Merge pull request #460 from chriso/chriso/configurable-email-normalization

Configurable GMail address normalization

Author: chriso

README.md

@@ -81,7 +81,7 @@ $ bower install validator-js
 - **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, '\\[\\]')`.
 - **escape(input)** - replace `<`, `>`, `&`, `'`, `"` and `/` with HTML entities.
 - **ltrim(input [, chars])** - trim characters from the left-side of the input.
-- **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`.
+- **normalizeEmail(email [, options])** - canonicalize an email address. `options` is an object which defaults to `{ lowercase: true, remove_dots: true, remove_extension: 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`.
 - **rtrim(input [, chars])** - trim characters from the right-side of the input.
 - **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.
 - **toBoolean(input [, strict])** - convert the input to a boolean. Everything except for `'0'`, `'false'` and `''` returns `true`. In strict mode only `'1'` and `'true'` return `true`.

test/sanitizers.js

@@ -198,7 +198,9 @@ describe('Sanitizers', function () {
               , 'an invalid email address': false
               , '': false
               , '[email protected]': false
-              // [email protected] was removed from test cases because of a bug with validator.isEmail. See issue #258
+              , '[email protected]': false
+              , '[email protected]': false
+              , '[email protected]': '[email protected]'
             }
         });
         test({
@@ -211,13 +213,27 @@ describe('Sanitizers', function () {
               , '[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({
+            sanitizer: 'normalizeEmail'
+          , args: [{remove_dots: false}]
+          , expect: {
+                '[email protected]': '[email protected]'
+            }
+        });
+        test({
+            sanitizer: 'normalizeEmail'
+          , args: [{remove_extension: false}]
+          , expect: {
+                '[email protected]': '[email protected]'
+            }
+        });
     });
 
 });

validator.js

@@ -777,7 +777,9 @@
     };
 
     var default_normalize_email_options = {
-        lowercase: true
+        lowercase: true,
+        remove_dots: true,
+        remove_extension: true
     };
 
     validator.normalizeEmail = function (email, options) {
@@ -788,11 +790,16 @@
         var parts = email.split('@', 2);
         parts[1] = parts[1].toLowerCase();
         if (parts[1] === 'gmail.com' || parts[1] === 'googlemail.com') {
-            parts[0] = parts[0].toLowerCase().replace(/\./g, '');
-            if (parts[0][0] === '+') {
+            if (options.remove_extension) {
+                parts[0] = parts[0].split('+')[0];
+            }
+            if (options.remove_dots) {
+                parts[0] = parts[0].replace(/\./g, '');
+            }
+            if (!parts[0].length) {
                 return false;
             }
-            parts[0] = parts[0].split('+')[0];
+            parts[0] = parts[0].toLowerCase();
             parts[1] = 'gmail.com';
         } else if (options.lowercase) {
             parts[0] = parts[0].toLowerCase();