535 lines
22 KiB
Python
535 lines
22 KiB
Python
"""Files 路由(user-rooted,不绑 task)+ 用户磁盘用量 + pptx 在线预览。
|
||
|
||
文件面板的目录树 mutation 入口(DESIGN §7.4):顶层目录 rename 复用
|
||
core.working_dirs 的 DB-aware 服务，delete/move 走本路由状态闸。路径安全原语在
|
||
web/userfiles.py。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
from pathlib import Path
|
||
from uuid import UUID
|
||
|
||
from fastapi import Depends, File, Form, HTTPException, UploadFile
|
||
from fastapi.responses import FileResponse
|
||
from sqlalchemy import func, select
|
||
|
||
from core.paths import from_db_path, to_db_path
|
||
from core.storage import session_scope
|
||
from core.storage.models import Task
|
||
from core.working_dirs import (
|
||
WorkingDirConflictError,
|
||
WorkingDirRenameError,
|
||
rename_working_dir,
|
||
)
|
||
|
||
from ..common import norm_path
|
||
from ..schemas import FileDeleteRequest, FileRenameRequest, FileTransferRequest
|
||
from ..userfiles import (
|
||
enumerate_files,
|
||
load_user_root,
|
||
rel_to,
|
||
safe_join,
|
||
system_wd_names,
|
||
validate_transfer,
|
||
)
|
||
|
||
# pptx→PDF 预览:按解析后的 pptx 绝对路径加锁,防同一文件并发重复转换(DESIGN §8.3)。
|
||
_pptx_preview_locks: dict[str, asyncio.Lock] = {}
|
||
|
||
|
||
def _pptx_lock_for(abs_path: str) -> asyncio.Lock:
|
||
lock = _pptx_preview_locks.get(abs_path)
|
||
if lock is None:
|
||
lock = _pptx_preview_locks[abs_path] = asyncio.Lock()
|
||
return lock
|
||
|
||
|
||
def _regular_file_response(target: Path, display_path: str) -> FileResponse:
|
||
if not target.exists():
|
||
raise HTTPException(404, f"file not found: {display_path}")
|
||
if not target.is_file():
|
||
raise HTTPException(400, f"not a file: {display_path}")
|
||
media_type = "image/svg+xml" if target.suffix.lower() == ".svg" else None
|
||
return FileResponse(
|
||
path=str(target),
|
||
filename=target.name,
|
||
media_type=media_type,
|
||
headers={"Cache-Control": "no-cache"},
|
||
)
|
||
|
||
|
||
def _task_working_dir(task_id: str, user_id: UUID, root: Path) -> tuple[UUID, Path]:
|
||
try:
|
||
tid = UUID(task_id)
|
||
except ValueError:
|
||
raise HTTPException(404, f"invalid task id: {task_id!r}")
|
||
with session_scope() as s:
|
||
db_path = s.execute(
|
||
select(Task.working_dir).where(Task.task_id == tid, Task.user_id == user_id)
|
||
).scalar_one_or_none()
|
||
if not db_path:
|
||
raise HTTPException(404, "task not found")
|
||
working_dir = from_db_path(db_path).resolve()
|
||
try:
|
||
working_dir.relative_to(root.resolve())
|
||
except ValueError:
|
||
raise HTTPException(400, "task working_dir is outside user workspace")
|
||
return tid, working_dir
|
||
|
||
|
||
def _task_file_target(root: Path, working_dir: Path, path: str, legacy: bool) -> Path:
|
||
"""Resolve canonical task refs, with a read-only fallback chain for old cards.
|
||
|
||
Historical messages used user-root paths, while one known failure accidentally emitted
|
||
a task-relative path with the same leading directory name. Old cards therefore try the
|
||
original user-root meaning first, then both task-relative interpretations. New refs never
|
||
use this branch and remain unambiguous.
|
||
"""
|
||
if not legacy:
|
||
return safe_join(working_dir, path)
|
||
candidates = [safe_join(root, path), safe_join(working_dir, path)]
|
||
normalized = str(path or "").replace("\\", "/")
|
||
if "/" in normalized:
|
||
candidates.append(safe_join(working_dir, normalized.split("/", 1)[1]))
|
||
for candidate in candidates:
|
||
if candidate.is_file():
|
||
return candidate
|
||
return candidates[0]
|
||
|
||
|
||
async def _pptx_preview_response(target: Path, display_path: str) -> FileResponse:
|
||
from ..pptx_render import (
|
||
PptxConvertError,
|
||
SofficeNotFoundError,
|
||
pptx_to_pdf,
|
||
)
|
||
|
||
if not target.exists():
|
||
raise HTTPException(404, f"file not found: {display_path}")
|
||
if not target.is_file():
|
||
raise HTTPException(400, f"not a file: {display_path}")
|
||
if target.suffix.lower() not in (".pptx", ".ppt"):
|
||
raise HTTPException(400, f"not a pptx: {display_path}")
|
||
abs_path = str(target.resolve())
|
||
loop = asyncio.get_event_loop()
|
||
async with _pptx_lock_for(abs_path):
|
||
try:
|
||
pdf_path = await loop.run_in_executor(None, pptx_to_pdf, target)
|
||
except SofficeNotFoundError as e:
|
||
raise HTTPException(501, str(e))
|
||
except PptxConvertError as e:
|
||
raise HTTPException(500, str(e))
|
||
return FileResponse(
|
||
path=str(pdf_path),
|
||
media_type="application/pdf",
|
||
headers={"Cache-Control": "no-cache"},
|
||
)
|
||
|
||
|
||
def register_file_routes(app, *, require_user) -> None:
|
||
@app.get("/v1/user/storage", tags=["user"])
|
||
def user_storage(user_id: UUID = Depends(require_user)):
|
||
"""当前用户磁盘用量 + 配额。
|
||
|
||
数据来自后台扫描落库的 user_disk_usage(默 15min 一次),非实时;
|
||
无扫描记录(新用户 / 首次扫描前)bytes_used/file_count=0、scanned_at=None。
|
||
limit_bytes<=0 或 None → 不限(前端不画进度条)。
|
||
"""
|
||
from core.agent_builder import load_config as _load_cfg
|
||
from core.storage.disk_quota import get_user_usage, parse_bytes
|
||
_quotas_cfg = (_load_cfg().get("quotas") or {})
|
||
_limit = parse_bytes(_quotas_cfg.get("disk_bytes_per_user"))
|
||
usage = get_user_usage(user_id)
|
||
if usage is None:
|
||
bytes_used, file_count, scanned_at = 0, 0, None
|
||
else:
|
||
bytes_used, file_count, scanned_at = usage
|
||
return {
|
||
"bytes_used": bytes_used,
|
||
"file_count": file_count,
|
||
"limit_bytes": (_limit if (_limit and _limit > 0) else None),
|
||
"scanned_at": scanned_at.isoformat() if scanned_at else None,
|
||
}
|
||
|
||
@app.get("/v1/files", tags=["files"])
|
||
def list_files(
|
||
path: str = "",
|
||
include_hidden: bool = False,
|
||
task_id: str = "",
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""列 user_root 下子目录条目 + 面包屑。`path` 留空 → user_root;
|
||
`../` / 绝对 → 400。dotfile/dotdir 默认隐藏；`include_hidden=true`
|
||
仅在 `task_id` 属于当前用户且 current 位于该 task 工作目录子树时展示
|
||
dotdir，永不从 user_root 展示平台目录。根目录层再隐藏系统工作目录
|
||
(定时任务 / 渠道对话,见 system_wd_names)。点文件始终隐藏。
|
||
"""
|
||
root = load_user_root(user_id)
|
||
current = safe_join(root, path)
|
||
include_task_hidden = False
|
||
if include_hidden and task_id:
|
||
_tid, working_dir = _task_working_dir(task_id, user_id, root)
|
||
try:
|
||
current.relative_to(working_dir)
|
||
include_task_hidden = True
|
||
except ValueError:
|
||
pass
|
||
entries, crumbs, exists = enumerate_files(
|
||
root,
|
||
current,
|
||
include_hidden_dirs=include_task_hidden,
|
||
)
|
||
if not rel_to(root, current):
|
||
hidden = system_wd_names(user_id)
|
||
if hidden:
|
||
entries = [
|
||
e for e in entries
|
||
if not (e["is_dir"] and e["name"] in hidden)
|
||
]
|
||
return {
|
||
"root": norm_path(str(root)),
|
||
"current": rel_to(root, current),
|
||
"exists": exists,
|
||
"crumbs": crumbs,
|
||
"entries": entries,
|
||
"hidden_dirs_included": include_task_hidden,
|
||
}
|
||
|
||
@app.get("/v1/files/download", tags=["files"])
|
||
def download_file(
|
||
path: str,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""下载 user_root 下单个 regular file(目录 → 400 / 不存在 → 404)。"""
|
||
root = load_user_root(user_id)
|
||
target = safe_join(root, path)
|
||
# workspace 文件可变, 禁浏览器启发式缓存 (RFC 7234 默认能缓数小时)
|
||
# 否则文件改了 SPA 预览还是旧内容
|
||
# (Starlette FileResponse 不实现 304, 总是 200 全量; workspace 文件小, 可接受)
|
||
# .svg 显式给 image/svg+xml: 部分部署环境 mimetypes 未注册 svg, FileResponse
|
||
# 会猜成 octet-stream, 前端 <img> 就渲染不出 SVG 预览
|
||
return _regular_file_response(target, path)
|
||
|
||
@app.get("/v1/tasks/{task_id}/files/download", tags=["files"])
|
||
def download_task_file(
|
||
task_id: str,
|
||
path: str,
|
||
legacy: bool = False,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""Download a file addressed relative to the task's current working_dir."""
|
||
root = load_user_root(user_id)
|
||
_tid, working_dir = _task_working_dir(task_id, user_id, root)
|
||
target = _task_file_target(root, working_dir, path, legacy)
|
||
return _regular_file_response(target, path)
|
||
|
||
@app.get("/v1/files/preview_pdf", tags=["files"])
|
||
async def preview_pdf(
|
||
path: str,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""把 user_root 下的 .pptx 转成 PDF 返回,供前端复用 PDF iframe 在线预览。
|
||
|
||
转换跑在 backend host(不进沙盒),按需触发 + 缓存到 `.preview/`(DESIGN §8.3)。
|
||
soffice 缺失 → 501;转换失败/超时 → 500;前端据此回退到下载。
|
||
"""
|
||
root = load_user_root(user_id)
|
||
target = safe_join(root, path)
|
||
return await _pptx_preview_response(target, path)
|
||
|
||
@app.get("/v1/tasks/{task_id}/files/preview_pdf", tags=["files"])
|
||
async def preview_task_pdf(
|
||
task_id: str,
|
||
path: str,
|
||
legacy: bool = False,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""Preview a PPT addressed relative to the task's current working_dir."""
|
||
root = load_user_root(user_id)
|
||
_tid, working_dir = _task_working_dir(task_id, user_id, root)
|
||
target = _task_file_target(root, working_dir, path, legacy)
|
||
return await _pptx_preview_response(target, path)
|
||
|
||
@app.post("/v1/files/upload", tags=["files"])
|
||
async def upload_files(
|
||
path: str = Form(""),
|
||
files: list[UploadFile] = File(...),
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""multipart 多文件上传到 `<user_root>/<path>/`。
|
||
路径不存在自动 mkdir(parents=True);重名直接覆盖。
|
||
文件名严格校验(含 `/ \\ ..` 或为空 → 400)。
|
||
"""
|
||
# 磁盘配额 gate(§7.5 #4):超额 413 阻止上传,提示 user 清旧产物
|
||
from core.agent_builder import load_config as _load_cfg
|
||
from core.storage.disk_quota import check_disk_quota, parse_bytes
|
||
_quotas_cfg = (_load_cfg().get("quotas") or {})
|
||
_limit = parse_bytes(_quotas_cfg.get("disk_bytes_per_user"))
|
||
if _limit is not None and _limit > 0:
|
||
_err = check_disk_quota(user_id, _limit)
|
||
if _err is not None:
|
||
raise HTTPException(413, _err)
|
||
|
||
root = load_user_root(user_id)
|
||
dest_dir = safe_join(root, path)
|
||
if dest_dir.exists() and not dest_dir.is_dir():
|
||
raise HTTPException(400, f"upload target is a file, not a directory: {path}")
|
||
dest_dir.mkdir(parents=True, exist_ok=True)
|
||
|
||
saved: list[dict] = []
|
||
for up in files or []:
|
||
raw_name = up.filename or ""
|
||
if (
|
||
not raw_name
|
||
or raw_name in (".", "..")
|
||
or "/" in raw_name or "\\" in raw_name
|
||
or any(part in (".", "..") for part in Path(raw_name).parts)
|
||
):
|
||
raise HTTPException(400, f"invalid filename: {raw_name!r}")
|
||
dest = dest_dir / raw_name
|
||
try:
|
||
dest.resolve().relative_to(root.resolve())
|
||
except ValueError:
|
||
raise HTTPException(400, f"path escapes user_root: {raw_name!r}")
|
||
data = await up.read()
|
||
dest.write_bytes(data)
|
||
saved.append({"name": raw_name, "size": len(data), "rel": rel_to(root, dest)})
|
||
if not saved:
|
||
raise HTTPException(400, "no files uploaded")
|
||
return {"count": len(saved), "saved": saved}
|
||
|
||
@app.post("/v1/files/delete", tags=["files"])
|
||
def delete_file(
|
||
body: FileDeleteRequest,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""删 user_root 下文件或目录。
|
||
|
||
- `recursive=False`(默认):目录必须为空(`rmdir`),非空 → 400
|
||
- `recursive=True`:`shutil.rmtree`;若目标是顶层目录且被某 task.working_dir
|
||
引用 → 409,提示先 DELETE task(避免 DB 还引用、FS artifacts 已清的错位)
|
||
- 顶层空目录 / 子级空目录无论 recursive 与否都可删:task.working_dir 字段不动,
|
||
下次 build_agent 按需 mkdir 重建,FS 目录视为可重生
|
||
- root → 400;不存在 → 404
|
||
"""
|
||
root = load_user_root(user_id)
|
||
target = safe_join(root, body.path)
|
||
if target.resolve() == root.resolve():
|
||
raise HTTPException(400, "cannot delete user_root")
|
||
if not target.exists():
|
||
raise HTTPException(404, f"path not found: {body.path}")
|
||
|
||
if target.is_dir() and body.recursive:
|
||
is_top_level = target.parent.resolve() == root.resolve()
|
||
if is_top_level:
|
||
db_form = to_db_path(target)
|
||
with session_scope() as s:
|
||
n = s.execute(
|
||
select(func.count()).select_from(Task).where(
|
||
Task.user_id == user_id,
|
||
Task.working_dir == db_form,
|
||
Task.deleted_at.is_(None), # 软删 task 不再算引用
|
||
)
|
||
).scalar_one() or 0
|
||
if n:
|
||
raise HTTPException(
|
||
409,
|
||
f"该顶层目录正被 {n} 个 task 引用,不能递归删除;"
|
||
f"请先 DELETE task,再清残留文件",
|
||
)
|
||
|
||
try:
|
||
if target.is_dir():
|
||
if body.recursive:
|
||
import shutil
|
||
shutil.rmtree(target)
|
||
else:
|
||
target.rmdir() # 非空目录会触发 OSError
|
||
else:
|
||
target.unlink()
|
||
except OSError as e:
|
||
raise HTTPException(400, f"delete failed: {e}")
|
||
return {"ok": True, "path": body.path}
|
||
|
||
@app.post("/v1/files/rename", tags=["files"])
|
||
def rename_path(
|
||
body: FileRenameRequest,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""重命名 user_root 下文件或目录(任意深度)。
|
||
|
||
- `path` 必填,指被重命名对象;不能为 user_root
|
||
- `new_name` 是新 leaf 名(`validate_task_name`:非空 / 不含 `/\\..` / 非 dotfile / ≤255);
|
||
不是路径,parent 自动取自原 path
|
||
- 目标 sibling `<parent>/<new_name>` 不能已存在(防覆盖)
|
||
- **path 是顶层目录**(user_root 直接子项,且为目录)→ DB-aware:
|
||
* 同事务内 `SELECT ... FOR UPDATE` 锁该目录对应 task;任一 run_status 在
|
||
running/cancelling → 409(避免 BG 线程握旧路径而 DB 已指新路径)
|
||
* `check_no_subtask(new_db, exclude=被改名 tids)` 防止改名后跟其它 task 形成嵌套
|
||
* `UPDATE tasks SET working_dir=new_db WHERE task_id IN (...)` 先写 DB
|
||
* 再 `os.rename` FS;失败 → 抛错 → session_scope 回滚 DB
|
||
* 唯一不一致窗口是 "FS 已改名 + commit 阶段失败"(PG 单事务 commit 极少失败)
|
||
- 非顶层(子目录 / 文件)→ 纯 FS rename,不动 DB
|
||
"""
|
||
from core.agent_builder import InvalidTaskName, validate_task_name
|
||
|
||
root = load_user_root(user_id)
|
||
target = safe_join(root, body.path)
|
||
if target.resolve() == root.resolve():
|
||
raise HTTPException(400, "cannot rename user_root")
|
||
if not target.exists():
|
||
raise HTTPException(404, f"path not found: {body.path}")
|
||
|
||
try:
|
||
new_name = validate_task_name(body.new_name)
|
||
except InvalidTaskName as e:
|
||
raise HTTPException(400, f"new_name 不合法: {e}")
|
||
|
||
if new_name == target.name:
|
||
raise HTTPException(400, f"new_name 与原名相同: {new_name!r}")
|
||
|
||
new_target = target.parent / new_name
|
||
if new_target.exists():
|
||
raise HTTPException(
|
||
409, f"target already exists: {rel_to(root, new_target)!r}"
|
||
)
|
||
|
||
is_top_level_dir = (
|
||
target.is_dir() and target.parent.resolve() == root.resolve()
|
||
)
|
||
|
||
if not is_top_level_dir:
|
||
try:
|
||
target.rename(new_target)
|
||
except OSError as e:
|
||
raise HTTPException(400, f"rename failed: {e}")
|
||
return {
|
||
"ok": True,
|
||
"old": body.path,
|
||
"new": rel_to(root, new_target),
|
||
"tasks_updated": 0,
|
||
}
|
||
|
||
# 顶层目录:网页和对话内延迟动作共用同一个 DB-aware 服务。
|
||
try:
|
||
renamed = rename_working_dir(
|
||
user_id=user_id,
|
||
old_path=target,
|
||
new_path=new_target,
|
||
)
|
||
except WorkingDirConflictError as e:
|
||
raise HTTPException(409, str(e))
|
||
except WorkingDirRenameError as e:
|
||
# 保持原 files API 的普通 FS 失败 400 语义。
|
||
raise HTTPException(400, str(e))
|
||
|
||
return {
|
||
"ok": True,
|
||
"old": body.path,
|
||
"new": rel_to(root, new_target),
|
||
"tasks_updated": renamed.tasks_updated,
|
||
}
|
||
|
||
@app.post("/v1/files/copy", tags=["files"])
|
||
def copy_files(
|
||
body: FileTransferRequest,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""批量拷贝 paths → dest_dir/<name>(目录递归)。
|
||
|
||
- 不覆盖(任一目标已存在 → 409)
|
||
- 不能拷到自己 / 自身子树
|
||
- 顶层目录(可能是某 task 的 working_dir)可以拷:新副本无 task 关联,不动 DB
|
||
- 部分失败语义:任一 FS 拷贝抛错 → 抛 HTTPException,**前面已成功的拷贝保留**
|
||
(无 FS 事务可回滚;预检通过后通常不会失败,失败也是磁盘满 / 权限这类不能恢复的)
|
||
"""
|
||
import shutil
|
||
root = load_user_root(user_id)
|
||
sources, dest = validate_transfer(root, body.paths, body.dest_dir)
|
||
transferred: list[dict] = []
|
||
for src in sources:
|
||
target = dest / src.name
|
||
try:
|
||
if src.is_dir():
|
||
shutil.copytree(src, target)
|
||
else:
|
||
shutil.copy2(src, target)
|
||
except OSError as e:
|
||
raise HTTPException(
|
||
500,
|
||
f"copy failed at {src.name!r}: {e} "
|
||
f"(已成功 {len(transferred)} 项,剩余未处理)",
|
||
)
|
||
transferred.append({
|
||
"old": rel_to(root, src),
|
||
"new": rel_to(root, target),
|
||
})
|
||
return {"ok": True, "count": len(transferred), "transferred": transferred}
|
||
|
||
@app.post("/v1/files/move", tags=["files"])
|
||
def move_files(
|
||
body: FileTransferRequest,
|
||
user_id: UUID = Depends(require_user),
|
||
):
|
||
"""批量移动 paths → dest_dir/<name>。
|
||
|
||
- 不覆盖、不自嵌套(同 /copy)
|
||
- **顶层目录是某 task 的 working_dir → 409**,维持 "working_dir = 顶层目录" invariant
|
||
(允许的话 task working_dir 沉到子目录会让 rename 顶层的 DB-aware 逻辑失效;
|
||
用户想归档:先 DELETE task)
|
||
- 拷贝(`/copy`)无此限制,因为新副本无 task 关联
|
||
- 部分失败:同 /copy,前面成功的不回滚(`shutil.move` 失败几乎只发生在
|
||
跨卷拷贝中断,workspace 都在同一磁盘下罕见)
|
||
"""
|
||
import shutil
|
||
root = load_user_root(user_id)
|
||
sources, dest = validate_transfer(root, body.paths, body.dest_dir)
|
||
|
||
# 顶层目录-是-某 task.working_dir → 闸
|
||
top_level_dir_srcs = [
|
||
s for s in sources
|
||
if s.is_dir() and s.parent.resolve() == root.resolve()
|
||
]
|
||
if top_level_dir_srcs:
|
||
db_forms = [to_db_path(s) for s in top_level_dir_srcs]
|
||
with session_scope() as s:
|
||
rows = s.execute(
|
||
select(Task.working_dir, func.count())
|
||
.where(
|
||
Task.user_id == user_id,
|
||
Task.working_dir.in_(db_forms),
|
||
)
|
||
.group_by(Task.working_dir)
|
||
).all()
|
||
occupied = {wd: n for wd, n in rows}
|
||
if occupied:
|
||
# 反查 db_form → src.name 给报错文案
|
||
form2name = {to_db_path(s): s.name for s in top_level_dir_srcs}
|
||
names = ", ".join(
|
||
f"{form2name[wd]!r}({n} 个 task)"
|
||
for wd, n in occupied.items()
|
||
)
|
||
raise HTTPException(
|
||
409,
|
||
f"以下顶层目录正被 task 引用,不能移动:{names};"
|
||
f"请先删 task,或改用复制",
|
||
)
|
||
|
||
transferred: list[dict] = []
|
||
for src in sources:
|
||
target = dest / src.name
|
||
try:
|
||
shutil.move(str(src), str(target))
|
||
except OSError as e:
|
||
raise HTTPException(
|
||
500,
|
||
f"move failed at {src.name!r}: {e} "
|
||
f"(已成功 {len(transferred)} 项,剩余未处理)",
|
||
)
|
||
transferred.append({
|
||
"old": rel_to(root, src),
|
||
"new": rel_to(root, target),
|
||
})
|
||
return {"ok": True, "count": len(transferred), "transferred": transferred}
|