diff options
| -rw-r--r-- | modules/filter/filter.module | 60 |
1 files changed, 45 insertions, 15 deletions
diff --git a/modules/filter/filter.module b/modules/filter/filter.module index d6adb6d76..c76e69759 100644 --- a/modules/filter/filter.module +++ b/modules/filter/filter.module @@ -571,6 +571,50 @@ function _filter_tips($format, $long = FALSE) { return $tips; } +/** + * Parses an HTML snippet and returns it as a DOM object. + * + * This function loads the body part of a partial (X)HTML document + * and returns a full DOMDocument object that represents this document. + * You can use filter_dom_serialize() to serialize this DOMDocument + * back to a XHTML snippet. + * + * @param $text + * The partial (X)HTML snippet to load. Invalid mark-up + * will be corrected on import. + * @return + * A DOMDocument that represents the loaded (X)HTML snippet. + */ +function filter_dom_load($text) { + // Ignore warnings during HTML soup loading. + $dom_document = @DOMDocument::loadHTML('<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head><body>' . $text . '</body></html>'); + + return $dom_document; +} + +/** + * Converts a DOM object back to an HTML snippet. + * + * The function serializes the body part of a DOMDocument + * back to an XHTML snippet. + * + * The resulting XHTML snippet will be properly formatted + * to be compatible with HTML user agents. + * + * @param $dom_document + * A DOMDocument object to serialize, only the tags below + * the first <body> node will be converted. + * @return + * A valid (X)HTML snippet, as a string. + */ +function filter_dom_serialize($dom_document) { + $body_node = $dom_document->getElementsByTagName('body')->item(0); + $body_content = ''; + foreach ($body_node->childNodes as $child_node) { + $body_content .= $dom_document->saveXML($child_node); + } + return preg_replace('|<([^>]*)/>|i', '<$1 />', $body_content); +} /** * Format a link to the more extensive filter tips. @@ -757,21 +801,7 @@ function _filter_url($text, $format) { * Scan input and make sure that all HTML tags are properly closed and nested. */ function _filter_htmlcorrector($text) { - // Ignore warnings during HTML soup loading. - $htmlDom = @DOMDocument::loadHTML('<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head><body>' . $text . '</body></html>'); - - // The result of DOMDocument->saveXML($bodyNode) is a partial (X)HTML document. - // We only need what is inside the body tag. - $bodyNode = $htmlDom->getElementsByTagName('body')->item(0); - if (preg_match("|^<body[^>]*>(.*)</body>$|s", $htmlDom->saveXML($bodyNode), $matches)) { - $body_content = $matches[1]; - // The XHTML guidelines recommend to include a space before the trailing / - // and > of empty elements for better rendering on HTML user agents. - return preg_replace('|<([^>]*)/>|i', '<$1 />', $body_content); - } - else { - return ''; - } + return filter_dom_serialize(filter_dom_load($text)); } /** |