Spaces:
Sleeping
Sleeping
File size: 7,092 Bytes
fee2f22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | """API tests for core Phase 2.2 endpoints."""
from __future__ import annotations
from dataclasses import dataclass, field
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
from uuid import UUID, uuid4
import pytest
from fastapi.testclient import TestClient
from backend.app import app
from backend.database import get_db
from backend.models.cleaning_job import JobStatus
from backend.routes import datasets as datasets_routes
from backend.routes import jobs as jobs_routes
@dataclass
class DummyDataset:
"""Simple test double for Dataset ORM instances."""
id: UUID = field(default_factory=uuid4)
filename: str = "sample.csv"
file_path: str = ""
file_size: int = 128
rows: int = 3
columns: list[str] = field(default_factory=lambda: ["name", "age"])
data_quality_score: float = 0.7
@dataclass
class DummyJob:
"""Simple test double for CleaningJob ORM instances."""
id: UUID = field(default_factory=uuid4)
dataset_id: UUID = field(default_factory=uuid4)
status: JobStatus = JobStatus.QUEUED
created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
rows_processed: int = 0
total_rows: int = 0
result_score: float = 0.0
class FakeQuery:
def __init__(self, logs: list[dict[str, Any]]) -> None:
self.logs = logs
def filter(self, *_args: Any, **_kwargs: Any) -> "FakeQuery":
return self
def order_by(self, *_args: Any, **_kwargs: Any) -> "FakeQuery":
return self
def all(self) -> list[dict[str, Any]]:
return self.logs
class FakeDB:
"""Minimal fake DB session for API tests."""
def __init__(self, dataset: DummyDataset, job: DummyJob, logs: list[dict[str, Any]]) -> None:
self.dataset = dataset
self.job = job
self.logs = logs
def add(self, item: Any) -> None:
if hasattr(item, "filename"):
item.id = self.dataset.id
self.dataset = item
if hasattr(item, "dataset_id") and hasattr(item, "status"):
item.id = self.job.id
item.created_at = self.job.created_at
self.job = item
def commit(self) -> None:
return None
def flush(self) -> None:
return None
def refresh(self, item: Any) -> None:
if hasattr(item, "rows_processed"):
item.status = self.job.status
item.result_score = self.job.result_score
return None
def get(self, model: Any, item_id: UUID) -> Any:
name = getattr(model, "__name__", "")
if name == "Dataset" and item_id == self.dataset.id:
return self.dataset
if name == "CleaningJob" and item_id == self.job.id:
return self.job
return None
def query(self, _model: Any) -> FakeQuery:
return FakeQuery(self.logs)
@pytest.fixture()
def client(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> TestClient:
dataset_file = tmp_path / "sample.csv"
dataset_file.write_text("name,age\nalice,30\nbob,\ncharlie,22\n", encoding="utf-8")
dataset = DummyDataset(file_path=str(dataset_file))
job = DummyJob(dataset_id=dataset.id, total_rows=3)
logs = [
{
"id": str(uuid4()),
"job_id": job.id,
"action_type": "fill_missing",
"row_index": 1,
"column": "age",
"old_value": None,
"new_value": 25,
"reward": 0.2,
"agent_used": "FillMissingAgent",
"confidence": 0.88,
"timestamp": datetime.now(timezone.utc),
}
]
fake_db = FakeDB(dataset=dataset, job=job, logs=logs)
def _get_test_db() -> Any:
yield fake_db
app.dependency_overrides[get_db] = _get_test_db
monkeypatch.setattr(datasets_routes, "UPLOAD_DIR", tmp_path)
class _StubTask:
def delay(self, job_id: str) -> None:
assert job_id == str(job.id)
monkeypatch.setattr(jobs_routes, "clean_dataset", _StubTask())
app.state.test_dataset_id = dataset.id
app.state.test_job_id = job.id
test_client = TestClient(app)
yield test_client
app.dependency_overrides.clear()
def test_upload_dataset(client: TestClient) -> None:
response = client.post(
"/api/datasets/upload",
files={"file": ("upload.csv", b"name,age\nalice,30\nbob,\n", "text/csv")},
data={"task_name": "easy"},
)
assert response.status_code == 201
body = response.json()
assert "id" in body
assert body["filename"] == "upload.csv"
assert body["rows"] == 2
assert body["columns"] == ["name", "age"]
def test_get_dataset(client: TestClient) -> None:
known_dataset_id = str(app.state.test_dataset_id)
response = client.get(f"/api/datasets/{known_dataset_id}")
assert response.status_code == 200
body = response.json()
assert body["id"] == known_dataset_id
def test_start_batch_job(client: TestClient) -> None:
dataset_id = str(app.state.test_dataset_id)
response = client.post(
"/api/jobs/batch",
json={"dataset_id": dataset_id, "cleaning_mode": "conservative"},
)
assert response.status_code == 201
payload = response.json()
assert payload["status"] in {"completed", "queued", "processing"}
assert "job_id" in payload
def test_get_job_status(client: TestClient) -> None:
job_id = str(app.state.test_job_id)
response = client.get(f"/api/jobs/{job_id}")
assert response.status_code == 200
payload = response.json()
assert payload["id"] == job_id
assert 0.0 <= payload["progress"] <= 1.0
def test_interactive_step(client: TestClient) -> None:
job_id = str(app.state.test_job_id)
response = client.post(
"/api/inference/step",
json={
"job_id": job_id,
"row_data": {"name": "bob", "age": None},
"issues_detected": ["missing:age"],
},
)
assert response.status_code == 200
payload = response.json()
assert "action" in payload
assert "confidence" in payload
assert "agent_used" in payload
assert "explanation" in payload
def test_metrics_calculation(client: TestClient) -> None:
dataset_id = str(app.state.test_dataset_id)
response = client.get(f"/api/datasets/{dataset_id}/metrics")
assert response.status_code == 200
payload = response.json()
assert "original" in payload
assert "cleaned" in payload
assert "improvement" in payload
def test_upload_dataset_invalid_format(client: TestClient) -> None:
response = client.post(
"/api/datasets/upload",
files={"file": ("bad.txt", b"not,a,csv", "text/plain")},
data={"task_name": "easy"},
)
assert response.status_code == 400
assert "Invalid format" in response.json()["detail"]
def test_get_dataset_not_found(client: TestClient) -> None:
unknown_dataset_id = str(uuid4())
response = client.get(f"/api/datasets/{unknown_dataset_id}")
assert response.status_code == 404
assert response.json()["detail"] == "Dataset not found"
|