include/bbcode.php

   1 <?php
   2
   3 require_once("include/oembed.php");
   4 require_once('include/event.php');
   5
   6
   7
   8 function stripcode_br_cb($s) {
   9         return '[code]' . str_replace('<br />', '', $s[1]) . '[/code]';
  10 }
  11
  12 function tryoembed($match){
  13         $url = ((count($match)==2)?$match[1]:$match[2]);
  14 //      logger("tryoembed: $url");
  15
  16         $o = oembed_fetch_url($url);
  17
  18         //echo "<pre>"; var_dump($match, $url, $o); killme();
  19
  20         if ($o->type=="error") return $match[0];
  21
  22         $html = oembed_format_object($o);
  23         return $html; //oembed_iframe($html,$o->width,$o->height);
  24
  25 }
  26
  27 // [noparse][i]italic[/i][/noparse] turns into
  28 // [noparse][ i ]italic[ /i ][/noparse],
  29 // to hide them from parser.
  30
  31 function bb_spacefy($st) {
  32   $whole_match = $st[0];
  33   $captured = $st[1];
  34   $spacefied = preg_replace("/\[(.*?)\]/", "[ $1 ]", $captured);
  35   $new_str = str_replace($captured, $spacefied, $whole_match);
  36   return $new_str;
  37 }
  38
  39 // The previously spacefied [noparse][ i ]italic[ /i ][/noparse],
  40 // now turns back and the [noparse] tags are trimed
  41 // returning [i]italic[/i]
  42
  43 function bb_unspacefy_and_trim($st) {
  44   $whole_match = $st[0];
  45   $captured = $st[1];
  46   $unspacefied = preg_replace("/\[ (.*?)\ ]/", "[$1]", $captured);
  47   return $unspacefied;
  48 }
  49
  50         // BBcode 2 HTML was written by WAY2WEB.net
  51         // extended to work with Mistpark/Friendica - Mike Macgirvin
  52
  53 function bbcode($Text,$preserve_nl = false, $tryoembed = true) {
  54
  55         $a = get_app();
  56
  57         // Hide all [noparse] contained bbtags spacefying them
  58
  59         $Text = preg_replace_callback("/\[noparse\](.*?)\[\/noparse\]/ism", 'bb_spacefy',$Text);
  60         $Text = preg_replace_callback("/\[nobb\](.*?)\[\/nobb\]/ism", 'bb_spacefy',$Text);
  61         $Text = preg_replace_callback("/\[pre\](.*?)\[\/pre\]/ism", 'bb_spacefy',$Text);
  62
  63
  64         // Extract a single private image which uses data url's since preg has issues with
  65         // large data sizes. Stash it away while we do bbcode conversion, and then put it back
  66         // in after we've done all the regex matching. We cannot use any preg functions to do this.
  67
  68         $saved_image = '';
  69         $img_start = strpos($Text,'[img]data:');
  70         $img_end = strpos($Text,'[/img]');
  71
  72         if($img_start !== false && $img_end !== false && $img_end > $img_start) {
  73                 $start_fragment = substr($Text,0,$img_start);
  74                 $img_start += strlen('[img]');
  75                 $saved_image = substr($Text,$img_start,$img_end - $img_start);
  76                 $end_fragment = substr($Text,$img_end + strlen('[/img]'));
  77 //              logger('saved_image: ' . $saved_image,LOGGER_DEBUG);
  78                 $Text = $start_fragment . '[$#saved_image#$]' . $end_fragment;
  79         }
  80
  81         // If we find any event code, turn it into an event.
  82         // After we're finished processing the bbcode we'll
  83         // replace all of the event code with a reformatted version.
  84
  85         $ev = bbtoevent($Text);
  86
  87
  88         // Replace any html brackets with HTML Entities to prevent executing HTML or script
  89         // Don't use strip_tags here because it breaks [url] search by replacing & with amp
  90
  91         $Text = str_replace("<", "&lt;", $Text);
  92         $Text = str_replace(">", "&gt;", $Text);
  93
  94         // Convert new line chars to html <br /> tags
  95
  96         $Text = nl2br($Text);
  97         if($preserve_nl)
  98                 $Text = str_replace(array("\n","\r"), array('',''),$Text);
  99
 100
 101         // Set up the parameters for a URL search string
 102         $URLSearchString = "^\[\]";
 103         // Set up the parameters for a MAIL search string
 104         $MAILSearchString = $URLSearchString;
 105
 106
 107         // Perform URL Search
 108
 109         $Text = preg_replace("/([^\]\=]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism", '$1<a href="$2" target="external-link">$2</a>', $Text);
 110
 111         if ($tryoembed)
 112                 $Text = preg_replace_callback("/\[bookmark\=([^\]]*)\].*?\[\/bookmark\]/ism",'tryoembed',$Text);
 113
 114         $Text = preg_replace("/\[bookmark\=([^\]]*)\](.*?)\[\/bookmark\]/ism",'[url=$1]$2[/url]',$Text);
 115
 116         if ($tryoembed)
 117                 $Text = preg_replace_callback("/\[url\]([$URLSearchString]*)\[\/url\]/ism",'tryoembed',$Text);
 118
 119         $Text = preg_replace("/\[url\]([$URLSearchString]*)\[\/url\]/ism", '<a href="$1" target="external-link">$1</a>', $Text);
 120         $Text = preg_replace("/\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '<a href="$1" target="external-link">$2</a>', $Text);
 121         //$Text = preg_replace("/\[url\=([$URLSearchString]*)\]([$URLSearchString]*)\[\/url\]/ism", '<a href="$1" target="_blank">$2</a>', $Text);
 122
 123         // we may need to restrict this further if it picks up too many strays
 124         // link acct:user@host to a webfinger profile redirector
 125
 126         $Text = preg_replace('/acct:(.*?)@(.*?)([ ,])/', '<a href="' . $a->get_baseurl() . '/acctlink?addr=' . "$1@$2"
 127                 . '" target="extlink" >acct:' . "$1@$2$3" . '</a>',$Text);
 128
 129         // Perform MAIL Search
 130         $Text = preg_replace("/\[mail\]([$MAILSearchString]*)\[\/mail\]/", '<a href="mailto:$1">$1</a>', $Text);
 131         $Text = preg_replace("/\[mail\=([$MAILSearchString]*)\](.*?)\[\/mail\]/", '<a href="mailto:$1">$2</a>', $Text);
 132
 133         // Check for bold text
 134         $Text = preg_replace("(\[b\](.*?)\[\/b\])ism",'<strong>$1</strong>',$Text);
 135
 136         // Check for Italics text
 137         $Text = preg_replace("(\[i\](.*?)\[\/i\])ism",'<em>$1</em>',$Text);
 138
 139         // Check for Underline text
 140         $Text = preg_replace("(\[u\](.*?)\[\/u\])ism",'<u>$1</u>',$Text);
 141
 142         // Check for strike-through text
 143         $Text = preg_replace("(\[s\](.*?)\[\/s\])ism",'<strike>$1</strike>',$Text);
 144
 145         // Check for over-line text
 146         $Text = preg_replace("(\[o\](.*?)\[\/o\])ism",'<span class="overline">$1</span>',$Text);
 147
 148         // Check for colored text
 149         $Text = preg_replace("(\[color=(.*?)\](.*?)\[\/color\])ism","<span style=\"color: $1;\">$2</span>",$Text);
 150
 151         // Check for sized text
 152         // [size=50] --> font-size: 50px (with the unit).
 153         $Text = preg_replace("(\[size=(\d*?)\](.*?)\[\/size\])ism","<span style=\"font-size: $1px;\">$2</span>",$Text);
 154         $Text = preg_replace("(\[size=(.*?)\](.*?)\[\/size\])ism","<span style=\"font-size: $1;\">$2</span>",$Text);
 155
 156         // Check for centered text
 157         $Text = preg_replace("(\[center\](.*?)\[\/center\])ism","<div style=\"text-align:center;\">$1</div>",$Text);
 158
 159         // Check for list text
 160         $Text = str_replace("[*]", "<li>", $Text);
 161         $Text = preg_replace("/\[li\](.*?)\[\/li\]/ism", '<li>$1</li>' ,$Text);
 162
 163         // handle nested lists
 164         $endlessloop = 0;
 165
 166         while ((((strpos($Text, "[/list]") !== false) && (strpos($Text, "[list") !== false)) ||
 167                ((strpos($Text, "[/ol]") !== false) && (strpos($Text, "[ol]") !== false)) ||
 168                ((strpos($Text, "[/ul]") !== false) && (strpos($Text, "[ul]") !== false))) && (++$endlessloop < 20)) {
 169                 $Text = preg_replace("/\[list\](.*?)\[\/list\]/ism", '<ul class="listbullet" style="list-style-type: circle;">$1</ul>' ,$Text);
 170                 $Text = preg_replace("/\[list=\](.*?)\[\/list\]/ism", '<ul class="listnone" style="list-style-type: none;">$1</ul>' ,$Text);
 171                 $Text = preg_replace("/\[list=1\](.*?)\[\/list\]/ism", '<ul class="listdecimal" style="list-style-type: decimal;">$1</ul>' ,$Text);
 172                 $Text = preg_replace("/\[list=((?-i)i)\](.*?)\[\/list\]/ism",'<ul class="listlowerroman" style="list-style-type: lower-roman;">$2</ul>' ,$Text);
 173                 $Text = preg_replace("/\[list=((?-i)I)\](.*?)\[\/list\]/ism", '<ul class="listupperroman" style="list-style-type: upper-roman;">$2</ul>' ,$Text);
 174                 $Text = preg_replace("/\[list=((?-i)a)\](.*?)\[\/list\]/ism", '<ul class="listloweralpha" style="list-style-type: lower-alpha;">$2</ul>' ,$Text);
 175                 $Text = preg_replace("/\[list=((?-i)A)\](.*?)\[\/list\]/ism", '<ul class="listupperalpha" style="list-style-type: upper-alpha;">$2</ul>' ,$Text);
 176                 $Text = preg_replace("/\[ul\](.*?)\[\/ul\]/ism", '<ul class="listbullet" style="list-style-type: circle;">$1</ul>' ,$Text);
 177                 $Text = preg_replace("/\[ol\](.*?)\[\/ol\]/ism", '<ul class="listdecimal" style="list-style-type: decimal;">$1</ul>' ,$Text);
 178         }
 179
 180         $Text = preg_replace("/\[th\](.*?)\[\/th\]/sm", '<th>$1</th>' ,$Text);
 181         $Text = preg_replace("/\[td\](.*?)\[\/td\]/sm", '<td>$1</td>' ,$Text);
 182         $Text = preg_replace("/\[tr\](.*?)\[\/tr\]/sm", '<tr>$1</tr>' ,$Text);
 183         $Text = preg_replace("/\[table\](.*?)\[\/table\]/sm", '<table>$1</table>' ,$Text);
 184
 185         $Text = preg_replace("/\[table border=1\](.*?)\[\/table\]/sm", '<table border="1" >$1</table>' ,$Text);
 186         $Text = preg_replace("/\[table border=0\](.*?)\[\/table\]/sm", '<table border="0" >$1</table>' ,$Text);
 187
 188         $Text = str_replace('[hr]','<hr />', $Text);
 189
 190         // This is actually executed in prepare_body()
 191
 192         $Text = str_replace('[nosmile]','',$Text);
 193
 194         // Check for font change text
 195         $Text = preg_replace("/\[font=(.*?)\](.*?)\[\/font\]/sm","<span style=\"font-family: $1;\">$2</span>",$Text);
 196
 197         // Declare the format for [code] layout
 198
 199         $Text = preg_replace_callback("/\[code\](.*?)\[\/code\]/ism",'stripcode_br_cb',$Text);
 200
 201         $CodeLayout = '<code>$1</code>';
 202         // Check for [code] text
 203         $Text = preg_replace("/\[code\](.*?)\[\/code\]/ism","$CodeLayout", $Text);
 204
 205         // Declare the format for [spoiler] layout
 206         $SpoilerLayout = '<blockquote class="spoiler">$1</blockquote>';
 207
 208         // Check for [spoiler] text
 209         // handle nested quotes
 210         $endlessloop = 0;
 211         while ((strpos($Text, "[/spoiler]") !== false) and (strpos($Text, "[spoiler]") !== false) and (++$endlessloop < 20))
 212                 $Text = preg_replace("/\[spoiler\](.*?)\[\/spoiler\]/ism","$SpoilerLayout", $Text);
 213
 214         // Check for [spoiler=Author] text
 215
 216         $t_wrote = t('$1 wrote:');
 217
 218         // handle nested quotes
 219         $endlessloop = 0;
 220         while ((strpos($Text, "[/spoiler]")!== false)  and (strpos($Text, "[spoiler=") !== false) and (++$endlessloop < 20))
 221                 $Text = preg_replace("/\[spoiler=[\"\']*(.*?)[\"\']*\](.*?)\[\/spoiler\]/ism",
 222                                      "<br /><strong class=".'"spoiler"'.">" . $t_wrote . "</strong><blockquote class=".'"spoiler"'.">$2</blockquote>",
 223                                      $Text);
 224
 225         // Declare the format for [quote] layout
 226         $QuoteLayout = '<blockquote>$1</blockquote>';
 227
 228         // Check for [quote] text
 229         // handle nested quotes
 230         $endlessloop = 0;
 231         while ((strpos($Text, "[/quote]") !== false) and (strpos($Text, "[quote]") !== false) and (++$endlessloop < 20))
 232                 $Text = preg_replace("/\[quote\](.*?)\[\/quote\]/ism","$QuoteLayout", $Text);
 233
 234         // Check for [quote=Author] text
 235
 236         $t_wrote = t('$1 wrote:');
 237
 238         // handle nested quotes
 239         $endlessloop = 0;
 240         while ((strpos($Text, "[/quote]")!== false)  and (strpos($Text, "[quote=") !== false) and (++$endlessloop < 20))
 241                 $Text = preg_replace("/\[quote=[\"\']*(.*?)[\"\']*\](.*?)\[\/quote\]/ism",
 242                                      "<br /><strong class=".'"author"'.">" . $t_wrote . "</strong><blockquote>$2</blockquote>",
 243                                      $Text);
 244
 245         // [img=widthxheight]image source[/img]
 246         //$Text = preg_replace("/\[img\=([0-9]*)x([0-9]*)\](.*?)\[\/img\]/ism", '<img src="$3" style="height: $2px; width: $1px;" >', $Text);
 247         $Text = preg_replace("/\[img\=([0-9]*)x([0-9]*)\](.*?)\[\/img\]/ism", '<img src="$3" style="width: $1px;" >', $Text);
 248
 249         // Images
 250         // [img]pathtoimage[/img]
 251         $Text = preg_replace("/\[img\](.*?)\[\/img\]/ism", '<img src="$1" alt="' . t('Image/photo') . '" />', $Text);
 252
 253
 254         // Try to Oembed
 255         if ($tryoembed) {
 256                 $Text = preg_replace("/\[video\](.*?\.(ogg|ogv|oga|ogm|webm|mp4))\[\/video\]/ism", '<video src="$1" controls="controls" width="425" height="350"><a href="$1">$1</a></video>', $Text);
 257                 $Text = preg_replace("/\[audio\](.*?\.(ogg|ogv|oga|ogm|webm|mp4|mp3))\[\/audio\]/ism", '<audio src="$1" controls="controls"><a href="$1">$1</a></audio>', $Text);
 258
 259                 $Text = preg_replace_callback("/\[video\](.*?)\[\/video\]/ism", 'tryoembed', $Text);
 260                 $Text = preg_replace_callback("/\[audio\](.*?)\[\/audio\]/ism", 'tryoembed', $Text);
 261         } else {
 262                 $Text = preg_replace("/\[video\](.*?)\[\/video\]/", '$1', $Text);
 263                 $Text = preg_replace("/\[audio\](.*?)\[\/audio\]/", '$1', $Text);
 264         }
 265
 266         // html5 video and audio
 267
 268
 269         if ($tryoembed)
 270                 $Text = preg_replace("/\[iframe\](.*?)\[\/iframe\]/ism", '<iframe src="$1" width="425" height="350"><a href="$1">$1</a></iframe>', $Text);
 271         else
 272                 $Text = preg_replace("/\[iframe\](.*?)\[\/iframe\]/ism", '<a href="$1">$1</a>', $Text);
 273
 274         // Youtube extensions
 275         if ($tryoembed) {
 276                 $Text = preg_replace_callback("/\[youtube\](https?:\/\/www.youtube.com\/watch\?v\=.*?)\[\/youtube\]/ism", 'tryoembed', $Text);
 277                 $Text = preg_replace_callback("/\[youtube\](www.youtube.com\/watch\?v\=.*?)\[\/youtube\]/ism", 'tryoembed', $Text);
 278                 $Text = preg_replace_callback("/\[youtube\](https?:\/\/youtu.be\/.*?)\[\/youtube\]/ism",'tryoembed',$Text);
 279         }
 280
 281         $Text = preg_replace("/\[youtube\]https?:\/\/www.youtube.com\/watch\?v\=(.*?)\[\/youtube\]/ism",'[youtube]$1[/youtube]',$Text);
 282         $Text = preg_replace("/\[youtube\]https?:\/\/www.youtube.com\/embed\/(.*?)\[\/youtube\]/ism",'[youtube]$1[/youtube]',$Text);
 283         $Text = preg_replace("/\[youtube\]https?:\/\/youtu.be\/(.*?)\[\/youtube\]/ism",'[youtube]$1[/youtube]',$Text);
 284
 285         if ($tryoembed)
 286                 $Text = preg_replace("/\[youtube\]([A-Za-z0-9\-_=]+)(.*?)\[\/youtube\]/ism", '<iframe width="425" height="350" src="http://www.youtube.com/embed/$1" frameborder="0" ></iframe>', $Text);
 287         else
 288                 $Text = preg_replace("/\[youtube\]([A-Za-z0-9\-_=]+)(.*?)\[\/youtube\]/ism", "http://www.youtube.com/watch?v=$1", $Text);
 289
 290
 291         if ($tryoembed) {
 292                 $Text = preg_replace_callback("/\[vimeo\](https?:\/\/player.vimeo.com\/video\/[0-9]+).*?\[\/vimeo\]/ism",'tryoembed',$Text);
 293                 $Text = preg_replace_callback("/\[vimeo\](https?:\/\/vimeo.com\/[0-9]+).*?\[\/vimeo\]/ism",'tryoembed',$Text);
 294         }
 295
 296         $Text = preg_replace("/\[vimeo\]https?:\/\/player.vimeo.com\/video\/([0-9]+)(.*?)\[\/vimeo\]/ism",'[vimeo]$1[/vimeo]',$Text);
 297         $Text = preg_replace("/\[vimeo\]https?:\/\/vimeo.com\/([0-9]+)(.*?)\[\/vimeo\]/ism",'[vimeo]$1[/vimeo]',$Text);
 298
 299         if ($tryoembed)
 300                 $Text = preg_replace("/\[vimeo\]([0-9]+)(.*?)\[\/vimeo\]/ism", '<iframe width="425" height="350" src="http://player.vimeo.com/video/$1" frameborder="0" ></iframe>', $Text);
 301         else
 302                 $Text = preg_replace("/\[vimeo\]([0-9]+)(.*?)\[\/vimeo\]/ism", "http://vimeo.com/$1", $Text);
 303
 304 //      $Text = preg_replace("/\[youtube\](.*?)\[\/youtube\]/", '<object width="425" height="350" type="application/x-shockwave-flash" data="http://www.youtube.com/v/$1" ><param name="movie" value="http://www.youtube.com/v/$1"></param><!--[if IE]><embed src="http://www.youtube.com/v/$1" type="application/x-shockwave-flash" width="425" height="350" /><![endif]--></object>', $Text);
 305
 306
 307         // oembed tag
 308         $Text = oembed_bbcode2html($Text);
 309
 310         // If we found an event earlier, strip out all the event code and replace with a reformatted version.
 311         // Replace the event-start section with the entire formatted event. The other bbcode is stripped.
 312         // Summary (e.g. title) is required, earlier revisions only required description (in addition to
 313         // start which is always required). Allow desc with a missing summary for compatibility.
 314
 315         if((x($ev,'desc') || x($ev,'summary')) && x($ev,'start')) {
 316                 $sub = format_event_html($ev);
 317
 318                 $Text = preg_replace("/\[event\-summary\](.*?)\[\/event\-summary\]/ism",'',$Text);
 319                 $Text = preg_replace("/\[event\-description\](.*?)\[\/event\-description\]/ism",'',$Text);
 320                 $Text = preg_replace("/\[event\-start\](.*?)\[\/event\-start\]/ism",$sub,$Text);
 321                 $Text = preg_replace("/\[event\-finish\](.*?)\[\/event\-finish\]/ism",'',$Text);
 322                 $Text = preg_replace("/\[event\-location\](.*?)\[\/event\-location\]/ism",'',$Text);
 323                 $Text = preg_replace("/\[event\-adjust\](.*?)\[\/event\-adjust\]/ism",'',$Text);
 324         }
 325
 326         // Unhide all [noparse] contained bbtags unspacefying them
 327         // and triming the [noparse] tag.
 328
 329         $Text = preg_replace_callback("/\[noparse\](.*?)\[\/noparse\]/ism", 'bb_unspacefy_and_trim',$Text);
 330         $Text = preg_replace_callback("/\[nobb\](.*?)\[\/nobb\]/ism", 'bb_unspacefy_and_trim',$Text);
 331         $Text = preg_replace_callback("/\[pre\](.*?)\[\/pre\]/ism", 'bb_unspacefy_and_trim',$Text);
 332
 333
 334         $Text = preg_replace('/\[\&amp\;([#a-z0-9]+)\;\]/','&$1;',$Text);
 335
 336         // fix any escaped ampersands that may have been converted into links
 337         $Text = preg_replace("/\<(.*?)(src|href)=(.*?)\&amp\;(.*?)\>/ism",'<$1$2=$3&$4>',$Text);
 338         if(strlen($saved_image))
 339                 $Text = str_replace('[$#saved_image#$]','<img src="' . $saved_image .'" alt="' . t('Image/photo') . '" />',$Text);
 340
 341         // Clean up the HTML by loading and saving the HTML with the DOM
 342         // Only do it when it has to be done - for performance reasons
 343         if (!$tryoembed) {
 344                 $doc = new DOMDocument();
 345                 $doc->preserveWhiteSpace = false;
 346
 347                 $Text = mb_convert_encoding($Text, 'HTML-ENTITIES', "UTF-8");
 348
 349                 $doctype = '<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">';
 350                 @$doc->loadHTML($doctype."<html><body>".$Text."</body></html>");
 351
 352                 $Text = $doc->saveHTML();
 353                 $Text = str_replace(array("<html><body>", "</body></html>", $doctype), array("", "", ""), $Text);
 354
 355                 $Text = str_replace('<br></li>','</li>', $Text);
 356
 357                 $Text = mb_convert_encoding($Text, "UTF-8", 'HTML-ENTITIES');
 358         }
 359
 360         call_hooks('bbcode',$Text);
 361
 362         return $Text;
 363 }
 364