private/deposit_checks: Adapt reading tarballs using the File api

Using the File api is consistent across various storage backends. The previous
implementation was only working for file storage. As we are migrating towards remote
backends, this no longer is enough.

Unfortunately though, we cannot rely on zipfile.is_zipfile or tarfile.is_tarfile as
those only works with local filepath. So we need to rely on testing & failing with
exception trapping to read properly the tarballs...

Refs. swh/infra/sysadm-environment#5129

swh/deposit/api/private/deposit_check.py

@@ -114,20 +114,29 @@ class APIChecks(APIPrivateView, APIGet, DepositReadMixin):
             <detail-error>) otherwise.
 
         """
-        archive_path = archive_request.archive.path
+        archive = archive_request.archive
+        archive_name = archive.name
 
-        if not known_archive_format(archive_path):
+        if not known_archive_format(archive_name):
             return False, MANDATORY_ARCHIVE_UNSUPPORTED
 
         try:
-            if zipfile.is_zipfile(archive_path):
-                with zipfile.ZipFile(archive_path) as zipfile_:
-                    files = zipfile_.namelist()
-            elif tarfile.is_tarfile(archive_path):
-                with tarfile.open(archive_path) as tarfile_:
-                    files = tarfile_.getnames()
-            else:
-                return False, MANDATORY_ARCHIVE_UNSUPPORTED
+            # Use python's File api which is consistent across different types of
+            # storage backends (e.g. file, azure, ...)
+
+            with archive.open("rb") as archive_fp:
+                try:
+                    with zipfile.ZipFile(archive_fp) as zip_fp:
+                        files = zip_fp.namelist()
+                except Exception:
+                    try:
+                        # rewind since the first tryout reading may have moved the
+                        # cursor
+                        archive_fp.seek(0)
+                        with tarfile.open(fileobj=archive_fp) as tar_fp:
+                            files = tar_fp.getnames()
+                    except Exception:
+                        return False, MANDATORY_ARCHIVE_UNSUPPORTED
         except Exception:
             return False, MANDATORY_ARCHIVE_UNREADABLE
         if len(files) > 1:

swh/deposit/tests/api/test_deposit_private_check.py

@@ -75,11 +75,11 @@ def test_deposit_ok(
 
 @pytest.mark.parametrize("extension", ["zip", "tar", "tar.gz", "tar.bz2", "tar.xz"])
 def test_deposit_invalid_tarball(
-    tmp_path, authenticated_client, deposit_collection, extension
+    tmp_path, authenticated_client, deposit_collection, extension, atom_dataset
 ):
     """Deposit with tarball (of 1 tarball) should fail the checks: rejected"""
     deposit = create_deposit_archive_with_archive(
-        tmp_path, extension, authenticated_client, deposit_collection.name
+        tmp_path, extension, authenticated_client, deposit_collection.name, atom_dataset
     )
     for url in private_check_url_endpoints(deposit_collection, deposit):
         response = authenticated_client.get(url)