FilesExpand file tree

 mlengine

/

async_query.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

executable file

·

75 lines (56 loc) · 2.03 KB

 mlengine

/

async_query.py

Copy path

Top

File metadata and controls

• Code
• Blame

executable file

·

75 lines (56 loc) · 2.03 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

#!/usr/bin/env python

# Copyright 2016 Google Inc. All Rights Reserved.

#

# 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 asynchronous queries in BigQuery.

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

Example invocation:

$ python async_query.py \\

'SELECT corpus FROM `publicdata.samples.shakespeare` GROUP BY corpus'

"""

import argparse

import time

import uuid

from google.cloud import bigquery

def wait_for_job(job):

while True:

job.reload() # Refreshes the state via a GET request.

if job.state == 'DONE':

if job.error_result:

raise RuntimeError(job.errors)

return

time.sleep(1)

def async_query(query):

client = bigquery.Client()

query_job = client.run_async_query(str(uuid.uuid4()), query)

query_job.use_legacy_sql = False

query_job.begin()

wait_for_job(query_job)

# Drain the query results by requesting a page at a time.

query_results = query_job.results()

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

if __name__ == '__main__':

parser = argparse.ArgumentParser(

description=__doc__,

formatter_class=argparse.RawDescriptionHelpFormatter)

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

args = parser.parse_args()

async_query(args.query)