Src/Common/Expat/doc/xmlwf.sgml

   1 <!doctype refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN" [
   2
   3 <!-- Process this file with docbook-to-man to generate an nroff manual
   4      page: `docbook-to-man manpage.sgml > manpage.1'.  You may view
   5      the manual page with: `docbook-to-man manpage.sgml | nroff -man |
   6      less'.  A typical entry in a Makefile or Makefile.am is:
   7
   8 manpage.1: manpage.sgml
   9         docbook-to-man $< > $@
  10   -->
  11
  12   <!-- Fill in your name for FIRSTNAME and SURNAME. -->
  13   <!ENTITY dhfirstname "<firstname>Scott</firstname>">
  14   <!ENTITY dhsurname   "<surname>Bronson</surname>">
  15   <!-- Please adjust the date whenever revising the manpage. -->
  16   <!ENTITY dhdate      "<date>December  5, 2001</date>">
  17   <!-- SECTION should be 1-8, maybe w/ subsection other parameters are
  18        allowed: see man(7), man(1). -->
  19   <!ENTITY dhsection   "<manvolnum>1</manvolnum>">
  20   <!ENTITY dhemail     "<email>bronson@rinspin.com</email>">
  21   <!ENTITY dhusername  "Scott Bronson">
  22   <!ENTITY dhucpackage "<refentrytitle>XMLWF</refentrytitle>">
  23   <!ENTITY dhpackage   "xmlwf">
  24
  25   <!ENTITY debian      "<productname>Debian GNU/Linux</productname>">
  26   <!ENTITY gnu         "<acronym>GNU</acronym>">
  27 ]>
  28
  29 <refentry>
  30   <refentryinfo>
  31     <address>
  32       &dhemail;
  33     </address>
  34     <author>
  35       &dhfirstname;
  36       &dhsurname;
  37     </author>
  38     <copyright>
  39       <year>2001</year>
  40       <holder>&dhusername;</holder>
  41     </copyright>
  42     &dhdate;
  43   </refentryinfo>
  44   <refmeta>
  45     &dhucpackage;
  46
  47     &dhsection;
  48   </refmeta>
  49   <refnamediv>
  50     <refname>&dhpackage;</refname>
  51
  52     <refpurpose>Determines if an XML document is well-formed</refpurpose>
  53   </refnamediv>
  54   <refsynopsisdiv>
  55     <cmdsynopsis>
  56       <command>&dhpackage;</command>
  57           <arg><option>-s</option></arg>
  58           <arg><option>-n</option></arg>
  59           <arg><option>-p</option></arg>
  60           <arg><option>-x</option></arg>
  61
  62           <arg><option>-e <replaceable>encoding</replaceable></option></arg>
  63           <arg><option>-w</option></arg>
  64
  65           <arg><option>-d <replaceable>output-dir</replaceable></option></arg>
  66           <arg><option>-c</option></arg>
  67           <arg><option>-m</option></arg>
  68
  69           <arg><option>-r</option></arg>
  70           <arg><option>-t</option></arg>
  71
  72           <arg><option>-v</option></arg>
  73
  74           <arg>file ...</arg>
  75     </cmdsynopsis>
  76   </refsynopsisdiv>
  77
  78   <refsect1>
  79     <title>DESCRIPTION</title>
  80
  81     <para>
  82         <command>&dhpackage;</command> uses the Expat library to determine
  83         if an XML document is well-formed.  It is non-validating.
  84         </para>
  85
  86         <para>
  87         If you do not specify any files on the command-line,
  88         and you have a recent version of &dhpackage;, the input
  89         file will be read from stdin.
  90         </para>
  91
  92   </refsect1>
  93
  94   <refsect1>
  95     <title>WELL-FORMED DOCUMENTS</title>
  96
  97         <para>
  98           A well-formed document must adhere to the
  99           following rules:
 100         </para>
 101
 102         <itemizedlist>
 103       <listitem><para>
 104             The file begins with an XML declaration.  For instance,
 105                 <literal>&lt;?xml version="1.0" standalone="yes"?&gt;</literal>.
 106                 <emphasis>NOTE:</emphasis> &dhpackage; does not currently
 107                 check for a valid XML declaration.
 108       </para></listitem>
 109       <listitem><para>
 110                 Every start tag is either empty (&lt;tag/&gt;)
 111                 or has a corresponding end tag.
 112       </para></listitem>
 113       <listitem><para>
 114             There is exactly one root element.  This element must contain
 115                 all other elements in the document.  Only comments, white
 116                 space, and processing instructions may come after the close
 117                 of the root element.
 118       </para></listitem>
 119       <listitem><para>
 120                 All elements nest properly.
 121       </para></listitem>
 122       <listitem><para>
 123                 All attribute values are enclosed in quotes (either single
 124                 or double).
 125       </para></listitem>
 126     </itemizedlist>
 127
 128         <para>
 129           If the document has a DTD, and it strictly complies with that
 130           DTD, then the document is also considered <emphasis>valid</emphasis>.
 131           &dhpackage; is a non-validating parser -- it does not check the DTD.
 132           However, it does support external entities (see the -x option).
 133         </para>
 134   </refsect1>
 135
 136   <refsect1>
 137     <title>OPTIONS</title>
 138
 139 <para>
 140 When an option includes an argument, you may specify the argument either
 141 separate ("d output") or mashed ("-doutput").  &dhpackage; supports both.
 142 </para>
 143
 144     <variablelist>
 145
 146       <varlistentry>
 147         <term><option>-c</option></term>
 148         <listitem>
 149                 <para>
 150   If the input file is well-formed and &dhpackage; doesn't
 151   encounter any errors, the input file is simply copied to
 152   the output directory unchanged.
 153   This implies no namespaces (turns off -n) and
 154   requires -d to specify an output file.
 155                 </para>
 156         </listitem>
 157       </varlistentry>
 158
 159       <varlistentry>
 160         <term><option>-d output-dir</option></term>
 161         <listitem>
 162                 <para>
 163   Specifies a directory to contain transformed
 164   representations of the input files.
 165   By default, -d outputs a canonical representation
 166   (described below).
 167   You can select different output formats using -c and -m.
 168           </para>
 169           <para>
 170   The output filenames will
 171   be exactly the same as the input filenames or "STDIN" if the input is
 172   coming from STDIN.  Therefore, you must be careful that the
 173   output file does not go into the same directory as the input
 174   file.  Otherwise, &dhpackage; will delete the input file before
 175   it generates the output file (just like running
 176   <literal>cat &lt; file &gt; file</literal> in most shells).
 177           </para>
 178           <para>
 179   Two structurally equivalent XML documents have a byte-for-byte
 180   identical canonical XML representation.
 181   Note that ignorable white space is considered significant and
 182   is treated equivalently to data.
 183   More on canonical XML can be found at
 184   http://www.jclark.com/xml/canonxml.html .
 185           </para>
 186         </listitem>
 187       </varlistentry>
 188
 189       <varlistentry>
 190         <term><option>-e encoding</option></term>
 191         <listitem>
 192                 <para>
 193    Specifies the character encoding for the document, overriding
 194    any document encoding declaration.  &dhpackage;
 195    has four built-in encodings:
 196         <literal>US-ASCII</literal>,
 197         <literal>UTF-8</literal>,
 198         <literal>UTF-16</literal>, and
 199     <literal>ISO-8859-1</literal>.
 200         Also see the -w option.
 201            </para>
 202         </listitem>
 203       </varlistentry>
 204
 205       <varlistentry>
 206         <term><option>-m</option></term>
 207         <listitem>
 208                 <para>
 209   Outputs some strange sort of XML file that completely
 210   describes the the input file, including character postitions.
 211   Requires -d to specify an output file.
 212            </para>
 213         </listitem>
 214       </varlistentry>
 215
 216       <varlistentry>
 217         <term><option>-n</option></term>
 218         <listitem>
 219                 <para>
 220   Turns on namespace processing.  (describe namespaces)
 221   -c disables namespaces.
 222            </para>
 223         </listitem>
 224       </varlistentry>
 225
 226       <varlistentry>
 227         <term><option>-p</option></term>
 228         <listitem>
 229                 <para>
 230     Tells xmlwf to process external DTDs and parameter
 231     entities.
 232          </para>
 233          <para>
 234         Normally &dhpackage; never parses parameter entities.
 235         -p tells it to always parse them.
 236         -p implies -x.
 237            </para>
 238         </listitem>
 239       </varlistentry>
 240
 241       <varlistentry>
 242         <term><option>-r</option></term>
 243         <listitem>
 244                 <para>
 245    Normally &dhpackage; memory-maps the XML file before parsing.
 246    -r turns off memory-mapping and uses normal file IO calls instead.
 247    Of course, memory-mapping is automatically turned off
 248    when reading from STDIN.
 249            </para>
 250         </listitem>
 251       </varlistentry>
 252
 253       <varlistentry>
 254         <term><option>-s</option></term>
 255         <listitem>
 256                 <para>
 257   Prints an error if the document is not standalone.
 258   A document is standalone if it has no external subset and no
 259   references to parameter entities.
 260            </para>
 261         </listitem>
 262       </varlistentry>
 263
 264       <varlistentry>
 265         <term><option>-t</option></term>
 266         <listitem>
 267                 <para>
 268   Turns on timings.  This tells Expat to parse the entire file,
 269   but not perform any processing.
 270   This gives a fairly accurate idea of the raw speed of Expat itself
 271   without client overhead.
 272    -t turns off most of the output options (-d, -m -c, ...).
 273            </para>
 274         </listitem>
 275       </varlistentry>
 276
 277       <varlistentry>
 278         <term><option>-v</option></term>
 279         <listitem>
 280                 <para>
 281   Prints the version of the Expat library being used, and then exits.
 282            </para>
 283         </listitem>
 284       </varlistentry>
 285
 286       <varlistentry>
 287         <term><option>-w</option></term>
 288         <listitem>
 289                 <para>
 290   Enables Windows code pages.
 291   Normally, &dhpackage; will throw an error if it runs across
 292   an encoding that it is not equipped to handle itself.  With
 293   -w, &dhpackage; will try to use a Windows code page.  See
 294   also -e.
 295            </para>
 296         </listitem>
 297       </varlistentry>
 298
 299       <varlistentry>
 300         <term><option>-x</option></term>
 301         <listitem>
 302                 <para>
 303   Turns on parsing external entities.
 304   </para>
 305 <para>
 306   Non-validating parsers are not required to resolve external
 307   entities, or even expand entities at all.
 308   Expat always expands internal entities (?),
 309   but external entity parsing must be enabled explicitly.
 310   </para>
 311   <para>
 312   External entities are simply entities that obtain their
 313   data from outside the XML file currently being parsed.
 314   </para>
 315   <para>
 316   This is an example of an internal entity:
 317 <literallayout>
 318 &lt;!ENTITY vers '1.0.2'&gt;
 319 </literallayout>
 320   </para>
 321   <para>
 322   And here are some examples of external entities:
 323
 324 <literallayout>
 325 &lt;!ENTITY header SYSTEM "header-&amp;vers;.xml"&gt;  (parsed)
 326 &lt;!ENTITY logo SYSTEM "logo.png" PNG&gt;         (unparsed)
 327 </literallayout>
 328
 329            </para>
 330         </listitem>
 331       </varlistentry>
 332
 333       <varlistentry>
 334         <term><option>--</option></term>
 335         <listitem>
 336                 <para>
 337     For some reason, &dhpackage; specifically ignores "--"
 338         anywhere it appears on the command line.
 339            </para>
 340         </listitem>
 341       </varlistentry>
 342     </variablelist>
 343
 344         <para>
 345         Older versions of &dhpackage; do not support reading from STDIN.
 346         </para>
 347   </refsect1>
 348
 349   <refsect1>
 350   <title>OUTPUT</title>
 351     <para>
 352         If an input file is not well-formed, &dhpackage; outputs
 353         a single line describing the problem to STDOUT.
 354         If a file is well formed, &dhpackage; outputs nothing.
 355         Note that the result code is <emphasis>not</emphasis> set.
 356         </para>
 357   </refsect1>
 358
 359   <refsect1>
 360     <title>BUGS</title>
 361         <para>
 362         According to the W3C standard, an XML file without a
 363         declaration at the beginning is not considered well-formed.
 364         However, &dhpackage; allows this to pass.
 365         </para>
 366         <para>
 367         &dhpackage; returns a 0 - noerr result, even if the file is
 368         not well-formed.  There is no good way for a program to use
 369         xmlwf to quickly check a file -- it must parse xmlwf's STDOUT.
 370         </para>
 371     <para>
 372     The errors should go to STDERR, not stdout.
 373     </para>
 374         <para>
 375         There should be a way to get -d to send its output to STDOUT
 376         rather than forcing the user to send it to a file.
 377         </para>
 378         <para>
 379         I have no idea why anyone would want to use the -d, -c
 380         and -m options.  If someone could explain it to me, I'd
 381         like to add this information to this manpage.
 382         </para>
 383   </refsect1>
 384
 385   <refsect1>
 386     <title>ALTERNATIVES</title>
 387         <para>
 388           Here are some XML validators on the web:
 389
 390 <literallayout>
 391 http://www.hcrc.ed.ac.uk/~richard/xml-check.html
 392 http://www.stg.brown.edu/service/xmlvalid/
 393 http://www.scripting.com/frontier5/xml/code/xmlValidator.html
 394 http://www.xml.com/pub/a/tools/ruwf/check.html
 395 &nbsp;    (on a page with no less than 15 ads!  Shame!)
 396 </literallayout>
 397
 398                  </para>
 399   </refsect1>
 400
 401   <refsect1>
 402     <title>SEE ALSO</title>
 403         <para>
 404
 405 <literallayout>
 406 The Expat home page:        http://www.libexpat.org/
 407 The W3 XML specification:   http://www.w3.org/TR/REC-xml
 408 </literallayout>
 409
 410         </para>
 411   </refsect1>
 412
 413   <refsect1>
 414     <title>AUTHOR</title>
 415     <para>
 416           This manual page was written by &dhusername; &dhemail; for
 417       the &debian; system (but may be used by others).  Permission is
 418       granted to copy, distribute and/or modify this document under
 419       the terms of the <acronym>GNU</acronym> Free Documentation
 420       License, Version 1.1.
 421         </para>
 422   </refsect1>
 423 </refentry>
 424
 425 <!-- Keep this comment at the end of the file
 426 Local variables:
 427 mode: sgml
 428 sgml-omittag:t
 429 sgml-shorttag:t
 430 sgml-minimize-attributes:nil
 431 sgml-always-quote-attributes:t
 432 sgml-indent-step:2
 433 sgml-indent-data:t
 434 sgml-parent-document:nil
 435 sgml-default-dtd-file:nil
 436 sgml-exposed-tags:nil
 437 sgml-local-catalogs:nil
 438 sgml-local-ecat-files:nil
 439 End:
 440 -->