test: add test for converting Arrow C stream to DataFrame

Author: kosiew

python/tests/test_dataframe.py

@@ -1582,6 +1582,29 @@ def test_empty_to_arrow_table(df):
     assert set(pyarrow_table.column_names) == {"a", "b", "c"}
 
 
+def test_arrow_c_stream_to_table(monkeypatch):
+    ctx = SessionContext()
+
+    # Create a DataFrame with two separate record batches
+    batch1 = pa.record_batch([pa.array([1])], names=["a"])
+    batch2 = pa.record_batch([pa.array([2])], names=["a"])
+    df = ctx.create_dataframe([[batch1], [batch2]])
+
+    # Fail if the DataFrame is pre-collected
+    def fail_collect(self):  # pragma: no cover - failure path
+        msg = "collect should not be called"
+        raise AssertionError(msg)
+
+    monkeypatch.setattr(DataFrame, "collect", fail_collect)
+
+    table = pa.Table.from_batches(df)
+    expected = pa.Table.from_batches([batch1, batch2])
+
+    assert table.equals(expected)
+    assert table.schema == df.schema()
+    assert table.column("a").num_chunks == 2
+
+
 def test_to_pylist(df):
     # Convert datafusion dataframe to Python list
     pylist = df.to_pylist()