[英]Error when providing arguments during Dataflow Job creation on GCP Console
[英]Dataflow Error providing pubsub topic as arugument
我有一個問題,我正在使用 python 創建數據流模板,並且該模板在啟動新的數據流作業時需要接受 3 個用戶定義的 arguments。
問題出現在 beam.io.gcp.pubsub.WriteToPubSub() 中,我嘗試從 ValueProvider 提供主題名稱,根據谷歌文檔,創建模板時需要該名稱:
https://cloud.google.com/dataflow/docs/guides/templates/creating-templates
源 beam.io.ReadFromPubSub() 與轉換 beam.io.gcp.bigquery.WriteToBigQuery() 一樣,成功接受訂閱值的值提供程序。
顯然分享我的代碼會有所幫助:)
首先是通常的進口:
from __future__ import absolute_import
import argparse
import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.pipeline_options import SetupOptions
from apache_beam.options.pipeline_options import StandardOptions
from apache_beam.options.value_provider import StaticValueProvider
import json
import time
from datetime import datetime
import dateutil.parser
import sys
接下來是我為提供給模板的輸入 arguments 定義的 class :
class userOptions(PipelineOptions):
@classmethod
def _add_argparse_args(cls, parser):
parser.add_value_provider_argument(
'--subscription',
default='projects/MYPROJECT/subscrpiptions/subscription',
help='PubSub subscription to listen on')
parser.add_value_provider_argument(
'--bqtable',
default='dataset.table',
help='Big Query Table Name in the format project:dataset.table')
parser.add_value_provider_argument(
'--topic',
default='projects/MYPROJECT/subscrpiptions/subscription',
help='PubSub topic to write failed messages to')
管道本身定義為(注意我省略了 map 函數)
def run():
user_options = PipelineOptions().view_as(userOptions)
pipeline_options = PipelineOptions()
pipeline_options.view_as(SetupOptions).save_main_session = True
pipeline_options.view_as(StandardOptions).streaming = True
with beam.Pipeline(options=pipeline_options) as p:
records = (
p | 'Read from PubSub'
>> beam.io.ReadFromPubSub(
subscription=str(user_options.subscription),
id_label='Message_ID',
with_attributes=True)
| 'Format Message' >>
beam.Map(format_message_element)
| 'Transform null records to empty list' >>
beam.Map(transform_null_records)
| 'Transform Dates' >>
beam.Map(format_dates)
| 'Write to Big Query' >>
beam.io.gcp.bigquery.WriteToBigQuery(
table=user_options.bqtable,
create_disposition='CREATE_IF_NEEDED',
write_disposition='WRITE_APPEND',
insert_retry_strategy='RETRY_NEVER'
)
| 'Write Failures to Pub Sub' >>
beam.io.gcp.pubsub.WriteToPubSub(user_options.topic)
)
現在,當我嘗試使用 powershell 命令生成模板時:
python profiles-pipeline.py --project xxxx-xxxxxx-xxxx `
--subscription projects/xxxx-xxxxxx-xxxx/subscriptions/sub-xxxx-xxxxxx-xxxx-dataflow `
--bqtable xxxx-xxxxxx-xxxx:dataset.table `
--topic projects/xxxx-xxxxxx-xxxx/topics/top-xxxx-xxxxxx-xxxx-failures `
--runner DataflowRunner `
--temp_location gs://xxxx-xxxxxx-xxxx/temp/ `
--staging_location gs://xxxx-xxxxxx-xxxx/staging/ `
--template_location gs://xxxx-xxxxxx-xxxx/template
我收到此錯誤:
File "pipeline.py", line 193, in <module>
run()
File "pipeline.py", line 183, in run
beam.io.gcp.pubsub.WriteToPubSub(user_options.topic)
File "C:\github\pipeline-dataflow-jobs\dataflow\lib\site-packages\apache_beam\io\gcp\pubsub.py", line 292, in __init__
topic, id_label, with_attributes, timestamp_attribute)
File "C:\github\pipeline-dataflow-jobs\dataflow\lib\site-packages\apache_beam\io\gcp\pubsub.py", line 430, in __init__
self.project, self.topic_name = parse_topic(topic)
File "C:\github\pipeline-dataflow-jobs\dataflow\lib\site-packages\apache_beam\io\gcp\pubsub.py", line 325, in parse_topic
match = re.match(TOPIC_REGEXP, full_topic)
File "c:\program files\python37\lib\re.py", line 173, in match
return _compile(pattern, flags).match(string)
TypeError: expected string or bytes-like object
我在嘗試使用 beam.io.WriteToBigQuery() 之前遇到過此錯誤,但是一旦我更改為 beam.io.gcp.bigquery.WriteToBigQuery() 錯誤就解決了,因為它接受表名的 ValueProvider。 但是對於 pubsub,我找不到有效的寫入方法。
非常感激任何的幫助。
我已經部分解決了這個問題,因為我的管道錯誤地嘗試將失敗的插入發布到 Big Query,但是我仍然遇到無法將 pubsub 主題名稱作為輸入參數傳遞的問題。 但是,如果主題名稱是硬編碼的,它確實有效
#################################################################
# Import the libraries required by the pipeline #
#################################################################
from __future__ import absolute_import
import argparse
import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.pipeline_options import SetupOptions
from apache_beam.options.pipeline_options import StandardOptions
from apache_beam.options.value_provider import RuntimeValueProvider
import json
import time
from datetime import datetime
import dateutil.parser
import sys
import logging
#################################################################
# Create a class for the user defined settings provided at job
# creation
#################################################################
class userOptions(PipelineOptions):
@classmethod
def _add_argparse_args(cls, parser):
parser.add_value_provider_argument(
'--subscription',
default='projects/MYPROJECT/subscrpiptions/subscription',
help='PubSub subscription to listen on')
parser.add_value_provider_argument(
'--bqtable',
default='dataset.table',
help='Big Query Table Name in the format project:dataset.table')
parser.add_value_provider_argument(
'--topic',
default='projects/MYPROJECT/topics/subscription',
help='Pubsub topic to write failures to')
##############################################################################
# Format failure message
##############################################################################
def format_failed_message(data):
try:
message=json.dumps(data)
except:
print("customError in function format_failed_message occured.", sys.exc_info(), "Message contents: ", data)
return message
#################################################################
# create a function called run #
#################################################################
def run():
##############################################################
# Setup the pipeline options with both passed in arguments
# and streaming options
##############################################################
user_options = PipelineOptions().view_as(userOptions)
pipeline_options = PipelineOptions()
pipeline_options.view_as(SetupOptions).save_main_session = True
pipeline_options.view_as(StandardOptions).streaming = True
##############################################################
# Define the pipeline
##############################################################
with beam.Pipeline(options=pipeline_options) as p:
# First we create a PCollection which will contain the messages read from Pubsub
records = (
p | 'Read from PubSub'
>> beam.io.ReadFromPubSub(
subscription=str(user_options.subscription),
id_label='Message_ID',
with_attributes=True)
# Transform the message and its attributes to a dict.
| 'Format Message' >>
beam.Map(format_message_element)
# Transform the empty arrays defined as element:null to element:[].
| 'Transform null records to empty list' >>
beam.Map(transform_null_records)
# Transform the dateCreated and DateModified to a big query compatible timestamp format.
| 'Transform Dates' >>
beam.Map(format_dates)
# Attempt to write the rows to BQ
| 'Write to Big Query' >>
beam.io.gcp.bigquery.WriteToBigQuery(
table=user_options.bqtable,
create_disposition='CREATE_IF_NEEDED',
write_disposition='WRITE_APPEND',
insert_retry_strategy='RETRY_NEVER'
)
)
#For any rows that failed to write to BQ
failed_data = (records[beam.io.gcp.bigquery.BigQueryWriteFn.FAILED_ROWS]
#Format the dictionary to a string
| 'Format the dictionary as a string for publishing' >>
beam.Map(format_failed_message)
#Encode the string to utf8 bytes
| 'Encode the message' >>
beam.Map(lambda x: x.encode('utf-8')).with_output_types(bytes)
)
#Published the failed rows to pubsub
failed_data | beam.io.gcp.pubsub.WriteToPubSub(topic='projects/xxxx-xxxxx-xxxxxx/topics/top-xxxxx-failures')
#failed_data | beam.io.gcp.pubsub.WriteToPubSub(topic=user_options.topic)
# As this is a streaming pipeline it will run continuosly till either we
# stop the pipeline or it fails.
result = p.run()
result.wait_until_finish()
#At the main entry point call the run function
if __name__ == '__main__':
#logging.getLogger().setLevel(logging.INFO)
run()
| 'Encode bytestring' >> beam.Map(encode_byte_string) #我想這部分你已經實現了 | '寫給 pusub' >> beam.io.WriteToPubSub(output_topic) -- 它對我有用。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.