xref: /plugin/zwidoku/getEncyc.php (revision 1cc518519efdb2527f225b3a3fd18643f0187f9b) 
1<?php
2/**
3 * ZWIdoku Plugin: Export DokuWiki acrticle to the ZWI format.
4 *
5 * @license  LGPL 2 (http://www.gnu.org/licenses/gpl.html)
6 * @author   S.Chekanov (KSF)
7 *
8 */
9########################## start configuration ###############################
10
11# add name of your encyclopedia (or sandbox)
12$wgMzwiName="sandbox";
13#
14# action tab to make "Export to ZWI"
15$wgMzwiTab=true;
16# Submission webpage to Encyclosphere
17# Set to 0 to trigger download and nothing more
18# Set to 1 to create ZWI in extension/ZWIMaker/tmp and do not do anything
19# Set to 2 to create ZWI in extension/ZWIMaker/tmp and submit to the Encyclosphre
20$wgMzwiSubmit=1;
21#
22# if false, then anybody after login can send ZWI file to Encyclosphere
23# if true, then only authors or contributors can send the article to Encyclosphere
24$wgMzwiAuthorApprove=false;
25#
26# Password for the submission
27$wgMzwiPassword='0123456789';
28#
29# Encyclosphere submission URL if select 1
30$wgMzwiSubmitUrl="https://encycloreader.org/upload/";
31#
32# what about the license?
33$wgMzwiLicense='CC BY-SA 3.0';
34#
35# Current URL of your wiki
36$CURRENT_URL="https://enhub.org/dokuwiki/";
37#
38############################ end configuration #############################
39
40
41if(!defined('DOKU_INC')) define('DOKU_INC',realpath(dirname(__FILE__).'/../../../').'/');
42if(!defined('DOKU_LIB')) define('DOKU_LIB',realpath(dirname(__FILE__).'/../../').'/');
43if(!defined('DOKU_PLUGIN')) define('DOKU_PLUGIN',DOKU_LIB.'plugins/');
44//define('DOKU_MAIN',realpath(dirname(__FILE__).'/../../../').'/');
45
46// must be run within Dokuwiki
47if(!defined('DOKU_INC')) die("Cannot find installed DokuWiki");
48
49require_once(DOKU_INC.'/inc/init.php');
50require_once(DOKU_INC.'/inc/template.php');
51
52
53$actual_link = (isset($_SERVER['HTTPS']) && $_SERVER['HTTPS'] === 'on' ? "https" : "http") . "://$_SERVER[HTTP_HOST]$_SERVER[REQUEST_URI]";
54$newlink = str_replace("lib/plugins/zwidoku/getEncyc.php?id=", "doku.php?id=", "$actual_link");
55
56$tmp=explode("getEncyc.php", $actual_link);
57$ext_path = trim( $tmp[0] );
58
59
60require("Html2Text.php");
61require("ShortDescription.php");
62
63
64       function texifyReference($reference) {
65                $patterns[ 0] = '/[áâ�| åä]/ui';
66                $patterns[ 1] = '/[ðéêèë]/ui';
67                $patterns[ 2] = '/[íîìï]/ui';
68                $patterns[ 3] = '/[óôòøõö]/ui';
69                $patterns[ 4] = '/[úûùü]/ui';
70                $patterns[ 5] = '/æ/ui';
71                $patterns[ 6] = '/ç/ui';
72                $patterns[ 7] = '/�~_/ui';
73                $patterns[ 8] = '/\\s/';
74                $patterns[ 9] = '/#/';
75                $patterns[10] = '/[^A-Za-z0-9\\-:]/';
76                $replacements[ 0] = 'a';
77                $replacements[ 1] = 'e';
78                $replacements[ 2] = 'i';
79                $replacements[ 3] = 'o';
80                $replacements[ 4] = 'u';
81                $replacements[ 5] = 'ae';
82                $replacements[ 6] = 'c';
83                $replacements[ 7] = 'ss';
84                $replacements[ 8] = '-';
85                $replacements[ 9] = ':';
86                $replacements[10] = '_';
87
88                return preg_replace($patterns, $replacements, $reference);
89        }
90
91
92
93$ID = cleanID(getID());
94//die("ID=".$ID);
95$onlyCode = $INPUT->str('onlyCode');
96$insideTag = $INPUT->str('insideTag');
97$title=tpl_pagetitle(null,true);
98$titletext=tpl_pagetitle(null,true);
99
100
101    if (empty($conf['useacl']) || auth_quickaclcheck($ID) >= AUTH_READ) {
102    	$file = rawWiki($ID);
103        $articleWiki = $file;
104
105	$fileLastMod = wikiFN($ID);
106        $lastMod     = @filemtime($fileLastMod); // from page
107        $NS=getNS($ID);
108
109        // get revisions
110        $filepath = str_replace(":", "/", $ID);
111        // list all revisions
112        $path=DOKU_INC."data/attic/". $filepath."*";
113        $files = glob($path);
114
115        //print_r($files);
116
117        $changes="data/meta/".$filepath .".changes";
118        $indexed="data/meta/".$filepath .".indexed";
119        $meta="data/meta/".$filepath .".meta";
120
121        $dir_changes=DOKU_INC."data/meta/".$filepath .".changes";
122        $dir_indexed=DOKU_INC."data/meta/".$filepath .".indexed";
123        $dir_meta=DOKU_INC."data/meta/".$filepath .".meta";
124
125        //echo $dir_changes;
126
127    	//if ($onlyCode)
128    	//	$file = preg_replace('/[\s\S]*<code>/m', '', preg_replace('/<\/code>[\s\S]*/m', '', $file));
129    	//if ($insideTag)
130        //		$file = preg_replace('/[\s\S]*<' . $insideTag . '[^>]*>/m', '', preg_replace('/<\/' . $insideTag . '>[\s\S]*/m', '', $file));
131
132    	//print $file;
133       // file_put_contents("tmp/article.txt", $file);
134
135
136$pieces = explode(":", $ID);
137
138$filename="article";
139if (count($pieces)>1)
140   $filename=texifyReference($pieces[1]);  // no spaces etc..
141
142$filename=DOKU_INC."data/cache/".$filename . ".zwi";
143$zipfilename=$filename;
144// clear
145unlink( $filename );
146
147//$filename="/tmp/".$filename . ".wik";
148//echo $filename;
149//die("OK");
150
151$zip = new ZipArchive;
152$isZipOpen=$zip->open($filename, ZipArchive::CREATE);
153
154if ($isZipOpen === TRUE)
155{
156    // Add files to the zip file
157    //$zip->addFile('test.txt');
158    //$zip->addFile('test.pdf');
159    // Add random.txt file to zip and rename it to newfile.txt
160    //$zip->addFile('random.txt', 'newfile.txt');
161    // Add a file new.txt file to zip using the text specified
162    $zip->addFromString('article.dokuwiki', $articleWiki);
163
164   // XHTML for embedding
165   $xx=$CURRENT_URL."/doku.php?id=".$ID."&do=export_xhtmlbody";
166   $body_content = file_get_contents($xx);
167
168
169   # push all revisions too
170    $xr=0;
171    foreach ($files as $xfile) {
172             $destination = str_replace(DOKU_INC, "", $xfile);
173             //print($destination);
174             $zip->addFile($xfile, $destination);
175             $xr=$xr+1;
176             };
177
178    // metadata
179    $zip->addFile($dir_changes, $changes);
180    $zip->addFile($dir_indexed, $indexed);
181    $zip->addFile($dir_meta,   $meta);
182
183
184    // css
185    $css_file=DOKU_INC."/lib/plugins/zwidoku/files/common.css";
186    $zip->addFile($css_file, "data/css/common.css");
187    $css_file=DOKU_INC."/lib/plugins/zwidoku/files/fonts.css";
188    $zip->addFile($css_file, "data/css/fonts.css");
189    $css_file=DOKU_INC."/lib/plugins/zwidoku/files/doku.css";
190    $zip->addFile($css_file, "data/css/doku.css");
191
192
193    $page_title=tpl_pagetitle(null,true);
194    //$page_info=tpl_pageinfo(true);
195
196    //die("OK");
197
198    // list used plugins for consistency
199     foreach(glob(DOKU_INC."lib/plugins/*", GLOB_ONLYDIR) as $dir) {
200        $usedplugins[] = basename($dir);
201     }
202
203
204    $zip->addFromString('plugins.json', json_encode($usedplugins));
205
206
207    $DESC = new ShortDescription($articleWiki,$articleTXT);
208    $description=$DESC->getDescription();
209
210    $Lang="en";
211
212    // remove styles
213    $html_tmp=preg_replace('/(<(script|style)\b[^>]*>).*?(<\/\2>)/is', "$1$3", $body_content);
214    $html_tmp=strip_tags($html_tmp, '<b>');    // remove bold, so it will not move to upper case;
215    $html_tmp=strip_tags($html_tmp, '<i>'); // remove italic
216    $html2TextConverter = new \Html2Text\Html2Text($html_tmp);
217    $articleTXT = $html2TextConverter->getText();
218
219
220    $content_array= array();
221    $content_array["article.dokuwiki"]=sha1($file); //$revision->getSha1();
222    $content_array["article.html"]=sha1($body_content);
223    $content_array["article.txt"]=sha1($articleTXT);
224
225    $generator="DokuWiki";
226
227    // ZWI -specific metadata for the current revision
228    $tt['ZWIversion'] = "1.3";
229    $tt['Primary'] = "article.dokuwiki";
230    $tt['Title'] = $title;
231    $tt['Namespace'] = $NS;
232    $tt['LastModified'] = dformat($INFO['lastmod']);
233    $tt['TimeCreated'] = dformat($INFO['lastmod']);
234    $tt['Location'] =  $fileLastMod;
235    $tt['Revisions'] =  $xr;
236    $tt['Publisher']=$wgMzwiName;
237    $tt['Content'] = $content_array;
238    $tt['GeneratorName'] = $generator;
239
240   // short description
241   // article information
242   $pagemeta=pageinfo();
243
244   // do not expose pass
245   $pagemeta["userinfo"]["pass"]="";
246   $tt['PageInfo'] =  $pagemeta;
247   //$tt['Creator']=$pagemeta['meta'][;
248   //$tt['Contributors']=$pagemeta['contributor'];
249   // $mresult = array_merge($tt, $pagemeta);
250   //$mresult=$tt;
251
252    $tt['Lang'] = $Lang;
253    //$tt['Comment'] = $title->getEditNotices ();
254    $tt['Rating'] = "";
255    $tt['License'] = $wgMzwiLicense;
256    $tt['Description']=$description;
257    $tt['Author']=$author;
258
259   // write
260   $zip->addFromString('metadata.json', json_encode($tt, JSON_PRETTY_PRINT));
261
262
263$toReplace = array();
264$replacement = array();
265
266$nn=0;
267$doc = new DOMDocument();
268@$doc->loadHTML($body_content);
269$tags = $doc->getElementsByTagName('img');
270foreach ($tags as $tag) {
271       $URL=$tag->getAttribute('src');
272       //die($URL);
273
274       $pieces = explode($NS.":", $URL);
275       $img="none";
276       if (count($pieces))
277                     $img=$pieces[1];
278
279       $output="data/media/".$NS."/".$img;
280       //echo $output ."\n";
281       $imgfile_tmp=$output;
282       //die($imgfile_tmp);
283
284       $imgfile=DOKU_INC.$output;
285       //die($imgfile);
286
287       $info = pathinfo($imgfile);
288       $ext   = $info["extension"];
289       if (strlen($ext)<1) continue;
290
291       if (!file_exists($imgfile)) continue;
292
293       //die($imgfile);
294
295       //echo $imgfile ."\n";
296       $URL = str_replace("&", "&amp;", $URL);
297       //echo $URL . " -> " . $imgfile;
298       //die($imgfile);
299
300       //print($URL);
301
302       $zip->addFile($imgfile, $output);
303       array_push($toReplace,$URL);
304       array_push($replacement,$imgfile_tmp);
305
306       //$newbody_content  = str_replace($URL, $imgfile_tmp, $body_content);
307       //$newhtml_content  = str_replace($URL, $imgfile_tmp, $html_content);
308       //print($URL. "\n");
309
310       $nn=$nn+1;
311}
312
313
314//print_r($toReplace);
315//print_r($replacement);
316//die();
317
318//$newhtml_content = str_replace($toReplace, $replacement, $html_content);
319$newbody_content = str_replace($toReplace, $replacement, $body_content);
320
321//print($newhtml_content);
322//die();
323
324/*
325$lines = explode("\n", $newbody_content);
326$exclude = array();
327$n=0;
328foreach ($lines as $line) {
329    if (strpos($line, 'stylesheet') !== FALSE) {
330            $exclude[] = "<link rel=\"stylesheet\" href=\"data/css/styles.css\">";
331            continue;
332    }
333    $exclude[] = $line;
334}
335$newhtml_content=implode("\n", $exclude);
336*/
337
338
339$start_content = file_get_contents( DOKU_INC."/lib/plugins/zwidoku/html_start" );
340$end_content = file_get_contents( DOKU_INC."/lib/plugins/zwidoku/html_end" );
341
342$html_content = $start_content . $newbody_content  . $end_content;
343
344
345$zip->addFromString('article.html', $html_content);
346// $zip->addFromString('article.xhtml', $newbody_content);
347$zip->addFromString("article.txt", $articleTXT);
348
349
350}
351
352// All files are added, so close the zip file.
353$zip->close();
354
355/*
356if (file_exists($filename)) {
357     print($filename);
358};
359*/
360
361/*
362  if (file_exists($filename)) {
363     header('Content-Type: application/zip');
364     header('Content-Disposition: attachment; filename="'.basename($filename).'"');
365     header('Content-Length: ' . filesize($filename));
366     flush();
367     readfile($filename);
368     // delete file
369     unlink($filename);
370   }
371 */
372
373
374//die($ext_path);
375
376$permissionErr = 0;
377$xsub="";
378if ($permissionErr ==0)
379        $xsub="<input type=\"submit\" name=\"submit\" value=\"Submit to the Encyclosphere Network\" />";
380else if ($permissionErr == 1)
381        $xsub="<input type=\"submit\" name=\"submit\" value=\"Submission to the Encyclosphere is disabled\"  readonly=\"readonly\"  onfocus=\"this.blur();\"  disabled/> <br> (not registered user)";
382else if ($permissionErr == 2)
383        $xsub="<input type=\"submit\" name=\"submit\" value=\"Submission to the Encyclosphere is disabled\"   readonly=\"readonly\"   onfocus=\"this.blur();\"  disabled/> <br> (did not contribute to this article)";
384
385
386$submit_script=$ext_path . "/" . "zwipush.php";
387
388
389$str = <<<EOD
390<!DOCTYPE html>
391<html class="client-nojs" lang="en" dir="ltr">
392<head>
393<meta charset="UTF-8"/>
394<title>ZWI submit</title>
395<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=5.0"/>
396<link rel="stylesheet" type="text/css" href="$ext_path/css/zwimaker.css" />
397</head>
398<body>
399<p>
400</p>
401<center>
402<h3>Export the article '$title' ?</h3>
403<p>
404</p>
405<form action="$submit_script" method="post">
406$xsub
407<br>Submit this article to the Encyclosphere Network
408that can be viewed in <a href="https://encycloreader.org/">EncycloReader</a> supported by <a href='https://encyclosphere.org/about/'><img src='$ext_path/img/Encyclosphere_logo24px.png' alt="Encyclosphere" style='vertical-align:middle;margin:0;'/>KSF</a>
409<p></p>
410<input type="submit" name="download" value="Download to your computer" />
411<br>Save this article to your computer
412<p></p>
413<input type="button" name="cancel" value="Cancel" onClick="window.location='$newlink';" />
414<input type="hidden" id="zwititle" name="zwititle" value='$titletext'  >
415<input type="hidden" id="zwifile" name="zwifile" value='$zipfilename' >
416<input type="hidden" id="posturl" name="posturl" value='$wgMzwiSubmitUrl' >
417<input type="hidden" id="postkey" name="postkey" value='$wgMzwiPassword'  >
418<input type="hidden" id="backlink" name="backlink" value='$newlink'  >
419<input type="hidden" id="extpath" name="extpath" value='$ext_path'  >
420<input type="hidden" id="permission" name="permission" value='$permissionErr'  >
421</form>
422<center>
423</body>
424</html>
425EOD;
426
427    print($str);
428
429    }
430    else
431    	print "Unauthorized";
432
433?>
434
435