Allow image+annotation generator to give mirrored URLs (#433)

* Allow image+annotation generator to give mirrored URLs

* add to docstring

Author: edwardpark97

nucleus/dataset.py

@@ -1447,11 +1447,13 @@ def items_and_annotations(
     def items_and_annotation_generator(
         self,
         query: Optional[str] = None,
+        use_mirrored_images: bool = False,
     ) -> Iterable[Dict[str, Union[DatasetItem, Dict[str, List[Annotation]]]]]:
         """Provides a generator of all DatasetItems and Annotations in the dataset.
 
         Args:
             query: Structured query compatible with the `Nucleus query language <https://nucleus.scale.com/docs/query-language-reference>`_.
+            use_mirrored_images: If True, returns the location of the mirrored image hosted in Scale S3. Useful when the original image is no longer available.
 
         Returns:
             Generator where each element is a dict containing the DatasetItem
@@ -1477,6 +1479,7 @@ def items_and_annotation_generator(
             result_key=EXPORT_FOR_TRAINING_KEY,
             page_size=10000,  # max ES page size
             query=query,
+            chip=use_mirrored_images,
         )
         for data in json_generator:
             for ia in convert_export_payload([data], has_predictions=False):

nucleus/dataset_item.py

@@ -18,6 +18,7 @@
     METADATA_KEY,
     ORIGINAL_IMAGE_URL_KEY,
     POINTCLOUD_URL_KEY,
+    PROCESSED_URL_KEY,
     REFERENCE_ID_KEY,
     TYPE_KEY,
     URL_KEY,
@@ -156,8 +157,10 @@ def __post_init__(self):
     @classmethod
     def from_json(cls, payload: dict):
         """Instantiates dataset item object from schematized JSON dict payload."""
-        image_url = payload.get(IMAGE_URL_KEY, None) or payload.get(
-            ORIGINAL_IMAGE_URL_KEY, None
+        image_url = (
+            payload.get(PROCESSED_URL_KEY, None)
+            or payload.get(IMAGE_URL_KEY, None)
+            or payload.get(ORIGINAL_IMAGE_URL_KEY, None)
         )
         pointcloud_url = payload.get(POINTCLOUD_URL_KEY, None)