225. </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>
    226. 

  226. <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. 

  227.         <hr/>
    228. 

  228.         <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/>
    229. 

  229. </pre><p>Create a parser context for an HTML in-memory document.</p>
    230. 

  230. <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. 

  231.         <hr/>
    232. 

  232.         <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/>
    233. 

  233. </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>
    234. 

  234. <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. 

  235.         <hr/>
    236. 

  236.         <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/>
    237. 

  237. </pre><p>parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context</p>
    238. 

  238. <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. 

  239.         <hr/>
    240. 

  240.         <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/>
    241. 

  241. </pre><p>parse an XML from a file descriptor and build a tree. This reuses the existing @ctxt parser context</p>
    242. 

  242. <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. 

  243.         <hr/>
    244. 

  244.         <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/>
    245. 

  245. </pre><p>parse an XML file from the filesystem or the network. This reuses the existing @ctxt parser context</p>
    246. 

  246. <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. 

  247.         <hr/>
    248. 

  248.         <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/>
    249. 

  249. </pre><p>parse an HTML document from I/O functions and source and build a tree. This reuses the existing @ctxt parser context</p>
    250. 

  250. <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. 

  251.         <hr/>
    252. 

  252.         <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/>
    253. 

  253. </pre><p>parse an XML in-memory document and build a tree. This reuses the existing @ctxt parser context</p>
    254. 

  254. <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. 

  255.         <hr/>
    256. 

  256.         <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/>
    257. 

  257. </pre><p>Reset a parser context</p>
    258. 

  258. <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. 

  259.         <hr/>
    260. 

  260.         <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/>
    261. 

  261. </pre><p>Applies the options to the parser context</p>
    262. 

  262. <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. 

  263.         <hr/>
    264. 

  264.         <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/>
    265. 

  265. </pre><p>Checks whether an HTML element may be a direct child of a parent element. Note - doesn't check for deprecated elements</p>
    266. 

  266. <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. 

  267.         <hr/>
    268. 

  268.         <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/>
    269. 

  269. </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>
    270. 

  270. <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. 

  271.         <hr/>
    272. 

  272.         <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/>
    273. 

  273. </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>
    274. 

  274. <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. 

  275.         <hr/>
    276. 

  276.         <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/>
    277. 

  277. </pre><p>Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.</p>
    278. 

  278. <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. 

  279.         <hr/>
    280. 

  280.         <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/>
    281. 

  281. </pre><p>Lookup the given entity in EntitiesTable TODO: the linear scan is really ugly, an hash table is really needed.</p>
    282. 

  282. <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. 

  283.         <hr/>
    284. 

  284.         <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/>
    285. 

  285. </pre><p>Free all the memory used by a parser context. However the parsed document in ctxt-&gt;myDoc is not freed.</p>
    286. 

  286. <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. 

  287.         <hr/>
    288. 

  288.         <div class="refsect2" lang="en"><h3><a name="htmlHandleOmittedElem"/>htmlHandleOmittedElem ()</h3><pre class="programlisting">int	htmlHandleOmittedElem		(int val)<br/>
    289. 

  289. </pre><p>Set and return the previous value for handling HTML omitted tags.</p>
    290. 

  290. <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. 

  291.         <hr/>
    292. 

  292.         <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/>
    293. 

  293. </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>
    294. 

  294. <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. 

  295.         <hr/>
    296. 

  296.         <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/>
    297. 

  297. </pre><p>Check if an <a href="libxml2-SAX.html#attribute">attribute</a> is of content type Script</p>
    298. 

  298. <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. 

  299.         <hr/>
    300. 

  300.         <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/>
    301. 

  301. </pre><p>Allocate and initialize a new parser context.</p>
    302. 

  302. <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. 

  303.         <hr/>
    304. 

  304.         <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/>
    305. 

  305. </pre><p>Checks whether the tree node is valid. Experimental (the author only uses the HTML enhancements in a SAX parser)</p>
    306. 

  306. <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. 

  307.         <hr/>
    308. 

  308.         <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/>
    309. 

  309. </pre><p>parse Reference declarations [66] CharRef ::= '&amp;#' [0-9]+ ';' | '&amp;#x' [0-9a-fA-F]+ ';'</p>
    310. 

  310. <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. 

  311.         <hr/>
    312. 

  312.         <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/>
    313. 

  313. </pre><p>Parse a Chunk of memory</p>
    314. 

  314. <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. 

  315.         <hr/>
    316. 

  316.         <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/>
    317. 

  317. </pre><p>parse an HTML in-memory document and build a tree.</p>
    318. 

  318. <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. 

  319.         <hr/>
    320. 

  320.         <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/>
    321. 

  321. </pre><p>parse an HTML document (and build a tree if using the standard SAX interface).</p>
    322. 

  322. <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. 

  323.         <hr/>
    324. 

  324.         <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/>
    325. 

  325. </pre><p>parse an HTML element, this is highly recursive this is kept for compatibility with previous code versions [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue</p>
    326. 

  326. <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. 

  327.         <hr/>
    328. 

  328.         <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/>
    329. 

  329. </pre><p>parse an HTML ENTITY references [68] EntityRef ::= '&amp;' Name ';'</p>
    330. 

  330. <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. 

  331.         <hr/>
    332. 

  332.         <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/>
    333. 

  333. </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>
    334. 

  334. <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. 

  335.         <hr/>
    336. 

  336.         <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/>
    337. 

  337. </pre><p>parse an XML in-memory document and build a tree.</p>
    338. 

  338. <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. 

  339.         <hr/>
    340. 

  340.         <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/>
    341. 

  341. </pre><p>parse an XML from a file descriptor and build a tree.</p>
    342. 

  342. <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. 

  343.         <hr/>
    344. 

  344.         <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/>
    345. 

  345. </pre><p>parse an XML file from the filesystem or the network.</p>
    346. 

  346. <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. 

  347.         <hr/>
    348. 

  348.         <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/>
    349. 

  349. </pre><p>parse an HTML document from I/O functions and source and build a tree.</p>
    350. 

  350. <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. 

  351.         <hr/>
    352. 

  352.         <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/>
    353. 

  353. </pre><p>parse an XML in-memory document and build a tree.</p>
    354. 

  354. <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. 

  355.         <hr/>
    356. 

  356.         <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/>
    357. 

  357. </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>
    358. 

  358. <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. 

  359.         <hr/>
    360. 

  360.         <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/>
    361. 

  361. </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>
    362. 

  362. <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. 

  363.         <hr/>
    364. 

  364.         <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/>
    365. 

  365. </pre><p>Lookup the HTML tag in the ElementTable</p>
    366. 

  366. <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>
    367. 

  367.         <hr/>
    368. 

  368.       </div>
    369. 

  369.     </div>
    370. 

  370.   </body>
    371. 

  371. </html>
    372.