"""Idempotent per-(format, variant) updates to out/bench/storage_sizes.csv.

Contract (docs/rules/build-pipeline-tasks.md section 4): columns
format,variant,bytes; a task re-run REPLACES its own (format, variant) rows
and never touches other rows. Replacement is per variant, not per format:
converters 04-07 own the working-footprint variants while task 09 appends
archival variants of the same formats.
"""

from __future__ import annotations

import logging
import os
import time
from pathlib import Path

logger = logging.getLogger(__name__)

HEADER = "format,variant,bytes"
LOCK_TIMEOUT_S = 30.0  # converters 04-07 may run in parallel; the update is a
LOCK_POLL_S = 0.2      # read-modify-write, so it is serialized via a lock file


def update_storage_sizes(bench_dir: Path, fmt: str, variants: list[tuple[str, int]]) -> Path:
	bench_dir.mkdir(parents=True, exist_ok=True)
	path = bench_dir / "storage_sizes.csv"
	lock = bench_dir / "storage_sizes.lock"
	fd = _acquire(lock)
	try:
		replaced = {(fmt, variant) for variant, _ in variants}
		kept: list[str] = []
		if path.exists():
			lines = path.read_text(encoding="ascii").splitlines()
			if lines and lines[0] != HEADER:
				raise ValueError(f"{path}: unexpected header {lines[0]!r}")
			kept = [ln for ln in lines[1:] if ln and tuple(ln.split(",")[:2]) not in replaced]
		rows = kept + [f"{fmt},{variant},{nbytes}" for variant, nbytes in variants]
		with open(path, "w", encoding="ascii", newline="\n") as fh:
			fh.write(HEADER + "\n" + "\n".join(rows) + "\n")
	finally:
		os.close(fd)
		lock.unlink()
	logger.info("storage_sizes.csv: %s -> %s", fmt, ", ".join(f"{v}={b}" for v, b in variants))
	return path


def _acquire(lock: Path) -> int:
	deadline = time.monotonic() + LOCK_TIMEOUT_S
	while True:
		try:
			return os.open(lock, os.O_CREAT | os.O_EXCL | os.O_WRONLY)
		except FileExistsError:
			if time.monotonic() > deadline:
				raise TimeoutError(f"storage_sizes lock held too long: {lock}")
			time.sleep(LOCK_POLL_S)