Audiolib/backend/app/routers/matching.py

import asyncio
import logging
from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy import select
from ..dependencies import get_db, get_current_user, require_admin
from ..models.user import User
from ..models.media_item import LibraryItem
from ..services.matcher import match_audiobook, search_for_item, _apply_match, _enrich_match
from ..services.matching.musicbrainz import get_release_details
from ..services.matching.open_library import get_work_details
from ..services.matching.base import MatchResult
from datetime import datetime

logger = logging.getLogger(__name__)

router = APIRouter(prefix="/api/items", tags=["matching"])


@router.post("/{item_id}/match")
async def trigger_match(
    item_id: str,
    background_tasks: BackgroundTasks,
    current_user: User = Depends(get_current_user),
    db: AsyncSession = Depends(get_db),
):
    result = await db.execute(select(LibraryItem).where(LibraryItem.id == item_id))
    item = result.scalar_one_or_none()
    if not item:
        raise HTTPException(status_code=404, detail="Item not found")

    background_tasks.add_task(match_audiobook, item_id)
    return {"message": "Matching gestartet", "itemId": item_id}


@router.get("/{item_id}/match/search")
async def search_match(
    item_id: str,
    q: str | None = None,
    current_user: User = Depends(get_current_user),
    db: AsyncSession = Depends(get_db),
):
    result = await db.execute(select(LibraryItem).where(LibraryItem.id == item_id))
    item = result.scalar_one_or_none()
    if not item:
        raise HTTPException(status_code=404, detail="Item not found")

    query = q or item.title or ""
    author = item.author if not q else None

    results = await search_for_item(query, author)
    return {"results": results}


@router.get("/match/connectivity")
async def check_connectivity(
    current_user: User = Depends(get_current_user),
):
    """Testet ob das Backend die externen Metadaten-APIs erreichen kann."""
    import httpx
    import time

    targets = [
        ("Google", "https://www.google.com"),
        ("MusicBrainz", "https://musicbrainz.org/ws/2/release?query=test&fmt=json&limit=1"),
        ("OpenLibrary", "https://openlibrary.org/search.json?title=test&limit=1"),
        ("GoogleBooks", "https://www.googleapis.com/books/v1/volumes?q=test&maxResults=1"),
        ("DNB", "https://services.dnb.de/sru/dnb?version=1.1&operation=searchRetrieve&query=tit%3Dtest&maximumRecords=1"),
    ]
    headers = {"User-Agent": "audiolib/1.0"}

    results = []
    async with httpx.AsyncClient(headers=headers, timeout=15, follow_redirects=True) as client:
        for name, url in targets:
            t0 = time.time()
            try:
                r = await client.get(url)
                results.append({
                    "name": name,
                    "url": url,
                    "ok": True,
                    "status": r.status_code,
                    "bytes": len(r.content),
                    "ms": int((time.time() - t0) * 1000),
                    "body_snippet": (r.text[:150] if r.status_code != 200 else None),
                })
            except Exception as e:
                results.append({
                    "name": name,
                    "url": url,
                    "ok": False,
                    "error": f"{type(e).__name__}: {e}",
                    "ms": int((time.time() - t0) * 1000),
                })

    # Auch Env-Variablen die httpx beeinflussen
    import os
    proxy_env = {
        k: v for k, v in os.environ.items()
        if k.upper() in ("HTTP_PROXY", "HTTPS_PROXY", "NO_PROXY", "ALL_PROXY")
    }

    return {
        "results": results,
        "proxy_env": proxy_env or "keine",
    }


@router.get("/match/debug")
async def debug_match(
    title: str,
    author: str | None = None,
    current_user: User = Depends(get_current_user),
):
    """Debug-Endpoint: gibt rohe Ergebnisse aller Such-Quellen zurück.
    Aufruf direkt aus Browser: /api/items/match/debug?title=Foo&author=Bar
    """
    from ..services.matching.musicbrainz import search_musicbrainz
    from ..services.matching.open_library import search_open_library
    from ..services.matching.google_books import search_google_books
    from ..services.matching.dnb import search_dnb
    from ..services.matcher import _build_search_title, detect_series, _strip_series_prefix

    series, episode = detect_series(title)
    if series and episode:
        search_title = f"{series} {episode}"
    elif series:
        cleaned = _build_search_title(title)
        search_title = _strip_series_prefix(cleaned, series)
    else:
        search_title = _build_search_title(title)

    logger.info(f"DEBUG: title={title!r} → search={search_title!r} series={series!r} episode={episode!r}")

    async def _try(name, coro):
        try:
            r = await coro
            return {
                "source": name,
                "ok": True,
                "count": len(r),
                "results": [
                    {
                        "title": x.title, "author": x.author, "narrator": x.narrator,
                        "publisher": x.publisher, "year": x.publish_year,
                        "series": x.series, "series_sequence": x.series_sequence,
                        "cover_url": x.cover_url, "language": x.language,
                        "genres": x.genres, "description": (x.description or "")[:200],
                        "confidence": x.confidence, "source_id": x.source_id,
                    } for x in r
                ],
            }
        except Exception as e:
            return {"source": name, "ok": False, "error": f"{type(e).__name__}: {e}"}

    results = await asyncio.gather(
        _try("musicbrainz", search_musicbrainz(search_title, author)),
        _try("open_library", search_open_library(search_title, author)),
        _try("google_books", search_google_books(search_title, author)),
        _try("dnb", search_dnb(search_title, author)),
    )

    return {
        "input": {"title": title, "author": author},
        "normalized": {"search_title": search_title, "series": series, "episode": episode},
        "sources": results,
    }


@router.post("/{item_id}/match/apply")
async def apply_match(
    item_id: str,
    body: dict,
    current_user: User = Depends(get_current_user),
    db: AsyncSession = Depends(get_db),
):
    """
    Wendet einen manuell gewählten Match-Treffer an.
    body: { source, id, title, author, narrator, description, publisher, publishYear, series, seriesSequence, language, genres, cover, ... }
    """
    result = await db.execute(select(LibraryItem).where(LibraryItem.id == item_id))
    item = result.scalar_one_or_none()
    if not item:
        raise HTTPException(status_code=404, detail="Item not found")

    source = body.get("source", "manual")
    source_id = body.get("id", "")

    logger.info(
        f"Manual apply: item={item_id} source={source} source_id={source_id} "
        f"body_keys={sorted(body.keys())}"
    )

    # Immer aus body konstruieren (search_for_item liefert jetzt alle Felder)
    match_result = MatchResult(
        source=source,
        source_id=source_id,
        title=body.get("title") or item.title or "",
        subtitle=body.get("subtitle"),
        author=body.get("author"),
        narrator=body.get("narrator"),
        description=body.get("description"),
        publisher=body.get("publisher"),
        publish_year=body.get("publishYear"),
        series=body.get("series"),
        series_sequence=body.get("seriesSequence"),
        language=body.get("language"),
        genres=body.get("genres") or [],
        cover_url=body.get("cover"),
        confidence=1.0,
    )

    # Mit Details anreichern (Beschreibung, Kapitel) — überschreibt keine vorhandenen Werte
    try:
        if source == "musicbrainz":
            details = await get_release_details(source_id)
            if details:
                _enrich_match(match_result, details)
        elif source == "open_library":
            details = await get_work_details(source_id)
            if details:
                _enrich_match(match_result, details)
    except Exception as e:
        logger.warning(f"Details-Laden fehlgeschlagen ({source}: {source_id}): {e}")

    match_result.confidence = 1.0
    await _apply_match(db, item, match_result, confidence=1.0)
    item.match_locked = True
    item.updated_at = datetime.utcnow()
    await db.commit()
    await db.refresh(item)

    from ..routers.items import _enrich_item_with_files
    return await _enrich_item_with_files(item, db)


@router.post("/{item_id}/extract-tags")
async def extract_audio_tags(
    item_id: str,
    current_user: User = Depends(get_current_user),
    db: AsyncSession = Depends(get_db),
):
    """Liest ID3-Tags aus der ersten Audio-Datei und füllt leere Metadaten."""
    from ..services.scanner import _extract_audio_tags, _apply_tags_to_item, _series_from_parent
    from ..models.media_item import BookFile
    from ..models.library import Library

    result = await db.execute(select(LibraryItem).where(LibraryItem.id == item_id))
    item = result.scalar_one_or_none()
    if not item:
        raise HTTPException(status_code=404, detail="Item not found")

    lib_result = await db.execute(select(Library).where(Library.id == item.library_id))
    lib = lib_result.scalar_one_or_none()
    library_folders = lib.folders if lib else []

    files_result = await db.execute(
        select(BookFile).where(BookFile.library_item_id == item_id).order_by(BookFile.track_index)
    )
    files = files_result.scalars().all()
    if not files:
        return {"success": False, "message": "Keine Audio-Dateien"}

    tags = _extract_audio_tags(files[0].path)
    parent_series = _series_from_parent(item.path, library_folders)
    before = {
        "title": item.title, "author": item.author, "publisher": item.publisher,
        "publish_year": item.publish_year, "series": item.series, "genres": item.genres,
    }
    _apply_tags_to_item(item, tags, parent_series)
    item.updated_at = datetime.utcnow()
    await db.commit()
    after = {
        "title": item.title, "author": item.author, "publisher": item.publisher,
        "publish_year": item.publish_year, "series": item.series, "genres": item.genres,
    }
    logger.info(f"Tags extrahiert für {item_id}: tags={list(tags.keys())} before={before} after={after}")
    return {"success": True, "tags": tags, "before": before, "after": after}


@router.post("/{item_id}/extract-cover")
async def extract_local_cover(
    item_id: str,
    current_user: User = Depends(get_current_user),
    db: AsyncSession = Depends(get_db),
):
    """Extrahiert ein Cover aus Ordner-Dateien oder eingebettetem Artwork."""
    from ..services.scanner import _save_local_cover
    from ..models.media_item import BookFile
    import os

    result = await db.execute(select(LibraryItem).where(LibraryItem.id == item_id))
    item = result.scalar_one_or_none()
    if not item:
        raise HTTPException(status_code=404, detail="Item not found")

    files_result = await db.execute(
        select(BookFile).where(BookFile.library_item_id == item_id).order_by(BookFile.track_index)
    )
    audio_files = [f.path for f in files_result.scalars().all()]

    cover = _save_local_cover(item.path, audio_files, item.id)
    if cover:
        item.cover_path = cover
        item.updated_at = datetime.utcnow()
        await db.commit()
        logger.info(f"Lokales Cover gesetzt für {item_id}: {cover}")
        return {"success": True, "cover_path": cover}
    return {"success": False, "message": "Kein Cover gefunden"}


@router.delete("/{item_id}/match")
async def clear_match(
    item_id: str,
    current_user: User = Depends(get_current_user),
    db: AsyncSession = Depends(get_db),
):
    result = await db.execute(select(LibraryItem).where(LibraryItem.id == item_id))
    item = result.scalar_one_or_none()
    if not item:
        raise HTTPException(status_code=404, detail="Item not found")

    item.matched_source = "none"
    item.matched_id = None
    item.match_confidence = 0.0
    item.match_locked = False
    tags = item.tags or []
    if "zu_prüfen" not in tags:
        tags.append("zu_prüfen")
    item.tags = tags
    item.updated_at = datetime.utcnow()
    await db.commit()
    return {"success": True}