#!/usr/bin/env python3
"""판례 JSONL 스키마와 사건번호/출처 중복을 검증한다."""

from __future__ import annotations

import argparse
import json
import re
import sys
from pathlib import Path

if __package__ in (None, ""):
    sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

from app.engine.legal_risk import load_precedents


CASE_ID_RE = re.compile(r"^(?:19|20)?\d{2}[가-힣]{1,4}\d+$")
ALLOWED_WORK_TYPES = {"literary", "visual", "musical"}
ALLOWED_LEGAL_TAGS = {
    "reproduction", "derivative_work", "public_transmission", "distribution",
    "publication", "attribution", "integrity", "citation_missing", "false_authorship",
}


def validate_engine_labels(path: Path) -> None:
    for lineno, line in enumerate(path.read_text(encoding="utf-8").splitlines(), 1):
        if not line.strip():
            continue
        row = json.loads(line)
        case_id = str(row.get("case_id", ""))
        if not CASE_ID_RE.fullmatch(case_id):
            raise ValueError(f"{path}:{lineno} 사건번호 형식 오류: {case_id}")
        work_types = set(row.get("work_types", []))
        legal_tags = set(row.get("legal_tags", []))
        criteria = row.get("criteria", [])
        if unknown := work_types - ALLOWED_WORK_TYPES:
            raise ValueError(f"{path}:{lineno} 미지원 저작물 유형: {sorted(unknown)}")
        if unknown := legal_tags - ALLOWED_LEGAL_TAGS:
            raise ValueError(f"{path}:{lineno} 미지원 법적 태그: {sorted(unknown)}")
        if not legal_tags:
            raise ValueError(f"{path}:{lineno} 법적 태그 없음: {case_id}")
        if not work_types and not criteria:
            raise ValueError(f"{path}:{lineno} 저작물 유형·판단 기준 없음: {case_id}")


def main() -> int:
    p = argparse.ArgumentParser(description=__doc__)
    p.add_argument("jsonl", type=Path)
    args = p.parse_args()
    precedents = load_precedents(args.jsonl)
    validate_engine_labels(args.jsonl)
    print(json.dumps({"valid": True, "precedent_count": len(precedents)}, ensure_ascii=False))
    return 0


if __name__ == "__main__":
    raise SystemExit(main())