#!/usr/bin/env python3
from __future__ import annotations

import json
import re
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
REQUIRED = [
    ROOT / "SKILL.md",
    ROOT / "references" / "decision-policy.md",
    ROOT / "references" / "rule-catalog.md",
    ROOT / "references" / "output-modes.md",
    ROOT / "tests" / "cases.json",
    ROOT / "tests" / "evaluation-rubric.md",
]


def fail(message: str) -> None:
    print(f"FAIL: {message}")
    raise SystemExit(1)


def parse_frontmatter(text: str) -> dict[str, str]:
    match = re.match(r"^---\n(.*?)\n---\n", text, re.S)
    if not match:
        fail("SKILL.md must begin with YAML frontmatter")
    data: dict[str, str] = {}
    for line in match.group(1).splitlines():
        if not line.strip() or line.lstrip().startswith("#"):
            continue
        if ":" not in line:
            fail(f"invalid frontmatter line: {line!r}")
        key, value = line.split(":", 1)
        data[key.strip()] = value.strip().strip('"').strip("'")
    return data


def main() -> None:
    missing = [str(path.relative_to(ROOT)) for path in REQUIRED if not path.exists()]
    if missing:
        fail("missing required files: " + ", ".join(missing))

    skill_text = (ROOT / "SKILL.md").read_text(encoding="utf-8")
    frontmatter = parse_frontmatter(skill_text)
    name = frontmatter.get("name", "")
    description = frontmatter.get("description", "")

    if name != ROOT.name:
        fail(f"frontmatter name {name!r} must match directory {ROOT.name!r}")
    if not re.fullmatch(r"[A-Za-z0-9-]+", name):
        fail("name must contain only letters, numbers, and hyphens")
    if not description.startswith("Use when "):
        fail("description must start with 'Use when '")
    if len((name + description).encode("utf-8")) > 1024:
        fail("name + description frontmatter exceeds 1024 bytes")
    if "cite" in skill_text or "turn" in frontmatter.get("description", ""):
        fail("runtime-specific citation markers must not appear in SKILL.md")

    cases = json.loads((ROOT / "tests" / "cases.json").read_text(encoding="utf-8"))
    if not isinstance(cases, list) or not cases:
        fail("tests/cases.json must be a non-empty array")
    ids: set[str] = set()
    allowed_actions = {"correct", "keep", "suggest", "review"}
    required_keys = {"id", "category", "input", "expected_text", "expected_action", "rule_id", "explanation"}
    for index, case in enumerate(cases):
        missing_keys = required_keys - set(case)
        if missing_keys:
            fail(f"case #{index} missing keys: {sorted(missing_keys)}")
        if case["id"] in ids:
            fail(f"duplicate case id: {case['id']}")
        ids.add(case["id"])
        if case["expected_action"] not in allowed_actions:
            fail(f"invalid expected_action in {case['id']}: {case['expected_action']}")

    print(f"PASS: package structure valid; {len(cases)} test cases loaded")


if __name__ == "__main__":
    main()