chore: bring codebase to 100% clean mypy compliance across core modules

.sampo/changesets/steadfast-lady-sampsa.md

@@ -0,0 +1,5 @@
+---
+pypi/posthog: patch
+---
+
+Improve mypy coverage for core SDK modules without changing runtime behavior.

mypy-baseline.txt

@@ -1,20 +0,0 @@
-posthog/request.py:0: error: Library stubs not installed for "requests"  [import-untyped]
-posthog/request.py:0: note: Hint: "python3 -m pip install types-requests"
-posthog/request.py:0: note: (or run "mypy --install-types" to install all missing stub packages)
-posthog/request.py:0: note: See https://mypy.readthedocs.io/en/stable/running_mypy.html#missing-imports
-posthog/request.py:0: error: Incompatible types in assignment (expression has type "bytes", variable has type "str")  [assignment]
-posthog/consumer.py:0: error: Name "Empty" already defined (possibly by an import)  [no-redef]
-posthog/consumer.py:0: error: Unsupported operand types for <= ("int" and "str")  [operator]
-posthog/consumer.py:0: note: Right operand is of type "int | str"
-posthog/consumer.py:0: error: Unsupported operand types for < ("str" and "int")  [operator]
-posthog/consumer.py:0: note: Left operand is of type "int | str"
-posthog/feature_flags.py:0: error: Unused "type: ignore" comment  [unused-ignore]
-posthog/client.py:0: error: Name "queue" already defined (by an import)  [no-redef]
-posthog/client.py:0: error: Need type annotation for "queue"  [var-annotated]
-posthog/client.py:0: error: Incompatible types in assignment (expression has type "Any | list[Any]", variable has type "None")  [assignment]
-posthog/client.py:0: error: Incompatible types in assignment (expression has type "dict[Any, Any]", variable has type "None")  [assignment]
-posthog/client.py:0: error: "None" has no attribute "__iter__" (not iterable)  [attr-defined]
-posthog/client.py:0: error: Statement is unreachable  [unreachable]
-posthog/client.py:0: error: Statement is unreachable  [unreachable]
-posthog/client.py:0: error: Name "parse_qs" already defined (possibly by an import)  [no-redef]
-posthog/client.py:0: error: Name "urlparse" already defined (possibly by an import)  [no-redef]

mypy.ini

@@ -2,6 +2,7 @@
 python_version = 3.11
 plugins =
     pydantic.mypy
+mypy_path = typings
 strict_optional = True
 no_implicit_optional = True
 warn_unused_ignores = True

posthog/client.py

@@ -90,10 +90,8 @@
 )
 from posthog.version import VERSION
 
-try:
-    import queue
-except ImportError:
-    import Queue as queue
+
+from queue import Queue, Full
 
 
 MAX_DICT_SIZE = 50_000
@@ -283,7 +281,7 @@ def __init__(
             Initialization
         """
         self._max_queue_size = max_queue_size
-        self.queue = queue.Queue(max_queue_size)
+        self.queue: Queue = Queue(max_queue_size)
 
         # api_key: This should be the Team API Key (token), public
         self.api_key = (project_api_key or "").strip()
@@ -297,8 +295,10 @@ def __init__(
         self.host = determine_server_host(host)
         self.gzip = gzip
         self.timeout = timeout
-        self._feature_flags = None  # private variable to store flags
-        self.feature_flags_by_key = None
+        self._feature_flags: Optional[list[Any]] = (
+            None  # private variable to store flags
+        )
+        self.feature_flags_by_key: Optional[dict[str, Any]] = None
         self.group_type_mapping: Optional[dict[str, str]] = None
         self.cohorts: Optional[dict[str, Any]] = None
         self.poll_interval = poll_interval
@@ -1250,7 +1250,7 @@ def _reinit_after_fork(self):
         as they'll be handled by the parent process's consumers.
         """
         if self.consumers:
-            self.queue = queue.Queue(self._max_queue_size)
+            self.queue = Queue(self._max_queue_size)
 
             new_consumers = []
             for old in self.consumers:
@@ -1376,7 +1376,7 @@ def _enqueue(self, msg, disable_geoip):
             self.queue.put(msg, block=False)
             self.log.debug("enqueued %s.", msg["event"])
             return sent_uuid
-        except queue.Full:
+        except Full:
             self.log.warning("analytics-python queue is full")
             return None
 
@@ -2805,10 +2805,7 @@ def _initialize_flag_cache(self, cache_url):
         if not cache_url:
             return None
 
-        try:
-            from urllib.parse import parse_qs, urlparse
-        except ImportError:
-            from urlparse import parse_qs, urlparse
+        from urllib.parse import parse_qs, urlparse
 
         try:
             parsed = urlparse(cache_url)

posthog/consumer.py

@@ -6,10 +6,7 @@
 
 from posthog.request import APIError, DatetimeSerializer, batch_post
 
-try:
-    from queue import Empty
-except ImportError:
-    from Queue import Empty
+from queue import Empty
 
 
 MAX_MSG_SIZE = 900 * 1024  # 900KiB per event
@@ -133,9 +130,11 @@ def is_retryable(exc):
                 # retry on server errors and client errors
                 # with 408 (request timeout) or 429 (rate limited),
                 # don't retry on other client errors
-                if exc.status == "N/A":
-                    return False
-                return not ((400 <= exc.status < 500) and exc.status not in (408, 429))
+                if isinstance(exc.status, int):
+                    return not (
+                        (400 <= exc.status < 500) and exc.status not in (408, 429)
+                    )
+                return False
             else:
                 # retry on all other errors (eg. network)
                 return True

posthog/feature_flags.py

@@ -511,7 +511,7 @@ def compare(lhs, rhs, operator):
 
         parsed_value = None
         try:
-            parsed_value = float(value)  # type: ignore
+            parsed_value = float(value)
         except Exception:
             pass
 

posthog/request.py

@@ -6,10 +6,10 @@
 from datetime import date, datetime, timezone
 from gzip import GzipFile
 from io import BytesIO
-from typing import Any, List, Optional, Tuple, Union
+from typing import Any, List, Optional, Tuple, Union, cast
 
 import requests
-from requests.adapters import HTTPAdapter  # type: ignore[import-untyped]
+from requests.adapters import HTTPAdapter
 from urllib3.connection import HTTPConnection
 from urllib3.util.retry import Retry
 
@@ -219,7 +219,7 @@ def determine_server_host(host: Optional[str]) -> str:
 def post(
     api_key: str,
     host: Optional[str] = None,
-    path=None,
+    path: Optional[str] = None,
     gzip: bool = False,
     timeout: int = 15,
     session: Optional[requests.Session] = None,
@@ -230,9 +230,9 @@ def post(
     body = kwargs
     body["sentAt"] = datetime.now(tz=timezone.utc).isoformat()
     trimmed_host = remove_trailing_slash(normalize_host(host))
-    url = trimmed_host + path
+    url = trimmed_host + cast(str, path)
     body["api_key"] = api_key
-    data = json.dumps(body, cls=DatetimeSerializer)
+    data: str | bytes = json.dumps(body, cls=DatetimeSerializer)
     log.debug("making request: %s to url: %s", data, url)
     headers = {"Content-Type": "application/json", "User-Agent": USER_AGENT}
     if gzip:
@@ -241,7 +241,7 @@ def post(
         with GzipFile(fileobj=buf, mode="w") as gz:
             # 'data' was produced by json.dumps(),
             # whose default encoding is utf-8.
-            gz.write(data.encode("utf-8"))
+            gz.write(cast(str, data).encode("utf-8"))
         data = buf.getvalue()
 
     res = (session or _get_session()).post(

posthog/test/test_request.py

@@ -79,6 +79,58 @@ def test_invalid_host(self):
             Exception, batch_post, "testsecret", "t.posthog.com/", batch=[]
         )
 
+    def test_post_without_path_preserves_type_error(self):
+        mock_session = mock.MagicMock()
+
+        with self.assertRaises(TypeError):
+            request_module.post(
+                TEST_API_KEY,
+                host="https://test.posthog.com",
+                session=mock_session,
+            )
+
+        mock_session.post.assert_not_called()
+
+    def test_post_sends_string_payload_without_gzip(self):
+        mock_response = requests.Response()
+        mock_response.status_code = 200
+        mock_session = mock.MagicMock()
+        mock_session.post.return_value = mock_response
+
+        request_module.post(
+            TEST_API_KEY,
+            host="https://test.posthog.com",
+            path="/batch/",
+            session=mock_session,
+            batch=[],
+        )
+
+        mock_session.post.assert_called_once()
+        url = mock_session.post.call_args.args[0]
+        data = mock_session.post.call_args.kwargs["data"]
+        self.assertEqual(url, "https://test.posthog.com/batch/")
+        self.assertIsInstance(data, str)
+
+    def test_post_sends_bytes_payload_with_gzip(self):
+        mock_response = requests.Response()
+        mock_response.status_code = 200
+        mock_session = mock.MagicMock()
+        mock_session.post.return_value = mock_response
+
+        request_module.post(
+            TEST_API_KEY,
+            host="https://test.posthog.com",
+            path="/batch/",
+            gzip=True,
+            session=mock_session,
+            batch=[],
+        )
+
+        data = mock_session.post.call_args.kwargs["data"]
+        headers = mock_session.post.call_args.kwargs["headers"]
+        self.assertIsInstance(data, bytes)
+        self.assertEqual(headers["Content-Encoding"], "gzip")
+
     def test_datetime_serialization(self):
         data = {"created": datetime(2012, 3, 4, 5, 6, 7, 891011)}
         result = json.dumps(data, cls=DatetimeSerializer)

sdk_compliance_adapter/adapter.py

@@ -287,7 +287,7 @@ def capture():
         kwargs = {"distinct_id": distinct_id, "properties": properties}
         if timestamp:
             # Parse ISO8601 timestamp
-            from dateutil.parser import parse  # type: ignore[import-untyped]
+            from dateutil.parser import parse
 
             kwargs["timestamp"] = parse(timestamp)
 

typings/dateutil/parser.pyi

@@ -0,0 +1,4 @@
+from datetime import datetime
+from typing import Any
+
+def parse(timestr: str, *args: Any, **kwargs: Any) -> datetime: ...

typings/requests/__init__.pyi

@@ -0,0 +1,29 @@
+from typing import Any
+
+from . import adapters as adapters, exceptions as exceptions
+
+class Response:
+    status_code: int
+    ok: bool
+    text: str
+    headers: dict[str, str]
+    def json(self) -> Any: ...
+
+class Session:
+    def mount(self, prefix: str, adapter: adapters.HTTPAdapter) -> None: ...
+    def close(self) -> None: ...
+    def post(
+        self,
+        url: str,
+        *,
+        data: str | bytes,
+        headers: dict[str, str],
+        timeout: int,
+    ) -> Response: ...
+    def get(
+        self,
+        url: str,
+        *,
+        headers: dict[str, str],
+        timeout: int | None = ...,
+    ) -> Response: ...

typings/requests/adapters.pyi

@@ -0,0 +1,5 @@
+from typing import Any
+
+class HTTPAdapter:
+    def __init__(self, *args: Any, **kwargs: Any) -> None: ...
+    def init_poolmanager(self, *args: Any, **kwargs: Any) -> None: ...

typings/requests/exceptions.pyi

@@ -0,0 +1,2 @@
+class Timeout(Exception): ...
+class ConnectionError(Exception): ...