winscp/libs/expat/doc/xmlwf.xml

<!--
                            __  __            _
                         ___\ \/ /_ __   __ _| |_
                        / _ \\  /| '_ \ / _` | __|
                       |  __//  \| |_) | (_| | |_
                        \___/_/\_\ .__/ \__,_|\__|
                                 |_| XML parser

   Copyright (c) 2001      Scott Bronson <[email protected]>
   Copyright (c) 2002-2003 Fred L. Drake, Jr. <[email protected]>
   Copyright (c) 2009      Karl Waclawek <[email protected]>
   Copyright (c) 2016-2025 Sebastian Pipping <[email protected]>
   Copyright (c) 2016      Ardo van Rangelrooij <[email protected]>
   Copyright (c) 2017      Rhodri James <[email protected]>
   Copyright (c) 2020      Joe Orton <[email protected]>
   Copyright (c) 2021      Tim Bray <[email protected]>
   Unlike most of Expat,
   this file is copyrighted under the GNU Free Documentation License 1.1.
-->
<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook XML V4.2//EN"
          "http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd" [
  <!ENTITY dhfirstname "<firstname>Scott</firstname>">
  <!ENTITY dhsurname   "<surname>Bronson</surname>">
  <!ENTITY dhdate      "<date>September 24, 2025</date>">
  <!-- Please adjust this^^ date whenever cutting a new release. -->
  <!ENTITY dhsection   "<manvolnum>1</manvolnum>">
  <!ENTITY dhemail     "<email>[email protected]</email>">
  <!ENTITY dhusername  "Scott Bronson">
  <!ENTITY dhucpackage "<refentrytitle>XMLWF</refentrytitle>">
  <!ENTITY dhpackage   "xmlwf">

  <!ENTITY debian      "<productname>Debian GNU/Linux</productname>">
  <!ENTITY gnu         "<acronym>GNU</acronym>">
]>

<refentry>
  <refentryinfo>
    <address>
      &dhemail;
    </address>
    <author>
      &dhfirstname;
      &dhsurname;
    </author>
    <copyright>
      <year>2001</year>
      <holder>&dhusername;</holder>
    </copyright>
    &dhdate;
  </refentryinfo>
  <refmeta>
    &dhucpackage;

    &dhsection;
  </refmeta>
  <refnamediv>
    <refname>&dhpackage;</refname>

    <refpurpose>Determines if an XML document is well-formed</refpurpose>
  </refnamediv>
  <refsynopsisdiv>
    <cmdsynopsis>
      <command>&dhpackage;</command>
      <arg><replaceable>OPTIONS</replaceable></arg>
      <arg><replaceable>FILE</replaceable> ...</arg>
    </cmdsynopsis>
    <cmdsynopsis>
      <command>&dhpackage;</command>
      <group choice="plain">
        <arg><option>-h</option></arg>
        <arg><option>--help</option></arg>
      </group>
    </cmdsynopsis>
    <cmdsynopsis>
      <command>&dhpackage;</command>
      <group choice="plain">
        <arg><option>-v</option></arg>
        <arg><option>--version</option></arg>
      </group>
    </cmdsynopsis>
  </refsynopsisdiv>
 
  <refsect1>
    <title>DESCRIPTION</title>

    <para>
	<command>&dhpackage;</command> uses the Expat library to
	determine if an XML document is well-formed.  It is
	non-validating.
	</para>

	<para>
	If you do not specify any files on the command-line, and you
	have a recent version of <command>&dhpackage;</command>, the
	input file will be read from standard input.
	</para>

  </refsect1>

  <refsect1>
    <title>WELL-FORMED DOCUMENTS</title>

	<para>
	  A well-formed document must adhere to the
	  following rules:
	</para>

	<itemizedlist>
      <listitem><para>
	    The file begins with an XML declaration.  For instance,
		<literal>&lt;?xml version="1.0" standalone="yes"?&gt;</literal>.
		<emphasis>NOTE</emphasis>:
		<command>&dhpackage;</command> does not currently
		check for a valid XML declaration.
      </para></listitem>
      <listitem><para>
		Every start tag is either empty (&lt;tag/&gt;)
		or has a corresponding end tag.
      </para></listitem>
      <listitem><para>
	    There is exactly one root element.  This element must contain
		all other elements in the document.  Only comments, white
		space, and processing instructions may come after the close
		of the root element.
      </para></listitem>
      <listitem><para>
		All elements nest properly.
      </para></listitem>
      <listitem><para>
		All attribute values are enclosed in quotes (either single
		or double).
      </para></listitem>
    </itemizedlist>

	<para>
	  If the document has a DTD, and it strictly complies with that
	  DTD, then the document is also considered <emphasis>valid</emphasis>.
	  <command>&dhpackage;</command> is a non-validating parser --
	  it does not check the DTD.  However, it does support
	  external entities (see the <option>-x</option> option).
	</para>
  </refsect1>

  <refsect1>
    <title>OPTIONS</title>

<para>
When an option includes an argument, you may specify the argument either
separately ("<option>-d</option> <replaceable>output</replaceable>") or concatenated with the
option ("<option>-d</option><replaceable>output</replaceable>").  <command>&dhpackage;</command>
supports both.
</para>

    <variablelist>

      <varlistentry>
        <term><option>-a</option> <replaceable>factor</replaceable></term>
        <listitem>
          <para>
            Sets the maximum tolerated amplification factor
            for protection against amplification attacks
            like the billion laughs attack
            (default: 100.0
            for the sum of direct and indirect output and also
            for allocations of dynamic memory).
            The amplification factor is calculated as ..
          </para>
          <literallayout>
            amplification := (direct + indirect) / direct
          </literallayout>
          <para>
            .. with regard to use of entities and ..
          </para>
          <literallayout>
            amplification := allocated / direct
          </literallayout>
          <para>
            .. with regard to dynamic memory while parsing.
            &lt;direct&gt; is the number of bytes read
              from the primary document in parsing,
            &lt;indirect&gt; is the number of bytes
              added by expanding entities and reading of external DTD files,
              combined, and
            &lt;allocated&gt; is the total number of bytes of dynamic memory
              allocated (and not freed) per hierarchy of parsers.
          </para>
          <para>
            <emphasis>NOTE</emphasis>:
            If you ever need to increase this value for non-attack payload,
            please file a bug report.
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-b</option> <replaceable>bytes</replaceable></term>
        <listitem>
          <para>
            Sets the number of output bytes (including amplification)
            needed to activate protection against amplification attacks
            like billion laughs
            (default: 8 MiB for the sum of direct and indirect output,
            and 64 MiB for allocations of dynamic memory).
            This can be thought of as an &quot;activation threshold&quot;.
          </para>
          <para>
            <emphasis>NOTE</emphasis>:
            If you ever need to increase this value for non-attack payload,
            please file a bug report.
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-c</option></term>
        <listitem>
		<para>
  If the input file is well-formed and <command>&dhpackage;</command>
  doesn't encounter any errors, the input file is simply copied to
  the output directory unchanged.
  This implies no namespaces (turns off <option>-n</option>) and
  requires <option>-d</option> to specify an output directory.
  		</para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-d</option> <replaceable>output-dir</replaceable></term>
        <listitem>
		<para>
  Specifies a directory to contain transformed
  representations of the input files.
  By default, <option>-d</option> outputs a canonical representation
  (described below).
  You can select different output formats using <option>-c</option>,
  <option>-m</option> and <option>-N</option>.
	  </para>
	  <para>
  The output filenames will
  be exactly the same as the input filenames or "STDIN" if the input is
  coming from standard input.  Therefore, you must be careful that the
  output file does not go into the same directory as the input
  file.  Otherwise, <command>&dhpackage;</command> will delete the
  input file before it generates the output file (just like running
  <literal>cat &lt; file &gt; file</literal> in most shells).
	  </para>
	  <para> 
  Two structurally equivalent XML documents have a byte-for-byte
  identical canonical XML representation.
  Note that ignorable white space is considered significant and
  is treated equivalently to data.
  More on canonical XML can be found at
  http://www.jclark.com/xml/canonxml.html .
	  </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-e</option> <replaceable>encoding</replaceable></term>
        <listitem>
		<para>
   Specifies the character encoding for the document, overriding
   any document encoding declaration.  <command>&dhpackage;</command>
   supports four built-in encodings:
   	<literal>US-ASCII</literal>,
	<literal>UTF-8</literal>,
	<literal>UTF-16</literal>, and
	<literal>ISO-8859-1</literal>.
   Also see the <option>-w</option> option.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-g</option> <replaceable>bytes</replaceable></term>
        <listitem>
          <para>
            Sets the buffer size to request per call pair to
            <function>XML_GetBuffer</function> and <function>read</function>
            (default: 8 KiB).
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-h</option></term>
        <term><option>--help</option></term>
        <listitem>
          <para>
            Prints short usage information on command <command>&dhpackage;</command>,
            and then exits.
            Similar to this man page but more concise.
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-k</option></term>
        <listitem>
          <para>
            When processing multiple files, <command>&dhpackage;</command>
            by default halts after the the first file with an error.
            This tells <command>&dhpackage;</command> to report the error
            but to keep processing.
            This can be useful, for example, when testing a filter that converts
            many files to XML and you want to quickly find out which conversions
            failed.
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-m</option></term>
        <listitem>
		<para>
  Outputs some strange sort of XML file that completely
  describes the input file, including character positions.
  Requires <option>-d</option> to specify an output file.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-n</option></term>
        <listitem>
		<para>
  Turns on namespace processing.  (describe namespaces)
  <option>-c</option> disables namespaces.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-N</option></term>
        <listitem>
          <para>
  Adds a doctype and notation declarations to canonical XML output.
  This matches the example output used by the formal XML test cases.
  Requires <option>-d</option> to specify an output file.
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-p</option></term>
        <listitem>
		<para>
    Tells <command>&dhpackage;</command> to process external DTDs and parameter
    entities.
	 </para>
	 <para>
   Normally <command>&dhpackage;</command> never parses parameter
   entities.  <option>-p</option> tells it to always parse them.
   <option>-p</option> implies <option>-x</option>.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-q</option></term>
        <listitem>
          <para>
            Disable reparse deferral, and allow quadratic parse runtime
            on large tokens (default: reparse deferral enabled).
          </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-r</option></term>
        <listitem>
		<para>
   Normally <command>&dhpackage;</command> memory-maps the XML file
   before parsing; this can result in faster parsing on many
   platforms.
   <option>-r</option> turns off memory-mapping and uses normal file
   IO calls instead.
   Of course, memory-mapping is automatically turned off
   when reading from standard input.
	   </para>
		<para>
   Use of memory-mapping can cause some platforms to report
   substantially higher memory usage for
   <command>&dhpackage;</command>, but this appears to be a matter of
   the operating system reporting memory in a strange way; there is
   not a leak in <command>&dhpackage;</command>.
           </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-s</option></term>
        <listitem>
		<para>
  Prints an error if the document is not standalone. 
  A document is standalone if it has no external subset and no
  references to parameter entities.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-t</option></term>
        <listitem>
		<para>
  Turns on timings.  This tells Expat to parse the entire file,
  but not perform any processing.
  This gives a fairly accurate idea of the raw speed of Expat itself
  without client overhead.
  <option>-t</option> turns off most of the output options
  (<option>-d</option>, <option>-m</option>, <option>-c</option>, ...).
	   </para>
        </listitem>
      </varlistentry>
      
      <varlistentry>
        <term><option>-v</option></term>
        <term><option>--version</option></term>
        <listitem>
		<para>
  Prints the version of the Expat library being used, including some
  information on the compile-time configuration of the library, and
  then exits.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-w</option></term>
        <listitem>
		<para>
  Enables support for Windows code pages.
  Normally, <command>&dhpackage;</command> will throw an error if it
  runs across an encoding that it is not equipped to handle itself.  With
  <option>-w</option>, <command>&dhpackage;</command> will try to use a Windows code
  page.  See also <option>-e</option>.
	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>-x</option></term>
        <listitem>
		<para>
  Turns on parsing external entities.
  </para>
<para>
  Non-validating parsers are not required to resolve external
  entities, or even expand entities at all.
  Expat always expands internal entities (?),
  but external entity parsing must be enabled explicitly.
  </para>
  <para>
  External entities are simply entities that obtain their
  data from outside the XML file currently being parsed.
  </para>
  <para>
  This is an example of an internal entity:
<literallayout>
&lt;!ENTITY vers '1.0.2'&gt;
</literallayout>
  </para>
  <para>
  And here are some examples of external entities:

<literallayout>
&lt;!ENTITY header SYSTEM "header-&amp;vers;.xml"&gt;  (parsed)
&lt;!ENTITY logo SYSTEM "logo.png" PNG&gt;         (unparsed)
</literallayout>

	   </para>
        </listitem>
      </varlistentry>

      <varlistentry>
        <term><option>--</option></term>
        <listitem>
		<para>
    (Two hyphens.)
    Terminates the list of options.  This is only needed if a filename
    starts with a hyphen.  For example:
	   </para>
<literallayout>
&dhpackage; -- -myfile.xml
</literallayout>
		<para>
    will run <command>&dhpackage;</command> on the file
    <filename>-myfile.xml</filename>.
	   </para>
        </listitem>
      </varlistentry>
    </variablelist>

	<para>
    Older versions of <command>&dhpackage;</command> do not support
    reading from standard input.
	</para>
  </refsect1>

  <refsect1>
  <title>OUTPUT</title>
    <para>
	<command>&dhpackage;</command> outputs nothing for files which are problem-free.
        If any input file is not well-formed, or if the output for any
	input file cannot be opened, <command>&dhpackage;</command> prints a single
	line describing	the problem to standard output.
    </para>
    <para>
        If the <option>-k</option> option is not provided, <command>&dhpackage;</command>
	halts upon encountering a well-formedness or output-file error. 
	If <option>-k</option> is provided, <command>&dhpackage;</command> continues
	processing the remaining input files, describing problems found with any of them.
    </para>
  </refsect1>

  <refsect1>
  <title>EXIT STATUS</title>
    <para>For options <option>-v</option>|<option>--version</option> or <option>-h</option>|<option>--help</option>, <command>&dhpackage;</command> always exits with status code 0.  For other cases, the following exit status codes are returned:
    <variablelist>
      <varlistentry>
        <term><option>0</option></term>
        <listitem><para>The input files are well-formed and the output (if requested) was written successfully.</para>
        </listitem>
      </varlistentry>
      <varlistentry>
        <term><option>1</option></term>
        <listitem><para>An internal error occurred.</para>
        </listitem>
      </varlistentry>
      <varlistentry>
        <term><option>2</option></term>
        <listitem><para>One or more input files were not well-formed or could not be parsed.</para>
        </listitem>
      </varlistentry>
      <varlistentry>
        <term><option>3</option></term>
        <listitem><para>If using the <option>-d</option> option, an error occurred opening an output file.</para>
        </listitem>
      </varlistentry>
      <varlistentry>
        <term><option>4</option></term>
        <listitem><para>There was a command-line argument error in how <command>&dhpackage;</command> was invoked.</para>
        </listitem>
      </varlistentry>
    </variablelist>
	</para>
  </refsect1>

  
  <refsect1>
    <title>BUGS</title>
	<para>
	The errors should go to standard error, not standard output.
	</para>
	<para>
	There should be a way to get <option>-d</option> to send its
	output to standard output rather than forcing the user to send
	it to a file.
	</para>
	<para>
	I have no idea why anyone would want to use the
	<option>-d</option>, <option>-c</option>, and
	<option>-m</option> options.  If someone could explain it to
	me, I'd like to add this information to this manpage.
	</para>
  </refsect1>

  <refsect1>
    <title>SEE ALSO</title>
	<para>

<literallayout>
The Expat home page:                            https://libexpat.github.io/
The W3 XML 1.0 specification (fourth edition):  https://www.w3.org/TR/2006/REC-xml-20060816/
Billion laughs attack:                          https://en.wikipedia.org/wiki/Billion_laughs_attack
</literallayout>

	</para>
  </refsect1>

  <refsect1>
    <title>AUTHOR</title>
    <para>
      This manual page was originally written by &dhusername; &dhemail;
      in December 2001 for
      the &debian; system (but may be used by others).  Permission is
      granted to copy, distribute and/or modify this document under
      the terms of the <acronym>GNU</acronym> Free Documentation
      License, Version 1.1.
	</para>
  </refsect1>
</refentry>