我正在尝试从以下内容合并2个JSON输入(本例来自一个文件,但稍后将来自一个Google Pub子输入):
orderID.json:
{"orderID":"test1","orderPacked":"Yes","orderSubmitted":"Yes","orderVerified":"Yes","stage":1}
combined.json:
{"barcode":"95590","name":"Ash","quantity":6,"orderID":"test1"}
{"barcode":"95591","name":"Beat","quantity":6,"orderID":"test1"}
{"barcode":"95592","name":"Cat","quantity":6,"orderID":"test1"}
{"barcode":"95593","name":"Dog","quantity":6,"orderID":"test2"}
{"barcode":"95594","name":"Scar","quantity":6,"orderID":"test2"}
类似这样的操作(使用orderID作为唯一主键):
output.json:
{"orderID":"test1","orderPacked":"Yes","orderSubmitted":"Yes","orderVerified":"Yes","stage":1,"barcode":"95590","name":"Ash","quantity":6}
{"orderID":"test1","orderPacked":"Yes","orderSubmitted":"Yes","orderVerified":"Yes","stage":1,"barcode":"95591","name":"Beat","quantity":6}
{"orderID":"test1","orderPacked":"Yes","orderSubmitted":"Yes","orderVerified":"Yes","stage":1,"barcode":"95592","name":"Cat","quantity":6}
我现在有这样的代码,是从join two json in Google Cloud Platform with dataflow改编的
from __future__ import absolute_import
import argparse
import apache_beam as beam
import json
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 google.api_core import datetime_helpers
from google.api_core.exceptions import InternalServerError
from google.api_core.exceptions import ServiceUnavailable
from google.api_core.exceptions import TooManyRequests
from google.cloud import bigquery
def run(argv=None):
"""Build and run the pipeline."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--topic',
type=str,
help='Pub/Sub topic to read from')
parser.add_argument(
'--topic2',
type=str,
help='Pub/Sub topic to match with'
)
parser.add_argument(
'--output',
help=('Output local filename'))
args, pipeline_args = parser.parse_known_args(argv)
options = PipelineOptions(pipeline_args)
options.view_as(SetupOptions).save_main_session = True
options.view_as(StandardOptions).streaming = True
p = beam.Pipeline(options=options)
orderID = (p | 'read from text1' >> beam.io.ReadFromText('orderID.json')
#'Read from orderID PubSub' >> beam.io.ReadFromPubSub(topic=args.topic2)
| 'Parse JSON to Dict' >> beam.Map(lambda e: json.loads(e))
| 'key_orderID' >> beam.Map(lambda orders: (orders['orderID'], orders))
)
orders_si = beam.pvalue.AsDict(orderID)
orderDetails = (p | 'read from text' >> beam.io.ReadFromText('combined.json')
| 'Parse JSON to Dict1' >> beam.Map(lambda e: json.loads(e)))
#'Read from PubSub' >> beam.io.ReadFromPubSub(topic=args.topic))
def join_orderID_orderDetails(order, order_dict):
return order.update(order_dict[order['orderID']])
joined_dicts = orderDetails | beam.Map(join_orderID_orderDetails, order_dict=orders_si)
joined_dicts | beam.io.WriteToText('beam.output')
p.run()
#result.wait_until_finish()
if __name__ == '__main__':
run()
但我现在的产出光束输出仅显示:
None
None
None
有人能告诉我我做错了什么吗?你知道吗
与报告的重复职位不同的问题是:
我怀疑这些是问题:
试试下面的,希望能对你有所帮助。你知道吗
在这里,我使用了一个数组的顺序和组合,而不是使用一个文件。你知道吗
相关问题 更多 >
编程相关推荐