- title = title
- // Strip Unicode bidi override characters
- .replace( rUnicodeBidi, '' )
- // Normalise whitespace to underscores and remove duplicates
- .replace( rWhitespace, '_' )
- // Trim underscores
- .replace( rUnderscoreTrim, '' );
+ // From MediaWikiTitleCodec::splitTitleString() in PHP
+ rUnicodeBidi = /[\u200E\u200F\u202A-\u202E]/g,
+
+ /**
+ * Slightly modified from Flinfo. Credit goes to Lupo and Flominator.
+ * @private
+ * @static
+ * @property sanitationRules
+ */
+ sanitationRules = [
+ // "signature"
+ {
+ pattern: /~{3}/g,
+ replace: '',
+ generalRule: true
+ },
+ // control characters
+ {
+ // eslint-disable-next-line no-control-regex
+ pattern: /[\x00-\x1f\x7f]/g,
+ replace: '',
+ generalRule: true
+ },
+ // URL encoding (possibly)
+ {
+ pattern: /%([0-9A-Fa-f]{2})/g,
+ replace: '% $1',
+ generalRule: true
+ },
+ // HTML-character-entities
+ {
+ pattern: /&(([A-Za-z0-9\x80-\xff]+|#[0-9]+|#x[0-9A-Fa-f]+);)/g,
+ replace: '& $1',
+ generalRule: true
+ },
+ // slash, colon (not supported by file systems like NTFS/Windows, Mac OS 9 [:], ext4 [/])
+ {
+ pattern: new RegExp( '[' + mw.config.get( 'wgIllegalFileChars', '' ) + ']', 'g' ),
+ replace: '-',
+ fileRule: true
+ },
+ // brackets, greater than
+ {
+ pattern: /[\]\}>]/g,
+ replace: ')',
+ generalRule: true
+ },
+ // brackets, lower than
+ {
+ pattern: /[\[\{<]/g,
+ replace: '(',
+ generalRule: true
+ },
+ // everything that wasn't covered yet
+ {
+ pattern: new RegExp( rInvalid.source, 'g' ),
+ replace: '-',
+ generalRule: true
+ },
+ // directory structures
+ {
+ pattern: /^(\.|\.\.|\.\/.*|\.\.\/.*|.*\/\.\/.*|.*\/\.\.\/.*|.*\/\.|.*\/\.\.)$/g,
+ replace: '',
+ generalRule: true
+ }
+ ],
+
+ /**
+ * Internal helper for #constructor and #newFromText.
+ *
+ * Based on Title.php#secureAndSplit
+ *
+ * @private
+ * @static
+ * @method parse
+ * @param {string} title
+ * @param {number} [defaultNamespace=NS_MAIN]
+ * @return {Object|boolean}
+ */
+ parse = function ( title, defaultNamespace ) {
+ var namespace, m, id, i, fragment, ext;
+
+ namespace = defaultNamespace === undefined ? NS_MAIN : defaultNamespace;