// // Regular Expression for URL validation // // Author: Diego Perini // Created: 2010/12/05 // Updated: 2018/09/12 // Modified: 2019/01/05 (Simon Schmeisser) // License: MIT // // SPDX-FileCopyrightText: 2010-2018 Diego Perini (http://www.iport.it) // // SPDX-License-Identifier: MIT // // the regular expression composed & commented // could be easily tweaked for RFC compliance, // it was expressly modified to fit & satisfy // these test for an URL shortener: // // http://mathiasbynens.be/demo/url-regex // // Notes on possible differences from a standard/generic validation: // // - utf-8 char class take in consideration the full Unicode range // - TLDs have been made mandatory so single names like "localhost" fails // - protocols have been restricted to ftp, http and https only as requested // // Changes: // // - IP address dotted notation validation, range: 1.0.0.0 - 223.255.255.255 // first and last IP address of each class is considered invalid // (since they are broadcast/network addresses) // // - Made starting path slash optional (http://example.com?foo=bar) // - Allow a dot (.) at the end of hostnames (http://example.com.) // - Allow an underscore (_) character in host/domain names // - Check dot delimited parts length and total length // - Made protocol optional, allowed short syntax // // // local changes: // // - removed "short syntax //", either http://, https://, ftp:// or just the domain // // Compressed one-line versions: // // Javascript regex version // // /^(?:(?:https?|ftp):\/\/)?(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z0-9\u00a1-\uffff][a-z0-9\u00a1-\uffff_-]{0,62})?[a-z0-9\u00a1-\uffff]\.)+(?:[a-z\u00a1-\uffff]{2,}\.?))(?::\d{2,5})?(?:[/?#]\S*)?$/i // // PHP version (uses % symbol as delimiter) // // %^(?:(?:https?|ftp):\/\/)?(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z0-9\x{00a1}-\x{ffff}][a-z0-9\x{00a1}-\x{ffff}_-]{0,62})?[a-z0-9\x{00a1}-\x{ffff}]\.)+(?:[a-z\x{00a1}-\x{ffff}]{2,})\.?))(?::\d{2,5})?(?:[/?#]\S*)?$%iuS // var re_weburl = new RegExp( "^" + // protocol identifier (optional) "(?:(?:https?|ftp):\\/\\/)?" + // user:pass BasicAuth (optional) "(?:\\S+(?::\\S*)?@)?" + "(?:" + // IP address dotted notation octets // excludes loopback network 0.0.0.0 // excludes reserved space >= 224.0.0.0 // excludes network & broacast addresses // (first & last IP address of each class) "(?:[1-9]\\d?|1\\d\\d|2[01]\\d|22[0-3])" + "(?:\\.(?:1?\\d{1,2}|2[0-4]\\d|25[0-5])){2}" + "(?:\\.(?:[1-9]\\d?|1\\d\\d|2[0-4]\\d|25[0-4]))" + "|" + // host & domain names, may end with dot // can be replaced by a shortest alternative // (?![-_])(?:[-\\w\\u00a1-\\uffff]{0,63}[^-_]\\.)+ "(?:" + "(?:" + "[a-z0-9\\u00a1-\\uffff]" + "[a-z0-9\\u00a1-\\uffff_-]{0,62}" + ")?" + "[a-z0-9\\u00a1-\\uffff]\\." + ")+" + // TLD identifier name, may end with dot "(?:[a-z\\u00a1-\\uffff]{2,}\\.?)" + ")" + // port number (optional) "(?::\\d{2,5})?" + // resource path (optional) "(?:[/?#]\\S*)?" + "$", "i" );