add support for broken images to hash encoding

image_prediction/encoder/encoders/hash_encoder.py

@@ -3,16 +3,28 @@ from typing import Iterable
 from PIL import Image
 
 from image_prediction.encoder.encoder import Encoder
+from image_prediction.utils import get_logger
+
+logger = get_logger()
 
 
 class HashEncoder(Encoder):
     def encode(self, images: Iterable[Image.Image]):
-        yield from map(hash_image, images)
+        yield from map(_monitored_hashing, images)
 
     def __call__(self, images: Iterable[Image.Image], batch_size=16):
         yield from self.encode(images)
 
 
+def _monitored_hashing(image):
+    try:  # RED-5170: fails if image is 'broken'
+        image_hash = hash_image(image)
+    except (OSError, Exception) as err:
+        logger.warn(f"{err}: Couldn't hash image, generate dummy hash.")
+        image_hash = "F" * 25
+    return image_hash
+
+
 def hash_image(image: Image.Image):
     """See: https://stackoverflow.com/a/49692185/3578468"""
     image = image.resize((10, 10), Image.ANTIALIAS)

image_prediction/stitching/merging.py

@@ -190,7 +190,7 @@ def concat_images(im1: Image, im2: Image, metadata: dict, axis):
 
         try:  # RED-5170: fails if image is 'broken'
             im_aggr.paste(im, box=box)
-        except Exception as err:
+        except (OSError, Exception) as err:
             logger.warn(
                 f"{err}: Couldn't merge image, replace broken part by blank image and passthrough. (page: {metadata[Info.PAGE_IDX]})"
             )