Add manual client for BigQuery Storage (googleapis#474)

* Add manual client for BigQuery Storage.

The manual client adds a default project, which is used by the wrapped
create_read_session to make the project parameter optional.

A future purpose of the manual client is to override the read_rows
method to return an iterator that can reconnect with the correct offset,
much like Spanner's StreamedResultSet class. This work is not yet
complete.  I'd like feedback on the approach for the manual client
first.

* Use same client name as wrapped gapic class.

* Use subclass for BigQueryStorageClient

Also, change create_read_session project argument back to 'parent' to
better match the super class.

* Add unit tests.

* Remove default project from manual client.

Author: tswast

bigquery_storage/google/cloud/bigquery_storage_v1beta1/__init__.py

@@ -16,18 +16,27 @@
 
 from __future__ import absolute_import
 
+import pkg_resources
+__version__ = pkg_resources.get_distribution('google-cloud-bigquery-storage').version  # noqa
+
 from google.cloud.bigquery_storage_v1beta1 import types
-from google.cloud.bigquery_storage_v1beta1.gapic import big_query_storage_client  # noqa
+from google.cloud.bigquery_storage_v1beta1 import client
 from google.cloud.bigquery_storage_v1beta1.gapic import enums
 
 
-class BigQueryStorageClient(big_query_storage_client.BigQueryStorageClient):
-    __doc__ = big_query_storage_client.BigQueryStorageClient.__doc__
+class BigQueryStorageClient(client.BigQueryStorageClient):
+    __doc__ = client.BigQueryStorageClient.__doc__
     enums = enums
 
 
 __all__ = (
-    'enums',
+    # google.cloud.bigquery_storage_v1beta1
+    '__version__',
     'types',
+
+    # google.cloud.bigquery_storage_v1beta1.client
     'BigQueryStorageClient',
+
+    # google.cloud.bigquery_storage_v1beta1.gapic
+    'enums',
 )

bigquery_storage/google/cloud/bigquery_storage_v1beta1/client.py

@@ -0,0 +1,108 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright 2018 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
+#
+#     https://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.
+
+"""Parent client for calling the Cloud BigQuery Storage API.
+
+This is the base from which all interactions with the API occur.
+"""
+
+from __future__ import absolute_import
+
+import google.api_core.gapic_v1.method
+
+from google.cloud.bigquery_storage_v1beta1.gapic import big_query_storage_client  # noqa
+
+
+_SCOPES = (
+    'https://www.googleapis.com/auth/bigquery',
+    'https://www.googleapis.com/auth/cloud-platform',
+)
+
+
+class BigQueryStorageClient(big_query_storage_client.BigQueryStorageClient):
+    """Client for interacting with BigQuery Storage API.
+
+    The BigQuery storage API can be used to read data stored in BigQuery.
+    """
+
+    def read_rows(self,
+                  read_position,
+                  retry=google.api_core.gapic_v1.method.DEFAULT,
+                  timeout=google.api_core.gapic_v1.method.DEFAULT,
+                  metadata=None):
+        """
+        Reads rows from the table in the format prescribed by the read
+        session. Each response contains one or more table rows, up to a
+        maximum of 10 MiB per response; read requests which attempt to read
+        individual rows larger than this will fail.
+
+        Each request also returns a set of stream statistics reflecting the
+        estimated total number of rows in the read stream. This number is
+        computed based on the total table size and the number of active
+        streams in the read session, and may change as other streams continue
+        to read data.
+
+        Example:
+            >>> from google.cloud import bigquery_storage_v1beta1
+            >>>
+            >>> client = bigquery_storage_v1beta1.BigQueryStorageClient()
+            >>>
+            >>> # TODO: Initialize ``read_position``:
+            >>> read_position = {}
+            >>>
+            >>> for element in client.read_rows(read_position):
+            ...     # process element
+            ...     pass
+
+        Args:
+            read_position (Union[ \
+                dict, \
+                ~google.cloud.bigquery_storage_v1beta1.types.StreamPosition \
+            ]):
+                Required. Identifier of the position in the stream to start
+                reading from. The offset requested must be less than the last
+                row read from ReadRows. Requesting a larger offset is
+                undefined. If a dict is provided, it must be of the same form
+                as the protobuf message
+                :class:`~google.cloud.bigquery_storage_v1beta1.types.StreamPosition`
+            retry (Optional[google.api_core.retry.Retry]):  A retry object used
+                to retry requests. If ``None`` is specified, requests will not
+                be retried.
+            timeout (Optional[float]): The amount of time, in seconds, to wait
+                for the request to complete. Note that if ``retry`` is
+                specified, the timeout applies to each individual attempt.
+            metadata (Optional[Sequence[Tuple[str, str]]]): Additional metadata
+                that is provided to the method.
+
+        Returns:
+            Iterable[~google.cloud.bigquery_storage_v1beta1.types.ReadRowsResponse].
+
+        Raises:
+            google.api_core.exceptions.GoogleAPICallError: If the request
+                    failed for any reason.
+            google.api_core.exceptions.RetryError: If the request failed due
+                    to a retryable error and retry attempts failed.
+            ValueError: If the parameters are invalid.
+        """
+        # TODO: Accept a stream and start at offset 0.
+        # TODO: Return a custom iterator which reconnects to the stream
+        #       automatically. See: Spanner's StreamedResultSet.
+        return super(BigQueryStorageClient, self).read_rows(
+            read_position,
+            retry=retry,
+            timeout=timeout,
+            metadata=metadata,
+        )

bigquery_storage/noxfile.py

@@ -48,7 +48,7 @@ def default(session):
         '--cov-append',
         '--cov-config=.coveragerc',
         '--cov-report=',
-        os.path.join('tests', 'unit', 'gapic', 'v1beta1'),
+        os.path.join('tests', 'unit'),
         *session.posargs
     )
 
@@ -91,6 +91,7 @@ def cover(session):
     session.run('coverage', 'report', '--show-missing', '--fail-under=100')
     session.run('coverage', 'erase')
 
+
 @nox.session(python=['2.7', '3.6'])
 def system(session):
     """Run the system test suite."""

bigquery_storage/synth.py

@@ -31,8 +31,15 @@
 
 s.move(
     library,
-    excludes=['docs/conf.py', 'docs/index.rst', 'README.rst',
-              'nox*.py', 'setup.py', 'setup.cfg']
+    excludes=[
+        'docs/conf.py',
+        'docs/index.rst',
+        'google/cloud/bigquery_storage_v1beta1/__init__.py',
+        'README.rst',
+        'nox*.py',
+        'setup.py',
+        'setup.cfg',
+    ],
 )
 
 s.replace(
@@ -55,13 +62,19 @@
     '\g<0>import google.api_core.path_template\n'
 )
 
-# START: Ignore lint and coverage
 s.replace(
-    ['google/cloud/bigquery_storage_v1beta1/__init__.py'],
-    'import big_query_storage_client',
-    'import big_query_storage_client  # noqa',
+    ['tests/unit/gapic/v1beta1/test_big_query_storage_client_v1beta1.py'],
+    'from google.cloud import bigquery_storage_v1beta1',
+    'from google.cloud.bigquery_storage_v1beta1.gapic import big_query_storage_client  # noqa',
 )
 
+s.replace(
+    ['tests/unit/gapic/v1beta1/test_big_query_storage_client_v1beta1.py'],
+    'bigquery_storage_v1beta1.BigQueryStorageClient',
+    'big_query_storage_client.BigQueryStorageClient',
+)
+
+# START: Ignore lint and coverage
 s.replace(
     ['google/cloud/bigquery_storage_v1beta1/gapic/big_query_storage_client.py'],
     'if transport:',

bigquery_storage/tests/system/test_system.py

@@ -32,16 +32,21 @@ def client():
     return bigquery_storage_v1beta1.BigQueryStorageClient()
 
 
-def test_read_rows(project_id, client):
+@pytest.fixture()
+def table_reference():
     table_ref = bigquery_storage_v1beta1.types.TableReference()
     table_ref.project_id = 'bigquery-public-data'
     table_ref.dataset_id = 'usa_names'
     table_ref.table_id = 'usa_1910_2013'
+    return table_ref
+
 
+def test_read_rows(client, table_reference):
     session = client.create_read_session(
-        table_ref,
+        table_reference,
         requested_streams=1,
-        parent='projects/{}'.format(project_id))
+        parent='projects/{}'.format(project_id),
+    )
 
     stream_pos = bigquery_storage_v1beta1.types.StreamPosition(
         stream=session.streams[0])
@@ -50,3 +55,17 @@ def test_read_rows(project_id, client):
 
     assert page.status.estimated_row_count > 0
     assert len(page.avro_rows.serialized_binary_rows) > 0
+
+
+def test_split_read_stream(client, table_reference):
+    session = client.create_read_session(
+        table_reference,
+        requested_streams=1,
+        parent='projects/{}'.format(project_id),
+    )
+
+    split = client.split_read_stream(session.streams[0])
+
+    assert split.primary_stream is not None
+    assert split.remainder_stream is not None
+    assert split.primary_stream != split.remainder_stream

bigquery_storage/tests/unit/gapic/v1beta1/test_big_query_storage_client_v1beta1.py

@@ -17,7 +17,7 @@
 
 import pytest
 
-from google.cloud import bigquery_storage_v1beta1
+from google.cloud.bigquery_storage_v1beta1.gapic import big_query_storage_client  # noqa
 from google.cloud.bigquery_storage_v1beta1.proto import storage_pb2
 from google.cloud.bigquery_storage_v1beta1.proto import table_reference_pb2
 from google.protobuf import empty_pb2
@@ -77,7 +77,7 @@ def test_create_read_session(self):
 
         # Mock the API response
         channel = ChannelStub(responses=[expected_response])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup Request
@@ -98,7 +98,7 @@ def test_create_read_session(self):
     def test_create_read_session_exception(self):
         # Mock the API response
         channel = ChannelStub(responses=[CustomException()])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup request
@@ -115,7 +115,7 @@ def test_read_rows(self):
 
         # Mock the API response
         channel = ChannelStub(responses=[iter([expected_response])])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup Request
@@ -135,7 +135,7 @@ def test_read_rows(self):
     def test_read_rows_exception(self):
         # Mock the API response
         channel = ChannelStub(responses=[CustomException()])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup request
@@ -152,7 +152,7 @@ def test_batch_create_read_session_streams(self):
 
         # Mock the API response
         channel = ChannelStub(responses=[expected_response])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup Request
@@ -172,7 +172,7 @@ def test_batch_create_read_session_streams(self):
     def test_batch_create_read_session_streams_exception(self):
         # Mock the API response
         channel = ChannelStub(responses=[CustomException()])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup request
@@ -185,7 +185,7 @@ def test_batch_create_read_session_streams_exception(self):
 
     def test_finalize_stream(self):
         channel = ChannelStub()
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup Request
@@ -201,7 +201,7 @@ def test_finalize_stream(self):
     def test_finalize_stream_exception(self):
         # Mock the API response
         channel = ChannelStub(responses=[CustomException()])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup request
@@ -218,7 +218,7 @@ def test_split_read_stream(self):
 
         # Mock the API response
         channel = ChannelStub(responses=[expected_response])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup Request
@@ -236,7 +236,7 @@ def test_split_read_stream(self):
     def test_split_read_stream_exception(self):
         # Mock the API response
         channel = ChannelStub(responses=[CustomException()])
-        client = bigquery_storage_v1beta1.BigQueryStorageClient(
+        client = big_query_storage_client.BigQueryStorageClient(
             channel=channel)
 
         # Setup request