From ff38e6edfa8c6da4deeb7bb96b990301216d36c2 Mon Sep 17 00:00:00 2001
From: Wauplin <lucainp@gmail.com>
Date: Thu, 25 Jun 2026 15:14:01 +0200
Subject: [PATCH] Fix CI: huggingface_hub 1.20.0 commit op equality + pytest
 parametrize

Two unrelated CI failures:

1. tests/test_hub.py::test_delete_from_hub
   Since huggingface_hub 1.20.0 (https://github.com/huggingface/huggingface_hub/pull/4331),
   `UploadInfo` is no longer a dataclass and `CommitOperationAdd`/`CommitOperationDelete`
   no longer implement value equality. Two operations with identical content are therefore
   not equal anymore, breaking the `operations == expected_operations` assertion. Compare
   operations attribute by attribute instead. This is a breaking change in huggingface_hub
   that will not be reverted upstream.

2. tests/test_load.py collection error
   A trailing comma in `@pytest.mark.parametrize("stream_from_cache, ", ...)` made recent
   pytest parse it as two argnames, raising `TypeError: object of type 'bool' has no len()`
   at collection time. Drop the trailing comma.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 tests/test_hub.py  | 42 ++++++++++++++++++++++++------------------
 tests/test_load.py |  2 +-
 2 files changed, 25 insertions(+), 19 deletions(-)

diff --git a/tests/test_hub.py b/tests/test_hub.py
index d0394c34441..1b76c8ed068 100644
--- a/tests/test_hub.py
+++ b/tests/test_hub.py
@@ -66,21 +66,27 @@ def test_delete_from_hub(temporary_repo, hf_api, hf_token, csv_path, ci_hub_conf
     assert mock_method.called
     assert mock_method.call_args.kwargs.get("commit_message") == "Delete 'dogs' config"
     assert mock_method.call_args.kwargs.get("create_pr")
-    expected_operations = [
-        CommitOperationDelete(path_in_repo="dogs/train/0000.csv", is_folder=False),
-        CommitOperationAdd(
-            path_in_repo="README.md",
-            path_or_fileobj=dedent(
-                f"""\
-            ---
-            {METADATA_CONFIGS_FIELD}:
-            - config_name: cats
-              data_files:
-              - split: train
-                path: cats/train/*
-            ---
-            """
-            ).encode(),
-        ),
-    ]
-    assert mock_method.call_args.kwargs.get("operations") == expected_operations
+    expected_readme = dedent(
+        f"""\
+        ---
+        {METADATA_CONFIGS_FIELD}:
+        - config_name: cats
+          data_files:
+          - split: train
+            path: cats/train/*
+        ---
+        """
+    ).encode()
+    # Note: we compare operations attribute by attribute rather than relying on `==`. Since
+    # huggingface_hub 1.20.0 (https://github.com/huggingface/huggingface_hub/pull/4331),
+    # `CommitOperationAdd`/`CommitOperationDelete` no longer implement value equality, so two
+    # operations with identical content are not considered equal.
+    operations = mock_method.call_args.kwargs.get("operations")
+    assert len(operations) == 2
+    delete_operation, add_operation = operations
+    assert isinstance(delete_operation, CommitOperationDelete)
+    assert delete_operation.path_in_repo == "dogs/train/0000.csv"
+    assert delete_operation.is_folder is False
+    assert isinstance(add_operation, CommitOperationAdd)
+    assert add_operation.path_in_repo == "README.md"
+    assert add_operation.path_or_fileobj == expected_readme
diff --git a/tests/test_load.py b/tests/test_load.py
index dba83bfc52c..eb5e631d7e2 100644
--- a/tests/test_load.py
+++ b/tests/test_load.py
@@ -921,7 +921,7 @@ def test_load_dataset_from_hub(kwargs, expected_train_num_rows, expected_test_nu
 
 
 @pytest.mark.integration
-@pytest.mark.parametrize("stream_from_cache, ", [False, True])
+@pytest.mark.parametrize("stream_from_cache", [False, True])
 def test_load_dataset_cached_from_hub(stream_from_cache, caplog):
     dataset = load_dataset(SAMPLE_DATASET_IDENTIFIER3)
     assert isinstance(dataset, DatasetDict)