RDB Loader is raising the following error:
Data discovery error with following issues:
JSONPath file [com.snowplowanalytics.snowplow/parent_event_1.json] was not found
I cannot find such a JSON file in GitHub repositories.
Config file:
aws:
# Credentials can be hardcoded or set in environment variables
access_key_id: <%= ENV['AWS_ACCESS_KEY'] %>
secret_access_key: <%= ENV['AWS_SECRET_KEY'] %>
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: s3://company-snowplow-schema-dev/jsonpaths/ # If you have defined your own JSON Schemas, add the s3:// path to your own JSON Path files in your own bucket here
log: s3n://company-shared-production/redshift/var/log/snowplow_tracker/logs/
encrypted: false
raw:
in:
- s3://company-snowplow-raw-production/
processing: s3://company-shared-production/redshift/var/log/snowplow_tracker/raw/processing/
archive: s3://company-shared-production/redshift/var/log/snowplow_tracker/raw/archive/
enriched:
good: s3://company-shared-production/redshift/var/log/snowplow_tracker/enriched/good/ # e.g. s3://my-out-bucket/enriched/good
archive: s3://company-shared-production/redshift/var/log/snowplow_tracker/enriched/archive/ # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
bad: s3://company-shared-production/redshift/var/log/snowplow_tracker/enriched/bad/ # S3 Loader's output folder with enriched data. If present raw buckets will be discarded
errors: s3://company-shared-production/redshift/var/log/snowplow_tracker/enriched/errors/
# stream: s3://company-shared-production/var/log/snowplow_tracker/enriched/stream/
shredded:
good: s3://company-shared-production/redshift/var/log/snowplow_tracker/shredded/good/ # e.g. s3://my-out-bucket/shredded/good
bad: s3://company-shared-production/redshift/var/log/snowplow_tracker/shredded/rdb_loader/ # e.g. s3://my-out-bucket/shredded/bad
errors: s3://company-shared-production/redshift/var/log/snowplow_tracker/shredded/errors/ # Leave blank unless :continue_on_unexpected_error: set to true below
archive: s3://company-shared-production/redshift/var/log/snowplow_tracker/shredded/archive/ # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
consolidate_shredded_output: false # Whether to combine files when copying from hdfs to s3
emr:
ami_version: 5.9.0
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: # Set this if not running in VPC. Leave blank otherwise
ec2_subnet_id: subnet-690b1543 # Set this if running in VPC. Leave blank otherwise
ec2_key_name: amplify-keypair
security_configuration: # Specify your EMR security configuration if needed. Leave blank otherwise
bootstrap: [] # Set this to specify custom boostrap actions. Leave empty otherwise
software:
hbase: #"1.3.1" #"1.4.13" # Optional. To launch on cluster, provide version, "0.92.0", keep quotes. Leave empty otherwise.
lingual: #"1.1" # Optional. To launch on cluster, provide version, "1.1", keep quotes. Leave empty otherwise.
# Adjust your Hadoop cluster below
jobflow:
job_name: Snowplow to Redshift ETL # Give your job a name
master_instance_type: m1.medium
core_instance_count: 12
core_instance_type: r3.2xlarge
core_instance_bid: #0.015 # In USD. Adjust bid, or leave blank for on-demand core instances
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: m4.large
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-defaults:
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: 1.19.0 # 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: GZIP # Stream mode supports only GZIP
storage:
versions:
rdb_loader: 0.14.0
rdb_shredder: 0.14.0 # Version of the Spark Shredding process
hadoop_elasticsearch: 0.1.0 # Version of the Hadoop to Elasticsearch copying process
monitoring:
tags:
app: Snowplow ETL # Name-value pairs describing this job
logging:
level: DEBUG # You can optionally switch to INFO for production
# snowplow:
# method: get
# app_id: redshift_loader # e.g. snowplow
# collector: # e.g. d3rkrsqld9gmqf.cloudfront.net
# protocol: http
# port: 80
resolver:
{
"schema": "iglu:com.snowplowanalytics.iglu/resolver-config/jsonschema/1-0-0",
"data": {
"cacheSize": 500,
"repositories": [
{
"name": "Iglu Central",
"priority": 0,
"vendorPrefixes": [ "com.snowplowanalytics" ],
"connection": {
"http": {
"uri": "http://iglucentral.com"
}
}
},
{
"name": "company Central",
"priority": 5,
"vendorPrefixes": [ "com.company" ],
"connection": {
"http": {
"uri": "http://company-snowplow-schema-dev.s3.amazonaws.com"
}
}
}
]
}
}
Anyone can help with this issue please?