--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/xml/xmlexpatparser/src/expat-1.95.5/doc_pub/reference.html Tue May 25 14:41:02 2010 +0300
@@ -0,0 +1,1770 @@
+<?xml version="1.0" encoding="iso-8859-1"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html>
+<head>
+<!-- Copyright 1999,2000 Clark Cooper <coopercc@netheaven.com>
+ All rights reserved.
+ This is free software. You may distribute or modify according to
+ the terms of the MIT/X License -->
+ <title>Expat XML Parser</title>
+ <meta name="author" content="Clark Cooper, coopercc@netheaven.com" />
+ <meta http-equiv="Content-Style-Type" content="text/css" />
+ <link href="style.css" rel="stylesheet" type="text/css" />
+</head>
+<body>
+<h1>Expat XML Parser</h1>
+
+<p>Expat is a library, written in C, for parsing XML documents. It's
+the underlying XML parser for the open source Mozilla project, Perl's
+<code>XML::Parser</code>, Python's <code>xml.parsers.expat</code>, and
+other open-source XML parsers.</p>
+
+<p>This library is the creation of James Clark, who's also given us
+groff (an nroff look-alike), Jade (an implemention of ISO's DSSSL
+stylesheet language for SGML), XP (a Java XML parser package), XT (a
+Java XSL engine). James was also the technical lead on the XML
+Working Group at W3C that produced the XML specification.</p>
+
+<p>This is free software, licensed under the <a
+href="../COPYING">MIT/X Consortium license</a>. You may download it
+from <a href="http://www.libexpat.org/">the Expat home page</a>.
+</p>
+
+<p>The bulk of this document was originally commissioned as an article by
+<a href="http://www.xml.com/">XML.com</a>. They graciously allowed
+Clark Cooper to retain copyright and to distribute it with Expat.</p>
+
+<hr />
+<h2>Table of Contents</h2>
+<ul>
+ <li><a href="#overview">Overview</a></li>
+ <li><a href="#building">Building and Installing</a></li>
+ <li><a href="#using">Using Expat</a></li>
+ <li><a href="#reference">Reference</a>
+ <ul>
+ <li><a href="#creation">Parser Creation Functions</a>
+ <ul>
+ <li><a href="#XML_ParserCreate">XML_ParserCreate</a></li>
+ <li><a href="#XML_ParserCreateNS">XML_ParserCreateNS</a></li>
+ <li><a href="#XML_ParserCreate_MM">XML_ParserCreate_MM</a></li>
+ <li><a href="#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a></li>
+ <li><a href="#XML_ParserFree">XML_ParserFree</a></li>
+ <li><a href="#XML_ParserReset">XML_ParserReset</a></li>
+ </ul>
+ </li>
+ <li><a href="#parsing">Parsing Functions</a>
+ <ul>
+ <li><a href="#XML_Parse">XML_Parse</a></li>
+ <li><a href="#XML_ParseBuffer">XML_ParseBuffer</a></li>
+ <li><a href="#XML_GetBuffer">XML_GetBuffer</a></li>
+ </ul>
+ </li>
+ <li><a href="#setting">Handler Setting Functions</a>
+ <ul>
+ <li><a href="#XML_SetStartElementHandler">XML_SetStartElementHandler</a></li>
+ <li><a href="#XML_SetEndElementHandler">XML_SetEndElementHandler</a></li>
+ <li><a href="#XML_SetElementHandler">XML_SetElementHandler</a></li>
+ <li><a href="#XML_SetCharacterDataHandler">XML_SetCharacterDataHandler</a></li>
+ <li><a href="#XML_SetProcessingInstructionHandler">XML_SetProcessingInstructionHandler</a></li>
+ <li><a href="#XML_SetCommentHandler">XML_SetCommentHandler</a></li>
+ <li><a href="#XML_SetStartCdataSectionHandler">XML_SetStartCdataSectionHandler</a></li>
+ <li><a href="#XML_SetEndCdataSectionHandler">XML_SetEndCdataSectionHandler</a></li>
+ <li><a href="#XML_SetCdataSectionHandler">XML_SetCdataSectionHandler</a></li>
+ <li><a href="#XML_SetDefaultHandler">XML_SetDefaultHandler</a></li>
+ <li><a href="#XML_SetDefaultHandlerExpand">XML_SetDefaultHandlerExpand</a></li>
+ <li><a href="#XML_SetExternalEntityRefHandler">XML_SetExternalEntityRefHandler</a></li>
+ <li><a href="#XML_SetSkippedEntityHandler">XML_SetSkippedEntityHandler</a></li>
+ <li><a href="#XML_SetUnknownEncodingHandler">XML_SetUnknownEncodingHandler</a></li>
+ <li><a href="#XML_SetStartNamespaceDeclHandler">XML_SetStartNamespaceDeclHandler</a></li>
+ <li><a href="#XML_SetEndNamespaceDeclHandler">XML_SetEndNamespaceDeclHandler</a></li>
+ <li><a href="#XML_SetNamespaceDeclHandler">XML_SetNamespaceDeclHandler</a></li>
+ <li><a href="#XML_SetXmlDeclHandler">XML_SetXmlDeclHandler</a></li>
+ <li><a href="#XML_SetStartDoctypeDeclHandler">XML_SetStartDoctypeDeclHandler</a></li>
+ <li><a href="#XML_SetEndDoctypeDeclHandler">XML_SetEndDoctypeDeclHandler</a></li>
+ <li><a href="#XML_SetDoctypeDeclHandler">XML_SetDoctypeDeclHandler</a></li>
+ <li><a href="#XML_SetElementDeclHandler">XML_SetElementDeclHandler</a></li>
+ <li><a href="#XML_SetAttlistDeclHandler">XML_SetAttlistDeclHandler</a></li>
+ <li><a href="#XML_SetEntityDeclHandler">XML_SetEntityDeclHandler</a></li>
+ <li><a href="#XML_SetUnparsedEntityDeclHandler">XML_SetUnparsedEntityDeclHandler</a></li>
+ <li><a href="#XML_SetNotationDeclHandler">XML_SetNotationDeclHandler</a></li>
+ <li><a href="#XML_SetNotStandaloneHandler">XML_SetNotStandaloneHandler</a></li>
+ </ul>
+ </li>
+ <li><a href="#position">Parse Position and Error Reporting Functions</a>
+ <ul>
+ <li><a href="#XML_GetErrorCode">XML_GetErrorCode</a></li>
+ <li><a href="#XML_ErrorString">XML_ErrorString</a></li>
+ <li><a href="#XML_GetCurrentByteIndex">XML_GetCurrentByteIndex</a></li>
+ <li><a href="#XML_GetCurrentLineNumber">XML_GetCurrentLineNumber</a></li>
+ <li><a href="#XML_GetCurrentColumnNumber">XML_GetCurrentColumnNumber</a></li>
+ <li><a href="#XML_GetCurrentByteCount">XML_GetCurrentByteCount</a></li>
+ <li><a href="#XML_GetInputContext">XML_GetInputContext</a></li>
+ </ul>
+ </li>
+ <li><a href="#miscellaneous">Miscellaneous Functions</a>
+ <ul>
+ <li><a href="#XML_SetUserData">XML_SetUserData</a></li>
+ <li><a href="#XML_GetUserData">XML_GetUserData</a></li>
+ <li><a href="#XML_UseParserAsHandlerArg">XML_UseParserAsHandlerArg</a></li>
+ <li><a href="#XML_SetBase">XML_SetBase</a></li>
+ <li><a href="#XML_GetBase">XML_GetBase</a></li>
+ <li><a href="#XML_GetSpecifiedAttributeCount">XML_GetSpecifiedAttributeCount</a></li>
+ <li><a href="#XML_GetIdAttributeIndex">XML_GetIdAttributeIndex</a></li>
+ <li><a href="#XML_SetEncoding">XML_SetEncoding</a></li>
+ <li><a href="#XML_SetParamEntityParsing">XML_SetParamEntityParsing</a></li>
+ <li><a href="#XML_UseForeignDTD">XML_UseForeignDTD</a></li>
+ <li><a href="#XML_SetReturnNSTriplet">XML_SetReturnNSTriplet</a></li>
+ <li><a href="#XML_DefaultCurrent">XML_DefaultCurrent</a></li>
+ <li><a href="#XML_ExpatVersion">XML_ExpatVersion</a></li>
+ <li><a href="#XML_ExpatVersionInfo">XML_ExpatVersionInfo</a></li>
+ <li><a href="#XML_GetFeatureList">XML_GetFeatureList</a></li>
+ </ul>
+ </li>
+ </ul>
+ </li>
+</ul>
+
+<hr />
+<h2><a name="overview">Overview</a></h2>
+
+<p>Expat is a stream-oriented parser. You register callback (or
+handler) functions with the parser and then start feeding it the
+document. As the parser recognizes parts of the document, it will
+call the appropriate handler for that part (if you've registered one.)
+The document is fed to the parser in pieces, so you can start parsing
+before you have all the document. This also allows you to parse really
+huge documents that won't fit into memory.</p>
+
+<p>Expat can be intimidating due to the many kinds of handlers and
+options you can set. But you only need to learn four functions in
+order to do 90% of what you'll want to do with it:</p>
+
+<dl>
+
+<dt><code><a href= "#XML_ParserCreate"
+ >XML_ParserCreate</a></code></dt>
+ <dd>Create a new parser object.</dd>
+
+<dt><code><a href= "#XML_SetElementHandler"
+ >XML_SetElementHandler</a></code></dt>
+ <dd>Set handlers for start and end tags.</dd>
+
+<dt><code><a href= "#XML_SetCharacterDataHandler"
+ >XML_SetCharacterDataHandler</a></code></dt>
+ <dd>Set handler for text.</dd>
+
+<dt><code><a href= "#XML_Parse"
+ >XML_Parse</a></code></dt>
+ <dd>Pass a buffer full of document to the parser</dd>
+</dl>
+
+<p>These functions and others are described in the <a
+href="#reference">reference</a> part of this document. The reference
+section also describes in detail the parameters passed to the
+different types of handlers.</p>
+
+<p>Let's look at a very simple example program that only uses 3 of the
+above functions (it doesn't need to set a character handler.) The
+program <a href="../examples/outline.c">outline.c</a> prints an
+element outline, indenting child elements to distinguish them from the
+parent element that contains them. The start handler does all the
+work. It prints two indenting spaces for every level of ancestor
+elements, then it prints the element and attribute
+information. Finally it increments the global <code>Depth</code>
+variable.</p>
+
+<pre class="eg">
+int Depth;
+
+void
+start(void *data, const char *el, const char **attr) {
+ int i;
+
+ for (i = 0; i < Depth; i++)
+ printf(" ");
+
+ printf("%s", el);
+
+ for (i = 0; attr[i]; i += 2) {
+ printf(" %s='%s'", attr[i], attr[i + 1]);
+ }
+
+ printf("\n");
+ Depth++;
+} /* End of start handler */
+</pre>
+
+<p>The end tag simply does the bookkeeping work of decrementing
+<code>Depth</code>.</p>
+<pre class="eg">
+void
+end(void *data, const char *el) {
+ Depth--;
+} /* End of end handler */
+</pre>
+
+<p>After creating the parser, the main program just has the job of
+shoveling the document to the parser so that it can do its work.</p>
+
+<hr />
+<h2><a name="building">Building and Installing Expat</a></h2>
+
+<p>The Expat distribution comes as a compressed (with GNU gzip) tar
+file. You may download the latest version from <a href=
+"http://sourceforge.net/projects/expat/" >Source Forge</a>. After
+unpacking this, cd into the directory. Then follow either the Win32
+directions or Unix directions below.</p>
+
+<h3>Building under Win32</h3>
+
+<p>If you're using the GNU compiler under cygwin, follow the Unix
+directions in the next section. Otherwise if you have Microsoft's
+Developer Studio installed, then from Windows Explorer double-click on
+"expat.dsp" in the lib directory and build and install in the usual
+manner.</p>
+
+<p>Alternatively, you may download the Win32 binary package that
+contains the "expat.h" include file and a pre-built DLL.</p>
+
+<h3>Building under Unix (or GNU)</h3>
+
+<p>First you'll need to run the configure shell script in order to
+configure the Makefiles and headers for your system.</p>
+
+<p>If you're happy with all the defaults that configure picks for you,
+and you have permission on your system to install into /usr/local, you
+can install Expat with this sequence of commands:</p>
+
+<pre class="eg">
+ ./configure
+ make
+ make install
+</pre>
+
+<p>There are some options that you can provide to this script, but the
+only one we'll mention here is the <code>--prefix</code> option. You
+can find out all the options available by running configure with just
+the <code>--help</code> option.</p>
+
+<p>By default, the configure script sets things up so that the library
+gets installed in <code>/usr/local/lib</code> and the associated
+header file in <code>/usr/local/include</code>. But if you were to
+give the option, <code>--prefix=/home/me/mystuff</code>, then the
+library and header would get installed in
+<code>/home/me/mystuff/lib</code> and
+<code>/home/me/mystuff/include</code> respectively.</p>
+
+<hr />
+<h2><a name="using">Using Expat</a></h2>
+
+<h3>Compiling and Linking Against Expat</h3>
+
+<p>Unless you installed Expat in a location not expected by your
+compiler and linker, all you have to do to use Expat in your programs
+is to include the Expat header (<code>#include <expat.h></code>)
+in your files that make calls to it and to tell the linker that it
+needs to link against the Expat library. On Unix systems, this would
+usually be done with the <code>-lexpat</code> argument. Otherwise,
+you'll need to tell the compiler where to look for the Expat header
+and the linker where to find the Expat library. You may also need to
+take steps to tell the operating system where to find this libary at
+run time.</p>
+
+<p>On a Unix-based system, here's what a Makefile might look like when
+Expat is installed in a standard location:</p>
+
+<pre class="eg">
+CC=cc
+LDFLAGS=
+LIBS= -lexpat
+xmlapp: xmlapp.o
+ $(CC) $(LDFLAGS) -o xmlapp xmlapp.o $(LIBS)
+</pre>
+
+<p>If you installed Expat in, say, <code>/home/me/mystuff</code>, then
+the Makefile would look like this:</p>
+
+<pre class="eg">
+CC=cc
+CFLAGS= -I/home/me/mystuff/include
+LDFLAGS=
+LIBS= -L/home/me/mystuff/lib -lexpat
+xmlapp: xmlapp.o
+ $(CC) $(LDFLAGS) -o xmlapp xmlapp.o $(LIBS)
+</pre>
+
+<p>You'd also have to set the environment variable
+<code>LD_LIBRARY_PATH</code> to <code>/home/me/mystuff/lib</code> (or
+to <code>${LD_LIBRARY_PATH}:/home/me/mystuff/lib</code> if
+LD_LIBRARY_PATH already has some directories in it) in order to run
+your application.</p>
+
+<h3>Expat Basics</h3>
+
+<p>As we saw in the example in the overview, the first step in parsing
+an XML document with Expat is to create a parser object. There are <a
+href="#creation">three functions</a> in the Expat API for creating a
+parser object. However, only two of these (<code><a href=
+"#XML_ParserCreate" >XML_ParserCreate</a></code> and <code><a href=
+"#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>) can be used for
+constructing a parser for a top-level document. The object returned
+by these functions is an opaque pointer (i.e. "expat.h" declares it as
+void *) to data with further internal structure. In order to free the
+memory associated with this object you must call <code><a href=
+"#XML_ParserFree" >XML_ParserFree</a></code>. Note that if you have
+provided any <a href="userdata">user data</a> that gets stored in the
+parser, then your application is responsible for freeing it prior to
+calling <code>XML_ParserFree</code>.</p>
+
+<p>The objects returned by the parser creation functions are good for
+parsing only one XML document or external parsed entity. If your
+application needs to parse many XML documents, then it needs to create
+a parser object for each one. The best way to deal with this is to
+create a higher level object that contains all the default
+initialization you want for your parser objects.</p>
+
+<p>Walking through a document hierarchy with a stream oriented parser
+will require a good stack mechanism in order to keep track of current
+context. For instance, to answer the simple question, "What element
+does this text belong to?" requires a stack, since the parser may have
+descended into other elements that are children of the current one and
+has encountered this text on the way out.</p>
+
+<p>The things you're likely to want to keep on a stack are the
+currently opened element and it's attributes. You push this
+information onto the stack in the start handler and you pop it off in
+the end handler.</p>
+
+<p>For some tasks, it is sufficient to just keep information on what
+the depth of the stack is (or would be if you had one.) The outline
+program shown above presents one example. Another such task would be
+skipping over a complete element. When you see the start tag for the
+element you want to skip, you set a skip flag and record the depth at
+which the element started. When the end tag handler encounters the
+same depth, the skipped element has ended and the flag may be
+cleared. If you follow the convention that the root element starts at
+1, then you can use the same variable for skip flag and skip
+depth.</p>
+
+<pre class="eg">
+void
+init_info(Parseinfo *info) {
+ info->skip = 0;
+ info->depth = 1;
+ /* Other initializations here */
+} /* End of init_info */
+
+void
+rawstart(void *data, const char *el, const char **attr) {
+ Parseinfo *inf = (Parseinfo *) data;
+
+ if (! inf->skip) {
+ if (should_skip(inf, el, attr)) {
+ inf->skip = inf->depth;
+ }
+ else
+ start(inf, el, attr); /* This does rest of start handling */
+ }
+
+ inf->depth++;
+} /* End of rawstart */
+
+void
+rawend(void *data, const char *el) {
+ Parseinfo *inf = (Parseinfo *) data;
+
+ inf->depth--;
+
+ if (! inf->skip)
+ end(inf, el); /* This does rest of end handling */
+
+ if (inf->skip == inf->depth)
+ inf->skip = 0;
+} /* End rawend */
+</pre>
+
+<p>Notice in the above example the difference in how depth is
+manipulated in the start and end handlers. The end tag handler should
+be the mirror image of the start tag handler. This is necessary to
+properly model containment. Since, in the start tag handler, we
+incremented depth <em>after</em> the main body of start tag code, then
+in the end handler, we need to manipulate it <em>before</em> the main
+body. If we'd decided to increment it first thing in the start
+handler, then we'd have had to decrement it last thing in the end
+handler.</p>
+
+<h3 id="userdata">Communicating between handlers</h3>
+
+<p>In order to be able to pass information between different handlers
+without using globals, you'll need to define a data structure to hold
+the shared variables. You can then tell Expat (with the <code><a href=
+"#XML_SetUserData" >XML_SetUserData</a></code> function) to pass a
+pointer to this structure to the handlers. This is typically the first
+argument received by most handlers.</p>
+
+<h3>XML Version</h3>
+
+<p>Expat is an XML 1.0 parser, and as such never complains based on
+the value of the <code>version</code> pseudo-attribute in the XML
+declaration, if present.</p>
+
+<p>If an application needs to check the version number (to support
+alternate processing), it should use the <code><a href=
+"#XML_SetXmlDeclHandler" >XML_SetXmlDeclHandler</a></code> function to
+set a handler that uses the information in the XML declaration to
+determine what to do. This example shows how to check that only a
+version number of <code>"1.0"</code> is accepted:</p>
+
+<pre class="eg">
+static int wrong_version;
+static XML_Parser parser;
+
+static void
+xmldecl_handler(void *userData,
+ const XML_Char *version,
+ const XML_Char *encoding,
+ int standalone)
+{
+ static const XML_Char Version_1_0[] = {'1', '.', '0', 0};
+
+ int i;
+
+ for (i = 0; i < (sizeof(Version_1_0) / sizeof(Version_1_0[0])); ++i) {
+ if (version[i] != Version_1_0[i]) {
+ wrong_version = 1;
+ /* also clear all other handlers: */
+ XML_SetCharacterDataHandler(parser, NULL);
+ ...
+ return;
+ }
+ }
+ ...
+}
+</pre>
+
+<h3>Namespace Processing</h3>
+
+<p>When the parser is created using the <code><a href=
+"#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>, function, Expat
+performs namespace processing. Under namespace processing, Expat
+consumes <code>xmlns</code> and <code>xmlns:...</code> attributes,
+which declare namespaces for the scope of the element in which they
+occur. This means that your start handler will not see these
+attributes. Your application can still be informed of these
+declarations by setting namespace declaration handlers with <a href=
+"#XML_SetNamespaceDeclHandler"
+><code>XML_SetNamespaceDeclHandler</code></a>.</p>
+
+<p>Element type and attribute names that belong to a given namespace
+are passed to the appropriate handler in expanded form. By default
+this expanded form is a concatenation of the namespace URI, the
+separator character (which is the 2nd argument to <code><a href=
+"#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>), and the local
+name (i.e. the part after the colon). Names with undeclared prefixes
+are passed through to the handlers unchanged, with the prefix and
+colon still attached. Unprefixed attribute names are never expanded,
+and unprefixed element names are only expanded when they are in the
+scope of a default namespace.</p>
+
+<p>However if <code><a href= "XML_SetReturnNSTriplet"
+>XML_SetReturnNSTriplet</a></code> has been called with a non-zero
+<code>do_nst</code> parameter, then the expanded form for names with
+an explicit prefix is a concatenation of: URI, separator, local name,
+separator, prefix.</p>
+
+<p>You can set handlers for the start of a namespace declaration and
+for the end of a scope of a declaration with the <code><a href=
+"#XML_SetNamespaceDeclHandler" >XML_SetNamespaceDeclHandler</a></code>
+function. The StartNamespaceDeclHandler is called prior to the start
+tag handler and the EndNamespaceDeclHandler is called before the
+corresponding end tag that ends the namespace's scope. The namespace
+start handler gets passed the prefix and URI for the namespace. For a
+default namespace declaration (xmlns='...'), the prefix will be null.
+The URI will be null for the case where the default namespace is being
+unset. The namespace end handler just gets the prefix for the closing
+scope.</p>
+
+<p>These handlers are called for each declaration. So if, for
+instance, a start tag had three namespace declarations, then the
+StartNamespaceDeclHandler would be called three times before the start
+tag handler is called, once for each declaration.</p>
+
+<h3>Character Encodings</h3>
+
+<p>While XML is based on Unicode, and every XML processor is required
+to recognized UTF-8 and UTF-16 (1 and 2 byte encodings of Unicode),
+other encodings may be declared in XML documents or entities. For the
+main document, an XML declaration may contain an encoding
+declaration:</p>
+<pre>
+<?xml version="1.0" encoding="ISO-8859-2"?>
+</pre>
+
+<p>External parsed entities may begin with a text declaration, which
+looks like an XML declaration with just an encoding declaration:</p>
+<pre>
+<?xml encoding="Big5"?>
+</pre>
+
+<p>With Expat, you may also specify an encoding at the time of
+creating a parser. This is useful when the encoding information may
+come from a source outside the document itself (like a higher level
+protocol.)</p>
+
+<p><a name="builtin_encodings"></a>There are four built-in encodings
+in Expat:</p>
+<ul>
+<li>UTF-8</li>
+<li>UTF-16</li>
+<li>ISO-8859-1</li>
+<li>US-ASCII</li>
+</ul>
+
+<p>Anything else discovered in an encoding declaration or in the
+protocol encoding specified in the parser constructor, triggers a call
+to the <code>UnknownEncodingHandler</code>. This handler gets passed
+the encoding name and a pointer to an <code>XML_Encoding</code> data
+structure. Your handler must fill in this structure and return 1 if it
+knows how to deal with the encoding. Otherwise the handler should
+return 0. The handler also gets passed a pointer to an optional
+application data structure that you may indicate when you set the
+handler.</p>
+
+<p>Expat places restrictions on character encodings that it can
+support by filling in the <code>XML_Encoding</code> structure.
+include file:</p>
+<ol>
+<li>Every ASCII character that can appear in a well-formed XML document
+must be represented by a single byte, and that byte must correspond to
+it's ASCII encoding (except for the characters $@\^'{}~)</li>
+<li>Characters must be encoded in 4 bytes or less.</li>
+<li>All characters encoded must have Unicode scalar values less than or
+equal to 65535 (0xFFFF)<em>This does not apply to the built-in support
+for UTF-16 and UTF-8</em></li>
+<li>No character may be encoded by more that one distinct sequence of
+bytes</li>
+</ol>
+
+<p><code>XML_Encoding</code> contains an array of integers that
+correspond to the 1st byte of an encoding sequence. If the value in
+the array for a byte is zero or positive, then the byte is a single
+byte encoding that encodes the Unicode scalar value contained in the
+array. A -1 in this array indicates a malformed byte. If the value is
+-2, -3, or -4, then the byte is the beginning of a 2, 3, or 4 byte
+sequence respectively. Multi-byte sequences are sent to the convert
+function pointed at in the <code>XML_Encoding</code> structure. This
+function should return the Unicode scalar value for the sequence or -1
+if the sequence is malformed.</p>
+
+<p>One pitfall that novice Expat users are likely to fall into is that
+although Expat may accept input in various encodings, the strings that
+it passes to the handlers are always encoded in UTF-8 or UTF-16
+(depending on how Expat was compiled). Your application is responsible
+for any translation of these strings into other encodings.</p>
+
+<h3>Handling External Entity References</h3>
+
+<p>Expat does not read or parse external entities directly. Note that
+any external DTD is a special case of an external entity. If you've
+set no <code>ExternalEntityRefHandler</code>, then external entity
+references are silently ignored. Otherwise, it calls your handler with
+the information needed to read and parse the external entity.</p>
+
+<p>Your handler isn't actually responsible for parsing the entity, but
+it is responsible for creating a subsidiary parser with <code><a href=
+"#XML_ExternalEntityParserCreate"
+>XML_ExternalEntityParserCreate</a></code> that will do the job. This
+returns an instance of <code>XML_Parser</code> that has handlers and
+other data structures initialized from the parent parser. You may then
+use <code><a href= "#XML_Parse" >XML_Parse</a></code> or <code><a
+href= "#XML_ParseBuffer">XML_ParseBuffer</a></code> calls against this
+parser. Since external entities my refer to other external entities,
+your handler should be prepared to be called recursively.</p>
+
+<h3>Parsing DTDs</h3>
+
+<p>In order to parse parameter entities, before starting the parse,
+you must call <code><a href= "#XML_SetParamEntityParsing"
+>XML_SetParamEntityParsing</a></code> with one of the following
+arguments:</p>
+<dl>
+<dt><code>XML_PARAM_ENTITY_PARSING_NEVER</code></dt>
+<dd>Don't parse parameter entities or the external subset</dd>
+<dt><code>XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE</code></dt>
+<dd>Parse parameter entites and the external subset unless
+<code>standalone</code> was set to "yes" in the XML declaration.</dd>
+<dt><code>XML_PARAM_ENTITY_PARSING_ALWAYS</code></dt>
+<dd>Always parse parameter entities and the external subset</dd>
+</dl>
+
+<p>In order to read an external DTD, you also have to set an external
+entity reference handler as described above.</p>
+
+<hr />
+<!-- ================================================================ -->
+
+<h2><a name="reference">Expat Reference</a></h2>
+
+<h3><a name="creation">Parser Creation</a></h3>
+
+<pre class="fcndec" id="XML_ParserCreate">
+XML_Parser
+XML_ParserCreate(const XML_Char *encoding);
+</pre>
+<div class="fcndef">
+Construct a new parser. If encoding is non-null, it specifies a
+character encoding to use for the document. This overrides the document
+encoding declaration. There are four built-in encodings:
+<ul>
+<li>US-ASCII</li>
+<li>UTF-8</li>
+<li>UTF-16</li>
+<li>ISO-8859-1</li>
+</ul>
+Any other value will invoke a call to the UnknownEncodingHandler.
+</div>
+
+<pre class="fcndec" id="XML_ParserCreateNS">
+XML_Parser
+XML_ParserCreateNS(const XML_Char *encoding,
+ XML_Char sep);
+</pre>
+<div class="fcndef">
+Constructs a new parser that has namespace processing in effect. Namespace
+expanded element names and attribute names are returned as a concatenation
+of the namespace URI, <em>sep</em>, and the local part of the name. This
+means that you should pick a character for <em>sep</em> that can't be
+part of a legal URI.</div>
+
+<pre class="fcndec" id="XML_ParserCreate_MM">
+XML_Parser
+XML_ParserCreate_MM(const XML_Char *encoding,
+ const XML_Memory_Handling_Suite *ms,
+ const XML_Char *sep);
+</pre>
+<pre class="signature">
+typedef struct {
+ void *(*malloc_fcn)(size_t size);
+ void *(*realloc_fcn)(void *ptr, size_t size);
+ void (*free_fcn)(void *ptr);
+} XML_Memory_Handling_Suite;
+</pre>
+<div class="fcndef">
+<p>Construct a new parser using the suite of memory handling functions
+specified in <code>ms</code>. If <code>ms</code> is NULL, then use the
+standard set of memory management functions. If <code>sep</code> is
+non NULL, then namespace processing is enabled in the created parser
+and the character pointed at by sep is used as the separator between
+the namespace URI and the local part of the name.</p>
+</div>
+
+<pre class="fcndec" id="XML_ExternalEntityParserCreate">
+XML_Parser
+XML_ExternalEntityParserCreate(XML_Parser p,
+ const XML_Char *context,
+ const XML_Char *encoding);
+</pre>
+<div class="fcndef">
+Construct a new <code>XML_Parser</code> object for parsing an external
+general entity. Context is the context argument passed in a call to a
+ExternalEntityRefHandler. Other state information such as handlers,
+user data, namespace processing is inherited from the parser passed as
+the 1st argument. So you shouldn't need to call any of the behavior
+changing functions on this parser (unless you want it to act
+differently than the parent parser).
+</div>
+
+<pre class="fcndec" id="XML_ParserFree">
+void
+XML_ParserFree(XML_Parser p);
+</pre>
+<div class="fcndef">
+Free memory used by the parser. Your application is responsible for
+freeing any memory associated with <a href="#userdata">user data</a>.
+</div>
+
+<pre class="fcndec" id="XML_ParserReset">
+XML_Bool
+XML_ParserReset(XML_Parser p);
+</pre>
+<div class="fcndef">
+Clean up the memory structures maintained by the parser so that it may
+be used again. After this has been called, <code>parser</code> is
+ready to start parsing a new document. This function may not be used
+on a parser created using <code><a href=
+"#XML_ExternalEntityParserCreate" >XML_ExternalEntityParserCreate</a
+></code>; it will return <code>XML_FALSE</code> in that case. Returns
+<code>XML_TRUE</code> on success. Your application is responsible for
+dealing with any memory associated with <a href="#userdata">user data</a>.
+</div>
+
+<h3><a name="parsing">Parsing</a></h3>
+
+<p>To state the obvious: the three parsing functions <code><a href=
+"#XML_Parse" >XML_Parse</a></code>, <code><a href= "#XML_ParseBuffer"
+>XML_ParseBuffer</a></code> and <code><a href= "#XML_GetBuffer"
+>>XML_GetBuffer</a></code> must not be
+called from within a handler unless they operate on a separate parser
+instance, that is, one that did not call the handler. For example, it
+is OK to call the parsing functions from within an
+<code>XML_ExternalEntityRefHandler</code>, if they apply to the parser
+created by <code><a href= "#XML_ExternalEntityParserCreate"
+>XML_ExternalEntityParserCreate</a></code>.</p>
+
+<pre class="fcndec" id="XML_Parse">
+XML_Status
+XML_Parse(XML_Parser p,
+ const char *s,
+ int len,
+ int isFinal);
+</pre>
+<pre class="signature">
+enum XML_Status {
+ XML_STATUS_ERROR = 0,
+ XML_STATUS_OK = 1
+};
+</pre>
+<div class="fcndef">
+Parse some more of the document. The string <code>s</code> is a buffer
+containing part (or perhaps all) of the document. The number of bytes of s
+that are part of the document is indicated by <code>len</code>. This means
+that <code>s</code> doesn't have to be null terminated. It also means that
+if <code>len</code> is larger than the number of bytes in the block of
+memory that <code>s</code> points at, then a memory fault is likely. The
+<code>isFinal</code> parameter informs the parser that this is the last
+piece of the document. Frequently, the last piece is empty (i.e.
+<code>len</code> is zero.)
+If a parse error occurred, it returns <code>XML_STATUS_ERROR</code>.
+Otherwise it returns <code>XML_STATUS_OK</code> value.
+</div>
+
+<pre class="fcndec" id="XML_ParseBuffer">
+XML_Status
+XML_ParseBuffer(XML_Parser p,
+ int len,
+ int isFinal);
+</pre>
+<div class="fcndef">
+This is just like <code><a href= "#XML_Parse" >XML_Parse</a></code>,
+except in this case Expat provides the buffer. By obtaining the
+buffer from Expat with the <code><a href= "#XML_GetBuffer"
+>XML_GetBuffer</a></code> function, the application can avoid double
+copying of the input.
+</div>
+
+<pre class="fcndec" id="XML_GetBuffer">
+void *
+XML_GetBuffer(XML_Parser p,
+ int len);
+</pre>
+<div class="fcndef">
+Obtain a buffer of size <code>len</code> to read a piece of the document
+into. A NULL value is returned if Expat can't allocate enough memory for
+this buffer. This has to be called prior to every call to
+<code><a href= "#XML_ParseBuffer" >XML_ParseBuffer</a></code>. A
+typical use would look like this:
+
+<pre class="eg">
+for (;;) {
+ int bytes_read;
+ void *buff = XML_GetBuffer(p, BUFF_SIZE);
+ if (buff == NULL) {
+ /* handle error */
+ }
+
+ bytes_read = read(docfd, buff, BUFF_SIZE);
+ if (bytes_read < 0) {
+ /* handle error */
+ }
+
+ if (! XML_ParseBuffer(p, bytes_read, bytes_read == 0)) {
+ /* handle parse error */
+ }
+
+ if (bytes_read == 0)
+ break;
+}
+</pre>
+</div>
+
+<h3><a name="setting">Handler Setting</a></h3>
+
+<p>Although handlers are typically set prior to parsing and left alone, an
+application may choose to set or change the handler for a parsing event
+while the parse is in progress. For instance, your application may choose
+to ignore all text not descended from a <code>para</code> element. One
+way it could do this is to set the character handler when a para start tag
+is seen, and unset it for the corresponding end tag.</p>
+
+<p>A handler may be <em>unset</em> by providing a NULL pointer to the
+appropriate handler setter. None of the handler setting functions have
+a return value.</p>
+
+<p>Your handlers will be receiving strings in arrays of type
+<code>XML_Char</code>. This type is defined in expat.h as <code>char
+*</code> and contains bytes encoding UTF-8. Note that you'll receive
+them in this form independent of the original encoding of the
+document.</p>
+
+<div class="handler">
+<pre class="setter" id="XML_SetStartElementHandler">
+XML_SetStartElementHandler(XML_Parser p,
+ XML_StartElementHandler start);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_StartElementHandler)(void *userData,
+ const XML_Char *name,
+ const XML_Char **atts);
+</pre>
+<p>Set handler for start (and empty) tags. Attributes are passed to the start
+handler as a pointer to a vector of char pointers. Each attribute seen in
+a start (or empty) tag occupies 2 consecutive places in this vector: the
+attribute name followed by the attribute value. These pairs are terminated
+by a null pointer.</p>
+<p>Note that an empty tag generates a call to both start and end handlers
+(in that order).</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetEndElementHandler">
+XML_SetEndElementHandler(XML_Parser p,
+ XML_EndElementHandler);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_EndElementHandler)(void *userData,
+ const XML_Char *name);
+</pre>
+<p>Set handler for end (and empty) tags. As noted above, an empty tag
+generates a call to both start and end handlers.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetElementHandler">
+XML_SetElementHandler(XML_Parser p,
+ XML_StartElementHandler start,
+ XML_EndElementHandler end);
+</pre>
+<p>Set handlers for start and end tags with one call.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetCharacterDataHandler">
+XML_SetCharacterDataHandler(XML_Parser p,
+ XML_CharacterDataHandler charhndl)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_CharacterDataHandler)(void *userData,
+ const XML_Char *s,
+ int len);
+</pre>
+<p>Set a text handler. The string your handler receives
+is <em>NOT nul-terminated</em>. You have to use the length argument
+to deal with the end of the string. A single block of contiguous text
+free of markup may still result in a sequence of calls to this handler.
+In other words, if you're searching for a pattern in the text, it may
+be split across calls to this handler.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetProcessingInstructionHandler">
+XML_SetProcessingInstructionHandler(XML_Parser p,
+ XML_ProcessingInstructionHandler proc)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_ProcessingInstructionHandler)(void *userData,
+ const XML_Char *target,
+ const XML_Char *data);
+
+</pre>
+<p>Set a handler for processing instructions. The target is the first word
+in the processing instruction. The data is the rest of the characters in
+it after skipping all whitespace after the initial word.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetCommentHandler">
+XML_SetCommentHandler(XML_Parser p,
+ XML_CommentHandler cmnt)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_CommentHandler)(void *userData,
+ const XML_Char *data);
+</pre>
+<p>Set a handler for comments. The data is all text inside the comment
+delimiters.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetStartCdataSectionHandler">
+XML_SetStartCdataSectionHandler(XML_Parser p,
+ XML_StartCdataSectionHandler start);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_StartCdataSectionHandler)(void *userData);
+</pre>
+<p>Set a handler that gets called at the beginning of a CDATA section.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetEndCdataSectionHandler">
+XML_SetEndCdataSectionHandler(XML_Parser p,
+ XML_EndCdataSectionHandler end);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_EndCdataSectionHandler)(void *userData);
+</pre>
+<p>Set a handler that gets called at the end of a CDATA section.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetCdataSectionHandler">
+XML_SetCdataSectionHandler(XML_Parser p,
+ XML_StartCdataSectionHandler start,
+ XML_EndCdataSectionHandler end)
+</pre>
+<p>Sets both CDATA section handlers with one call.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetDefaultHandler">
+XML_SetDefaultHandler(XML_Parser p,
+ XML_DefaultHandler hndl)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_DefaultHandler)(void *userData,
+ const XML_Char *s,
+ int len);
+</pre>
+
+<p>Sets a handler for any characters in the document which wouldn't
+otherwise be handled. This includes both data for which no handlers
+can be set (like some kinds of DTD declarations) and data which could
+be reported but which currently has no handler set. The characters
+are passed exactly as they were present in the XML document except
+that they will be encoded in UTF-8 or UTF-16. Line boundaries are not
+normalized. Note that a byte order mark character is not passed to the
+default handler. There are no guarantees about how characters are
+divided between calls to the default handler: for example, a comment
+might be split between multiple calls. Setting the handler with
+this call has the side effect of turning off expansion of references
+to internally defined general entities. Instead these references are
+passed to the default handler.</p>
+
+<p>See also <code><a
+href="#XML_DefaultCurrent">XML_DefaultCurrent</a></code>.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetDefaultHandlerExpand">
+XML_SetDefaultHandlerExpand(XML_Parser p,
+ XML_DefaultHandler hndl)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_DefaultHandler)(void *userData,
+ const XML_Char *s,
+ int len);
+</pre>
+<p>This sets a default handler, but doesn't inhibit the expansion of
+internal entity references. The entity reference will not be passed
+to the default handler.</p>
+
+<p>See also <code><a
+href="#XML_DefaultCurrent">XML_DefaultCurrent</a></code>.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetExternalEntityRefHandler">
+XML_SetExternalEntityRefHandler(XML_Parser p,
+ XML_ExternalEntityRefHandler hndl)
+</pre>
+<pre class="signature">
+typedef int
+(*XML_ExternalEntityRefHandler)(XML_Parser p,
+ const XML_Char *context,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *publicId);
+</pre>
+<p>Set an external entity reference handler. This handler is also
+called for processing an external DTD subset if parameter entity parsing
+is in effect. (See <a href="#XML_SetParamEntityParsing">
+<code>XML_SetParamEntityParsing</code></a>.)</p>
+
+
+<p>The base parameter is the base to use for relative system identifiers.
+It is set by <a href="#XML_SetBase">XML_SetBase</a> and may be null. The
+public id parameter is the public id given in the entity declaration and
+may be null. The system id is the system identifier specified in the entity
+declaration and is never null.</p>
+
+<p>There are a couple of ways in which this handler differs from others.
+First, this handler returns an integer. A non-zero value should be returned
+for successful handling of the external entity reference. Returning a zero
+indicates failure, and causes the calling parser to return
+an <code>XML_ERROR_EXTERNAL_ENTITY_HANDLING</code> error.</p>
+
+<p>Second, instead of having userData as its first argument, it receives the
+parser that encountered the entity reference. This, along with the context
+parameter, may be used as arguments to a call to
+<a href="#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a>.
+Using the returned parser, the body of the external entity can be recursively
+parsed.</p>
+
+<p>Since this handler may be called recursively, it should not be saving
+information into global or static variables.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetSkippedEntityHandler">
+XML_SetSkippedEntityHandler(XML_Parser p,
+ XML_SkippedEntityHandler handler)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_SkippedEntityHandler)(void *userData,
+ const XML_Char *entityName,
+ int is_parameter_entity);
+</pre>
+<p>Set a skipped entity handler. This is called in two situations:</p>
+<ol>
+ <li>An entity reference is encountered for which no declaration
+ has been read <em>and</em> this is not an error.</li>
+ <li>An internal entity reference is read, but not expanded, because
+ <a href="#XML_SetDefaultHandler"><code>XML_SetDefaultHandler</code></a>
+ has been called.</li>
+</ol>
+<p>The <code>is_parameter_entity</code> argument will be non-zero for
+a parameter entity and zero for a general entity.</p> <p>Note: skipped
+parameter entities in declarations and skipped general entities in
+attribute values cannot be reported, because the event would be out of
+sync with the reporting of the declarations or attribute values</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetUnknownEncodingHandler">
+XML_SetUnknownEncodingHandler(XML_Parser p,
+ XML_UnknownEncodingHandler enchandler,
+ void *encodingHandlerData)
+</pre>
+<pre class="signature">
+typedef int
+(*XML_UnknownEncodingHandler)(void *encodingHandlerData,
+ const XML_Char *name,
+ XML_Encoding *info);
+
+typedef struct {
+ int map[256];
+ void *data;
+ int (*convert)(void *data, const char *s);
+ void (*release)(void *data);
+} XML_Encoding;
+</pre>
+<p>Set a handler to deal with encodings other than the
+<a href="#builtin_encodings">built in set</a>. This should be done before
+<code><a href= "#XML_Parse" >XML_Parse</a></code> or <code><a href=
+"#XML_ParseBuffer" >XML_ParseBuffer</a></code> have been called on the
+given parser.</p>
+<p>If the handler knows how to deal with an encoding with the given
+name, it should fill in the <code>info</code> data structure and return
+1. Otherwise it should return 0. The handler will be called at most
+once per parsed (external) entity. The optional application data
+pointer <code>encodingHandlerData</code> will be passed back to the
+handler.</p>
+
+<p>The map array contains information for every possible possible leading
+byte in a byte sequence. If the corresponding value is >= 0, then it's
+a single byte sequence and the byte encodes that Unicode value. If the
+value is -1, then that byte is invalid as the initial byte in a sequence.
+If the value is -n, where n is an integer > 1, then n is the number of
+bytes in the sequence and the actual conversion is accomplished by a
+call to the function pointed at by convert. This function may return -1
+if the sequence itself is invalid. The convert pointer may be null if
+there are only single byte codes. The data parameter passed to the convert
+function is the data pointer from <code>XML_Encoding</code>. The
+string s is <em>NOT</em> nul-terminated and points at the sequence of
+bytes to be converted.</p>
+
+<p>The function pointed at by <code>release</code> is called by the
+parser when it is finished with the encoding. It may be NULL.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetStartNamespaceDeclHandler">
+XML_SetStartNamespaceDeclHandler(XML_Parser p,
+ XML_StartNamespaceDeclHandler start);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_StartNamespaceDeclHandler)(void *userData,
+ const XML_Char *prefix,
+ const XML_Char *uri);
+</pre>
+<p>Set a handler to be called when a namespace is declared. Namespace
+declarations occur inside start tags. But the namespace declaration start
+handler is called before the start tag handler for each namespace declared
+in that start tag.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetEndNamespaceDeclHandler">
+XML_SetEndNamespaceDeclHandler(XML_Parser p,
+ XML_EndNamespaceDeclHandler end);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_EndNamespaceDeclHandler)(void *userData,
+ const XML_Char *prefix);
+</pre>
+<p>Set a handler to be called when leaving the scope of a namespace
+declaration. This will be called, for each namespace declaration,
+after the handler for the end tag of the element in which the
+namespace was declared.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetNamespaceDeclHandler">
+XML_SetNamespaceDeclHandler(XML_Parser p,
+ XML_StartNamespaceDeclHandler start,
+ XML_EndNamespaceDeclHandler end)
+</pre>
+<p>Sets both namespace declaration handlers with a single call</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetXmlDeclHandler">
+XML_SetXmlDeclHandler(XML_Parser p,
+ XML_XmlDeclHandler xmldecl);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_XmlDeclHandler) (void *userData,
+ const XML_Char *version,
+ const XML_Char *encoding,
+ int standalone);
+</pre>
+<p>Sets a handler that is called for XML declarations and also for
+text declarations discovered in external entities. The way to
+distinguish is that the <code>version</code> parameter will be NULL
+for text declarations. The <code>encoding</code> parameter may be NULL
+for an XML declaration. The <code>standalone</code> argument will
+contain -1, 0, or 1 indicating respectively that there was no
+standalone parameter in the declaration, that it was given as no, or
+that it was given as yes.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetStartDoctypeDeclHandler">
+XML_SetStartDoctypeDeclHandler(XML_Parser p,
+ XML_StartDoctypeDeclHandler start);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_StartDoctypeDeclHandler)(void *userData,
+ const XML_Char *doctypeName,
+ const XML_Char *sysid,
+ const XML_Char *pubid,
+ int has_internal_subset);
+</pre>
+<p>Set a handler that is called at the start of a DOCTYPE declaration,
+before any external or internal subset is parsed. Both <code>sysid</code>
+and <code>pubid</code> may be NULL. The <code>has_internal_subset</code>
+will be non-zero if the DOCTYPE declaration has an internal subset.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetEndDoctypeDeclHandler">
+XML_SetEndDoctypeDeclHandler(XML_Parser p,
+ XML_EndDoctypeDeclHandler end);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_EndDoctypeDeclHandler)(void *userData);
+</pre>
+<p>Set a handler that is called at the end of a DOCTYPE declaration,
+after parsing any external subset.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetDoctypeDeclHandler">
+XML_SetDoctypeDeclHandler(XML_Parser p,
+ XML_StartDoctypeDeclHandler start,
+ XML_EndDoctypeDeclHandler end);
+</pre>
+<p>Set both doctype handlers with one call.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetElementDeclHandler">
+XML_SetElementDeclHandler(XML_Parser p,
+ XML_ElementDeclHandler eldecl);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_ElementDeclHandler)(void *userData,
+ const XML_Char *name,
+ XML_Content *model);
+</pre>
+<pre class="signature">
+enum XML_Content_Type {
+ XML_CTYPE_EMPTY = 1,
+ XML_CTYPE_ANY,
+ XML_CTYPE_MIXED,
+ XML_CTYPE_NAME,
+ XML_CTYPE_CHOICE,
+ XML_CTYPE_SEQ
+};
+
+enum XML_Content_Quant {
+ XML_CQUANT_NONE,
+ XML_CQUANT_OPT,
+ XML_CQUANT_REP,
+ XML_CQUANT_PLUS
+};
+
+typedef struct XML_cp XML_Content;
+
+struct XML_cp {
+ enum XML_Content_Type type;
+ enum XML_Content_Quant quant;
+ const XML_Char * name;
+ unsigned int numchildren;
+ XML_Content * children;
+};
+</pre>
+<p>Sets a handler for element declarations in a DTD. The handler gets
+called with the name of the element in the declaration and a pointer
+to a structure that contains the element model. It is the
+application's responsibility to free this data structure.</p>
+
+<p>The <code>model</code> argument is the root of a tree of
+<code>XML_Content</code> nodes. If <code>type</code> equals
+<code>XML_CTYPE_EMPTY</code> or <code>XML_CTYPE_ANY</code>, then
+<code>quant</code> will be <code>XML_CQUANT_NONE</code>, and the other
+fields will be zero or NULL. If <code>type</code> is
+<code>XML_CTYPE_MIXED</code>, then <code>quant</code> will be
+<code>XML_CQUANT_NONE</code> or <code>XML_CQUANT_REP</code> and
+<code>numchildren</code> will contain the number of elements that are
+allowed to be mixed in and <code>children</code> points to an array of
+<code>XML_Content</code> structures that will all have type
+XML_CTYPE_NAME with no quantification. Only the root node can be type
+<code>XML_CTYPE_EMPTY</code>, <code>XML_CTYPE_ANY</code>, or
+<code>XML_CTYPE_MIXED</code>.</p>
+
+<p>For type <code>XML_CTYPE_NAME</code>, the <code>name</code> field
+points to the name and the <code>numchildren</code> and
+<code>children</code> fields will be zero and NULL. The
+<code>quant</code> field will indicate any quantifiers placed on the
+name.</p>
+
+<p>Types <code>XML_CTYPE_CHOICE</code> and <code>XML_CTYPE_SEQ</code>
+indicate a choice or sequence respectively. The
+<code>numchildren</code> field indicates how many nodes in the choice
+or sequence and <code>children</code> points to the nodes.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetAttlistDeclHandler">
+XML_SetAttlistDeclHandler(XML_Parser p,
+ XML_AttlistDeclHandler attdecl);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_AttlistDeclHandler) (void *userData,
+ const XML_Char *elname,
+ const XML_Char *attname,
+ const XML_Char *att_type,
+ const XML_Char *dflt,
+ int isrequired);
+</pre>
+<p>Set a handler for attlist declarations in the DTD. This handler is
+called for <em>each</em> attribute. So a single attlist declaration
+with multiple attributes declared will generate multiple calls to this
+handler. The <code>elname</code> parameter returns the name of the
+element for which the attribute is being declared. The attribute name
+is in the <code>attname</code> parameter. The attribute type is in the
+<code>att_type</code> parameter. It is the string representing the
+type in the declaration with whitespace removed.</p>
+
+<p>The <code>dflt</code> parameter holds the default value. It will be
+NULL in the case of "#IMPLIED" or "#REQUIRED" attributes. You can
+distinguish these two cases by checking the <code>isrequired</code>
+parameter, which will be true in the case of "#REQUIRED" attributes.
+Attributes which are "#FIXED" will have also have a true
+<code>isrequired</code>, but they will have the non-NULL fixed value
+in the <code>dflt</code> parameter.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetEntityDeclHandler">
+XML_SetEntityDeclHandler(XML_Parser p,
+ XML_EntityDeclHandler handler);
+</pre>
+<pre class="signature">
+typedef void
+(*XML_EntityDeclHandler) (void *userData,
+ const XML_Char *entityName,
+ int is_parameter_entity,
+ const XML_Char *value,
+ int value_length,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *publicId,
+ const XML_Char *notationName);
+</pre>
+<p>Sets a handler that will be called for all entity declarations.
+The <code>is_parameter_entity</code> argument will be non-zero in the
+case of parameter entities and zero otherwise.</p>
+
+<p>For internal entities (<code><!ENTITY foo "bar"></code>),
+<code>value</code> will be non-NULL and <code>systemId</code>,
+<code>publicId</code>, and <code>notationName</code> will all be NULL.
+The value string is <em>not</em> NULL terminated; the length is
+provided in the <code>value_length</code> parameter. Do not use
+<code>value_length</code> to test for internal entities, since it is
+legal to have zero-length values. Instead check for whether or not
+<code>value</code> is NULL.</p> <p>The <code>notationName</code>
+argument will have a non-NULL value only for unparsed entity
+declarations.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetUnparsedEntityDeclHandler">
+XML_SetUnparsedEntityDeclHandler(XML_Parser p,
+ XML_UnparsedEntityDeclHandler h)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_UnparsedEntityDeclHandler)(void *userData,
+ const XML_Char *entityName,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *publicId,
+ const XML_Char *notationName);
+</pre>
+<p>Set a handler that receives declarations of unparsed entities. These
+are entity declarations that have a notation (NDATA) field:</p>
+
+<div id="eg"><pre>
+<!ENTITY logo SYSTEM "images/logo.gif" NDATA gif>
+</pre></div>
+<p>This handler is obsolete and is provided for backwards
+compatibility. Use instead <a href= "#XML_SetEntityDeclHandler"
+>XML_SetEntityDeclHandler</a>.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetNotationDeclHandler">
+XML_SetNotationDeclHandler(XML_Parser p,
+ XML_NotationDeclHandler h)
+</pre>
+<pre class="signature">
+typedef void
+(*XML_NotationDeclHandler)(void *userData,
+ const XML_Char *notationName,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *publicId);
+</pre>
+<p>Set a handler that receives notation declarations.</p>
+</div>
+
+<div class="handler">
+<pre class="setter" id="XML_SetNotStandaloneHandler">
+XML_SetNotStandaloneHandler(XML_Parser p,
+ XML_NotStandaloneHandler h)
+</pre>
+<pre class="signature">
+typedef int
+(*XML_NotStandaloneHandler)(void *userData);
+</pre>
+<p>Set a handler that is called if the document is not "standalone".
+This happens when there is an external subset or a reference to a
+parameter entity, but does not have standalone set to "yes" in an XML
+declaration. If this handler returns 0, then the parser will throw an
+<code>XML_ERROR_NOT_STANDALONE</code> error.</p>
+</div>
+
+<h3><a name="position">Parse position and error reporting functions</a></h3>
+
+<p>These are the functions you'll want to call when the parse
+functions return 0 (i.e. a parse error has ocurred), although the
+position reporting functions are useful outside of errors. The
+position reported is the byte position (in the original document or
+entity encoding) of the first of the sequence of characters that
+generated the current event (or the error that caused the parse
+functions to return 0.)</p>
+
+<p>The position reporting functions are accurate only outside of the
+DTD. In other words, they usually return bogus information when
+called from within a DTD declaration handler.</p>
+
+<pre class="fcndec" id="XML_GetErrorCode">
+enum XML_Error
+XML_GetErrorCode(XML_Parser p);
+</pre>
+<div class="fcndef">
+Return what type of error has occurred.
+</div>
+
+<pre class="fcndec" id="XML_ErrorString">
+const XML_LChar *
+XML_ErrorString(int code);
+</pre>
+<div class="fcndef">
+Return a string describing the error corresponding to code.
+The code should be one of the enums that can be returned from
+<code><a href= "#XML_GetErrorCode" >XML_GetErrorCode</a></code>.
+</div>
+
+<pre class="fcndec" id="XML_GetCurrentByteIndex">
+long
+XML_GetCurrentByteIndex(XML_Parser p);
+</pre>
+<div class="fcndef">
+Return the byte offset of the position.
+</div>
+
+<pre class="fcndec" id="XML_GetCurrentLineNumber">
+int
+XML_GetCurrentLineNumber(XML_Parser p);
+</pre>
+<div class="fcndef">
+Return the line number of the position.
+</div>
+
+<pre class="fcndec" id="XML_GetCurrentColumnNumber">
+int
+XML_GetCurrentColumnNumber(XML_Parser p);
+</pre>
+<div class="fcndef">
+Return the offset, from the beginning of the current line, of
+the position.
+</div>
+
+<pre class="fcndec" id="XML_GetCurrentByteCount">
+int
+XML_GetCurrentByteCount(XML_Parser p);
+</pre>
+<div class="fcndef">
+Return the number of bytes in the current event. Returns
+<code>0</code> if the event is inside a reference to an internal
+entity and for the end-tag event for empty element tags (the later can
+be used to distinguish empty-element tags from empty elements using
+separate start and end tags).
+</div>
+
+<pre class="fcndec" id="XML_GetInputContext">
+const char *
+XML_GetInputContext(XML_Parser p,
+ int *offset,
+ int *size);
+</pre>
+<div class="fcndef">
+
+<p>Returns the parser's input buffer, sets the integer pointed at by
+<code>offset</code> to the offset within this buffer of the current
+parse position, and set the integer pointed at by <code>size</code> to
+the size of the returned buffer.</p>
+
+<p>This should only be called from within a handler during an active
+parse and the returned buffer should only be referred to from within
+the handler that made the call. This input buffer contains the
+untranslated bytes of the input.</p>
+
+<p>Only a limited amount of context is kept, so if the event
+triggering a call spans over a very large amount of input, the actual
+parse position may be before the beginning of the buffer.</p>
+</div>
+
+<h3><a name="miscellaneous">Miscellaneous functions</a></h3>
+
+<p>The functions in this section either obtain state information from
+the parser or can be used to dynamicly set parser options.</p>
+
+<pre class="fcndec" id="XML_SetUserData">
+void
+XML_SetUserData(XML_Parser p,
+ void *userData);
+</pre>
+<div class="fcndef">
+This sets the user data pointer that gets passed to handlers. It
+overwrites any previous value for this pointer. Note that the
+application is responsible for freeing the memory associated with
+<code>userData</code> when it is finished with the parser. So if you
+call this when there's already a pointer there, and you haven't freed
+the memory associated with it, then you've probably just leaked
+memory.
+</div>
+
+<pre class="fcndec" id="XML_GetUserData">
+void *
+XML_GetUserData(XML_Parser p);
+</pre>
+<div class="fcndef">
+This returns the user data pointer that gets passed to handlers.
+It is actually implemented as a macro.
+</div>
+
+<pre class="fcndec" id="XML_UseParserAsHandlerArg">
+void
+XML_UseParserAsHandlerArg(XML_Parser p);
+</pre>
+<div class="fcndef">
+After this is called, handlers receive the parser in the userData
+argument. The userData information can still be obtained using the
+<code><a href= "#XML_GetUserData" >XML_GetUserData</a></code>
+function.
+</div>
+
+<pre class="fcndec" id="XML_SetBase">
+int
+XML_SetBase(XML_Parser p,
+ const XML_Char *base);
+</pre>
+<div class="fcndef">
+Set the base to be used for resolving relative URIs in system
+identifiers. The return value is 0 if there's no memory to store
+base, otherwise it's non-zero.
+</div>
+
+<pre class="fcndec" id="XML_GetBase">
+const XML_Char *
+XML_GetBase(XML_Parser p);
+</pre>
+<div class="fcndef">
+Return the base for resolving relative URIs.
+</div>
+
+<pre class="fcndec" id="XML_GetSpecifiedAttributeCount">
+int
+XML_GetSpecifiedAttributeCount(XML_Parser p);
+</pre>
+<div class="fcndef">
+When attributes are reported to the start handler in the atts vector,
+attributes that were explicitly set in the element occur before any
+attributes that receive their value from default information in an
+ATTLIST declaration. This function returns the number of attributes
+that were explicitly set times two, thus giving the offset in the
+<code>atts</code> array passed to the start tag handler of the first
+attribute set due to defaults. It supplies information for the last
+call to a start handler. If called inside a start handler, then that
+means the current call.
+</div>
+
+<pre class="fcndec" id="XML_GetIdAttributeIndex">
+int
+XML_GetIdAttributeIndex(XML_Parser p);
+</pre>
+<div class="fcndef">
+Returns the index of the ID attribute passed in the atts array in the
+last call to <code><a href= "#XML_StartElementHandler"
+>XML_StartElementHandler</a></code>, or -1 if there is no ID
+attribute. If called inside a start handler, then that means the
+current call.
+</div>
+
+<pre class="fcndec" id="XML_SetEncoding">
+int
+XML_SetEncoding(XML_Parser p,
+ const XML_Char *encoding);
+</pre>
+<div class="fcndef">
+Set the encoding to be used by the parser. It is equivalent to
+passing a non-null encoding argument to the parser creation functions.
+It must not be called after <code><a href= "#XML_Parse"
+>XML_Parse</a></code> or <code><a href= "#XML_ParseBuffer"
+>XML_ParseBuffer</a></code> have been called on the given parser.
+</div>
+
+<pre class="fcndec" id="XML_SetParamEntityParsing">
+int
+XML_SetParamEntityParsing(XML_Parser p,
+ enum XML_ParamEntityParsing code);
+</pre>
+<div class="fcndef">
+This enables parsing of parameter entities, including the external
+parameter entity that is the external DTD subset, according to
+<code>code</code>.
+The choices for <code>code</code> are:
+<ul>
+<li><code>XML_PARAM_ENTITY_PARSING_NEVER</code></li>
+<li><code>XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE</code></li>
+<li><code>XML_PARAM_ENTITY_PARSING_ALWAYS</code></li>
+</ul>
+</div>
+
+<pre class="fcndec" id="XML_UseForeignDTD">
+enum XML_Error
+XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD);
+</pre>
+<div class="fcndef">
+<p>This function allows an application to provide an external subset
+for the document type declaration for documents which do not specify
+an external subset of their own. For documents which specify an
+external subset in their DOCTYPE declaration, the application-provided
+subset will be ignored. If the document does not contain a DOCTYPE
+declaration at all and <code>useDTD</code> is true, the
+application-provided subset will be parsed, but the
+<code>startDoctypeDeclHandler</code> and
+<code>endDoctypeDeclHandler</code> functions, if set, will not be
+called. The setting of parameter entity parsing, controlled using
+<code><a href= "#XML_SetParamEntityParsing"
+>XML_SetParamEntityParsing</a></code>, will be honored.</p>
+
+<p>The application-provided external subset is read by calling the
+external entity reference handler set via <code><a href=
+"#XML_SetExternalEntityRefHandler"
+>XML_SetExternalEntityRefHandler</a></code> with both
+<code>publicId</code> and <code>systemId</code> set to NULL.</p>
+
+<p>If this function is called after parsing has begun, it returns
+<code>XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING</code> and ignores
+<code>useDTD</code>. If called when Expat has been compiled without
+DTD support, it returns
+<code>XML_ERROR_FEATURE_REQUIRES_XML_DTD</code>. Otherwise, it
+returns <code>XML_ERROR_NONE</code>.</p>
+</div>
+
+<pre class="fcndec" id="XML_SetReturnNSTriplet">
+void
+XML_SetReturnNSTriplet(XML_Parser parser,
+ int do_nst);
+</pre>
+<div class="fcndef">
+<p>
+This function only has an effect when using a parser created with
+<code><a href= "#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>,
+i.e. when namespace processing is in effect. The <code>do_nst</code>
+sets whether or not prefixes are returned with names qualified with a
+namespace prefix. If this function is called with <code>do_nst</code>
+non-zero, then afterwards namespace qualified names (that is qualified
+with a prefix as opposed to belonging to a default namespace) are
+returned as a triplet with the three parts separated by the namespace
+separator specified when the parser was created. The order of
+returned parts is URI, local name, and prefix.</p> <p>If
+<code>do_nst</code> is zero, then namespaces are reported in the
+default manner, URI then local_name separated by the namespace
+separator.</p>
+</div>
+
+<pre class="fcndec" id="XML_DefaultCurrent">
+void
+XML_DefaultCurrent(XML_Parser parser);
+</pre>
+<div class="fcndef">
+This can be called within a handler for a start element, end element,
+processing instruction or character data. It causes the corresponding
+markup to be passed to the default handler set by <code><a
+href="#XML_SetDefaultHandler" >XML_SetDefaultHandler</a></code> or
+<code><a href="#XML_SetDefaultHandlerExpand"
+>XML_SetDefaultHandlerExpand</a></code>. It does nothing if there is
+not a default handler.
+</div>
+
+<pre class="fcndec" id="XML_ExpatVersion">
+XML_LChar *
+XML_ExpatVersion();
+</pre>
+<div class="fcndef">
+Return the library version as a string (e.g. <code>"expat_1.95.1"</code>).
+</div>
+
+<pre class="fcndec" id="XML_ExpatVersionInfo">
+struct XML_Expat_Version
+XML_ExpatVersionInfo();
+</pre>
+<pre class="signature">
+typedef struct {
+ int major;
+ int minor;
+ int micro;
+} XML_Expat_Version;
+</pre>
+<div class="fcndef">
+Return the library version information as a structure.
+Some macros are also defined that support compile-time tests of the
+library version:
+<ul>
+<li><code>XML_MAJOR_VERSION</code></li>
+<li><code>XML_MINOR_VERSION</code></li>
+<li><code>XML_MICRO_VERSION</code></li>
+</ul>
+Testing these constants is currently the best way to determine if
+particular parts of the Expat API are available.
+</div>
+
+<pre class="fcndec" id="XML_GetFeatureList">
+const XML_Feature *
+XML_GetFeatureList();
+</pre>
+<pre class="signature">
+enum XML_FeatureEnum {
+ XML_FEATURE_END = 0,
+ XML_FEATURE_UNICODE,
+ XML_FEATURE_UNICODE_WCHAR_T,
+ XML_FEATURE_DTD,
+ XML_FEATURE_CONTEXT_BYTES,
+ XML_FEATURE_MIN_SIZE,
+ XML_FEATURE_SIZEOF_XML_CHAR,
+ XML_FEATURE_SIZEOF_XML_LCHAR
+};
+
+typedef struct {
+ enum XML_FeatureEnum feature;
+ XML_LChar *name;
+ long int value;
+} XML_Feature;
+</pre>
+<div class="fcndef">
+<p>Returns a list of "feature" records, providing details on how
+Expat was configured at compile time. Most applications should not
+need to worry about this, but this information is otherwise not
+available from Expat. This function allows code that does need to
+check these features to do so at runtime.</p>
+
+<p>The return value is an array of <code>XML_Feature</code>,
+terminated by a record with a <code>feature</code> of
+<code>XML_FEATURE_END</code> and <code>name</code> of NULL,
+identifying the feature-test macros Expat was compiled with. Since an
+application that requires this kind of information needs to determine
+the type of character the <code>name</code> points to, records for the
+<code>XML_FEATURE_SIZEOF_XML_CHAR</code> and
+<code>XML_FEATURE_SIZEOF_XML_LCHAR</code> will be located at the
+beginning of the list, followed by <code>XML_FEATURE_UNICODE</code>
+and <code>XML_FEATURE_UNICODE_WCHAR_T</code>, if they are present at
+all.</p>
+
+<p>Some features have an associated value. If there isn't an
+associated value, the <code>value</code> field is set to 0. At this
+time, the following features have been defined to have values:</p>
+
+<dl>
+ <dt><code>XML_FEATURE_SIZEOF_XML_CHAR</code></dt>
+ <dd>The number of bytes occupied by one <code>XML_Char</code>
+ character.</dd>
+ <dt><code>XML_FEATURE_SIZEOF_XML_LCHAR</code></dt>
+ <dd>The number of bytes occupied by one <code>XML_LChar</code>
+ character.</dd>
+ <dt><code>XML_FEATURE_CONTEXT_BYTES</code></dt>
+ <dd>The maximum number of characters of context which can be
+ reported by <code><a href= "#XML_GetInputContext"
+ >XML_GetInputContext</a></code>.</dd>
+</dl>
+</div>
+
+<hr />
+<p><a href="http://validator.w3.org/check/referer"><img
+ src="valid-xhtml10.png" alt="Valid XHTML 1.0!"
+ height="31" width="88" class="noborder" /></a></p>
+</body>
+</html>