content-explorer/scripts/check_ui_provenance.py

#!/usr/bin/env python3
"""Require provenance headers on UI files adapted from the pinned OnCo commit."""

from __future__ import annotations

import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
UI = ROOT / "ui"
PIN_FILE = ROOT / "research" / "baseline" / "ONCO_PIN"
SOURCE_SUFFIXES = {".ts", ".tsx", ".css", ".mjs"}
ADAPTED = ("adapted from OnCo", "reduced from OnCo")
HEADER_MARKS = ("Copyright (c) 2026 OnCo", "MIT License", "ui/NOTICE")
NOTICE_MARKS = (
    "Copyright (c) 2026 OnCo",
    "MIT License",
    "Permission is hereby granted",
    "The above copyright notice and this permission notice shall be included",
)


def load_pin(path: Path = PIN_FILE) -> str:
    for line in path.read_text(encoding="utf-8").splitlines():
        if line.startswith("sha:"):
            return line.split(":", 1)[1].strip()
    raise ValueError(f"{path} has no sha")


def is_adapted(text: str) -> bool:
    folded = text.casefold()
    return any(mark.casefold() in folded for mark in ADAPTED)


def header_problems(text: str, label: str, pin: str) -> list[str]:
    if not is_adapted(text):
        return []
    missing = [mark for mark in (*HEADER_MARKS, pin) if mark not in text]
    if not missing:
        return []
    return [f"{label}: provenance header missing {', '.join(missing)}"]


def notice_problems(text: str, pin: str) -> list[str]:
    missing = [mark for mark in (*NOTICE_MARKS, pin) if mark not in text]
    if not missing:
        return []
    return [f"ui/NOTICE missing {', '.join(missing)}"]


def footer_problems(text: str, pin: str) -> list[str]:
    missing = [mark for mark in ("MIT License", pin) if mark not in text]
    if not missing:
        return []
    return [f"ui/components/SiteFooter.tsx missing {', '.join(missing)}"]


def third_party_problems(root: Path = ROOT, pin: str | None = None) -> list[str]:
    pin = load_pin() if pin is None else pin
    path = root / "THIRD_PARTY.md"
    if not path.is_file():
        return ["THIRD_PARTY.md is missing"]
    text = path.read_text(encoding="utf-8")
    missing = [mark for mark in ("Copyright (c) 2026 OnCo", "MIT License", pin) if mark not in text]
    if not missing:
        return []
    return [f"THIRD_PARTY.md missing {', '.join(missing)}"]


def tree_problems(root: Path = UI, pin: str | None = None) -> list[str]:
    pin = load_pin() if pin is None else pin
    problems: list[str] = []
    for path in sorted(root.rglob("*")):
        if not path.is_file() or "node_modules" in path.parts or ".next" in path.parts:
            continue
        if path.suffix not in SOURCE_SUFFIXES:
            continue
        problems.extend(header_problems(path.read_text(encoding="utf-8"), str(path.relative_to(ROOT)), pin))
    notice = root / "NOTICE"
    if not notice.is_file():
        problems.append("ui/NOTICE is missing")
    else:
        problems.extend(notice_problems(notice.read_text(encoding="utf-8"), pin))
    footer = root / "components" / "SiteFooter.tsx"
    if not footer.is_file():
        problems.append("ui/components/SiteFooter.tsx is missing")
    else:
        problems.extend(footer_problems(footer.read_text(encoding="utf-8"), pin))
    problems.extend(third_party_problems(root.parent if root == UI else root, pin))
    return problems


def main() -> int:
    problems = tree_problems()
    if problems:
        print("\n".join(problems))
        return 1
    print("ui provenance: adapted files name the OnCo pin, copyright, and NOTICE")
    return 0


if __name__ == "__main__":
    sys.exit(main())