Redact httpx2 URLs whenever httpx2 is installed (#939)

_HTTP_URL_CLASSES took httpx2 from dns.query, so it only matched
httpx2.URL when dnspython 2.9+ had imported httpx2. dnspython 2.9
requires Python >= 3.11, so on Python 3.10 CI gets dnspython 2.8 while
httpx2 is still installed (hatch in the [build] extra requires it), and
httpx2.URL arguments on the httpx2 logger went unmasked. Three
TestHttpx2LogRedaction tests failed on 3.10 as a result.

httpx2 is now imported directly behind a ModuleNotFoundError guard.
The new tests re-execute cli.py with dns.query.httpx2 removed and with
httpx2 unimportable, so the regression is caught on every dnspython
version. Also drops the import of dns.query, which nothing uses now.

Follow-up to GHSA-hjr3-rx4c-24cv (unreleased).

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

parsedmarc/cli.py

@@ -20,7 +20,6 @@ from ssl import CERT_NONE, create_default_context
 from typing import TYPE_CHECKING, Any
 
 import dns.exception
-import dns.query
 import dns.resolver
 import dns.reversename
 import httpx
@@ -115,6 +114,23 @@ else:
             """Never-raised placeholder for the absent msgraph extra."""
 
 
+# dnspython 2.9+ does DNS over HTTPS through httpx2 (installed by its
+# [doh] extra); 2.7 and 2.8 use httpx, so httpx2 may be absent. It may
+# also be present without dnspython having imported it: dnspython 2.9
+# needs Python 3.11, but httpx2 installs on 3.10 and other tools pull it
+# in. _RedactUrlCredentialsFilter must recognize httpx2.URL whenever
+# httpx2 can log one, so it is imported here rather than taken from
+# dns.query (unlike utils.py's _doh_client_class(), which has to match
+# the library dnspython itself imported).
+if TYPE_CHECKING:
+    import httpx2  # pyright: ignore[reportMissingImports]
+else:
+    try:
+        import httpx2
+    except ModuleNotFoundError:
+        httpx2 = None
+
+
 from parsedmarc.constants import DEFAULT_DNS_MAX_RETRIES, DEFAULT_DNS_TIMEOUT
 from parsedmarc.log import logger
 import parsedmarc.mail
@@ -687,12 +703,11 @@ _DEPENDENCY_LOGGERS = (
 )
 
 
-# URL classes whose instances appear as log-record arguments. dnspython
-# 2.9+ does DNS over HTTPS through httpx2, whose URL is not an httpx.URL;
-# like _doh_client_class() in utils.py, take the module dnspython itself
-# imported (absent under dnspython 2.7/2.8, which use httpx).
-_HTTP_URL_CLASSES: tuple[type, ...] = (httpx.URL,) + tuple(
-    module.URL for module in (getattr(dns.query, "httpx2", None),) if module
+# URL classes whose instances appear as log-record arguments. httpx2.URL
+# is not an httpx.URL, so each installed library contributes its own
+# class (see the httpx2 import guard above).
+_HTTP_URL_CLASSES: tuple[type, ...] = (httpx.URL,) + (
+    (httpx2.URL,) if httpx2 is not None else ()
 )
 
 

tests/test_cli.py

@@ -30,6 +30,7 @@ from typing import cast
 from unittest.mock import MagicMock, patch
 
 import dns.message
+import dns.query
 import dns.rcode
 import dns.rdata
 import dns.rdataclass
@@ -5771,6 +5772,66 @@ class TestHttpx2LogRedaction(unittest.TestCase):
         self.assertEqual(len(installed), 1)
 
 
+class TestHttpx2UrlClassImport(unittest.TestCase):
+    """GHSA-hjr3-rx4c-24cv: ``_HTTP_URL_CLASSES`` must recognize
+    ``httpx2.URL`` whenever httpx2 is importable, not only when dnspython
+    imported it. dnspython 2.9 requires Python >= 3.11, so on Python 3.10
+    CI installs dnspython 2.8 (which never imports httpx2) while httpx2
+    still installs there (hatch in the ``[build]`` extra requires it), so
+    a constant taken from ``dns.query`` left ``httpx2.URL`` arguments on
+    the ``httpx2`` logger unmasked there."""
+
+    def _exec_fresh_cli(self):
+        """Execute parsedmarc.cli's source into a throwaway module and
+        return it, leaving the canonical module untouched. Module import
+        adds a StreamHandler to the parsedmarc logger, so the handler list
+        is restored afterwards."""
+        spec = importlib.util.find_spec("parsedmarc.cli")
+        assert spec is not None and spec.loader is not None
+        mod = importlib.util.module_from_spec(spec)
+        saved = list(parsedmarc.log.logger.handlers)
+        try:
+            spec.loader.exec_module(mod)
+        finally:
+            parsedmarc.log.logger.handlers[:] = saved
+        return mod
+
+    def test_httpx2_url_masked_when_dnspython_did_not_import_httpx2(self):
+        """Simulate dnspython 2.8 (no ``dns.query.httpx2``) with httpx2
+        installed anyway: the httpx2 URL must still be masked. The old
+        constant, built from ``getattr(dns.query, "httpx2", None)``, left
+        it unredacted."""
+        try:
+            import httpx2  # pyright: ignore[reportMissingImports]
+        except ModuleNotFoundError:
+            self.skipTest("httpx2 is not installed")
+        with patch.dict(dns.query.__dict__):
+            dns.query.__dict__.pop("httpx2", None)
+            fresh = self._exec_fresh_cli()
+        url = httpx2.URL("https://u:S3CRET@h.example/x?token=TOKSECRET")
+        self.assertEqual(
+            fresh._RedactUrlCredentialsFilter._redact(url),
+            "https://u:***@h.example/x?token=***",
+        )
+
+    def test_without_httpx2_only_httpx_urls_are_matched(self):
+        """With httpx2 unimportable (a None ``sys.modules`` entry makes
+        ``import httpx2`` raise ModuleNotFoundError), the module still
+        imports, ``httpx2`` is None, and httpx URLs are still masked.
+        This covers the fallback arm of the guard added for
+        GHSA-hjr3-rx4c-24cv."""
+        with patch.dict(sys.modules, {"httpx2": None}):
+            fresh = self._exec_fresh_cli()
+        self.assertIsNone(fresh.httpx2)
+        self.assertEqual(fresh._HTTP_URL_CLASSES, (httpx.URL,))
+        self.assertEqual(
+            fresh._RedactUrlCredentialsFilter._redact(
+                httpx.URL("https://u:S3CRET@h.example/x")
+            ),
+            "https://u:***@h.example/x",
+        )
+
+
 class TestInitOutputClientsRollback(unittest.TestCase):
     """_init_output_clients() is all-or-nothing against the search backends'
     process-wide ``default`` connection alias.