'; - //$headline = '

'; - - if ($avatar != "") - $headline .= '

'; - - $headline .= sprintf(t('%s wrote the following post'.$reldate.':'), $profile, $author, $link); - - $headline .= "

"; - - $text = $headline.'

'.trim($match[2])."

"; - - return($text); -} - -function bb_ShareAttributesSimple($match) { - - $attributes = $match[1]; - - $author = ""; - preg_match("/author='(.*?)'/ism", $attributes, $matches); - if ($matches[1] != "") - $author = html_entity_decode($matches[1],ENT_QUOTES,'UTF-8'); - - preg_match('/author="(.*?)"/ism', $attributes, $matches); - if ($matches[1] != "") - $author = $matches[1]; - - $profile = ""; - preg_match("/profile='(.*?)'/ism", $attributes, $matches); - if ($matches[1] != "") - $profile = $matches[1]; - - preg_match('/profile="(.*?)"/ism', $attributes, $matches); - if ($matches[1] != "") - $profile = $matches[1]; - - $userid = GetProfileUsername($profile,$author); - - $text = "
".html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').' '.$userid.":
Â»".$match[2]."Â«"; - - return($text); + $userid = GetProfileUsername($profile,$author, false); + $userid_compact = GetProfileUsername($profile,$author, true); + + $preshare = trim($share[1]); + + if ($preshare != "") + $preshare .= "

"; + + switch ($simplehtml) { + case 1: + $text = $preshare.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').' '.$userid.":
Â»".$share[3]."Â«"; + break; + case 2: + $text = $preshare.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').' '.$userid_compact.":
".$share[3]; + break; + case 3: // Diaspora + $headline = '

'; + $headline .= ''.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').$userid.':'; + $headline .= "

"; + + $text = trim($share[1]); + + if ($text != "") + $text .= "

"; + + $text .= $headline.'

'.trim($share[3])."

"; + + if ($link != "") + $text .= '
[l]'; + break; + case 4: + $headline = '

'; + $headline .= ''.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8'); + $headline .= sprintf(t('%2$s %3$s'), $link, $userid, $posted); + $headline .= ":

"; + + $text = trim($share[1]); + + if ($text != "") + $text .= "

"; + + $text .= $headline.'

'.trim($share[3])."

"; + + break; + case 5: + $text = $preshare.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').' '.$userid_compact.":
".$share[3]; + break; + case 6: // app.net + $text = $preshare.">> @".$userid_compact.":
".$share[3]; + break; + case 7: // statusnet/GNU Social + $text = $preshare.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8')." @".$userid_compact.": ".$share[3]; + break; + case 8: // twitter + $text = $preshare."RT @".$userid_compact.": ".$share[3]; + break; + case 9: // Google+/Facebook + $text = $preshare.html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').' '.$userid_compact.":
".$share[3]; + + if ($link != "") + $text .= "

".$link; + break; + default: + $headline = trim($share[1]).'

'; + if ($avatar != "") + $headline .= '

'; + + $headline .= sprintf(t('%s wrote the following post'.$reldate.':'), $profile, $author, $link); + $headline .= "

"; + $text = $headline.'

'.trim($share[3])."

"; + break; + } + return($text); } -function bb_ShareAttributesSimple2($match) { - - $attributes = $match[1]; - - $author = ""; - preg_match("/author='(.*?)'/ism", $attributes, $matches); - if ($matches[1] != "") - $author = html_entity_decode($matches[1],ENT_QUOTES,'UTF-8'); - - preg_match('/author="(.*?)"/ism', $attributes, $matches); - if ($matches[1] != "") - $author = $matches[1]; - $profile = ""; - preg_match("/profile='(.*?)'/ism", $attributes, $matches); - if ($matches[1] != "") - $profile = $matches[1]; +function GetProfileUsername($profile, $username, $compact = false, $getnetwork = false) { - preg_match('/profile="(.*?)"/ism', $attributes, $matches); - if ($matches[1] != "") - $profile = $matches[1]; - - $userid = GetProfileUsername($profile,$author); + $twitter = preg_replace("=https?://twitter.com/(.*)=ism", "$1@twitter.com", $profile); + if ($twitter != $profile) { + if ($getnetwork) + return(NETWORK_TWITTER); + elseif ($compact) + return($twitter); + else + return($username." (".$twitter.")"); + } - $text = "
".html_entity_decode("♲ ", ENT_QUOTES, 'UTF-8').' '.$userid.":
".$match[2]; + $appnet = preg_replace("=https?://alpha.app.net/(.*)=ism", "$1@alpha.app.net", $profile); + if ($appnet != $profile) { + if ($getnetwork) + return(NETWORK_APPNET); + elseif ($compact) + return($appnet); + else + return($username." (".$appnet.")"); + } - return($text); -} + $gplus = preg_replace("=https?://plus.google.com/(.*)=ism", "$1@plus.google.com", $profile); + if ($gplus != $profile) { + if ($getnetwork) + return(NETWORK_GPLUS); + elseif ($compact) + return($gplususername." (".$username.")"); + else + return($username." (".$gplus.")"); + } -function GetProfileUsername($profile, $username) { $friendica = preg_replace("=https?://(.*)/profile/(.*)=ism", "$2@$1", $profile); - if ($friendica != $profile) - return($friendica." (".$username.")"); + if ($friendica != $profile) { + if ($getnetwork) + return(NETWORK_DFRN); + elseif ($compact) + return($friendica); + else + return($username." (".$friendica.")"); + } $diaspora = preg_replace("=https?://(.*)/u/(.*)=ism", "$2@$1", $profile); - if ($diaspora != $profile) - return($diaspora." (".$username.")"); - - $twitter = preg_replace("=https?://twitter.com/(.*)=ism", "$1@twitter.com", $profile); - if ($twitter != $profile) - return($twitter." (".$username.")"); + if ($diaspora != $profile) { + if ($getnetwork) + return(NETWORK_DIASPORA); + elseif ($compact) + return($diaspora); + else + return($username." (".$diaspora.")"); + } $StatusnetHost = preg_replace("=https?://(.*)/user/(.*)=ism", "$1", $profile); if ($StatusnetHost != $profile) { @@ -367,18 +642,133 @@ function GetProfileUsername($profile, $username) { if ($StatusnetUser != $profile) { $UserData = fetch_url("http://".$StatusnetHost."/api/users/show.json?user_id=".$StatusnetUser); $user = json_decode($UserData); - if ($user) - return($user->screen_name."@".$StatusnetHost." (".$username.")"); + if ($user) { + if ($getnetwork) + return(NETWORK_STATUSNET); + elseif ($compact) + return($user->screen_name."@".$StatusnetHost); + else + return($username." (".$user->screen_name."@".$StatusnetHost.")"); + } + } + } + + // pumpio (http://host.name/user) + $rest = preg_replace("=https?://([\.\w]+)/([\.\w]+)(.*)=ism", "$3", $profile); + if ($rest == "") { + $pumpio = preg_replace("=https?://([\.\w]+)/([\.\w]+)(.*)=ism", "$2@$1", $profile); + if ($pumpio != $profile) { + if ($getnetwork) + return(NETWORK_PUMPIO); + elseif ($compact) + return($pumpio); + else + return($username." (".$pumpio.")"); } } return($username); } +function bb_RemovePictureLinks($match) { + $text = Cache::get($match[1]); + + if(is_null($text)){ + $ch = @curl_init($match[1]); + @curl_setopt($ch, CURLOPT_NOBODY, true); + @curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); + @curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (compatible; ".FRIENDICA_PLATFORM." ".FRIENDICA_VERSION."-".DB_UPDATE_VERSION.")"); + @curl_exec($ch); + $curl_info = @curl_getinfo($ch); + + if (substr($curl_info["content_type"], 0, 6) == "image/") + $text = "[url=".$match[1]."]".$match[1]."[/url]"; + else { + $text = "[url=".$match[2]."]".$match[2]."[/url]"; + + // if its not a picture then look if its a page that contains a picture link + require_once("include/network.php"); + + $body = fetch_url($match[1]); + + $doc = new DOMDocument(); + @$doc->loadHTML($body); + $xpath = new DomXPath($doc); + $list = $xpath->query("//meta[@name]"); + foreach ($list as $node) { + $attr = array(); + + if ($node->attributes->length) + foreach ($node->attributes as $attribute) + $attr[$attribute->name] = $attribute->value; + + if (strtolower($attr["name"]) == "twitter:image") + $text = "[url=".$attr["content"]."]".$attr["content"]."[/url]"; + } + } + Cache::set($match[1],$text); + } + return($text); +} + +function bb_expand_links($match) { + if (stristr($match[2], $match[3]) OR ($match[2] == $match[3])) + return ($match[1]."[url]".$match[2]."[/url]"); + else + return ($match[1].$match[3]." [url]".$match[2]."[/url]"); +} + +function bb_CleanPictureLinksSub($match) { + $text = Cache::get($match[1]); + + if(is_null($text)){ + $ch = @curl_init($match[1]); + @curl_setopt($ch, CURLOPT_NOBODY, true); + @curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); + @curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (compatible; ".FRIENDICA_PLATFORM." ".FRIENDICA_VERSION."-".DB_UPDATE_VERSION.")"); + @curl_exec($ch); + $curl_info = @curl_getinfo($ch); + + // if its a link to a picture then embed this picture + if (substr($curl_info["content_type"], 0, 6) == "image/") + $text = "[img]".$match[1]."[/img]"; + else { + $text = "[img]".$match[2]."[/img]"; + + // if its not a picture then look if its a page that contains a picture link + require_once("include/network.php"); + + $body = fetch_url($match[1]); + + $doc = new DOMDocument(); + @$doc->loadHTML($body); + $xpath = new DomXPath($doc); + $list = $xpath->query("//meta[@name]"); + foreach ($list as $node) { + $attr = array(); + + if ($node->attributes->length) + foreach ($node->attributes as $attribute) + $attr[$attribute->name] = $attribute->value; + + if (strtolower($attr["name"]) == "twitter:image") + $text = "[img]".$attr["content"]."[/img]"; + } + } + Cache::set($match[1],$text); + } + return($text); +} + +function bb_CleanPictureLinks($text) { + $text = preg_replace_callback("&\[url=([^\[\]]*)\]\[img\](.*)\[\/img\]\[\/url\]&Usi", 'bb_CleanPictureLinksSub', $text); + return ($text); +} + // BBcode 2 HTML was written by WAY2WEB.net // extended to work with Mistpark/Friendica - Mike Macgirvin -function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = false) { +function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = false, $forplaintext = false) { $stamp1 = microtime(true); @@ -396,7 +786,7 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace("/\[(\w*)\](\s*)/ism", '$2[$1]', $Text); $Text = preg_replace("/(\s*)\[\/(\w*)\]/ism", '[/$2]$1', $Text); - // Extract the private images which use data url's since preg has issues with + // Extract the private images which use data urls since preg has issues with // large data sizes. Stash them away while we do bbcode conversion, and then put them back // in after we've done all the regex matching. We cannot use any preg functions to do this. @@ -424,6 +814,16 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace("/\n\[code\]/ism", "[code]", $Text); $Text = preg_replace("/\[\/code\]\n/ism", "[/code]", $Text); + // Rearrange shares to attachments + $Text = preg_replace_callback("((.*?)\[class=(.*?)\](.*?)\[\/class\])ism", "bb_rearrange_share",$Text); + + // Handle attached links or videos + $Text = bb_attachment($Text, ($simplehtml != 4) AND ($simplehtml != 0), $tryoembed); + + // Rearrange shared links +// if (get_config("system", "rearrange_shared_links") AND (!$simplehtml OR $tryoembed)) +// $Text = preg_replace_callback("(\[class=(.*?)\](.*?)\[\/class\])ism","bb_rearrange_link",$Text); + // when the content is meant exporting to other systems then remove the avatar picture since this doesn't really look good on these systems if (!$tryoembed) $Text = preg_replace("/\[share(.*?)avatar\s?=\s?'.*?'\s?(.*?)\]\s?(.*?)\s?\[\/share\]\s?/ism","\n[share$1$2]$3[/share]",$Text); @@ -440,8 +840,8 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal // removing multiplicated newlines if (get_config("system", "remove_multiplicated_lines")) { - $search = array("\n\n\n", "\n ", " \n", "[/quote]\n\n", "\n[/quote]", "[/li]\n", "\n[li]", "\n[ul]", "[/ul]\n"); - $replace = array("\n\n", "\n", "\n", "[/quote]\n", "[/quote]", "[/li]", "[li]", "[ul]", "[/ul]"); + $search = array("\n\n\n", "\n ", " \n", "[/quote]\n\n", "\n[/quote]", "[/li]\n", "\n[li]", "\n[ul]", "[/ul]\n", "\n\n[share "); + $replace = array("\n\n", "\n", "\n", "[/quote]\n", "[/quote]", "[/li]", "[li]", "[ul]", "[/ul]", "\n[share "); do { $oldtext = $Text; $Text = str_replace($search, $replace, $Text); @@ -460,25 +860,51 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal // Set up the parameters for a MAIL search string $MAILSearchString = $URLSearchString; + // Remove all hashtag addresses + if (!$tryoembed OR $simplehtml) + $Text = preg_replace("/([#@])\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '$1$3', $Text); + + // Bookmarks in red - will be converted to bookmarks in friendica + $Text = preg_replace("/#\^\[url\]([$URLSearchString]*)\[\/url\]/ism", '[bookmark=$1]$1[/bookmark]', $Text); + $Text = preg_replace("/#\^\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '[bookmark=$1]$2[/bookmark]', $Text); + $Text = preg_replace("/#\[url\=[$URLSearchString]*\]\^\[\/url\]\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/i", + "[bookmark=$1]$2[/bookmark]", $Text); + + if (in_array($simplehtml, array(2, 6, 7, 8, 9))) { + $Text = preg_replace_callback("/([^#@])\[url\=([^\]]*)\](.*?)\[\/url\]/ism","bb_expand_links",$Text); + //$Text = preg_replace("/[^#@]\[url\=([^\]]*)\](.*?)\[\/url\]/ism",' $2 [url]$1[/url]',$Text); + $Text = preg_replace("/\[bookmark\=([^\]]*)\](.*?)\[\/bookmark\]/ism",' $2 [url]$1[/url]',$Text); + } - // Perform URL Search - - $Text = preg_replace("/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism", '$1$2', $Text); + if ($simplehtml == 5) + $Text = preg_replace("/[^#@]\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '[url]$1[/url]', $Text); + // Perform URL Search if ($tryoembed) - $Text = preg_replace_callback("/\[bookmark\=([^\]]*)\].*?\[\/bookmark\]/ism",'tryoembed',$Text); + $Text = preg_replace_callback("/\[bookmark\=([^\]]*)\](.*?)\[\/bookmark\]/ism",'tryoembed',$Text); - $Text = preg_replace("/\[bookmark\=([^\]]*)\](.*?)\[\/bookmark\]/ism",'[url=$1]$2[/url]',$Text); + if ($simplehtml == 5) + $Text = preg_replace("/\[bookmark\=([^\]]*)\](.*?)\[\/bookmark\]/ism",'[url]$1[/url]',$Text); + else + $Text = preg_replace("/\[bookmark\=([^\]]*)\](.*?)\[\/bookmark\]/ism",'[url=$1]$2[/url]',$Text); + + // if the HTML is used to generate plain text, then don't do this search, but replace all URL of that kind to text + if (!$forplaintext) + $Text = preg_replace("/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism", '$1$2', $Text); + else { + $Text = preg_replace("(\[url\]([$URLSearchString]*)\[\/url\])ism"," $1 ",$Text); + $Text = preg_replace_callback("&\[url=([^\[\]]*)\]\[img\](.*)\[\/img\]\[\/url\]&Usi", 'bb_RemovePictureLinks', $Text); + } if ($tryoembed) $Text = preg_replace_callback("/\[url\]([$URLSearchString]*)\[\/url\]/ism",'tryoembed',$Text); - $Text = preg_replace("/\[url\]([$URLSearchString]*)\[\/url\]/ism", '$1', $Text); - $Text = preg_replace("/\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '$2', $Text); + $Text = preg_replace("/\[url\]([$URLSearchString]*)\[\/url\]/ism", '$1', $Text); + $Text = preg_replace("/\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '$2', $Text); //$Text = preg_replace("/\[url\=([$URLSearchString]*)\]([$URLSearchString]*)\[\/url\]/ism", '$2', $Text); // Red compatibility, though the link can't be authenticated on Friendica - $Text = preg_replace("/\[zrl\=([$URLSearchString]*)\](.*?)\[\/zrl\]/ism", '$2', $Text); + $Text = preg_replace("/\[zrl\=([$URLSearchString]*)\](.*?)\[\/zrl\]/ism", '$2', $Text); // we may need to restrict this further if it picks up too many strays @@ -510,9 +936,9 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace("(\[color=(.*?)\](.*?)\[\/color\])ism","$2",$Text); // Check for sized text - // [size=50] --> font-size: 50px (with the unit). - $Text = preg_replace("(\[size=(\d*?)\](.*?)\[\/size\])ism","$2",$Text); - $Text = preg_replace("(\[size=(.*?)\](.*?)\[\/size\])ism","$2",$Text); + // [size=50] --> font-size: 50px (with the unit). + $Text = preg_replace("(\[size=(\d*?)\](.*?)\[\/size\])ism","$2",$Text); + $Text = preg_replace("(\[size=(.*?)\](.*?)\[\/size\])ism","$2",$Text); // Check for centered text $Text = preg_replace("(\[center\](.*?)\[\/center\])ism","

",$Text); @@ -526,7 +952,7 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal // Check for CSS classes $Text = preg_replace_callback("(\[class=(.*?)\](.*?)\[\/class\])ism","bb_cleanclass",$Text); - // handle nested lists + // handle nested lists $endlessloop = 0; while ((((strpos($Text, "[/list]") !== false) && (strpos($Text, "[list") !== false)) || @@ -587,8 +1013,8 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $endlessloop = 0; while ((strpos($Text, "[/spoiler]")!== false) and (strpos($Text, "[spoiler=") !== false) and (++$endlessloop < 20)) $Text = preg_replace("/\[spoiler=[\"\']*(.*?)[\"\']*\](.*?)\[\/spoiler\]/ism", - "
" . $t_wrote . "

$2

", - $Text); + "
" . $t_wrote . "

$2

", + $Text); // Declare the format for [quote] layout $QuoteLayout = '

$1

'; @@ -607,8 +1033,8 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $endlessloop = 0; while ((strpos($Text, "[/quote]")!== false) and (strpos($Text, "[quote=") !== false) and (++$endlessloop < 20)) $Text = preg_replace("/\[quote=[\"\']*(.*?)[\"\']*\](.*?)\[\/quote\]/ism", - "
" . $t_wrote . "

$2

", - $Text); + "
" . $t_wrote . "

$2

", + $Text); // [img=widthxheight]image source[/img] //$Text = preg_replace("/\[img\=([0-9]*)x([0-9]*)\](.*?)\[\/img\]/ism", '

', $Text); @@ -621,12 +1047,10 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace("/\[zmg\](.*?)\[\/zmg\]/ism", ' ' . t('Image/photo') . '

', $Text); // Shared content - if (!$simplehtml) - $Text = preg_replace_callback("/\[share(.*?)\](.*?)\[\/share\]/ism","bb_ShareAttributes",$Text); - elseif ($simplehtml == 1) - $Text = preg_replace_callback("/\[share(.*?)\](.*?)\[\/share\]/ism","bb_ShareAttributesSimple",$Text); - elseif ($simplehtml == 2) - $Text = preg_replace_callback("/\[share(.*?)\](.*?)\[\/share\]/ism","bb_ShareAttributesSimple2",$Text); + $Text = preg_replace_callback("/(.*?)\[share(.*?)\](.*?)\[\/share\]/ism", + function ($match) use ($simplehtml){ + return(bb_ShareAttributes($match, $simplehtml)); + },$Text); $Text = preg_replace("/\[crypt\](.*?)\[\/crypt\]/ism",'
' . t('Encrypted content') . '

', $Text); $Text = preg_replace("/\[crypt(.*?)\](.*?)\[\/crypt\]/ism",'
' . t('Encrypted content') . '

', $Text); @@ -642,9 +1066,9 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace_callback("/\[audio\](.*?)\[\/audio\]/ism", 'tryoembed', $Text); } else { $Text = preg_replace("/\[video\](.*?)\[\/video\]/", - '$1', $Text); + '$1', $Text); $Text = preg_replace("/\[audio\](.*?)\[\/audio\]/", - '$1', $Text); + '$1', $Text); } // html5 video and audio @@ -670,7 +1094,7 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace("/\[youtube\]([A-Za-z0-9\-_=]+)(.*?)\[\/youtube\]/ism", '', $Text); else $Text = preg_replace("/\[youtube\]([A-Za-z0-9\-_=]+)(.*?)\[\/youtube\]/ism", - 'https://www.youtube.com/watch?v=$1', $Text); + 'https://www.youtube.com/watch?v=$1', $Text); if ($tryoembed) { $Text = preg_replace_callback("/\[vimeo\](https?:\/\/player.vimeo.com\/video\/[0-9]+).*?\[\/vimeo\]/ism",'tryoembed',$Text); @@ -684,7 +1108,7 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal $Text = preg_replace("/\[vimeo\]([0-9]+)(.*?)\[\/vimeo\]/ism", '', $Text); else $Text = preg_replace("/\[vimeo\]([0-9]+)(.*?)\[\/vimeo\]/ism", - 'https://vimeo.com/$1', $Text); + 'https://vimeo.com/$1', $Text); // $Text = preg_replace("/\[youtube\](.*?)\[\/youtube\]/", '

', $Text); @@ -730,25 +1154,26 @@ function bbcode($Text,$preserve_nl = false, $tryoembed = true, $simplehtml = fal if($saved_image) $Text = bb_replace_images($Text, $saved_image); - // Clean up the HTML by loading and saving the HTML with the DOM - // Only do it when it has to be done - for performance reasons - // Update: Now it is done every time - since bad structured html can break a whole page - //if (!$tryoembed) { - // $doc = new DOMDocument(); - // $doc->preserveWhiteSpace = false; - - // $Text = mb_convert_encoding($Text, 'HTML-ENTITIES', "UTF-8"); + // Clean up the HTML by loading and saving the HTML with the DOM. + // Bad structured html can break a whole page. + // For performance reasons do it only with ativated item cache or at export. + if (!$tryoembed OR (get_itemcachepath() != "")) { + $doc = new DOMDocument(); + $doc->preserveWhiteSpace = false; - // $doctype = ''; - // @$doc->loadHTML($doctype."".$Text.""); + $Text = mb_convert_encoding($Text, 'HTML-ENTITIES', "UTF-8"); - // $Text = $doc->saveHTML(); - // $Text = str_replace(array("", "", $doctype), array("", "", ""), $Text); + $doctype = ''; + $encoding = ''; + @$doc->loadHTML($encoding.$doctype."".$Text.""); + $doc->encoding = 'UTF-8'; + $Text = $doc->saveHTML(); + $Text = str_replace(array("", "", $doctype, $encoding), array("", "", "", ""), $Text); - // $Text = str_replace('
','', $Text); + $Text = str_replace('
','', $Text); - // $Text = mb_convert_encoding($Text, "UTF-8", 'HTML-ENTITIES'); - //} + //$Text = mb_convert_encoding($Text, "UTF-8", 'HTML-ENTITIES'); + } // Clean up some useless linebreaks in lists //$Text = str_replace('
save_timestamp($stamp1, "parser"); return $Text; } +?>