"""텍스트 추출 워커 — kordoc / PyMuPDF / Surya OCR / LibreOffice / 직접 읽기 / 웹 HTML"""

import hashlib
import re
import subprocess
from datetime import datetime, timezone
from pathlib import Path

import httpx
from sqlalchemy.ext.asyncio import AsyncSession

from core.config import settings
from core.utils import setup_logger
from models.document import Document

logger = setup_logger("extract_worker")

# kordoc으로 파싱 가능한 포맷
KORDOC_FORMATS = {"hwp", "hwpx", "pdf"}
# 직접 읽기 가능한 텍스트 포맷
TEXT_FORMATS = {"md", "txt", "csv", "json", "xml", "html"}
# LibreOffice로 텍스트 추출 가능한 포맷
OFFICE_FORMATS = {"xlsx", "xls", "docx", "doc", "pptx", "ppt", "odt", "ods", "odp", "odoc", "osheet"}
# OCR 대상 이미지 포맷
IMAGE_FORMATS = {"jpg", "jpeg", "png", "tiff", "tif", "bmp", "gif", "webp"}

EXTRACTOR_VERSION = "kordoc@1.7"
PYMUPDF_VERSION = "pymupdf"


# ─── OCR 판정 함수 ───

def _should_ocr(text: str, page_count: int) -> tuple[bool, str]:
    """텍스트 추출 결과로 OCR 필요 여부 판정 — 2단계"""
    total = len(text.strip())
    if total < 300:
        return True, "no_text_layer"
    avg = total / max(page_count, 1)
    if avg < 80 and total < 3000:
        return True, "low_text_density"
    return False, ""


def _ocr_skip_reason(file_size: int, page_count: int) -> str | None:
    """OCR 상한 체크"""
    if page_count > 200:
        return "page_limit"
    if file_size > 150 * 1024 * 1024:
        return "size_limit"
    return None


def _ocr_quality_ok(text: str, page_count: int, is_image: bool) -> bool:
    """OCR 결과 품질 검증 — 유형별 차등"""
    chars = len(text.strip())
    if is_image:
        return chars >= 50
    if page_count > 0:
        return chars >= 200 or (chars / max(page_count, 1)) >= 30
    return chars >= 200


def _postprocess_ocr(text: str) -> str:
    """OCR 후처리 — NUL 제거 + 과도한 공백 정리"""
    text = text.replace("\x00", "")
    text = re.sub(r'\s{3,}', '\n', text)
    return text.strip()


def _extract_pdf_pymupdf(
    file_path: Path, start_page: int | None = None, end_page: int | None = None
) -> str:
    """PyMuPDF fallback — 페이지 단위 스트리밍으로 대형 PDF도 저메모리 처리.

    G2 (PR-G2-2): start_page/end_page(1-based inclusive) 가 주어지면 그 범위만 추출
    (번들 자식 doc = 부모 파일 공유 + 자기 page 범위). 둘 다 None = 전체(기존 동작 동일).
    """
    import fitz
    text_parts = []
    with fitz.open(str(file_path)) as doc:
        if start_page is None and end_page is None:
            for page in doc:
                text_parts.append(page.get_text())
        else:
            # 1-based inclusive → 0-based range. 범위는 [0, page_count] 로 클램프(방어).
            total = doc.page_count
            lo = max(1, start_page or 1) - 1
            hi = min(total, end_page or total)        # inclusive 끝 (0-based 마지막 인덱스 = hi-1)
            for i in range(lo, hi):
                text_parts.append(doc.load_page(i).get_text())
    return "\n".join(text_parts)


def _get_pdf_page_count(
    file_path: Path, start_page: int | None = None, end_page: int | None = None
) -> int:
    """PDF 페이지 수 확인. G2: 범위가 주어지면 그 범위의 페이지 수(자식 doc 밀도 계산용).

    둘 다 None = 전체 페이지 수(기존 동작 동일).
    """
    import fitz
    with fitz.open(str(file_path)) as doc:
        total = len(doc)
        if start_page is None and end_page is None:
            return total
        lo = max(1, start_page or 1)
        hi = min(total, end_page or total)
        return max(0, hi - lo + 1)


async def _call_ocr(file_path: Path, is_image: bool, max_pages: int = 200) -> str | None:
    """OCR 서비스 호출 — 타임아웃 페이지 수 비례"""
    container_path = f"/documents/{file_path.relative_to(Path(settings.nas_mount_path))}"
    timeout = 60 if is_image else min(600, max(120, max_pages * 3))
    try:
        async with httpx.AsyncClient(timeout=timeout) as client:
            resp = await client.post(
                f"{settings.ocr_endpoint}/ocr",
                json={"filePath": container_path, "langs": ["ko", "en"], "maxPages": max_pages},
            )
        if resp.status_code == 200:
            data = resp.json()
            return data.get("text", "")
    except Exception as e:
        logger.error(f"[ocr] OCR 서비스 호출 실패: {e}")
    return None


# ─── Web/Blog ingest (devonagent 트랙) — HTML → markdown 4-tier ────────────

_WEB_MIN_BODY_LEN = 200  # 4-tier fallback 전환 임계


def _extract_web_with_trafilatura(html: str) -> tuple[str, str | None]:
    """trafilatura 로 본문 markdown 추출. (body, engine_version) 반환. 실패 시 ("", None)."""
    try:
        import trafilatura
    except ImportError:
        logger.warning("[web] trafilatura 미설치 — 다음 fallback 시도")
        return "", None
    try:
        body = trafilatura.extract(
            html,
            output_format="markdown",
            include_comments=False,
            include_tables=True,
            with_metadata=True,
            deduplicate=True,
            favor_precision=True,
        )
        return (body or "", getattr(trafilatura, "__version__", "unknown"))
    except Exception as e:
        logger.warning(f"[web] trafilatura 실패: {e}")
        return "", None


def _extract_web_with_readability(html: str) -> tuple[str, str | None]:
    """readability-lxml 로 본문 추출 + markdownify 로 markdown 변환."""
    try:
        from readability import Document as ReadabilityDocument
        from markdownify import markdownify
    except ImportError:
        logger.warning("[web] readability/markdownify 미설치 — 다음 fallback 시도")
        return "", None
    try:
        rd = ReadabilityDocument(html)
        body_html = rd.summary() or ""
        if not body_html:
            return "", None
        body_md = markdownify(body_html, heading_style="ATX")
        return (body_md or "", "readability+markdownify")
    except Exception as e:
        logger.warning(f"[web] readability 실패: {e}")
        return "", None


def _extract_web_with_bs4(html: str) -> tuple[str, str | None]:
    """최종 fallback — BeautifulSoup 으로 script/style 제거 후 get_text."""
    try:
        from bs4 import BeautifulSoup
    except ImportError:
        logger.warning("[web] beautifulsoup4 미설치 — 빈 본문 반환")
        return "", None
    try:
        soup = BeautifulSoup(html, "lxml")
        for tag in soup(["script", "style", "noscript", "nav", "footer", "aside"]):
            tag.decompose()
        text = soup.get_text(" ", strip=True)
        return (text or "", "bs4_text")
    except Exception as e:
        logger.warning(f"[web] bs4 실패: {e}")
        return "", None


async def _extract_web_html(doc: Document, html_path: Path) -> None:
    """devonagent HTML → markdown 4-tier fallback. md_* 컬럼 전체 채움."""
    html_bytes = html_path.read_bytes()
    html_text = html_bytes.decode("utf-8", errors="replace")
    src_hash = hashlib.sha256(html_bytes).hexdigest()

    # 1) trafilatura
    body, engine_ver = _extract_web_with_trafilatura(html_text)
    engine = "trafilatura" if body and len(body) >= _WEB_MIN_BODY_LEN else None

    # 2) sibling .md (DEVONthink rendered)
    if not engine:
        md_path = html_path.with_suffix(".md")
        if md_path.is_file():
            try:
                md_body = md_path.read_text(encoding="utf-8", errors="replace")
                if md_body and len(md_body) >= _WEB_MIN_BODY_LEN:
                    body = md_body
                    engine = "devonthink_export"
                    engine_ver = "smart_rule"
            except Exception as e:
                logger.warning(f"[web] sibling .md 읽기 실패 {md_path}: {e}")

    # 3) readability + markdownify
    if not engine:
        body2, ver2 = _extract_web_with_readability(html_text)
        if body2 and len(body2) >= _WEB_MIN_BODY_LEN:
            body = body2
            engine = "readability"
            engine_ver = ver2

    # 4) bs4 get_text (최종 fallback)
    if not engine:
        body3, ver3 = _extract_web_with_bs4(html_text)
        if body3:
            body = body3
            engine = "bs4_text"
            engine_ver = ver3
        else:
            body = ""
            engine = "empty"
            engine_ver = None

    clean_body = (body or "").replace("\x00", "")
    now = datetime.now(timezone.utc)

    doc.extracted_text = clean_body
    doc.extracted_at = now
    doc.extractor_version = f"web@{engine}"
    doc.md_content = clean_body
    doc.md_status = "success" if clean_body else "failed"
    doc.md_extraction_engine = engine
    doc.md_extraction_engine_version = engine_ver
    doc.md_format_version = "1.0"
    doc.md_generated_at = now
    doc.md_source_hash = src_hash
    doc.md_content_hash = hashlib.sha256(clean_body.encode("utf-8")).hexdigest()
    doc.content_origin = "extracted"

    # extract_meta 의 web_meta 는 file_watcher 가 박은 그대로 유지 (sidecar 출처)
    logger.info(
        f"[web/{engine}] {doc.file_path} ({len(clean_body)}자, engine_ver={engine_ver})"
    )


# ─── 메인 처리 ───

async def process(document_id: int, session: AsyncSession) -> None:
    """문서 텍스트 추출"""
    doc = await session.get(Document, document_id)
    if not doc:
        raise ValueError(f"문서 ID {document_id}를 찾을 수 없음")

    fmt = doc.file_format.lower()
    full_path = Path(settings.nas_mount_path) / doc.file_path

    # ─── Web/Blog ingest (devonagent 트랙) — HTML 본문 정화 4-tier fallback ───
    # plan: ~/.claude/plans/db-snuggly-petal.md
    # 1) trafilatura (markdown body)
    # 2) sibling .md (DEVONthink rendered, >= 200 char)
    # 3) readability-lxml + markdownify
    # 4) BeautifulSoup get_text
    # md_extraction_engine 으로 어느 경로로 추출됐는지 기록 → 품질 모니터링용
    if fmt == "html" and doc.source_channel == "devonagent":
        if not full_path.exists():
            raise FileNotFoundError(f"파일 없음: {full_path}")
        await _extract_web_html(doc, full_path)
        return

    # ─── 텍스트 파일 — 직접 읽기 ───
    if fmt in TEXT_FORMATS:
        if not full_path.exists():
            raise FileNotFoundError(f"파일 없음: {full_path}")
        text = full_path.read_text(encoding="utf-8", errors="replace")
        doc.extracted_text = text.replace("\x00", "")
        doc.extracted_at = datetime.now(timezone.utc)
        doc.extractor_version = "direct_read"
        logger.info(f"[텍스트] {doc.file_path} ({len(text)}자)")
        return

    # ─── 이미지 — OCR ───
    if fmt in IMAGE_FORMATS:
        meta = doc.extract_meta or {}

        # OCR 1회 제한
        if meta.get("ocr_attempted"):
            meta["ocr_skip_reason"] = "already_attempted"
            doc.extract_meta = meta
            logger.info(f"[이미지] {doc.file_path} — OCR 이미 시도됨, 스킵")
            return

        # 상한 체크
        skip = _ocr_skip_reason(doc.file_size or 0, 1)
        if skip:
            doc.extracted_text = ""
            doc.extractor_version = None
            doc.extract_meta = {**meta, "ocr_skip_reason": skip, "ocr_terminal": True}
            doc.extracted_at = datetime.now(timezone.utc)
            logger.warning(f"[이미지] {doc.file_path} — OCR 스킵 ({skip})")
            return

        # OCR 서비스 호출
        ocr_text = await _call_ocr(full_path, is_image=True)
        meta["ocr_attempted"] = True
        meta["ocr_reason"] = "image_file"

        if ocr_text and _ocr_quality_ok(ocr_text, 1, is_image=True):
            doc.extracted_text = _postprocess_ocr(ocr_text)
            doc.extractor_version = "surya_ocr"
            meta["ocr_chars"] = len(doc.extracted_text)
            logger.info(f"[surya_ocr] {doc.file_path} ({len(doc.extracted_text)}자)")
        else:
            doc.extracted_text = ""
            doc.extractor_version = None
            meta["ocr_quality_ok"] = False
            meta["ocr_terminal"] = True
            logger.warning(f"[이미지] {doc.file_path} — OCR 결과 품질 미달")

        doc.extract_meta = meta
        doc.extracted_at = datetime.now(timezone.utc)
        return

    # ─── G2 (PR-G2-2): 번들 자식 PDF — 부모 파일 공유 + 자기 page 범위만 추출 ───
    # kordoc 서비스는 page-range 파라미터가 없어 전체 파일을 파싱한다(자식엔 부적합) → kordoc
    # 우회, PyMuPDF 로 [bundle_page_start, bundle_page_end] 범위만 추출. range OCR 은 본 PR 범위
    # 밖(자식은 ToC 존재 = digital text layer 전제 → 대개 OCR 불필요). PyMuPDF 텍스트가 빈약해도
    # 그대로 보존하고 사유를 남긴다.
    if fmt == "pdf" and doc.bundle_page_start is not None and doc.bundle_page_end is not None:
        # 후보 A: 자식 file_path 는 합성값(`{부모}#p{s}-{e}`) → 실파일 = bundle_source_path 로 부모경로
        # 복원 + NFC/NFD resolve. (자식 file_path 는 디스크에 없음.)
        from workers.presegment_worker import _resolve_path as _resolve_bundle_path
        from workers.presegment_worker import bundle_source_path
        real_rel = bundle_source_path(doc.file_path)
        src = _resolve_bundle_path(str(Path(settings.nas_mount_path) / real_rel))
        if src is None:
            raise FileNotFoundError(f"번들 원본 파일 없음: {real_rel}")
        start, end = doc.bundle_page_start, doc.bundle_page_end
        try:
            pymupdf_text = _extract_pdf_pymupdf(src, start, end)
            page_count = _get_pdf_page_count(src, start, end)
        except Exception as e:
            logger.error(f"[pymupdf:child] {doc.file_path} pages={start}-{end} 실패: {e}")
            raise

        meta = doc.extract_meta or {}
        meta["presegment_child_range"] = {"start_page": start, "end_page": end}
        meta["pymupdf_chars"] = len(pymupdf_text.strip())
        should, reason = _should_ocr(pymupdf_text, page_count)
        if should:
            # range OCR 미지원(후속 PR) — PyMuPDF 결과 유지 + 사유 기록(silent skip 아님).
            meta["ocr_skip_reason"] = "presegment_child_range_ocr_unsupported"
            meta["ocr_reason"] = reason
            logger.warning(
                f"[pymupdf:child] {doc.file_path} pages={start}-{end} "
                f"OCR 필요({reason})하나 range OCR 미지원 → PyMuPDF 결과 유지"
            )
        doc.extracted_text = pymupdf_text.replace("\x00", "")
        doc.extracted_at = datetime.now(timezone.utc)
        doc.extractor_version = PYMUPDF_VERSION if pymupdf_text.strip() else None
        doc.extract_meta = meta
        logger.info(
            f"[pymupdf:child] {doc.file_path} pages={start}-{end} ({len(pymupdf_text)}자)"
        )
        return

    # ─── kordoc 파싱 (HWP/HWPX/PDF) + PyMuPDF fallback + OCR ───
    if fmt in KORDOC_FORMATS:
        container_path = f"/documents/{doc.file_path}"
        kordoc_timeout = min(300, max(60, (doc.file_size or 0) // (10 * 1024 * 1024) * 60 + 60))

        kordoc_ok = False
        try:
            async with httpx.AsyncClient(timeout=kordoc_timeout) as client:
                resp = await client.post(
                    f"{settings.kordoc_endpoint}/parse",
                    json={"filePath": container_path},
                )

            if resp.status_code == 404:
                raise FileNotFoundError(f"kordoc: 파일 없음 — {container_path}")

            if resp.status_code == 200:
                data = resp.json()
                text = data.get("markdown", "").replace("\x00", "")
                if text:
                    doc.extracted_text = text
                    doc.extracted_at = datetime.now(timezone.utc)
                    doc.extractor_version = EXTRACTOR_VERSION
                    logger.info(f"[kordoc] {doc.file_path} ({len(text)}자)")
                    kordoc_ok = True

        except FileNotFoundError:
            raise
        except Exception as e:
            logger.warning(f"[kordoc] {doc.file_path} 실패 ({e.__class__.__name__}), fallback 시도")

        if kordoc_ok:
            return

        # ─── PyMuPDF fallback (PDF만) ───
        if fmt == "pdf" and full_path.exists():
            try:
                pymupdf_text = _extract_pdf_pymupdf(full_path)
                page_count = _get_pdf_page_count(full_path)
            except Exception as e:
                logger.error(f"[pymupdf] {doc.file_path} 실패: {e}")
                pymupdf_text = ""
                page_count = 0

            meta = doc.extract_meta or {}
            meta["pymupdf_chars"] = len(pymupdf_text.strip())

            # PyMuPDF 텍스트 충분 여부 판정
            should, reason = _should_ocr(pymupdf_text, page_count)

            if not should:
                # PyMuPDF 텍스트 충분 → OCR 불필요
                doc.extracted_text = pymupdf_text.replace("\x00", "")
                doc.extracted_at = datetime.now(timezone.utc)
                doc.extractor_version = PYMUPDF_VERSION
                doc.extract_meta = meta
                logger.info(f"[pymupdf] {doc.file_path} ({len(pymupdf_text)}자)")
                return

            # ─── OCR 필요 ───

            # OCR 1회 제한
            if meta.get("ocr_attempted"):
                doc.extracted_text = pymupdf_text.replace("\x00", "") or ""
                doc.extracted_at = datetime.now(timezone.utc)
                doc.extractor_version = "pymupdf" if pymupdf_text.strip() else None
                meta["ocr_skip_reason"] = "already_attempted"
                doc.extract_meta = meta
                logger.info(f"[pdf] {doc.file_path} — OCR 이미 시도됨, PyMuPDF 결과 유지")
                return

            # 상한 체크
            skip = _ocr_skip_reason(doc.file_size or 0, page_count)
            if skip:
                doc.extracted_text = pymupdf_text.replace("\x00", "") or ""
                doc.extracted_at = datetime.now(timezone.utc)
                doc.extractor_version = "pymupdf" if pymupdf_text.strip() else None
                doc.extract_meta = {**meta, "ocr_skip_reason": skip, "ocr_terminal": not pymupdf_text.strip()}
                logger.warning(f"[pdf] {doc.file_path} — OCR 스킵 ({skip}), PyMuPDF 결과 유지")
                return

            # OCR 서비스 호출
            meta["ocr_attempted"] = True
            meta["ocr_reason"] = reason
            logger.info(f"[pdf] {doc.file_path} — OCR 시도 (reason={reason}, pages={page_count})")

            ocr_text = await _call_ocr(full_path, is_image=False, max_pages=min(page_count, 200))

            if ocr_text and _ocr_quality_ok(ocr_text, page_count, is_image=False):
                doc.extracted_text = _postprocess_ocr(ocr_text)
                doc.extractor_version = "surya_ocr"
                meta["ocr_chars"] = len(doc.extracted_text)
                logger.info(f"[surya_ocr] {doc.file_path} ({len(doc.extracted_text)}자)")
            else:
                # OCR 실패 → PyMuPDF 텍스트라도 보존
                doc.extracted_text = pymupdf_text.replace("\x00", "") or ""
                doc.extractor_version = "pymupdf" if pymupdf_text.strip() else None
                meta["ocr_quality_ok"] = False
                if not pymupdf_text.strip():
                    meta["ocr_terminal"] = True
                logger.warning(f"[pdf] {doc.file_path} — OCR 결과 품질 미달, PyMuPDF 결과 유지")

            doc.extract_meta = meta
            doc.extracted_at = datetime.now(timezone.utc)
            return

        # HWP/HWPX는 kordoc 전용 — fallback 없음
        if fmt != "pdf":
            raise ValueError(f"kordoc 파싱 실패 (HWP/HWPX는 fallback 없음)")
        raise ValueError(f"PDF 텍스트 추출 실패 — kordoc + PyMuPDF 모두 실패")

    # ─── 오피스 포맷 — LibreOffice 텍스트 변환 ───
    if fmt in OFFICE_FORMATS:
        if not full_path.exists():
            raise FileNotFoundError(f"파일 없음: {full_path}")

        import shutil
        tmp_dir = Path("/tmp/extract_work")
        tmp_dir.mkdir(exist_ok=True)

        tmp_input = tmp_dir / f"input_{document_id}.{fmt}"
        shutil.copy2(str(full_path), str(tmp_input))

        CALC_FORMATS = {"xlsx", "xls", "ods", "osheet"}
        if fmt in CALC_FORMATS:
            convert_to = "csv:Text - txt - csv (StarCalc):44,34,76,1"
            out_ext = "csv"
        else:
            convert_to = "txt:Text"
            out_ext = "txt"

        try:
            result = subprocess.run(
                ["libreoffice", "--headless", "--convert-to", convert_to, "--outdir", str(tmp_dir), str(tmp_input)],
                capture_output=True, text=True, timeout=60,
            )
            out_file = tmp_dir / f"input_{document_id}.{out_ext}"
            if out_file.exists():
                text = out_file.read_text(encoding="utf-8", errors="replace")
                # 설계 원칙: extract는 전체 텍스트 저장. classify/summarize가 자체 상한으로 slice.
                doc.extracted_text = text.replace("\x00", "")
                doc.extracted_at = datetime.now(timezone.utc)
                doc.extractor_version = "libreoffice"
                out_file.unlink()
                logger.info(f"[LibreOffice] {doc.file_path} ({len(text)}자)")
            else:
                raise RuntimeError(f"LibreOffice 변환 실패: {result.stderr[:300]}")
        except subprocess.TimeoutExpired:
            raise RuntimeError(f"LibreOffice 텍스트 추출 timeout (60s)")
        finally:
            tmp_input.unlink(missing_ok=True)

        # ─── ODF 변환 (편집용) ───
        CONVERT_MAP = {
            'xlsx': 'ods', 'xls': 'ods',
            'docx': 'odt', 'doc': 'odt',
            'pptx': 'odp', 'ppt': 'odp',
        }
        target_fmt = CONVERT_MAP.get(fmt)
        if target_fmt:
            try:
                derived_dir = full_path.parent / ".derived"
                derived_dir.mkdir(exist_ok=True)
                tmp_input2 = tmp_dir / f"convert_{document_id}.{fmt}"
                shutil.copy2(str(full_path), str(tmp_input2))

                conv_result = subprocess.run(
                    ["libreoffice", "--headless", "--convert-to", target_fmt, "--outdir", str(tmp_dir), str(tmp_input2)],
                    capture_output=True, text=True, timeout=60,
                )
                tmp_input2.unlink(missing_ok=True)

                conv_file = tmp_dir / f"convert_{document_id}.{target_fmt}"
                if conv_file.exists():
                    final_path = derived_dir / f"{document_id}.{target_fmt}"
                    shutil.move(str(conv_file), str(final_path))

                    nas_root = Path(settings.nas_mount_path)
                    doc.derived_path = str(final_path.relative_to(nas_root))
                    doc.original_format = doc.file_format
                    doc.conversion_status = "done"
                    logger.info(f"[ODF변환] {doc.file_path} → derived: {doc.derived_path}")
                else:
                    doc.conversion_status = "failed"
                    logger.warning(f"[ODF변환] 실패: {conv_result.stderr[:200]}")
            except Exception as e:
                doc.conversion_status = "failed"
                logger.error(f"[ODF변환] {doc.file_path} 에러: {e}")
        else:
            doc.conversion_status = "none"

        return

    # ─── 미지원 포맷 ───
    doc.extracted_text = ""
    doc.extracted_at = datetime.now(timezone.utc)
    doc.extractor_version = f"unsupported_{fmt}"
    logger.warning(f"[미지원] {doc.file_path} (format={fmt})")