regex-weburl.js

//
// Regular Expression for URL validation
//
// Author: Diego Perini
// Created: 2010/12/05
// Updated: 2018/09/12
// License: MIT
//
// Copyright (c) 2010-2018 Diego Perini (http://www.iport.it)
//
// Permission is hereby granted, free of charge, to any person
// obtaining a copy of this software and associated documentation
// files (the "Software"), to deal in the Software without
// restriction, including without limitation the rights to use,
// copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the
// Software is furnished to do so, subject to the following
// conditions:
//
// The above copyright notice and this permission notice shall be
// included in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
// EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
// OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
// NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
// HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
// WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
// FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
// OTHER DEALINGS IN THE SOFTWARE.
//
// 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)
//
// - Added exclusion of private, reserved and/or local networks ranges
// - 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 //
//
// 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)
    // short syntax // still required
    "(?:(?:(?:https?|ftp):)?\\/\\/)" +
    // user:pass BasicAuth (optional)
    "(?:\\S+(?::\\S*)?@)?" +
    "(?:" +
      // IP address exclusion
      // private & local networks
      "(?!(?: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})" +
      // IP address dotted notation octets
      // excludes loopback network 0.0.0.0
      // excludes reserved space >= 224.0.0.0
      // excludes network & broadcast 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"
);

@dperini - "(?::\d{2,5})?" for port testing Usually the port is always two numbers long at least. But technically, the valid port range is 0-65535 so the rule should be {1,5} in this case. What is you thought?

@sakshivishnoi681
{1,5} will be precise to cover the number of digits (5) that could possibly be constructed by using 1 to 5 digits.
However the scope it was written {2,5} is to cover real world cases where PORTS of just 1 digit are excluded.

What about IPv6?
This fails:
http://[fe80::1] even though it is perfectly legal...

It doesn't match http://www.4j/images/iepng/iepngfix.webp you can check it here.

Previously discussed punycode TLDs aside, the hypothetical www.4j above raises the question whether numbers in TLDs should be allowed by the regex (although there are currently none in the Public Suffix List)?

^ "number in TLD" has come up before: there are currently no TLDs containing digits in the PSL, meaning that you probably won't encounter it in the wild 👍

But IP addresses do have digit ....

1.1.1.1 would beg to differ

yeah, but you can also use one.one.one.one if you want an domain name instead of an IP.

Hello everyone, the regex is failing the code QL scanning of our pipeline.

Is this an known issue?