Add Email type (#870)

docs/reference/types.md

@@ -11,6 +11,7 @@ Outlines provides custom Pydantic types so you can focus on your use case rather
 |  | numeric code | `outlines.types.countries.Numeric` | Valid [country numeric codes][wiki-country-numeric] |
 |  | name | `outlines.types.countries.Name` | Valid country names |
 |  | flag | `outlines.types.countries.Flag` | Valid flag emojis |
+| | email | `outlines.types.Email` | Valid email address |
 
 Some types require localization. We currently only support US types, but please don't hesitate to create localized versions of the different types and open a Pull Request. Localized types are specified using `types.locale` in the following way:
 

outlines/types/__init__.py

@@ -1,3 +1,4 @@
 from . import airports, countries
+from .email import Email
 from .isbn import ISBN
 from .locales import locale

outlines/types/email.py

@@ -0,0 +1,11 @@
+"""Email Address types."""
+from pydantic import WithJsonSchema
+from typing_extensions import Annotated
+
+# Taken from StackOverflow
+# https://stackoverflow.com/a/201378/14773537
+EMAIL_REGEX = r"""(?:[a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\[(?:(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\.){3}(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9])|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])"""
+Email = Annotated[
+    str,
+    WithJsonSchema({"type": "string", "pattern": EMAIL_REGEX}),
+]

tests/test_types.py

@@ -24,6 +24,12 @@
         (types.ISBN, "9780596520687", True),
         (types.ISBN, "ISBN-10: 0-596-52068-9", True),
         (types.ISBN, "0-596-52068-9", True),
+        (types.Email, "[email protected]", True),
+        (types.Email, "[email protected]", True),
+        (types.Email, "[email protected]", False),
+        (types.Email, "myemail", False),
+        (types.Email, "eitan@gmail", False),
+        (types.Email, "[email protected]", True),
     ],
 )
 def test_type_regex(custom_type, test_string, should_match):