Skip to content

BigQuery: Adds schema update options and snippets #5415

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

Merged
theacodes merged 8 commits into from
May 31, 2018
Merged

BigQuery: Adds schema update options and snippets #5415

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
662bf81
Adds SchemaUpdateOption
alixhami May 29, 2018
9ece7a8
adds schema update options for load jobs
alixhami May 30, 2018
de2bf6a
adds schema update options for query jobs
alixhami May 30, 2018
602292c
adds snippets for adding/relaxing column through load or query job
alixhami May 30, 2018
82f0a1c
add SchemaUpdateOption to reference page
alixhami May 30, 2018
a78df1e
fixes lint
alixhami May 30, 2018
1a31110
Refactors code samples to be clearer and closer to actual use case
alixhami May 31, 2018
30d22a3
fixes lint
alixhami May 31, 2018
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: 2 additions & 0 deletions bigquery/google/cloud/bigquery/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@
from google.cloud.bigquery.job import QueryJob
from google.cloud.bigquery.job import QueryJobConfig
from google.cloud.bigquery.job import QueryPriority
from google.cloud.bigquery.job import SchemaUpdateOption
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import UnknownJob
from google.cloud.bigquery.job import WriteDisposition
Expand Down Expand Up @@ -113,6 +114,7 @@
'DestinationFormat',
'Encoding',
'QueryPriority',
'SchemaUpdateOption',
'SourceFormat',
'WriteDisposition'
]
Expand Down
50 changes: 50 additions & 0 deletions bigquery/google/cloud/bigquery/job.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,18 @@ class WriteDisposition(object):
returned in the job result."""


class SchemaUpdateOption(object):
"""Specifies an update to the destination table schema as a side effect of
a load job.
"""

ALLOW_FIELD_ADDITION = 'ALLOW_FIELD_ADDITION'
"""Allow adding a nullable field to the schema."""

ALLOW_FIELD_RELAXATION = 'ALLOW_FIELD_RELAXATION'
"""Allow relaxing a required field in the original schema to nullable."""


class _JobReference(object):
"""A reference to a job.

Expand Down Expand Up @@ -1004,6 +1016,18 @@ def time_partitioning(self, value):
api_repr = value.to_api_repr()
self._set_sub_prop('timePartitioning', api_repr)

@property
def schema_update_options(self):
"""List[google.cloud.bigquery.job.SchemaUpdateOption]: Specifies
updates to the destination table schema to allow as a side effect of
the load job.
"""
return self._get_sub_prop('schemaUpdateOptions')

@schema_update_options.setter
def schema_update_options(self, values):
self._set_sub_prop('schemaUpdateOptions', values)


class LoadJob(_AsyncJob):
"""Asynchronous job for loading data into a table.
Expand Down Expand Up @@ -1158,6 +1182,13 @@ def time_partitioning(self):
"""
return self._configuration.time_partitioning

@property
def schema_update_options(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.schema_update_options`.
"""
return self._configuration.schema_update_options

@property
def input_file_bytes(self):
"""Count of bytes loaded from source files.
Expand Down Expand Up @@ -1971,6 +2002,18 @@ def time_partitioning(self, value):
api_repr = value.to_api_repr()
self._set_sub_prop('timePartitioning', api_repr)

@property
def schema_update_options(self):
"""List[google.cloud.bigquery.job.SchemaUpdateOption]: Specifies
updates to the destination table schema to allow as a side effect of
the query job.
"""
return self._get_sub_prop('schemaUpdateOptions')

@schema_update_options.setter
def schema_update_options(self, values):
self._set_sub_prop('schemaUpdateOptions', values)

def to_api_repr(self):
"""Build an API representation of the query job config.

Expand Down Expand Up @@ -2149,6 +2192,13 @@ def time_partitioning(self):
"""
return self._configuration.time_partitioning

@property
def schema_update_options(self):
"""See
:attr:`google.cloud.bigquery.job.QueryJobConfig.schema_update_options`.
"""
return self._configuration.schema_update_options

def _build_resource(self):
"""Generate a resource for :meth:`begin`."""
configuration = self._configuration.to_api_repr()
Expand Down
34 changes: 32 additions & 2 deletions bigquery/tests/unit/test_job.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -380,6 +380,11 @@ def _verifyEnumConfigProperties(self, job, config):
config['writeDisposition'])
else:
self.assertIsNone(job.write_disposition)
if 'schemaUpdateOptions' in config:
self.assertEqual(
job.schema_update_options, config['schemaUpdateOptions'])
else:
self.assertIsNone(job.schema_update_options)

def _verifyResourceProperties(self, job, resource):
self._verifyReadonlyResourceProperties(job, resource)
Expand Down Expand Up @@ -467,6 +472,7 @@ def test_ctor(self):
self.assertIsNone(job.write_disposition)
self.assertIsNone(job.destination_encryption_configuration)
self.assertIsNone(job.time_partitioning)
self.assertIsNone(job.schema_update_options)

def test_ctor_w_config(self):
from google.cloud.bigquery.schema import SchemaField
Expand Down Expand Up @@ -780,6 +786,7 @@ def test_begin_w_autodetect(self):

def test_begin_w_alternate_client(self):
from google.cloud.bigquery.job import CreateDisposition
from google.cloud.bigquery.job import SchemaUpdateOption
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.schema import SchemaField

Expand Down Expand Up @@ -817,7 +824,10 @@ def test_begin_w_alternate_client(self):
'mode': 'REQUIRED',
'description': None,
},
]}
]},
'schemaUpdateOptions': [
SchemaUpdateOption.ALLOW_FIELD_ADDITION,
],
}
RESOURCE['configuration']['load'] = LOAD_CONFIGURATION
conn1 = _make_connection()
Expand All @@ -842,6 +852,9 @@ def test_begin_w_alternate_client(self):
config.skip_leading_rows = 1
config.source_format = 'CSV'
config.write_disposition = WriteDisposition.WRITE_TRUNCATE
config.schema_update_options = [
SchemaUpdateOption.ALLOW_FIELD_ADDITION,
]

job._begin(client=client2)

Expand Down Expand Up @@ -2127,6 +2140,11 @@ def _verifyResourceProperties(self, job, resource):
'kmsKeyName'])
else:
self.assertIsNone(job.destination_encryption_configuration)
if 'schemaUpdateOptions' in query_config:
self.assertEqual(
job.schema_update_options, query_config['schemaUpdateOptions'])
else:
self.assertIsNone(job.schema_update_options)

def test_ctor_defaults(self):
client = _make_client(project=self.PROJECT)
Expand Down Expand Up @@ -2157,6 +2175,7 @@ def test_ctor_defaults(self):
self.assertIsNone(job.table_definitions)
self.assertIsNone(job.destination_encryption_configuration)
self.assertIsNone(job.time_partitioning)
self.assertIsNone(job.schema_update_options)

def test_ctor_w_udf_resources(self):
from google.cloud.bigquery.job import QueryJobConfig
Expand Down Expand Up @@ -2248,6 +2267,7 @@ def test_from_api_repr_with_encryption(self):

def test_from_api_repr_w_properties(self):
from google.cloud.bigquery.job import CreateDisposition
from google.cloud.bigquery.job import SchemaUpdateOption
from google.cloud.bigquery.job import WriteDisposition

client = _make_client(project=self.PROJECT)
Expand All @@ -2260,6 +2280,9 @@ def test_from_api_repr_w_properties(self):
'datasetId': self.DS_ID,
'tableId': self.DESTINATION_TABLE,
}
query_config['schemaUpdateOptions'] = [
SchemaUpdateOption.ALLOW_FIELD_ADDITION,
]
klass = self._get_target_class()
job = klass.from_api_repr(RESOURCE, client=client)
self.assertIs(job._client, client)
Expand Down Expand Up @@ -2841,6 +2864,7 @@ def test_begin_w_alternate_client(self):
from google.cloud.bigquery.job import CreateDisposition
from google.cloud.bigquery.job import QueryJobConfig
from google.cloud.bigquery.job import QueryPriority
from google.cloud.bigquery.job import SchemaUpdateOption
from google.cloud.bigquery.job import WriteDisposition

PATH = '/projects/%s/jobs' % (self.PROJECT,)
Expand All @@ -2866,7 +2890,10 @@ def test_begin_w_alternate_client(self):
'useLegacySql': True,
'writeDisposition': WriteDisposition.WRITE_TRUNCATE,
'maximumBillingTier': 4,
'maximumBytesBilled': '123456'
'maximumBytesBilled': '123456',
'schemaUpdateOptions': [
SchemaUpdateOption.ALLOW_FIELD_RELAXATION,
]
}
RESOURCE['configuration']['query'] = QUERY_CONFIGURATION
RESOURCE['configuration']['dryRun'] = True
Expand All @@ -2890,6 +2917,9 @@ def test_begin_w_alternate_client(self):
config.use_query_cache = True
config.write_disposition = WriteDisposition.WRITE_TRUNCATE
config.maximum_bytes_billed = 123456
config.schema_update_options = [
SchemaUpdateOption.ALLOW_FIELD_RELAXATION,
]
job = self._make_one(
self.JOB_ID, self.QUERY, client1, job_config=config)

Expand Down
1 change: 1 addition & 0 deletions docs/bigquery/reference.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,7 @@ Job-Related Types
job.QueryPriority
job.SourceFormat
job.WriteDisposition
job.SchemaUpdateOption


Dataset
Expand Down
Loading