def test_from_query_job(self):
from google.cloud.bigquery.dataset import Dataset
from google.cloud.bigquery.job import QueryJob
from google.cloud.bigquery._helpers import UDFResource
DS_NAME = 'DATASET'
RESOURCE_URI = 'gs://some-bucket/js/lib.js'
client = _Client(self.PROJECT)
job = QueryJob(
self.JOB_NAME,
self.QUERY,
client,
udf_resources=[UDFResource("resourceUri", RESOURCE_URI)])
dataset = job.default_dataset = Dataset(DS_NAME, client)
job.use_query_cache = True
job.use_legacy_sql = True
klass = self._getTargetClass()
query = klass.from_query_job(job)
self.assertEqual(query.name, self.JOB_NAME)
self.assertEqual(query.query, self.QUERY)
self.assertIs(query._client, client)
self.assertIs(query._job, job)
self.assertEqual(query.udf_resources, job.udf_resources)
self.assertIs(query.default_dataset, dataset)
self.assertTrue(query.use_query_cache)
self.assertTrue(query.use_legacy_sql)
def run_async_query(self,
job_name,
query,
udf_resources=(),
query_parameters=()):
"""Construct a job for running a SQL query asynchronously.
See
https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.query
:type job_name: str
:param job_name: Name of the job.
:type query: str
:param query: SQL query to be executed
:type udf_resources: tuple
:param udf_resources: An iterable of
:class:`google.cloud.bigquery._helpers.UDFResource`
(empty by default)
:type query_parameters: tuple
:param query_parameters:
An iterable of
:class:`google.cloud.bigquery._helpers.AbstractQueryParameter`
(empty by default)
:rtype: :class:`google.cloud.bigquery.job.QueryJob`
:returns: a new ``QueryJob`` instance
"""
return QueryJob(job_name,
query,
client=self,
udf_resources=udf_resources,
query_parameters=query_parameters)
def send_to_gcs(self, query, project_id, output_uri, delimiter=","):
job_results = {}
client = self.bq_client
queryJob = QueryJob(self.__create_job_id(project_id, "queryJob"),
query, client)
job_results["queryJob"] = self.__get_results(queryJob)
output_type = output_uri.split(".")[-1]
dest_format = self.__get_file_type(output_type)
if dest_format == SourceFormat.CSV:
config = ExtractJobConfig(destination_format=dest_format,
field_delimiter=delimiter)
else:
config = ExtractJobConfig(destination_format=dest_format)
extractJob = ExtractJob(self.__create_job_id(project_id, "extractJob"),
queryJob.destination,
output_uri,
client,
job_config=config)
job_results["extractJob"] = self.__get_results(extractJob)
return job_results
def job(self):
"""Job instance used to run the query.
:rtype: :class:`google.cloud.bigquery.job.QueryJob`, or ``NoneType``
:returns: Job instance used to run the query (None until
``jobReference`` property is set by the server).
"""
if self._job is None:
job_ref = self._properties.get('jobReference')
if job_ref is not None:
self._job = QueryJob(job_ref['jobId'], self.query,
self._client)
return self._job
def run_async_query(self, job_name, query):
"""Construct a job for running a SQL query asynchronously.
See:
https://cloud.google.com/bigquery/docs/reference/v2/jobs#configuration.query
:type job_name: str
:param job_name: Name of the job.
:type query: str
:param query: SQL query to be executed
:rtype: :class:`google.cloud.bigquery.job.QueryJob`
:returns: a new ``QueryJob`` instance
"""
return QueryJob(job_name, query, client=self)
def test_from_query_job_wo_default_dataset(self):
from google.cloud.bigquery.job import QueryJob
from google.cloud.bigquery._helpers import UDFResource
RESOURCE_URI = 'gs://some-bucket/js/lib.js'
client = _Client(self.PROJECT)
job = QueryJob(
self.JOB_NAME, self.QUERY, client,
udf_resources=[UDFResource("resourceUri", RESOURCE_URI)])
klass = self._getTargetClass()
query = klass.from_query_job(job)
self.assertEqual(query.query, self.QUERY)
self.assertTrue(query._client is client)
self.assertTrue(query._job is job)
self.assertEqual(query.udf_resources, job.udf_resources)
self.assertIsNone(query.default_dataset)
self.assertIsNone(query.use_query_cache)
self.assertIsNone(query.use_legacy_sql)
