Migrate to WHATWG URL everywhere

Also discovers & resolves a few URL related issues:
- WHATWG parses any potentially valid integer string as an IP - add explicit IP detection to avoid this case and preserve existing parsing functionality
- WHATWG does not fuzzy parse ipv6 addresses, so add simple regex-based ipv6 extraction to handle this case and preserve existing functionality
- WHATWG does not parse scheme-less URLs so change prefixing behavior to include a scheme when falling back to URL-based parsing

lib/clean-host.js

@@ -14,7 +14,9 @@ var isValid = require('./is-valid.js');
  */
 
 // scheme      = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
-var hasPrefixRE = /^(([a-z][a-z0-9+.-]*)?:)?\/\//;
+var hasPrefixRE = /^(([a-z][a-z0-9+.-]+)?:)\/\//;
+var ipLikeRE = /(\d+\.){3}\d+/i;
+var ipv6LikeRE = /(([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4}|::1)/i;
 
 
 /**
@@ -74,30 +76,45 @@ module.exports = function extractHostname(value) {
     url = '' + url;
   }
 
-  var needsTrimming = checkTrimmingNeeded(url);
-  if (needsTrimming) {
-    url = url.trim();
-  }
-
   var needsLowerCase = checkLowerCaseNeeded(url);
   if (needsLowerCase) {
     url = url.toLowerCase();
   }
 
+  var v6Match = url.match(ipv6LikeRE);
+  if (v6Match) {
+    return v6Match[1];
+  }
+
+  var needsTrimming = checkTrimmingNeeded(url);
+  if (needsTrimming) {
+    url = url.trim();
+  }
+
   // Try again after `url` has been transformed to lowercase and trimmed.
   if ((needsLowerCase || needsTrimming) && isValid(url)) {
     return trimTrailingDots(url);
   }
 
   // Proceed with heavier url parsing to extract the hostname.
   if (!hasPrefixRE.test(url)) {
-    url = '//' + url;
+    url = 'https://' + url;
   }
 
-  var parts = new URL(url);
-
-  if (parts.hostname) {
-    return trimTrailingDots(parts.hostname);
+  try {
+    var parts = new URL(url);
+
+    if (parts.hostname) {
+      // WHATWG URL parses any integer sequence as an IP, whereas the legacy
+      // node URL module would not. Preserve behavior where non-ip-like strings
+      // will not result in valid hostnames.
+      if (ipLikeRE.test(parts.hostname) && !ipLikeRE.test(value)) {
+        return value;
+      }
+      return trimTrailingDots(parts.hostname);
+    }
+  } catch (e) {
+    // Invalid URL
   }
 
   return null;

test/tld.js

@@ -291,7 +291,7 @@ describe('tld.js', function () {
     });
 
     it('should return the initial value if it is not a valid hostname', function(){
-      expect(tld.extractHostname(42)).to.equal('42');
+      expect(tld.extractHostname(42)).to.equal(42);
     });
 
     it('should return www.nytimes.com even with an URL as a parameter', function(){