/**
* @return DOMDocument DOM to manipulate
*/
public function getDoc()
{
if (!$this->doc) {
// DOMDocument::loadHTML apparently isn't very good with encodings, so
// convert input to ASCII by encoding everything above 128 as entities.
if (function_exists('mb_convert_encoding')) {
$html = mb_convert_encoding($this->html, 'HTML-ENTITIES', 'UTF-8');
} else {
$html = preg_replace_callback('/[\\x{80}-\\x{10ffff}]/u', function ($m) {
return '&#' . UtfNormal\Utils::utf8ToCodepoint($m[0]) . ';';
}, $this->html);
}
// Workaround for bug that caused spaces before references
// to disappear during processing: https://phabricator.wikimedia.org/T55086
// TODO: Please replace with a better fix if one can be found.
$html = str_replace(' <', ' <', $html);
libxml_use_internal_errors(true);
$loader = libxml_disable_entity_loader();
$this->doc = new DOMDocument();
$this->doc->strictErrorChecking = false;
$this->doc->loadHTML($html);
libxml_disable_entity_loader($loader);
libxml_use_internal_errors(false);
$this->doc->encoding = 'UTF-8';
}
return $this->doc;
}
/**
* Get the first character of a string.
*
* @param string $s
* @return string
*/
function firstChar($s)
{
$matches = array();
preg_match('/^([\\x00-\\x7f]|[\\xc0-\\xdf][\\x80-\\xbf]|' . '[\\xe0-\\xef][\\x80-\\xbf]{2}|[\\xf0-\\xf7][\\x80-\\xbf]{3})/', $s, $matches);
if (isset($matches[1])) {
if (strlen($matches[1]) != 3) {
return $matches[1];
}
// Break down Hangul syllables to grab the first jamo
$code = UtfNormal\Utils::utf8ToCodepoint($matches[1]);
if ($code < 0xac00 || 0xd7a4 <= $code) {
return $matches[1];
} elseif ($code < 0xb098) {
return "ㄱ";
} elseif ($code < 0xb2e4) {
return "ㄴ";
} elseif ($code < 0xb77c) {
return "ㄷ";
} elseif ($code < 0xb9c8) {
return "ㄹ";
} elseif ($code < 0xbc14) {
return "ㅁ";
} elseif ($code < 0xc0ac) {
return "ㅂ";
} elseif ($code < 0xc544) {
return "ㅅ";
} elseif ($code < 0xc790) {
return "ㅇ";
} elseif ($code < 0xcc28) {
return "ㅈ";
} elseif ($code < 0xce74) {
return "ㅊ";
} elseif ($code < 0xd0c0) {
return "ㅋ";
} elseif ($code < 0xd30c) {
return "ㅌ";
} elseif ($code < 0xd558) {
return "ㅍ";
} else {
return "ㅎ";
}
} else {
return '';
}
}
/**
* Normalize CSS into a format we can easily search for hostile input
* - decode character references
* - decode escape sequences
* - convert characters that IE6 interprets into ascii
* - remove comments, unless the entire value is one single comment
* @param string $value the css string
* @return string normalized css
*/
public static function normalizeCss($value)
{
// Decode character references like {
$value = Sanitizer::decodeCharReferences($value);
// Decode escape sequences and line continuation
// See the grammar in the CSS 2 spec, appendix D.
// This has to be done AFTER decoding character references.
// This means it isn't possible for this function to return
// unsanitized escape sequences. It is possible to manufacture
// input that contains character references that decode to
// escape sequences that decode to character references, but
// it's OK for the return value to contain character references
// because the caller is supposed to escape those anyway.
static $decodeRegex;
if (!$decodeRegex) {
$space = '[\\x20\\t\\r\\n\\f]';
$nl = '(?:\\n|\\r\\n|\\r|\\f)';
$backslash = '\\\\';
$decodeRegex = "/ {$backslash}\n\t\t\t\t(?:\n\t\t\t\t\t({$nl}) | # 1. Line continuation\n\t\t\t\t\t([0-9A-Fa-f]{1,6}){$space}? | # 2. character number\n\t\t\t\t\t(.) | # 3. backslash cancelling special meaning\n\t\t\t\t\t() | # 4. backslash at end of string\n\t\t\t\t)/xu";
}
$value = preg_replace_callback($decodeRegex, array(__CLASS__, 'cssDecodeCallback'), $value);
// Normalize Halfwidth and Fullwidth Unicode block that IE6 might treat as ascii
$value = preg_replace_callback('/[！-［］-ｚ]/u', function ($matches) {
$cp = UtfNormal\Utils::utf8ToCodepoint($matches[0]);
if ($cp === false) {
return '';
}
return chr($cp - 65248);
// ASCII range \x21-\x7A
}, $value);
// Convert more characters IE6 might treat as ascii
// U+0280, U+0274, U+207F, U+029F, U+026A, U+207D, U+208D
$value = str_replace(array('ʀ', 'ɴ', 'ⁿ', 'ʟ', 'ɪ', '⁽', '₍'), array('r', 'n', 'n', 'l', 'i', '(', '('), $value);
// Let the value through if it's nothing but a single comment, to
// allow other functions which may reject it to pass some error
// message through.
if (!preg_match('! ^ \\s* /\\* [^*\\/]* \\*/ \\s* $ !x', $value)) {
// Remove any comments; IE gets token splitting wrong
// This must be done AFTER decoding character references and
// escape sequences, because those steps can introduce comments
// This step cannot introduce character references or escape
// sequences, because it replaces comments with spaces rather
// than removing them completely.
$value = StringUtils::delimiterReplace('/*', '*/', ' ', $value);
// Remove anything after a comment-start token, to guard against
// incorrect client implementations.
$commentPos = strpos($value, '/*');
if ($commentPos !== false) {
$value = substr($value, 0, $commentPos);
}
}
// S followed by repeat, iteration, or prolonged sound marks,
// which IE will treat as "ss"
$value = preg_replace('/s(?:
\\xE3\\x80\\xB1 | # U+3031
\\xE3\\x82\\x9D | # U+309D
\\xE3\\x83\\xBC | # U+30FC
\\xE3\\x83\\xBD | # U+30FD
\\xEF\\xB9\\xBC | # U+FE7C
\\xEF\\xB9\\xBD | # U+FE7D
\\xEF\\xBD\\xB0 # U+FF70
)/ix', 'ss', $value);
return $value;
}
function getFirstLetter($string)
{
$string = strval($string);
if ($string === '') {
return '';
}
// Check for CJK
$firstChar = mb_substr($string, 0, 1, 'UTF-8');
if (ord($firstChar) > 0x7f && self::isCjk(UtfNormal\Utils::utf8ToCodepoint($firstChar))) {
return $firstChar;
}
$sortKey = $this->getPrimarySortKey($string);
// Do a binary search to find the correct letter to sort under
$min = ArrayUtils::findLowerBound(array($this, 'getSortKeyByLetterIndex'), $this->getFirstLetterCount(), 'strcmp', $sortKey);
if ($min === false) {
// Before the first letter
return '';
}
return $this->getLetterByIndex($min);
}
public function getFirstLetter($string)
{
$string = strval($string);
if ($string === '') {
return '';
}
$firstChar = mb_substr($string, 0, 1, 'UTF-8');
// If the first character is a CJK character, just return that character.
if (ord($firstChar) > 0x7f && self::isCjk(UtfNormal\Utils::utf8ToCodepoint($firstChar))) {
return $firstChar;
}
$sortKey = $this->getPrimarySortKey($string);
// Do a binary search to find the correct letter to sort under
$min = ArrayUtils::findLowerBound([$this, 'getSortKeyByLetterIndex'], $this->getFirstLetterCount(), 'strcmp', $sortKey);
if ($min === false) {
// Before the first letter
return '';
}
$sortLetter = $this->getLetterByIndex($min);
if ($this->useNumericCollation) {
// If the sort letter is a number, return '0–9' (or localized equivalent).
// ASCII value of 0 is 48. ASCII value of 9 is 57.
// Note that this also applies to non-Arabic numerals since they are
// mapped to Arabic numeral sort letters. For example, ২ sorts as 2.
if (ord($sortLetter) >= 48 && ord($sortLetter) <= 57) {
$sortLetter = wfMessage('category-header-numerals')->numParams(0, 9)->text();
}
}
return $sortLetter;
}
/**
* Mangle XML-invalid names to be valid in XML
* @param string $name
* @param array $preserveKeys Names to not mangle
* @return string Mangled name
*/
private static function mangleName($name, $preserveKeys = [])
{
static $nsc = null, $nc = null;
if (in_array($name, $preserveKeys, true)) {
return $name;
}
if ($name === '') {
return '_';
}
if ($nsc === null) {
// Note we omit ':' from $nsc and $nc because it's reserved for XML
// namespacing, and we omit '_' from $nsc (but not $nc) because we
// reserve it.
$nsc = 'A-Za-z\\x{C0}-\\x{D6}\\x{D8}-\\x{F6}\\x{F8}-\\x{2FF}\\x{370}-\\x{37D}\\x{37F}-\\x{1FFF}' . '\\x{200C}-\\x{200D}\\x{2070}-\\x{218F}\\x{2C00}-\\x{2FEF}\\x{3001}-\\x{D7FF}' . '\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFFD}\\x{10000}-\\x{EFFFF}';
$nc = $nsc . '_\\-.0-9\\x{B7}\\x{300}-\\x{36F}\\x{203F}-\\x{2040}';
}
if (preg_match("/^[{$nsc}][{$nc}]*\$/uS", $name)) {
return $name;
}
return '_' . preg_replace_callback("/[^{$nc}]/uS", function ($m) {
return sprintf('.%X.', UtfNormal\Utils::utf8ToCodepoint($m[0]));
}, str_replace('.', '.2E.', $name));
}
