Normalize author name unicode before matching (#2006)

* Fix accented characters not being matched in author name

Fixes #2004

* Normalized the strings instead of modifying the pattern

* Applied isort & black

poetry/packages/package.py

@@ -5,6 +5,7 @@ import re
 
 from contextlib import contextmanager
 from typing import Union
+from unicodedata import normalize
 from warnings import warn
 
 from poetry.semver import Version
@@ -160,7 +161,7 @@ class Package(object):
         if not self._authors:
             return {"name": None, "email": None}
 
-        m = AUTHOR_REGEX.match(self._authors[0])
+        m = AUTHOR_REGEX.match(normalize("NFC", self._authors[0]))
 
         name = m.group("name")
         email = m.group("email")
@@ -171,7 +172,7 @@ class Package(object):
         if not self._maintainers:
             return {"name": None, "email": None}
 
-        m = AUTHOR_REGEX.match(self._maintainers[0])
+        m = AUTHOR_REGEX.match(normalize("NFC", self._maintainers[0]))
 
         name = m.group("name")
         email = m.group("email")

tests/packages/test_package.py

@@ -13,6 +13,18 @@ def test_package_authors():
     assert package.author_name == "Sébastien Eustace"
     assert package.author_email == "sebastien@eustace.io"
 
+    package.authors.insert(
+        0, "Raphaël Yancey <raphael@badfile.net>"
+    )  # With combining diacritics (ë = e + ¨ = e\u0308)
+    assert package.author_name == "Raphaël Yancey"  # Is normalized into \u00EB
+    assert package.author_email == "raphael@badfile.net"
+
+    package.authors.insert(
+        0, "Raphaël Yancey <raphael@badfile.net>"
+    )  # Without (ë = \u00EB)
+    assert package.author_name == "Raphaël Yancey"
+    assert package.author_email == "raphael@badfile.net"
+
     package.authors.insert(0, "John Doe")
     assert package.author_name == "John Doe"
     assert package.author_email is None