Merge pull request #20694 from arash77/fix_encoded_id_datasets_on_release_25.0

[25.0] Fix dataset serializers and response models

Author: mvdbeek

client/src/api/schema/schema.ts

@@ -11284,6 +11284,11 @@ export interface components {
             copied_from_history_dataset_association_id?: string | null;
             /** Copied From Ldda Id */
             copied_from_ldda_id?: string | null;
+            /**
+             * Copied From Library Dataset Dataset Association Id
+             * @description ID of LDDA this HDA was copied from.
+             */
+            copied_from_library_dataset_dataset_association_id?: string | null;
             /**
              * Create Time
              * @description The time and date this item was created.
@@ -11533,6 +11538,11 @@ export interface components {
             copied_from_history_dataset_association_id?: string | null;
             /** Copied From Ldda Id */
             copied_from_ldda_id?: string | null;
+            /**
+             * Copied From Library Dataset Dataset Association Id
+             * @description ID of LDDA this HDA was copied from.
+             */
+            copied_from_library_dataset_dataset_association_id?: string | null;
             /**
              * Create Time
              * @description The time and date this item was created.

lib/galaxy/managers/datasets.py

@@ -652,7 +652,7 @@ def add_serializers(self):
             "file_size": lambda item, key, **context: self.serializers["size"](item, key, **context),
             "nice_size": lambda item, key, **context: item.get_size(nice_size=True, calculate_size=False),
             # common to lddas and hdas - from mapping.py
-            "copied_from_history_dataset_association_id": lambda item, key, **context: item.id,
+            "copied_from_history_dataset_association_id": self.serialize_id,
             "copied_from_library_dataset_dataset_association_id": self.serialize_id,
             "info": lambda item, key, **context: item.info.strip() if isinstance(item.info, str) else item.info,
             "blurb": lambda item, key, **context: item.blurb,

lib/galaxy/managers/hdas.py

@@ -576,14 +576,6 @@ def __init__(self, app: StructuredApp):
             ["accessible", "id", "name", "history_id", "hid", "history_content_type", "state", "deleted", "visible"],
         )
 
-    def serialize_copied_from_ldda_id(self, item, key, **context):
-        """
-        Serialize an id attribute of `item`.
-        """
-        if item.copied_from_library_dataset_dataset_association is not None:
-            return self.app.security.encode_id(item.copied_from_library_dataset_dataset_association.id)
-        return None
-
     def add_serializers(self):
         super().add_serializers()
         taggable.TaggableSerializerMixin.add_serializers(self)
@@ -595,7 +587,9 @@ def add_serializers(self):
             "history_content_type": lambda item, key, **context: "dataset",
             "hda_ldda": lambda item, key, **context: "hda",
             "type_id": self.serialize_type_id,
-            "copied_from_ldda_id": self.serialize_copied_from_ldda_id,
+            "copied_from_ldda_id": lambda item, key, **context: self.serialize_id(
+                item, "copied_from_library_dataset_dataset_association_id", **context
+            ),
             "history_id": self.serialize_id,
             # remapped
             "misc_info": self._remap_from("info"),

lib/galaxy/schema/schema.py

@@ -942,6 +942,9 @@ class HDADetailed(HDASummary, WithModelClass):
     copied_from_history_dataset_association_id: Annotated[
         Optional[EncodedDatabaseIdField], Field(None, description="ID of HDA this HDA was copied from.")
     ]
+    copied_from_library_dataset_dataset_association_id: Annotated[
+        Optional[EncodedDatabaseIdField], Field(None, description="ID of LDDA this HDA was copied from.")
+    ]
 
 
 class HDAExtended(HDADetailed):

lib/galaxy_test/api/test_datasets.py

@@ -920,3 +920,33 @@ def test_download_non_english_characters(self, history_id):
         response = self._get(f"histories/{history_id}/contents/{hda['id']}/display?to_ext=json")
         self._assert_status_code_is(response, 200)
         assert quote(name, safe="") in response.headers["Content-Disposition"]
+
+    def test_copy_dataset_from_history_with_copied_from_fields(self, history_id):
+        original_hda = self.dataset_populator.new_dataset(history_id, content="original data", wait=True)
+        self._assert_copied_from_fields(history_id, original_hda["id"], None, None, None)
+
+        copy_payload = {"content": original_hda["id"], "source": "hda", "type": "dataset"}
+        copied_hda_id = self._post(f"histories/{history_id}/contents", data=copy_payload, json=True).json()["id"]
+        self._assert_copied_from_fields(history_id, copied_hda_id, original_hda["id"], None, None)
+
+    @requires_new_library
+    def test_copy_dataset_from_library_with_copied_from_fields(self, history_id):
+        library_dataset = self.library_populator.new_library_dataset("test_library_dataset")
+        copy_payload = {"content": library_dataset["id"], "source": "library", "type": "dataset"}
+        copied_hda_id = self._post(f"histories/{history_id}/contents", data=copy_payload, json=True).json()["id"]
+        self._assert_copied_from_fields(
+            history_id, copied_hda_id, None, library_dataset["ldda_id"], library_dataset["ldda_id"]
+        )
+
+    def _assert_copied_from_fields(
+        self, history_id, hda_id, expected_history_id, expected_ldda_id, expected_library_id
+    ):
+        keys = "copied_from_history_dataset_association_id,copied_from_ldda_id,copied_from_library_dataset_dataset_association_id"
+        for url in [
+            f"datasets/{hda_id}?keys={keys}",
+            f"histories/{history_id}/contents/datasets/{hda_id}?keys={keys}",
+        ]:
+            data = self._get(url).json()
+            assert data["copied_from_history_dataset_association_id"] == expected_history_id
+            assert data["copied_from_ldda_id"] == expected_ldda_id
+            assert data["copied_from_library_dataset_dataset_association_id"] == expected_library_id

test/unit/app/managers/test_HDAManager.py

@@ -412,7 +412,7 @@ def test_serializers(self):
         assert isinstance(serialized["file_size"], int)
         assert isinstance(serialized["nice_size"], str)
         # TODO: these should be tested w/copy
-        assert isinstance(serialized["copied_from_history_dataset_association_id"], int)
+        self.assertNullableEncodedId(serialized["copied_from_history_dataset_association_id"])
         self.assertNullableEncodedId(serialized["copied_from_library_dataset_dataset_association_id"])
         self.assertNullableBasestring(serialized["info"])
         self.assertNullableBasestring(serialized["blurb"])