From 8b0e213c07df3d6f4e304e2fcb0df3ab26fd8151 Mon Sep 17 00:00:00 2001
From: John Wilkie <john@v7labs.com>
Date: Wed, 18 Oct 2023 20:12:19 +0100
Subject: [PATCH] Undo accidental changes meant as part of IO-1445

---
 darwin/dataset/local_dataset.py | 24 +++++++++++++++--------
 darwin/dataset/utils.py         | 34 +++++++++++++++++++++------------
 2 files changed, 38 insertions(+), 20 deletions(-)

diff --git a/darwin/dataset/local_dataset.py b/darwin/dataset/local_dataset.py
index 01d2d1d89..c686f516a 100644
--- a/darwin/dataset/local_dataset.py
+++ b/darwin/dataset/local_dataset.py
@@ -95,15 +95,23 @@ def __init__(
         stems = build_stems(release_path, annotations_dir, annotation_type, split, partition, split_type)
 
         # Find all the annotations and their corresponding images
-        for annotation_path in sorted(annotations_dir.glob("**/*.json")):
-            darwin_json = parse_darwin_json(annotation_path)
-            image_path = images_dir / Path(darwin_json.full_path.lstrip('/\\'))
-            if image_path.exists():
-                self.images_path.append(image_path)
-                self.annotations_path.append(annotation_path)
-                continue
-            else:
+        for stem in stems:
+            annotation_path = annotations_dir / f"{stem}.json"
+            images = []
+            for ext in SUPPORTED_IMAGE_EXTENSIONS:
+                image_path = images_dir / f"{stem}{ext}"
+                if image_path.exists():
+                    images.append(image_path)
+                    continue
+                image_path = images_dir / f"{stem}{ext.upper()}"
+                if image_path.exists():
+                    images.append(image_path)
+            if len(images) < 1:
                 raise ValueError(f"Annotation ({annotation_path}) does not have a corresponding image")
+            if len(images) > 1:
+                raise ValueError(f"Image ({stem}) is present with multiple extensions. This is forbidden.")
+            self.images_path.append(images[0])
+            self.annotations_path.append(annotation_path)
 
         if len(self.images_path) == 0:
             raise ValueError(f"Could not find any {SUPPORTED_IMAGE_EXTENSIONS} file", f" in {images_dir}")
diff --git a/darwin/dataset/utils.py b/darwin/dataset/utils.py
index cdaae8ce2..3f3bb865f 100644
--- a/darwin/dataset/utils.py
+++ b/darwin/dataset/utils.py
@@ -434,19 +434,29 @@ def get_annotations(
 
     # Find all the annotations and their corresponding images
     invalid_annotation_paths = []
-    for annotation_path in annotations_dir.glob("**/*.json"):
-        darwin_json = parse_darwin_json(annotation_path)
-        image_path = images_dir / Path(darwin_json.full_path.lstrip('/\\'))
-        if image_path.exists():
-            images_paths.append(image_path)
-            annotations_paths.append(annotation_path)
-            continue
-        else:
-            if ignore_inconsistent_examples:
-                invalid_annotation_paths.append(annotation_path)
+    for stem in stems:
+        annotation_path = annotations_dir / f"{stem}.json"
+        images = []
+        for ext in SUPPORTED_EXTENSIONS:
+            image_path = images_dir / f"{stem}{ext}"
+            if image_path.exists():
+                images.append(image_path)
                 continue
-            else:
-                raise ValueError(f"Annotation ({annotation_path}) does not have a corresponding image")
+            image_path = images_dir / f"{stem}{ext.upper()}"
+            if image_path.exists():
+                images.append(image_path)
+
+        image_count = len(images)
+        if image_count != 1 and ignore_inconsistent_examples:
+            invalid_annotation_paths.append(annotation_path)
+            continue
+        elif image_count < 1:
+            raise ValueError(f"Annotation ({annotation_path}) does not have a corresponding image")
+        elif image_count > 1:
+            raise ValueError(f"Image ({stem}) is present with multiple extensions. This is forbidden.")
+
+        images_paths.append(images[0])
+        annotations_paths.append(annotation_path)
 
     print(f"Found {len(invalid_annotation_paths)} invalid annotations")
     for p in invalid_annotation_paths: