validator.normalizeEmail improvements

README.md

@@ -83,9 +83,7 @@ $ bower install validator-js
 - **stripLow(input [, keep_new_lines])** - remove characters with a numerical value < 32 and 127, mostly control characters. If `keep_new_lines` is `true`, newline characters are preserved (`\n` and `\r`, hex `0xA` and `0xD`). Unicode-safe in JavaScript.
 - **whitelist(input, chars)** - remove characters that do not appear in the whitelist. The characters are used in a RegExp and so you will need to escape some chars, e.g. whitelist(input, '\\[\\]').
 - **blacklist(input, chars)** - remove characters that appear in the blacklist. The characters are used in a RegExp and so you will need to escape some chars, e.g. blacklist(input, '\\[\\]').
-- **normalizeEmail(email)** - canonicalize a gmail address.
-
-### Strings only
+- **normalizeEmail(email [, options])** - canonicalize an email address. `options` is an object which defaults to `{ lowercase: true }`. With `lowercase` set to `true`, the local part of the email address is lowercased for all domains; the hostname is always lowercased and the local part of the email address is always lowercased for hosts that are known to be case-insensitive (currently only GMail). Normalization follows special rules for known providers: currently, GMail addresses have dots removed in the local part and are stripped of tags (e.g. `[email protected]` becomes `[email protected]`) and all `@googlemail.com` addresses are normalized to `@gmail.com`.
 
 This library validates and sanitizes **strings** only. All input will be coerced to a string using the following rules
 

test/sanitizers.js

@@ -183,17 +183,37 @@ describe('Sanitizers', function () {
         test({
             sanitizer: 'normalizeEmail'
           , expect: {
-                '[email protected]': '[email protected]'
-              , '[email protected]': '[email protected]'
+                '[email protected]': '[email protected]'
+              , '[email protected]': '[email protected]'
+              , '[email protected]': '[email protected]'
               , '[email protected]': '[email protected]'
-              , '[email protected]': 'somename@googlemail.com'
+              , '[email protected]': 'somename@gmail.com'
               , '[email protected]': '[email protected]'
-              , '[email protected]': 'somenamemiddlename@googlemail.com'
-              , 'some.name.midd..leNa...me..[email protected]': '[email protected]'
-              , 'some.name.midd..leNa...me...[email protected]': 'somenamemiddlename@googlemail.com'
+              , '[email protected]': 'somenamemiddlename@gmail.com'
+              , 'some.name.midd.leNa.me[email protected]': '[email protected]'
+              , '[email protected]': 'somenamemiddlename@gmail.com'
               , '[email protected]': '[email protected]'
-              , 'an invalid email address': 'an invalid email address'
-              , '': ''
+              , 'hans@m端ller.com': 'hans@m端ller.com'
+              , 'an invalid email address': false
+              , '': false
+              // [email protected] was removed from test cases because of a bug with validator.isEmail. See issue #258
+            }
+        });
+        test({
+            sanitizer: 'normalizeEmail'
+          , args: [{lowercase: false}]
+          , expect: {
+                '[email protected]': '[email protected]'
+              , 'hans@m端ller.com': 'hans@m端ller.com'
+              , '[email protected]': '[email protected]' // Hostname is always lowercased
+              , '[email protected]': '[email protected]'
+              , '[email protected]': '[email protected]'
+              , '[email protected]': '[email protected]'
+
+                // Domains that are known for being case-insensitive are always lowercased
+              , '[email protected]': '[email protected]'
+              , '[email protected]': '[email protected]'
+              , '[email protected]': '[email protected]'
             }
         });
     });

test/validators.js

@@ -45,6 +45,8 @@ describe('Validators', function () {
               , 'hans.m端[email protected]'
               , 'hans@m端ller.com'
               , 'test|123@m端ller.com'
+              , '[email protected]'
+              , '[email protected]'
             ]
           , invalid: [
                 'invalidemail@'

validator.js

@@ -433,14 +433,38 @@
     validator.blacklist = function (str, chars) {
         return str.replace(new RegExp('[' + chars + ']+', 'g'), '');
     };
+
+    var default_normalize_email_options = {
+        // Lowercase the local part for all domains (domains that are known for having case-insensitive local parts are always lowercased, such as gmail.com)
+        lowercase: true
+    };
 
-    validator.normalizeEmail = function (email) {
-        var parts = email.toLowerCase().split('@', 2);
+    validator.normalizeEmail = function (email, options) {
+        options = merge(options, default_normalize_email_options);
+
+        // Fail if the email address is invalid
+        if (!validator.isEmail(email)) {
+            return false;
+        }
+
+        var parts = email.split('@', 2);
+
+        // Always lowercase the domain, but the local part only if requested
+        parts[1] = parts[1].toLowerCase();
+        if (options.lowercase) {
+            parts[0] = parts[0].toLowerCase();
+        }
+
+        // gmail.com and googlemail.com
         if (parts[1] === 'gmail.com' || parts[1] === 'googlemail.com') {
+            if (!options.lowercase) { // case-insensitive
+                parts[0] = parts[0].toLowerCase();
+            }
             parts[0] = parts[0].replace(/\./g, '').split('+')[0];
-            email = parts.join('@');
+            parts[1] = 'gmail.com'; // Always replace googlemail.com to gmail.com
         }
-        return email;
+
+        return parts.join('@');
     };
 
     function merge(obj, defaults) {