Refactor PostgreSQLExecutor to support Windows compatibility for process management #1182
Conversation
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. WalkthroughReplaces static start-command quoting with cross‑platform command assembly, adds Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant Executor as PostgreSQLExecutor
participant OS as OperatingSystem
participant Proc as PostgreSQLProcess
Client->>Executor: call stop()
Executor->>Executor: assemble pg_ctl stop command (list)
alt Windows
Executor->>OS: start pg_ctl stop (no-shell list)
Executor->>Executor: invoke _windows_terminate_process()
Executor->>Proc: send terminate(), wait()
alt timeout
Executor->>Proc: send kill(), wait()
Proc-->>Executor: killed
else terminated
Proc-->>Executor: terminated
end
else Non‑Windows
Executor->>OS: call super().stop() (uses os.killpg)
alt AttributeError (killpg missing)
Executor->>Executor: fallback to _windows_terminate_process()
end
end
Executor-->>Client: return self / stop result
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@pytest_postgresql/executor.py`:
- Around line 263-283: In stop(self, sig: Optional[int] = None, exp_sig:
Optional[int] = None) replace the subprocess.check_output call that builds a
shell string with a list-style invocation (e.g., [self.executable, "stop", "-D",
self.datadir, "-m", "f"]) and remove shell=True so subprocess runs the
executable directly; this avoids breaking paths with spaces and removes the
shell injection risk while keeping the same arguments and behavior before the
platform-specific termination logic (_windows_terminate_process / super().stop).
- Around line 53-66: The _get_base_command constructs the -o string with
unix_socket_directories unquoted which breaks for paths with spaces; update
_get_base_command to detect whitespace in the unixsocketdir variable and wrap
that value in double quotes (or escape quotes) when building the -o option so
the produced fragment becomes -c unix_socket_directories="/path/with space"
(referencing the unix_socket_directories token and BASE_PROC_START_COMMAND
assignment), and add a unit test that passes a datadir/unixsocketdir containing
a space to ensure the command line includes the quoted socket directory (or
alternatively, add explicit validation/documentation and raise a clear error
when whitespace is present).
🧹 Nitpick comments (1)
pytest_postgresql/executor.py (1)
231-262: Tidy up the termination helper API surface.
sigis unused in_windows_terminate_process, and_unix_terminate_processis currently unused. Either wire_unix_terminate_processintostop()for symmetry and usesig, or drop/rename the parameter to avoid dead code and lint noise.
tboy1337
force-pushed
the
edit
branch
2 times, most recently
from
5d4fb91 to
efa4633
Compare
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@tests/test_windows_compatibility.py`:
- Around line 35-39: The test assertions in tests/test_windows_compatibility.py
don't match the actual string produced by _get_base_command(): update the
assertions to expect the escaped-quote form for unix_socket_directories (i.e.,
include the backslash-escaped double quotes around {unixsocketdir}) and assert
that the non-quoted form is not present; specifically change the positive
assertion referencing unix_socket_directories to look for
unix_socket_directories=\"{unixsocketdir}\" and keep the negative assertion for
unix_socket_directories='{unixsocketdir}' to ensure consistency with
_get_base_command().
- Around line 189-204: The test's expected_parts entry for
unix_socket_directories doesn't match the actual command string (which includes
escaped quotes), so update the expectation in the test to match the
implementation: replace the "-c unix_socket_directories=C:/temp/socket" entry
with the escaped-quote form that appears in executor.command (e.g., -c
unix_socket_directories=\"C:/temp/socket\"), keeping the rest of the
expected_parts and the loop over executor.command unchanged; reference the test
variable executor.command and the expected_parts list when making the change.
🧹 Nitpick comments (2)
pytest_postgresql/executor.py (2)
25-25: Unused importsignal.The
signalmodule is imported but not used anywhere in the file. This appears to be a leftover from development.🧹 Suggested fix
-import signal
250-269: Good refactor to list-based subprocess call.The change from shell string to list format (
[self.executable, "stop", "-D", self.datadir, "-m", "f"]) properly addresses the previous security concern and handles paths with spaces correctly.One minor observation: the
AttributeErrorfallback (lines 263-268) uses string matching"killpg" in str(e)which is somewhat fragile. Consider whether this fallback is still needed given the explicitplatform.system()check now handles Windows upfront.
tboy1337
force-pushed
the
edit
branch
2 times, most recently
from
b02c61b to
4a0b22e
Compare
tboy1337
force-pushed
the
edit
branch
2 times, most recently
from
059e4bc to
54140ac
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@pytest_postgresql/executor.py`:
- Around line 226-246: The parameter sig in _windows_terminate_process is
intentionally unused and triggers Ruff ARG002; either rename it to _sig to
indicate it’s intentionally unused or keep sig and add a local lint suppression
(e.g., append a noqa comment for ARG002) where the function is defined to
silence the warning; update the function signature (or add the noqa) in the
_windows_terminate_process definition and run linters to confirm the ARG002
warning is resolved.
…ess management - Convert _get_base_command method to BASE_PROC_START_COMMAND class attribute - Use unified command format without single quotes around PostgreSQL config values - Add _windows_terminate_process method for graceful Windows process termination - Update stop() method to use list args instead of shell=True for security - Add platform-specific termination logic with killpg fallback - Add comprehensive Windows compatibility test suite - Rename parameter in _windows_terminate_process method for clarity
2 participants
Refactors
PostgreSQLExecutorto improve Windows compatibility and security for PostgreSQL process management. This change addresses platform-specific issues with process termination and command formatting that could cause failures on Windows systems.Changes
_get_base_commandmethod toBASE_PROC_START_COMMANDclass attribute with cross-platform compatible syntax (removed single quotes around PostgreSQL config values that caused issues on Windows)_windows_terminate_processmethod that attempts graceful shutdown before force-killing stuck processesstop()method to use list arguments instead ofshell=Trueto prevent shell injection vulnerabilitiesos.killpgAttributeError on WindowsTest plan
tests/test_windows_compatibility.pywith 7 test caseskillpgAttributeErrorSummary by CodeRabbit
Bug Fixes
Tests
✏️ Tip: You can customize this high-level summary in your review settings.