I am starting to run the enrichment process and when I get to using the storage loader I get the following error. here is the error I get:
./snowplow-storage-loader --config config/config.yml
Unexpected error: no implicit conversion of nil into String
org/jruby/RubyFileTest.java:95:in directory?' org/jruby/RubyFileTest.java:87:indirectory?'
uri:classloader:/storage-loader/lib/snowplow-storage-loader/config.rb:88:in get_config' uri:classloader:/storage-loader/bin/snowplow-storage-loader:31:in'
org/jruby/RubyKernel.java:973:in load' uri:classloader:/META-INF/main.rb:1:in'
org/jruby/RubyKernel.java:955: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 `’
aws:
# Credentials can be hardcoded or set in environment variables
access_key_id: XXXXX
secret_access_key: XXX
s3:
region: us-west-2
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://elasticbeanstalk-us-west-2-XXXXX/resources/environments/emrlog
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://elasticbeanstalk-us-west-2-XXXXX/resources/environments/logs/publish/e-cftpjpq6vh # e.g. s3://my-old-collector-bucket
processing: s3://XXXXX-etl/processing
archive: s3://XXXXX-archive/raw # e.g. s3://my-archive-bucket/raw
enriched:
good: s3://XXXXX-data/enriched/good # e.g. s3://my-out-bucket/enriched/good
bad: s3://XXXXX-data/enriched/bad # e.g. s3://my-out-bucket/enriched/bad
errors: # Leave blank unless :continue_on_unexpected_error: set to true below
archive: s3://XXXXX-data/enriched/archive # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
shredded:
good: s3://XXXXX-data/shredded/good # e.g. s3://my-out-bucket/shredded/good
bad: s3://XXXXX-data/shredded/bad # e.g. s3://my-out-bucket/shredded/bad
errors: # Leave blank unless :continue_on_unexpected_error: set to true below
archive: s3://XXXXX-data/shredded/archive # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
emr:
ami_version: 4.5.0
region: us-west-2 # 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-west-2b # Set this if not running in VPC. Leave blank otherwise
ec2_subnet_id: ADD HERE # Set this if running in VPC. Leave blank otherwise
ec2_key_name: XXXXX
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:
master_instance_type: m1.medium
core_instance_count: 2
core_instance_type: m1.medium
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: m1.medium
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
additional_info: # Optional JSON string for selecting additional features
collectors:
format: clj-tomcat # 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:
job_name: XXXXX ETL # Give your job a name
versions:
hadoop_enrich: 1.8.0 # Version of the Hadoop Enrichment process
hadoop_shred: 0.10.0 # Version of the Hadoop Shredding process
hadoop_elasticsearch: 0.1.0 # Version of the Hadoop to Elasticsearch copying 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:
download:
folder: downloads # Postgres-only config option. Where to store the downloaded files. Leave blank for Redshift
targets:
- name: "XXXXX"
type: postgres
host: 127.0.0.1 # Hostname of database server
database: XXXXXetl # Name of database
port: 5432 # Default Postgres port
ssl_mode: disable # One of disable (default), require, verify-ca or verify-full
table: atomic.events
username: XXXXX
password: XXXXX
maxerror: # Not required for Postgres
comprows: # Not required for Postgres
monitoring:
tags: {} # Name-value pairs describing this job
logging:
level: DEBUG # You can optionally switch to INFO for production