feat(downloads): local file upload ingest — media library backend (E7 S5a)

Add the non-yt-dlp ingest path so a user-uploaded file joins the same download library and inherits its function set. Any file type is accepted: media (video/audio) gets the full set (metadata, share, play/edit), a generic file (pdf/zip/docx/…) is download-only. - MediaAsset.media_kind ("video"|"audio"|"file") — the stored discriminator that gates library actions. Set at every finalize (download probe, editor carries the source's kind, upload probe); consolidates the ad-hoc audio-detect that lived only in links.py into one invariant (downloads.mediakind.derive). Migration 0076 adds the column + backfills existing rows. - downloads/upload.py: ingest_upload probes the file (ffprobe → codecs/dims/duration), places it in a per-user .uploads tree, and creates an already-ready asset + done job (the same cache-hit shortcut enqueue uses). Uploads never expire (irreplaceable). - POST /api/downloads/upload: streaming multipart with the per-file cap (download_upload_max_bytes, default 500 MiB) enforced on actual bytes read; quota charges the known size up front (quota.check_upload). - Security: a generic file is always served force-download (attachment + application/octet-stream) on both the in-app and public endpoints, so uploaded HTML/SVG can't execute inline. Edit + redownload reject non-media / upload sources. - python-multipart added (first multipart endpoint in the app).
2026-08-29 08:02:11 +02:00
parent 9eaa01617c
commit fe0b34cd00
17 changed files with 578 additions and 19 deletions
@@ -0,0 +1,184 @@
+"""E7 S5a — local file upload ingest (the non-yt-dlp path into the media library).
+
+Covers the ingest spine: media vs generic-file classification, the download-only serving of a
+generic file (force-download so uploaded HTML/SVG can't execute inline), quota accounting with the
+size known up front, the per-file cap enforced while streaming, filename sanitization, and the two
+guards that keep an upload out of paths that assume a re-fetchable source (edit / redownload).
+
+DB-backed (real Postgres) — skipped when no database is reachable. `settings.download_root` is
+pointed at a per-test tmp dir so ingest's on-disk moves are isolated; `_probe` is monkeypatched so
+the tests don't depend on ffprobe (its real behaviour is exercised by the download/edit suites).
+"""
+
+import pytest
+
+from app.config import settings
+from app.downloads import mediakind, quota, storage
+from app.downloads import upload as uploadmod
+from app.models import DownloadQuota, MediaAsset
+
+
+# --- pure: the kind invariant ---------------------------------------------------------------
+
+
+def test_derive_media_kind():
+    assert uploadmod.mediakind.derive("h264", "aac") == mediakind.VIDEO
+    assert uploadmod.mediakind.derive("vp9", None) == mediakind.VIDEO
+    assert uploadmod.mediakind.derive(None, "aac") == mediakind.AUDIO
+    assert uploadmod.mediakind.derive(None, None) == mediakind.FILE
+
+
+# --- ingest (direct) ------------------------------------------------------------------------
+
+
+@pytest.fixture
+def _root(tmp_path, monkeypatch):
+    monkeypatch.setattr(settings, "download_root", str(tmp_path))
+    return tmp_path
+
+
+def _probe(monkeypatch, result):
+    monkeypatch.setattr(uploadmod, "_probe", lambda _p: result)
+
+
+def test_ingest_generic_file_is_download_only(db, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, None, None, None, None))
+    u = make_user()
+    src = _root / "src.bin"
+    src.write_bytes(b"%PDF-1.4 hello")
+    job = uploadmod.ingest_upload(
+        db, u.id, filename="My Notes.pdf", src_path=src, size=src.stat().st_size
+    )
+    asset = db.get(MediaAsset, job.asset_id)
+    assert asset.media_kind == mediakind.FILE
+    assert asset.status == "ready" and job.status == "done" and job.progress == 100
+    assert asset.container == "pdf"
+    assert asset.poster_path is None  # a generic file has no player and no poster
+    assert asset.title == "My Notes"  # display title from the original name
+    assert job.job_kind == "upload" and job.source_kind == "upload"
+    # The file was MOVED into the per-user uploads tree, inside the root, and the temp is gone.
+    assert not src.exists()
+    assert asset.rel_path.startswith(".uploads/")
+    assert storage.safe_abs_path(str(_root), asset.rel_path) is not None
+
+
+def test_ingest_audio_is_media_no_poster(db, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, "aac", None, None, 200))
+    u = make_user()
+    src = _root / "song.m4a"
+    src.write_bytes(b"fake-audio")
+    job = uploadmod.ingest_upload(db, u.id, filename="song.m4a", src_path=src, size=10)
+    asset = db.get(MediaAsset, job.asset_id)
+    assert asset.media_kind == mediakind.AUDIO
+    assert asset.duration_s == 200
+    assert asset.poster_path is None  # audio has no frame to poster
+
+
+def test_ingest_video_records_dims_and_poster(db, make_user, _root, monkeypatch):
+    _probe(monkeypatch, ("h264", "aac", 640, 480, 60))
+    # Stub the frame-cut so the test doesn't shell out to ffmpeg.
+    monkeypatch.setattr(uploadmod.editmod, "ensure_poster", lambda _a, _root: "p/x.jpg")
+    u = make_user()
+    src = _root / "clip.mp4"
+    src.write_bytes(b"fake-video")
+    job = uploadmod.ingest_upload(db, u.id, filename="clip.mp4", src_path=src, size=10)
+    asset = db.get(MediaAsset, job.asset_id)
+    assert asset.media_kind == mediakind.VIDEO
+    assert (asset.width, asset.height) == (640, 480)
+    assert asset.poster_path == "p/x.jpg"
+
+
+def test_ingest_filename_is_sanitized_no_traversal(db, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, None, None, None, None))
+    u = make_user()
+    src = _root / "src"
+    src.write_bytes(b"x")
+    job = uploadmod.ingest_upload(db, u.id, filename="../../etc/passwd", src_path=src, size=1)
+    asset = db.get(MediaAsset, job.asset_id)
+    assert ".." not in asset.rel_path
+    assert asset.rel_path.startswith(f".uploads/{u.id}/")
+    assert storage.safe_abs_path(str(_root), asset.rel_path) is not None
+
+
+def test_ingest_rejects_over_footprint_cap_before_writing(db, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, None, None, None, None))
+    u = make_user()
+    db.add(
+        DownloadQuota(user_id=u.id, max_bytes=1000, max_concurrent=2, max_jobs=50, unlimited=False)
+    )
+    db.commit()
+    src = _root / "big.bin"
+    src.write_bytes(b"x" * 10)
+    with pytest.raises(quota.QuotaExceeded) as e:
+        uploadmod.ingest_upload(db, u.id, filename="big.bin", src_path=src, size=2000)
+    assert e.value.reason == "max_bytes"
+    assert src.exists()  # rejected before any disk move — nothing landed
+    assert db.query(MediaAsset).count() == 0  # and no orphan asset row
+
+
+# --- route ----------------------------------------------------------------------------------
+
+
+def test_upload_route_generic_forces_download(as_user, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, None, None, None, None))
+    c = as_user(make_user())
+    r = c.post(
+        "/api/downloads/upload",
+        files={"file": ("report.html", b"<script>alert(1)</script>", "text/html")},
+    )
+    assert r.status_code == 200, r.text
+    job = r.json()
+    assert job["asset"]["media_kind"] == "file"
+    assert job["can_download"] is True
+    # The served file must be a neutral force-download attachment — never inline text/html.
+    fr = c.get(f"/api/downloads/{job['id']}/file")
+    assert fr.status_code == 200
+    assert fr.headers["content-type"].startswith("application/octet-stream")
+    assert "attachment" in fr.headers["content-disposition"].lower()
+
+
+def test_upload_route_enforces_per_file_cap(as_user, make_user, db, _root, monkeypatch):
+    from app import sysconfig
+
+    sysconfig.set_value(db, "download_upload_max_bytes", 5)
+    db.commit()
+    c = as_user(make_user())
+    r = c.post(
+        "/api/downloads/upload",
+        files={"file": ("big.bin", b"way over the cap", "application/octet-stream")},
+    )
+    assert r.status_code == 422
+    assert r.json()["detail"]["code"] == "upload_too_large"
+
+
+def test_upload_route_rejects_empty_file(as_user, make_user, _root, monkeypatch):
+    c = as_user(make_user())
+    r = c.post(
+        "/api/downloads/upload", files={"file": ("empty.bin", b"", "application/octet-stream")}
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"]["code"] == "upload_empty"
+
+
+def test_redownload_rejects_an_upload(as_user, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, None, None, None, None))
+    c = as_user(make_user())
+    job = c.post(
+        "/api/downloads/upload", files={"file": ("a.bin", b"data", "application/octet-stream")}
+    ).json()
+    r = c.post(f"/api/downloads/{job['id']}/redownload")
+    assert r.status_code == 409
+
+
+def test_edit_rejects_a_generic_upload_source(as_user, make_user, _root, monkeypatch):
+    _probe(monkeypatch, (None, None, None, None, None))
+    c = as_user(make_user())
+    job = c.post(
+        "/api/downloads/upload", files={"file": ("a.bin", b"data", "application/octet-stream")}
+    ).json()
+    r = c.post(
+        "/api/downloads/edit",
+        json={"source_job_id": job["id"], "edit_spec": {"trim": {"start_s": 0, "end_s": 1}}},
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"]["reason"] == "not_media"