beige/backend/app/workers/packaging_task.py

"""
app/workers/packaging_task.py — 交付打包 Celery 任务
build_delivery_package：查已选文案+图片 → package_exporter → 存路径
"""

import json
import logging

from app.workers.celery_app import celery_app

logger = logging.getLogger(__name__)


def _get_db():
    from app.core.database import SessionLocal
    return SessionLocal()


@celery_app.task(
    bind=True,
    name="app.workers.tasks.build_delivery_package",
    max_retries=2,
    default_retry_delay=10,
    queue="packaging",
)
def build_delivery_package(self, package_id: int) -> dict:
    """打包交付任务。查 delivery_packages → 收集笔记 → package_exporter"""
    logger.info("build_delivery_package start: package_id=%s", package_id)
    db = _get_db()
    try:
        from app.models.task import DeliveryPackage, TextCandidate, ImageCandidate
        from app.constants.enums import PackageStatus

        pkg = db.query(DeliveryPackage).filter(DeliveryPackage.id == package_id).first()
        if not pkg:
            raise ValueError(f"package_id={package_id} not found")

        workspace_id = pkg.workspace_id
        task_id = pkg.task_id

        from app.core.config import get_settings
        settings = get_settings()
        upload_base = settings.UPLOAD_BASE_PATH.rstrip("/")

        # A8 多套打包：按 strategy(A/B/C 三套正交叙事)分组，每套成一篇独立 note。
        # 北哥拿到的交付包含完整 3 套（note_01/02/03），不再只打第 1 条文案。
        selected_texts = db.query(TextCandidate).filter(
            TextCandidate.task_id == task_id, TextCandidate.is_selected == True,
        ).order_by(TextCandidate.id).all()
        if not selected_texts:
            raise ValueError("无已选文案，请先选择文案")

        # 整套全打：一套内全部图按 seq 排序进包，不只打封面。重生场景同 (strategy,seq)
        # 可能多条(新增不删旧)，去重取最新(id最大)，避免包内重复图。
        all_images = db.query(ImageCandidate).filter(
            ImageCandidate.task_id == task_id,
        ).order_by(ImageCandidate.strategy, ImageCandidate.seq).all()

        def _read_image(ic) -> dict:
            img_bytes = b""
            if ic.url:
                # url 已含 uploads 前缀；工作目录 /app，lstrip 当相对路径读，勿再拼 base(防 uploads/uploads)
                try:
                    with open(ic.url.lstrip("/"), "rb") as f:
                        img_bytes = f.read()
                except OSError as e:
                    logger.warning("图片读取失败，跳过：%s %s", ic.url, e)
            return {
                "seq": ic.seq,
                "role": ic.role.value if hasattr(ic.role, "value") else str(ic.role),
                "data": img_bytes,
            }

        # 按 strategy 分组（A/B/C；老数据 strategy=None 归一套，向后兼容）
        from collections import OrderedDict
        groups: "OrderedDict[str, dict]" = OrderedDict()
        for ic in all_images:
            slot = groups.setdefault(ic.strategy or "_", {})
            prev = slot.get(ic.seq)
            if prev is None or ic.id > prev.id:
                slot[ic.seq] = ic  # 同 seq 留最新

        # 文案按 strategy 建映射，供图片组按套精准配对（A8：文图同套对齐，不靠脆弱 idx）。
        # 同套多条选中取第 1 条；老数据 strategy=None 的归入 fallback 列表。
        texts_by_strategy: dict = {}
        texts_no_strategy: list = []
        for tc in selected_texts:
            if tc.strategy:
                texts_by_strategy.setdefault(tc.strategy, tc)
            else:
                texts_no_strategy.append(tc)
        _text_fallback = iter(texts_no_strategy or selected_texts)

        notes = []
        for idx, (_strategy, slot) in enumerate(groups.items()):
            images_data = [_read_image(slot[k]) for k in sorted(slot)]
            # 配对优先级：①同 strategy 文案精准对齐 ②无同套则按顺序取无套文案
            # ③再兜底用第 idx 条/第 1 条，确保每组图都有文案不漏。
            tc = texts_by_strategy.get(_strategy)
            if tc is None:
                tc = next(_text_fallback, None)
            if tc is None:
                tc = selected_texts[idx] if idx < len(selected_texts) else selected_texts[0]
            text_data = json.loads(tc.content or "{}")
            notes.append({
                "title": text_data.get("title", ""),
                "content": text_data.get("content", ""),
                "tags": text_data.get("tags", []),
                "images": images_data,
                "banned_word_status": (tc.banned_word_status.value
                                       if hasattr(tc.banned_word_status, "value")
                                       else str(tc.banned_word_status)),
            })
        if not notes:
            raise ValueError("无图片候选，无法打包")

        from app.services.ai_engine.package_exporter import build_delivery_package as do_build
        # 打包产物放专用目录 uploads/packages/，与图片目录 uploads/{ws}/{task}/ 分开
        packages_base = f"{upload_base}/packages"
        zip_path = do_build(workspace_id, task_id, notes, base_path=packages_base)

        pkg.package_path = zip_path
        pkg.download_url = f"/api/v1/delivery-packages/{package_id}/download-file"
        pkg.status = PackageStatus.READY
        db.commit()

        logger.info("delivery package ready: package_id=%s path=%s", package_id, zip_path)
        return {"package_id": package_id, "status": "ready", "path": zip_path}

    except Exception as exc:
        logger.error("build_delivery_package failed: package_id=%s err=%s", package_id, exc)
        raise self.retry(exc=exc)
    finally:
        db.close()