Update from database to schema in unit tests

Author: timsaucer

python/tests/test_catalog.py

@@ -32,7 +32,7 @@ def test_basic(ctx, database):
     default = ctx.catalog()
     assert default.names() == {"public"}
 
-    for db in [default.database("public"), default.database()]:
+    for db in [default.schema("public"), default.schema()]:
         assert db.names() == {"csv1", "csv", "csv2"}
 
     table = db.table("csv")

python/tests/test_context.py

@@ -57,7 +57,7 @@ def test_runtime_configs(tmp_path, path_to_str):
     ctx = SessionContext(config, runtime)
     assert ctx is not None
 
-    db = ctx.catalog("foo").database("bar")
+    db = ctx.catalog("foo").schema("bar")
     assert db is not None
 
 
@@ -70,7 +70,7 @@ def test_temporary_files(tmp_path, path_to_str):
     ctx = SessionContext(config, runtime)
     assert ctx is not None
 
-    db = ctx.catalog("foo").database("bar")
+    db = ctx.catalog("foo").schema("bar")
     assert db is not None
 
 
@@ -91,7 +91,7 @@ def test_create_context_with_all_valid_args():
     ctx = SessionContext(config, runtime)
 
     # verify that at least some of the arguments worked
-    ctx.catalog("foo").database("bar")
+    ctx.catalog("foo").schema("bar")
     with pytest.raises(KeyError):
         ctx.catalog("datafusion")
 
@@ -105,7 +105,7 @@ def test_register_record_batches(ctx):
 
     ctx.register_record_batches("t", [[batch]])
 
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     result = ctx.sql("SELECT a+b, a-b FROM t").collect()
 
@@ -121,7 +121,7 @@ def test_create_dataframe_registers_unique_table_name(ctx):
     )
 
     df = ctx.create_dataframe([[batch]])
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -141,7 +141,7 @@ def test_create_dataframe_registers_with_defined_table_name(ctx):
     )
 
     df = ctx.create_dataframe([[batch]], name="tbl")
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -155,7 +155,7 @@ def test_from_arrow_table(ctx):
 
     # convert to DataFrame
     df = ctx.from_arrow(table)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -200,7 +200,7 @@ def test_from_arrow_table_with_name(ctx):
 
     # convert to DataFrame with optional name
     df = ctx.from_arrow(table, name="tbl")
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert tables[0] == "tbl"
@@ -213,7 +213,7 @@ def test_from_arrow_table_empty(ctx):
 
     # convert to DataFrame
     df = ctx.from_arrow(table)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -228,7 +228,7 @@ def test_from_arrow_table_empty_no_schema(ctx):
 
     # convert to DataFrame
     df = ctx.from_arrow(table)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -246,7 +246,7 @@ def test_from_pylist(ctx):
     ]
 
     df = ctx.from_pylist(data)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -260,7 +260,7 @@ def test_from_pydict(ctx):
     data = {"a": [1, 2, 3], "b": [4, 5, 6]}
 
     df = ctx.from_pydict(data)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -276,7 +276,7 @@ def test_from_pandas(ctx):
     pandas_df = pd.DataFrame(data)
 
     df = ctx.from_pandas(pandas_df)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -292,7 +292,7 @@ def test_from_polars(ctx):
     polars_df = pd.DataFrame(data)
 
     df = ctx.from_polars(polars_df)
-    tables = list(ctx.catalog().database().names())
+    tables = list(ctx.catalog().schema().names())
 
     assert df
     assert len(tables) == 1
@@ -303,7 +303,7 @@ def test_from_polars(ctx):
 
 def test_register_table(ctx, database):
     default = ctx.catalog()
-    public = default.database("public")
+    public = default.schema("public")
     assert public.names() == {"csv", "csv1", "csv2"}
     table = public.table("csv")
 
@@ -313,7 +313,7 @@ def test_register_table(ctx, database):
 
 def test_read_table(ctx, database):
     default = ctx.catalog()
-    public = default.database("public")
+    public = default.schema("public")
     assert public.names() == {"csv", "csv1", "csv2"}
 
     table = public.table("csv")
@@ -323,7 +323,7 @@ def test_read_table(ctx, database):
 
 def test_deregister_table(ctx, database):
     default = ctx.catalog()
-    public = default.database("public")
+    public = default.schema("public")
     assert public.names() == {"csv", "csv1", "csv2"}
 
     ctx.deregister_table("csv")
@@ -339,7 +339,7 @@ def test_register_dataset(ctx):
     dataset = ds.dataset([batch])
     ctx.register_dataset("t", dataset)
 
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     result = ctx.sql("SELECT a+b, a-b FROM t").collect()
 
@@ -356,7 +356,7 @@ def test_dataset_filter(ctx, capfd):
     dataset = ds.dataset([batch])
     ctx.register_dataset("t", dataset)
 
-    assert ctx.catalog().database().names() == {"t"}
+    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
@@ -455,7 +455,7 @@ def test_dataset_filter_nested_data(ctx):
     dataset = ds.dataset([batch])
     ctx.register_dataset("t", dataset)
 
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     df = ctx.table("t")
 

python/tests/test_sql.py

@@ -75,7 +75,7 @@ def test_register_csv(ctx, tmp_path):
     )
     ctx.register_csv("csv3", path, schema=alternative_schema)
 
-    assert ctx.catalog().database().names() == {
+    assert ctx.catalog().schema().names() == {
         "csv",
         "csv1",
         "csv2",
@@ -150,7 +150,7 @@ def test_register_parquet(ctx, tmp_path):
     path = helpers.write_parquet(tmp_path / "a.parquet", helpers.data())
     ctx.register_parquet("t", path)
     ctx.register_parquet("t1", str(path))
-    assert ctx.catalog().database().names() == {"t", "t1"}
+    assert ctx.catalog().schema().names() == {"t", "t1"}
 
     result = ctx.sql("SELECT COUNT(a) AS cnt FROM t").collect()
     result = pa.Table.from_batches(result)
@@ -184,7 +184,7 @@ def test_register_parquet_partitioned(ctx, tmp_path, path_to_str):
         parquet_pruning=True,
         file_extension=".parquet",
     )
-    assert ctx.catalog().database().names() == {"datapp"}
+    assert ctx.catalog().schema().names() == {"datapp"}
 
     result = ctx.sql("SELECT grp, COUNT(*) AS cnt FROM datapp GROUP BY grp").collect()
     result = pa.Table.from_batches(result)
@@ -200,7 +200,7 @@ def test_register_dataset(ctx, tmp_path, path_to_str):
     dataset = ds.dataset(path, format="parquet")
 
     ctx.register_dataset("t", dataset)
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     result = ctx.sql("SELECT COUNT(a) AS cnt FROM t").collect()
     result = pa.Table.from_batches(result)
@@ -247,7 +247,7 @@ def test_register_json(ctx, tmp_path):
     )
     ctx.register_json("json3", path, schema=alternative_schema)
 
-    assert ctx.catalog().database().names() == {
+    assert ctx.catalog().schema().names() == {
         "json",
         "json1",
         "json2",
@@ -304,7 +304,7 @@ def test_execute(ctx, tmp_path):
     path = helpers.write_parquet(tmp_path / "a.parquet", pa.array(data))
     ctx.register_parquet("t", path)
 
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     # count
     result = ctx.sql("SELECT COUNT(a) AS cnt FROM t WHERE a IS NOT NULL").collect()
@@ -520,7 +520,7 @@ def test_register_listing_table(
         schema=table.schema if pass_schema else None,
         file_sort_order=file_sort_order,
     )
-    assert ctx.catalog().database().names() == {"my_table"}
+    assert ctx.catalog().schema().names() == {"my_table"}
 
     result = ctx.sql(
         "SELECT grp, COUNT(*) AS count FROM my_table GROUP BY grp"

python/tests/test_substrait.py

@@ -34,7 +34,7 @@ def test_substrait_serialization(ctx):
 
     ctx.register_record_batches("t", [[batch]])
 
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     # For now just make sure the method calls blow up
     substrait_plan = ss.Serde.serialize_to_plan("SELECT * FROM t", ctx)
@@ -59,7 +59,7 @@ def test_substrait_file_serialization(ctx, tmp_path, path_to_str):
 
     ctx.register_record_batches("t", [[batch]])
 
-    assert ctx.catalog().database().names() == {"t"}
+    assert ctx.catalog().schema().names() == {"t"}
 
     path = tmp_path / "substrait_plan"
     path = str(path) if path_to_str else path