feat: 新增 PDF 转换服务(epub->pdf,cookie 用户隔离,软删/硬删两级删除)

纯 Python 转换(ebooklib 解析 epub + weasyprint 渲染 HTML/CSS 为 PDF),
无需 calibre/xvfb 系统依赖。复用 UploadedFile 存储(原始文件与产物 PDF)。

- model/dao/schema:PdfJob 记录转换任务(owner_cookie/source/output/进度/状态)
- pdf_converter:epub->PDF 转换器(按 spine 顺序拼 HTML,OPF 目录解析相对资源)
- pdf_service:上传落盘 + asyncio 后台转换(独立 Session)+ 进度追踪 + 两级删除
  · 用户软删(user_deleted,管理页仍可见)· 管理员硬删(真正删磁盘+记录)
- pdf_controller:/api/pdf/*(用户,cookie)+ /api/admin/pdf/*(Basic Auth)
- /pdf、/pdf-admin 页面(原生 JS,复用 common.css/js)
- 配置 pdf 段(max_size 250MB、转换超时、cookie)
- pytest 7 项(SQLite→MySQL 隔离测试库):上传/转换/下载/软删/硬删/超限/越权
This commit is contained in:
2026-07-27 11:33:43 +08:00
parent fa980e74e0
commit aa08a1cf60
21 changed files with 1549 additions and 6 deletions

68
app/dao/pdf_job_dao.py Normal file
View File

@@ -0,0 +1,68 @@
"""PdfJob 的 DAO。
所有写操作均在该层 commitservice 不直接操作 session。
用户/管理两条查询路径分别按 user_deleted 过滤。
"""
from __future__ import annotations
from datetime import datetime
from sqlalchemy import func, select
from sqlalchemy.orm import Session
from ..models.pdf_job import PdfJob
class PdfJobDAO:
def __init__(self, db: Session) -> None:
self.db = db
def create(self, job: PdfJob) -> PdfJob:
self.db.add(job)
self.db.commit()
self.db.refresh(job)
return job
def get(self, job_id: int) -> PdfJob | None:
return self.db.get(PdfJob, job_id)
def update(self, job: PdfJob) -> PdfJob:
"""提交对 job 的就地修改并刷新。"""
self.db.commit()
self.db.refresh(job)
return job
def list_for_user(self, owner_cookie: str, limit: int = 100, offset: int = 0) -> list[PdfJob]:
"""用户视角:仅未软删的任务,按创建时间倒序。"""
stmt = (
select(PdfJob)
.where(PdfJob.owner_cookie == owner_cookie)
.where(PdfJob.user_deleted == False) # noqa: E712
.order_by(PdfJob.created_at.desc())
.limit(limit)
.offset(offset)
)
return list(self.db.scalars(stmt).all())
def count_for_user(self, owner_cookie: str) -> int:
stmt = (
select(func.count())
.select_from(PdfJob)
.where(PdfJob.owner_cookie == owner_cookie)
.where(PdfJob.user_deleted == False) # noqa: E712
)
return self.db.scalar(stmt) or 0
def list_all(self, limit: int = 100, offset: int = 0) -> list[PdfJob]:
"""管理视角:全部任务(含已软删),按创建时间倒序。"""
stmt = (
select(PdfJob)
.order_by(PdfJob.created_at.desc())
.limit(limit)
.offset(offset)
)
return list(self.db.scalars(stmt).all())
def count_all(self) -> int:
return self.db.scalar(select(func.count()).select_from(PdfJob)) or 0