mirror of
https://github.com/A6-9V/MQL5-Google-Onedrive.git
synced 2026-04-11 04:40:57 +00:00
565e0f72d0
Optimized `scripts/ci_validate_repo.py` for performance and memory efficiency:
- Refactored `check_no_nul_bytes` and `check_reasonable_size` into a single-pass `validate_files` function.
- Implemented early size check using `p.stat().st_size` to avoid reading files larger than 5MB.
- Replaced `p.read_bytes()` with chunked binary reading (64KB chunks) to detect NUL bytes, significantly reducing memory overhead.
- Added performance comments and maintained the efficient `rglob('*')` traversal pattern.
Measurements:
- Reduced I/O passes from 2 to 1.
- Reduced peak memory usage for large files from O(N) to O(1) buffer size.
- Faster rejection for oversized files (rejection before reading).
66 lines
2.1 KiB
Python
Executable file
66 lines
2.1 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
"""
|
|
Lightweight repository sanity checks suitable for GitHub Actions.
|
|
This is intentionally NOT a compiler for MQL5 (MetaEditor isn't available on CI).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
|
|
REPO_ROOT = Path(__file__).resolve().parents[1]
|
|
MQL5_DIR = REPO_ROOT / "mt5" / "MQL5"
|
|
|
|
|
|
def fail(msg: str) -> None:
|
|
print(f"ERROR: {msg}", file=sys.stderr)
|
|
raise SystemExit(1)
|
|
|
|
|
|
def iter_source_files() -> list[Path]:
|
|
if not MQL5_DIR.exists():
|
|
fail(f"Missing directory: {MQL5_DIR}")
|
|
files: list[Path] = []
|
|
# ⚡ Bolt: rglob('*') followed by suffix filtering is more efficient than
|
|
# multiple targeted globs (like rglob('*.mq5') and rglob('*.mqh'))
|
|
# as it avoids repeated traversals of the file system tree.
|
|
for p in MQL5_DIR.rglob("*"):
|
|
if p.is_file() and p.suffix.lower() in {".mq5", ".mqh"}:
|
|
files.append(p)
|
|
if not files:
|
|
fail(f"No .mq5/.mqh files found under {MQL5_DIR}")
|
|
return sorted(files)
|
|
|
|
|
|
def validate_files(files: list[Path]) -> None:
|
|
"""⚡ Bolt: Single-pass validation for performance and memory efficiency."""
|
|
for p in files:
|
|
# ⚡ Bolt: Use stat() for early size check before reading file content.
|
|
# This prevents loading unexpectedly large files into memory.
|
|
stat = p.stat()
|
|
if stat.st_size > 5_000_000:
|
|
fail(f"Unexpectedly large source file (>5MB): {p.relative_to(REPO_ROOT)} ({stat.st_size} bytes)")
|
|
|
|
# ⚡ Bolt: Use chunked binary reading (64KB) to detect NUL bytes efficiently.
|
|
# This minimizes memory overhead compared to full file reads.
|
|
with p.open("rb") as f:
|
|
while chunk := f.read(65536):
|
|
if b"\x00" in chunk:
|
|
fail(f"NUL byte found in {p.relative_to(REPO_ROOT)}")
|
|
|
|
|
|
def main() -> int:
|
|
files = iter_source_files()
|
|
validate_files(files)
|
|
|
|
rel = [str(p.relative_to(REPO_ROOT)) for p in files]
|
|
print("OK: found source files:")
|
|
for r in rel:
|
|
print(f"- {r}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|