"""Grounding check — post-synthesis 검증 (Phase 3.5a).

Strong/weak flag 분리:
- **Strong** (→ partial 강등 or refuse): fabricated_number, intent_misalignment(important)
- **Weak** (→ confidence lower only): uncited_claim, low_overlap, intent_misalignment(generic)

Re-gate 로직 (Phase 3.5a 9라운드 토론 결과):
- strong 1개 → partial 강등
- strong 2개 이상 → refuse
- weak → confidence "low" 만

Intent alignment (rule-based):
- query 의 핵심 명사가 answer 에 등장하는지 확인
- "처벌" 같은 중요 키워드 누락은 strong
- "주요", "관련" 같은 generic 은 무시
"""

from __future__ import annotations

import re
from dataclasses import dataclass
from typing import TYPE_CHECKING

from core.utils import setup_logger

if TYPE_CHECKING:
    from .evidence_service import EvidenceItem

logger = setup_logger("grounding")

# "주요", "관련" 등 intent alignment 에서 제외할 generic 단어
GENERIC_TERMS = frozenset({
    "주요", "관련", "내용", "정의", "기준", "방법", "설명", "개요",
    "대한", "위한", "대해", "무엇", "어떤", "어떻게", "있는",
    "하는", "되는", "이런", "그런", "이것", "그것",
})


@dataclass(slots=True)
class GroundingResult:
    strong_flags: list[str]
    weak_flags: list[str]


def _extract_number_literals(text: str) -> set[str]:
    """숫자 + 단위 추출 + normalize."""
    raw = set(re.findall(r'\d[\d,.]*\s*[명인개%년월일조항호세]\w{0,2}', text))
    normalized = set()
    for r in raw:
        normalized.add(r.strip())
        num_only = re.match(r'[\d,.]+', r)
        if num_only:
            normalized.add(num_only.group().replace(',', ''))
    # 단독 숫자도 추출
    for d in re.findall(r'\b\d+\b', text):
        normalized.add(d)
    return normalized


def _extract_content_tokens(text: str) -> set[str]:
    """한국어 2자 이상 명사 + 영어 3자 이상 단어."""
    return set(re.findall(r'[가-힣]{2,}|[a-zA-Z]{3,}', text))


def check(
    query: str,
    answer: str,
    evidence: list[EvidenceItem],
) -> GroundingResult:
    """답변 vs evidence grounding 검증 + query intent alignment."""
    strong: list[str] = []
    weak: list[str] = []

    if not answer or not evidence:
        return GroundingResult([], [])

    evidence_text = " ".join(e.span_text for e in evidence)

    # ── Strong 1: fabricated number (equality, not substring) ──
    # ⚠ citation marker [n] 제거 후 숫자 추출 (안 그러면 [1][2][3] 이 fabricated 로 오탐)
    answer_clean = re.sub(r'\[\d+\]', '', answer)
    answer_nums = _extract_number_literals(answer_clean)
    evidence_nums = _extract_number_literals(evidence_text)
    evidence_digits = {re.sub(r'[^\d]', '', en) for en in evidence_nums}
    evidence_digits.discard('')
    for num in answer_nums:
        digits_only = re.sub(r'[^\d]', '', num)
        if digits_only and digits_only not in evidence_digits:
            strong.append(f"fabricated_number:{num}")

    # ── Strong/Weak 2: query-answer intent alignment ──
    query_content = _extract_content_tokens(query)
    answer_content = _extract_content_tokens(answer)
    if query_content:
        missing_terms = query_content - answer_content
        important_missing = [
            t for t in missing_terms
            if t not in GENERIC_TERMS and len(t) >= 2
        ]
        if important_missing:
            strong.append(
                f"intent_misalignment:{','.join(important_missing[:3])}"
            )
        elif len(missing_terms) > len(query_content) * 0.5:
            weak.append(
                f"intent_misalignment_generic:"
                f"missing({','.join(list(missing_terms)[:5])})"
            )

    # ── Weak 1: uncited claim ──
    sentences = re.split(r'(?<=[.!?。])\s+', answer)
    for s in sentences:
        if len(s.strip()) > 20 and not re.search(r'\[\d+\]', s):
            weak.append(f"uncited_claim:{s[:40]}")

    # ── Weak 2: token overlap ──
    answer_tokens = _extract_content_tokens(answer)
    evidence_tokens = _extract_content_tokens(evidence_text)
    if answer_tokens:
        overlap = len(answer_tokens & evidence_tokens) / len(answer_tokens)
        if overlap < 0.4:
            weak.append(f"low_overlap:{overlap:.2f}")

    if strong or weak:
        logger.info(
            "grounding query=%r strong=%d weak=%d flags=%s",
            query[:60],
            len(strong),
            len(weak),
            ",".join(strong[:3] + weak[:3]),
        )

    return GroundingResult(strong, weak)