from pathlib import Path

from image_prediction.encoder.encoders.hash_encoder import HashEncoder
from image_prediction.image_extractor.extractors.parsable import ParsablePDFImageExtractor


def test_all_hashes_have_length_of_twentyfive():
    """See RED-3814: all hashes should have 25 characters."""
    pdf_path = Path(__file__).parents[1] / "data" / "RED-3814" / "similarImages2.pdf"
    pdf_bytes = pdf_path.read_bytes()
    image_extractor = ParsablePDFImageExtractor()
    image_metadata_pairs = list(image_extractor.extract(pdf_bytes))
    images = [image for image, _ in image_metadata_pairs]

    hash_encoder = HashEncoder()
    hashes = list(hash_encoder.encode(images))

    assert all(len(h) == 25 for h in hashes)