fix(sp37-followup): add SftpClient.stat() method

The SftpClient wrapper previously exposed write_file, list_inbound,
list_inbound_names, download_inbound, and read_file — but NO stat().
The canonical cyclone.submission.submit_file helper needs to compare
the local file size against the remote file size for idempotency
(SKIPPED outcome short-circuit); the lack of stat() forced the helper
to bypass the wrapper and open paramiko directly via
submission/core.py:_default_sftp_factory.

This commit adds:
- SftpStat frozen dataclass: narrow projection of paramiko's
  SFTPAttributes (size + modified_at). Callers don't need paramiko.
- SftpClient.stat(remote_path) -> SftpStat public method
- _stat_stub + _stat_paramiko backends (mirrors the existing
  _read_file_stub / _read_file_paramiko pattern)
- 8 new tests covering dataclass shape, frozen invariant, stub size,
  stub mtime, missing-file FileNotFoundError, large-file size, and
  the actual SKIPPED-outcome idempotency check from submit_file

Also adds backend/var/ to .gitignore — contains HCPF-delivered
inbound production files that should never be committed (same
rationale as the existing ingest/ entry).
This commit is contained in:
Nora
2026-07-07 12:24:35 -06:00
parent dc5bff617d
commit f62e1a7881
3 changed files with 224 additions and 0 deletions
+1
View File
@@ -7,3 +7,4 @@ __pycache__/
venv/
build/
dist/
var/
@@ -94,6 +94,22 @@ def _op_timeout_seconds() -> float:
return value
@dataclass(frozen=True)
class SftpStat:
"""File metadata returned by :meth:`SftpClient.stat`.
Mirrors the subset of paramiko's ``SFTPAttributes`` that callers
actually need (``size``, ``modified_at``). Keeping the surface
narrow means callers don't need to import paramiko to consume
the result, and the wrapper's stub mode can populate it from a
plain ``os.stat_result`` without any paramiko dance.
Frozen so callers can hash / cache the result if they need to.
"""
size: int
modified_at: datetime | None = None
@dataclass
class InboundFile:
"""A single file observed in the inbound MFT path."""
@@ -216,6 +232,30 @@ class SftpClient:
return self._read_file_stub(remote_path)
return self._read_file_paramiko(remote_path)
def stat(self, remote_path: str) -> SftpStat:
"""Return file metadata for ``remote_path``.
Mirrors the subset of paramiko's ``SFTPAttributes`` that
callers need (``size`` for idempotency checks; ``modified_at``
for cache-busting). The SP37 submission helper uses
``stat().size`` to short-circuit re-uploads of already-uploaded
files (the SKIPPED outcome path).
Stub mode: reads ``os.stat_result`` from
``{staging_dir}/{remote_path}``.
Real mode: calls ``sftp.stat(remote_path)`` on a paramiko
connection.
Raises:
FileNotFoundError: if ``remote_path`` does not exist
(stub: missing local file; real: paramiko raises
``IOError`` which is a ``FileNotFoundError`` subclass).
"""
if self._stub:
return self._stat_stub(remote_path)
return self._stat_paramiko(remote_path)
def _read_file_stub(self, remote_path: str) -> bytes:
"""Read bytes from ``{staging_dir}/{remote_path}`` (SP16 stub)."""
staging = Path(self._block.staging_dir).resolve()
@@ -224,6 +264,25 @@ class SftpClient:
raise FileNotFoundError(f"inbound stub file not found: {target}")
return target.read_bytes()
def _stat_stub(self, remote_path: str) -> SftpStat:
"""Return ``SftpStat`` for ``{staging_dir}/{remote_path}`` (SP37 stub).
Mirrors what paramiko's ``sftp.stat()`` returns in real mode:
``size`` from ``st.st_size`` and ``modified_at`` from
``st.st_mtime``. Raises ``FileNotFoundError`` if the local
file is missing — matches paramiko's ``IOError`` behavior
so the caller doesn't need to special-case stub mode.
"""
staging = Path(self._block.staging_dir).resolve()
target = staging / remote_path.lstrip("/")
if not target.is_file():
raise FileNotFoundError(f"inbound stub file not found: {target}")
st = target.stat()
return SftpStat(
size=st.st_size,
modified_at=datetime.fromtimestamp(st.st_mtime),
)
def get_secret(self, name: str) -> Optional[str]:
"""Fetch the auth secret from Keychain. Returns the stub secret if absent."""
value = secrets.get_secret(name)
@@ -506,6 +565,20 @@ class SftpClient:
shutil.copyfileobj(f, buf, length=64 * 1024)
return buf.getvalue()
def _stat_paramiko(self, remote_path: str) -> SftpStat:
"""Return ``SftpStat`` for ``remote_path`` via paramiko.
Paramiko's ``SFTPAttributes`` already provides ``st_size`` and
``st_mtime``; we project them into our narrow public
``SftpStat`` shape so callers don't need to know about paramiko.
"""
with self._connect() as (ssh, sftp):
attr = sftp.stat(remote_path)
return SftpStat(
size=attr.st_size or 0,
modified_at=datetime.fromtimestamp(attr.st_mtime or 0),
)
# ---------------------------------------------------------------------------
# Module-level helper
+150
View File
@@ -0,0 +1,150 @@
"""SP37 follow-up #5: SftpClient.stat() method.
The SftpClient wrapper previously exposed ``write_file``,
``list_inbound``, ``list_inbound_names``, ``download_inbound``, and
``read_file`` — but NO ``stat()``. The canonical
``cyclone.submission.submit_file`` helper needs to compare the local
file size against the remote file size for idempotency; the lack of
``stat()`` forced the helper to bypass the wrapper and open paramiko
directly (see ``submission/core.py:_default_sftp_factory``).
This file adds a ``stat()`` method to the wrapper so the helper can
use ``SftpClient(block=b)`` instead of bypassing the wrapper. Tests
cover the stub implementation only (paramiko real-mode tests would
need a real SFTP server).
"""
from __future__ import annotations
from pathlib import Path
import pytest
from cyclone.clearhouse import SftpClient, SftpStat
from cyclone.providers import SftpBlock
def _stub_block(staging_dir: Path) -> SftpBlock:
return SftpBlock(
host="mft.example.com",
port=22,
username="user",
auth={"password_keychain_account": "x"},
paths={"inbound": "/inbound", "outbound": "/outbound"},
staging_dir=str(staging_dir),
stub=True,
)
@pytest.fixture
def staging(tmp_path: Path) -> Path:
"""A staging dir pre-populated with one file. Mirrors what the
SP9 stub layout looks like when an operator has dropped a real
inbound file for testing."""
inbound = tmp_path / "inbound"
inbound.mkdir(parents=True)
(inbound / "test.txt").write_bytes(b"hello world\n")
return tmp_path
# ---- SftpStat dataclass ----------------------------------------------------- #
def test_sftp_stat_dataclass_exists():
"""The wrapper exposes a small SftpStat dataclass for the result.
Mirrors the paramiko ``SFTPAttributes`` shape (at least ``size``)
but keeps the public surface narrow so callers can use it
without depending on paramiko.
"""
assert SftpStat is not None
stat = SftpStat(size=42, modified_at=None)
assert stat.size == 42
assert stat.modified_at is None
def test_sftp_stat_is_frozen():
"""SftpStat is a frozen dataclass so it can be hashed / used as a
cache key by future callers without surprise mutation."""
from dataclasses import FrozenInstanceError
stat = SftpStat(size=1, modified_at=None)
with pytest.raises(FrozenInstanceError):
stat.size = 2 # type: ignore[misc]
# ---- Public method --------------------------------------------------------- #
def test_sftp_client_has_stat_method():
"""``SftpClient`` exposes a ``stat(remote_path)`` public method.
Guards the API surface — a future contributor who renames or
removes ``stat()`` (forcing the helper to bypass the wrapper
again) would break this test, prompting them to update the
helper instead.
"""
assert hasattr(SftpClient, "stat")
assert callable(SftpClient.stat)
def test_sftp_client_stat_returns_size_in_stub_mode(staging: Path):
"""Stub mode: ``stat(remote_path)`` returns the local staging
file's size via ``os.stat_result.st_size``. Mirrors what a real
paramiko ``SFTPAttributes.st_size`` would return for a remote file.
"""
client = SftpClient(block=_stub_block(staging))
stat = client.stat("/inbound/test.txt")
assert stat.size == len(b"hello world\n")
def test_sftp_client_stat_returns_modified_at_in_stub_mode(staging: Path):
"""Stub mode: ``stat`` populates ``modified_at`` from the local
file's mtime. Mirrors paramiko's behavior for parity."""
client = SftpClient(block=_stub_block(staging))
stat = client.stat("/inbound/test.txt")
assert stat.modified_at is not None
def test_sftp_client_stat_raises_for_missing_file(staging: Path):
"""Stub mode: ``stat`` raises ``FileNotFoundError`` for a path
that doesn't exist locally — matches the real paramiko behavior
(which raises ``IOError``/``FileNotFoundError``). The helper's
SKIPPED-outcome short-circuit depends on this exception type.
"""
client = SftpClient(block=_stub_block(staging))
with pytest.raises(FileNotFoundError):
client.stat("/inbound/missing.txt")
def test_sftp_client_stat_handles_large_file(staging: Path):
"""Stub mode: ``stat`` returns the correct size for non-trivial files.
Sanity check: the size path doesn't truncate or accidentally
cast (e.g. to int8) on larger files.
"""
payload = b"x" * (1024 * 1024) # 1 MiB
(staging / "inbound" / "big.bin").write_bytes(payload)
client = SftpClient(block=_stub_block(staging))
stat = client.stat("/inbound/big.bin")
assert stat.size == 1024 * 1024
def test_sftp_client_stat_supports_idempotency_check(staging: Path):
"""The submission helper's idempotency check works against the
wrapper now.
Replays the SKIPPED-outcome check from
``cyclone.submission.submit_file`` (lines 178-182) using the
wrapper directly. Before this follow-up, the helper had to open
paramiko directly because the wrapper lacked ``stat()``.
"""
payload = b"identical contents"
(staging / "outbound").mkdir(parents=True, exist_ok=True)
(staging / "outbound" / "claim.x12").write_bytes(payload)
client = SftpClient(block=_stub_block(staging))
local_size = len(payload)
# stat() returns the size that was previously uploaded.
remote_stat = client.stat("/outbound/claim.x12")
assert remote_stat.size == local_size # idempotency check passes
# → SKIPPED outcome in the submission helper