BigQuery: named parameter query samples

- query using an array value as a parameter. - query using timestamps in named parameters. See: https://cloud.google.com/bigquery/querying-data#using_timestamps_in_parameterized_queries - query using a struct in query parameters.

Author: tswast

bigquery/cloud-client/requirements.txt

@@ -1 +1,2 @@
 google-cloud-bigquery==0.22.1
+pytz==2016.10

bigquery/cloud-client/sync_query_params.py

@@ -24,8 +24,10 @@
 """
 
 import argparse
+import datetime
 
 from google.cloud import bigquery
+import pytz
 
 
 def print_results(query_results):
@@ -46,13 +48,14 @@ def print_results(query_results):
 
 def sync_query_positional_params(corpus, min_word_count):
  client = bigquery.Client()
+ query = """SELECT word, word_count
+ FROM `bigquery-public-data.samples.shakespeare`
+ WHERE corpus = ?
+ AND word_count >= ?
+ ORDER BY word_count DESC;
+ """
  query_results = client.run_sync_query(
- """SELECT word, word_count
- FROM `bigquery-public-data.samples.shakespeare`
- WHERE corpus = ?
- AND word_count >= ?
- ORDER BY word_count DESC;
- """,
+ query,
  query_parameters=(
  bigquery.ScalarQueryParameter(
  # Set the name to None to use positional parameters (? symbol
@@ -72,13 +75,14 @@ def sync_query_positional_params(corpus, min_word_count):
 
 def sync_query_named_params(corpus, min_word_count):
  client = bigquery.Client()
+ query = """SELECT word, word_count
+ FROM `bigquery-public-data.samples.shakespeare`
+ WHERE corpus = @corpus
+ AND word_count >= @min_word_count
+ ORDER BY word_count DESC;
+ """
  query_results = client.run_sync_query(
- """SELECT word, word_count
- FROM `bigquery-public-data.samples.shakespeare`
- WHERE corpus = @corpus
- AND word_count >= @min_word_count
- ORDER BY word_count DESC;
- """,
+ query,
  query_parameters=(
  bigquery.ScalarQueryParameter('corpus', 'STRING', corpus),
  bigquery.ScalarQueryParameter(
@@ -90,31 +94,118 @@ def sync_query_named_params(corpus, min_word_count):
  print_results(query_results)
 
 
+def sync_query_array_params(gender, states):
+ client = bigquery.Client()
+ query = """SELECT name, sum(number) as count
+ FROM `bigquery-public-data.usa_names.usa_1910_2013`
+ WHERE gender = @gender
+ AND state IN UNNEST(@states)
+ GROUP BY name
+ ORDER BY count DESC
+ LIMIT 10;
+ """
+ query_results = client.run_sync_query(
+ query,
+ query_parameters=(
+ bigquery.ScalarQueryParameter('gender', 'STRING', gender),
+ bigquery.ArrayQueryParameter('states', 'STRING', states)))
+ query_results.use_legacy_sql = False
+ query_results.run()
+ print_results(query_results)
+
+
+def sync_query_timestamp_params(year, month, day, hour, minute):
+ client = bigquery.Client()
+ query = 'SELECT TIMESTAMP_ADD(@ts_value, INTERVAL 1 HOUR);'
+ query_results = client.run_sync_query(
+ query,
+ query_parameters=[
+ bigquery.ScalarQueryParameter(
+ 'ts_value',
+ 'TIMESTAMP',
+ datetime.datetime(
+ year, month, day, hour, minute, tzinfo=pytz.UTC))])
+ query_results.use_legacy_sql = False
+ query_results.run()
+ print_results(query_results)
+
+
+def sync_query_struct_params(x, y):
+ client = bigquery.Client()
+ query = 'SELECT @struct_value AS s;'
+ query_results = client.run_sync_query(
+ query,
+ query_parameters=[
+ bigquery.StructQueryParameter(
+ 'struct_value',
+ bigquery.ScalarQueryParameter('x', 'INT64', x),
+ bigquery.ScalarQueryParameter('y', 'STRING', y))])
+ query_results.use_legacy_sql = False
+ query_results.run()
+ print_results(query_results)
+
+
 if __name__ == '__main__':
  parser = argparse.ArgumentParser(
  description=__doc__,
  formatter_class=argparse.RawDescriptionHelpFormatter)
- parser.add_argument(
+ subparsers = parser.add_subparsers(dest='sample', help='samples')
+ named_parser = subparsers.add_parser(
+ 'named',
+ help='Run a query with named parameters.')
+ named_parser.add_argument(
  'corpus',
  help='Corpus to search from Shakespeare dataset.')
- parser.add_argument(
+ named_parser.add_argument(
  'min_word_count',
  help='Minimum count of words to query.',
  type=int)
-
- params_type_parser = parser.add_mutually_exclusive_group(required=False)
- params_type_parser.add_argument(
- '--use-named-params',
- dest='use_named_params',
- action='store_true')
- params_type_parser.add_argument(
- '--use-positional-params',
- dest='use_named_params',
- action='store_false')
- parser.set_defaults(use_named_params=False)
+ positional_parser = subparsers.add_parser(
+ 'positional',
+ help='Run a query with positional parameters.')
+ positional_parser.add_argument(
+ 'corpus',
+ help='Corpus to search from Shakespeare dataset.')
+ positional_parser.add_argument(
+ 'min_word_count',
+ help='Minimum count of words to query.',
+ type=int)
+ array_parser = subparsers.add_parser(
+ 'array',
+ help='Run a query with an array parameter.')
+ array_parser.add_argument(
+ 'gender',
+ choices=['F', 'M'],
+ help='Gender of baby in the Social Security baby names database.')
+ array_parser.add_argument(
+ 'states',
+ help='U.S. States to consider for popular baby names.',
+ nargs='+')
+ timestamp_parser = subparsers.add_parser(
+ 'timestamp',
+ help='Run a query with a timestamp parameter.')
+ timestamp_parser.add_argument('year', type=int)
+ timestamp_parser.add_argument('month', type=int)
+ timestamp_parser.add_argument('day', type=int)
+ timestamp_parser.add_argument('hour', type=int)
+ timestamp_parser.add_argument('minute', type=int)
+ struct_parser = subparsers.add_parser(
+ 'struct',
+ help='Run a query with a struct parameter.')
+ struct_parser.add_argument('x', help='Integer for x', type=int)
+ struct_parser.add_argument('y', help='String for y')
  args = parser.parse_args()
 
- if args.use_named_params:
+ if args.sample == 'named':
  sync_query_named_params(args.corpus, args.min_word_count)
- else:
+ elif args.sample == 'positional':
  sync_query_positional_params(args.corpus, args.min_word_count)
+ elif args.sample == 'array':
+ sync_query_array_params(args.gender, args.states)
+ elif args.sample == 'timestamp':
+ sync_query_timestamp_params(
+ args.year, args.month, args.day, args.hour, args.minute)
+ elif args.sample == 'struct':
+ sync_query_struct_params(args.x, args.y)
+ else:
+ print('Unexpected value for sample')

bigquery/cloud-client/sync_query_params_test.py

@@ -16,11 +16,11 @@
 
 
 def test_sync_query_named_params(capsys):
- sync_query_params.sync_query_named_params(
- corpus='romeoandjuliet',
- min_word_count=100)
+ sync_query_params.sync_query_array_params(
+ gender='M',
+ states=['WA', 'WI', 'WV', 'WY'])
  out, _ = capsys.readouterr()
- assert 'love' in out
+ assert 'James' in out
 
 
 def test_sync_query_positional_params(capsys):
@@ -29,3 +29,16 @@ def test_sync_query_positional_params(capsys):
  min_word_count=100)
  out, _ = capsys.readouterr()
  assert 'love' in out
+
+
+def test_sync_query_struct_params(capsys):
+ sync_query_params.sync_query_struct_params(765, "hello world")
+ out, _ = capsys.readouterr()
+ assert '765' in out
+ assert 'hello world' in out
+
+
+def test_sync_query_timestamp_params(capsys):
+ sync_query_params.sync_query_timestamp_params(2016, 12, 7, 8, 0)
+ out, _ = capsys.readouterr()
+ assert '2016-12-07 09:00:00' in out