4 * Copyright 2005 Wincor Nixdorf International GmbH
6 * This file is part of PhpWiki.
8 * PhpWiki is free software; you can redistribute it and/or modify
9 * it under the terms of the GNU General Public License as published by
10 * the Free Software Foundation; either version 2 of the License, or
11 * (at your option) any later version.
13 * PhpWiki is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 * GNU General Public License for more details.
18 * You should have received a copy of the GNU General Public License
19 * along with PhpWiki; if not, write to the Free Software
20 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
24 * HtmlConverter: Convert HTML tags as far to Wiki markup as possible
25 * and eliminate all other HTML markup, so the output can be
26 * copied and pasted into a wiki page.
27 * Credit to an unknown programmer, who has provided the first
28 * version 0.01 on http://www.gpgstudy.com/striphtml.phps
29 * Usage: <?plugin HtmlConverter ?>
30 * Author: HendrikScheider <hendrik.scheider@wincor-nixdorf.com>
33 class WikiPlugin_HtmlConverter extends WikiPlugin
37 return "HtmlConverter";
40 function getDescription () {
41 return _("Convert HTML markup into wiki markup.");
44 function getVersion() {
45 return preg_replace("/[Revision: $]/", '',
49 function getDefaultArguments() {
53 function run($dbi, $argstr, &$request, $basepage) {
55 /* plugin not yet has arguments - save for later (copied from UpLoad)
56 $args = $this->getArgs($argstr, $request);
60 $form = HTML::form(array('action' => $request->getPostURL(),
61 'enctype' => 'multipart/form-data',
63 $contents = HTML::div(array('class' => 'wikiaction'));
64 $contents->pushContent(HTML::input(array('type' => 'hidden',
65 'name' => 'MAX_FILE_SIZE',
66 'value' => MAX_UPLOAD_SIZE)));
67 $contents->pushContent(HTML::input(array('name' => 'userfile',
70 $contents->pushContent(HTML::raw(" "));
71 $contents->pushContent(HTML::input(array('value' => _("Convert"),
72 'type' => 'submit')));
73 $form->pushContent($contents);
76 $userfile = $request->getUploadedFile('userfile');
78 $userfile_name = $userfile->getName();
79 $userfile_name = basename($userfile_name);
80 $userfile_tmpname = $userfile->getTmpName();
82 if ( !preg_match("/(\.html|\.htm)$/i", $userfile_name)) {
83 $message->pushContent(_("Only files with extension HTML are allowed"),HTML::br(),HTML::br());
85 $message->pushContent( _("Processed $userfile_name"), HTML::br(), HTML::br());
86 $message->pushContent( _("Copy the output below and paste it into your Wiki page."), HTML::br());
87 $message->pushContent( $this->_process( $userfile_tmpname));
90 $message->pushContent(HTML::br(),HTML::br());
94 $result->pushContent($form);
95 $result->pushContent($message);
99 function _processA(&$file) {
101 $file = eregi_replace(
102 "<a([[:space:]]+)href([[:space:]]*)=([[:space:]]*)\"([-/.a-zA-Z0-9_~#@%$?&=:\200-\377\(\)[:space:]]+)\"([^>]*)>", "{{\\4}}", $file);
104 $file = eregi_replace("{{([-/a-zA-Z0-9._~#@%$?&=:\200-\377\(\)[:space:]]+)}}([^<]+)</a>", "[ \\2 | \\1 ]", $file);
107 function _processIMG(&$file) {
109 $img_regexp = "_<img\s+src\s*=\s*\"([-/.a-zA-Z0-9\_~#@%$?&=:\200-\377\(\)\s]+)\"[^>]*>_";
111 $file = preg_replace( $img_regexp, "\n\n[Upload:\\1]", $file);
114 function _processUL( &$file) {
116 // put any <li>-Tag in a new line to indent correctly and strip trailing white space (including new-lines)
117 $file = str_replace( "<li", "\n<li", $file);
118 $file = preg_replace( "/<li>\s*/", "<li>", $file);
120 $enclosing_regexp = "_(.*)<ul\s?[^>]*>((?U).*)</ul>(.*)_is";
122 $embedded_fragment_array = array();
123 $found = preg_match( $enclosing_regexp, $file, $embedded_fragment_array);
125 $indented = str_replace( $indent_tag, "\t".$indent_tag, $embedded_fragment_array[2]);
126 // string the file together again with the indented part in the middle.
127 // a <p> is inserted instead of the erased <ul> tags to have a paragraph generated at the end of the script
128 $file = $embedded_fragment_array[1] . "<p>" . $indented . $embedded_fragment_array[3];
129 $found = preg_match( $enclosing_regexp, $file, $embedded_fragment_array);
133 function _process( $file_name) {
135 $file = file_get_contents( $file_name);
136 $file = html_entity_decode( $file);
138 $ascii = '[\x00-\x7F]';
139 $euc = '[\xA1-\xFE][\xA1-\xFE]';
140 $character = "$ascii|$euc";
142 $this->_processA( $file);
143 $this->_processIMG( $file);
144 $this->_processUL( $file);
146 $file = str_replace ("\r\n", "\n", $file);
148 $file = eregi_replace ("<h1[[:space:]]?[^>]*>", "\n\n!!!!", $file);
150 $file = eregi_replace ("<h2[[:space:]]?[^>]*>", "\n\n!!!", $file);
152 $file = eregi_replace ("<h3[[:space:]]?[^>]*>", "\n\n!!", $file);
154 $file = eregi_replace ("<h4[[:space:]]?[^>]*>", "\n\n!", $file);
156 $file = eregi_replace ("<h5[[:space:]]?[^>]*>", "\n\n__", $file);
158 $file = eregi_replace ("</h1>", "\n\n", $file);
160 $file = eregi_replace ("</h2>", "\n\n", $file);
162 $file = eregi_replace ("</h3>", "\n\n", $file);
164 $file = eregi_replace ("</h4>", "\n\n", $file);
166 $file = eregi_replace ("</h5>", "__\n\n", $file);
168 $file = eregi_replace ("<hr[[:space:]]?[^>]*>", "\n----\n", $file);
170 $file = eregi_replace ("<li[[:space:]]?[^>]*>", "* ", $file);
172 // strip all tags, except for <pre>, which is supported by wiki
173 // and <p>'s which will be converted after compression.
174 $file = strip_tags($file, "<pre><p>");
175 // strip </p> end tags with trailing white space
176 $file = preg_replace ("_</p>\s*_i", "", $file);
178 // get rid of all blank lines
179 $file = preg_replace( "/\n\s*\n/", "\n", $file);
181 // finally only add paragraphs where defined by inserting double new-lines
182 // be sure to only catch <p> or <p[space]...> and not <pre>!
183 // Actually <p> tags with all white space and one new-line before
184 // and after around are replaced
185 $file = preg_replace ("_\n?[^\S\n]*<p(\s[^>]*|)>[^\S\n]*\n?_i", "\n\n", $file);
187 // strip attributes from <pre>-Tags and add a new-line before
188 $file = preg_replace ("_<pre(\s[^>]*|)>_iU", "\n<pre>", $file);
190 $outputArea = HTML::textarea(array('rows' => '30', 'cols' => '80'));
192 $outputArea->pushContent( _($file));
193 $result->pushContent( $outputArea);