S3: Add tests for PyArrow with native S3 filesystem (#7508)

* PyArrow native S3 filesystem

* add sse-s3 tests

* update

* minor

* ENABLE_SSE_S3

* Update test_pyarrow_native_s3.py

* clean up

* refactoring

* Update test_pyarrow_native_s3.py

1 files changed, 41 insertions, 0 deletions

diff --git a/test/s3/parquet/parquet_test_utils.py b/test/s3/parquet/parquet_test_utils.py
new file mode 100644
index 000000000..d7e4c43db
--- /dev/null
+++ b/test/s3/parquet/parquet_test_utils.py
@@ -0,0 +1,41 @@
+"""
+Shared utility functions for PyArrow Parquet tests.
+
+This module provides common test utilities used across multiple test scripts
+to avoid code duplication and ensure consistency.
+"""
+
+import pyarrow as pa
+
+
+def create_sample_table(num_rows: int = 5) -> pa.Table:
+    """Create a sample PyArrow table for testing.
+    
+    Args:
+        num_rows: Number of rows to generate (default: 5)
+    
+    Returns:
+        PyArrow Table with test data containing:
+        - id: int64 sequential IDs (0 to num_rows-1)
+        - name: string user names (user_0, user_1, ...)
+        - value: float64 values (id * 1.5)
+        - flag: bool alternating True/False based on even/odd id
+    
+    Example:
+        >>> table = create_sample_table(3)
+        >>> print(table)
+        pyarrow.Table
+        id: int64
+        name: string
+        value: double
+        flag: bool
+    """
+    return pa.table(
+        {
+            "id": pa.array(range(num_rows), type=pa.int64()),
+            "name": pa.array([f"user_{i}" for i in range(num_rows)], type=pa.string()),
+            "value": pa.array([float(i) * 1.5 for i in range(num_rows)], type=pa.float64()),
+            "flag": pa.array([i % 2 == 0 for i in range(num_rows)], type=pa.bool_()),
+        }
+    )
+