Files
siftlode/backend/app/routes/public.py
T
peter 614c5528ad fix(downloads): harden upload serving + ingest against stored-XSS and leaks (E7 review)
Deep-review remediation for the E7 upload path, all findings adversarially verified:

- Serve every library file with a Content-Type chosen from the ffprobe-verified media_kind
  + a strict container allow-list (storage.served_media_type), never guessed from the
  user-controlled file extension. Closes a stored-XSS vector where a media/HTML polyglot
  uploaded as "evil.html" was served inline as text/html on the login-free /watch surface.
  Applied to both the authenticated /file and the public watch_file endpoints.
- Classify uploaded still images (jpg/png/gif/webp/…) as media_kind='file' so they are
  force-downloaded and don't get a broken in-app video player.
- Roll back the on-disk side of an upload when the ingest transaction fails after place_file
  (unlink the placed file + its deterministic poster path), so a failed commit can't orphan
  bytes in the GC-skipped .uploads tree.
- Floor download_upload_max_bytes at min=1 so a stored 0 can't silently disable the per-file cap.
- Dedupe the ffprobe-JSON invocation into edit.run_ffprobe_json (shared by probe_codecs and
  upload._probe) and the upload extension into storage._clean_upload_ext; drop the now-unused
  parse_probe_streams.

Tests: public + authenticated force-download and the polyglot-not-served-as-HTML guard, the
real _probe classifier (image/cover-art/dims/duration), the ingest rollback/cleanup path, the
max_jobs branch, the cap-floor invariant, and run_ffprobe_json error handling.
2026-08-29 21:52:02 +02:00

160 lines
7.2 KiB
Python

"""Public, login-free surface for shared download links (the `/watch/{token}` player page).
These routes are deliberately OUTSIDE the auth/`require_human` gate — the unguessable token IS the
credential (a capability URL). They only ever expose one file's stream + minimal metadata, never
the app or any account data. Password-protected links exchange the password once at `/unlock` for
a short-lived signed grant that the media URL carries (a `<video src>` can't send a header).
"""
from fastapi import APIRouter, Depends, HTTPException
from fastapi.responses import FileResponse
from pydantic import BaseModel
from sqlalchemy import select
from sqlalchemy.orm import Session
from app.config import settings
from app.db import get_db
from app.downloads import links as linksmod
from app.downloads import storage
from app.models import DownloadJob, DownloadLink, MediaAsset
from app.ratelimit import RateLimiter
from app.security import verify_password
router = APIRouter(prefix="/api/public", tags=["public"])
# Slow password guessing per link (the token itself is 192-bit, so it needs no throttle).
_unlock_limit = RateLimiter(max_events=10, window_seconds=300)
def _link_or_404(db: Session, token: str) -> DownloadLink:
link = db.execute(select(DownloadLink).where(DownloadLink.token == token)).scalar_one_or_none()
if link is None or linksmod.is_expired(link):
raise HTTPException(status_code=404, detail="This link is no longer available.")
return link
def _ready_target(db: Session, link: DownloadLink) -> tuple[DownloadJob, MediaAsset]:
job = db.get(DownloadJob, link.job_id)
asset = db.get(MediaAsset, job.asset_id) if job and job.asset_id else None
if job is None or asset is None or asset.status != "ready" or not asset.rel_path:
raise HTTPException(status_code=404, detail="This video is no longer available.")
# Verify the file is actually on disk here (not just flagged ready), so the watch page never
# loads a player for a missing file — meta and file agree.
path = storage.safe_abs_path(settings.download_root, asset.rel_path)
if path is None:
raise HTTPException(status_code=404, detail="This video is no longer available.")
return job, asset
def _ready_asset(db: Session, link: DownloadLink) -> MediaAsset:
return _ready_target(db, link)[1]
def _file_url(token: str, grant: str | None = None) -> str:
base = f"/api/public/watch/{token}/file"
return f"{base}?g={grant}" if grant else base
def _poster_url(token: str, asset, grant: str | None = None) -> str | None:
if not asset.poster_path:
return None
base = f"/api/public/watch/{token}/poster.jpg"
return f"{base}?g={grant}" if grant else base
@router.get("/watch/{token}")
def watch_meta(token: str, db: Session = Depends(get_db)) -> dict:
"""Public metadata for the watch page. For a password link, returns only `needs_password`
until the viewer unlocks it (no title/thumbnail leak)."""
link = _link_or_404(db, token)
if link.password_hash:
return {"needs_password": True}
job, asset = _ready_target(db, link)
link.view_count += 1
db.commit()
return {
"needs_password": False,
**linksmod.public_meta(link, job, asset, _file_url(token), _poster_url(token, asset)),
}
class WatchUnlockIn(BaseModel):
password: str = ""
@router.post("/watch/{token}/unlock")
def watch_unlock(token: str, body: WatchUnlockIn, db: Session = Depends(get_db)) -> dict:
"""Exchange the link password for a signed grant carried by the media URL."""
if not _unlock_limit.allow(token):
raise HTTPException(status_code=429, detail="Too many attempts. Try again later.")
link = _link_or_404(db, token)
if not link.password_hash:
# Not a password link — nothing to unlock; just hand back the plain meta.
job, asset = _ready_target(db, link)
return {
"needs_password": False,
**linksmod.public_meta(link, job, asset, _file_url(token), _poster_url(token, asset)),
}
if not verify_password(body.password, link.password_hash):
raise HTTPException(status_code=403, detail="Wrong password.")
job, asset = _ready_target(db, link)
link.view_count += 1
db.commit()
grant = linksmod.make_grant(token, link.password_version)
return {
"needs_password": False,
**linksmod.public_meta(
link, job, asset, _file_url(token, grant), _poster_url(token, asset, grant)
),
}
@router.get("/watch/{token}/file")
def watch_file(token: str, g: str | None = None, db: Session = Depends(get_db)):
"""Range-aware stream of the shared file. Inline by default (plays in the page); an
`allow_download` link serves it as an attachment. Password links require a valid grant."""
link = _link_or_404(db, token)
if link.password_hash and not linksmod.check_grant(token, g, link.password_version):
raise HTTPException(status_code=403, detail="This link needs a password.")
asset = _ready_asset(db, link)
path = storage.safe_abs_path(settings.download_root, asset.rel_path)
if path is None:
raise HTTPException(status_code=404, detail="This video is no longer available.")
filename = storage.download_filename(asset.title or "video", asset.container, path)
# The served Content-Type comes from the asset's ffprobe-verified media_kind + a container
# allow-list (storage.served_media_type) — NEVER guessed from the file's own extension. A generic
# 'file' (and any media whose container we don't positively recognise, e.g. a media/HTML polyglot
# named "evil.html") returns None → a neutral force-download attachment, so arbitrary uploaded
# HTML/SVG can't execute inline on this login-free public origin. A recognised media container is
# served with its real audio/video type, inline unless the link forces a download so it can play
# in the watch page. Both are range-aware (FileResponse → 206) for seeking/resume.
media_type = storage.served_media_type(asset.media_kind, asset.container)
if media_type is None:
return FileResponse(
path,
filename=filename,
media_type="application/octet-stream",
content_disposition_type="attachment",
)
disposition = "attachment" if link.allow_download else "inline"
return FileResponse(
path, filename=filename, media_type=media_type, content_disposition_type=disposition
)
@router.get("/watch/{token}/poster.jpg")
def watch_poster(token: str, g: str | None = None, db: Session = Depends(get_db)):
"""The generated poster frame for a shared thumbnail-less video (used as the page/video poster
and the link-preview image). Password links require a valid grant, like the file."""
link = _link_or_404(db, token)
if link.password_hash and not linksmod.check_grant(token, g, link.password_version):
raise HTTPException(status_code=403, detail="This link needs a password.")
job, asset = _ready_target(db, link)
if not asset.poster_path:
raise HTTPException(status_code=404, detail="No poster.")
path = storage.safe_abs_path(settings.download_root, asset.poster_path)
if path is None:
raise HTTPException(status_code=404, detail="No poster.")
return FileResponse(path, media_type="image/jpeg")