forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathload_data_from_csv.py
More file actions
executable file
·164 lines (135 loc) · 4.67 KB
/
load_data_from_csv.py
File metadata and controls
executable file
·164 lines (135 loc) · 4.67 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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
#!/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 that loads data into BigQuery from a CSV file in
Google Cloud Storage.
This sample is used on this page:
https://cloud.google.com/bigquery/loading-data-into-bigquery#loaddatagcs
For more information, see the README.rst.
"""
import argparse
import json
import time
import uuid
import googleapiclient.discovery
# [START load_table]
def load_table(bigquery, project_id, dataset_id, table_name, source_schema,
source_path, num_retries=5):
"""
Starts a job to load a bigquery table from CSV
Args:
bigquery: an initialized and authorized bigquery client
google-api-client object
source_schema: a valid bigquery schema,
see https://cloud.google.com/bigquery/docs/reference/v2/tables
source_path: the fully qualified Google Cloud Storage location of
the data to load into your table
Returns: a bigquery load job, see
https://cloud.google.com/bigquery/docs/reference/v2/jobs#configuration.load
"""
# Generate a unique job ID so retries
# don't accidentally duplicate query
job_data = {
'jobReference': {
'projectId': project_id,
'jobId': str(uuid.uuid4())
},
'configuration': {
'load': {
'sourceUris': [source_path],
'schema': {
'fields': source_schema
},
'destinationTable': {
'projectId': project_id,
'datasetId': dataset_id,
'tableId': table_name
}
}
}
}
return bigquery.jobs().insert(
projectId=project_id,
body=job_data).execute(num_retries=num_retries)
# [END load_table]
# [START poll_job]
def poll_job(bigquery, job):
"""Waits for a job to complete."""
print('Waiting for job to finish...')
request = bigquery.jobs().get(
projectId=job['jobReference']['projectId'],
jobId=job['jobReference']['jobId'])
while True:
result = request.execute(num_retries=2)
if result['status']['state'] == 'DONE':
if 'errorResult' in result['status']:
raise RuntimeError(result['status']['errorResult'])
print('Job complete.')
return
time.sleep(1)
# [END poll_job]
# [START run]
def main(project_id, dataset_id, table_name, schema_file, data_path,
poll_interval, num_retries):
# [START build_service]
# Construct the service object for interacting with the BigQuery API.
bigquery = googleapiclient.discovery.build('bigquery', 'v2')
# [END build_service]
with open(schema_file, 'r') as f:
schema = json.load(f)
job = load_table(
bigquery,
project_id,
dataset_id,
table_name,
schema,
data_path,
num_retries)
poll_job(bigquery, job)
# [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('dataset_id', help='A BigQuery dataset ID.')
parser.add_argument(
'table_name', help='Name of the table to load data into.')
parser.add_argument(
'schema_file',
help='Path to a schema file describing the table schema.')
parser.add_argument(
'data_path',
help='Google Cloud Storage path to the CSV data, for example: '
'gs://mybucket/in.csv')
parser.add_argument(
'-p', '--poll_interval',
help='How often to poll the query for completion (seconds).',
type=int,
default=1)
parser.add_argument(
'-r', '--num_retries',
help='Number of times to retry in case of 500 error.',
type=int,
default=5)
args = parser.parse_args()
main(
args.project_id,
args.dataset_id,
args.table_name,
args.schema_file,
args.data_path,
args.poll_interval,
args.num_retries)
# [END main]