157 lines
5.7 KiB
Python
157 lines
5.7 KiB
Python
"""电子书种子：把 res/ 下已有的三本书挂到教材上。
|
||
|
||
幂等：只补不覆盖，管理员在后台重新上传的文件不会被种子冲掉。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import shutil
|
||
from pathlib import Path
|
||
|
||
from sqlalchemy.orm import Session
|
||
|
||
from database import REPO_ROOT
|
||
from models import Textbook
|
||
from services import ebooks as store
|
||
|
||
RES_ROOT = REPO_ROOT / "res"
|
||
|
||
# res/ 里的文件名带书目后缀，展示时用干净的名称
|
||
PRINCETON = {
|
||
"name": "普林斯顿微积分读本(修订版)",
|
||
"author": "阿德里安·班纳 (Adrian Banner)",
|
||
"publisher": "人民邮电出版社",
|
||
"grade": "高中至大学先修",
|
||
"description": "面向微积分入门的系统辅导书，覆盖极限、导数、积分与级数，"
|
||
"按考点组织，适合自学与考前查漏补缺。",
|
||
"resource": "普林斯顿微积分读本(修订版)",
|
||
"display": "普林斯顿微积分读本(修订版).epub",
|
||
}
|
||
|
||
# 已有教材 → res/ 中的 PDF（按教材名前缀匹配）
|
||
PDF_LINKS = [
|
||
("函数和图像", "函数和图像", "函数和图像（盖尔范德中学生数学思维丛书）.pdf"),
|
||
("三角函数", "三角函数", "三角函数（盖尔范德中学生数学思维丛书）.pdf"),
|
||
]
|
||
|
||
|
||
def _find_resource(prefix: str, suffix: str) -> Path | None:
|
||
"""res/ 下的文件名带作者与来源后缀，只按标题前缀匹配。"""
|
||
if not RES_ROOT.is_dir():
|
||
return None
|
||
for path in sorted(RES_ROOT.iterdir()):
|
||
if (
|
||
path.is_file()
|
||
and path.suffix.lower() == suffix
|
||
and path.name.startswith(prefix)
|
||
):
|
||
return path
|
||
return None
|
||
|
||
|
||
# 旧库里的教材：数据库只是引用磁盘上的文件，库一旦丢失，这些文件就成了孤儿。
|
||
# 按“大小 + SHA-256”认领已知电子书，重建教材条目并把文件挪进该书自己的目录，
|
||
# 管理员就不必重新上传，种子也不会再往 res/ 里复制第二份。
|
||
KNOWN_EBOOKS = [
|
||
{
|
||
"size": 44110741,
|
||
"sha256": "f432fa058420f1032a169a91fe2dcefbc95c61a6793f1b0ec5fd1fcc84ee67da",
|
||
"display": "柯西-施瓦茨大师课：不等式的艺术.pdf",
|
||
"textbook": {
|
||
"name": "柯西-施瓦茨大师课：不等式的艺术",
|
||
"author": "J. Michael Steele 著；欧阳顺湘 译",
|
||
"publisher": "高等教育出版社 · 世界数学精品译丛 7",
|
||
"isbn": "9787040278678",
|
||
"grade": "高中至大学",
|
||
"description": (
|
||
"Cambridge 出版的不等式专题大师课：以 Cauchy-Schwarz 不等式为主线，"
|
||
"串起凸性、排序、切比雪夫、Young、Hölder、Minkowski 等常用不等式，"
|
||
"每章配大量例题与习题，适合竞赛与数学分析进阶训练。"
|
||
),
|
||
},
|
||
},
|
||
]
|
||
|
||
|
||
def _referenced_files(db: Session) -> set[Path]:
|
||
used: set[Path] = set()
|
||
rows = db.query(Textbook).filter(Textbook.ebook_file != "").all()
|
||
for row in rows:
|
||
used.add((store.book_dir(row.id) / row.ebook_file).resolve())
|
||
return used
|
||
|
||
|
||
def recover_lost_ebooks(db: Session) -> list[str]:
|
||
"""认领 data/ebooks 下未被引用的已知电子书，返回恢复的教材名。"""
|
||
if not store.EBOOK_ROOT.is_dir():
|
||
return []
|
||
referenced = _referenced_files(db)
|
||
recovered: list[str] = []
|
||
for book in KNOWN_EBOOKS:
|
||
meta = book["textbook"]
|
||
if db.query(Textbook).filter(Textbook.name == meta["name"]).first():
|
||
continue
|
||
for path in sorted(store.EBOOK_ROOT.glob("*/*")):
|
||
if not path.is_file() or path.suffix.lower() not in {".pdf", ".epub"}:
|
||
continue
|
||
if path.stat().st_size != book["size"] or path.resolve() in referenced:
|
||
continue
|
||
if store.sha256_file(path) != book["sha256"]:
|
||
continue
|
||
textbook = Textbook(
|
||
**meta, position=db.query(Textbook).count()
|
||
)
|
||
db.add(textbook)
|
||
db.commit()
|
||
target_dir = store.book_dir(textbook.id)
|
||
target_dir.mkdir(parents=True, exist_ok=True)
|
||
shutil.move(str(path), str(target_dir / path.name))
|
||
store.adopt_file(
|
||
db, textbook, path.name, display_name=book["display"]
|
||
)
|
||
recovered.append(textbook.name)
|
||
break
|
||
return recovered
|
||
|
||
|
||
def ensure_ebooks(db: Session) -> None:
|
||
created = False
|
||
textbook = (
|
||
db.query(Textbook).filter(Textbook.name == PRINCETON["name"]).first()
|
||
)
|
||
if textbook is None:
|
||
position = (
|
||
db.query(Textbook).count()
|
||
)
|
||
textbook = Textbook(
|
||
name=PRINCETON["name"],
|
||
author=PRINCETON["author"],
|
||
publisher=PRINCETON["publisher"],
|
||
grade=PRINCETON["grade"],
|
||
description=PRINCETON["description"],
|
||
position=position,
|
||
)
|
||
db.add(textbook)
|
||
db.commit()
|
||
created = True
|
||
if created:
|
||
epub = _find_resource(PRINCETON["resource"], ".epub")
|
||
if epub is not None and not textbook.ebook_file:
|
||
store.attach_local_file(
|
||
db, textbook, epub, display_name=PRINCETON["display"]
|
||
)
|
||
|
||
for name_prefix, file_prefix, display in PDF_LINKS:
|
||
textbook = (
|
||
db.query(Textbook)
|
||
.filter(Textbook.name.startswith(name_prefix))
|
||
.first()
|
||
)
|
||
if textbook is None or textbook.ebook_file:
|
||
continue
|
||
pdf = _find_resource(file_prefix, ".pdf")
|
||
if pdf is None:
|
||
continue
|
||
store.attach_local_file(db, textbook, pdf, display_name=display)
|
||
|
||
recover_lost_ebooks(db)
|