ss-tools/backend/src/api/routes/__tests__/test_datasets.py

# [DEF:backend.src.api.routes.__tests__.test_datasets:Module]
# @TIER: STANDARD
# @SEMANTICS: datasets, api, tests, pagination, mapping, docs
# @PURPOSE: Unit tests for Datasets API endpoints
# @LAYER: API
# @RELATION: TESTS -> backend.src.api.routes.datasets
# @INVARIANT: Endpoint contracts remain stable for success and validation failure paths.

import pytest
from unittest.mock import MagicMock, patch, AsyncMock
from fastapi.testclient import TestClient
from src.app import app
from src.api.routes.datasets import DatasetsResponse, DatasetDetailResponse
from src.dependencies import get_current_user, has_permission, get_config_manager, get_task_manager, get_resource_service, get_mapping_service

# Global mock user for get_current_user dependency overrides
mock_user = MagicMock()
mock_user.username = "testuser"
mock_user.roles = []
admin_role = MagicMock()
admin_role.name = "Admin"
mock_user.roles.append(admin_role)

@pytest.fixture(autouse=True)
def mock_deps():
    config_manager = MagicMock()
    task_manager = MagicMock()
    resource_service = MagicMock()
    mapping_service = MagicMock()
    
    app.dependency_overrides[get_config_manager] = lambda: config_manager
    app.dependency_overrides[get_task_manager] = lambda: task_manager
    app.dependency_overrides[get_resource_service] = lambda: resource_service
    app.dependency_overrides[get_mapping_service] = lambda: mapping_service
    app.dependency_overrides[get_current_user] = lambda: mock_user
    
    app.dependency_overrides[has_permission("plugin:migration", "READ")] = lambda: mock_user
    app.dependency_overrides[has_permission("plugin:migration", "EXECUTE")] = lambda: mock_user
    app.dependency_overrides[has_permission("plugin:backup", "EXECUTE")] = lambda: mock_user
    app.dependency_overrides[has_permission("tasks", "READ")] = lambda: mock_user
    
    yield {
        "config": config_manager,
        "task": task_manager,
        "resource": resource_service,
        "mapping": mapping_service
    }
    app.dependency_overrides.clear()

client = TestClient(app)


# [DEF:test_get_datasets_success:Function]
# @PURPOSE: Validate successful datasets listing contract for an existing environment.
# @TEST: GET /api/datasets returns 200 and valid schema
# @PRE: env_id exists
# @POST: Response matches DatasetsResponse schema
def test_get_datasets_success(mock_deps):
    # Mock environment
    mock_env = MagicMock()
    mock_env.id = "prod"
    mock_deps["config"].get_environments.return_value = [mock_env]
    
    # Mock resource service response
    mock_deps["resource"].get_datasets_with_status = AsyncMock(
        return_value=[
            {
                "id": 1,
                "table_name": "sales_data",
                "schema": "public",
                "database": "sales_db",
                "mapped_fields": {"total": 10, "mapped": 5},
                "last_task": {"task_id": "task-1", "status": "SUCCESS"}
            }
        ]
    )

    response = client.get("/api/datasets?env_id=prod")
    
    assert response.status_code == 200
    data = response.json()
    assert "datasets" in data
    assert len(data["datasets"]) >= 0
    # Validate against Pydantic model
    DatasetsResponse(**data)


# [/DEF:test_get_datasets_success:Function]


# [DEF:test_get_datasets_env_not_found:Function]
# @TEST: GET /api/datasets returns 404 if env_id missing
# @PRE: env_id does not exist
# @POST: Returns 404 error
def test_get_datasets_env_not_found(mock_deps):
    mock_deps["config"].get_environments.return_value = []

    response = client.get("/api/datasets?env_id=nonexistent")
    
    assert response.status_code == 404
    assert "Environment not found" in response.json()["detail"]


# [/DEF:test_get_datasets_env_not_found:Function]


# [DEF:test_get_datasets_invalid_pagination:Function]
# @TEST: GET /api/datasets returns 400 for invalid page/page_size
# @PRE: page < 1 or page_size > 100
# @POST: Returns 400 error
def test_get_datasets_invalid_pagination(mock_deps):
    mock_env = MagicMock()
    mock_env.id = "prod"
    mock_deps["config"].get_environments.return_value = [mock_env]

    # Invalid page
    response = client.get("/api/datasets?env_id=prod&page=0")
    assert response.status_code == 400
    assert "Page must be >= 1" in response.json()["detail"]
    
    # Invalid page_size (too small)
    response = client.get("/api/datasets?env_id=prod&page_size=0")
    assert response.status_code == 400
    assert "Page size must be between 1 and 100" in response.json()["detail"]

    # @TEST_EDGE: page_size > 100 exceeds max
    response = client.get("/api/datasets?env_id=prod&page_size=101")
    assert response.status_code == 400
    assert "Page size must be between 1 and 100" in response.json()["detail"]


# [/DEF:test_get_datasets_invalid_pagination:Function]


# [DEF:test_map_columns_success:Function]
# @TEST: POST /api/datasets/map-columns creates mapping task
# @PRE: Valid env_id, dataset_ids, source_type
# @POST: Returns task_id
def test_map_columns_success(mock_deps):
    # Mock environment
    mock_env = MagicMock()
    mock_env.id = "prod"
    mock_deps["config"].get_environments.return_value = [mock_env]
    
    # Mock task manager
    mock_task = MagicMock()
    mock_task.id = "task-123"
    mock_deps["task"].create_task = AsyncMock(return_value=mock_task)

    response = client.post(
        "/api/datasets/map-columns",
        json={
            "env_id": "prod",
            "dataset_ids": [1, 2, 3],
            "source_type": "postgresql"
        }
    )
    
    assert response.status_code == 200
    data = response.json()
    assert "task_id" in data
    # @POST/@SIDE_EFFECT: create_task was called
    mock_deps["task"].create_task.assert_called_once()


# [/DEF:test_map_columns_success:Function]


# [DEF:test_map_columns_invalid_source_type:Function]
# @TEST: POST /api/datasets/map-columns returns 400 for invalid source_type
# @PRE: source_type is not 'postgresql' or 'xlsx'
# @POST: Returns 400 error
def test_map_columns_invalid_source_type(mock_deps):
    response = client.post(
        "/api/datasets/map-columns",
        json={
            "env_id": "prod",
            "dataset_ids": [1],
            "source_type": "invalid"
        }
    )
    
    assert response.status_code == 400
    assert "Source type must be 'postgresql' or 'xlsx'" in response.json()["detail"]


# [/DEF:test_map_columns_invalid_source_type:Function]


# [DEF:test_generate_docs_success:Function]
# @TEST: POST /api/datasets/generate-docs creates doc generation task
# @PRE: Valid env_id, dataset_ids, llm_provider
# @POST: Returns task_id
def test_generate_docs_success(mock_deps):
    # Mock environment
    mock_env = MagicMock()
    mock_env.id = "prod"
    mock_deps["config"].get_environments.return_value = [mock_env]
    
    # Mock task manager
    mock_task = MagicMock()
    mock_task.id = "task-456"
    mock_deps["task"].create_task = AsyncMock(return_value=mock_task)

    response = client.post(
        "/api/datasets/generate-docs",
        json={
            "env_id": "prod",
            "dataset_ids": [1],
            "llm_provider": "openai"
        }
    )
    
    assert response.status_code == 200
    data = response.json()
    assert "task_id" in data
    # @POST/@SIDE_EFFECT: create_task was called
    mock_deps["task"].create_task.assert_called_once()


# [/DEF:test_generate_docs_success:Function]


# [DEF:test_map_columns_empty_ids:Function]
# @TEST: POST /api/datasets/map-columns returns 400 for empty dataset_ids
# @PRE: dataset_ids is empty
# @POST: Returns 400 error
def test_map_columns_empty_ids(mock_deps):
    """@PRE: dataset_ids must be non-empty."""
    response = client.post(
        "/api/datasets/map-columns",
        json={
            "env_id": "prod",
            "dataset_ids": [],
            "source_type": "postgresql"
        }
    )
    assert response.status_code == 400
    assert "At least one dataset ID must be provided" in response.json()["detail"]
# [/DEF:test_map_columns_empty_ids:Function]


# [DEF:test_generate_docs_empty_ids:Function]
# @TEST: POST /api/datasets/generate-docs returns 400 for empty dataset_ids
# @PRE: dataset_ids is empty
# @POST: Returns 400 error
def test_generate_docs_empty_ids(mock_deps):
    """@PRE: dataset_ids must be non-empty."""
    response = client.post(
        "/api/datasets/generate-docs",
        json={
            "env_id": "prod",
            "dataset_ids": [],
            "llm_provider": "openai"
        }
    )
    assert response.status_code == 400
    assert "At least one dataset ID must be provided" in response.json()["detail"]
# [/DEF:test_generate_docs_empty_ids:Function]


# [DEF:test_generate_docs_env_not_found:Function]
# @TEST: POST /api/datasets/generate-docs returns 404 for missing env
# @PRE: env_id does not exist
# @POST: Returns 404 error
def test_generate_docs_env_not_found(mock_deps):
    """@PRE: env_id must be a valid environment."""
    mock_deps["config"].get_environments.return_value = []
    response = client.post(
        "/api/datasets/generate-docs",
        json={
            "env_id": "ghost",
            "dataset_ids": [1],
            "llm_provider": "openai"
        }
    )
    assert response.status_code == 404
    assert "Environment not found" in response.json()["detail"]
# [/DEF:test_generate_docs_env_not_found:Function]


# [DEF:test_get_datasets_superset_failure:Function]
# @TEST_EDGE: external_superset_failure -> {status: 503}
def test_get_datasets_superset_failure(mock_deps):
    """@TEST_EDGE: external_superset_failure -> {status: 503}"""
    mock_env = MagicMock()
    mock_env.id = "bad_conn"
    mock_deps["config"].get_environments.return_value = [mock_env]
    mock_deps["task"].get_all_tasks.return_value = []
    mock_deps["resource"].get_datasets_with_status = AsyncMock(
        side_effect=Exception("Connection refused")
    )

    response = client.get("/api/datasets?env_id=bad_conn")
    assert response.status_code == 503
    assert "Failed to fetch datasets" in response.json()["detail"]
# [/DEF:test_get_datasets_superset_failure:Function]


# [/DEF:backend.src.api.routes.__tests__.test_datasets:Module]