kemal
5a20e7131c
Readers for IDAT v3, BPM (locus entries v4-v8), CSV manifest, EGT (data blocks 5-9) and GTC v3-v5 (plus a layout-preserving GTC writer); sample-sheet validation (IN-001..IN-014), IDAT discovery and pairing (IN-020..IN-022), message catalogue and exit codes (CLI-014/016), JSON Lines logging (CLI-007/008), atomic writes (CLI-011), run manifest, and `simurg inspect`. Validation (docs/validation/P1.md): GTC, BPM and EGT readers agree exactly with Illumina BeadArrayFiles on GSA v4 / GDA v1 files; GTCs round-trip byte-identically; BPM and CSV manifests are consistent.
87 lines
2.8 KiB
Python
87 lines
2.8 KiB
Python
"""Atomic output writing and overwrite policy (spec CLI-010, CLI-011).
|
|
|
|
Every output is written to ``<name>.part`` in the same directory, fsynced, then renamed, so an interrupted run
|
|
never leaves a truncated file under its final name.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import contextlib
|
|
import os
|
|
from collections.abc import Iterable, Iterator
|
|
from pathlib import Path
|
|
from typing import IO
|
|
|
|
from simurg.core.errors import SimurgError
|
|
|
|
PART_SUFFIX = ".part"
|
|
|
|
|
|
def _fsync_dir(d: Path) -> None:
|
|
with contextlib.suppress(OSError):
|
|
fd = os.open(d, os.O_RDONLY)
|
|
try:
|
|
os.fsync(fd)
|
|
finally:
|
|
os.close(fd)
|
|
|
|
|
|
@contextlib.contextmanager
|
|
def atomic_open(path: Path, mode: str = "wb", encoding: str | None = None) -> Iterator[IO[bytes] | IO[str]]:
|
|
"""Open ``path.part`` for writing; on success fsync and rename to ``path``; on error remove the part file."""
|
|
path = Path(path)
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
tmp = path.with_name(path.name + PART_SUFFIX)
|
|
fh: IO[bytes] | IO[str] = (
|
|
open(tmp, mode) # noqa: SIM115 - closed below
|
|
if "b" in mode
|
|
else open(tmp, mode, encoding=encoding or "utf-8", newline="") # noqa: SIM115
|
|
)
|
|
try:
|
|
yield fh
|
|
fh.flush()
|
|
os.fsync(fh.fileno())
|
|
fh.close()
|
|
os.replace(tmp, path)
|
|
_fsync_dir(path.parent)
|
|
except BaseException:
|
|
fh.close()
|
|
with contextlib.suppress(FileNotFoundError):
|
|
tmp.unlink()
|
|
raise
|
|
|
|
|
|
def atomic_write_bytes(path: Path, data: bytes) -> None:
|
|
with atomic_open(path, "wb") as fh:
|
|
fh.write(data) # type: ignore[arg-type]
|
|
|
|
|
|
def atomic_write_text(path: Path, text: str) -> None:
|
|
with atomic_open(path, "w", encoding="utf-8") as fh:
|
|
fh.write(text) # type: ignore[call-overload]
|
|
|
|
|
|
def check_outputs_absent(paths: Iterable[Path], *, force: bool) -> None:
|
|
"""Pre-flight overwrite check (CLI-010): raise E_OUTPUT_EXISTS listing up to 10 existing paths."""
|
|
if force:
|
|
return
|
|
existing = [str(p) for p in paths if Path(p).exists()]
|
|
if existing:
|
|
shown = "\n ".join(existing[:10])
|
|
more = f"\n … and {len(existing) - 10} more" if len(existing) > 10 else ""
|
|
raise SimurgError(
|
|
"E_OUTPUT_EXISTS",
|
|
f"{len(existing)} output file(s) already exist:\n {shown}{more}",
|
|
hint="use --force to replace them or --resume to keep completed samples",
|
|
)
|
|
|
|
|
|
def remove_stale_parts(directory: Path) -> list[Path]:
|
|
"""Delete leftover ``*.part`` files (e.g. after a crash); returns what was removed."""
|
|
removed = []
|
|
for p in sorted(Path(directory).rglob(f"*{PART_SUFFIX}")):
|
|
with contextlib.suppress(OSError):
|
|
p.unlink()
|
|
removed.append(p)
|
|
return removed
|