]> git.mxchange.org Git - friendica.git/blobdiff - include/bbcode.php
The url detection in BBCode is too greedy
[friendica.git] / include / bbcode.php
index fed535db573b8c52609b3d7c0a756703555653ce..cad7ddc9251df74ca149e7713efcf341c5d541f2 100644 (file)
@@ -3,6 +3,7 @@
 use Friendica\App;
 use Friendica\Content\Smilies;
 use Friendica\Content\OEmbed;
+use Friendica\Core\Addon;
 use Friendica\Core\Cache;
 use Friendica\Core\System;
 use Friendica\Core\Config;
@@ -46,21 +47,21 @@ function bb_map_location($match) {
  * Note: Can produce a [bookmark] tag in the returned string
  *
  * @brief Processes [attachment] tags
- * @param string $Text
+ * @param string $return
  * @param bool|int $simplehtml
  * @param bool $tryoembed
  * @return string
  */
-function bb_attachment($Text, $simplehtml = false, $tryoembed = true)
+function bb_attachment($return, $simplehtml = false, $tryoembed = true)
 {
-       $data = get_attachment_data($Text);
+       $data = get_attachment_data($return);
        if (!$data) {
-               return $Text;
+               return $return;
        }
 
        if (isset($data["title"])) {
                $data["title"] = strip_tags($data["title"]);
-               $data["title"] = str_replace(array("http://", "https://"), "", $data["title"]);
+               $data["title"] = str_replace(["http://", "https://"], "", $data["title"]);
        }
 
        if (((strpos($data["text"], "[img=") !== false) || (strpos($data["text"], "[img]") !== false) || Config::get('system', 'always_show_preview')) && ($data["image"] != "")) {
@@ -68,49 +69,50 @@ function bb_attachment($Text, $simplehtml = false, $tryoembed = true)
                $data["image"] = "";
        }
 
+       $return = '';
        if ($simplehtml == 7) {
-               $text = style_url_for_mastodon($data["url"]);
+               $return = style_url_for_mastodon($data["url"]);
        } elseif (($simplehtml != 4) && ($simplehtml != 0)) {
-               $text = sprintf('<a href="%s" target="_blank">%s</a><br>', $data["url"], $data["title"]);
+               $return = sprintf('<a href="%s" target="_blank">%s</a><br>', $data["url"], $data["title"]);
        } else {
-               if ($simplehtml != 4) {
-                       $text = sprintf('<span class="type-%s">', $data["type"]);
-               }
-
-               $oembed = sprintf('[bookmark=%s]%s[/bookmark]', $data['url'], $data['title']);
-               if ($tryoembed) {
-                       try {
-                               $oembed = OEmbed::getHTML($data['url'], $data['title']);
-                       } catch (Exception $e) {
-                               // $oembed isn't modified
+               try {
+                       if ($tryoembed && OEmbed::isAllowedURL($data['url'])) {
+                               $return = OEmbed::getHTML($data['url'], $data['title']);
+                       } else {
+                               throw new Exception('OEmbed is disabled for this attachment.');
+                       }
+               } catch (Exception $e) {
+                       if ($simplehtml != 4) {
+                               $return = sprintf('<div class="type-%s">', $data["type"]);
                        }
-               }
 
-               if (stripos($oembed, "<iframe ") !== false) {
-                       $text = $oembed;
-               } else {
-                       if (($data["image"] != "") && !strstr(strtolower($oembed), "<img ")) {
-                               $text .= sprintf('<a href="%s" target="_blank"><img src="%s" alt="" title="%s" class="attachment-image" /></a><br />', $data["url"], proxy_url($data["image"]), $data["title"]);
-                       } elseif (($data["preview"] != "") && !strstr(strtolower($oembed), "<img ")) {
-                               $text .= sprintf('<a href="%s" target="_blank"><img src="%s" alt="" title="%s" class="attachment-preview" /></a><br />', $data["url"], proxy_url($data["preview"]), $data["title"]);
+                       if ($data["image"] != "") {
+                               $return .= sprintf('<a href="%s" target="_blank"><img src="%s" alt="" title="%s" class="attachment-image" /></a><br />', $data["url"], proxy_url($data["image"]), $data["title"]);
+                       } elseif ($data["preview"] != "") {
+                               $return .= sprintf('<a href="%s" target="_blank"><img src="%s" alt="" title="%s" class="attachment-preview" /></a><br />', $data["url"], proxy_url($data["preview"]), $data["title"]);
                        }
 
                        if (($data["type"] == "photo") && ($data["url"] != "") && ($data["image"] != "")) {
-                               $text .= sprintf('<a href="%s" target="_blank"><img src="%s" alt="" title="%s" class="attachment-image" /></a>', $data["url"], proxy_url($data["image"]), $data["title"]);
+                               $return .= sprintf('<a href="%s" target="_blank"><img src="%s" alt="" title="%s" class="attachment-image" /></a>', $data["url"], proxy_url($data["image"]), $data["title"]);
                        } else {
-                               $text .= $oembed;
+                               $return .= sprintf('<h4><a href="%s">%s</a></h4>', $data['url'], $data['title']);
                        }
 
-                       if (trim($data["description"]) != "") {
-                               $text .= sprintf('<blockquote>%s</blockquote>', trim(bbcode($data["description"])));
+                       if ($data["description"] != "" && $data["description"] != $data["title"]) {
+                               $return .= sprintf('<blockquote>%s</blockquote>', trim(bbcode($data["description"])));
                        }
-               }
 
-               if ($simplehtml != 4) {
-                       $text .= '</span>';
+                       if ($data["type"] == "link") {
+                               $return .= sprintf('<h5><a href="%s">%s</a></h5>', $data['url'], parse_url($data['url'], PHP_URL_HOST));
+                       }
+
+                       if ($simplehtml != 4) {
+                               $return .= '</div>';
+                       }
                }
        }
-       return trim($data["text"] . ' ' . $text . ' ' . $data["after"]);
+
+       return trim($data["text"] . ' ' . $return . ' ' . $data["after"]);
 }
 
 function bb_remove_share_information($Text, $plaintext = false, $nolink = false) {
@@ -279,7 +281,7 @@ function bb_find_open_close($s, $open, $close, $occurence = 1) {
                return false;
        }
 
-       $res = array( 'start' => $start_pos, 'end' => $end_pos );
+       $res = [ 'start' => $start_pos, 'end' => $end_pos ];
 
        return $res;
 }
@@ -315,16 +317,16 @@ function get_bb_tag_pos($s, $name, $occurence = 1) {
                return false;
        }
 
-       $res = array(
-               'start' => array(
+       $res = [
+               'start' => [
                        'open'  => $start_open,
                        'close' => $start_close
-               ),
-               'end'   => array(
+               ],
+               'end'   => [
                        'open'  => $end_open,
                        'close' => $end_open + strlen('[/' . $name . ']')
-               ),
-       );
+               ],
+       ];
 
        if ($start_equal !== false) {
                $res['start']['equal'] = $start_equal + 1;
@@ -359,7 +361,7 @@ function bb_tag_preg_replace($pattern, $replace, $name, $s) {
 
 function bb_extract_images($body) {
 
-       $saved_image = array();
+       $saved_image = [];
        $orig_body = $body;
        $new_body = '';
 
@@ -397,7 +399,7 @@ function bb_extract_images($body) {
 
        $new_body = $new_body . $orig_body;
 
-       return array('body' => $new_body, 'images' => $saved_image);
+       return ['body' => $new_body, 'images' => $saved_image];
 }
 
 function bb_replace_images($body, $images) {
@@ -594,14 +596,14 @@ function bb_ShareAttributes($share, $simplehtml)
                                $avatar = proxy_url($avatar, false, PROXY_SIZE_THUMB);
 
                                $tpl = get_markup_template('shared_content.tpl');
-                               $text .= replace_macros($tpl, array(
+                               $text .= replace_macros($tpl, [
                                        '$profile' => $profile,
                                        '$avatar' => $avatar,
                                        '$author' => $author,
                                        '$link' => $link,
                                        '$posted' => $posted,
                                        '$content' => trim($share[3])
-                               ));
+                               ]);
                        }
                        break;
        }
@@ -751,7 +753,7 @@ function bb_RemovePictureLinks($match) {
                        $xpath = new DomXPath($doc);
                        $list = $xpath->query("//meta[@name]");
                        foreach ($list as $node) {
-                               $attr = array();
+                               $attr = [];
 
                                if ($node->attributes->length)
                                        foreach ($node->attributes as $attribute)
@@ -808,7 +810,7 @@ function bb_CleanPictureLinksSub($match) {
                        $xpath = new DomXPath($doc);
                        $list = $xpath->query("//meta[@name]");
                        foreach ($list as $node) {
-                               $attr = array();
+                               $attr = [];
 
                                if ($node->attributes->length)
                                        foreach ($node->attributes as $attribute)
@@ -950,32 +952,48 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
 
        // removing multiplicated newlines
        if (Config::get("system", "remove_multiplicated_lines")) {
-               $search = array("\n\n\n", "\n ", " \n", "[/quote]\n\n", "\n[/quote]", "[/li]\n", "\n[li]", "\n[ul]", "[/ul]\n", "\n\n[share ", "[/attachment]\n",
-                               "\n[h1]", "[/h1]\n", "\n[h2]", "[/h2]\n", "\n[h3]", "[/h3]\n", "\n[h4]", "[/h4]\n", "\n[h5]", "[/h5]\n", "\n[h6]", "[/h6]\n");
-               $replace = array("\n\n", "\n", "\n", "[/quote]\n", "[/quote]", "[/li]", "[li]", "[ul]", "[/ul]", "\n[share ", "[/attachment]",
-                               "[h1]", "[/h1]", "[h2]", "[/h2]", "[h3]", "[/h3]", "[h4]", "[/h4]", "[h5]", "[/h5]", "[h6]", "[/h6]");
+               $search = ["\n\n\n", "\n ", " \n", "[/quote]\n\n", "\n[/quote]", "[/li]\n", "\n[li]", "\n[ul]", "[/ul]\n", "\n\n[share ", "[/attachment]\n",
+                               "\n[h1]", "[/h1]\n", "\n[h2]", "[/h2]\n", "\n[h3]", "[/h3]\n", "\n[h4]", "[/h4]\n", "\n[h5]", "[/h5]\n", "\n[h6]", "[/h6]\n"];
+               $replace = ["\n\n", "\n", "\n", "[/quote]\n", "[/quote]", "[/li]", "[li]", "[ul]", "[/ul]", "\n[share ", "[/attachment]",
+                               "[h1]", "[/h1]", "[h2]", "[/h2]", "[h3]", "[/h3]", "[h4]", "[/h4]", "[h5]", "[/h5]", "[h6]", "[/h6]"];
                do {
                        $oldtext = $Text;
                        $Text = str_replace($search, $replace, $Text);
                } while ($oldtext != $Text);
        }
 
+       // Set up the parameters for a URL search string
+       $URLSearchString = "^\[\]";
+       // Set up the parameters for a MAIL search string
+       $MAILSearchString = $URLSearchString;
+
+       // if the HTML is used to generate plain text, then don't do this search, but replace all URL of that kind to text
+       if (!$forplaintext) {
+               // Autolink feature (thanks to http://code.seebz.net/p/autolink-php/)
+               $autolink_regex = "`([^\]\=\"']|^)(https?\://[^\s<]+[^\s<\.\)])`ism";
+               $autolink_regex = "/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism";
+               $Text = preg_replace($autolink_regex, '$1[url]$2[/url]', $Text);
+               if ($simplehtml == 7) {
+                       $Text = preg_replace_callback("/\[url\]([$URLSearchString]*)\[\/url\]/ism", 'bb_style_url', $Text);
+                       $Text = preg_replace_callback("/\[url\=([$URLSearchString]*)\]([$URLSearchString]*)\[\/url\]/ism", 'bb_style_url', $Text);
+               }
+       } else {
+               $Text = preg_replace("(\[url\]([$URLSearchString]*)\[\/url\])ism", " $1 ", $Text);
+               $Text = preg_replace_callback("&\[url=([^\[\]]*)\]\[img\](.*)\[\/img\]\[\/url\]&Usi", 'bb_RemovePictureLinks', $Text);
+       }
+
+
        // Handle attached links or videos
        $Text = bb_attachment($Text, $simplehtml, $tryoembed);
 
-       $Text = str_replace(array("\r","\n"), array('<br />', '<br />'), $Text);
+       $Text = str_replace(["\r","\n"], ['<br />', '<br />'], $Text);
 
        if ($preserve_nl) {
-               $Text = str_replace(array("\n", "\r"), array('', ''), $Text);
+               $Text = str_replace(["\n", "\r"], ['', ''], $Text);
        }
 
-       // Set up the parameters for a URL search string
-       $URLSearchString = "^\[\]";
-       // Set up the parameters for a MAIL search string
-       $MAILSearchString = $URLSearchString;
-
        // Remove all hashtag addresses
-       if ((!$tryoembed || $simplehtml) && !in_array($simplehtml, array(3, 7))) {
+       if ((!$tryoembed || $simplehtml) && !in_array($simplehtml, [3, 7])) {
                $Text = preg_replace("/([#@!])\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", '$1$3', $Text);
        } elseif ($simplehtml == 3) {
                $Text = preg_replace("/([@!])\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism",
@@ -997,7 +1015,7 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
        $Text = preg_replace("/#\[url\=[$URLSearchString]*\]\^\[\/url\]\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/i",
                                "[bookmark=$1]$2[/bookmark]", $Text);
 
-       if (in_array($simplehtml, array(2, 6, 7, 8, 9))) {
+       if (in_array($simplehtml, [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);
@@ -1026,25 +1044,8 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
        $expression = "=diaspora://.*?/post/([0-9A-Za-z\-_@.:]{15,254}[0-9A-Za-z])=ism";
        $Text = preg_replace($expression, System::baseUrl()."/display/$1", $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 ($simplehtml != 7) {
-               if (!$forplaintext) {
-                       if ($simplehtml != 7) {
-                               $Text = preg_replace("/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism", '$1<a href="$2" target="_blank">$2</a>', $Text);
-                       } else {
-                               $Text = preg_replace("/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism", '$1[url]$2[/url]', $Text);
-
-                               $Text = preg_replace_callback("/\[url\]([$URLSearchString]*)\[\/url\]/ism", 'bb_style_url', $Text);
-                               $Text = preg_replace_callback("/\[url\=([$URLSearchString]*)\]([$URLSearchString]*)\[\/url\]/ism", 'bb_style_url', $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_callback, $Text);
+       //      $Text = preg_replace_callback("/\[url\]([$URLSearchString]*)\[\/url\]/ism", $tryoembed_callback, $Text);
        }
 
        $Text = preg_replace("/([#])\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism",
@@ -1240,7 +1241,7 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
 
        // Try to Oembed
        if ($tryoembed) {
-               $Text = preg_replace("/\[video\](.*?\.(ogg|ogv|oga|ogm|webm|mp4))\[\/video\]/ism", '<video src="$1" controls="controls" width="' . $a->videowidth . '" height="' . $a->videoheight . '"><a href="$1">$1</a></video>', $Text);
+               $Text = preg_replace("/\[video\](.*?\.(ogg|ogv|oga|ogm|webm|mp4))\[\/video\]/ism", '<video src="$1" controls="controls" width="' . $a->videowidth . '" height="' . $a->videoheight . '" loop="true"><a href="$1">$1</a></video>', $Text);
                $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);
 
                $Text = preg_replace_callback("/\[video\](.*?)\[\/video\]/ism", $tryoembed_callback, $Text);
@@ -1352,20 +1353,20 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
        $Text = preg_replace('/\<([^>]*?)(src|href)=(.*?)\&amp\;(.*?)\>/ism', '<$1$2=$3&$4>', $Text);
 
        // sanitizes src attributes (http and redir URLs for displaying in a web page, cid used for inline images in emails)
-       static $allowed_src_protocols = array('http', 'redir', 'cid');
+       static $allowed_src_protocols = ['http', 'redir', 'cid'];
        $Text = preg_replace('#<([^>]*?)(src)="(?!' . implode('|', $allowed_src_protocols) . ')(.*?)"(.*?)>#ism',
-                            '<$1$2=""$4 class="invalid-src" title="' . t('Invalid source protocol') . '">', $Text);
+                            '<$1$2=""$4 data-original-src="$3" class="invalid-src" title="' . t('Invalid source protocol') . '">', $Text);
 
        // sanitize href attributes (only whitelisted protocols URLs)
        // default value for backward compatibility
-       $allowed_link_protocols = Config::get('system', 'allowed_link_protocols', array('ftp', 'mailto', 'gopher', 'cid'));
+       $allowed_link_protocols = Config::get('system', 'allowed_link_protocols', ['ftp', 'mailto', 'gopher', 'cid']);
 
        // Always allowed protocol even if config isn't set or not including it
        $allowed_link_protocols[] = 'http';
        $allowed_link_protocols[] = 'redir/';
 
        $regex = '#<([^>]*?)(href)="(?!' . implode('|', $allowed_link_protocols) . ')(.*?)"(.*?)>#ism';
-       $Text = preg_replace($regex, '<$1$2="javascript:void(0)"$4 class="invalid-href" title="' . t('Invalid link protocol') . '">', $Text);
+       $Text = preg_replace($regex, '<$1$2="javascript:void(0)"$4 data-original-href="$3" class="invalid-href" title="' . t('Invalid link protocol') . '">', $Text);
 
        if ($saved_image) {
                $Text = bb_replace_images($Text, $saved_image);
@@ -1385,7 +1386,7 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
                @$doc->loadHTML($encoding.$doctype."<html><body>".$Text."</body></html>");
                $doc->encoding = 'UTF-8';
                $Text = $doc->saveHTML();
-               $Text = str_replace(array("<html><body>", "</body></html>", $doctype, $encoding), array("", "", "", ""), $Text);
+               $Text = str_replace(["<html><body>", "</body></html>", $doctype, $encoding], ["", "", "", ""], $Text);
 
                $Text = str_replace('<br></li>', '</li>', $Text);
 
@@ -1399,7 +1400,7 @@ function bbcode($Text, $preserve_nl = false, $tryoembed = true, $simplehtml = fa
        //$Text = str_replace('<br /><li>', '<li>', $Text);
        //$Text = str_replace('<br /><ul', '<ul ', $Text);
 
-       call_hooks('bbcode', $Text);
+       Addon::callHooks('bbcode', $Text);
 
        return trim($Text);
 }
@@ -1426,7 +1427,7 @@ function remove_abstract($text) {
  */
 function fetch_abstract($text, $addon = "") {
        $abstract = "";
-       $abstracts = array();
+       $abstracts = [];
        $addon = strtolower($addon);
 
        if (preg_match_all("/\[abstract=(.*?)\](.*?)\[\/abstract\]/ism",$text, $results, PREG_SET_ORDER))