expat/doc/reference.html

<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  <head>
    <!--
                            __  __            _
                         ___\ \/ /_ __   __ _| |_
                        / _ \\  /| '_ \ / _` | __|
                       |  __//  \| |_) | (_| | |_
                        \___/_/\_\ .__/ \__,_|\__|
                                 |_| XML parser

   Copyright (c) 2000      Clark Cooper <coopercc@users.sourceforge.net>
   Copyright (c) 2000-2004 Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
   Copyright (c) 2002-2012 Karl Waclawek <karl@waclawek.net>
   Copyright (c) 2017-2026 Sebastian Pipping <sebastian@pipping.org>
   Copyright (c) 2017      Jakub Wilk <jwilk@jwilk.net>
   Copyright (c) 2021      Tomas Korbar <tkorbar@redhat.com>
   Copyright (c) 2021      Nicolas Cavallari <nicolas.cavallari@green-communications.fr>
   Copyright (c) 2022      Thijs Schreijer <thijs@thijsschreijer.nl>
   Copyright (c) 2023-2025 Hanno Böck <hanno@gentoo.org>
   Copyright (c) 2023      Sony Corporation / Snild Dolkow <snild@sony.com>
   Licensed under the MIT license:

   Permission is  hereby granted,  free of charge,  to any  person obtaining
   a  copy  of  this  software   and  associated  documentation  files  (the
   "Software"),  to  deal in  the  Software  without restriction,  including
   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
   distribute, sublicense, and/or sell copies of the Software, and to permit
   persons  to whom  the Software  is  furnished to  do so,  subject to  the
   following conditions:

   The above copyright  notice and this permission notice  shall be included
   in all copies or substantial portions of the Software.

   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
   USE OR OTHER DEALINGS IN THE SOFTWARE.
-->

    <title>
      Expat XML Parser
    </title>
    <meta name="author" content="Clark Cooper, coopercc@netheaven.com" />
    <link href="ok.min.css" rel="stylesheet" />
    <link href="style.css" rel="stylesheet" />
  </head>
  <body>
    <div>
      <h1>
        The Expat XML Parser <small>Release 2.7.5</small>
      </h1>
    </div>

    <div class="content">
      <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 implementation 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="https://libexpat.github.io/">the
        Expat home page</a>.
      </p>

      <p>
        The bulk of this document was originally commissioned as an article by <a href=
        "https://www.xml.com/">XML.com</a>. They graciously allowed Clark Cooper to
        retain copyright and to distribute it with Expat. This version has been
        substantially extended to include documentation on features which have been added
        since the original article was published, and additional information on using the
        original interface.
      </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>

                <li>
                  <a href="#XML_StopParser">XML_StopParser</a>
                </li>

                <li>
                  <a href="#XML_ResumeParser">XML_ResumeParser</a>
                </li>

                <li>
                  <a href="#XML_GetParsingStatus">XML_GetParsingStatus</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_SetExternalEntityRefHandlerArg">XML_SetExternalEntityRefHandlerArg</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="#attack-protection">Attack Protection</a>
              <ul>
                <li>
                  <a href=
                  "#XML_SetBillionLaughsAttackProtectionMaximumAmplification">XML_SetBillionLaughsAttackProtectionMaximumAmplification</a>
                </li>

                <li>
                  <a href=
                  "#XML_SetBillionLaughsAttackProtectionActivationThreshold">XML_SetBillionLaughsAttackProtectionActivationThreshold</a>
                </li>

                <li>
                  <a href=
                  "#XML_SetAllocTrackerMaximumAmplification">XML_SetAllocTrackerMaximumAmplification</a>
                </li>

                <li>
                  <a href=
                  "#XML_SetAllocTrackerActivationThreshold">XML_SetAllocTrackerActivationThreshold</a>
                </li>

                <li>
                  <a href=
                  "#XML_SetReparseDeferralEnabled">XML_SetReparseDeferralEnabled</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_GetAttributeInfo">XML_GetAttributeInfo</a>
                </li>

                <li>
                  <a href="#XML_SetEncoding">XML_SetEncoding</a>
                </li>

                <li>
                  <a href="#XML_SetParamEntityParsing">XML_SetParamEntityParsing</a>
                </li>

                <li>
                  <a href="#XML_SetHashSalt">XML_SetHashSalt</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>

                <li>
                  <a href="#XML_FreeContentModel">XML_FreeContentModel</a>
                </li>

                <li>
                  <a href="#XML_MemMalloc">XML_MemMalloc</a>
                </li>

                <li>
                  <a href="#XML_MemRealloc">XML_MemRealloc</a>
                </li>

                <li>
                  <a href="#XML_MemFree">XML_MemFree</a>
                </li>
              </ul>
            </li>
          </ul>
        </li>
      </ul>

      <hr />

      <h2>
        <a id="overview" 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 XMLCALL
start(void *data, const char *el, const char **attr) {
  int i;

  for (i = 0; i &lt; 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 XMLCALL
end(void *data, const char *el) {
  Depth--;
}  /* End of end handler */
</pre>
      <p>
        Note the <code>XMLCALL</code> annotation used for the callbacks. This is used to
        ensure that the Expat and the callbacks are using the same calling convention in
        case the compiler options used for Expat itself and the client code are
        different. Expat tries not to care what the default calling convention is, though
        it may require that it be compiled with a default convention of "cdecl" on some
        platforms. For code which uses Expat, however, the calling convention is
        specified by the <code>XMLCALL</code> annotation on most platforms; callbacks
        should be defined using this annotation.
      </p>

      <p>
        The <code>XMLCALL</code> annotation was added in Expat 1.95.7, but existing
        working Expat applications don't need to add it (since they are already using the
        "cdecl" calling convention, or they wouldn't be working). The annotation is only
        needed if the default calling convention may be something other than "cdecl". To
        use the annotation safely with older versions of Expat, you can conditionally
        define it <em>after</em> including Expat's header file:
      </p>

      <pre class="eg">
#include &lt;expat.h&gt;

#ifndef XMLCALL
#if defined(_MSC_VER) &amp;&amp; !defined(__BEOS__) &amp;&amp; !defined(__CYGWIN__)
#define XMLCALL __cdecl
#elif defined(__GNUC__)
#define XMLCALL __attribute__((cdecl))
#else
#define XMLCALL
#endif
#endif
</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 id="building" 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=
        "https://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, you
        can use CMake to generate a <code>.sln</code> file, e.g. <code>cmake -G"Visual
        Studio 17 2022" -DCMAKE_BUILD_TYPE=RelWithDebInfo .</code> , and build Expat
        using <code>msbuild /m expat.sln</code> after.
      </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>

      <h3>
        Configuring Expat Using the Pre-Processor
      </h3>

      <p>
        Expat's feature set can be configured using a small number of pre-processor
        definitions. The symbols are:
      </p>

      <dl class="cpp-symbols">
        <dt>
          <a id="XML_GE" name="XML_GE">XML_GE</a>
        </dt>

        <dd>
          Added in Expat 2.6.0. Include support for <a href=
          "https://www.w3.org/TR/2006/REC-xml-20060816/#sec-physical-struct">general
          entities</a> (syntax <code>&amp;e1;</code> to reference and syntax
          <code>&lt;!ENTITY e1 'value1'&gt;</code> (an internal general entity) or
          <code>&lt;!ENTITY e2 SYSTEM 'file2'&gt;</code> (an external general entity) to
          declare). With <code>XML_GE</code> enabled, general entities will be replaced
          by their declared replacement text; for this to work for <em>external</em>
          general entities, in addition an <code><a href=
          "#XML_SetExternalEntityRefHandler">XML_ExternalEntityRefHandler</a></code> must
          be set using <code><a href=
          "#XML_SetExternalEntityRefHandler">XML_SetExternalEntityRefHandler</a></code>.
          Also, enabling <code>XML_GE</code> makes the functions <code><a href=
          "#XML_SetBillionLaughsAttackProtectionMaximumAmplification">XML_SetBillionLaughsAttackProtectionMaximumAmplification</a></code>
          and <code><a href=
          "#XML_SetBillionLaughsAttackProtectionActivationThreshold">XML_SetBillionLaughsAttackProtectionActivationThreshold</a></code>
          available.<br />
          With <code>XML_GE</code> disabled, Expat has a smaller memory footprint and can
          be faster, but will not load external general entities and will replace all
          general entities (except the <a href=
          "https://www.w3.org/TR/2006/REC-xml-20060816/#sec-predefined-ent">predefined
          five</a>: <code>amp</code>, <code>apos</code>, <code>gt</code>,
          <code>lt</code>, <code>quot</code>) with a self-reference: for example,
          referencing an entity <code>e1</code> via <code>&amp;e1;</code> will be
          replaced by text <code>&amp;e1;</code>.
        </dd>

        <dt>
          <a id="XML_DTD" name="XML_DTD">XML_DTD</a>
        </dt>

        <dd>
          Include support for using and reporting DTD-based content. If this is defined,
          default attribute values from an external DTD subset are reported and attribute
          value normalization occurs based on the type of attributes defined in the
          external subset. Without this, Expat has a smaller memory footprint and can be
          faster, but will not load external parameter entities or process conditional
          sections. If defined, makes the functions <code><a href=
          "#XML_SetBillionLaughsAttackProtectionMaximumAmplification">XML_SetBillionLaughsAttackProtectionMaximumAmplification</a></code>
          and <code><a href=
          "#XML_SetBillionLaughsAttackProtectionActivationThreshold">XML_SetBillionLaughsAttackProtectionActivationThreshold</a></code>
          available.
        </dd>

        <dt>
          <a id="XML_NS" name="XML_NS">XML_NS</a>
        </dt>

        <dd>
          When defined, support for the <cite><a href=
          "https://www.w3.org/TR/REC-xml-names/">Namespaces in XML</a></cite>
          specification is included.
        </dd>

        <dt>
          <a id="XML_UNICODE" name="XML_UNICODE">XML_UNICODE</a>
        </dt>

        <dd>
          When defined, character data reported to the application is encoded in UTF-16
          using wide characters of the type <code>XML_Char</code>. This is implied if
          <code>XML_UNICODE_WCHAR_T</code> is defined.
        </dd>

        <dt>
          <a id="XML_UNICODE_WCHAR_T" name="XML_UNICODE_WCHAR_T">XML_UNICODE_WCHAR_T</a>
        </dt>

        <dd>
          If defined, causes the <code>XML_Char</code> character type to be defined using
          the <code>wchar_t</code> type; otherwise, <code>unsigned short</code> is used.
          Defining this implies <code>XML_UNICODE</code>.
        </dd>

        <dt>
          <a id="XML_LARGE_SIZE" name="XML_LARGE_SIZE">XML_LARGE_SIZE</a>
        </dt>

        <dd>
          If defined, causes the <code>XML_Size</code> and <code>XML_Index</code> integer
          types to be at least 64 bits in size. This is intended to support processing of
          very large input streams, where the return values of <code><a href=
          "#XML_GetCurrentByteIndex">XML_GetCurrentByteIndex</a></code>, <code><a href=
          "#XML_GetCurrentLineNumber">XML_GetCurrentLineNumber</a></code> and
          <code><a href=
          "#XML_GetCurrentColumnNumber">XML_GetCurrentColumnNumber</a></code> could
          overflow. It may not be supported by all compilers, and is turned off by
          default.
        </dd>

        <dt>
          <a id="XML_CONTEXT_BYTES" name="XML_CONTEXT_BYTES">XML_CONTEXT_BYTES</a>
        </dt>

        <dd>
          The number of input bytes of markup context which the parser will ensure are
          available for reporting via <code><a href=
          "#XML_GetInputContext">XML_GetInputContext</a></code>. This is normally set to
          1024, and must be set to a positive integer to enable. If this is set to zero,
          the input context will not be available and <code><a href=
          "#XML_GetInputContext">XML_GetInputContext</a></code> will always report
          <code>NULL</code>. Without this, Expat has a smaller memory footprint and can
          be faster.
        </dd>

        <dt>
          <a id="XML_STATIC" name="XML_STATIC">XML_STATIC</a>
        </dt>

        <dd>
          On Windows, this should be set if Expat is going to be linked statically with
          the code that calls it; this is required to get all the right MSVC magic
          annotations correct. This is ignored on other platforms.
        </dd>

        <dt>
          <a id="XML_ATTR_INFO" name="XML_ATTR_INFO">XML_ATTR_INFO</a>
        </dt>

        <dd>
          If defined, makes the additional function <code><a href=
          "#XML_GetAttributeInfo">XML_GetAttributeInfo</a></code> available for reporting
          attribute byte offsets.
        </dd>
      </dl>

      <hr />

      <h2>
        <a id="using" 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 &lt;expat.h&gt;</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 library 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-&gt;skip = 0;
  info-&gt;depth = 1;
  /* Other initializations here */
}  /* End of init_info */

void XMLCALL
rawstart(void *data, const char *el, const char **attr) {
  Parseinfo *inf = (Parseinfo *) data;

  if (! inf-&gt;skip) {
    if (should_skip(inf, el, attr)) {
      inf-&gt;skip = inf-&gt;depth;
    }
    else
      start(inf, el, attr);     /* This does rest of start handling */
  }

  inf-&gt;depth++;
}  /* End of rawstart */

void XMLCALL
rawend(void *data, const char *el) {
  Parseinfo *inf = (Parseinfo *) data;

  inf-&gt;depth--;

  if (! inf-&gt;skip)
    end(inf, el);              /* This does rest of end handling */

  if (inf-&gt;skip == inf-&gt;depth)
    inf-&gt;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 the first argument received by most handlers.
        In the <a href="#reference">reference section</a>, an argument to a callback
        function is named <code>userData</code> and have type <code>void *</code> if the
        user data is passed; it will have the type <code>XML_Parser</code> if the parser
        itself is passed. When the parser is passed, the user data may be retrieved using
        <code><a href="#XML_GetUserData">XML_GetUserData</a></code>.
      </p>

      <p>
        One common case where multiple calls to a single handler may need to communicate
        using an application data structure is the case when content passed to the
        character data handler (set by <code><a href=
        "#XML_SetCharacterDataHandler">XML_SetCharacterDataHandler</a></code>) needs to
        be accumulated. A common first-time mistake with any of the event-oriented
        interfaces to an XML parser is to expect all the text contained in an element to
        be reported by a single call to the character data handler. Expat, like many
        other XML parsers, reports such data as a sequence of calls; there's no way to
        know when the end of the sequence is reached until a different callback is made.
        A buffer referenced by the user data structure proves both an effective and
        convenient place to accumulate character data.
      </p>
      <!-- XXX example needed here -->

      <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 XMLCALL
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 &lt; (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 not well-formed when namespace processing is enabled, and will
        trigger an error. 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 after 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 <code>NULL</code>. The URI will be <code>NULL</code> 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>
&lt;?xml version="1.0" encoding="ISO-8859-2"?&gt;
</pre>
      <p>
        External parsed entities may begin with a text declaration, which looks like an
        XML declaration with just an encoding declaration:
      </p>

      <pre>
&lt;?xml encoding="Big5"?&gt;
</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 id="builtin_encodings" 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 <code>XML_STATUS_OK</code> if it knows how to
        deal with the encoding. Otherwise the handler should return
        <code>XML_STATUS_ERROR</code>. 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 entities 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>

      <h3 id="stop-resume">
        Temporarily Stopping Parsing
      </h3>

      <p>
        Expat 1.95.8 introduces a new feature: its now possible to stop parsing
        temporarily from within a handler function, even if more data has already been
        passed into the parser. Applications for this include
      </p>

      <ul>
        <li>Supporting the <a href="https://www.w3.org/TR/xinclude/">XInclude</a>
        specification.
        </li>

        <li>Delaying further processing until additional information is available from
        some other source.
        </li>

        <li>Adjusting processor load as task priorities shift within an application.
        </li>

        <li>Stopping parsing completely (simply free or reset the parser instead of
        resuming in the outer parsing loop). This can be useful if an application-domain
        error is found in the XML being parsed or if the result of the parse is
        determined not to be useful after all.
        </li>
      </ul>

      <p>
        To take advantage of this feature, the main parsing loop of an application needs
        to support this specifically. It cannot be supported with a parsing loop
        compatible with Expat 1.95.7 or earlier (though existing loops will continue to
        work without supporting the stop/resume feature).
      </p>

      <p>
        An application that uses this feature for a single parser will have the rough
        structure (in pseudo-code):
      </p>

      <pre class="pseudocode">
fd = open_input()
p = create_parser()

if parse_xml(p, fd) {
  /* suspended */

  int suspended = 1;

  while (suspended) {
    do_something_else()
    if ready_to_resume() {
      suspended = continue_parsing(p, fd);
    }
  }
}
</pre>
      <p>
        An application that may resume any of several parsers based on input (either from
        the XML being parsed or some other source) will certainly have more interesting
        control structures.
      </p>

      <p>
        This C function could be used for the <code>parse_xml</code> function mentioned
        in the pseudo-code above:
      </p>

      <pre class="eg">
#define BUFF_SIZE 10240

/* Parse a document from the open file descriptor 'fd' until the parse
   is complete (the document has been completely parsed, or there's
   been an error), or the parse is stopped.  Return non-zero when
   the parse is merely suspended.
*/
int
parse_xml(XML_Parser p, int fd)
{
  for (;;) {
    int last_chunk;
    int bytes_read;
    enum XML_Status status;

    void *buff = XML_GetBuffer(p, BUFF_SIZE);
    if (buff == NULL) {
      /* handle error... */
      return 0;
    }
    bytes_read = read(fd, buff, BUFF_SIZE);
    if (bytes_read &lt; 0) {
      /* handle error... */
      return 0;
    }
    status = XML_ParseBuffer(p, bytes_read, bytes_read == 0);
    switch (status) {
      case XML_STATUS_ERROR:
        /* handle error... */
        return 0;
      case XML_STATUS_SUSPENDED:
        return 1;
    }
    if (bytes_read == 0)
      return 0;
  }
}
</pre>
      <p>
        The corresponding <code>continue_parsing</code> function is somewhat simpler,
        since it only need deal with the return code from <code><a href=
        "#XML_ResumeParser">XML_ResumeParser</a></code>; it can delegate the input
        handling to the <code>parse_xml</code> function:
      </p>

      <pre class="eg">
/* Continue parsing a document which had been suspended.  The 'p' and
   'fd' arguments are the same as passed to parse_xml().  Return
   non-zero when the parse is suspended.
*/
int
continue_parsing(XML_Parser p, int fd)
{
  enum XML_Status status = XML_ResumeParser(p);
  switch (status) {
    case XML_STATUS_ERROR:
      /* handle error... */
      return 0;
    case XML_ERROR_NOT_SUSPENDED:
      /* handle error... */
      return 0;.
    case XML_STATUS_SUSPENDED:
      return 1;
  }
  return parse_xml(p, fd);
}
</pre>
      <p>
        Now that we've seen what a mess the top-level parsing loop can become, what have
        we gained? Very simply, we can now use the <code><a href=
        "#XML_StopParser">XML_StopParser</a></code> function to stop parsing, without
        having to go to great lengths to avoid additional processing that we're expecting
        to ignore. As a bonus, we get to stop parsing <em>temporarily</em>, and come back
        to it when we're ready.
      </p>

      <p>
        To stop parsing from a handler function, use the <code><a href=
        "#XML_StopParser">XML_StopParser</a></code> function. This function takes two
        arguments; the parser being stopped and a flag indicating whether the parse can
        be resumed in the future.
      </p>
      <!-- XXX really need more here -->

      <hr />
      <!-- ================================================================ -->

      <h2>
        <a id="reference" name="reference">Expat Reference</a>
      </h2>

      <h3>
        <a id="creation" name="creation">Parser Creation</a>
      </h3>

      <h4 id="XML_ParserCreate">
        XML_ParserCreate
      </h4>

      <pre class="fcndec">
XML_Parser XMLCALL
XML_ParserCreate(const XML_Char *encoding);
</pre>
      <div class="fcndef">
        <p>
          Construct a new parser. If encoding is non-<code>NULL</code>, it specifies a
          character encoding to use for the document. This overrides the document
          encoding declaration. There are four built-in encodings:
        </p>

        <ul>
          <li>US-ASCII
          </li>

          <li>UTF-8
          </li>

          <li>UTF-16
          </li>

          <li>ISO-8859-1
          </li>
        </ul>

        <p>
          Any other value will invoke a call to the UnknownEncodingHandler.
        </p>
      </div>

      <h4 id="XML_ParserCreateNS">
        XML_ParserCreateNS
      </h4>

      <pre class="fcndec">
XML_Parser XMLCALL
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 an URI. Since
        Expat does not check namespace URIs for conformance, the only safe choice for a
        namespace separator is a character that is illegal in XML. For instance,
        <code>'\xFF'</code> is not legal in UTF-8, and <code>'\xFFFF'</code> is not legal
        in UTF-16. There is a special case when <em>sep</em> is the null character
        <code>'\0'</code>: the namespace URI and the local part will be concatenated
        without any separator - this is intended to support RDF processors. It is a
        programming error to use the null separator with <a href=
        "#XML_SetReturnNSTriplet">namespace triplets</a>.
      </div>

      <p>
        <strong>Note:</strong> Expat does not validate namespace URIs (beyond encoding)
        against RFC 3986 today (and is not required to do so with regard to the XML 1.0
        namespaces specification) but it may start doing that in future releases. Before
        that, an application using Expat must be ready to receive namespace URIs
        containing non-URI characters.
      </p>

      <h4 id="XML_ParserCreate_MM">
        XML_ParserCreate_MM
      </h4>

      <pre class="fcndec">
XML_Parser XMLCALL
XML_ParserCreate_MM(const XML_Char *encoding,
                    const XML_Memory_Handling_Suite *ms,
                    const XML_Char *sep);
</pre>

      <pre class="signature">
typedef struct {
  void *(XMLCALL *malloc_fcn)(size_t size);
  void *(XMLCALL *realloc_fcn)(void *ptr, size_t size);
  void (XMLCALL *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 <code>NULL</code>, then use the
          standard set of memory management functions. If <code>sep</code> is
          non-<code>NULL</code>, 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>

      <h4 id="XML_ExternalEntityParserCreate">
        XML_ExternalEntityParserCreate
      </h4>

      <pre class="fcndec">
XML_Parser XMLCALL
XML_ExternalEntityParserCreate(XML_Parser p,
                               const XML_Char *context,
                               const XML_Char *encoding);
</pre>
      <div class="fcndef">
        <p>
          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).
        </p>

        <p>
          <strong>Note:</strong> Please be sure to free subparsers created by
          <code><a href=
          "#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a></code>
          <em>prior to</em> freeing their related parent parser, as subparsers reference
          and use parts of their respective parent parser, internally. Parent parsers
          must outlive subparsers.
        </p>
      </div>

      <h4 id="XML_ParserFree">
        XML_ParserFree
      </h4>

      <pre class="fcndec">
void XMLCALL
XML_ParserFree(XML_Parser p);
</pre>
      <div class="fcndef">
        <p>
          Free memory used by the parser.
        </p>

        <p>
          <strong>Note:</strong> Your application is responsible for freeing any memory
          associated with <a href="#userdata">user data</a>.
        </p>

        <p>
          <strong>Note:</strong> Please be sure to free subparsers created by
          <code><a href=
          "#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a></code>
          <em>prior to</em> freeing their related parent parser, as subparsers reference
          and use parts of their respective parent parser, internally. Parent parsers
          must outlive subparsers.
        </p>
      </div>

      <h4 id="XML_ParserReset">
        XML_ParserReset
      </h4>

      <pre class="fcndec">
XML_Bool XMLCALL
XML_ParserReset(XML_Parser p,
                const XML_Char *encoding);
</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. All handlers are cleared from the parser, except for the
        unknownEncodingHandler. The parser's external state is re-initialized except for
        the values of ns and ns_triplets. 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 id="parsing" 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>

      <p>
        Note: The <code>len</code> argument passed to these functions should be
        considerably less than the maximum value for an integer, as it could create an
        integer overflow situation if the added lengths of a buffer and the unprocessed
        portion of the previous buffer exceed the maximum integer value. Input data at
        the end of a buffer will remain unprocessed if it is part of an XML token for
        which the end is not part of that buffer.
      </p>

      <p>
        <a id="isFinal" name="isFinal"></a>The application <em>must</em> make a
        concluding <code><a href="#XML_Parse">XML_Parse</a></code> or <code><a href=
        "#XML_ParseBuffer">XML_ParseBuffer</a></code> call with <code>isFinal</code> set
        to <code>XML_TRUE</code>.
      </p>

      <h4 id="XML_Parse">
        XML_Parse
      </h4>

      <pre class="fcndec">
enum XML_Status XMLCALL
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">
        <p>
          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. Negative values for
          <code>len</code> are rejected since Expat 2.2.1. 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.)
        </p>

        <p>
          If a parse error occurred, it returns <code>XML_STATUS_ERROR</code>. Otherwise
          it returns <code>XML_STATUS_OK</code> value. Note that regardless of the return
          value, there is no guarantee that all provided input has been parsed; only
          after <a href="#isFinal">the concluding call</a> will all handler callbacks and
          parsing errors have happened.
        </p>

        <p>
          Simplified, <code>XML_Parse</code> can be considered a convenience wrapper that
          is pairing calls to <code><a href="#XML_GetBuffer">XML_GetBuffer</a></code> and
          <code><a href="#XML_ParseBuffer">XML_ParseBuffer</a></code> (when Expat is
          built with macro <code>XML_CONTEXT_BYTES</code> defined to a positive value,
          which is both common and default). <code>XML_Parse</code> is then functionally
          equivalent to calling <code><a href="#XML_GetBuffer">XML_GetBuffer</a></code>,
          <code>memcpy</code>, and <code><a href=
          "#XML_ParseBuffer">XML_ParseBuffer</a></code>.
        </p>

        <p>
          To avoid double copying of the input, direct use of functions <code><a href=
          "#XML_GetBuffer">XML_GetBuffer</a></code> and <code><a href=
          "#XML_ParseBuffer">XML_ParseBuffer</a></code> is advised for most production
          use, e.g. if you're using <code>read</code> or similar functionality to fill
          your buffers, fill directly into the buffer from <code><a href=
          "#XML_GetBuffer">XML_GetBuffer</a></code>, then parse with <code><a href=
          "#XML_ParseBuffer">XML_ParseBuffer</a></code>.
        </p>
      </div>

      <h4 id="XML_ParseBuffer">
        XML_ParseBuffer
      </h4>

      <pre class="fcndec">
enum XML_Status XMLCALL
XML_ParseBuffer(XML_Parser p,
                int len,
                int isFinal);
</pre>
      <div class="fcndef">
        <p>
          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.
        </p>

        <p>
          Negative values for <code>len</code> are rejected since Expat 2.6.3.
        </p>
      </div>

      <h4 id="XML_GetBuffer">
        XML_GetBuffer
      </h4>

      <pre class="fcndec">
void * XMLCALL
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
        <code>NULL</code> value is returned if Expat can't allocate enough memory for
        this buffer. A <code>NULL</code> value may also be returned if <code>len</code>
        is zero. 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 &lt; 0) {
    /* handle error */
  }

  if (! XML_ParseBuffer(p, bytes_read, bytes_read == 0)) {
    /* handle parse error */
  }

  if (bytes_read == 0)
    break;
}
</pre>
      </div>

      <h4 id="XML_StopParser">
        XML_StopParser
      </h4>

      <pre class="fcndec">
enum XML_Status XMLCALL
XML_StopParser(XML_Parser p,
               XML_Bool resumable);
</pre>
      <div class="fcndef">
        <p>
          Stops parsing, causing <code><a href="#XML_Parse">XML_Parse</a></code> or
          <code><a href="#XML_ParseBuffer">XML_ParseBuffer</a></code> to return. Must be
          called from within a call-back handler, except when aborting (when
          <code>resumable</code> is <code>XML_FALSE</code>) an already suspended parser.
          Some call-backs may still follow because they would otherwise get lost,
          including
        </p>

        <ul>
          <li>the end element handler for empty elements when stopped in the start
          element handler,
          </li>

          <li>the end namespace declaration handler when stopped in the end element
          handler,
          </li>

          <li>the character data handler when stopped in the character data handler while
          making multiple call-backs on a contiguous chunk of characters,
          </li>
        </ul>

        <p>
          and possibly others.
        </p>

        <p>
          This can be called from most handlers, including DTD related call-backs, except
          when parsing an external parameter entity and <code>resumable</code> is
          <code>XML_TRUE</code>. Returns <code>XML_STATUS_OK</code> when successful,
          <code>XML_STATUS_ERROR</code> otherwise. The possible error codes are:
        </p>

        <dl>
          <dt>
            <code>XML_ERROR_NOT_STARTED</code>
          </dt>

          <dd>
            when stopping or suspending a parser before it has started, added in Expat
            2.6.4.
          </dd>

          <dt>
            <code>XML_ERROR_SUSPENDED</code>
          </dt>

          <dd>
            when suspending an already suspended parser.
          </dd>

          <dt>
            <code>XML_ERROR_FINISHED</code>
          </dt>

          <dd>
            when the parser has already finished.
          </dd>

          <dt>
            <code>XML_ERROR_SUSPEND_PE</code>
          </dt>

          <dd>
            when suspending while parsing an external PE.
          </dd>
        </dl>

        <p>
          Since the stop/resume feature requires application support in the outer parsing
          loop, it is an error to call this function for a parser not being handled
          appropriately; see <a href="#stop-resume">Temporarily Stopping Parsing</a> for
          more information.
        </p>

        <p>
          When <code>resumable</code> is <code>XML_TRUE</code> then parsing is
          <em>suspended</em>, that is, <code><a href="#XML_Parse">XML_Parse</a></code>
          and <code><a href="#XML_ParseBuffer">XML_ParseBuffer</a></code> return
          <code>XML_STATUS_SUSPENDED</code>. Otherwise, parsing is <em>aborted</em>, that
          is, <code><a href="#XML_Parse">XML_Parse</a></code> and <code><a href=
          "#XML_ParseBuffer">XML_ParseBuffer</a></code> return
          <code>XML_STATUS_ERROR</code> with error code <code>XML_ERROR_ABORTED</code>.
        </p>

        <p>
          <strong>Note:</strong> This will be applied to the current parser instance
          only, that is, if there is a parent parser then it will continue parsing when
          the external entity reference handler returns. It is up to the implementation
          of that handler to call <code><a href=
          "#XML_StopParser">XML_StopParser</a></code> on the parent parser (recursively),
          if one wants to stop parsing altogether.
        </p>

        <p>
          When suspended, parsing can be resumed by calling <code><a href=
          "#XML_ResumeParser">XML_ResumeParser</a></code>.
        </p>

        <p>
          New in Expat 1.95.8.
        </p>
      </div>

      <h4 id="XML_ResumeParser">
        XML_ResumeParser
      </h4>

      <pre class="fcndec">
enum XML_Status XMLCALL
XML_ResumeParser(XML_Parser p);
</pre>
      <div class="fcndef">
        <p>
          Resumes parsing after it has been suspended with <code><a href=
          "#XML_StopParser">XML_StopParser</a></code>. Must not be called from within a
          handler call-back. Returns same status codes as <code><a href=
          "#XML_Parse">XML_Parse</a></code> or <code><a href=
          "#XML_ParseBuffer">XML_ParseBuffer</a></code>. An additional error code,
          <code>XML_ERROR_NOT_SUSPENDED</code>, will be returned if the parser was not
          currently suspended.
        </p>

        <p>
          <strong>Note:</strong> This must be called on the most deeply nested child
          parser instance first, and on its parent parser only after the child parser has
          finished, to be applied recursively until the document entity's parser is
          restarted. That is, the parent parser will not resume by itself and it is up to
          the application to call <code><a href=
          "#XML_ResumeParser">XML_ResumeParser</a></code> on it at the appropriate
          moment.
        </p>

        <p>
          New in Expat 1.95.8.
        </p>
      </div>

      <h4 id="XML_GetParsingStatus">
        XML_GetParsingStatus
      </h4>

      <pre class="fcndec">
void XMLCALL
XML_GetParsingStatus(XML_Parser p,
                     XML_ParsingStatus *status);
</pre>

      <pre class="signature">
enum XML_Parsing {
  XML_INITIALIZED,
  XML_PARSING,
  XML_FINISHED,
  XML_SUSPENDED
};

typedef struct {
  enum XML_Parsing parsing;
  XML_Bool finalBuffer;
} XML_ParsingStatus;
</pre>
      <div class="fcndef">
        <p>
          Returns status of parser with respect to being initialized, parsing, finished,
          or suspended, and whether the final buffer is being processed. The
          <code>status</code> parameter <em>must not</em> be <code>NULL</code>.
        </p>

        <p>
          New in Expat 1.95.8.
        </p>
      </div>

      <h3>
        <a id="setting" 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 <code>NULL</code> 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 conditionally defined in expat.h as either <code>char</code>,
        <code>wchar_t</code> or <code>unsigned short</code>. The former implies UTF-8
        encoding, the latter two imply UTF-16 encoding. Note that you'll receive them in
        this form independent of the original encoding of the document.
      </p>

      <div class="handler">
        <h4 id="XML_SetStartElementHandler">
          XML_SetStartElementHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetStartElementHandler(XML_Parser p,
                           XML_StartElementHandler start);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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
          <code>NULL</code> 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">
        <h4 id="XML_SetEndElementHandler">
          XML_SetEndElementHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetEndElementHandler(XML_Parser p,
                         XML_EndElementHandler);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetElementHandler">
          XML_SetElementHandler
        </h4>

        <pre class="setter">
void XMLCALL
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">
        <h4 id="XML_SetCharacterDataHandler">
          XML_SetCharacterDataHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetCharacterDataHandler(XML_Parser p,
                            XML_CharacterDataHandler charhndl)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *XML_CharacterDataHandler)(void *userData,
                                    const XML_Char *s,
                                    int len);
</pre>
        <p>
          Set a text handler. The string your handler receives is <em>NOT
          null-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. Note: Setting this handler to <code>NULL</code> may <em>NOT
          immediately</em> terminate call-backs if the parser is currently processing
          such a single block of contiguous markup-free text, as the parser will continue
          calling back until the end of the block is reached.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetProcessingInstructionHandler">
          XML_SetProcessingInstructionHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetProcessingInstructionHandler(XML_Parser p,
                                    XML_ProcessingInstructionHandler proc)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetCommentHandler">
          XML_SetCommentHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetCommentHandler(XML_Parser p,
                      XML_CommentHandler cmnt)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetStartCdataSectionHandler">
          XML_SetStartCdataSectionHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetStartCdataSectionHandler(XML_Parser p,
                                XML_StartCdataSectionHandler start);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *XML_StartCdataSectionHandler)(void *userData);
</pre>
        <p>
          Set a handler that gets called at the beginning of a CDATA section.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetEndCdataSectionHandler">
          XML_SetEndCdataSectionHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetEndCdataSectionHandler(XML_Parser p,
                              XML_EndCdataSectionHandler end);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *XML_EndCdataSectionHandler)(void *userData);
</pre>
        <p>
          Set a handler that gets called at the end of a CDATA section.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetCdataSectionHandler">
          XML_SetCdataSectionHandler
        </h4>

        <pre class="setter">
void XMLCALL
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">
        <h4 id="XML_SetDefaultHandler">
          XML_SetDefaultHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetDefaultHandler(XML_Parser p,
                      XML_DefaultHandler hndl)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetDefaultHandlerExpand">
          XML_SetDefaultHandlerExpand
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetDefaultHandlerExpand(XML_Parser p,
                            XML_DefaultHandler hndl)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetExternalEntityRefHandler">
          XML_SetExternalEntityRefHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetExternalEntityRefHandler(XML_Parser p,
                                XML_ExternalEntityRefHandler hndl)
</pre>

        <pre class="signature">
typedef int
(XMLCALL *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>
          <strong>Warning:</strong> Using an external entity reference handler can lead
          to <a href="https://libexpat.github.io/doc/xml-security/#external-entities">XXE
          vulnerabilities</a>. It should only be used in applications that do not parse
          untrusted XML input.
        </p>

        <p>
          The <code>context</code> parameter specifies the parsing context in the format
          expected by the <code>context</code> argument to <code><a href=
          "#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a></code>.
          <code>code</code> is valid only until the handler returns, so if the referenced
          entity is to be parsed later, it must be copied. <code>context</code> is
          <code>NULL</code> only when the entity is a parameter entity, which is how one
          can differentiate between general and parameter entities.
        </p>

        <p>
          The <code>base</code> parameter is the base to use for relative system
          identifiers. It is set by <code><a href="#XML_SetBase">XML_SetBase</a></code>
          and may be <code>NULL</code>. The <code>publicId</code> parameter is the public
          id given in the entity declaration and may be <code>NULL</code>.
          <code>systemId</code> is the system identifier specified in the entity
          declaration and is never <code>NULL</code>.
        </p>

        <p>
          There are a couple of ways in which this handler differs from others. First,
          this handler returns a status indicator (an integer).
          <code>XML_STATUS_OK</code> should be returned for successful handling of the
          external entity reference. Returning <code>XML_STATUS_ERROR</code> indicates
          failure, and causes the calling parser to return an
          <code>XML_ERROR_EXTERNAL_ENTITY_HANDLING</code> error.
        </p>

        <p>
          Second, instead of having the user data 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 <code><a href=
          "#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a></code>.
          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>

      <h4 id="XML_SetExternalEntityRefHandlerArg">
        XML_SetExternalEntityRefHandlerArg
      </h4>

      <pre class="fcndec">
void XMLCALL
XML_SetExternalEntityRefHandlerArg(XML_Parser p,
                                   void *arg)
</pre>
      <div class="fcndef">
        <p>
          Set the argument passed to the ExternalEntityRefHandler. If <code>arg</code> is
          not <code>NULL</code>, it is the new value passed to the handler set using
          <code><a href=
          "#XML_SetExternalEntityRefHandler">XML_SetExternalEntityRefHandler</a></code>;
          if <code>arg</code> is <code>NULL</code>, the argument passed to the handler
          function will be the parser object itself.
        </p>

        <p>
          <strong>Note:</strong> The type of <code>arg</code> and the type of the first
          argument to the ExternalEntityRefHandler do not match. This function takes a
          <code>void *</code> to be passed to the handler, while the handler accepts an
          <code>XML_Parser</code>. This is a historical accident, but will not be
          corrected before Expat 2.0 (at the earliest) to avoid causing compiler warnings
          for code that's known to work with this API. It is the responsibility of the
          application code to know the actual type of the argument passed to the handler
          and to manage it properly.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetSkippedEntityHandler">
          XML_SetSkippedEntityHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetSkippedEntityHandler(XML_Parser p,
                            XML_SkippedEntityHandler handler)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetUnknownEncodingHandler">
          XML_SetUnknownEncodingHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetUnknownEncodingHandler(XML_Parser p,
                              XML_UnknownEncodingHandler enchandler,
                              void *encodingHandlerData)
</pre>

        <pre class="signature">
typedef int
(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData,
                                      const XML_Char *name,
                                      XML_Encoding *info);

typedef struct {
  int map[256];
  void *data;
  int (XMLCALL *convert)(void *data, const char *s);
  void (XMLCALL *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
          <code>XML_STATUS_OK</code>. Otherwise it should return
          <code>XML_STATUS_ERROR</code>. 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 leading byte in a byte
          sequence. If the corresponding value is &gt;= 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 &gt; 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 <code>NULL</code> 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> null-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 <code>NULL</code>.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetStartNamespaceDeclHandler">
          XML_SetStartNamespaceDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetStartNamespaceDeclHandler(XML_Parser p,
                                 XML_StartNamespaceDeclHandler start);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetEndNamespaceDeclHandler">
          XML_SetEndNamespaceDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetEndNamespaceDeclHandler(XML_Parser p,
                               XML_EndNamespaceDeclHandler end);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetNamespaceDeclHandler">
          XML_SetNamespaceDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
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">
        <h4 id="XML_SetXmlDeclHandler">
          XML_SetXmlDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetXmlDeclHandler(XML_Parser p,
                      XML_XmlDeclHandler xmldecl);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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 <code>NULL</code> for text
          declarations. The <code>encoding</code> parameter may be <code>NULL</code> 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">
        <h4 id="XML_SetStartDoctypeDeclHandler">
          XML_SetStartDoctypeDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetStartDoctypeDeclHandler(XML_Parser p,
                               XML_StartDoctypeDeclHandler start);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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 <code>NULL</code>. The
          <code>has_internal_subset</code> will be non-zero if the DOCTYPE declaration
          has an internal subset.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetEndDoctypeDeclHandler">
          XML_SetEndDoctypeDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetEndDoctypeDeclHandler(XML_Parser p,
                             XML_EndDoctypeDeclHandler end);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetDoctypeDeclHandler">
          XML_SetDoctypeDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
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">
        <h4 id="XML_SetElementDeclHandler">
          XML_SetElementDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetElementDeclHandler(XML_Parser p,
                          XML_ElementDeclHandler eldecl);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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's the user code's responsibility to free model
          when finished with via a call to <code><a href=
          "#XML_FreeContentModel">XML_FreeContentModel</a></code>. There is no need to
          free the model from the handler, it can be kept around and freed at a later
          stage.
        </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 <code>NULL</code>. 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 <code>NULL</code>. 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">
        <h4 id="XML_SetAttlistDeclHandler">
          XML_SetAttlistDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetAttlistDeclHandler(XML_Parser p,
                          XML_AttlistDeclHandler attdecl);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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
          <code>NULL</code> 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-<code>NULL</code> fixed value in the <code>dflt</code> parameter.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetEntityDeclHandler">
          XML_SetEntityDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetEntityDeclHandler(XML_Parser p,
                         XML_EntityDeclHandler handler);
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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>&lt;!ENTITY foo "bar"&gt;</code>),
          <code>value</code> will be non-<code>NULL</code> and <code>systemId</code>,
          <code>publicId</code>, and <code>notationName</code> will all be
          <code>NULL</code>. 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
          <code>NULL</code>.
        </p>

        <p>
          The <code>notationName</code> argument will have a non-<code>NULL</code> value
          only for unparsed entity declarations.
        </p>
      </div>

      <div class="handler">
        <h4 id="XML_SetUnparsedEntityDeclHandler">
          XML_SetUnparsedEntityDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetUnparsedEntityDeclHandler(XML_Parser p,
                                 XML_UnparsedEntityDeclHandler h)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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>
&lt;!ENTITY logo SYSTEM "images/logo.gif" NDATA gif&gt;
</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">
        <h4 id="XML_SetNotationDeclHandler">
          XML_SetNotationDeclHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetNotationDeclHandler(XML_Parser p,
                           XML_NotationDeclHandler h)
</pre>

        <pre class="signature">
typedef void
(XMLCALL *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">
        <h4 id="XML_SetNotStandaloneHandler">
          XML_SetNotStandaloneHandler
        </h4>

        <pre class="setter">
void XMLCALL
XML_SetNotStandaloneHandler(XML_Parser p,
                            XML_NotStandaloneHandler h)
</pre>

        <pre class="signature">
typedef int
(XMLCALL *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
          <code>XML_STATUS_ERROR</code>, then the parser will throw an
          <code>XML_ERROR_NOT_STANDALONE</code> error.
        </p>
      </div>

      <h3>
        <a id="position" 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
        <code>XML_STATUS_ERROR</code> (a parse error has occurred), 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 <code>XML_STATUS_ERROR</code>.) The exceptions are
        callbacks triggered by declarations in the document prologue, in which case they
        exact position reported is somewhere in the relevant markup, but not necessarily
        as meaningful as for other events.
      </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>

      <h4 id="XML_GetErrorCode">
        XML_GetErrorCode
      </h4>

      <pre class="fcndec">
enum XML_Error XMLCALL
XML_GetErrorCode(XML_Parser p);
</pre>
      <div class="fcndef">
        Return what type of error has occurred.
      </div>

      <h4 id="XML_ErrorString">
        XML_ErrorString
      </h4>

      <pre class="fcndec">
const XML_LChar * XMLCALL
XML_ErrorString(enum XML_Error 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>

      <h4 id="XML_GetCurrentByteIndex">
        XML_GetCurrentByteIndex
      </h4>

      <pre class="fcndec">
XML_Index XMLCALL
XML_GetCurrentByteIndex(XML_Parser p);
</pre>
      <div class="fcndef">
        Return the byte offset of the position. This always corresponds to the values
        returned by <code><a href=
        "#XML_GetCurrentLineNumber">XML_GetCurrentLineNumber</a></code> and
        <code><a href="#XML_GetCurrentColumnNumber">XML_GetCurrentColumnNumber</a></code>.
      </div>

      <h4 id="XML_GetCurrentLineNumber">
        XML_GetCurrentLineNumber
      </h4>

      <pre class="fcndec">
XML_Size XMLCALL
XML_GetCurrentLineNumber(XML_Parser p);
</pre>
      <div class="fcndef">
        Return the line number of the position. The first line is reported as
        <code>1</code>.
      </div>

      <h4 id="XML_GetCurrentColumnNumber">
        XML_GetCurrentColumnNumber
      </h4>

      <pre class="fcndec">
XML_Size XMLCALL
XML_GetCurrentColumnNumber(XML_Parser p);
</pre>
      <div class="fcndef">
        Return the <em>offset</em>, from the beginning of the current line, of the
        position. The first column is reported as <code>0</code>.
      </div>

      <h4 id="XML_GetCurrentByteCount">
        XML_GetCurrentByteCount
      </h4>

      <pre class="fcndec">
int XMLCALL
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>

      <h4 id="XML_GetInputContext">
        XML_GetInputContext
      </h4>

      <pre class="fcndec">
const char * XMLCALL
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>

        <p>
          If <code>XML_CONTEXT_BYTES</code> is zero, this will always return
          <code>NULL</code>.
        </p>
      </div>

      <h3>
        <a id="attack-protection" name="attack-protection">Attack Protection</a><a id=
        "billion-laughs" name="billion-laughs"></a>
      </h3>

      <h4 id="XML_SetBillionLaughsAttackProtectionMaximumAmplification">
        XML_SetBillionLaughsAttackProtectionMaximumAmplification
      </h4>

      <pre class="fcndec">
/* Added in Expat 2.4.0. */
XML_Bool XMLCALL
XML_SetBillionLaughsAttackProtectionMaximumAmplification(XML_Parser p,
                                                         float maximumAmplificationFactor);
</pre>
      <div class="fcndef">
        <p>
          Sets the maximum tolerated amplification factor for protection against <a href=
          "https://en.wikipedia.org/wiki/Billion_laughs_attack">billion laughs
          attacks</a> (default: <code>100.0</code>) of parser <code>p</code> to
          <code>maximumAmplificationFactor</code>, and returns <code>XML_TRUE</code> upon
          success and <code>XML_FALSE</code> upon error.
        </p>

        <p>
          Once the <a href=
          "#XML_SetBillionLaughsAttackProtectionActivationThreshold">threshold for
          activation</a> is reached, the amplification factor is calculated as ..
        </p>

        <pre>amplification := (direct + indirect) / direct</pre>
        <p>
          .. while parsing, whereas <code>direct</code> is the number of bytes read from
          the primary document in parsing and <code>indirect</code> is the number of
          bytes added by expanding entities and reading of external DTD files, combined.
        </p>

        <p>
          For a call to
          <code>XML_SetBillionLaughsAttackProtectionMaximumAmplification</code> to
          succeed:
        </p>

        <ul>
          <li>parser <code>p</code> must be a non-<code>NULL</code> root parser (without
          any parent parsers) and
          </li>

          <li>
            <code>maximumAmplificationFactor</code> must be non-<code>NaN</code> and
            greater than or equal to <code>1.0</code>.
          </li>
        </ul>

        <p>
          <strong>Note:</strong> If you ever need to increase this value for non-attack
          payload, please <a href="https://github.com/libexpat/libexpat/issues">file a
          bug report</a>.
        </p>

        <p>
          <strong>Note:</strong> Peak amplifications of factor 15,000 for the entire
          payload and of factor 30,000 in the middle of parsing have been observed with
          small benign files in practice. So if you do reduce the maximum allowed
          amplification, please make sure that the activation threshold is still big
          enough to not end up with undesired false positives (i.e. benign files being
          rejected).
        </p>
      </div>

      <h4 id="XML_SetBillionLaughsAttackProtectionActivationThreshold">
        XML_SetBillionLaughsAttackProtectionActivationThreshold
      </h4>

      <pre class="fcndec">
/* Added in Expat 2.4.0. */
XML_Bool XMLCALL
XML_SetBillionLaughsAttackProtectionActivationThreshold(XML_Parser p,
                                                        unsigned long long activationThresholdBytes);
</pre>
      <div class="fcndef">
        <p>
          Sets number of output bytes (including amplification from entity expansion and
          reading DTD files) needed to activate protection against <a href=
          "https://en.wikipedia.org/wiki/Billion_laughs_attack">billion laughs
          attacks</a> (default: <code>8 MiB</code>) of parser <code>p</code> to
          <code>activationThresholdBytes</code>, and returns <code>XML_TRUE</code> upon
          success and <code>XML_FALSE</code> upon error.
        </p>

        <p>
          For a call to
          <code>XML_SetBillionLaughsAttackProtectionActivationThreshold</code> to
          succeed:
        </p>

        <ul>
          <li>parser <code>p</code> must be a non-<code>NULL</code> root parser (without
          any parent parsers).
          </li>
        </ul>

        <p>
          <strong>Note:</strong> If you ever need to increase this value for non-attack
          payload, please <a href="https://github.com/libexpat/libexpat/issues">file a
          bug report</a>.
        </p>

        <p>
          <strong>Note:</strong> Activation thresholds below 4 MiB are known to break
          support for <a href=
          "https://en.wikipedia.org/wiki/Darwin_Information_Typing_Architecture">DITA</a>
          1.3 payload and are hence not recommended.
        </p>
      </div>

      <h4 id="XML_SetAllocTrackerMaximumAmplification">
        XML_SetAllocTrackerMaximumAmplification
      </h4>

      <pre class="fcndec">
/* Added in Expat 2.7.2. */
XML_Bool
XML_SetAllocTrackerMaximumAmplification(XML_Parser p,
                                        float maximumAmplificationFactor);
</pre>
      <div class="fcndef">
        <p>
          Sets the maximum tolerated amplification factor between direct input and bytes
          of dynamic memory allocated (default: <code>100.0</code>) of parser
          <code>p</code> to <code>maximumAmplificationFactor</code>, and returns
          <code>XML_TRUE</code> upon success and <code>XML_FALSE</code> upon error.
        </p>

        <p>
          <strong>Note:</strong> There are three types of allocations that intentionally
          bypass tracking and limiting:
        </p>

        <ul>
          <li>application calls to functions <code><a href=
          "#XML_MemMalloc">XML_MemMalloc</a></code> and <code><a href="#XML_MemRealloc">
            XML_MemRealloc</a></code> — <em>healthy</em> use of these two functions
            continues to be a responsibility of the application using Expat —,
          </li>

          <li>the main character buffer used by functions <code><a href="#XML_GetBuffer">
            XML_GetBuffer</a></code> and <code><a href=
            "#XML_ParseBuffer">XML_ParseBuffer</a></code> (and thus also by plain
            <code><a href="#XML_Parse">XML_Parse</a></code>), and
          </li>

          <li>the <a href="#XML_SetElementDeclHandler">content model memory</a> (that is
          passed to the <a href="#XML_SetElementDeclHandler">element declaration
          handler</a> and freed by a call to <code><a href=
          "#XML_FreeContentModel">XML_FreeContentModel</a></code>).
          </li>
        </ul>

        <p>
          Once the <a href="#XML_SetAllocTrackerActivationThreshold">threshold for
          activation</a> is reached, the amplification factor is calculated as ..
        </p>

        <pre>amplification := allocated / direct</pre>
        <p>
          .. while parsing, whereas <code>direct</code> is the number of bytes read from
          the primary document in parsing and <code>allocated</code> is the number of
          bytes of dynamic memory allocated in the parser hierarchy.
        </p>

        <p>
          For a call to <code>XML_SetAllocTrackerMaximumAmplification</code> to succeed:
        </p>

        <ul>
          <li>parser <code>p</code> must be a non-<code>NULL</code> root parser (without
          any parent parsers) and
          </li>

          <li>
            <code>maximumAmplificationFactor</code> must be non-<code>NaN</code> and
            greater than or equal to <code>1.0</code>.
          </li>
        </ul>

        <p>
          <strong>Note:</strong> If you ever need to increase this value for non-attack
          payload, please <a href="https://github.com/libexpat/libexpat/issues">file a
          bug report</a>.
        </p>

        <p>
          <strong>Note:</strong> Amplifications factors greater than <code>100.0</code>
          can been observed near the start of parsing even with benign files in practice.
          So if you do reduce the maximum allowed amplification, please make sure that
          the activation threshold is still big enough to not end up with undesired false
          positives (i.e. benign files being rejected).
        </p>
      </div>

      <h4 id="XML_SetAllocTrackerActivationThreshold">
        XML_SetAllocTrackerActivationThreshold
      </h4>

      <pre class="fcndec">
/* Added in Expat 2.7.2. */
XML_Bool
XML_SetAllocTrackerActivationThreshold(XML_Parser p,
                                       unsigned long long activationThresholdBytes);
</pre>
      <div class="fcndef">
        <p>
          Sets number of allocated bytes of dynamic memory needed to activate protection
          against disproportionate use of RAM (default: <code>64 MiB</code>) of parser
          <code>p</code> to <code>activationThresholdBytes</code>, and returns
          <code>XML_TRUE</code> upon success and <code>XML_FALSE</code> upon error.
        </p>

        <p>
          <strong>Note:</strong> For types of allocations that intentionally bypass
          tracking and limiting, please see <code><a href=
          "#XML_SetAllocTrackerMaximumAmplification">XML_SetAllocTrackerMaximumAmplification</a></code>
          above.
        </p>

        <p>
          For a call to <code>XML_SetAllocTrackerActivationThreshold</code> to succeed:
        </p>

        <ul>
          <li>parser <code>p</code> must be a non-<code>NULL</code> root parser (without
          any parent parsers).
          </li>
        </ul>

        <p>
          <strong>Note:</strong> If you ever need to increase this value for non-attack
          payload, please <a href="https://github.com/libexpat/libexpat/issues">file a
          bug report</a>.
        </p>
      </div>

      <h4 id="XML_SetReparseDeferralEnabled">
        XML_SetReparseDeferralEnabled
      </h4>

      <pre class="fcndec">
/* Added in Expat 2.6.0. */
XML_Bool XMLCALL
XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled);
</pre>
      <div class="fcndef">
        <p>
          Large tokens may require many parse calls before enough data is available for
          Expat to parse it in full. If Expat retried parsing the token on every parse
          call, parsing could take quadratic time. To avoid this, Expat only retries once
          a significant amount of new data is available. This function allows disabling
          this behavior.
        </p>

        <p>
          The <code>enabled</code> argument should be <code>XML_TRUE</code> or
          <code>XML_FALSE</code>.
        </p>

        <p>
          Returns <code>XML_TRUE</code> on success, and <code>XML_FALSE</code> on error.
        </p>
      </div>

      <h3>
        <a id="miscellaneous" name="miscellaneous">Miscellaneous functions</a>
      </h3>

      <p>
        The functions in this section either obtain state information from the parser or
        can be used to dynamically set parser options.
      </p>

      <h4 id="XML_SetUserData">
        XML_SetUserData
      </h4>

      <pre class="fcndec">
void XMLCALL
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>

      <h4 id="XML_GetUserData">
        XML_GetUserData
      </h4>

      <pre class="fcndec">
void * XMLCALL
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>

      <h4 id="XML_UseParserAsHandlerArg">
        XML_UseParserAsHandlerArg
      </h4>

      <pre class="fcndec">
void XMLCALL
XML_UseParserAsHandlerArg(XML_Parser p);
</pre>
      <div class="fcndef">
        After this is called, handlers receive the parser in their <code>userData</code>
        arguments. The user data can still be obtained using the <code><a href=
        "#XML_GetUserData">XML_GetUserData</a></code> function.
      </div>

      <h4 id="XML_SetBase">
        XML_SetBase
      </h4>

      <pre class="fcndec">
enum XML_Status XMLCALL
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 <code>XML_STATUS_ERROR</code> if there's no memory to store base,
        otherwise it's <code>XML_STATUS_OK</code>.
      </div>

      <h4 id="XML_GetBase">
        XML_GetBase
      </h4>

      <pre class="fcndec">
const XML_Char * XMLCALL
XML_GetBase(XML_Parser p);
</pre>
      <div class="fcndef">
        Return the base for resolving relative URIs.
      </div>

      <h4 id="XML_GetSpecifiedAttributeCount">
        XML_GetSpecifiedAttributeCount
      </h4>

      <pre class="fcndec">
int XMLCALL
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>

      <h4 id="XML_GetIdAttributeIndex">
        XML_GetIdAttributeIndex
      </h4>

      <pre class="fcndec">
int XMLCALL
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>

      <h4 id="XML_GetAttributeInfo">
        XML_GetAttributeInfo
      </h4>

      <pre class="fcndec">
const XML_AttrInfo * XMLCALL
XML_GetAttributeInfo(XML_Parser parser);
</pre>

      <pre class="signature">
typedef struct {
  XML_Index  nameStart;  /* Offset to beginning of the attribute name. */
  XML_Index  nameEnd;    /* Offset after the attribute name's last byte. */
  XML_Index  valueStart; /* Offset to beginning of the attribute value. */
  XML_Index  valueEnd;   /* Offset after the attribute value's last byte. */
} XML_AttrInfo;
</pre>
      <div class="fcndef">
        Returns an array of <code>XML_AttrInfo</code> structures for the attribute/value
        pairs passed in the last call to the <code>XML_StartElementHandler</code> that
        were specified in the start-tag rather than defaulted. Each attribute/value pair
        counts as 1; thus the number of entries in the array is
        <code>XML_GetSpecifiedAttributeCount(parser) / 2</code>.
      </div>

      <h4 id="XML_SetEncoding">
        XML_SetEncoding
      </h4>

      <pre class="fcndec">
enum XML_Status XMLCALL
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-<code>NULL</code> 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. Returns <code>XML_STATUS_OK</code> on success or
        <code>XML_STATUS_ERROR</code> on error.
      </div>

      <h4 id="XML_SetParamEntityParsing">
        XML_SetParamEntityParsing
      </h4>

      <pre class="fcndec">
int XMLCALL
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>
        <b>Note:</b> If <code>XML_SetParamEntityParsing</code> is called after
        <code>XML_Parse</code> or <code>XML_ParseBuffer</code>, then it has no effect and
        will always return 0.
      </div>

      <h4 id="XML_SetHashSalt">
        XML_SetHashSalt
      </h4>

      <pre class="fcndec">
int XMLCALL
XML_SetHashSalt(XML_Parser p,
                unsigned long hash_salt);
</pre>
      <div class="fcndef">
        Sets the hash salt to use for internal hash calculations. Helps in preventing DoS
        attacks based on predicting hash function behavior. In order to have an effect
        this must be called before parsing has started. Returns 1 if successful, 0 when
        called after <code>XML_Parse</code> or <code>XML_ParseBuffer</code>.
        <p>
          <b>Note:</b> This call is optional, as the parser will auto-generate a new
          random salt value if no value has been set at the start of parsing.
        </p>

        <p>
          <b>Note:</b> One should not call <code>XML_SetHashSalt</code> with a hash salt
          value of 0, as this value is used as sentinel value to indicate that
          <code>XML_SetHashSalt</code> has <b>not</b> been called. Consequently such a
          call will have no effect, even if it returns 1.
        </p>
      </div>

      <h4 id="XML_UseForeignDTD">
        XML_UseForeignDTD
      </h4>

      <pre class="fcndec">
enum XML_Error XMLCALL
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
          <code>NULL</code>.
        </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>

        <p>
          <b>Note:</b> For the purpose of checking WFC: Entity Declared, passing
          <code>useDTD == XML_TRUE</code> will make the parser behave as if the document
          had a DTD with an external subset. This holds true even if the external entity
          reference handler returns without action.
        </p>
      </div>

      <h4 id="XML_SetReturnNSTriplet">
        XML_SetReturnNSTriplet
      </h4>

      <pre class="fcndec">
void XMLCALL
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>

      <h4 id="XML_DefaultCurrent">
        XML_DefaultCurrent
      </h4>

      <pre class="fcndec">
void XMLCALL
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>

      <h4 id="XML_ExpatVersion">
        XML_ExpatVersion
      </h4>

      <pre class="fcndec">
XML_LChar * XMLCALL
XML_ExpatVersion();
</pre>
      <div class="fcndef">
        Return the library version as a string (e.g. <code>"expat_1.95.1"</code>).
      </div>

      <h4 id="XML_ExpatVersionInfo">
        XML_ExpatVersionInfo
      </h4>

      <pre class="fcndec">
struct XML_Expat_Version XMLCALL
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>

      <h4 id="XML_GetFeatureList">
        XML_GetFeatureList
      </h4>

      <pre class="fcndec">
const XML_Feature * XMLCALL
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,
  XML_FEATURE_NS,
  XML_FEATURE_LARGE_SIZE
};

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 <code>NULL</code>, 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>

      <h4 id="XML_FreeContentModel">
        XML_FreeContentModel
      </h4>

      <pre class="fcndec">
void XMLCALL
XML_FreeContentModel(XML_Parser parser, XML_Content *model);
</pre>
      <div class="fcndef">
        Function to deallocate the <code>model</code> argument passed to the
        <code>XML_ElementDeclHandler</code> callback set using <code><a href=
        "#XML_SetElementDeclHandler">XML_ElementDeclHandler</a></code>. This function
        should not be used for any other purpose.
      </div>

      <p>
        The following functions allow external code to share the memory allocator an
        <code>XML_Parser</code> has been configured to use. This is especially useful for
        third-party libraries that interact with a parser object created by application
        code, or heavily layered applications. This can be essential when using
        dynamically loaded libraries which use different C standard libraries (this can
        happen on Windows, at least).
      </p>

      <h4 id="XML_MemMalloc">
        XML_MemMalloc
      </h4>

      <pre class="fcndec">
void * XMLCALL
XML_MemMalloc(XML_Parser parser, size_t size);
</pre>
      <div class="fcndef">
        Allocate <code>size</code> bytes of memory using the allocator the
        <code>parser</code> object has been configured to use. Returns a pointer to the
        memory or <code>NULL</code> on failure. Memory allocated in this way must be
        freed using <code><a href="#XML_MemFree">XML_MemFree</a></code>.
      </div>

      <h4 id="XML_MemRealloc">
        XML_MemRealloc
      </h4>

      <pre class="fcndec">
void * XMLCALL
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size);
</pre>
      <div class="fcndef">
        Allocate <code>size</code> bytes of memory using the allocator the
        <code>parser</code> object has been configured to use. <code>ptr</code> must
        point to a block of memory allocated by <code><a href=
        "#XML_MemMalloc">XML_MemMalloc</a></code> or <code>XML_MemRealloc</code>, or be
        <code>NULL</code>. This function tries to expand the block pointed to by
        <code>ptr</code> if possible. Returns a pointer to the memory or
        <code>NULL</code> on failure. On success, the original block has either been
        expanded or freed. On failure, the original block has not been freed; the caller
        is responsible for freeing the original block. Memory allocated in this way must
        be freed using <code><a href="#XML_MemFree">XML_MemFree</a></code>.
      </div>

      <h4 id="XML_MemFree">
        XML_MemFree
      </h4>

      <pre class="fcndec">
void XMLCALL
XML_MemFree(XML_Parser parser, void *ptr);
</pre>
      <div class="fcndef">
        Free a block of memory pointed to by <code>ptr</code>. The block must have been
        allocated by <code><a href="#XML_MemMalloc">XML_MemMalloc</a></code> or
        <code>XML_MemRealloc</code>, or be <code>NULL</code>.
      </div>

      <hr />

      <div class="footer">
        Found a bug in the documentation? <a href=
        "https://github.com/libexpat/libexpat/issues">Please file a bug report.</a>
      </div>
    </div>
  </body>
</html>