| <HTML |
| ><HEAD |
| ><TITLE |
| >HTMLparser</TITLE |
| ><META |
| NAME="GENERATOR" |
| CONTENT="Modular DocBook HTML Stylesheet Version 1.33"><LINK |
| REL="HOME" |
| TITLE="Gnome XML Library Reference Manual" |
| HREF="book1.html"><LINK |
| REL="UP" |
| TITLE="Libxml Library Reference" |
| HREF="libxml-lib.html"><LINK |
| REL="PREVIOUS" |
| TITLE="xml-error" |
| HREF="gnome-xml-xml-error.html"><LINK |
| REL="NEXT" |
| TITLE="HTMLtree" |
| HREF="gnome-xml-htmltree.html"></HEAD |
| ><BODY |
| BGCOLOR="#FFFFFF" |
| TEXT="#000000" |
| ><DIV |
| CLASS="NAVHEADER" |
| ><TABLE |
| WIDTH="100%" |
| BORDER="0" |
| BGCOLOR="#000000" |
| CELLPADDING="1" |
| CELLSPACING="0" |
| ><TR |
| ><TH |
| COLSPAN="4" |
| ALIGN="center" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="5" |
| >Gnome XML Library Reference Manual</FONT |
| ></TH |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#C00000" |
| ALIGN="left" |
| ><A |
| HREF="gnome-xml-xml-error.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| ><<< Previous Page</B |
| ></FONT |
| ></A |
| ></TD |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#0000C0" |
| ALIGN="center" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| ><A |
| HREF="book1.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >Home</B |
| ></FONT |
| ></A |
| ></B |
| ></FONT |
| ></TD |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#00C000" |
| ALIGN="center" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| ><A |
| HREF="libxml-lib.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >Up</B |
| ></FONT |
| ></A |
| ></B |
| ></FONT |
| ></TD |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#C00000" |
| ALIGN="right" |
| ><A |
| HREF="gnome-xml-htmltree.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >Next Page >>></B |
| ></FONT |
| ></A |
| ></TD |
| ></TR |
| ></TABLE |
| ></DIV |
| ><H1 |
| >HTMLparser</H1 |
| ><DIV |
| CLASS="REFNAMEDIV" |
| ><A |
| NAME="AEN8033" |
| ></A |
| ><H2 |
| >Name</H2 |
| >HTMLparser — </DIV |
| ><DIV |
| CLASS="REFSYNOPSISDIV" |
| ><A |
| NAME="AEN8036" |
| ></A |
| ><H2 |
| >Synopsis</H2 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="SYNOPSIS" |
| > |
| |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXT" |
| >htmlParserCtxt</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERNODEINFO" |
| >htmlParserNodeInfo</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLER" |
| >htmlSAXHandler</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERINPUT" |
| >htmlParserInput</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERINPUTPTR" |
| >htmlParserInputPtr</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLNODEPTR" |
| >htmlNodePtr</A |
| >; |
| struct <A |
| HREF="gnome-xml-htmlparser.html#HTMLELEMDESC" |
| >htmlElemDesc</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLELEMDESCPTR" |
| >htmlElemDescPtr</A |
| >; |
| struct <A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYDESC" |
| >htmlEntityDesc</A |
| >; |
| typedef <A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYDESCPTR" |
| >htmlEntityDescPtr</A |
| >; |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLELEMDESCPTR" |
| >htmlElemDescPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLTAGLOOKUP" |
| >htmlTagLookup</A |
| > (const <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *tag); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYDESCPTR" |
| >htmlEntityDescPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYLOOKUP" |
| >htmlEntityLookup</A |
| > (const <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *name); |
| int <A |
| HREF="gnome-xml-htmlparser.html#HTMLISAUTOCLOSED" |
| >htmlIsAutoClosed</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > doc, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLNODEPTR" |
| >htmlNodePtr</A |
| > elem); |
| int <A |
| HREF="gnome-xml-htmlparser.html#HTMLAUTOCLOSETAG" |
| >htmlAutoCloseTag</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > doc, |
| const <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *name, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLNODEPTR" |
| >htmlNodePtr</A |
| > elem); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYDESCPTR" |
| >htmlEntityDescPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSEENTITYREF" |
| >htmlParseEntityRef</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt, |
| <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > **str); |
| int <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSECHARREF" |
| >htmlParseCharRef</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt); |
| void <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSEELEMENT" |
| >htmlParseElement</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXPARSEDOC" |
| >htmlSAXParseDoc</A |
| > (<A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *cur, |
| const char *encoding, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| > sax, |
| void *userData); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSEDOC" |
| >htmlParseDoc</A |
| > (<A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *cur, |
| const char *encoding); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXPARSEFILE" |
| >htmlSAXParseFile</A |
| > (const char *filename, |
| const char *encoding, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| > sax, |
| void *userData); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSEFILE" |
| >htmlParseFile</A |
| > (const char *filename, |
| const char *encoding); |
| void <A |
| HREF="gnome-xml-htmlparser.html#HTMLFREEPARSERCTXT" |
| >htmlFreeParserCtxt</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt); |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > <A |
| HREF="gnome-xml-htmlparser.html#HTMLCREATEPUSHPARSERCTXT" |
| >htmlCreatePushParserCtxt</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| > sax, |
| void *user_data, |
| const char *chunk, |
| int size, |
| const char *filename, |
| <A |
| HREF="gnome-xml-encoding.html#XMLCHARENCODING" |
| >xmlCharEncoding</A |
| > enc); |
| int <A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSECHUNK" |
| >htmlParseChunk</A |
| > (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt, |
| const char *chunk, |
| int size, |
| int terminate);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ></DIV |
| ><DIV |
| CLASS="REFSECT1" |
| ><A |
| NAME="AEN8093" |
| ></A |
| ><H2 |
| >Description</H2 |
| ><P |
| ></P |
| ></DIV |
| ><DIV |
| CLASS="REFSECT1" |
| ><A |
| NAME="AEN8096" |
| ></A |
| ><H2 |
| >Details</H2 |
| ><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8098" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSERCTXT" |
| ></A |
| >htmlParserCtxt</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlParserCtxt htmlParserCtxt;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8103" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSERCTXTPTR" |
| ></A |
| >htmlParserCtxtPtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlParserCtxtPtr htmlParserCtxtPtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8108" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSERNODEINFO" |
| ></A |
| >htmlParserNodeInfo</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlParserNodeInfo htmlParserNodeInfo;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8113" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLSAXHANDLER" |
| ></A |
| >htmlSAXHandler</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlSAXHandler htmlSAXHandler;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8118" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLSAXHANDLERPTR" |
| ></A |
| >htmlSAXHandlerPtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlSAXHandlerPtr htmlSAXHandlerPtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8123" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSERINPUT" |
| ></A |
| >htmlParserInput</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlParserInput htmlParserInput;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8128" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSERINPUTPTR" |
| ></A |
| >htmlParserInputPtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlParserInputPtr htmlParserInputPtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8133" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLDOCPTR" |
| ></A |
| >htmlDocPtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlDocPtr htmlDocPtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8138" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLNODEPTR" |
| ></A |
| >htmlNodePtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef xmlNodePtr htmlNodePtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8143" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLELEMDESC" |
| ></A |
| >struct htmlElemDesc</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >struct htmlElemDesc { |
| const char *name; /* The tag name */ |
| int startTag; /* Whether the start tag can be implied */ |
| int endTag; /* Whether the end tag can be implied */ |
| int empty; /* Is this an empty element ? */ |
| int depr; /* Is this a deprecated element ? */ |
| int dtd; /* 1: only in Loose DTD, 2: only Frameset one */ |
| const char *desc; /* the description */ |
| };</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8148" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLELEMDESCPTR" |
| ></A |
| >htmlElemDescPtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef htmlElemDesc *htmlElemDescPtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8153" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLENTITYDESC" |
| ></A |
| >struct htmlEntityDesc</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >struct htmlEntityDesc { |
| int value; /* the UNICODE value for the character */ |
| const char *name; /* The entity name */ |
| const char *desc; /* the description */ |
| };</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8158" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLENTITYDESCPTR" |
| ></A |
| >htmlEntityDescPtr</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >typedef htmlEntityDesc *htmlEntityDescPtr;</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8163" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLTAGLOOKUP" |
| ></A |
| >htmlTagLookup ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLELEMDESCPTR" |
| >htmlElemDescPtr</A |
| > htmlTagLookup (const <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *tag);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >Lookup the HTML tag in the ElementTable</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >tag</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > The tag name</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the related htmlElemDescPtr or NULL if not found.</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8184" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLENTITYLOOKUP" |
| ></A |
| >htmlEntityLookup ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYDESCPTR" |
| >htmlEntityDescPtr</A |
| > htmlEntityLookup (const <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *name);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >Lookup the given entity in EntitiesTable</P |
| ><P |
| >TODO: the linear scan is really ugly, an hash table is really needed.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >name</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the entity name</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the associated htmlEntityDescPtr if found, NULL otherwise.</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8206" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLISAUTOCLOSED" |
| ></A |
| >htmlIsAutoClosed ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >int htmlIsAutoClosed (<A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > doc, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLNODEPTR" |
| >htmlNodePtr</A |
| > elem);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >The HTmL DtD allows a tag to implicitely close other tags. |
| The list is kept in htmlStartClose array. This function checks |
| if a tag is autoclosed by one of it's child</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >doc</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the HTML document</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >elem</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the HTML element</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >1 if autoclosed, 0 otherwise</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8231" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLAUTOCLOSETAG" |
| ></A |
| >htmlAutoCloseTag ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >int htmlAutoCloseTag (<A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > doc, |
| const <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *name, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLNODEPTR" |
| >htmlNodePtr</A |
| > elem);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >The HTmL DtD allows a tag to implicitely close other tags. |
| The list is kept in htmlStartClose array. This function checks |
| if the element or one of it's children would autoclose the |
| given tag.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >doc</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the HTML document</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >name</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > The tag name</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >elem</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the HTML element</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >1 if autoclose, 0 otherwise</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8261" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSEENTITYREF" |
| ></A |
| >htmlParseEntityRef ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLENTITYDESCPTR" |
| >htmlEntityDescPtr</A |
| > htmlParseEntityRef (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt, |
| <A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > **str);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse an HTML ENTITY references</P |
| ><P |
| >[68] EntityRef ::= '&' Name ';'</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >ctxt</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an HTML parser context</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >str</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > location to store the entity name</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the associated htmlEntityDescPtr if found, or NULL otherwise, |
| if non-NULL *str will have to be freed by the caller.</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8288" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSECHARREF" |
| ></A |
| >htmlParseCharRef ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >int htmlParseCharRef (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse Reference declarations</P |
| ><P |
| >[66] CharRef ::= '&#' [0-9]+ ';' | |
| '&<GTKDOCLINK |
| HREF="X" |
| >x</GTKDOCLINK |
| >' [0-9a-fA-F]+ ';'</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >ctxt</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an HTML parser context</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the value parsed (as an int)</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8310" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSEELEMENT" |
| ></A |
| >htmlParseElement ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >void htmlParseElement (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse an HTML element, this is highly recursive</P |
| ><P |
| >[39] element ::= EmptyElemTag | STag content ETag</P |
| ><P |
| >[41] Attribute ::= Name Eq AttValue</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >ctxt</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an HTML parser context</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8328" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLSAXPARSEDOC" |
| ></A |
| >htmlSAXParseDoc ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > htmlSAXParseDoc (<A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *cur, |
| const char *encoding, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| > sax, |
| void *userData);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse an HTML in-memory document and build a tree. |
| It use the given SAX function block to handle the parsing callback. |
| If sax is NULL, fallback to the default DOM tree building routines.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >cur</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a pointer to an array of xmlChar</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >encoding</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a free form C string describing the HTML document encoding, or NULL</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >sax</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the SAX handler block</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >userData</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > if using SAX, this pointer will be provided on callbacks. </TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the resulting document tree</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8362" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSEDOC" |
| ></A |
| >htmlParseDoc ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > htmlParseDoc (<A |
| HREF="gnome-xml-tree.html#XMLCHAR" |
| >xmlChar</A |
| > *cur, |
| const char *encoding);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse an HTML in-memory document and build a tree.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >cur</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a pointer to an array of xmlChar</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >encoding</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a free form C string describing the HTML document encoding, or NULL</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the resulting document tree</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8387" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLSAXPARSEFILE" |
| ></A |
| >htmlSAXParseFile ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > htmlSAXParseFile (const char *filename, |
| const char *encoding, |
| <A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| > sax, |
| void *userData);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse an HTML file and build a tree. Automatic support for ZLIB/Compress |
| compressed document is provided by default if found at compile-time. |
| It use the given SAX function block to handle the parsing callback. |
| If sax is NULL, fallback to the default DOM tree building routines.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >filename</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the filename</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >encoding</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a free form C string describing the HTML document encoding, or NULL</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >sax</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the SAX handler block</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >userData</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > if using SAX, this pointer will be provided on callbacks. </TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the resulting document tree</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8420" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSEFILE" |
| ></A |
| >htmlParseFile ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLDOCPTR" |
| >htmlDocPtr</A |
| > htmlParseFile (const char *filename, |
| const char *encoding);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >parse an HTML file and build a tree. Automatic support for ZLIB/Compress |
| compressed document is provided by default if found at compile-time.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >filename</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the filename</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >encoding</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a free form C string describing the HTML document encoding, or NULL</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the resulting document tree</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8444" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLFREEPARSERCTXT" |
| ></A |
| >htmlFreeParserCtxt ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >void htmlFreeParserCtxt (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >Free all the memory used by a parser context. However the parsed |
| document in ctxt->myDoc is not freed.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >ctxt</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an HTML parser context</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8460" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLCREATEPUSHPARSERCTXT" |
| ></A |
| >htmlCreatePushParserCtxt ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| ><A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > htmlCreatePushParserCtxt (<A |
| HREF="gnome-xml-htmlparser.html#HTMLSAXHANDLERPTR" |
| >htmlSAXHandlerPtr</A |
| > sax, |
| void *user_data, |
| const char *chunk, |
| int size, |
| const char *filename, |
| <A |
| HREF="gnome-xml-encoding.html#XMLCHARENCODING" |
| >xmlCharEncoding</A |
| > enc);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >Create a parser context for using the HTML parser in push mode |
| To allow content encoding detection, <TT |
| CLASS="PARAMETER" |
| ><I |
| >size</I |
| ></TT |
| > should be >= 4 |
| The value of <TT |
| CLASS="PARAMETER" |
| ><I |
| >filename</I |
| ></TT |
| > is used for fetching external entities |
| and error/warning reports.</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >sax</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a SAX handler</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >user_data</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > The user data returned on SAX callbacks</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >chunk</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > a pointer to an array of chars</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >size</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > number of chars in the array</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >filename</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an optional file name or URI</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >enc</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an optional encoding</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >the new parser context or NULL</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ><HR><DIV |
| CLASS="REFSECT2" |
| ><A |
| NAME="AEN8504" |
| ></A |
| ><H3 |
| ><A |
| NAME="HTMLPARSECHUNK" |
| ></A |
| >htmlParseChunk ()</H3 |
| ><TABLE |
| BORDER="0" |
| BGCOLOR="#D6E8FF" |
| WIDTH="100%" |
| CELLPADDING="6" |
| ><TR |
| ><TD |
| ><PRE |
| CLASS="PROGRAMLISTING" |
| >int htmlParseChunk (<A |
| HREF="gnome-xml-htmlparser.html#HTMLPARSERCTXTPTR" |
| >htmlParserCtxtPtr</A |
| > ctxt, |
| const char *chunk, |
| int size, |
| int terminate);</PRE |
| ></TD |
| ></TR |
| ></TABLE |
| ><P |
| >Parse a Chunk of memory</P |
| ><P |
| ></P |
| ><DIV |
| CLASS="INFORMALTABLE" |
| ><P |
| ></P |
| ><TABLE |
| BORDER="0" |
| WIDTH="100%" |
| BGCOLOR="#FFD0D0" |
| CELLSPACING="0" |
| CELLPADDING="4" |
| CLASS="CALSTABLE" |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >ctxt</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an XML parser context</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >chunk</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > an char array</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >size</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > the size in byte of the chunk</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><TT |
| CLASS="PARAMETER" |
| ><I |
| >terminate</I |
| ></TT |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| > last chunk indicator</TD |
| ></TR |
| ><TR |
| ><TD |
| WIDTH="20%" |
| ALIGN="RIGHT" |
| VALIGN="TOP" |
| ><I |
| CLASS="EMPHASIS" |
| >Returns</I |
| > :</TD |
| ><TD |
| WIDTH="80%" |
| ALIGN="LEFT" |
| VALIGN="TOP" |
| >zero if no error, the xmlParserErrors otherwise.</TD |
| ></TR |
| ></TABLE |
| ><P |
| ></P |
| ></DIV |
| ></DIV |
| ></DIV |
| ><DIV |
| CLASS="NAVFOOTER" |
| ><BR |
| CLEAR="all"><BR><TABLE |
| WIDTH="100%" |
| BORDER="0" |
| BGCOLOR="#000000" |
| CELLPADDING="1" |
| CELLSPACING="0" |
| ><TR |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#C00000" |
| ALIGN="left" |
| ><A |
| HREF="gnome-xml-xml-error.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| ><<< Previous Page</B |
| ></FONT |
| ></A |
| ></TD |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#0000C0" |
| ALIGN="center" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| ><A |
| HREF="book1.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >Home</B |
| ></FONT |
| ></A |
| ></B |
| ></FONT |
| ></TD |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#00C000" |
| ALIGN="center" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| ><A |
| HREF="libxml-lib.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >Up</B |
| ></FONT |
| ></A |
| ></B |
| ></FONT |
| ></TD |
| ><TD |
| WIDTH="25%" |
| BGCOLOR="#C00000" |
| ALIGN="right" |
| ><A |
| HREF="gnome-xml-htmltree.html" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >Next Page >>></B |
| ></FONT |
| ></A |
| ></TD |
| ></TR |
| ><TR |
| ><TD |
| COLSPAN="2" |
| ALIGN="left" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >xml-error</B |
| ></FONT |
| ></TD |
| ><TD |
| COLSPAN="2" |
| ALIGN="right" |
| ><FONT |
| COLOR="#FFFFFF" |
| SIZE="3" |
| ><B |
| >HTMLtree</B |
| ></FONT |
| ></TD |
| ></TR |
| ></TABLE |
| ></DIV |
| ></BODY |
| ></HTML |
| > |