Unexpected error: undefined method `[]' for nil:NilClass


#1

Hi All,
i am using EmrEtlRunner version 92
Upto EmrEtlRunner (shredding) configuration is successfully completed.

I have been stucked in storage loader.
While trying to run postgreSQl using below command.

./snowplow-emr-etl-runner run --config snowplow/4-storage/config/emretlrunner.yml --resolver snowplow/4-storage/config/resolver.json --targets snowplow/4-storage/config/targets/ --skip analyze

I am getting below error.

      Unexpected error: undefined method `[]' for nil:NilClass
uri:classloader:/storage-loader/lib/snowplow-storage-loader/config.rb:75:in `get_config'
uri:classloader:/storage-loader/bin/snowplow-storage-loader:31:in `<main>'
org/jruby/RubyKernel.java:977:in `load'
uri:classloader:/META-INF/main.rb:1:in `<main>'
org/jruby/RubyKernel.java:959:in `require'
uri:classloader:/META-INF/main.rb:1:in `(root)'
uri:classloader:/META-INF/jruby.home/lib/ruby/stdlib/rubygems/core_ext/kernel_require.rb:1:in `<main>'
https://discour

My emretlrunner.yml file is below.

aws:
  # Credentials can be hardcoded or set in environment variables
  access_key_id: xxxxxxxxxxxxx
  secret_access_key: xxxxxxxxx
  #keypair: Snowplowkeypair
  #key-pair-file: /home/ubuntu/snowplow/4-storage/config/Snowplowkeypair.pem
  region: us-east-1
  s3:
	region: us-east-1
	buckets:
	  assets: s3://snowplow-hosted-assets # DO NOT CHANGE unless you are hosting the jarfiles etc yourself in your own bucket
	  jsonpath_assets: # If you have defined your own JSON Schemas, add the s3:// path to your own JSON Path files in your own bucket here
	  log: s3://unilogregion1/logs
	  raw:
		in:                  # This is a YAML array of one or more in buckets - you MUST use hyphens before each entry in the array, as below
		  - s3://unilogregion1/      # e.g. s3://my-old-collector-bucket
		processing: s3://unilogregion1/raw/processing
		archive: s3://unilogregion1/raw/archive   # e.g. s3://my-archive-bucket/raw
	  enriched:
		good: s3://unilogregion1/enriched/good        # e.g. s3://my-out-bucket/enriched/good
		bad: s3://unilogregion1/enriched/bad       # e.g. s3://my-out-bucket/enriched/bad
		errors: s3://unilogregion1/enriched/errors     # Leave blank unless :continue_on_unexpected_error: set to true below
		archive: s3://unilogregion1/enriched/archive    # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
	  shredded:
		good: s3://unilogregion1/shredded/good        # e.g. s3://my-out-bucket/shredded/good
		bad: s3://unilogregion1/shredded/bad        # e.g. s3://my-out-bucket/shredded/bad
		errors: s3://unilogregion1/shredded/errors     # Leave blank unless :continue_on_unexpected_error: set to true below
		archive: s3://unilogregion1/shredded/archive     # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
  emr:
	ami_version: 5.5.0
	region: us-east-1       # Always set this
	jobflow_role: EMR_EC2_DefaultRole # Created using $ aws emr create-default-roles
	service_role: EMR_DefaultRole     # Created using $ aws emr create-default-roles
	placement: us-east-1a      # Set this if not running in VPC. Leave blank otherwise
	ec2_subnet_id:  # Set this if running in VPC. Leave blank otherwise
	ec2_key_name: Snowplowkeypair
	bootstrap: []           # Set this to specify custom boostrap actions. Leave empty otherwise
	software:
	  hbase:              # Optional. To launch on cluster, provide version, "0.92.0", keep quotes. Leave empty otherwise.
	  lingual:              # Optional. To launch on cluster, provide version, "1.1", keep quotes. Leave empty otherwise.
	# Adjust your Hadoop cluster below
	jobflow:
	  job_name: Snowplow ETL # Give your job a name
	  master_instance_type: m2.4xlarge
	  core_instance_count: 2
	  core_instance_type: m2.4xlarge
	  core_instance_ebs:    # Optional. Attach an EBS volume to each core instance.
		volume_size: 100    # Gigabytes
		volume_type: "gp2"
		volume_iops: 400    # Optional. Will only be used if volume_type is "io1"
		ebs_optimized: false # Optional. Will default to true
	  task_instance_count: 0 # Increase to use spot instances
	  task_instance_type: m2.4xlarge
	  task_instance_bid: 0.015 # In USD. Adjust bid, or leave blank for non-spot-priced (i.e. on-demand) task instances
	bootstrap_failure_tries: 3 # Number of times to attempt the job in the event of bootstrap failures
	configuration:
	  yarn-site:
		yarn.resourcemanager.am.max-attempts: "1"
	  spark:
		maximizeResourceAllocation: "true"
	additional_info:        # Optional JSON string for selecting additional features
collectors:
  format: thrift # For example: 'clj-tomcat' for the Clojure Collector, 'thrift' for Thrift records, 'tsv/com.amazon.aws.cloudfront/wd_access_log' for Cloudfront access logs or 'ndjson/urbanairship.connect/v1' for UrbanAirship Connect events
enrich:
  versions:
	spark_enrich: 1.9.0 # Version of the Spark Enrichment process
  continue_on_unexpected_error: false # Set to 'true' (and set :out_errors: above) if you don't want any exceptions thrown from ETL
  output_compression: NONE # Compression only supported with Redshift, set to NONE if you have Postgres targets. Allowed formats: NONE, GZIP
storage:
  versions:
	rdb_loader: 0.12.0
	rdb_shredder: 0.12.0        # Version of the Spark Shredding process
	hadoop_elasticsearch: 0.1.0 # Version of the Hadoop to Elasticsearch copying process
monitoring:
  tags: {} # Name-value pairs describing this job
  logging:
	level: DEBUG # You can optionally switch to INFO for production
  #snowplow:
	#method: get
	#app_id: unilog # e.g. snowplow
	#collector: 172.31.38.39:8082 # e.g. d3rkrsqld9gmqf.cloudfront.net

iglu_resolver.json file is below.

  	{
  "schema": "iglu:com.snowplowanalytics.iglu/resolver-config/jsonschema/1-0-1",
  "data": {
	"cacheSize": 500,
	"repositories": [
	  {
		"name": "Iglu Central",
		"priority": 0,
		"vendorPrefixes": [ "com.snowplowanalytics" ],
		"connection": {
		  "http": {
			"uri": "http://iglucentral.com"
		  }
		}
	  }
	]
  }
}

Please help me to solve this issue.