Skip to content

Fixed errors with nullables. #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
0xinsanity wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fixed errors with nullables. #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dc03768
fixed nullable array issues
0xinsanity Aug 27, 2020
5474c80
changed error handling
0xinsanity Aug 27, 2020
76999f2
finished ignore unknown values
0xinsanity Aug 27, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
from setuptools import setup

setup(name='target-bigquery',
version='1.4.0',
version='1.4.4',
description='Singer.io target for writing data to Google BigQuery',
author='RealSelf Business Intelligence',
url='https://github.com/RealSelf/target-bigquery',
Expand Down
16 changes: 8 additions & 8 deletions target_bigquery.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,11 +66,12 @@ def define_schema(field, name):
field = types

if isinstance(field['type'], list):
if field['type'][0] == "null":
schema_mode = 'NULLABLE'
else:
schema_mode = 'required'
schema_mode = 'NULLABLE'
schema_type = field['type'][-1]
if schema_type == 'null':
schema_type = field['type'][0]
if schema_type == 'null':
schema_type = field['type'][1]
else:
schema_type = field['type']
if schema_type == "object":
Expand All @@ -79,7 +80,7 @@ def define_schema(field, name):
if schema_type == "array":
schema_type = field.get('items').get('type')
schema_mode = "REPEATED"
if schema_type == "object":
if schema_type == "object" or "object" in schema_type:
schema_type = "RECORD"
schema_fields = tuple(build_schema(field.get('items')))

Expand Down Expand Up @@ -116,7 +117,6 @@ def persist_lines_job(project_id, dataset_id, lines=None, truncate=False, valida
errors = {}

bigquery_client = bigquery.Client(project=project_id)

# try:
# dataset = bigquery_client.create_dataset(Dataset(dataset_ref)) or Dataset(dataset_ref)
# except exceptions.Conflict:
Expand Down Expand Up @@ -228,7 +228,7 @@ def persist_lines_stream(project_id, dataset_id, lines=None, validate_records=Tr
if validate_records:
validate(msg.record, schema)

errors[msg.stream] = bigquery_client.insert_rows_json(tables[msg.stream], [msg.record])
errors[msg.stream] = bigquery_client.insert_rows_json(tables[msg.stream], [msg.record], ignore_unknown_values=True)
rows[msg.stream] += 1

state = None
Expand Down Expand Up @@ -261,7 +261,7 @@ def persist_lines_stream(project_id, dataset_id, lines=None, validate_records=Tr
logging.info('Loaded {} row(s) into {}:{}'.format(rows[table], dataset_id, table, tables[table].path))
emit_state(state)
else:
logging.error('Errors:', errors[table], sep=" ")
print(errors[table])

return state

Expand Down