44 lines
1.6 KiB
Python
44 lines
1.6 KiB
Python
import random
|
|
|
|
import fitz
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from image_prediction.estimator.preprocessor.utils import images_to_batch_tensor
|
|
from image_prediction.extraction import extract_images_from_pdf
|
|
from image_prediction.image_extractor.extractors.parsable import extract_pages
|
|
|
|
|
|
@pytest.mark.parametrize("extractor_type", ["mock"])
|
|
@pytest.mark.parametrize("batch_size", [1, 2, 16])
|
|
def test_image_extractor_mock(image_extractor, images):
|
|
images_extracted, metadata = map(list, zip(*image_extractor(images)))
|
|
assert images_extracted == images
|
|
|
|
|
|
@pytest.mark.parametrize("extractor_type", ["parsable_pdf", "default"])
|
|
@pytest.mark.parametrize(
|
|
"input_size",
|
|
[{"depth": 3, "width": 170, "height": 220}, {"depth": 3, "width": 170, "height": 220}],
|
|
indirect=["input_size"],
|
|
)
|
|
def test_parsable_pdf_image_extractor(image_extractor, pdf, images, metadata, input_size):
|
|
images_extracted, metadata_extracted = map(list, extract_images_from_pdf(pdf, image_extractor))
|
|
assert np.allclose(images_to_batch_tensor(images_extracted), images_to_batch_tensor(images))
|
|
assert list(metadata_extracted) == metadata
|
|
|
|
|
|
@pytest.mark.parametrize("batch_size", [1, 2, 16])
|
|
def test_extract_pages(pdf):
|
|
doc = fitz.Document(stream=pdf)
|
|
|
|
max_index = max(0, doc.page_count - 1)
|
|
i = random.randint(0, max(0, max_index - 1))
|
|
j = random.randint(i + 1, max_index) if max_index > 0 else 0
|
|
|
|
page_range = range(i, j)
|
|
|
|
pages = list(extract_pages(doc, page_range))
|
|
assert all((isinstance(p, fitz.Page) for p in pages))
|
|
assert len(pages) == len(page_range)
|