From d4949327efa15b492cab1bef3fe074290a328a17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 21 Feb 2014 15:43:14 +0100 Subject: [add] HTML Purifier added to clean code --- inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef.php | 138 +++++++++++++++++++++ 1 file changed, 138 insertions(+) create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef.php (limited to 'inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef.php') diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef.php new file mode 100644 index 00000000..880d8f6d --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef.php @@ -0,0 +1,138 @@ + by removing + * leading and trailing whitespace, ignoring line feeds, and replacing + * carriage returns and tabs with spaces. While most useful for HTML + * attributes specified as CDATA, it can also be applied to most CSS + * values. + * + * @note This method is not entirely standards compliant, as trim() removes + * more types of whitespace than specified in the spec. In practice, + * this is rarely a problem, as those extra characters usually have + * already been removed by HTMLPurifier_Encoder. + * + * @warning This processing is inconsistent with XML's whitespace handling + * as specified by section 3.3.3 and referenced XHTML 1.0 section + * 4.7. However, note that we are NOT necessarily + * parsing XML, thus, this behavior may still be correct. We + * assume that newlines have been normalized. + */ + public function parseCDATA($string) + { + $string = trim($string); + $string = str_replace(array("\n", "\t", "\r"), ' ', $string); + return $string; + } + + /** + * Factory method for creating this class from a string. + * @param string $string String construction info + * @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string + */ + public function make($string) + { + // default implementation, return a flyweight of this object. + // If $string has an effect on the returned object (i.e. you + // need to overload this method), it is best + // to clone or instantiate new copies. (Instantiation is safer.) + return $this; + } + + /** + * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work + * properly. THIS IS A HACK! + * @param string $string a CSS colour definition + * @return string + */ + protected function mungeRgb($string) + { + return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string); + } + + /** + * Parses a possibly escaped CSS string and returns the "pure" + * version of it. + */ + protected function expandCSSEscape($string) + { + // flexibly parse it + $ret = ''; + for ($i = 0, $c = strlen($string); $i < $c; $i++) { + if ($string[$i] === '\\') { + $i++; + if ($i >= $c) { + $ret .= '\\'; + break; + } + if (ctype_xdigit($string[$i])) { + $code = $string[$i]; + for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) { + if (!ctype_xdigit($string[$i])) { + break; + } + $code .= $string[$i]; + } + // We have to be extremely careful when adding + // new characters, to make sure we're not breaking + // the encoding. + $char = HTMLPurifier_Encoder::unichr(hexdec($code)); + if (HTMLPurifier_Encoder::cleanUTF8($char) === '') { + continue; + } + $ret .= $char; + if ($i < $c && trim($string[$i]) !== '') { + $i--; + } + continue; + } + if ($string[$i] === "\n") { + continue; + } + } + $ret .= $string[$i]; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 -- cgit v1.2.3