regex-weburl.js

//
// Regular Expression for URL validation
//
// Author: Diego Perini
// Updated: 2010/12/05
//
// 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 1.0.0.0 - 223.255.255.255
//   first and last IP of each class is invalid (broadcast addresses)
//
// Compressed one-line versions:
//
// Javascript version
//
// /^(https?|ftp):\/\/(\S+(:\S*)?@)?(([1-9]|[1-9]\d|1\d\d|2[0-1]\d|22[0-3])(\.([0-9]|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])){2}(\.([1-9]|[1-9]\d|1\d\d|2[0-4]\d|25[0-4]))|(([a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)(\.([a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)*(\.([a-z\u00a1-\uffff]{2,})))(:\d{2,5})?(\/[^\s]*)?$/i
//
// PHP version
//
// _^(https?|ftp)://(\S+(:\S*)?@)?(([1-9]|[1-9]\d|1\d\d|2[0-1]\d|22[0-3])(\.([0-9]|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])){2}(\.([1-9]|[1-9]\d|1\d\d|2[0-4]\d|25[0-4]))|(([a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)(\.([a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)*(\.([a-z\x{00a1}-\x{ffff}]{2,})))(:\d{2,5})?(/[^\s]*)?$_iuS
//
var re_weburl = new RegExp(
  "^" +
    // protocol identifier
    "(https?|ftp)://" +
    // user:pass authentication
    "(\\S+(:\\S*)?@)?" +
    "(" +
      // IP address dotted notation octets
          "([1-9]|[1-9]\\d|1\\d\\d|2[0-1]\\d|22[0-3])" +
      "(\\.([0-9]|[1-9]\\d|1\\d\\d|2[0-4]\\d|25[0-5])){2}" +
      "(\\.([1-9]|[1-9]\\d|1\\d\\d|2[0-4]\\d|25[0-4]))" +
    "|" +
      // host name
         "(([a-z\\u00a1-\\uffff0-9]+-?)*[a-z\\u00a1-\\uffff0-9]+)" +
      // domain name
      "(\\.([a-z\\u00a1-\\uffff0-9]+-?)*[a-z\\u00a1-\\uffff0-9]+)*" +
      // TLD identifier
      "(\\.([a-z\\u00a1-\\uffff]{2,}))" +
    ")" +
    // port number
    "(:\\d{2,5})?" +
    // resource path
    "(/[^\\s]*)?" +
  "$", "i"
);