def copy_datasets(client: bigquery.Client, input_dataset, output_dataset):
"""
Copies tables from source dataset to a destination datasets
:param client: an instantiated bigquery client object
:param input_dataset: name of the input dataset
:param output_dataset: name of the output dataset
:return:
"""
# Copy input dataset tables to backup and staging datasets
tables = client.list_tables(input_dataset)
for table in tables:
staging_table = f'{output_dataset}.{table.table_id}'
client.copy_table(table, staging_table)
def enrich_task():
client = Client()
# Need to use a temporary table because bq query sets field modes to NULLABLE and descriptions to null
# when writeDisposition is WRITE_TRUNCATE
# Create a temporary table
temp_table_name = '{task}_{milliseconds}'.format(
task=task, milliseconds=int(round(time.time() * 1000)))
temp_table_ref = client.dataset(dataset_name_temp).table(
temp_table_name)
table = Table(temp_table_ref)
description_path = os.path.join(
dags_folder,
'resources/stages/enrich/descriptions/{task}.txt'.format(
task=task))
table.description = read_file(description_path)
if time_partitioning_field is not None:
table.time_partitioning = TimePartitioning(
field=time_partitioning_field)
logging.info('Creating table: ' + json.dumps(table.to_api_repr()))
schema_path = os.path.join(
dags_folder,
'resources/stages/enrich/schemas/{task}.json'.format(
task=task))
schema = read_bigquery_schema_from_file(schema_path)
table.schema = schema
table = client.create_table(table)
assert table.table_id == temp_table_name
# Query from raw to temporary table
query_job_config = QueryJobConfig()
# Finishes faster, query limit for concurrent interactive queries is 50
query_job_config.priority = QueryPriority.INTERACTIVE
query_job_config.destination = temp_table_ref
sql_path = os.path.join(
dags_folder,
'resources/stages/enrich/sqls/{task}.sql'.format(task=task))
sql = read_file(sql_path, environment)
query_job = client.query(sql,
location='US',
job_config=query_job_config)
submit_bigquery_job(query_job, query_job_config)
assert query_job.state == 'DONE'
# Copy temporary table to destination
copy_job_config = CopyJobConfig()
copy_job_config.write_disposition = 'WRITE_TRUNCATE'
dest_table_name = '{task}'.format(task=task)
dest_table_ref = client.dataset(
dataset_name,
project=destination_dataset_project_id).table(dest_table_name)
copy_job = client.copy_table(temp_table_ref,
dest_table_ref,
location='US',
job_config=copy_job_config)
submit_bigquery_job(copy_job, copy_job_config)
assert copy_job.state == 'DONE'
# Delete temp table
client.delete_table(temp_table_ref)
def enrich_task(ds, **kwargs):
template_context = kwargs.copy()
template_context['ds'] = ds
template_context['params'] = environment
client = Client()
# Need to use a temporary table because bq query sets field modes to NULLABLE and descriptions to null
# when writeDisposition is WRITE_TRUNCATE
# Create a temporary table
temp_table_name = '{task}_{milliseconds}'.format(
task=task, milliseconds=int(round(time.time() * 1000)))
temp_table_ref = client.dataset(dataset_name_temp).table(
temp_table_name)
table = Table(temp_table_ref)
description_path = os.path.join(
dags_folder,
'resources/stages/enrich/descriptions/{task}.txt'.format(
task=task))
table.description = read_file(description_path)
table.time_partitioning = TimePartitioning(
field=time_partitioning_field)
logging.info('Creating table: ' + json.dumps(table.to_api_repr()))
schema_path = os.path.join(
dags_folder,
'resources/stages/enrich/schemas/{task}.json'.format(
task=task))
schema = read_bigquery_schema_from_file(schema_path)
table.schema = schema
table = client.create_table(table)
assert table.table_id == temp_table_name
# Query from raw to temporary table
query_job_config = QueryJobConfig()
# Finishes faster, query limit for concurrent interactive queries is 50
query_job_config.priority = QueryPriority.INTERACTIVE
query_job_config.destination = temp_table_ref
sql_path = os.path.join(
dags_folder,
'resources/stages/enrich/sqls/{task}.sql'.format(task=task))
sql_template = read_file(sql_path)
sql = kwargs['task'].render_template('', sql_template,
template_context)
print('Enrichment sql:')
print(sql)
query_job = client.query(sql,
location='US',
job_config=query_job_config)
submit_bigquery_job(query_job, query_job_config)
assert query_job.state == 'DONE'
if load_all_partitions:
# Copy temporary table to destination
copy_job_config = CopyJobConfig()
copy_job_config.write_disposition = 'WRITE_TRUNCATE'
dest_table_name = '{task}'.format(task=task)
dest_table_ref = client.dataset(
dataset_name,
project=destination_dataset_project_id).table(
dest_table_name)
copy_job = client.copy_table(temp_table_ref,
dest_table_ref,
location='US',
job_config=copy_job_config)
submit_bigquery_job(copy_job, copy_job_config)
assert copy_job.state == 'DONE'
else:
# Merge
# https://cloud.google.com/bigquery/docs/reference/standard-sql/dml-syntax#merge_statement
merge_job_config = QueryJobConfig()
# Finishes faster, query limit for concurrent interactive queries is 50
merge_job_config.priority = QueryPriority.INTERACTIVE
merge_sql_path = os.path.join(
dags_folder,
'resources/stages/enrich/sqls/merge_{task}.sql'.format(
task=task))
merge_sql_template = read_file(merge_sql_path)
template_context['params']['source_table'] = temp_table_name
merge_sql = kwargs['task'].render_template(
'', merge_sql_template, template_context)
print('Merge sql:')
print(merge_sql)
merge_job = client.query(merge_sql,
location='US',
job_config=merge_job_config)
submit_bigquery_job(merge_job, merge_job_config)
assert merge_job.state == 'DONE'
# Delete temp table
client.delete_table(temp_table_ref)
