docs: add sample to run DML query (#591)

* docs: add sample to run DML query

* cleanup leftover datasets before test run

* fix import order

Author: tswast

samples/snippets/conftest.py

@@ -12,10 +12,35 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import datetime
+import random
+
 from google.cloud import bigquery
 import pytest
 
 
+RESOURCE_PREFIX = "python_bigquery_samples_snippets"
+
+
+def resource_prefix() -> str:
+    timestamp = datetime.datetime.utcnow().strftime("%Y%m%d_%H%M%S")
+    random_string = hex(random.randrange(1000000))[2:]
+    return f"{RESOURCE_PREFIX}_{timestamp}_{random_string}"
+
+
+@pytest.fixture(scope="session", autouse=True)
+def cleanup_datasets(bigquery_client: bigquery.Client):
+    yesterday = datetime.datetime.utcnow() - datetime.timedelta(days=1)
+    for dataset in bigquery_client.list_datasets():
+        if (
+            dataset.dataset_id.startswith(RESOURCE_PREFIX)
+            and dataset.created < yesterday
+        ):
+            bigquery_client.delete_dataset(
+                dataset, delete_contents=True, not_found_ok=True
+            )
+
+
 @pytest.fixture(scope="session")
 def bigquery_client():
     bigquery_client = bigquery.Client()
@@ -25,3 +50,18 @@ def bigquery_client():
 @pytest.fixture(scope="session")
 def project_id(bigquery_client):
     return bigquery_client.project
+
+
+@pytest.fixture(scope="session")
+def dataset_id(bigquery_client: bigquery.Client, project_id: str):
+    dataset_id = resource_prefix()
+    full_dataset_id = f"{project_id}.{dataset_id}"
+    dataset = bigquery.Dataset(full_dataset_id)
+    bigquery_client.create_dataset(dataset)
+    yield dataset_id
+    bigquery_client.delete_dataset(dataset, delete_contents=True, not_found_ok=True)
+
+
+@pytest.fixture
+def bigquery_client_patch(monkeypatch, bigquery_client):
+    monkeypatch.setattr(bigquery, "Client", lambda: bigquery_client)

samples/snippets/test_update_with_dml.py

@@ -0,0 +1,36 @@
+# Copyright 2021 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.
+
+from google.cloud import bigquery
+import pytest
+
+from conftest import resource_prefix
+import update_with_dml
+
+
+@pytest.fixture
+def table_id(bigquery_client: bigquery.Client, project_id: str, dataset_id: str):
+    table_id = f"{resource_prefix()}_update_with_dml"
+    yield table_id
+    full_table_id = f"{project_id}.{dataset_id}.{table_id}"
+    bigquery_client.delete_table(full_table_id, not_found_ok=True)
+
+
+def test_update_with_dml(bigquery_client_patch, dataset_id, table_id):
+    override_values = {
+        "dataset_id": dataset_id,
+        "table_id": table_id,
+    }
+    num_rows = update_with_dml.run_sample(override_values=override_values)
+    assert num_rows > 0

samples/snippets/update_with_dml.py

@@ -0,0 +1,82 @@
+# Copyright 2021 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.
+
+# [START bigquery_update_with_dml]
+import pathlib
+
+from google.cloud import bigquery
+from google.cloud.bigquery import enums
+
+
+def load_from_newline_delimited_json(
+    client: bigquery.Client,
+    filepath: pathlib.Path,
+    project_id: str,
+    dataset_id: str,
+    table_id: str,
+):
+    full_table_id = f"{project_id}.{dataset_id}.{table_id}"
+    job_config = bigquery.LoadJobConfig()
+    job_config.source_format = enums.SourceFormat.NEWLINE_DELIMITED_JSON
+    job_config.schema = [
+        bigquery.SchemaField("id", enums.SqlTypeNames.STRING),
+        bigquery.SchemaField("user_id", enums.SqlTypeNames.INTEGER),
+        bigquery.SchemaField("login_time", enums.SqlTypeNames.TIMESTAMP),
+        bigquery.SchemaField("logout_time", enums.SqlTypeNames.TIMESTAMP),
+        bigquery.SchemaField("ip_address", enums.SqlTypeNames.STRING),
+    ]
+
+    with open(filepath, "rb") as json_file:
+        load_job = client.load_table_from_file(
+            json_file, full_table_id, job_config=job_config
+        )
+
+    # Wait for load job to finish.
+    load_job.result()
+
+
+def update_with_dml(
+    client: bigquery.Client, project_id: str, dataset_id: str, table_id: str
+):
+    query_text = f"""
+    UPDATE `{project_id}.{dataset_id}.{table_id}`
+    SET ip_address = REGEXP_REPLACE(ip_address, r"(\\.[0-9]+)$", ".0")
+    WHERE TRUE
+    """
+    query_job = client.query(query_text)
+
+    # Wait for query job to finish.
+    query_job.result()
+
+    print(f"DML query modified {query_job.num_dml_affected_rows} rows.")
+    return query_job.num_dml_affected_rows
+
+
+def run_sample(override_values={}):
+    client = bigquery.Client()
+    filepath = pathlib.Path(__file__).parent / "user_sessions_data.json"
+    project_id = client.project
+    dataset_id = "sample_db"
+    table_id = "UserSessions"
+    # [END bigquery_update_with_dml]
+    # To facilitate testing, we replace values with alternatives
+    # provided by the testing harness.
+    dataset_id = override_values.get("dataset_id", dataset_id)
+    table_id = override_values.get("table_id", table_id)
+    # [START bigquery_update_with_dml]
+    load_from_newline_delimited_json(client, filepath, project_id, dataset_id, table_id)
+    return update_with_dml(client, project_id, dataset_id, table_id)
+
+
+# [END bigquery_update_with_dml]

samples/snippets/user_sessions_data.json

@@ -0,0 +1,10 @@
+{"id":"2ad525d6-c832-4c3d-b7fe-59d104885519","user_id":"38","login_time":"1.47766087E9","logout_time":"1.477661109E9","ip_address":"192.0.2.12"}
+{"id":"53d65e20-6ea9-4650-98d9-a2111fbd1122","user_id":"88","login_time":"1.47707544E9","logout_time":"1.477075519E9","ip_address":"192.0.2.88"}
+{"id":"5e6c3021-d5e7-4ccd-84b2-adfa9176d13d","user_id":"39","login_time":"1.474022869E9","logout_time":"1.474022961E9","ip_address":"203.0.113.52"}
+{"id":"6196eefa-1498-4567-8ef0-498845b888d9","user_id":"52","login_time":"1.478604612E9","logout_time":"1.478604691E9","ip_address":"203.0.113.169"}
+{"id":"70656dc5-7e0f-49cf-9e00-f06ed93c1f5b","user_id":"46","login_time":"1.474089924E9","logout_time":"1.474090227E9","ip_address":"192.0.2.10"}
+{"id":"aafa5eef-ad49-49a7-9a0f-fbc7fd639bd3","user_id":"40","login_time":"1.478031161E9","logout_time":"1.478031388E9","ip_address":"203.0.113.18"}
+{"id":"d2792fc2-24dd-4260-9456-3fbe6cdfdd90","user_id":"5","login_time":"1.481259081E9","logout_time":"1.481259247E9","ip_address":"192.0.2.140"}
+{"id":"d835dc49-32f9-4790-b4eb-dddee62e0dcc","user_id":"62","login_time":"1.478892977E9","logout_time":"1.478893219E9","ip_address":"203.0.113.83"}
+{"id":"f4a0d3c7-351f-471c-8e11-e093e7a6ce75","user_id":"89","login_time":"1.459031555E9","logout_time":"1.459031831E9","ip_address":"203.0.113.233"}
+{"id":"f6e9f526-5b22-4679-9c3e-56a636e815bb","user_id":"97","login_time":"1.482426034E9","logout_time":"1.482426415E9","ip_address":"203.0.113.167"}