Files
Pre_Seg_Server/backend/tests/test_media.py
admin 5ab4602535 feat: 完善视频传播、标注编辑和拆帧闭环
- 接入 SAM2 视频传播能力:新增 /api/ai/propagate,支持用当前帧 mask/polygon/bbox 作为 seed,通过 SAM2 video predictor 向前、向后或双向传播,并可保存为真实 annotation。
- 接入 SAM3 video tracker:通过独立 Python 3.12 external worker 调用 SAM3 video predictor/tracker,使用本地 checkpoint 与 bbox seed 执行视频级跟踪,并在模型状态中标记 video_track 能力。
- 完善 SAM 模型分发:sam_registry 按 model_id 明确区分 sam2 propagation 与 sam3 video_track,避免两个模型链路混用。
- 打通前端“传播片段”:VideoWorkspace 使用当前选中 mask 和当前 AI 模型调用后端传播接口,传播结果回写并刷新工作区已保存标注。
- 增强 SAM3 本地 checkpoint 配置:新增 sam3_checkpoint_path 配置和 .env.example 示例,状态检查改为基于本地 checkpoint/独立环境/模型包可用性。
- 完善视频拆帧参数:/api/media/parse 支持 parse_fps、max_frames、target_width,后端任务保存帧时间戳、源帧号和 frame_sequence 元数据。
- 增加运行时 schema 兼容处理:启动时为旧 frames 表补充 timestamp_ms 和 source_frame_number 列,避免旧库升级后缺字段。
- 强化 Canvas 标注编辑:补齐多边形闭合、点工具、顶点拖拽、边中点插入、Delete/Backspace 删除、区域合并和重叠去除等交互。
- 增强语义分类联动:选中 mask 后可通过右侧语义分类树更新标签、颜色和 class metadata,并同步到保存/导出链路。
- 增加关键帧时间轴体验:FrameTimeline 显示具体时间信息,并支持键盘左右方向键切换关键帧。
- 完善 AI 交互分割参数:前端保留正向点、反向点、框选和 interactive prompt 的调用状态,支持 SAM2 细化候选区域与 SAM3 bbox 入口。
- 扩展后端/前端 API 类型:新增 propagateMasks、传播请求/响应 schema,并补齐 annotation、导出、模型状态和任务接口的测试覆盖。
- 更新项目文档:同步 README、AGENTS、接口契约、需求冻结、设计冻结、前端元素审计、实施计划和测试计划,标明真实功能边界与剩余风险。
- 增加测试覆盖:补充 SAM2/SAM3 传播、SAM3 状态、媒体拆帧参数、Canvas 编辑、语义标签切换、时间轴、工作区传播和 API 合约测试。
- 加强仓库安全边界:将 sam3权重/ 加入 .gitignore,避免本地模型权重被误提交。

验证:npm run test:run;pytest backend/tests;npm run lint;npm run build;python -m py_compile;git diff --check。
2026-05-01 20:27:33 +08:00

217 lines
7.9 KiB
Python

def test_upload_rejects_unsupported_file_type(client):
response = client.post(
"/api/media/upload",
files={"file": ("notes.txt", b"text", "text/plain")},
)
assert response.status_code == 400
assert "Unsupported file type" in response.json()["detail"]
def test_upload_auto_creates_project(client, monkeypatch):
uploaded = []
monkeypatch.setattr("routers.media.upload_file", lambda object_name, data, content_type, length: uploaded.append(object_name))
monkeypatch.setattr("routers.media.get_presigned_url", lambda object_name, expires=3600: f"http://storage/{object_name}")
response = client.post(
"/api/media/upload",
files={"file": ("clip.mp4", b"video", "video/mp4")},
)
assert response.status_code == 201
data = response.json()
assert data["project_id"] is not None
assert data["object_name"] == f"uploads/{data['project_id']}/clip.mp4"
assert uploaded == ["uploads/general/clip.mp4", f"uploads/{data['project_id']}/clip.mp4"]
def test_upload_links_existing_project(client, monkeypatch):
project = client.post("/api/projects", json={"name": "Existing"}).json()
monkeypatch.setattr("routers.media.upload_file", lambda *args, **kwargs: None)
monkeypatch.setattr("routers.media.get_presigned_url", lambda object_name, expires=3600: f"http://storage/{object_name}")
response = client.post(
"/api/media/upload",
data={"project_id": str(project["id"])},
files={"file": ("clip.mp4", b"video", "video/mp4")},
)
assert response.status_code == 201
detail = client.get(f"/api/projects/{project['id']}").json()
assert detail["video_path"] == f"uploads/{project['id']}/clip.mp4"
def test_upload_dicom_batch_filters_files_and_creates_project(client, monkeypatch):
uploaded = []
monkeypatch.setattr("routers.media.upload_file", lambda object_name, data, content_type, length: uploaded.append(object_name))
response = client.post(
"/api/media/upload/dicom",
files=[
("files", ("a.dcm", b"dcm", "application/dicom")),
("files", ("skip.txt", b"text", "text/plain")),
],
)
assert response.status_code == 201
data = response.json()
assert data["uploaded_count"] == 1
assert uploaded == [f"uploads/{data['project_id']}/dicom/a.dcm"]
def test_parse_media_queues_background_task(client, monkeypatch):
project = client.post("/api/projects", json={
"name": "Parse Me",
"video_path": "uploads/1/clip.mp4",
"source_type": "video",
"parse_fps": 5,
}).json()
class FakeAsyncResult:
id = "celery-1"
queued = []
monkeypatch.setattr("routers.media.parse_project_media.delay", lambda task_id: queued.append(task_id) or FakeAsyncResult())
published = []
monkeypatch.setattr("routers.media.publish_task_progress_event", lambda task: published.append(task.id))
response = client.post(f"/api/media/parse?project_id={project['id']}")
assert response.status_code == 202
data = response.json()
assert data["task_type"] == "parse_video"
assert data["status"] == "queued"
assert data["progress"] == 0
assert data["project_id"] == project["id"]
assert data["celery_task_id"] == "celery-1"
assert data["payload"] == {
"source_type": "video",
"parse_fps": 5.0,
"max_frames": None,
"target_width": 640,
}
assert queued == [data["id"]]
assert published == [data["id"]]
detail = client.get(f"/api/tasks/{data['id']}")
assert detail.status_code == 200
assert detail.json()["status"] == "queued"
project_detail = client.get(f"/api/projects/{project['id']}").json()
assert project_detail["status"] == "parsing"
def test_parse_media_accepts_frame_sequence_options(client, monkeypatch):
project = client.post("/api/projects", json={
"name": "Parse Options",
"video_path": "uploads/1/clip.mp4",
"source_type": "video",
"parse_fps": 30,
}).json()
class FakeAsyncResult:
id = "celery-options"
monkeypatch.setattr("routers.media.parse_project_media.delay", lambda task_id: FakeAsyncResult())
monkeypatch.setattr("routers.media.publish_task_progress_event", lambda task: None)
response = client.post(
f"/api/media/parse?project_id={project['id']}&parse_fps=15&max_frames=120&target_width=960"
)
assert response.status_code == 202
data = response.json()
assert data["payload"] == {
"source_type": "video",
"parse_fps": 15.0,
"max_frames": 120,
"target_width": 960,
}
assert client.get(f"/api/projects/{project['id']}").json()["parse_fps"] == 15.0
def test_parse_task_runner_registers_frames(client, db_session, monkeypatch, tmp_path):
from models import ProcessingTask
from services.media_task_runner import run_parse_media_task
project = client.post("/api/projects", json={
"name": "Parse Me",
"video_path": "uploads/1/clip.mp4",
"source_type": "video",
"parse_fps": 5,
}).json()
task = ProcessingTask(
task_type="parse_video",
status="queued",
progress=0,
project_id=project["id"],
payload={"source_type": "video"},
)
db_session.add(task)
db_session.commit()
db_session.refresh(task)
frame_file = tmp_path / "frame_000001.jpg"
frame_file.write_bytes(b"fake image")
monkeypatch.setattr("services.media_task_runner.download_file", lambda object_name: b"video")
monkeypatch.setattr(
"services.media_task_runner.parse_video",
lambda local_path, output_dir, fps, max_frames=None, target_width=640: ([str(frame_file)], 25.0),
)
monkeypatch.setattr("services.media_task_runner.extract_thumbnail", lambda local_path, thumbnail_path: open(thumbnail_path, "wb").write(b"thumb"))
monkeypatch.setattr("services.media_task_runner.upload_file", lambda *args, **kwargs: None)
monkeypatch.setattr("services.media_task_runner.upload_frames_to_minio", lambda frame_files, project_id: [f"projects/{project_id}/frames/frame_000001.jpg"])
monkeypatch.setattr("routers.projects.get_presigned_url", lambda object_name, expires=3600: f"http://storage/{object_name}")
published = []
monkeypatch.setattr(
"services.media_task_runner.publish_task_progress_event",
lambda event_task: published.append((event_task.status, event_task.progress, event_task.message)),
)
result = run_parse_media_task(db_session, task.id)
assert result["frames_extracted"] == 1
assert result["frame_sequence"] == {
"original_fps": 25.0,
"parse_fps": 5.0,
"frame_count": 1,
"duration_ms": 0.0,
"target_width": 640,
"frame_width": None,
"frame_height": None,
"max_frames": None,
"object_prefix": f"projects/{project['id']}/frames",
}
db_session.refresh(task)
assert task.status == "success"
assert task.progress == 100
assert ("running", 5, "后台解析已启动") in published
assert ("success", 100, "解析完成") in published
project_detail = client.get(f"/api/projects/{project['id']}").json()
assert project_detail["status"] == "ready"
frames = client.get(f"/api/projects/{project['id']}/frames").json()
assert "frame_000001.jpg" in frames[0]["image_url"]
assert frames[0]["timestamp_ms"] == 0.0
assert frames[0]["source_frame_number"] == 0
def test_parse_task_runner_skips_already_cancelled_task(db_session):
from models import ProcessingTask
from services.media_task_runner import run_parse_media_task
task = ProcessingTask(
task_type="parse_video",
status="cancelled",
progress=100,
message="任务已取消",
project_id=1,
payload={"source_type": "video"},
)
db_session.add(task)
db_session.commit()
db_session.refresh(task)
result = run_parse_media_task(db_session, task.id)
assert result["status"] == "cancelled"
assert result["message"] == "任务已取消"