This file was generated by ChatGPT on 2025-08-28

find_unreferenced_cs.py

#!/usr/bin/env python3
"""
find_unreferenced_cs.py

Finds all *.cs files under a given directory and lists the ones
whose **filename** is not mentioned in ANY *.csproj or *.projitems in the repo.

Run from repo root:
  python3 find_unreferenced_cs.py --dir src/libraries/Common/src/Interop

Options:
  --repo-root .                        # default: current directory
  --dir <path>                         # directory to scan for .cs files (relative to repo root)
  --ignore-case                        # do case-insensitive matching (default is case-sensitive)
"""
from __future__ import annotations
import argparse
import sys
from pathlib import Path

def read_text_best_effort(p: Path) -> str:
    """Read text from a file with best-effort encoding fallback."""
    for enc in ("utf-8", "utf-16-le", "utf-16-be", "latin-1"):
        try:
            return p.read_text(encoding=enc)
        except Exception:
            pass
    return p.read_bytes().decode("utf-8", errors="ignore")

def main() -> None:
    ap = argparse.ArgumentParser(description="List .cs files not mentioned in any project file.")
    ap.add_argument("--repo-root", default=".", help="Path to repo root (default: .)")
    ap.add_argument("--dir", required=True,
                    help="Path (relative to repo root) of directory to scan for .cs files.")
    ap.add_argument("--ignore-case", action="store_true",
                    help="Use case-insensitive matching (default: case-sensitive).")
    args = ap.parse_args()

    root = Path(args.repo_root).resolve()
    target_dir = (root / args.dir).resolve()

    if not target_dir.exists():
        print(f"ERROR: Target directory not found: {target_dir}", file=sys.stderr)
        sys.exit(2)

    # Gather all project files in repo
    proj_files = list(root.rglob("*.csproj")) + list(root.rglob("*.projitems"))
    if not proj_files:
        print("WARNING: No .csproj or .projitems files found in repo.", file=sys.stderr)

    # Read all project files into one big string for fast membership checks
    chunks = []
    for pf in proj_files:
        try:
            chunks.append(read_text_best_effort(pf))
        except Exception as e:
            print(f"WARNING: Could not read {pf}: {e}", file=sys.stderr)
    haystack = "\n".join(chunks)
    haystack_cmp = haystack if not args.ignore_case else haystack.lower()

    # Find all .cs files under target_dir
    cs_files = sorted(target_dir.rglob("*.cs"))

    unreferenced: list[str] = []

    for cf in cs_files:
        name = cf.name
        key = name if not args.ignore_case else name.lower()
        if key not in haystack_cmp:
            unreferenced.append(str(cf.relative_to(root)))

    # Print results
    for path in unreferenced:
        print(path)

    print(
        f"\n# Summary: {len(unreferenced)} of {len(cs_files)} .cs files in {target_dir.relative_to(root)} "
        f"not mentioned in any .csproj/.projitems",
        file=sys.stderr
    )

if __name__ == "__main__":
    main()