From 4741cf1d17243cf7bfc6a1ca65a90ad4e3dd3447 Mon Sep 17 00:00:00 2001
From: Tim Swast <swast@google.com>
Date: Thu, 7 Sep 2017 13:26:37 -0700
Subject: [PATCH] BigQuery : add sample for writing query results to a
 destination table.

See: https://cloud.google.com/bigquery/docs/writing-results
---
 bigquery/cloud-client/query.py      | 33 +++++++++++++++++++++++++++++
 bigquery/cloud-client/query_test.py | 20 +++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/bigquery/cloud-client/query.py b/bigquery/cloud-client/query.py
index f01f912cce6..93b13b84873 100755
--- a/bigquery/cloud-client/query.py
+++ b/bigquery/cloud-client/query.py
@@ -63,6 +63,30 @@ def query_standard_sql(query):
         print(row)
 
 
+def query_destination_table(query, dest_dataset_id, dest_table_id):
+    client = bigquery.Client()
+    query_job = client.run_async_query(str(uuid.uuid4()), query)
+
+    # Allow for query results larger than the maximum response size.
+    query_job.allow_large_results = True
+
+    # When large results are allowed, a destination table must be set.
+    dest_dataset = client.dataset(dest_dataset_id)
+    dest_table = dest_dataset.table(dest_table_id)
+    query_job.destination = dest_table
+
+    # Allow the results table to be overwritten.
+    query_job.write_disposition = 'WRITE_TRUNCATE'
+
+    query_job.begin()
+    query_job.result()  # Wait for job to complete.
+
+    # Verify that the results were written to the destination table.
+    dest_table.reload()  # Get the table metadata, such as the schema.
+    for row in dest_table.fetch_data():
+        print(row)
+
+
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(
         description=__doc__,
@@ -72,10 +96,19 @@ def query_standard_sql(query):
         '--use_standard_sql',
         action='store_true',
         help='Use standard SQL syntax.')
+    parser.add_argument(
+        '--destination_table',
+        type=str,
+        help=(
+            'Destination table to use for results. '
+            'Example: my_dataset.my_table'))
 
     args = parser.parse_args()
 
     if args.use_standard_sql:
         query_standard_sql(args.query)
+    elif args.destination_table:
+        dataset, table = args.destination_table.split('.')
+        query_destination_table(args.query, dataset, table)
     else:
         query(args.query)
diff --git a/bigquery/cloud-client/query_test.py b/bigquery/cloud-client/query_test.py
index fa698e146a8..9d6c912b4e5 100644
--- a/bigquery/cloud-client/query_test.py
+++ b/bigquery/cloud-client/query_test.py
@@ -15,6 +15,10 @@
 import query
 
 
+DATASET_ID = 'test_dataset'
+TABLE_ID = 'test_destination_table'
+
+
 def test_query(capsys):
     # Query only outputs the first 10 rows, sort results to avoid randomness
     query_string = '''#standardSQL
@@ -44,3 +48,19 @@ def test_query_standard_sql(capsys):
     out, _ = capsys.readouterr()
 
     assert 'antonyandcleopatra' in out
+
+
+def test_query_destination_table(capsys):
+    # Query only outputs the first 10 rows, sort results to avoid randomness
+    query_string = '''#standardSQL
+          SELECT corpus
+          FROM `publicdata.samples.shakespeare`
+          GROUP BY corpus
+          ORDER BY corpus
+          LIMIT 10;'''
+
+    query.query_destination_table(query_string, DATASET_ID, TABLE_ID)
+
+    out, _ = capsys.readouterr()
+
+    assert 'antonyandcleopatra' in out