Refactor/extensions custom dataset (#1562)

* Explanation how to use extension names in the config file

* Added information about extensions to the error message and control of the user input

* Easier to read code

* Replacing assert with raise

README.md

@@ -173,7 +173,7 @@ dataset:
   normal_test_dir: null # name of the folder containing normal test images.
   task: segmentation # classification or segmentation
   mask: <path/to/mask/annotations> #optional
-  extensions: null
+  extensions: null # .ext or [.ext1, .ext2, ...]
   split_ratio: 0.2 # ratio of the normal images that will be used to create a test split
   image_size: 256
   train_batch_size: 32

src/anomalib/data/utils/path.py

@@ -58,13 +58,16 @@ def _prepare_files_labels(
     if isinstance(extensions, str):
         extensions = (extensions,)
 
+    if not all(extension.startswith(".") for extension in extensions):
+        raise RuntimeError(f"All extensions {extensions} must start with the dot")
+
     filenames = [
         f
         for f in path.glob("**/*")
         if f.suffix in extensions and not f.is_dir() and not any(part.startswith(".") for part in f.parts)
     ]
     if not filenames:
-        raise RuntimeError(f"Found 0 {path_type} images in {path}")
+        raise RuntimeError(f"Found 0 {path_type} images in {path} with extensions {extensions}")
 
     labels = [path_type] * len(filenames)