FilesExpand file tree

 numpy

/

sync_query.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

executable file

·

116 lines (95 loc) · 3.31 KB

 numpy

/

sync_query.py

Copy path

Top

File metadata and controls

• Code
• Blame

executable file

·

116 lines (95 loc) · 3.31 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

#!/usr/bin/env python

# Copyright 2015, 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 application to perform an synchronous query in BigQuery.

For more information, see the README.md under /bigquery.

"""

import argparse

import json

from googleapiclient import discovery

from oauth2client.client import GoogleCredentials

# [START sync_query]

def sync_query(

bigquery, project_id, query,

timeout=10000, num_retries=5, use_legacy_sql=False):

query_data = {

'query': query,

'timeoutMs': timeout,

# Set to False to use standard SQL syntax. See:

# https://cloud.google.com/bigquery/sql-reference/enabling-standard-sql

'useLegacySQL': use_legacy_sql

}

return bigquery.jobs().query(

projectId=project_id,

body=query_data).execute(num_retries=num_retries)

# [END sync_query]

# [START run]

def main(project_id, query, timeout, num_retries, use_legacy_sql):

# [START build_service]

# Grab the application's default credentials from the environment.

credentials = GoogleCredentials.get_application_default()

# Construct the service object for interacting with the BigQuery API.

bigquery = discovery.build('bigquery', 'v2', credentials=credentials)

# [END build_service]

query_job = sync_query(

bigquery,

project_id,

query,

timeout,

num_retries,

use_legacy_sql)

# [START paging]

# Page through the result set and print all results.

results = []

page_token = None

while True:

page = bigquery.jobs().getQueryResults(

pageToken=page_token,

**query_job['jobReference']).execute(num_retries=2)

results.extend(page.get('rows', []))

page_token = page.get('pageToken')

if not page_token:

break

print(json.dumps(results))

# [END paging]

# [END run]

# [START main]

if __name__ == '__main__':

parser = argparse.ArgumentParser(

description=__doc__,

formatter_class=argparse.RawDescriptionHelpFormatter)

parser.add_argument('project_id', help='Your Google Cloud project ID.')

parser.add_argument('query', help='BigQuery SQL Query.')

parser.add_argument(

'-t', '--timeout',

help='Number seconds to wait for a result',

type=int,

default=30)

parser.add_argument(

'-r', '--num_retries',

help='Number of times to retry in case of 500 error.',

type=int,

default=5)

parser.add_argument(

'-l', '--use_legacy_sql',

help='Use legacy BigQuery SQL syntax instead of standard SQL syntax.',

type=bool,

default=False)

args = parser.parse_args()

main(

args.project_id,

args.query,

args.timeout,

args.num_retries,

args.use_legacy_sql)

# [END main]