Live Tests: batch deletions on azure / limited to 256 - Closes #509 (#508)

HISTORY.md

@@ -1,5 +1,9 @@
 # cloudpathlib Changelog
 
+## Unreleased
+
+- Fixed `rmtree` fail on Azure with no `hns` and more than 256 blobs to drop (Issue [#509](https://github.com/drivendataorg/cloudpathlib/issues/509), PR [#508](https://github.com/drivendataorg/cloudpathlib/pull/508), thanks @alikefia)
+
 ## v0.21.0 (2025-03-03)
 
 - Removed support for deprecated env var that had a typo (`CLOUPATHLIB_FILE_CACHE_MODE`; you should use `CLOUDPATHLIB_FILE_CACHE_MODE`).

cloudpathlib/azure/azblobclient.py

@@ -4,6 +4,7 @@
 from http import HTTPStatus
 from pathlib import Path
 from typing import Any, Callable, Dict, Iterable, Optional, Tuple, Union
+from itertools import islice
 
 try:
     from typing import cast
@@ -437,11 +438,12 @@ def _remove(self, cloud_path: AzureBlobPath, missing_ok: bool = True) -> None:
                 _hns_rmtree(self.data_lake_client, cloud_path.container, cloud_path.blob)
                 return
 
-            blobs = [
+            blobs = (
                 b.blob for b, is_dir in self._list_dir(cloud_path, recursive=True) if not is_dir
-            ]
+            )
             container_client = self.service_client.get_container_client(cloud_path.container)
-            container_client.delete_blobs(*blobs)
+            while batch := tuple(islice(blobs, 256)):
+                container_client.delete_blobs(*batch)
         elif file_or_dir == "file":
             blob = self.service_client.get_blob_client(
                 container=cloud_path.container, blob=cloud_path.blob

requirements-dev.txt

@@ -13,7 +13,7 @@ mike
 mkdocs>=1.2.2
 mkdocs-jupyter
 mkdocs-material>=7.2.6
-mkdocstrings[python-legacy]>=0.19.0
+mkdocstrings[python]>=0.19.0
 mypy
 nbautoexport
 pandas

tests/test_azure_specific.py

@@ -206,3 +206,13 @@ def test_adls_gen2_rename(azure_gen2_rig):
     p2 = p.rename(azure_gen2_rig.create_cloud_path("dir2"))
     assert not p.exists()
     assert p2.exists()
+
+
+def test_batched_rmtree_no_hns(azure_rig):
+    p = azure_rig.create_cloud_path("new_dir")
+
+    p.mkdir()
+    for i in range(400):
+        (p / f"{i}.txt").write_text("content")
+    p.rmtree()
+    assert not p.exists()