tests/test_ocr_api.py

"""
Tests for the OCR API endpoint.
"""

import sys
import os
import pytest
from fastapi.testclient import TestClient
from unittest.mock import patch, AsyncMock

# Add project root to sys.path
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))

from main import app

client = TestClient(app)


@pytest.fixture
def mock_ocr_router():
    with patch("app.api.ocr.ocr_router") as mock:
        mock.extract = AsyncMock()
        yield mock


def test_ocr_endpoint_no_file():
    """Missing file should return 422 (Unprocessable Entity)."""
    response = client.post("/api/ai/ocr", headers={"X-API-Key": "test-api-key"})

def test_ocr_endpoint_invalid_file_type():
    """Non-image file should return 400."""
    files = {"file": ("test.txt", b"hello world", "text/plain")}
    data = {"document_type": "id_card"}
    response = client.post("/api/ai/ocr", files=files, data=data, headers={"X-API-Key": "test-api-key"})
    assert response.status_code == 400
    assert "not an image" in response.json()["detail"]


def test_ocr_endpoint_missing_document_type():
    """Missing document_type should return 422."""
    dummy_image = (
        b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01"
        b"\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00\x01"
        b"\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82"
    )
    files = {"file": ("test.png", dummy_image, "image/png")}
    response = client.post("/api/ai/ocr", files=files, headers={"X-API-Key": "test-api-key"})
    assert response.status_code == 422


def test_ocr_endpoint_invalid_document_type():
    """Invalid document_type value should return 422."""
    dummy_image = (
        b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01"
        b"\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00\x01"
        b"\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82"
    )
    files = {"file": ("test.png", dummy_image, "image/png")}
    data = {"document_type": "invalid_type"}
    response = client.post("/api/ai/ocr", files=files, data=data, headers={"X-API-Key": "test-api-key"})
    assert response.status_code == 422


def test_ocr_endpoint_success(mock_ocr_router):
    """Valid image + document_type should return 200 with extracted data."""
    mock_ocr_router.extract.return_value = {"_provider": "GeminiOCRProvider", "text": "صحيفة دعوى"}

    dummy_image = (
        b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01"
        b"\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00\x01"
        b"\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82"
    )
    files = {"file": ("test.png", dummy_image, "image/png")}
    data = {"document_type": "id_card"}

    response = client.post("/api/ai/ocr", files=files, data=data, headers={"X-API-Key": "test-api-key"})

    assert response.status_code == 200
    result = response.json()
    assert result["text"] == "صحيفة دعوى"
    assert result["_provider"] == "GeminiOCRProvider"
    mock_ocr_router.extract.assert_called_once()