Exclude .arpa tld names from domains() strategy

.readthedocs.yml

@@ -5,7 +5,10 @@
 version: 2
 
 # Optionally build your docs in additional formats such as PDF and ePub
-formats: all
+formats:
+  - htmlzip
+  - epub
+  # - pdf  # busted by latex crash on unicode U+030A combining ring above, in text() docs
 
 # Optionally set the version of Python and requirements required to build your docs
 build:

AUTHORS.rst

@@ -79,6 +79,7 @@ their individual contributions.
 * `James Lamb <https://github.com/jameslamb>`_
 * `Jenny Rouleau <https://github.com/jennyrou>`_
 * `Jens Heinrich <https://github.com/JensHeinrich>`_
+* `Jens Tröger <https://github.com/jenstroeger>`_
 * `Jeremy Thurgood <https://github.com/jerith>`_
 * `J.J. Green <http://soliton.vm.bytemark.co.uk/pub/jjg/>`_
 * `JP Viljoen <https://github.com/froztbyte>`_ (froztbyte@froztbyte.net)

hypothesis-python/RELEASE.rst

@@ -0,0 +1,8 @@
+RELEASE_TYPE: minor
+
+This release adds an optional ``domains=`` parameter to the
+:func:`~hypothesis.strategies.emails` strategy, and excludes
+the special-use :wikipedia:`.arpa` domain from the default
+strategy (:issue:`3567`).
+
+Thanks to Jens Tröger for reporting and fixing this bug!

hypothesis-python/src/hypothesis/provisional.py

@@ -34,14 +34,16 @@
 # The file contains additional information about the date that it was last updated.
 try:  # pragma: no cover
     traversable = resources.files("hypothesis.vendor") / "tlds-alpha-by-domain.txt"
-    _tlds = traversable.read_text().splitlines()
+    _comment, *_tlds = traversable.read_text().splitlines()
 except (AttributeError, ValueError):  # pragma: no cover  # .files() was added in 3.9
-    _tlds = resources.read_text(
+    _comment, *_tlds = resources.read_text(
         "hypothesis.vendor", "tlds-alpha-by-domain.txt"
     ).splitlines()
+assert _comment.startswith("#")
 
-assert _tlds[0].startswith("#")
-TOP_LEVEL_DOMAINS = ["COM"] + sorted(_tlds[1:], key=len)
+# Remove special-use domain names from the list. For more discussion
+# see https://github.com/HypothesisWorks/hypothesis/pull/3572
+TOP_LEVEL_DOMAINS = ["COM"] + sorted((d for d in _tlds if d != "ARPA"), key=len)
 
 
 class DomainNameStrategy(st.SearchStrategy):

hypothesis-python/src/hypothesis/strategies/_internal/core.py

@@ -2012,21 +2012,30 @@ def deferred(definition: Callable[[], SearchStrategy[Ex]]) -> SearchStrategy[Ex]
     return DeferredStrategy(definition)
 
 
+def domains():
+    import hypothesis.provisional
+
+    return hypothesis.provisional.domains()
+
+
 @defines_strategy(force_reusable_values=True)
-def emails() -> SearchStrategy[str]:
+def emails(
+    *, domains: SearchStrategy[str] = LazyStrategy(domains, (), {})
+) -> SearchStrategy[str]:
     """A strategy for generating email addresses as unicode strings. The
     address format is specified in :rfc:`5322#section-3.4.1`. Values shrink
     towards shorter local-parts and host domains.
 
+    If ``domains`` is given then it must be a strategy that generates domain
+    names for the emails, defaulting to :func:`~hypothesis.provisional.domains`.
+
     This strategy is useful for generating "user data" for tests, as
     mishandling of email addresses is a common source of bugs.
     """
-    from hypothesis.provisional import domains
-
     local_chars = string.ascii_letters + string.digits + "!#$%&'*+-/=^_`{|}~"
     local_part = text(local_chars, min_size=1, max_size=64)
     # TODO: include dot-atoms, quoted strings, escaped chars, etc in local part
-    return builds("{}@{}".format, local_part, domains()).filter(
+    return builds("{}@{}".format, local_part, domains).filter(
         lambda addr: len(addr) <= 254
     )
 

hypothesis-python/tests/nocover/test_emails.py

@@ -9,13 +9,19 @@
 # obtain one at https://mozilla.org/MPL/2.0/.
 
 from hypothesis import given
-from hypothesis.strategies import emails
+from hypothesis.strategies import emails, just
 
 
 @given(emails())
-def test_is_valid_email(address):
+def test_is_valid_email(address: str):
     local, at_, domain = address.rpartition("@")
     assert len(address) <= 254
     assert at_ == "@"
     assert local
     assert domain
+    assert not domain.lower().endswith(".arpa")
+
+
+@given(emails(domains=just("mydomain.com")))
+def test_can_restrict_email_domains(address: str):
+    assert address.endswith("@mydomain.com")