refactor: move DDL gen to bigframes.session._io, add missing test (#131)

Towards internal issue 280662868
🦕

Author: tswast

bigframes/dataframe.py

@@ -46,7 +46,6 @@
 import bigframes.core.guid
 import bigframes.core.indexers as indexers
 import bigframes.core.indexes as indexes
-import bigframes.core.io
 import bigframes.core.ordering as order
 import bigframes.core.utils as utils
 import bigframes.core.window
@@ -56,6 +55,7 @@
 import bigframes.operations.aggregations as agg_ops
 import bigframes.series
 import bigframes.series as bf_series
+import bigframes.session._io.bigquery
 import third_party.bigframes_vendored.pandas.core.frame as vendored_pandas_frame
 import third_party.bigframes_vendored.pandas.pandas._typing as vendored_pandas_typing
 
@@ -2201,9 +2201,9 @@ def to_csv(
             raise NotImplementedError(ERROR_IO_REQUIRES_WILDCARD)
 
         result_table = self._run_io_query(
-            index=index, ordering_id=bigframes.core.io.IO_ORDERING_ID
+            index=index, ordering_id=bigframes.session._io.bigquery.IO_ORDERING_ID
         )
-        export_data_statement = bigframes.core.io.create_export_csv_statement(
+        export_data_statement = bigframes.session._io.bigquery.create_export_csv_statement(
             f"{result_table.project}.{result_table.dataset_id}.{result_table.table_id}",
             uri=path_or_buf,
             field_delimiter=sep,
@@ -2243,9 +2243,9 @@ def to_json(
             )
 
         result_table = self._run_io_query(
-            index=index, ordering_id=bigframes.core.io.IO_ORDERING_ID
+            index=index, ordering_id=bigframes.session._io.bigquery.IO_ORDERING_ID
         )
-        export_data_statement = bigframes.core.io.create_export_data_statement(
+        export_data_statement = bigframes.session._io.bigquery.create_export_data_statement(
             f"{result_table.project}.{result_table.dataset_id}.{result_table.table_id}",
             uri=path_or_buf,
             format="JSON",
@@ -2319,9 +2319,9 @@ def to_parquet(
             export_options["compression"] = compression.upper()
 
         result_table = self._run_io_query(
-            index=index, ordering_id=bigframes.core.io.IO_ORDERING_ID
+            index=index, ordering_id=bigframes.session._io.bigquery.IO_ORDERING_ID
         )
-        export_data_statement = bigframes.core.io.create_export_data_statement(
+        export_data_statement = bigframes.session._io.bigquery.create_export_data_statement(
             f"{result_table.project}.{result_table.dataset_id}.{result_table.table_id}",
             uri=path,
             format="PARQUET",

bigframes/session/__init__.py

@@ -67,13 +67,13 @@
 import bigframes.core as core
 import bigframes.core.blocks as blocks
 import bigframes.core.guid as guid
-import bigframes.core.io as bigframes_io
 from bigframes.core.ordering import IntegerEncoding, OrderingColumnReference
 import bigframes.core.utils as utils
 import bigframes.dataframe as dataframe
 import bigframes.formatting_helpers as formatting_helpers
 from bigframes.remote_function import read_gbq_function as bigframes_rgf
 from bigframes.remote_function import remote_function as bigframes_rf
+import bigframes.session._io.bigquery as bigframes_io
 import bigframes.session.clients
 import bigframes.version
 

bigframes/session/_io/__init__.py

@@ -0,0 +1,13 @@
+# Copyright 2023 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

bigframes/core/io.py renamed to bigframes/session/_io/bigquery.py

@@ -18,15 +18,15 @@
 import google.cloud.bigquery as bigquery
 import pytest
 
-import bigframes.core.io
+import bigframes.session._io.bigquery
 
 
 def test_create_snapshot_sql_doesnt_timetravel_anonymous_datasets():
     table_ref = bigquery.TableReference.from_string(
         "my-test-project._e8166e0cdb.anonbb92cd"
     )
 
-    sql = bigframes.core.io.create_snapshot_sql(
+    sql = bigframes.session._io.bigquery.create_snapshot_sql(
         table_ref, datetime.datetime.now(datetime.timezone.utc)
     )
 
@@ -40,7 +40,7 @@ def test_create_snapshot_sql_doesnt_timetravel_anonymous_datasets():
 def test_create_snapshot_sql_doesnt_timetravel_session_datasets():
     table_ref = bigquery.TableReference.from_string("my-test-project._session.abcdefg")
 
-    sql = bigframes.core.io.create_snapshot_sql(
+    sql = bigframes.session._io.bigquery.create_snapshot_sql(
         table_ref, datetime.datetime.now(datetime.timezone.utc)
     )
 
@@ -101,4 +101,5 @@ def test_create_snapshot_sql_doesnt_timetravel_session_datasets():
     ),
 )
 def test_bq_schema_to_sql(schema: Iterable[bigquery.SchemaField], expected: str):
-    pass
+    sql = bigframes.session._io.bigquery.bq_schema_to_sql(schema)
+    assert sql == expected