[
https://issues.apache.org/jira/browse/BEAM-6553?focusedWorklogId=198397&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-198397
]
ASF GitHub Bot logged work on BEAM-6553:
----------------------------------------
Author: ASF GitHub Bot
Created on: 13/Feb/19 23:32
Start Date: 13/Feb/19 23:32
Worklog Time Spent: 10m
Work Description: pabloem commented on pull request #7655: [BEAM-6553] A
Python SDK sink that supports File Loads into BQ
URL: https://github.com/apache/beam/pull/7655#discussion_r256634728
##########
File path: sdks/python/apache_beam/io/gcp/bigquery_file_loads.py
##########
@@ -0,0 +1,589 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You 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.
+#
+
+"""
+Functionality to perform file loads into BigQuery for Batch and Streaming
+pipelines.
+
+This source is able to work around BigQuery load quotas and limitations. When
+destinations are dynamic, or when data for a single job is too large, the data
+will be split into multiple jobs.
+
+NOTHING IN THIS FILE HAS BACKWARDS COMPATIBILITY GUARANTEES.
+"""
+
+from __future__ import absolute_import
+
+import datetime
+import hashlib
+import logging
+import random
+import time
+import uuid
+
+from future.utils import iteritems
+
+import apache_beam as beam
+from apache_beam import pvalue
+from apache_beam.io import filesystems as fs
+from apache_beam.io.gcp import bigquery_tools
+from apache_beam.io.gcp.internal.clients import bigquery as bigquery_api
+from apache_beam.options import value_provider as vp
+from apache_beam.transforms.combiners import Count
+
+ONE_TERABYTE = (1 << 40)
+
+# The maximum file size for imports is 5TB. We keep our files under that.
+_DEFAULT_MAX_FILE_SIZE = 4 * ONE_TERABYTE
+
+_DEFAULT_MAX_WRITERS_PER_BUNDLE = 20
+
+# The maximum size for a single load job is one terabyte
+_MAXIMUM_LOAD_SIZE = 15 * ONE_TERABYTE
+
+# Big query only supports up to 10 thousand URIs for a single load job.
+_MAXIMUM_SOURCE_URIS = 10*1000
+
+
+def _generate_load_job_name():
+ datetime_component = datetime.datetime.now().strftime("%Y_%m_%d_%H%M%S")
+ # TODO(pabloem): include job id / pipeline component?
+ return 'beam_load_%s_%s' % (datetime_component, random.randint(0, 100))
+
+
+def _generate_file_prefix(pipeline_gcs_location):
+ # If a gcs location is provided to the pipeline, then we shall use that.
Review comment:
Hm? GCS is what it says : )
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 198397)
Time Spent: 9h (was: 8h 50m)
> A BigQuery sink thta is SDK-implemented and supports file loads in Python
> -------------------------------------------------------------------------
>
> Key: BEAM-6553
> URL: https://issues.apache.org/jira/browse/BEAM-6553
> Project: Beam
> Issue Type: Improvement
> Components: sdk-py-core
> Reporter: Pablo Estrada
> Assignee: Pablo Estrada
> Priority: Major
> Labels: triaged
> Time Spent: 9h
> Remaining Estimate: 0h
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
