forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathsync_query_params.py
More file actions
120 lines (100 loc) · 3.84 KB
/
Copy pathsync_query_params.py
File metadata and controls
120 lines (100 loc) · 3.84 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
#!/usr/bin/env python
# Copyright 2016 Google Inc.
#
# 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
#
# http://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.
"""Command-line app to perform synchronous queries with parameters in BigQuery.
For more information, see the README.md under /bigquery.
Example invocation:
$ python sync_query_params.py --use-named-params 'romeoandjuliet' 100
$ python sync_query_params.py --use-positional-params 'romeoandjuliet' 100
"""
import argparse
from google.cloud import bigquery
def print_results(query_results):
"""Print the query results by requesting a page at a time."""
page_token = None
while True:
rows, total_rows, page_token = query_results.fetch_data(
max_results=10,
page_token=page_token)
for row in rows:
print(row)
if not page_token:
break
def sync_query_positional_params(corpus, min_word_count):
client = bigquery.Client()
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_parameters=(
bigquery.ScalarQueryParameter(
# Set the name to None to use positional parameters (? symbol
# in the query). Note that you cannot mix named and positional
# parameters.
None,
'STRING',
corpus),
bigquery.ScalarQueryParameter(None, 'INT64', min_word_count)))
# Only standard SQL syntax supports parameters in queries.
# See: https://cloud.google.com/bigquery/sql-reference/
query_results.use_legacy_sql = False
query_results.run()
print_results(query_results)
def sync_query_named_params(corpus, min_word_count):
client = bigquery.Client()
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_parameters=(
bigquery.ScalarQueryParameter('corpus', 'STRING', corpus),
bigquery.ScalarQueryParameter(
'min_word_count',
'INT64',
min_word_count)))
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(
'corpus',
help='Corpus to search from Shakespeare dataset.')
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)
args = parser.parse_args()
if args.use_named_params:
sync_query_named_params(args.corpus, args.min_word_count)
else:
sync_query_positional_params(args.corpus, args.min_word_count)