Merge branch 'release/1.2.x' of ssh://git.iqser.com:2222/rr/image-prediction into RED-5107-robustify-image-service

image_prediction/image_extractor/extractors/parsable.py

@@ -50,6 +50,20 @@ class ParsablePDFImageExtractor(ImageExtractor):
 
         yield from image_metadata_pairs
 
+    # def __preprocess(self, image_metadata_pair):
+    #     image, metadata = image_metadata_pair
+    #
+    #     try:
+    #         image = self.__resize_and_convert(image)
+    #         image_metadata_pair = ImageMetadataPair(image, metadata)
+    #     except Exception as err:
+    #         logger.warn(
+    #             f"{err}: couldn't preprocess image [ page_idx: {metadata[Info.PAGE_IDX]}, x1: {metadata[Info.X1]}, y1: {metadata[Info.Y1]}, width: {metadata[Info.WIDTH]}, height: {metadata[Info.HEIGHT]} ]"
+    #         )
+    #         image_metadata_pair = None
+    #
+    #     return image_metadata_pair
+
 
 def extract_pages(doc, page_range):
     page_range = range(page_range.start + 1, page_range.stop + 1)

test/unit_tests/image_extractor_test.py

@@ -5,7 +5,7 @@ import fitz
 import fpdf
 import pytest
 from PIL import Image
-from funcy import first, rest
+from funcy import first, rest, lmap
 
 from image_prediction.extraction import extract_images_from_pdf
 from image_prediction.image_extractor.extractor import ImageMetadataPair
@@ -27,6 +27,7 @@ def test_image_extractor_mock(image_extractor, images):
 @pytest.mark.parametrize("alpha", [False, True])
 def test_parsable_pdf_image_extractor(image_extractor, pdf, images, metadata, input_size, alpha):
     images_extracted, metadata_extracted = map(list, extract_images_from_pdf(pdf, image_extractor))
+
     if not alpha:
         assert image_sets_equal(images_extracted, images)
     assert metadata_equal(metadata_extracted, metadata)