opened parenthesis converted to class field

Remove duplicated tokens

.travis.yml

@@ -1,3 +1,5 @@
+sudo: false
+
 language: php
 
 php:
@@ -5,11 +7,25 @@ php:
   - 5.4
   - 5.5
   - 5.6
+  - 7.0
   - hhvm
 
-before_script:
- - wget http://getcomposer.org/composer.phar
- - php composer.phar install --dev --no-interaction
+env:
+  global:
+    - deps=no
+
+matrix:
+  fast_finish: true
+  include:
+    - php: 5.3
+      env: deps=low
+    - php: 5.6
+      env: deps=high
+
+install:
+  - if [ "$deps" = "no" ]; then composer install; fi
+  - if [ "$deps" = "low" ]; then composer update --prefer-lowest; fi
+  - if [ "$deps" = "high" ]; then composer update; fi
 
 script:
  - mkdir -p build/logs

README.md

@@ -1,56 +1,59 @@
-EmailValidator [![Build Status](https://travis-ci.org/egulias/EmailValidator.png?branch=master)](https://travis-ci.org/egulias/EmailValidator) [![Coverage Status](https://coveralls.io/repos/egulias/EmailValidator/badge.png?branch=master)](https://coveralls.io/r/egulias/EmailValidator?branch=master) [![SensioLabsInsight](https://insight.sensiolabs.com/projects/22ba6692-9c02-42e5-a65d-1c5696bfffc6/small.png)](https://insight.sensiolabs.com/projects/22ba6692-9c02-42e5-a65d-1c5696bfffc6)[![Scrutinizer Code Quality](https://scrutinizer-ci.com/g/egulias/EmailValidator/badges/quality-score.png?b=master)](https://scrutinizer-ci.com/g/egulias/EmailValidator/?branch=master)
-=============================
-
-##Installation##
-
-Run the command below to install via Composer
-
-```shell
-composer require egulias/email-validator
-```
-
-##Usage##
-
-Simple example:
-
-```php
-<?php
-
-use Egulias\EmailValidator\EmailValidator;
-
-$validator = new EmailValidator;
-if ($validator->isValid($email)) {
-	echo $email . ' is a valid email address';
-}
-```
-
-More advanced example (returns detailed diagnostic error codes):
-
-```php
-<?php
-
-use Egulias\EmailValidator\EmailValidator;
-
-$validator = new EmailValidator;
-$email = 'dominic@sayers.cc';
-$result = $validator->isValid($email);
-
-if ($result) {
-	echo $email . ' is a valid email address';
-} else if ($validator->hasWarnings()) {
-	echo 'Warning! ' . $email . ' has unusual/deprecated features (result code ' . var_export($validator->getWarnings(), true) . ')';
-} else {
-	echo $email . ' is not a valid email address (result code ' . $validator->getError() . ')';
-}
-```
-
-##Contributors##
-As this is a port from another library and work, here are other people related to the previous:
-
-* Ricard Clau [@ricardclau](http://github.com/ricardclau):      	Performance against PHP built-in filter_var
-* Josepf Bielawski [@stloyd](http://github.com/stloyd):      		For its first re-work of Dominic's lib
-* Dominic Sayers [@dominicsayers](http://github.com/dominicsayers):  	The original isemail function
-
-##License##
-Released under the MIT License attached with this code.
-
+#EmailValidator
+[![Build Status](https://travis-ci.org/egulias/EmailValidator.png?branch=master)](https://travis-ci.org/egulias/EmailValidator) [![Coverage Status](https://coveralls.io/repos/egulias/EmailValidator/badge.png?branch=master)](https://coveralls.io/r/egulias/EmailValidator?branch=master) [![Scrutinizer Code Quality](https://scrutinizer-ci.com/g/egulias/EmailValidator/badges/quality-score.png?b=master)](https://scrutinizer-ci.com/g/egulias/EmailValidator/?branch=master) [![SensioLabsInsight](https://insight.sensiolabs.com/projects/22ba6692-9c02-42e5-a65d-1c5696bfffc6/small.png)](https://insight.sensiolabs.com/projects/22ba6692-9c02-42e5-a65d-1c5696bfffc6)
+=============================
+With the help of
+
+![Powered by PhpStorm](https://www.jetbrains.com/phpstorm/documentation/docs/logo_phpstorm.png)
+##Installation##
+
+Run the command below to install via Composer
+
+```shell
+composer require egulias/email-validator "~1.2"
+```
+
+##Usage##
+
+Simple example:
+
+```php
+<?php
+
+use Egulias\EmailValidator\EmailValidator;
+
+$validator = new EmailValidator;
+if ($validator->isValid($email)) {
+	echo $email . ' is a valid email address';
+}
+```
+
+More advanced example (returns detailed diagnostic error codes):
+
+```php
+<?php
+
+use Egulias\EmailValidator\EmailValidator;
+
+$validator = new EmailValidator;
+$email = 'dominic@sayers.cc';
+$result = $validator->isValid($email);
+
+if ($result) {
+	echo $email . ' is a valid email address';
+} else if ($validator->hasWarnings()) {
+	echo 'Warning! ' . $email . ' has unusual/deprecated features (result code ' . var_export($validator->getWarnings(), true) . ')';
+} else {
+	echo $email . ' is not a valid email address (result code ' . $validator->getError() . ')';
+}
+```
+
+##Contributors##
+As this is a port from another library and work, here are other people related to the previous:
+
+* Ricard Clau [@ricardclau](http://github.com/ricardclau):      	Performance against PHP built-in filter_var
+* Josepf Bielawski [@stloyd](http://github.com/stloyd):      		For its first re-work of Dominic's lib
+* Dominic Sayers [@dominicsayers](http://github.com/dominicsayers):  	The original isemail function
+
+##License##
+Released under the MIT License attached with this code.
+

composer.json

@@ -3,22 +3,23 @@
   "description":  "A library for validating emails",
   "homepage":     "https://github.com/egulias/EmailValidator",
   "type":         "Library",
-  "keywords":     ["email", "validation", "validator"],
+  "keywords":     ["email", "validation", "validator", "emailvalidation", "emailvalidator"],
   "license":      "MIT",
   "authors": [
     {"name": "Eduardo Gulias Davis"}
   ],
   "extra": {
     "branch-alias": {
-      "dev-master": "1.3.x-dev"
+      "dev-master": "2.0.x-dev"
     }
   },
   "require":      {
     "php": ">= 5.3.3",
-    "doctrine/lexer": "~1.0"
+    "doctrine/lexer": "~1.0,>=1.0.1"
   },
   "require-dev" :   {
-    "satooshi/php-coveralls": "dev-master"
+    "satooshi/php-coveralls": "dev-master",
+    "phpunit/phpunit": "~4.4"
   },
   "autoload": {
     "psr-0": {

documentation/RFC5321BNF.html

@@ -1,89 +1,89 @@
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml">
-
-<head>
-<meta content="text/html; charset=utf-8" http-equiv="Content-Type" />
-<title>The BNF from RFC 5321 defining parts of a valid SMTP address</title>
-</head>
-
-<body>
-<pre style="font-size:11px;">
-   Mailbox        = Local-part "@" ( Domain / address-literal )
-
-   Local-part     = Dot-string / Quoted-string
-                  ; MAY be case-sensitive
-
-
-   Dot-string     = Atom *("."  Atom)
-
-   Atom           = 1*atext
-
-   Quoted-string  = DQUOTE *QcontentSMTP DQUOTE
-
-   QcontentSMTP   = qtextSMTP / quoted-pairSMTP
-
-   quoted-pairSMTP  = %d92 %d32-126
-                    ; i.e., backslash followed by any ASCII
-                    ; graphic (including itself) or SPace
-
-   qtextSMTP      = %d32-33 / %d35-91 / %d93-126
-                  ; i.e., within a quoted string, any
-                  ; ASCII graphic or space is permitted
-                  ; without blackslash-quoting except
-                  ; double-quote and the backslash itself.
-
-   Domain         = sub-domain *("." sub-domain)
-
-   sub-domain     = Let-dig [Ldh-str]
-
-   Let-dig        = ALPHA / DIGIT
-
-   Ldh-str        = *( ALPHA / DIGIT / "-" ) Let-dig
-
-   address-literal  = "[" ( IPv4-address-literal /
-                    IPv6-address-literal /
-                    General-address-literal ) "]"
-                    ; See Section 4.1.3
-
-   IPv4-address-literal  = Snum 3("."  Snum)
-
-   IPv6-address-literal  = "IPv6:" IPv6-addr
-
-   General-address-literal  = Standardized-tag ":" 1*dcontent
-
-   Standardized-tag  = Ldh-str
-                     ; Standardized-tag MUST be specified in a
-                     ; Standards-Track RFC and registered with IANA
-
-   dcontent       = %d33-90 / ; Printable US-ASCII
-                  %d94-126 ; excl. "[", "\", "]"
-
-   Snum           = 1*3DIGIT
-                  ; representing a decimal integer
-                  ; value in the range 0 through 255
-
-   IPv6-addr      = IPv6-full / IPv6-comp / IPv6v4-full / IPv6v4-comp
-
-   IPv6-hex       = 1*4HEXDIG
-
-   IPv6-full      = IPv6-hex 7(":" IPv6-hex)
-
-   IPv6-comp      = [IPv6-hex *5(":" IPv6-hex)] "::"
-                  [IPv6-hex *5(":" IPv6-hex)]
-                  ; The "::" represents at least 2 16-bit groups of
-                  ; zeros.  No more than 6 groups in addition to the
-                  ; "::" may be present.
-
-   IPv6v4-full    = IPv6-hex 5(":" IPv6-hex) ":" IPv4-address-literal
-
-   IPv6v4-comp    = [IPv6-hex *3(":" IPv6-hex)] "::"
-                  [IPv6-hex *3(":" IPv6-hex) ":"]
-                  IPv4-address-literal
-                  ; The "::" represents at least 2 16-bit groups of
-                  ; zeros.  No more than 4 groups in addition to the
-                  ; "::" and IPv4-address-literal may be present.
-
-</pre>
-</body>
-
-</html>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+
+<head>
+<meta content="text/html; charset=utf-8" http-equiv="Content-Type" />
+<title>The BNF from RFC 5321 defining parts of a valid SMTP address</title>
+</head>
+
+<body>
+<pre style="font-size:11px;">
+   Mailbox        = Local-part "@" ( Domain / address-literal )
+
+   Local-part     = Dot-string / Quoted-string
+                  ; MAY be case-sensitive
+
+
+   Dot-string     = Atom *("."  Atom)
+
+   Atom           = 1*atext
+
+   Quoted-string  = DQUOTE *QcontentSMTP DQUOTE
+
+   QcontentSMTP   = qtextSMTP / quoted-pairSMTP
+
+   quoted-pairSMTP  = %d92 %d32-126
+                    ; i.e., backslash followed by any ASCII
+                    ; graphic (including itself) or SPace
+
+   qtextSMTP      = %d32-33 / %d35-91 / %d93-126
+                  ; i.e., within a quoted string, any
+                  ; ASCII graphic or space is permitted
+                  ; without blackslash-quoting except
+                  ; double-quote and the backslash itself.
+
+   Domain         = sub-domain *("." sub-domain)
+
+   sub-domain     = Let-dig [Ldh-str]
+
+   Let-dig        = ALPHA / DIGIT
+
+   Ldh-str        = *( ALPHA / DIGIT / "-" ) Let-dig
+
+   address-literal  = "[" ( IPv4-address-literal /
+                    IPv6-address-literal /
+                    General-address-literal ) "]"
+                    ; See Section 4.1.3
+
+   IPv4-address-literal  = Snum 3("."  Snum)
+
+   IPv6-address-literal  = "IPv6:" IPv6-addr
+
+   General-address-literal  = Standardized-tag ":" 1*dcontent
+
+   Standardized-tag  = Ldh-str
+                     ; Standardized-tag MUST be specified in a
+                     ; Standards-Track RFC and registered with IANA
+
+   dcontent       = %d33-90 / ; Printable US-ASCII
+                  %d94-126 ; excl. "[", "\", "]"
+
+   Snum           = 1*3DIGIT
+                  ; representing a decimal integer
+                  ; value in the range 0 through 255
+
+   IPv6-addr      = IPv6-full / IPv6-comp / IPv6v4-full / IPv6v4-comp
+
+   IPv6-hex       = 1*4HEXDIG
+
+   IPv6-full      = IPv6-hex 7(":" IPv6-hex)
+
+   IPv6-comp      = [IPv6-hex *5(":" IPv6-hex)] "::"
+                  [IPv6-hex *5(":" IPv6-hex)]
+                  ; The "::" represents at least 2 16-bit groups of
+                  ; zeros.  No more than 6 groups in addition to the
+                  ; "::" may be present.
+
+   IPv6v4-full    = IPv6-hex 5(":" IPv6-hex) ":" IPv4-address-literal
+
+   IPv6v4-comp    = [IPv6-hex *3(":" IPv6-hex)] "::"
+                  [IPv6-hex *3(":" IPv6-hex) ":"]
+                  IPv4-address-literal
+                  ; The "::" represents at least 2 16-bit groups of
+                  ; zeros.  No more than 4 groups in addition to the
+                  ; "::" and IPv4-address-literal may be present.
+
+</pre>
+</body>
+
+</html>

documentation/RFC5322BNF.html

@@ -1,141 +1,141 @@
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml">
-
-<head>
-<meta content="text/html; charset=utf-8" http-equiv="Content-Type" />
-<title>The BNF from RFC 5322 defining parts of a valid internet message address</title>
-</head>
-
-<body>
-<pre style="font-size:11px;">
-   addr-spec       =   local-part "@" domain
-
-   local-part      =   dot-atom / quoted-string / obs-local-part
-
-   dot-atom        =   [CFWS] dot-atom-text [CFWS]
-
-   CFWS            =   (1*([FWS] comment) [FWS]) / FWS
-
-   FWS             =   ([*WSP CRLF] 1*WSP) /  obs-FWS
-                                          ; Folding white space
-
-   WSP             =   SP / HTAB          ; white space
-
-   obs-FWS         =   1*([CRLF] WSP)     ; As amended in erratum #1908
-
-   ctext           =   %d33-39 /          ; Printable US-ASCII
-                       %d42-91 /          ;  characters not including
-                       %d93-126 /         ;  "(", ")", or "\"
-                       obs-ctext
-
-   obs-ctext       =   obs-NO-WS-CTL
-   ccontent        =   ctext / quoted-pair / comment
-
-   comment         =   "(" *([FWS] ccontent) [FWS] ")"
-
-   dot-atom-text   =   1*atext *("." 1*atext)
-
-   atext           =   ALPHA / DIGIT /    ; Printable US-ASCII
-                       "!" / "#" /        ;  characters not including
-                       "$" / "%" /        ;  specials.  Used for atoms.
-                       "&amp;" / "'" /
-                       "*" / "+" /
-                       "-" / "/" /
-                       "=" / "?" /
-                       "^" / "_" /
-                       "`" / "{" /
-                       "|" / "}" /
-                       "~"
-
-   specials        =   "(" / ")" /        ; Special characters that do
-                       "&lt;" / "&gt;" /        ;  not appear in atext
-                       "[" / "]" /
-                       ":" / ";" /
-                       "@" / "\" /
-                       "," / "." /
-                       DQUOTE
-
-   quoted-string   =   [CFWS]
-                       DQUOTE *([FWS] qcontent) [FWS] DQUOTE
-                       [CFWS]
-
-   qcontent        =   qtext / quoted-pair
-
-   qtext           =   %d33 /             ; Printable US-ASCII
-                       %d35-91 /          ;  characters not including
-                       %d93-126 /         ;  "\" or the quote character
-                       obs-qtext
-
-   obs-qtext       =   obs-NO-WS-CTL
-
-   obs-NO-WS-CTL   =   %d1-8 /            ; US-ASCII control
-                       %d11 /             ;  characters that do not
-                       %d12 /             ;  include the carriage
-                       %d14-31 /          ;  return, line feed, and
-                       %d127              ;  white space characters
-
-   quoted-pair     =   ("\" (VCHAR / WSP)) / obs-qp
-
-   VCHAR           =   %x21-7E            ; visible (printing) characters
-
-   obs-qp          =   "\" (%d0 / obs-NO-WS-CTL / LF / CR)
-
-   obs-local-part  =   word *("." word)
-
-   word            =   atom / quoted-string
-
-   atom            =   [CFWS] 1*atext [CFWS]
-
-   domain          =   dot-atom / domain-literal / obs-domain
-
-   domain-literal  =   [CFWS] "[" *([FWS] dtext) [FWS] "]" [CFWS]
-
-   dtext           =   %d33-90 /          ; Printable US-ASCII
-                       %d94-126 /         ;  characters not including
-                       obs-dtext          ;  "[", "]", or "\"
-
-   obs-dtext       =   obs-NO-WS-CTL / quoted-pair
-
-   obs-domain      =   atom *("." atom)
-
-NB For SMTP mail, the domain-literal is restricted by RFC5321 as follows:
-
-   Mailbox        = Local-part "@" ( Domain / address-literal )
-
-   address-literal  = "[" ( IPv4-address-literal /
-                    IPv6-address-literal /
-                    General-address-literal ) "]"
-
-   IPv4-address-literal  = Snum 3("."  Snum)
-
-   IPv6-address-literal  = "IPv6:" IPv6-addr
-
-   Snum           = 1*3DIGIT
-                  ; representing a decimal integer
-                  ; value in the range 0 through 255
-
-   IPv6-addr      = IPv6-full / IPv6-comp / IPv6v4-full / IPv6v4-comp
-
-   IPv6-hex       = 1*4HEXDIG
-
-   IPv6-full      = IPv6-hex 7(":" IPv6-hex)
-
-   IPv6-comp      = [IPv6-hex *5(":" IPv6-hex)] "::"
-                  [IPv6-hex *5(":" IPv6-hex)]
-                  ; The "::" represents at least 2 16-bit groups of
-                  ; zeros.  No more than 6 groups in addition to the
-                  ; "::" may be present.
-
-   IPv6v4-full    = IPv6-hex 5(":" IPv6-hex) ":" IPv4-address-literal
-
-   IPv6v4-comp    = [IPv6-hex *3(":" IPv6-hex)] "::"
-                  [IPv6-hex *3(":" IPv6-hex) ":"]
-                  IPv4-address-literal
-                  ; The "::" represents at least 2 16-bit groups of
-                  ; zeros.  No more than 4 groups in addition to the
-                  ; "::" and IPv4-address-literal may be present.
-
-</pre>
-</body>
-
-</html>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+
+<head>
+<meta content="text/html; charset=utf-8" http-equiv="Content-Type" />
+<title>The BNF from RFC 5322 defining parts of a valid internet message address</title>
+</head>
+
+<body>
+<pre style="font-size:11px;">
+   addr-spec       =   local-part "@" domain
+
+   local-part      =   dot-atom / quoted-string / obs-local-part
+
+   dot-atom        =   [CFWS] dot-atom-text [CFWS]
+
+   CFWS            =   (1*([FWS] comment) [FWS]) / FWS
+
+   FWS             =   ([*WSP CRLF] 1*WSP) /  obs-FWS
+                                          ; Folding white space
+
+   WSP             =   SP / HTAB          ; white space
+
+   obs-FWS         =   1*([CRLF] WSP)     ; As amended in erratum #1908
+
+   ctext           =   %d33-39 /          ; Printable US-ASCII
+                       %d42-91 /          ;  characters not including
+                       %d93-126 /         ;  "(", ")", or "\"
+                       obs-ctext
+
+   obs-ctext       =   obs-NO-WS-CTL
+   ccontent        =   ctext / quoted-pair / comment
+
+   comment         =   "(" *([FWS] ccontent) [FWS] ")"
+
+   dot-atom-text   =   1*atext *("." 1*atext)
+
+   atext           =   ALPHA / DIGIT /    ; Printable US-ASCII
+                       "!" / "#" /        ;  characters not including
+                       "$" / "%" /        ;  specials.  Used for atoms.
+                       "&amp;" / "'" /
+                       "*" / "+" /
+                       "-" / "/" /
+                       "=" / "?" /
+                       "^" / "_" /
+                       "`" / "{" /
+                       "|" / "}" /
+                       "~"
+
+   specials        =   "(" / ")" /        ; Special characters that do
+                       "&lt;" / "&gt;" /        ;  not appear in atext
+                       "[" / "]" /
+                       ":" / ";" /
+                       "@" / "\" /
+                       "," / "." /
+                       DQUOTE
+
+   quoted-string   =   [CFWS]
+                       DQUOTE *([FWS] qcontent) [FWS] DQUOTE
+                       [CFWS]
+
+   qcontent        =   qtext / quoted-pair
+
+   qtext           =   %d33 /             ; Printable US-ASCII
+                       %d35-91 /          ;  characters not including
+                       %d93-126 /         ;  "\" or the quote character
+                       obs-qtext
+
+   obs-qtext       =   obs-NO-WS-CTL
+
+   obs-NO-WS-CTL   =   %d1-8 /            ; US-ASCII control
+                       %d11 /             ;  characters that do not
+                       %d12 /             ;  include the carriage
+                       %d14-31 /          ;  return, line feed, and
+                       %d127              ;  white space characters
+
+   quoted-pair     =   ("\" (VCHAR / WSP)) / obs-qp
+
+   VCHAR           =   %x21-7E            ; visible (printing) characters
+
+   obs-qp          =   "\" (%d0 / obs-NO-WS-CTL / LF / CR)
+
+   obs-local-part  =   word *("." word)
+
+   word            =   atom / quoted-string
+
+   atom            =   [CFWS] 1*atext [CFWS]
+
+   domain          =   dot-atom / domain-literal / obs-domain
+
+   domain-literal  =   [CFWS] "[" *([FWS] dtext) [FWS] "]" [CFWS]
+
+   dtext           =   %d33-90 /          ; Printable US-ASCII
+                       %d94-126 /         ;  characters not including
+                       obs-dtext          ;  "[", "]", or "\"
+
+   obs-dtext       =   obs-NO-WS-CTL / quoted-pair
+
+   obs-domain      =   atom *("." atom)
+
+NB For SMTP mail, the domain-literal is restricted by RFC5321 as follows:
+
+   Mailbox        = Local-part "@" ( Domain / address-literal )
+
+   address-literal  = "[" ( IPv4-address-literal /
+                    IPv6-address-literal /
+                    General-address-literal ) "]"
+
+   IPv4-address-literal  = Snum 3("."  Snum)
+
+   IPv6-address-literal  = "IPv6:" IPv6-addr
+
+   Snum           = 1*3DIGIT
+                  ; representing a decimal integer
+                  ; value in the range 0 through 255
+
+   IPv6-addr      = IPv6-full / IPv6-comp / IPv6v4-full / IPv6v4-comp
+
+   IPv6-hex       = 1*4HEXDIG
+
+   IPv6-full      = IPv6-hex 7(":" IPv6-hex)
+
+   IPv6-comp      = [IPv6-hex *5(":" IPv6-hex)] "::"
+                  [IPv6-hex *5(":" IPv6-hex)]
+                  ; The "::" represents at least 2 16-bit groups of
+                  ; zeros.  No more than 6 groups in addition to the
+                  ; "::" may be present.
+
+   IPv6v4-full    = IPv6-hex 5(":" IPv6-hex) ":" IPv4-address-literal
+
+   IPv6v4-comp    = [IPv6-hex *3(":" IPv6-hex)] "::"
+                  [IPv6-hex *3(":" IPv6-hex) ":"]
+                  IPv4-address-literal
+                  ; The "::" represents at least 2 16-bit groups of
+                  ; zeros.  No more than 4 groups in addition to the
+                  ; "::" and IPv4-address-literal may be present.
+
+</pre>
+</body>
+
+</html>

src/Egulias/EmailValidator/EmailLexer.php

@@ -67,16 +67,12 @@ class EmailLexer extends AbstractLexer
         "\n"   => self::S_LF,
         "\r\n" => self::CRLF,
         'IPv6' => self::S_IPV6TAG,
-        '<'    => self::S_LOWERTHAN,
-        '>'    => self::S_GREATERTHAN,
         '{'    => self::S_OPENQBRACKET,
         '}'    => self::S_CLOSEQBRACKET,
         ''     => self::S_EMPTY,
         '\0'   => self::C_NUL,
     );
 
-    protected $invalidASCII = array(226 => 1,);
-
     protected $hasInvalidTokens = false;
 
     protected $previous;
@@ -138,12 +134,12 @@ class EmailLexer extends AbstractLexer
     protected function getCatchablePatterns()
     {
         return array(
-            '[a-zA-Z_]+[46]?',
+            '[a-zA-Z_]+[46]?', //ASCII and domain literal
+            '[^\x00-\x7F]',  //UTF-8
             '[0-9]+',
             '\r\n',
             '::',
-            '\s+',
-            '[\x10-\x1F]+',
+            '\s+?',
             '.',
             );
     }
@@ -155,7 +151,7 @@ class EmailLexer extends AbstractLexer
      */
     protected function getNonCatchablePatterns()
     {
-        return array('[\x7f-\xff]+');
+        return array('[\xA0-\xff]+');
     }
 
     /**
@@ -167,16 +163,15 @@ class EmailLexer extends AbstractLexer
      */
     protected function getType(&$value)
     {
-
         if ($this->isNullType($value)) {
             return self::C_NUL;
         }
 
-        if (isset($this->charValue[$value])) {
+        if ($this->isValid($value)) {
             return $this->charValue[$value];
         }
 
-        if ($this->isInvalid($value)) {
+        if ($this->isUTF8Invalid($value)) {
             $this->hasInvalidTokens = true;
             return self::INVALID;
         }
@@ -184,8 +179,18 @@ class EmailLexer extends AbstractLexer
         return  self::GENERIC;
     }
 
+    protected function isValid($value)
+    {
+        if (isset($this->charValue[$value])) {
+            return true;
+        }
+
+        return false;
+    }
+
     /**
-     * @param string $value
+     * @param $value
+     * @return bool
      */
     protected function isNullType($value)
     {
@@ -197,18 +202,20 @@ class EmailLexer extends AbstractLexer
     }
 
     /**
-     * @param string $value
+     * @param $value
+     * @return bool
      */
-    protected function isInvalid($value)
+    protected function isUTF8Invalid($value)
     {
-        if (preg_match('/[\x10-\x1F]+/', $value)) {
-            return true;
-        }
-
-        if (isset($this->invalidASCII[ord($value)])) {
+        if (preg_match('/\p{Cc}+/u', $value)) {
             return true;
         }
 
         return false;
     }
+
+    protected function getModifiers()
+    {
+        return 'iu';
+    }
 }

src/Egulias/EmailValidator/EmailParser.php

@@ -29,7 +29,8 @@ class EmailParser
     }
 
     /**
-     * @param string $str
+     * @param $str
+     * @return array
      */
     public function parse($str)
     {
@@ -39,15 +40,16 @@ class EmailParser
             throw new \InvalidArgumentException('ERR_NOLOCALPART');
         }
 
-        if ($this->lexer->hasInvalidTokens()) {
-            throw new \InvalidArgumentException('ERR_INVALID_ATEXT');
-        }
 
         $this->localPartParser->parse($str);
         $this->domainPartParser->parse($str);
 
         $this->setParts($str);
 
+        if ($this->lexer->hasInvalidTokens()) {
+            throw new \InvalidArgumentException('ERR_INVALID_ATEXT');
+        }
+
         return array('local' => $this->localPart, 'domain' => $this->domainPart);
     }
 

src/Egulias/EmailValidator/EmailValidator.php

@@ -33,6 +33,7 @@ class EmailValidator
     const ERR_FWS_CRLF_END       = 149;
     const ERR_CR_NO_LF           = 150;
     const ERR_DEPREC_REACHED     = 151;
+    const ERR_UNOPENEDCOMMENT    = 152;
     const RFC5321_TLD             = 9;
     const RFC5321_TLDNUMERIC      = 10;
     const RFC5321_QUOTEDSTRING    = 11;

src/Egulias/EmailValidator/Parser/DomainPart.php

@@ -4,7 +4,6 @@
 namespace Egulias\EmailValidator\Parser;
 
 use Egulias\EmailValidator\EmailLexer;
-use Egulias\EmailValidator\Parser\Parser;
 use Egulias\EmailValidator\EmailValidator;
 
 class DomainPart extends Parser
@@ -103,6 +102,7 @@ class DomainPart extends Parser
     protected function doParseDomainPart()
     {
         $domain = '';
+        $openedParenthesis = 0;
         do {
             $prev = $this->lexer->getPrevious();
 
@@ -112,7 +112,19 @@ class DomainPart extends Parser
 
             if ($this->lexer->token['type'] === EmailLexer::S_OPENPARENTHESIS) {
                 $this->parseComments();
+                $openedParenthesis += $this->getOpenedParenthesis();
                 $this->lexer->moveNext();
+                $tmpPrev = $this->lexer->getPrevious();
+                if ($tmpPrev['type'] === EmailLexer::S_CLOSEPARENTHESIS) {
+                    $openedParenthesis--;
+                }
+            }
+            if ($this->lexer->token['type'] === EmailLexer::S_CLOSEPARENTHESIS) {
+                if ($openedParenthesis === 0) {
+                    throw new \InvalidArgumentException('ERR_UNOPENEDCOMMENT');
+                } else {
+                    $openedParenthesis--;
+                }
             }
 
             $this->checkConsecutiveDots();
@@ -179,7 +191,7 @@ class DomainPart extends Parser
             }
 
             if ($this->lexer->isNextToken(EmailLexer::S_CR)) {
-                throw new \InvalidArgumentException("ERR_CR_NO_LF");
+                throw new \InvalidArgumentException('ERR_CR_NO_LF');
             }
             if ($this->lexer->token['type'] === EmailLexer::S_BACKSLASH) {
                 $this->warnings[] = EmailValidator::RFC5322_DOMLIT_OBSDTEXT;
@@ -217,9 +229,6 @@ class DomainPart extends Parser
         return $addressLiteral;
     }
 
-    /**
-     * @param string $addressLiteral
-     */
     protected function checkIPV4Tag($addressLiteral)
     {
         $matchesIP  = array();
@@ -245,6 +254,17 @@ class DomainPart extends Parser
 
     protected function checkDomainPartExceptions($prev)
     {
+        $invalidDomainTokens = array(
+            EmailLexer::S_DQUOTE => true,
+            EmailLexer::S_SEMICOLON => true,
+            EmailLexer::S_GREATERTHAN => true,
+            EmailLexer::S_LOWERTHAN => true,
+        );
+
+        if (isset($invalidDomainTokens[$this->lexer->token['type']])) {
+            throw new \InvalidArgumentException('ERR_EXPECTING_ATEXT');
+        }
+
         if ($this->lexer->token['type'] === EmailLexer::S_COMMA) {
             throw new \InvalidArgumentException('ERR_COMMA_IN_DOMAIN');
         }

src/Egulias/EmailValidator/Parser/LocalPart.php

@@ -4,8 +4,6 @@ namespace Egulias\EmailValidator\Parser;
 
 use Egulias\EmailValidator\EmailLexer;
 use Egulias\EmailValidator\EmailValidator;
-use \InvalidArgumentException;
-
 
 class LocalPart extends Parser
 {
@@ -13,9 +11,9 @@ class LocalPart extends Parser
     {
         $parseDQuote = true;
         $closingQuote = false;
+        $openedParenthesis = 0;
 
         while ($this->lexer->token['type'] !== EmailLexer::S_AT && $this->lexer->token) {
-
             if ($this->lexer->token['type'] === EmailLexer::S_DOT && !$this->lexer->getPrevious()) {
                 throw new \InvalidArgumentException('ERR_DOT_START');
             }
@@ -27,12 +25,19 @@ class LocalPart extends Parser
 
             if ($this->lexer->token['type'] === EmailLexer::S_OPENPARENTHESIS) {
                 $this->parseComments();
+                $openedParenthesis += $this->getOpenedParenthesis();
+            }
+            if ($this->lexer->token['type'] === EmailLexer::S_CLOSEPARENTHESIS) {
+                if ($openedParenthesis === 0) {
+                    throw new \InvalidArgumentException('ERR_UNOPENEDCOMMENT');
+                } else {
+                    $openedParenthesis--;
+                }
             }
 
             $this->checkConsecutiveDots();
 
-            if (
-                $this->lexer->token['type'] === EmailLexer::S_DOT &&
+            if ($this->lexer->token['type'] === EmailLexer::S_DOT &&
                 $this->lexer->isNextToken(EmailLexer::S_AT)
             ) {
                 throw new \InvalidArgumentException('ERR_DOT_END');
@@ -83,7 +88,7 @@ class LocalPart extends Parser
             $this->lexer->moveNext();
 
             if (!$this->escaped() && isset($invalid[$this->lexer->token['type']])) {
-                throw new InvalidArgumentException("ERR_EXPECTED_ATEXT");
+                throw new \InvalidArgumentException('ERR_EXPECTED_ATEXT');
             }
         }
 
@@ -91,12 +96,12 @@ class LocalPart extends Parser
 
         if ($prev['type'] === EmailLexer::S_BACKSLASH) {
             if (!$this->checkDQUOTE(false)) {
-                throw new \InvalidArgumentException("ERR_UNCLOSED_DQUOTE");
+                throw new \InvalidArgumentException('ERR_UNCLOSED_DQUOTE');
             }
         }
 
         if (!$this->lexer->isNextToken(EmailLexer::S_AT) && $prev['type'] !== EmailLexer::S_BACKSLASH) {
-            throw new \InvalidArgumentException("ERR_EXPECED_AT");
+            throw new \InvalidArgumentException('ERR_EXPECED_AT');
         }
 
         return $parseAgain;

src/Egulias/EmailValidator/Parser/Parser.php

@@ -9,6 +9,7 @@ abstract class Parser
 {
     protected $warnings = array();
     protected $lexer;
+    protected $openedParenthesis = 0;
 
     public function __construct(EmailLexer $lexer)
     {
@@ -20,7 +21,13 @@ abstract class Parser
         return $this->warnings;
     }
 
-    abstract function parse($str);
+    abstract public function parse($str);
+
+    /** @return int */
+    public function getOpenedParenthesis()
+    {
+        return $this->openedParenthesis;
+    }
 
     /**
      * validateQuotedPair
@@ -35,15 +42,15 @@ abstract class Parser
         $this->warnings[] = EmailValidator::DEPREC_QP;
     }
 
-    /**
-     * @return string the the comment
-     * @throws \InvalidArgumentException
-     */
     protected function parseComments()
     {
+        $this->openedParenthesis = 1;
         $this->isUnclosedComment();
         $this->warnings[] = EmailValidator::CFWS_COMMENT;
         while (!$this->lexer->isNextToken(EmailLexer::S_CLOSEPARENTHESIS)) {
+            if ($this->lexer->isNextToken(EmailLexer::S_OPENPARENTHESIS)) {
+                $this->openedParenthesis++;
+            }
             $this->warnEscaping();
             $this->lexer->moveNext();
         }
@@ -75,11 +82,11 @@ abstract class Parser
         $this->checkCRLFInFWS();
 
         if ($this->lexer->token['type'] === EmailLexer::S_CR) {
-            throw new \InvalidArgumentException("ERR_CR_NO_LF");
+            throw new \InvalidArgumentException('ERR_CR_NO_LF');
         }
 
         if ($this->lexer->isNextToken(EmailLexer::GENERIC) && $previous['type']  !== EmailLexer::S_AT) {
-            throw new \InvalidArgumentException("ERR_ATEXT_AFTER_CFWS");
+            throw new \InvalidArgumentException('ERR_ATEXT_AFTER_CFWS');
         }
 
         if ($this->lexer->token['type'] === EmailLexer::S_LF || $this->lexer->token['type'] === EmailLexer::C_NUL) {
@@ -160,7 +167,7 @@ abstract class Parser
             return $hasClosingQuote;
         }
         $previous = $this->lexer->getPrevious();
-        if ($this->lexer->isNextToken(EmailLexer::GENERIC) && $previous['type'] === EmailLexer::GENERIC) {
+        if ($previous['type'] === EmailLexer::GENERIC && $this->lexer->isNextToken(EmailLexer::GENERIC)) {
             throw new \InvalidArgumentException('ERR_EXPECTING_ATEXT');
         }
 
@@ -181,10 +188,10 @@ abstract class Parser
             return;
         }
         if ($this->lexer->isNextToken(EmailLexer::CRLF)) {
-            throw new \InvalidArgumentException("ERR_FWS_CRLF_X2");
+            throw new \InvalidArgumentException('ERR_FWS_CRLF_X2');
         }
         if (!$this->lexer->isNextTokenAny(array(EmailLexer::S_SP, EmailLexer::S_HTAB))) {
-            throw new \InvalidArgumentException("ERR_FWS_CRLF_END");
+            throw new \InvalidArgumentException('ERR_FWS_CRLF_END');
         }
     }
 }

tests/egulias/Tests/EmailValidator/EmailLexerTest.php

@@ -26,6 +26,73 @@ class EmailLexerTests extends \PHPUnit_Framework_TestCase
         $this->assertEquals($token, $lexer->token['type']);
     }
 
+    public function testLexerParsesMultipleSpaces()
+    {
+        $lexer = new EmailLexer();
+        $lexer->setInput('  ');
+        $lexer->moveNext();
+        $lexer->moveNext();
+        $this->assertEquals(EmailLexer::S_SP, $lexer->token['type']);
+        $lexer->moveNext();
+        $this->assertEquals(EmailLexer::S_SP, $lexer->token['type']);
+    }
+
+    /**
+     * @dataProvider invalidUTF8CharsProvider
+     */
+    public function testLexerParsesInvalidUTF8($char)
+    {
+        $lexer = new EmailLexer();
+        $lexer->setInput($char);
+        $lexer->moveNext();
+        $lexer->moveNext();
+
+        $this->assertEquals(EmailLexer::INVALID, $lexer->token['type']);
+    }
+
+    public function invalidUTF8CharsProvider()
+    {
+        $chars = array();
+        for ($i = 0; $i < 0x100; ++$i) {
+            $c = $this->utf8Chr($i);
+            if (preg_match('/(?=\p{Cc})(?=[^\t\n\n\r])/u', $c) && !preg_match('/\x{0000}/u', $c)) {
+                $chars[] = array($c);
+            }
+        }
+
+        return $chars;
+    }
+
+    protected function utf8Chr($code_point)
+    {
+
+        if ($code_point < 0 || 0x10FFFF < $code_point || (0xD800 <= $code_point && $code_point <= 0xDFFF)) {
+            return '';
+        }
+
+        if ($code_point < 0x80) {
+            $hex[0] = $code_point;
+            $ret = chr($hex[0]);
+        } elseif ($code_point < 0x800) {
+            $hex[0] = 0x1C0 | $code_point >> 6;
+            $hex[1] = 0x80  | $code_point & 0x3F;
+            $ret = chr($hex[0]).chr($hex[1]);
+        } elseif ($code_point < 0x10000) {
+            $hex[0] = 0xE0 | $code_point >> 12;
+            $hex[1] = 0x80 | $code_point >> 6 & 0x3F;
+            $hex[2] = 0x80 | $code_point & 0x3F;
+            $ret = chr($hex[0]).chr($hex[1]).chr($hex[2]);
+        } else {
+            $hex[0] = 0xF0 | $code_point >> 18;
+            $hex[1] = 0x80 | $code_point >> 12 & 0x3F;
+            $hex[2] = 0x80 | $code_point >> 6 & 0x3F;
+            $hex[3] = 0x80 | $code_point  & 0x3F;
+            $ret = chr($hex[0]).chr($hex[1]).chr($hex[2]).chr($hex[3]);
+        }
+
+        return $ret;
+    }
+
     public function testLexerForTab()
     {
         $lexer = new EmailLexer();
@@ -36,6 +103,17 @@ class EmailLexerTests extends \PHPUnit_Framework_TestCase
         $this->assertEquals(EmailLexer::S_HTAB, $lexer->token['type']);
     }
 
+    public function testLexerForUTF8()
+    {
+        $lexer = new EmailLexer();
+        $lexer->setInput("áÇ@bar.com");
+        $lexer->moveNext();
+        $lexer->moveNext();
+        $this->assertEquals(EmailLexer::GENERIC, $lexer->token['type']);
+        $lexer->moveNext();
+        $this->assertEquals(EmailLexer::GENERIC, $lexer->token['type']);
+    }
+
     public function testLexerSearchToken()
     {
         $lexer = new EmailLexer();
@@ -44,15 +122,6 @@ class EmailLexerTests extends \PHPUnit_Framework_TestCase
         $this->assertTrue($lexer->find(EmailLexer::S_HTAB));
     }
 
-    public function testLexerHasInvalidTokens()
-    {
-        $lexer = new EmailLexer();
-        $lexer->setInput(chr(226));
-        $lexer->moveNext();
-        $lexer->moveNext();
-        $this->assertTrue($lexer->hasInvalidTokens());
-    }
-
     public function getTokens()
     {
         return array(
@@ -85,7 +154,7 @@ class EmailLexerTests extends \PHPUnit_Framework_TestCase
             array('}', EmailLexer::S_CLOSEQBRACKET),
             array('',  EmailLexer::S_EMPTY),
             array(chr(31),  EmailLexer::INVALID),
-            array(chr(226),  EmailLexer::INVALID),
+            array(chr(226),  EmailLexer::GENERIC),
             array(chr(0),  EmailLexer::C_NUL)
         );
     }

tests/egulias/Tests/EmailValidator/EmailValidatorTest.php

@@ -26,9 +26,18 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
         $this->assertTrue($this->validator->isValid($email));
     }
 
+    public function testInvalidUTF8Email()
+    {
+        $validator = new EmailValidator;
+        $email     = "\x80\x81\x82@\x83\x84\x85.\x86\x87\x88";
+
+        $this->assertFalse($validator->isValid($email));
+    }
+
     public function getValidEmails()
     {
         return array(
+            array('â@iana.org'),
             array('fabien@symfony.com'),
             array('example@example.co.uk'),
             array('fabien_potencier@example.fr'),
@@ -47,6 +56,13 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
             array('"test\ test"@iana.org'),
             array('""@iana.org'),
             array('"\""@iana.org'),
+            array('müller@möller.de'),
+            array('test@email*'),
+            array('test@email!'),
+            array('test@email&'),
+            array('test@email^'),
+            array('test@email%'),
+            array('test@email$'),
         );
     }
 
@@ -61,7 +77,9 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
     public function getInvalidEmails()
     {
         return array(
-
+            array('test@example.com test'),
+            array('user  name@example.com'),
+            array('user   name@example.com'),
             array('example.@example.co.uk'),
             array('example@example@example.co.uk'),
             array('(test_exampel@example.fr)'),
@@ -98,6 +116,13 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
             array('test@iana.org \r\n\r\n'),
             array('test@iana.org  \r\n\r\n '),
             array('test@iana/icann.org'),
+            array('test@foo;bar.com'),
+            array('test;123@foobar.com'),
+            array('test@example..com'),
+            array('email.email@email."'),
+            array('test@email>'),
+            array('test@email<'),
+            array('test@email{'),
         );
     }
 
@@ -127,6 +152,11 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
             array(EmailValidator::ERR_DOT_END, 'example@localhost.'),
             array(EmailValidator::ERR_DOT_END, 'example.@example.co.uk'),
             array(EmailValidator::ERR_UNCLOSEDCOMMENT, '(example@localhost'),
+            array(EmailValidator::ERR_UNOPENEDCOMMENT, 'comment)example@localhost'),
+            array(EmailValidator::ERR_UNOPENEDCOMMENT, 'example(comment))@localhost'),
+            array(EmailValidator::ERR_UNOPENEDCOMMENT, 'example@comment)localhost'),
+            array(EmailValidator::ERR_UNOPENEDCOMMENT, 'example@localhost(comment))'),
+            array(EmailValidator::ERR_UNOPENEDCOMMENT, 'example@(comment))example.com'),
             array(EmailValidator::ERR_UNCLOSEDQUOTEDSTR, '"example@localhost'),
             array(EmailValidator::ERR_EXPECTING_ATEXT, 'exa"mple@localhost'),
             //This was the original. But atext is not allowed after \n
@@ -163,13 +193,32 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
     public function getInvalidEmailsWithWarnings()
     {
         return array(
-            array(array( EmailValidator::DEPREC_CFWS_NEAR_AT,), 'example @example.co.uk'),
-            array(array( EmailValidator::DEPREC_CFWS_NEAR_AT,), 'example@ example.co.uk'),
-            array(array( EmailValidator::CFWS_COMMENT,), 'example@example(examplecomment).co.uk'),
+            array(
+                array(
+                    EmailValidator::DEPREC_CFWS_NEAR_AT,
+                    EmailValidator::DNSWARN_NO_RECORD
+                ),
+                'example @example.co.uk'
+            ),
+            array(
+                array(
+                    EmailValidator::DEPREC_CFWS_NEAR_AT,
+                    EmailValidator::DNSWARN_NO_RECORD
+                ),
+                'example@ example.co.uk'
+            ),
+            array(
+                array(
+                    EmailValidator::CFWS_COMMENT,
+                    EmailValidator::DNSWARN_NO_RECORD
+                ),
+                'example@example(examplecomment).co.uk'
+            ),
             array(
                 array(
                     EmailValidator::CFWS_COMMENT,
                     EmailValidator::DEPREC_CFWS_NEAR_AT,
+                    EmailValidator::DNSWARN_NO_RECORD,
                 ),
                 'example(examplecomment)@example.co.uk'
             ),
@@ -177,6 +226,7 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
                 array(
                     EmailValidator::RFC5321_QUOTEDSTRING,
                     EmailValidator::CFWS_FWS,
+                    EmailValidator::DNSWARN_NO_RECORD,
                 ),
                 "\"\t\"@example.co.uk"
             ),
@@ -184,6 +234,7 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
                 array(
                     EmailValidator::RFC5321_QUOTEDSTRING,
                     EmailValidator::CFWS_FWS,
+                    EmailValidator::DNSWARN_NO_RECORD
                 ),
                 "\"\r\"@example.co.uk"
             ),
@@ -275,12 +326,14 @@ class EmailValidatorTest extends \PHPUnit_Framework_TestCase
             array(
                 array(
                     EmailValidator::RFC5321_QUOTEDSTRING,
+                    EmailValidator::DNSWARN_NO_RECORD
                 ),
                 '"example"@example.co.uk'
             ),
             array(
                 array(
                     EmailValidator::RFC5322_LOCAL_TOOLONG,
+                    EmailValidator::DNSWARN_NO_RECORD
                 ),
                 'too_long_localpart_too_long_localpart_too_long_localpart_too_long_localpart@example.co.uk'
             ),