+function common_render_uri_thingy($matches) {
+ $uri = $matches[0];
+ $trailer = '';
+
+ # Some heuristics for extracting URIs from surrounding punctuation
+ # Strip from trailing text...
+ if (preg_match('/^(.*)([,.:"\']+)$/', $uri, $matches)) {
+ $uri = $matches[1];
+ $trailer = $matches[2];
+ }
+
+ $pairs = array(
+ ']' => '[', # technically disallowed in URIs, but used in Java docs
+ ')' => '(', # far too frequent in Wikipedia and MSDN
+ );
+ $final = substr($uri, -1, 1);
+ if (isset($pairs[$final])) {
+ $openers = substr_count($uri, $pairs[$final]);
+ $closers = substr_count($uri, $final);
+ if ($closers > $openers) {
+ // Assume the paren was opened outside the URI
+ $uri = substr($uri, 0, -1);
+ $trailer = $final . $trailer;
+ }
+ }
+ return '<a href="' . $uri . '" class="extlink">' . $uri . '</a>' . $trailer;
+}
+
+function common_xml_safe_str($str) {
+ $xmlStr = htmlentities(iconv('UTF-8', 'UTF-8//IGNORE', $str), ENT_NOQUOTES, 'UTF-8');
+
+ // Replace control, formatting, and surrogate characters with '*', ala Twitter
+ return preg_replace('/[\p{Cc}\p{Cf}\p{Cs}]/u', '*', $str);
+}
+