<?php
if (! class_exists('syntax_plugin_bomfix')) {
	if (! defined('DOKU_PLUGIN')) {
		if (! defined('DOKU_INC')) {
			define('DOKU_INC', realpath(dirname(__FILE__) . '/../../') . '/');
		} // if
		define('DOKU_PLUGIN', DOKU_INC . 'lib/plugins/');
	} // if
	// Include parent class:
	require_once(DOKU_PLUGIN . 'syntax.php');

/**
 * <tt>syntax_plugin_bomfix.php </tt>- A PHP4 class that implements
 * a <tt>DokuWiki</tt> plugin for <tt>UTF8 "magic" bytes</tt>.
 *
 * <p>
 * External editors (i.e. separate standalone programs like word processing
 * software) usually mark a file in UTF8 format by prepending its content
 * with a "magic" byte sequence at the very start of file. While there is
 * no harm in it as far as DokuWiki is concerned those "magic" bytes
 * (Byte Order Mark) <em>do</em> appear in the page presented to the user.
 * </p><p>
 * Depending on a page's actual content and the respective CSS rules in
 * effect this may lead to undesired results. One way to get rid of this
 * problem would be to open the affected page(s) with DokuWiki's built-in
 * edit feature and simply remove those bytes. However, such an approach
 * would cause the word processor to open the file as plain text assuming
 * it's in ASCII or, say, ISO-8859-1 format - whatever may be configured
 * as the default text format. That, in consequence, would invalidate (or
 * at least render strangely) all UTF8 character sequences.
 * </p><p>
 * Actually that is the recommended approach <em>if</em> (i.e. <tt>if</tt>)
 * you never intend to edit the wiki pages by an external editor.
 * </p><p>
 * As it happens, personally I prefer to edit the pages (of a local DokuWiki
 * installation) by OpenOffice.org for various reasons. (And, yes, I know
 * that I bypass DokuWiki's changes-system this way.) Therefor I need those
 * "magic" bytes <em>but</em> I don't want them to show up in the pages
 * presented to the end user (reader). Enter <tt>syntax_plugin_bomfix</tt>.
 * The whole purpose of this plugin is to suppress the output of that
 * "magic" byte sequence. And nothing more. There are no new wiki language
 * features introduced by this plugin. Nor is there anything special you
 * have to remember when editing one of your already existing or newly
 * created pages.
 * </p><p>
 * To use it just install the plugin in your DokuWiki's plugin folder.
 * That's all.
 * </p><pre>
 *	Copyright (C) 2006, 2010  M.Watermann, D-10247 Berlin, FRG
 *			All rights reserved
 *		EMail : &lt;support@mwat.de&gt;
 * </pre>
 * <div class="disclaimer">
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either
 * <a href="http://www.gnu.org/licenses/gpl.html">version 3</a> of the
 * License, or (at your option) any later version.<br>
 * This software is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 * </div>
 * @author <a href="mailto:support@mwat.de">Matthias Watermann</a>
 * @version <tt>$Id: syntax_plugin_bomfix.php,v 1.6 2010/02/22 10:49:59 matthias Exp $</tt>
 * @since created 24-Dec-2006
 */
class syntax_plugin_bomfix extends DokuWiki_Syntax_Plugin {

	/**
	 * @publicsection
	 */
	//@{

	/**
	 * Tell the parser whether the plugin accepts syntax mode
	 * <tt>$aMode</tt> within its own markup.
	 *
	 * @param $aMode String The requested syntaxmode.
	 * @return Boolean <tt>FALSE</tt> always since no nested markup
	 * is possible with this plugin.
	 * @public
	 */
	function accepts($aMode) {
		return FALSE;
	} // accepts()

	/**
	 * Connect lookup pattern to lexer.
	 *
	 * @param $aMode String The desired rendermode.
	 * @public
	 * @see render()
	 */
	function connectTo($aMode) {
		$this->Lexer->addSpecialPattern('^\xEF\xBB\xBF',
			$aMode, 'plugin_bomfix');
	} // connectTo()

	/**
	 * Get an associative array with plugin info.
	 *
	 * <p>
	 * The returned array holds the following fields:
	 * <dl>
	 * <dt>author</dt><dd>Author of the plugin</dd>
	 * <dt>email</dt><dd>Email address to contact the author</dd>
	 * <dt>date</dt><dd>Last modified date of the plugin in
	 * <tt>YYYY-MM-DD</tt> format</dd>
	 * <dt>name</dt><dd>Name of the plugin</dd>
	 * <dt>desc</dt><dd>Short description of the plugin (Text only)</dd>
	 * <dt>url</dt><dd>Website with more information on the plugin
	 * (eg. syntax description)</dd>
	 * </dl>
	 * @return Array Information about this plugin class.
	 * @public
	 * @static
	 */
	function getInfo() {
		return array(
			'author' =>	'Matthias Watermann',
			'email' =>	'support@mwat.de',
			'date' =>	'2010-02-22',
			'name' =>	'BOMfix Syntax Plugin',
			'desc' =>	'Ignore UTF8 "magic" bytes at start of page',
			'url' =>	'http://www.dokuwiki.org/plugin:bomfix');
	} // getInfo()

	/**
	 * Where to sort in?
	 *
	 * @return Integer <tt>380</tt> (doesn't really matter).
	 * @static
	 * @public
	 */
	function getSort() {
		return 380;
	} // getSort()

	/**
	 * Get the type of syntax this plugin defines.
	 *
	 * @return String <tt>'substition'</tt> (i.e. 'substitution').
	 * @static
	 * @public
	 */
	function getType() {
		return 'substition';	// sic! should be __substitution__
	} // getType()

	/**
	 * Handler to prepare matched data for the rendering process.
	 *
	 * <p>
	 * The <tt>$aState</tt> parameter gives the type of pattern
	 * which triggered the call to this method:
	 * </p>
	 * <dl>
	 * <dt>DOKU_LEXER_ENTER</dt>
	 * <dd>a pattern set by <tt>addEntryPattern()</tt></dd>
	 * <dt>DOKU_LEXER_MATCHED</dt>
	 * <dd>a pattern set by <tt>addPattern()</tt></dd>
	 * <dt>DOKU_LEXER_EXIT</dt>
	 * <dd> a pattern set by <tt>addExitPattern()</tt></dd>
	 * <dt>DOKU_LEXER_SPECIAL</dt>
	 * <dd>a pattern set by <tt>addSpecialPattern()</tt></dd>
	 * <dt>DOKU_LEXER_UNMATCHED</dt>
	 * <dd>ordinary text encountered within the plugin's syntax mode
	 * which doesn't match any pattern.</dd>
	 * </dl><p>
	 * This implementation does nothing (ignoring the passed arguments)
	 * and just returns the given <tt>$aState</tt>.
	 * </p>
	 * @param $aMatch String The text matched by the patterns.
	 * @param $aState Integer The lexer state for the match.
	 * @param $aPos Integer The character position of the matched text.
	 * @param $aHandler Object Reference to the Doku_Handler object.
	 * @return Integer The current lexer state.
	 * @public
	 * @see render()
	 * @static
	 */
	function handle($aMatch, $aState, $aPos, &$aHandler) {
		return $aState;	// doesn't really matter as it's ignored anyway ...
	} // handle()

	/**
	 * Handle the actual output creation.
	 *
	 * <p>
	 * The method checks for the given <tt>$aFormat</tt> and returns
	 * <tt>FALSE</tt> when a format isn't supported.
	 * <tt>$aRenderer</tt> contains a reference to the renderer object
	 * which is currently handling the rendering.
	 * The contents of <tt>$aData</tt> is the return value of the
	 * <tt>handle()</tt> method.
	 * </p><p>
	 * Besides "eating" the BOM implicitely this implementation does
	 * nothing (ignoring all passed arguments) and always returns
	 * <tt>TRUE</tt>.
	 * </p>
	 * @param $aFormat String The output format to generate.
	 * @param $aRenderer Object A reference to the renderer object.
	 * @param $aData Integer The data created/returned by the
	 * <tt>handle()</tt> method.
	 * @return Boolean <tt>TRUE</tt> always since there's no actual
	 * rendering done and hence can't ever fail.
	 * @public
	 * @see handle()
	 * @static
	 */
	function render($aFormat, &$aRenderer, $aData) {
		// nothing to do here - just 'eat' the BOM
		return TRUE;
	} // render()

	//@}
} // class syntax_plugin_bomfix
} // if
?>
