refactor: simplify dataset filter tests by removing unnecessary assertions and parameters

Author: kosiew

python/tests/test_context.py

@@ -347,7 +347,7 @@ def test_register_dataset(ctx):
     assert result[0].column(1) == pa.array([-3, -3, -3])
 
 
-def test_dataset_filter(ctx, capfd):
+def test_dataset_filter(ctx):
     # create a RecordBatch and register it as a pyarrow.dataset.Dataset
     batch = pa.RecordBatch.from_arrays(
         [pa.array([1, 2, 3]), pa.array([4, 5, 6])],
@@ -359,11 +359,6 @@ def test_dataset_filter(ctx, capfd):
     assert ctx.catalog().schema().names() == {"t"}
     df = ctx.sql("SELECT a+b, a-b FROM t WHERE a BETWEEN 2 and 3 AND b > 5")
 
-    # Make sure the filter was pushed down in Physical Plan
-    df.explain()
-    captured = capfd.readouterr()
-    assert "filter_expr=(((a >= 2) and (a <= 3)) and (b > 5))" in captured.out
-
     result = df.collect()
 
     assert result[0].column(0) == pa.array([9])
@@ -389,21 +384,16 @@ def test_dataset_count(ctx):
     assert count[0].column(0) == pa.array([3])
 
 
-def test_pyarrow_predicate_pushdown_is_null(ctx, capfd):
-    """Ensure that pyarrow filter gets pushed down for `IsNull`"""
+def test_pyarrow_predicate_is_null(ctx):
+    """Ensure that filters with `IsNull` produce correct results"""
     # create a RecordBatch and register it as a pyarrow.dataset.Dataset
     batch = pa.RecordBatch.from_arrays(
         [pa.array([1, 2, 3]), pa.array([4, 5, 6]), pa.array([7, None, 9])],
         names=["a", "b", "c"],
     )
     dataset = ds.dataset([batch])
     ctx.register_dataset("t", dataset)
-    # Make sure the filter was pushed down in Physical Plan
     df = ctx.sql("SELECT a FROM t WHERE c is NULL")
-    df.explain()
-    captured = capfd.readouterr()
-    assert "filter_expr=is_null(c, {nan_is_null=false})" in captured.out
-
     result = df.collect()
     assert result[0].column(0) == pa.array([2])