BigQuery: Updates samples for BigQuery Beta 2 (do not merge until release)

bigquery/cloud-client/export_data_to_gcs.py

@@ -26,40 +26,36 @@
 """
 
 import argparse
-import uuid
 
 from google.cloud import bigquery
 
 
-def export_data_to_gcs(dataset_name, table_name, destination):
+def export_data_to_gcs(dataset_id, table_id, destination):
     bigquery_client = bigquery.Client()
-    dataset = bigquery_client.dataset(dataset_name)
-    table = dataset.table(table_name)
-    job_name = str(uuid.uuid4())
+    dataset_ref = bigquery_client.dataset(dataset_id)
+    table_ref = dataset_ref.table(table_id)
 
-    job = bigquery_client.extract_table_to_storage(
-        job_name, table, destination)
+    job = bigquery_client.extract_table(table_ref, destination)
 
-    job.begin()
-    job.result()  # Wait for job to complete
+    job.result()  # Waits for job to complete
 
     print('Exported {}:{} to {}'.format(
-        dataset_name, table_name, destination))
+        dataset_id, table_id, destination))
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(
         description=__doc__,
         formatter_class=argparse.RawDescriptionHelpFormatter)
-    parser.add_argument('dataset_name')
-    parser.add_argument('table_name')
+    parser.add_argument('dataset_id')
+    parser.add_argument('table_id')
     parser.add_argument(
         'destination', help='The desintation Google Cloud Storage object.'
         'Must be in the format gs://bucket_name/object_name')
 
     args = parser.parse_args()
 
     export_data_to_gcs(
-        args.dataset_name,
-        args.table_name,
+        args.dataset_id,
+        args.table_id,
         args.destination)

bigquery/cloud-client/load_data_from_file.py

@@ -30,38 +30,37 @@
 from google.cloud import bigquery
 
 
-def load_data_from_file(dataset_name, table_name, source_file_name):
+def load_data_from_file(dataset_id, table_id, source_file_name):
     bigquery_client = bigquery.Client()
-    dataset = bigquery_client.dataset(dataset_name)
-    table = dataset.table(table_name)
-
-    # Reload the table to get the schema.
-    table.reload()
+    dataset_ref = bigquery_client.dataset(dataset_id)
+    table_ref = dataset_ref.table(table_id)
 
     with open(source_file_name, 'rb') as source_file:
         # This example uses CSV, but you can use other formats.
         # See https://cloud.google.com/bigquery/loading-data
-        job = table.upload_from_file(
-            source_file, source_format='text/csv')
+        job_config = bigquery.LoadJobConfig()
+        job_config.source_format = 'text/csv'
+        job = bigquery_client.load_table_from_file(
+            source_file, table_ref, job_config=job_config)
 
-    job.result()  # Wait for job to complete
+    job.result()  # Waits for job to complete
 
     print('Loaded {} rows into {}:{}.'.format(
-        job.output_rows, dataset_name, table_name))
+        job.output_rows, dataset_id, table_id))
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(
         description=__doc__,
         formatter_class=argparse.RawDescriptionHelpFormatter)
-    parser.add_argument('dataset_name')
-    parser.add_argument('table_name')
+    parser.add_argument('dataset_id')
+    parser.add_argument('table_id')
     parser.add_argument(
         'source_file_name', help='Path to a .csv file to upload.')
 
     args = parser.parse_args()
 
     load_data_from_file(
-        args.dataset_name,
-        args.table_name,
+        args.dataset_id,
+        args.table_id,
         args.source_file_name)

bigquery/cloud-client/load_data_from_gcs.py

@@ -26,40 +26,36 @@
 """
 
 import argparse
-import uuid
 
 from google.cloud import bigquery
 
 
-def load_data_from_gcs(dataset_name, table_name, source):
+def load_data_from_gcs(dataset_id, table_id, source):
     bigquery_client = bigquery.Client()
-    dataset = bigquery_client.dataset(dataset_name)
-    table = dataset.table(table_name)
-    job_name = str(uuid.uuid4())
+    dataset_ref = bigquery_client.dataset(dataset_id)
+    table_ref = dataset_ref.table(table_id)
 
-    job = bigquery_client.load_table_from_storage(
-        job_name, table, source)
+    job = bigquery_client.load_table_from_uri(source, table_ref)
 
-    job.begin()
-    job.result()  # Wait for job to complete
+    job.result()  # Waits for job to complete
 
     print('Loaded {} rows into {}:{}.'.format(
-        job.output_rows, dataset_name, table_name))
+        job.output_rows, dataset_id, table_id))
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(
         description=__doc__,
         formatter_class=argparse.RawDescriptionHelpFormatter)
-    parser.add_argument('dataset_name')
-    parser.add_argument('table_name')
+    parser.add_argument('dataset_id')
+    parser.add_argument('table_id')
     parser.add_argument(
         'source', help='The Google Cloud Storage object to load. Must be in '
         'the format gs://bucket_name/object_name')
 
     args = parser.parse_args()
 
     load_data_from_gcs(
-        args.dataset_name,
-        args.table_name,
+        args.dataset_id,
+        args.table_id,
         args.source)

bigquery/cloud-client/query.py

@@ -27,63 +27,52 @@
 """
 
 import argparse
-import uuid
 
 from google.cloud import bigquery
 
 
 def query(query):
     client = bigquery.Client()
-    query_job = client.run_async_query(str(uuid.uuid4()), query)
-
-    query_job.begin()
-    query_job.result()  # Wait for job to complete.
+    query_job = client.query(query)
 
     # Print the results.
-    destination_table = query_job.destination
-    destination_table.reload()
-    for row in destination_table.fetch_data():
+    for row in query_job.result():  # Waits for job to complete.
         print(row)
 
 
 def query_standard_sql(query):
     client = bigquery.Client()
-    query_job = client.run_async_query(str(uuid.uuid4()), query)
-    # Set use_legacy_sql to False to use standard SQL syntax. See:
-    # https://cloud.google.com/bigquery/docs/reference/standard-sql/enabling-standard-sql
-    query_job.use_legacy_sql = False
+    job_config = bigquery.QueryJobConfig()
 
-    query_job.begin()
-    query_job.result()  # Wait for job to complete.
+    # Set use_legacy_sql to False to use standard SQL syntax.
+    # Note that queries are treated as standard SQL by default.
+    job_config.use_legacy_sql = False
+    query_job = client.query(query, job_config=job_config)
 
     # Print the results.
-    destination_table = query_job.destination
-    destination_table.reload()
-    for row in destination_table.fetch_data():
+    for row in query_job.result():  # Waits for job to complete.
         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)
+    job_config = bigquery.QueryJobConfig()
 
     # Allow for query results larger than the maximum response size.
-    query_job.allow_large_results = True
+    job_config.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
+    dest_dataset_ref = client.dataset(dest_dataset_id)
+    dest_table_ref = dest_dataset_ref.table(dest_table_id)
+    job_config.destination = dest_table_ref
 
     # Allow the results table to be overwritten.
-    query_job.write_disposition = 'WRITE_TRUNCATE'
+    job_config.write_disposition = 'WRITE_TRUNCATE'
 
-    query_job.begin()
-    query_job.result()  # Wait for job to complete.
+    query_job = client.query(query, job_config=job_config)
 
-    # 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 the results.
+    for row in query_job.result():  # Waits for job to complete.
         print(row)