[Data] Raise error if PIL can't load image (ray-project#38030)

If you call read_images and PIL can't load a file, you get an unhelpful error message:

> PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x19997c350>

This PR updates the error message to include the path to the file

python/ray/data/datasource/image_datasource.py

@@ -76,13 +76,17 @@ def _read_file(
  include_paths: bool,
  **reader_args,
  ) -> "pyarrow.Table":
- from PIL import Image
+ from PIL import Image, UnidentifiedImageError
 
  records = super()._read_file(f, path, include_paths=True, **reader_args)
  assert len(records) == 1
  path, data = records[0]
 
- image = Image.open(io.BytesIO(data))
+ try:
+ image = Image.open(io.BytesIO(data))
+ except UnidentifiedImageError as e:
+ raise ValueError(f"PIL couldn't load image file at path '{path}'.") from e
+
  if size is not None:
  height, width = size
  image = image.resize((width, height))

python/ray/data/tests/test_image.py

@@ -1,4 +1,5 @@
 import os
+import tempfile
 from typing import Dict
 from unittest.mock import ANY, patch
 
@@ -256,6 +257,11 @@ def test_args_passthrough(ray_start_regular_shared):
  mock.assert_called_once_with(ANY, **kwargs)
  assert isinstance(mock.call_args[0][0], ImageDatasource)
 
+ def test_unidentified_image_error(ray_start_regular_shared):
+ with tempfile.NamedTemporaryFile(suffix=".png") as file:
+ with pytest.raises(ValueError):
+ ray.data.read_images(paths=file.name).materialize()
+
 
 if __name__ == "__main__":
  import sys