feat: VRSub 单体应用(WOV 单机版)初始提交

为视频生成 VR 双眼字幕的单体实现:FastAPI 后端、调度器与全部节点
(提音/转写/翻译/ASS/抽帧/OCR/LLM 过滤)在单进程内运行。

- 节点协议(wov_sdk 数据模型)与分布式版保持一致,预留回退桥梁
- 工作流即数据:DAG 存于 workflows/*.json,模型/链路改动只改数据
- 调度器:拓扑顺序执行、断点续跑(产物重建)、任务暂停/继续
- 抽帧按帧间隔(select 按帧号精确取帧),VLM OCR 与 LLM 过滤使用
  自适应线程池弹性并发,并打印数据处理速度进度日志
- 100% 行覆盖率(pytest --cov-fail-under=100)
This commit is contained in:
2026-08-16 23:58:25 +08:00
commit 4746e0363f
75 changed files with 10969 additions and 0 deletions
+108
View File
@@ -0,0 +1,108 @@
"""种子数据测试。
验证从 workflows/*.json 数据文件加载默认工作流、幂等性,以及
开启种子与调度器后的应用生命周期。工作流定义来自数据文件而非代码。
"""
from pathlib import Path
from fastapi.testclient import TestClient
from wov_app.db import Database
from wov_app.main import app
from wov_app.seed import seed_default_workflows
# 单体根目录:tests/ 的上一级。
WORKSPACE = Path(__file__).resolve().parent.parent
def test_seed_default_workflows_idempotent(tmp_path) -> None:
"""验证从数据文件加载 demo/zh-direct 两个工作流且重复调用幂等。"""
db = Database(tmp_path / "wov.db")
created = seed_default_workflows(db)
assert created == 3
assert db.get_workflow("demo") is not None
assert db.get_workflow("zh-direct") is not None
# demoasr 显式声明 model_path 与长音频参数,模型选择完全数据化。
demo = db.get_latest_workflow_version("demo")["definition"]
assert demo["name"] == "视频字幕生成"
demo_asr = next(node for node in demo["nodes"] if node["id"] == "asr")
assert demo_asr["params"]["model_path"] == "faster-whisper-large-v3"
assert demo_asr["params"]["condition_on_previous_text"] is False
# zh-direct:使用中文直出模型并开启翻译任务。
zh = db.get_latest_workflow_version("zh-direct")["definition"]
assert zh["name"] == "中文直出字幕"
zh_asr = next(node for node in zh["nodes"] if node["id"] == "asr")
assert zh_asr["params"]["model_path"] == "whisper-large-v2-translate-zh-v0.2-st-ct2"
assert zh_asr["params"]["task"] == "translate"
# 再次调用不重复创建。
assert seed_default_workflows(db) == 0
assert len(db.list_workflow_versions("demo")) == 1
def test_seed_custom_dir_and_empty(tmp_path) -> None:
"""验证自定义数据目录的加载与空目录返回 0。"""
db = Database(tmp_path / "wov.db")
custom = tmp_path / "workflows"
custom.mkdir()
(custom / "a.json").write_text(
"""
{
"id": "flow-a",
"name": "Flow A",
"description": "custom",
"version": 1,
"definition": {
"name": "Flow A",
"version": 1,
"nodes": [{"id": "step", "node_type": "echo"}],
"edges": [],
"entry_inputs": {},
"final_outputs": {}
}
}
""",
encoding="utf-8",
)
assert seed_default_workflows(db, custom) == 1
assert db.get_workflow("flow-a") is not None
# 空目录返回 0。
empty = tmp_path / "empty"
empty.mkdir()
assert seed_default_workflows(db, empty) == 0
# 已存在的工作流被跳过。
assert seed_default_workflows(db, custom) == 0
def test_lifespan_with_seed_and_scheduler(monkeypatch) -> None:
"""验证启用自动种子与调度器后应用正常启动,demo 与中文直出应用均可见。"""
monkeypatch.setenv("WOV_AUTO_SEED", "1")
monkeypatch.setenv("WOV_SCHEDULER_ENABLED", "1")
with TestClient(app) as client:
apps = client.get("/api/apps")
assert apps.status_code == 200
assert any(item["id"] == "demo" for item in apps.json())
assert any(item["id"] == "zh-direct" for item in apps.json())
def test_seed_workflows_have_chunk_seconds(tmp_path) -> None:
"""验证内置工作流的 asr 节点均显式声明分块参数。"""
db = Database(tmp_path / "wov.db")
seed_default_workflows(db)
for workflow_id in ("demo", "zh-direct"):
definition = db.get_latest_workflow_version(workflow_id)["definition"]
asr = next(node for node in definition["nodes"] if node["id"] == "asr")
assert asr["params"]["chunk_seconds"] == 60
def test_seed_workflows_vad_filter_off(tmp_path) -> None:
"""验证内置工作流 asr 显式开启 VAD。"""
db = Database(tmp_path / "wov.db")
seed_default_workflows(db)
for workflow_id in ("demo", "zh-direct"):
definition = db.get_latest_workflow_version(workflow_id)["definition"]
asr = next(node for node in definition["nodes"] if node["id"] == "asr")
assert asr["params"]["vad_filter"] is True