2a353040f6
G.2.5 - Tests: - Add pytest test suite with fixtures - test_preprocessing.py - PDF/image loading, normalization, validation - test_postprocessing.py - chunks, QA pairs, markdown generation - test_inference.py - dummy parser and inference functions - test_api.py - API endpoint tests - Add pytest.ini configuration G.1.3 - dots.ocr Integration: - Update model_loader.py with real model loading code - Support for AutoModelForVision2Seq and AutoProcessor - Device handling (CUDA/CPU/MPS) with fallback - Error handling with dummy fallback option - Update inference.py with real model inference - Process images through model - Generate and decode outputs - Parse model output to blocks - Add model_output_parser.py - Parse JSON or plain text model output - Convert to structured blocks - Layout detection support (placeholder) Dependencies: - Add pytest, pytest-asyncio, httpx for testing
54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
"""
|
|
Tests for inference functions
|
|
"""
|
|
|
|
import pytest
|
|
from PIL import Image
|
|
|
|
from app.runtime.inference import (
|
|
parse_document_from_images,
|
|
dummy_parse_document_from_images
|
|
)
|
|
from app.core.config import settings
|
|
|
|
|
|
class TestDummyParser:
|
|
"""Tests for dummy parser"""
|
|
|
|
def test_dummy_parse_document_from_images(self):
|
|
"""Test dummy parser with images"""
|
|
images = [
|
|
Image.new('RGB', (800, 600), color='white'),
|
|
Image.new('RGB', (800, 600), color='white')
|
|
]
|
|
|
|
doc = dummy_parse_document_from_images(images, doc_id="test-doc")
|
|
|
|
assert doc.doc_id == "test-doc"
|
|
assert len(doc.pages) == 2
|
|
assert all(len(page.blocks) > 0 for page in doc.pages)
|
|
assert all(page.width == 800 for page in doc.pages)
|
|
assert all(page.height == 600 for page in doc.pages)
|
|
|
|
|
|
class TestParseDocumentFromImages:
|
|
"""Tests for parse_document_from_images"""
|
|
|
|
def test_parse_document_from_images_dummy_mode(self, monkeypatch):
|
|
"""Test parsing with dummy mode enabled"""
|
|
monkeypatch.setenv("USE_DUMMY_PARSER", "true")
|
|
from app.core.config import Settings
|
|
settings = Settings()
|
|
|
|
images = [Image.new('RGB', (800, 600), color='white')]
|
|
doc = parse_document_from_images(images, doc_id="test-doc")
|
|
|
|
assert doc.doc_id == "test-doc"
|
|
assert len(doc.pages) == 1
|
|
|
|
def test_parse_document_from_images_empty(self):
|
|
"""Test parsing with empty images list"""
|
|
with pytest.raises(ValueError, match="No valid images"):
|
|
parse_document_from_images([], doc_id="test-doc")
|
|
|