sunnysideup / silverstripe-sharethis

        if (function_exists('get_last_retrieve_url_contents_content_type')) {

            $contentTypeHeader = get_last_retrieve_url_contents_content_type();

            $success = preg_match('/charset=(.+)/', $contentTypeHeader, $matches);

            if ($success) {

                $charset = $matches[1];

                if (is_object($debug_object)) {

                    $debug_object->debugLog(2, 'header content-type found charset of: ' . $charset);

                }

            }

        }

        if (empty($charset)) {

                if (!empty($fullvalue)) {

                    $success = preg_match('/charset=(.+)/', $fullvalue, $matches);

                    if ($success) {

                        $charset = $matches[1];

                    } else {

                        // If there is a meta tag, and they don't specify the character set, research says that it's typically ISO-8859-1

                        if (is_object($debug_object)) {

                            $debug_object->debugLog(2, 'meta content-type tag couldn\'t be parsed. using iso-8859 default.');

                        }

                        $charset = 'ISO-8859-1';

                    }

                }

            }

        }

            }

            // and if this doesn't work...  then we need to just wrongheadedly assume it's UTF-8 so that we can move on - cause this will usually give us most of what we need...

            if ($charset === false) {

                if (is_object($debug_object)) {

                    $debug_object->debugLog(2, 'since mb_detect failed - using default of utf-8');

                }

                $charset = 'UTF-8';

            }

        }

        // Since CP1252 is a superset, if we get one of it's subsets, we want it instead.