RED-5202 port temporary broken image handling so the hotfix won't be lost by upgrading the service. A proper solution is still desirable (see RED-5148)

image_prediction/image_extractor/extractors/parsable.py

@@ -1,14 +1,17 @@
 import atexit
 import io
+import json
+import traceback
 from functools import partial, lru_cache
 from itertools import chain, starmap, filterfalse
-from operator import itemgetter
+from operator import itemgetter, truth
 from typing import List
 
 import fitz
 from PIL import Image
 from funcy import rcompose, merge, pluck, curry, compose
 
+from image_prediction.formatter.formatters.enum import EnumFormatter
 from image_prediction.image_extractor.extractor import ImageExtractor, ImageMetadataPair
 from image_prediction.info import Info
 from image_prediction.stitching.stitching import stitch_pairs
@@ -47,10 +50,28 @@ class ParsablePDFImageExtractor(ImageExtractor):
         clear_caches()
 
         image_metadata_pairs = starmap(ImageMetadataPair, filter(all, zip(images, metadata)))
+        #  TODO: In the future, consider to introduce an image validator as a pipeline component rather than doing the
+        #   validation here. Invalid images can then be split into a different stream and joined with the intact images
+        #   again for the formatting step.
+        image_metadata_pairs = self.__filter_valid_images(image_metadata_pairs)
         image_metadata_pairs = stitch_pairs(list(image_metadata_pairs), tolerance=self.tolerance)
 
         yield from image_metadata_pairs
 
+    @staticmethod
+    def __filter_valid_images(image_metadata_pairs):
+        def validate(image: Image.Image, metadata: dict):
+            try:
+                # TODO: stand-in heuristic for testing if image is valid => find cleaner solution (RED-5148)
+                image.resize((100, 100)).convert("RGB")
+                return ImageMetadataPair(image, metadata)
+            except (OSError, Exception) as err:
+                metadata = json.dumps(EnumFormatter()(metadata), indent=2)
+                logger.warning(f"Invalid image encountered. Image metadata:\n{metadata}\n\n{traceback.format_exc()}")
+                return None
+
+        return filter(truth, starmap(validate, image_metadata_pairs))
+
 
 def extract_pages(doc, page_range):
     page_range = range(page_range.start + 1, page_range.stop + 1)