diff options
Diffstat (limited to 'engine/lib/output.php')
| -rw-r--r-- | engine/lib/output.php | 148 |
1 files changed, 93 insertions, 55 deletions
diff --git a/engine/lib/output.php b/engine/lib/output.php index b1245a924..bff0bf6e9 100644 --- a/engine/lib/output.php +++ b/engine/lib/output.php @@ -16,7 +16,7 @@ **/ function parse_urls($text) { // @todo this causes problems with <attr = "val"> - // must be ing <attr="val"> format (no space). + // must be in <attr="val"> format (no space). // By default htmlawed rewrites tags to this format. // if PHP supported conditional negative lookbehinds we could use this: // $r = preg_replace_callback('/(?<!=)(?<![ ])?(?<!["\'])((ht|f)tps?:\/\/[^\s\r\n\t<>"\'\!\(\),]+)/i', @@ -43,51 +43,26 @@ function parse_urls($text) { /** * Create paragraphs from text with line spacing - * Borrowed from Wordpress. * * @param string $pee The string - * @param bool $br Add BRs? + * @deprecated Use elgg_autop instead + * @todo Add deprecation warning in 1.9 * - * @todo Rewrite * @return string **/ -function autop($pee, $br = 1) { - $pee = $pee . "\n"; // just to make things a little easier, pad the end - $pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee); - // Space things out a little - $allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)'; - $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee); - $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee); - $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines - if (strpos($pee, '<object') !== false) { - $pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed - $pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee); - } - $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates - $pee = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "<p>$1</p>\n", $pee); // make paragraphs, including one at the end - $pee = preg_replace('|<p>\s*?</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace - $pee = preg_replace('!<p>([^<]+)\s*?(</(?:div|address|form)[^>]*>)!', "<p>$1</p>$2", $pee); - $pee = preg_replace('|<p>|', "$1<p>", $pee); - $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag - $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists - $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee); - $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee); - $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee); - $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); - if ($br) { - $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "<WPPreserveNewline />", $matches[0]);'), $pee); - $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks - $pee = str_replace('<WPPreserveNewline />', "\n", $pee); - } - $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee); - $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee); - //if (strpos($pee, '<pre') !== false) { - // mind the space between the ? and >. Only there because of the comment. - // $pee = preg_replace_callback('!(<pre.*? >)(.*?)</pre>!is', 'clean_pre', $pee ); - //} - $pee = preg_replace("|\n</p>$|", '</p>', $pee); - - return $pee; +function autop($pee) { + return elgg_autop($pee); +} + +/** + * Create paragraphs from text with line spacing + * + * @param string $string The string + * + * @return string + **/ +function elgg_autop($string) { + return ElggAutoP::getInstance()->process($string); } /** @@ -271,8 +246,8 @@ function elgg_normalize_url($url) { // '?query=test', #target return $url; - } elseif (stripos($url, 'javascript:') === 0) { - // 'javascript:' + } elseif (stripos($url, 'javascript:') === 0 || stripos($url, 'mailto:') === 0) { + // 'javascript:' and 'mailto:' // Not covered in FILTER_VALIDATE_URL return $url; @@ -310,19 +285,11 @@ function elgg_get_friendly_title($title) { return $result; } - // @todo not using this because of locale concerns - //$title = iconv('UTF-8', 'ASCII//TRANSLIT', $title); + // handle some special cases + $title = str_replace('&', 'and', $title); - // @todo this uses a utf8 character class. can use if - // we want to support utf8 in the url. - //$title = preg_replace('/[^\p{L}\- ]/u', '', $title); + $title = ElggTranslit::urlize($title); - // use A-Za-z0-9_ instead of \w because \w is locale sensitive - $title = preg_replace("/[^A-Za-z0-9_\- ]/", "", $title); - $title = str_replace(" ", "-", $title); - $title = str_replace("--", "-", $title); - $title = trim($title); - $title = elgg_strtolower($title); return $title; } @@ -392,7 +359,7 @@ function elgg_get_friendly_time($time) { /** * Strip tags and offer plugins the chance. * Plugins register for output:strip_tags plugin hook. - * Original string included in $params['original_string'] + * Original string included in $params['original_string'] * * @param string $string Formatted string * @@ -406,3 +373,74 @@ function elgg_strip_tags($string) { return $string; } + +/** + * Apply html_entity_decode() to a string while re-entitising HTML + * special char entities to prevent them from being decoded back to their + * unsafe original forms. + * + * This relies on html_entity_decode() not translating entities when + * doing so leaves behind another entity, e.g. &gt; if decoded would + * create > which is another entity itself. This seems to escape the + * usual behaviour where any two paired entities creating a HTML tag are + * usually decoded, i.e. a lone > is not decoded, but <foo> would + * be decoded to <foo> since it creates a full tag. + * + * Note: This function is poorly explained in the manual - which is really + * bad given its potential for misuse on user input already escaped elsewhere. + * Stackoverflow is littered with advice to use this function in the precise + * way that would lead to user input being capable of injecting arbitrary HTML. + * + * @param string $string + * + * @return string + * + * @author Pádraic Brady + * @copyright Copyright (c) 2010 Pádraic Brady (http://blog.astrumfutura.com) + * @license Released under dual-license GPL2/MIT by explicit permission of Pádraic Brady + * + * @access private + */ +function _elgg_html_decode($string) { + $string = str_replace( + array('>', '<', '&', '"', '''), + array('&gt;', '&lt;', '&amp;', '&quot;', '&#039;'), + $string + ); + $string = html_entity_decode($string, ENT_NOQUOTES, 'UTF-8'); + $string = str_replace( + array('&gt;', '&lt;', '&amp;', '&quot;', '&#039;'), + array('>', '<', '&', '"', '''), + $string + ); + return $string; +} + +/** + * Unit tests for Output + * + * @param sting $hook unit_test + * @param string $type system + * @param mixed $value Array of tests + * @param mixed $params Params + * + * @return array + * @access private + */ +function output_unit_test($hook, $type, $value, $params) { + global $CONFIG; + $value[] = $CONFIG->path . 'engine/tests/api/output.php'; + return $value; +} + +/** + * Initialise the Output subsystem. + * + * @return void + * @access private + */ +function output_init() { + elgg_register_plugin_hook_handler('unit_test', 'system', 'output_unit_test'); +} + +elgg_register_event_handler('init', 'system', 'output_init'); |