beige/backend/app/services/ai_engine/package_exporter.py

"""
package_exporter.py — 达人素材交付包生成
架构方案§五 1A步骤5：按笔记分文件夹 + 图(01/02/03) + 文案.txt + 发布清单 + 合规说明
路径规则：{UPLOAD_ABS_ROOT}/packages/{workspace_id}/{task_id}/note_{n}/
"""
from __future__ import annotations
import json
import logging
import os
import zipfile
from datetime import datetime
from pathlib import Path
from typing import Any

logger = logging.getLogger(__name__)

# 文件夹结构
# uploads/packages/{workspace_id}/{task_id}/
#   note_01/
#     01_hook.jpg   # 按 seq 序号命名防传错序
#     02_proof.jpg
#     文案.txt       # 标题 + 正文 + 标签
#   note_02/
#     ...
#   📋发布清单.txt
#   ✅合规说明.txt
#   package.zip    # 最终打包文件


def build_delivery_package(
    workspace_id: int,
    task_id: int,
    notes: list[dict],           # 每条笔记，含 text_candidate + image_candidates
    base_path: str = "uploads/packages",
) -> str:
    """
    打包交付，返回 zip 文件的本地路径。
    notes 格式：[{
        "title": str, "content": str, "tags": list[str],
        "images": [{"seq": int, "role": str, "data": bytes}],
        "banned_word_status": str,   # 合规说明用
    }]
    """
    package_dir = Path(base_path) / str(workspace_id) / str(task_id)
    package_dir.mkdir(parents=True, exist_ok=True)

    note_dirs: list[Path] = []
    for idx, note in enumerate(notes, start=1):
        note_dir = package_dir / f"note_{idx:02d}"
        note_dir.mkdir(exist_ok=True)
        note_dirs.append(note_dir)

        # ── 图片文件（按 seq 序号命名）
        for img in sorted(note.get("images", []), key=lambda x: x.get("seq", 0)):
            seq = img.get("seq", idx)
            role = img.get("role", "img")
            fname = f"{seq:02d}_{role}.jpg"
            img_data = img.get("data", b"")
            if img_data:
                (note_dir / fname).write_bytes(img_data)

        # ── 文案.txt（标题 + 正文 + 标签，达人可直接复制）
        tags = note.get("tags") or []
        body = note.get("content", "")
        # 正文末尾如果 LLM 已写入 #话题 标签，不再重复追加（避免重复）
        body_has_tags = bool(tags) and any(
            t.strip("#") in body for t in tags if t
        )
        copy_lines = [
            f"【标题】{note.get('title', '')}",
            "",
            body,
        ]
        if tags and not body_has_tags:
            copy_lines += ["", " ".join(tags)]
        (note_dir / "文案.txt").write_text("\n".join(copy_lines), encoding="utf-8")

    # ── 发布清单.txt
    checklist_lines = [
        "📋 发布清单",
        f"生成时间：{datetime.now().strftime('%Y-%m-%d %H:%M')}",
        f"任务ID：{task_id}",
        "",
    ]
    for idx, note in enumerate(notes, start=1):
        title = note.get("title", f"笔记{idx}")
        n_images = len(note.get("images", []))
        checklist_lines.append(f"note_{idx:02d}  标题：{title[:30]}  图片数：{n_images}")
    checklist_lines += [
        "",
        "发布注意事项：",
        "- 每条笔记图片按 01/02/03 顺序上传，避免传错序",
        "- 文案.txt 中标题/正文/标签已区分，复制对应部分",
        "- 品牌词已植入，请勿删除",
        "- 不要添加链接（种品牌词，引导天猫搜索成交）",
    ]
    (package_dir / "📋发布清单.txt").write_text("\n".join(checklist_lines), encoding="utf-8")

    # ── 合规说明.txt
    compliance_lines = [
        "✅ 合规说明",
        f"生成时间：{datetime.now().strftime('%Y-%m-%d %H:%M')}",
        "",
        "本批次内容已完成以下合规处理：",
        "1. 违禁词扫描（美白/祛斑/速效/医用/药妆等）",
        "2. 视觉违禁词处理（前后对比/变白等）",
        "3. 图片去水印处理（C2PA元数据已清除）",
        "",
        "各笔记合规状态：",
    ]
    for idx, note in enumerate(notes, start=1):
        status = note.get("banned_word_status", "pass")
        status_label = {"pass": "✅通过", "auto_fixed": "✅自动改写", "soft_warn": "⚠️软提示", "hard_block": "❌硬拦截"}.get(status, status)
        compliance_lines.append(f"note_{idx:02d}：{status_label}")
    compliance_lines += [
        "",
        "注：C2PA元数据可去除；私有像素水印只能削弱，不保证100%清除。",
        "如有合规疑问，请联系运营团队。",
    ]
    (package_dir / "✅合规说明.txt").write_text("\n".join(compliance_lines), encoding="utf-8")

    # ── 打 zip
    zip_path = package_dir / "package.zip"
    with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zf:
        for note_dir in note_dirs:
            for fpath in sorted(note_dir.iterdir()):
                zf.write(fpath, arcname=f"{note_dir.name}/{fpath.name}")
        zf.write(package_dir / "📋发布清单.txt", arcname="📋发布清单.txt")
        zf.write(package_dir / "✅合规说明.txt", arcname="✅合规说明.txt")

    logger.info("delivery package built: %s (notes=%d)", zip_path, len(notes))
    return str(zip_path)