Step Functions から Glue Spark ジョブに引数を渡す

Glue PySpark でダブルクオートなしタブ区切りで CSV に出力する - ablog で Step Functions からパラメータを渡すパティーン。

• Step Functions のステートマシン

{
  "Comment": "This is your state machine",
  "StartAt": "Glue StartJobRun",
  "States": {
    "Glue StartJobRun": {
      "Type": "Task",
      "Resource": "arn:aws:states:::glue:startJobRun.sync",
      "Parameters": {
        "JobName": "no_quote_test",
        "Arguments": {
          "--QUOTE_CHAR": "-1",
          "--SEPARATOR": "\t"
        }
      },
      "End": true
    }
  }
}

• Glue Spark ジョブで引数を受け取る

## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME', 'QUOTE_CHAR', 'SEPARATOR']) # ココ

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)

strQuoteChar = args['QUOTE_CHAR'] # ココ
strSeparator = args['SEPARATOR']# ココ

（中略）

datasink2 = glueContext.write_dynamic_frame.from_options(
	frame = applymapping1, 
	connection_type = "s3", 
	connection_options = {"path": "s3://dl-sfdc-dm/test/no_quote_test"}, 
		format = "csv", 
		format_options={
			"quoteChar": strQuoteChar, 
			"separator": strSeparator
		}, 
		transformation_ctx = "datasink2"
	)

参考

• getResolvedOptions を使用して、パラメータにアクセスする - AWS接着語

コード全量

import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job

## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME', 'QUOTE_CHAR', 'SEPARATOR'])

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)

strQuoteChar = args['QUOTE_CHAR'] # ココ
strSeparator = args['SEPARATOR'] # ココ

#strQuoteChar = -1
#strSeparator = "\t"


## @type: DataSource
## @args: [database = "default", table_name = "no_quote_test", transformation_ctx = "datasource0"]
## @return: datasource0
## @inputs: []
datasource0 = glueContext.create_dynamic_frame.from_catalog(database = "default", table_name = "no_quote_test", transformation_ctx = "datasource0")
## @type: ApplyMapping
## @args: [mapping = [("col0", "string", "col0", "string"), ("col1", "string", "col1", "string"), ("col2", "string", "col2", "string"), ("col3", "string", "col3", "string")], transformation_ctx = "applymapping1"]
## @return: applymapping1
## @inputs: [frame = datasource0]
applymapping1 = ApplyMapping.apply(frame = datasource0, mappings = [("col0", "string", "col0", "string"), ("col1", "string", "col1", "string"), ("col2", "string", "col2", "string"), ("col3", "string", "col3", "string")], transformation_ctx = "applymapping1")
## @type: DataSink
## @args: [connection_type = "s3", connection_options = {"path": "s3://dl-sfdc-dm/test/no_quote_test"}, format = "csv", transformation_ctx = "datasink2"]
## @return: datasink2
## @inputs: [frame = applymapping1]
datasink2 = glueContext.write_dynamic_frame.from_options(frame = applymapping1, connection_type = "s3", connection_options = {"path": "s3://dl-sfdc-dm/test/no_quote_test"}, format = "csv", format_options={"quoteChar": strQuoteChar, "separator": strSeparator }, transformation_ctx = "datasink2")
job.commit()