From 4a4ed22fe5ba9bcae9ceaeaa93f28a1ce67cc99c Mon Sep 17 00:00:00 2001
From: Thomas Zajac <thomas-jakob.zajac@uni-tuebingen.de>
Date: Thu, 25 May 2023 17:18:48 +0200
Subject: [PATCH] Added functionality to list all bucket object IDs (#58)

---
 hexkit/__init__.py              |  2 +-
 hexkit/protocols/objstorage.py  | 17 +++++++++++++++++
 hexkit/providers/s3/provider.py | 15 +++++++++++++++
 tests/integration/test_s3.py    | 20 ++++++++++++++++++++
 4 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/hexkit/__init__.py b/hexkit/__init__.py
index 3799f363..26a429ed 100644
--- a/hexkit/__init__.py
+++ b/hexkit/__init__.py
@@ -15,4 +15,4 @@
 
 """A Toolkit for Building Microservices using the Hexagonal Architecture"""
 
-__version__ = "0.9.3"
+__version__ = "0.10.0"
diff --git a/hexkit/protocols/objstorage.py b/hexkit/protocols/objstorage.py
index f3ed3a17..4a2ae54e 100644
--- a/hexkit/protocols/objstorage.py
+++ b/hexkit/protocols/objstorage.py
@@ -77,6 +77,13 @@ async def delete_bucket(
         self._validate_bucket_id(bucket_id)
         await self._delete_bucket(bucket_id, delete_content=delete_content)
 
+    async def list_all_object_ids(self, bucket_id: str) -> list[str]:
+        """
+        Retrieve a list of IDs for all objects currently present in the specified bucket
+        """
+        self._validate_bucket_id(bucket_id)
+        return await self._list_all_object_ids(bucket_id=bucket_id)
+
     async def get_object_upload_url(
         self,
         *,
@@ -293,6 +300,16 @@ async def _delete_bucket(
         """
         ...
 
+    @abstractmethod
+    async def _list_all_object_ids(self, *, bucket_id: str) -> list[str]:
+        """
+        Retrieve a list of IDs for all objects currently present in the specified bucket
+
+        *To be implemented by the provider. Input validation is done outside of this
+        method.*
+        """
+        ...
+
     @abstractmethod
     async def _get_object_upload_url(
         self,
diff --git a/hexkit/providers/s3/provider.py b/hexkit/providers/s3/provider.py
index 50d88516..5b99ab93 100644
--- a/hexkit/providers/s3/provider.py
+++ b/hexkit/providers/s3/provider.py
@@ -300,6 +300,21 @@ async def _delete_bucket(
                 error, bucket_id=bucket_id
             ) from error
 
+    async def _list_all_object_ids(self, *, bucket_id: str) -> list[str]:
+        """
+        Retrieve a list of IDs for all objects currently present in the specified bucket
+        """
+        await self._assert_bucket_exists(bucket_id)
+
+        try:
+            bucket = self._resource.Bucket(bucket_id)
+            content = await asyncio.to_thread(bucket.objects.all)
+            return [object_summary.key for object_summary in content]
+        except botocore.exceptions.ClientError as error:
+            raise self._translate_s3_client_errors(
+                error, bucket_id=bucket_id
+            ) from error
+
     async def _does_object_exist(
         self, *, bucket_id: str, object_id: str, object_md5sum: Optional[str] = None
     ) -> bool:
diff --git a/tests/integration/test_s3.py b/tests/integration/test_s3.py
index 35f97dc1..52f9e802 100644
--- a/tests/integration/test_s3.py
+++ b/tests/integration/test_s3.py
@@ -103,6 +103,26 @@ async def test_get_object_size(
     assert expected_size == observed_size
 
 
+@pytest.mark.asyncio
+async def test_list_all_object_ids(
+    s3_fixture: S3Fixture,  # noqa: F811
+    file_fixture: FileObject,  # noqa: F811
+):
+    """Test if listing all object IDs for a bucket works correctly."""
+
+    file_fixture2 = file_fixture.copy(deep=True)
+    file_fixture2.object_id = "mydefaulttestobject002"
+
+    # add file objects to storage
+    await s3_fixture.populate_file_objects([file_fixture, file_fixture2])
+
+    # retrieve all object ids
+    retrieved_ids = await s3_fixture.storage.list_all_object_ids(
+        bucket_id=file_fixture.bucket_id
+    )
+    assert retrieved_ids == [file_fixture.object_id, file_fixture2.object_id]
+
+
 @pytest.mark.asyncio
 async def test_bucket_existence_checks(s3_fixture: S3Fixture):  # noqa: F811
     """Test if the checks for existence of buckets work correctly."""