[Data][CI] Add fix_block.py back to CI (#57841)

## Description


https://arrow.apache.org/docs/python/generated/pyarrow.Array.html#pyarrow.Array.to_numpy
<img width="772" height="270" alt="Screenshot 2025-10-18 at 3 14 36 PM"
src="https://github.com/user-attachments/assets/d9cbf986-4271-41e6-9c4c-96201d32d1c6"
/>


`zero_copy_only` is actually default to True, so we should explicit pass
False, for pyarrow version < 13.0.0

https://github.com/ray-project/ray/blob/1e38c9408caa92c675f0aa3e8bb60409c2d9159f/python/ray/data/_internal/arrow_block.py#L540-L546

## Related issues
Closes #57819

## Additional information
> Optional: Add implementation details, API changes, usage examples,
screenshots, etc.

---------

Signed-off-by: You-Cheng Lin (Owen) <mses010108@gmail.com>
Signed-off-by: You-Cheng Lin <youchenglin@youchenglin-L3DPGF50JG.local>
Signed-off-by: You-Cheng Lin <106612301+owenowenisme@users.noreply.github.com>
Signed-off-by: You-Cheng Lin <mses010108@gmail.com>
Co-authored-by: You-Cheng Lin <youchenglin@youchenglin-L3DPGF50JG.local>

Author: owenowenisme

python/ray/data/_internal/arrow_block.py

@@ -572,9 +572,13 @@ def to_pylist(self) -> List[Any]:
         return self._column.to_pylist()
 
     def to_numpy(self, zero_copy_only: bool = False) -> np.ndarray:
-        # NOTE: Pyarrow < 13.0.0 does not support ``zero_copy_only``
         if get_pyarrow_version() < _MIN_PYARROW_VERSION_TO_NUMPY_ZERO_COPY_ONLY:
-            return self._column.to_numpy()
+            if isinstance(
+                self._column, pyarrow.ChunkedArray
+            ):  # NOTE: ChunkedArray in Pyarrow < 13.0.0 does not support ``zero_copy_only``
+                return self._column.to_numpy()
+            else:
+                return self._column.to_numpy(zero_copy_only=zero_copy_only)
 
         return self._column.to_numpy(zero_copy_only=zero_copy_only)
 

python/ray/data/tests/test_block.py

@@ -156,3 +156,9 @@ def test_find_partitions_duplicates():
     assert partitions[1].to_pydict() == {"value": []}  # [1,2)
     assert partitions[2].to_pydict() == {"value": [2, 2, 2, 2, 2]}  # [2,3)
     assert partitions[3].to_pydict() == {"value": []}  # >=3
+
+
+if __name__ == "__main__":
+    import sys
+
+    sys.exit(pytest.main(["-v", __file__]))

semgrep.yml

@@ -35,7 +35,6 @@ rules:
       exclude:
         # FIXME: These tests weren't run in CI, and now they're failing.
         - "python/ray/data/tests/test_arrow_serialization.py"
-        - "python/ray/data/tests/test_block.py"
         - "python/ray/data/tests/test_hash_shuffle.py"
     languages:
       - python