tests/test_app.py

import json

import pytest

from app import app as flask_app


@pytest.fixture
def app():
    yield flask_app


@pytest.fixture
def client(app):
    return app.test_client()


def test_health_endpoint(client):
    """
    Tests the /health endpoint.
    """
    response = client.get("/health")
    assert response.status_code == 200

    # Check that required fields are present
    response_data = response.json
    assert "status" in response_data
    assert "memory_mb" in response_data
    assert "timestamp" in response_data

    # Check status is ok
    assert response_data["status"] == "ok"

    # Check memory_mb is a number >= 0
    assert isinstance(response_data["memory_mb"], (int, float))
    assert response_data["memory_mb"] >= 0


def test_index_endpoint(client):
    """
    Tests the / endpoint.
    """
    response = client.get("/")
    assert response.status_code == 200


def test_ingest_endpoint_exists():
    """Test that the ingest endpoint is available"""
    from app import app

    client = app.test_client()
    response = client.post("/ingest")
    # Should not be 404 (not found)
    assert response.status_code != 404


class TestSearchEndpoint:
    """Test cases for the /search endpoint"""

    def test_search_endpoint_valid_request(self, client):
        """Test search endpoint with valid request"""
        request_data = {"query": "remote work policy", "top_k": 3, "threshold": 0.3}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 200
        data = response.get_json()

        assert data["status"] == "success"
        assert data["query"] == "remote work policy"
        assert "results_count" in data
        assert "results" in data
        assert isinstance(data["results"], list)

    def test_search_endpoint_minimal_request(self, client):
        """Test search endpoint with minimal request (only query)"""
        request_data = {"query": "employee benefits"}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 200
        data = response.get_json()

        assert data["status"] == "success"
        assert data["query"] == "employee benefits"

    def test_search_endpoint_missing_query(self, client):
        """Test search endpoint with missing query parameter"""
        request_data = {"top_k": 5}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 400
        data = response.get_json()

        assert data["status"] == "error"
        assert "Query parameter is required" in data["message"]

    def test_search_endpoint_empty_query(self, client):
        """Test search endpoint with empty query"""
        request_data = {"query": ""}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 400
        data = response.get_json()

        assert data["status"] == "error"
        assert "non-empty string" in data["message"]

    def test_search_endpoint_invalid_top_k(self, client):
        """Test search endpoint with invalid top_k parameter"""
        request_data = {"query": "test query", "top_k": -1}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 400
        data = response.get_json()

        assert data["status"] == "error"
        assert "positive integer" in data["message"]

    def test_search_endpoint_invalid_threshold(self, client):
        """Test search endpoint with invalid threshold parameter"""
        request_data = {"query": "test query", "threshold": 1.5}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 400
        data = response.get_json()

        assert data["status"] == "error"
        assert "between 0 and 1" in data["message"]

    def test_search_endpoint_non_json_request(self, client):
        """Test search endpoint with non-JSON request"""
        response = client.post("/search", data="not json", content_type="text/plain")

        assert response.status_code == 400
        data = response.get_json()

        assert data["status"] == "error"
        assert "application/json" in data["message"]

    def test_search_endpoint_result_structure(self, client):
        """Test that search results have the correct structure"""
        request_data = {"query": "policy"}

        response = client.post(
            "/search", data=json.dumps(request_data), content_type="application/json"
        )

        assert response.status_code == 200
        data = response.get_json()

        if data["results_count"] > 0:
            result = data["results"][0]
            assert "chunk_id" in result
            assert "content" in result
            assert "similarity_score" in result
            assert "metadata" in result
            assert isinstance(result["similarity_score"], (int, float))