b392bc3570
Create libs/ai-services/ with FastAPI app providing: - POST /avm/predict — XGBoost-backed property price prediction (heuristic fallback) - POST /avm/extract-features — Vietnamese NLP feature extraction from listing text - POST /moderation/check — content moderation with rule-based flagging - GET /health — health check endpoint Includes Dockerfile (Python 3.12), docker-compose integration, Pydantic models, and 9 passing tests covering all endpoints. Co-Authored-By: Paperclip <noreply@paperclip.ing>
51 lines
1.5 KiB
Python
51 lines
1.5 KiB
Python
from fastapi.testclient import TestClient
|
|
|
|
from app.main import app
|
|
|
|
client = TestClient(app)
|
|
|
|
|
|
def test_clean_text():
|
|
resp = client.post(
|
|
"/moderation/check",
|
|
json={"text": "Bán căn hộ đẹp tại quận 1", "context": "listing"},
|
|
)
|
|
assert resp.status_code == 200
|
|
data = resp.json()
|
|
assert data["is_flagged"] is False
|
|
assert data["score"] == 0.0
|
|
|
|
|
|
def test_phone_number_flagged():
|
|
resp = client.post(
|
|
"/moderation/check",
|
|
json={"text": "Liên hệ 0912345678 để xem nhà", "context": "listing"},
|
|
)
|
|
assert resp.status_code == 200
|
|
data = resp.json()
|
|
assert data["is_flagged"] is True
|
|
assert any(f["category"] == "contact_info" for f in data["flags"])
|
|
assert "[REDACTED]" in data["cleaned_text"]
|
|
|
|
|
|
def test_scam_language_flagged():
|
|
resp = client.post(
|
|
"/moderation/check",
|
|
json={"text": "Cảnh báo lừa đảo từ chủ nhà", "context": "comment"},
|
|
)
|
|
assert resp.status_code == 200
|
|
data = resp.json()
|
|
assert data["is_flagged"] is True
|
|
assert any(f["category"] == "profanity" for f in data["flags"])
|
|
|
|
|
|
def test_prohibited_property():
|
|
resp = client.post(
|
|
"/moderation/check",
|
|
json={"text": "Bán lô đất rừng phòng hộ 500m2", "context": "listing"},
|
|
)
|
|
assert resp.status_code == 200
|
|
data = resp.json()
|
|
assert data["is_flagged"] is True
|
|
assert any(f["category"] == "prohibited_content" for f in data["flags"])
|