we are using EmreEtlRunner in the bellow version
snowplow_emr_r88_angkor_wat.zip
While running this bellow Command
./snowplow-storage-loader --config 4-storage/config/emretlrunner.yml --resolver 4-storage/config/resolver.json --targets 4-storage/config/targets/ --skip analyze
Bellow is the error i am getting
Unexpected error: JSON instance is not self-describing (schema property is absent):
{"$schema":"http://iglucentral.com/schemas/com.snowplowanalytics.self-desc/schema/jsonschema/1-0-0#","description":"Snowplow PostgreSQL storage configuration","self":{"vendor":"com.snowplowanalytics.snowplow.storage","name":"postgresql_config","format":"jsonschema","version":"1-0-0"},"type":"object","properties":{"name":{"type":"PostgreSQL enriched events storage"},"host":{"type":"localhost"},"database":{"type":"snowplow"},"port":{"type":"integer","minimum":1,"maximum":65535},"sslMode":{"type":"DISABLE","enum":["DISABLE","REQUIRE","VERIFY_CA","VERIFY_FULL"]},"schema":{"type":"atomic"},"username":{"type":"power_user"},"password":{"type":"hadoop"},"purpose":{"type":"ENRICHED_EVENTS","enum":["ENRICHED_EVENTS"]}},"additionalProperties":false,"required":["name","host","database","port","sslMode","schema","username","password","purpose"]}
uri:classloader:/gems/iglu-ruby-client-0.1.0/lib/iglu-client/resolver.rb:92:in `get_schema_key'
uri:classloader:/gems/iglu-ruby-client-0.1.0/lib/iglu-client/resolver.rb:66:in `parse'
uri:classloader:/storage-loader/lib/snowplow-storage-loader/config.rb:55: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>'
Bellow is the Config.yml file
aws:
# Credentials can be hardcoded or set in environment variables
access_key_id: xxxxxxxxxxx
secret_access_key: xxxxxxxxxxxxxxxxxx
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://ilogregion1 # e.g. s3://my-old-collector-bucket
processing: s3://ilogregion1/raw/processing
archive: s3://ilogregion1/raw/archive # e.g. s3://my-archive-bucket/raw
enriched:
good: s3://ilogregion1/enriched/good # e.g. s3://my-out-bucket/enriched/good
bad: s3://ilogregion1/enriched/bad # e.g. s3://my-out-bucket/enriched/bad
errors: s3://ilogregion1/enriched/errors # Leave blank unless :continue_on_unexpected_error: set to true below
archive: s3://ilogregion1/enriched/archive # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
shredded:
good: s3://ilogregion1/shredded/good # e.g. s3://my-out-bucket/shredded/good
bad: s3://ilogregion1/shredded/bad # e.g. s3://my-out-bucket/shredded/bad
errors: s3://ilogregion1/shredded/errors # Leave blank unless :continue_on_unexpected_error: set to true below
archive: s3://ilogregion1/shredded/archive # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
emr:
ami_version: 5.5.0
region: us-east-1a # 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: snowplow
bootstrap: [] # Set this to specify custom boostrap actions. Leave empty otherwise
software:
hbase: "0.92.0" # 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 ETL # Give your job a name
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
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
Bellow is my resolver file
{
"$schema": "http://iglucentral.com/schemas/com.snowplowanalytics.self-desc/schema/jsonschema/1-0-0#",
"description": "Snowplow PostgreSQL storage configuration",
"self": {
"vendor": "com.snowplowanalytics.snowplow.storage",
"name": "postgresql_config",
"format": "jsonschema",
"version": "1-0-0"
},
"type": "object",
"properties": {
"name": {
"type": "PostgreSQL enriched events storage"
},
"host": {
"type": "localhost"
},
"database": {
"type": "snowplow"
},
"port": {
"type": "integer",
"minimum": 1,
"maximum": 65535
},
"sslMode": {
"type": "DISABLE",
"enum": ["DISABLE", "REQUIRE", "VERIFY_CA", "VERIFY_FULL"]
},
"schema": {
"type": "atomic"
},
"username": {
"type": "power_user"
},
"password": {
"type": "hadoop"
},
"purpose": {
"type": "ENRICHED_EVENTS",
"enum": ["ENRICHED_EVENTS"]
}
},
"additionalProperties": false,
"required": ["name", "host", "database", "port", "sslMode", "schema", "username", "password", "purpose"]
}
please help me is their any change i have do in my congfig file or command
How to run Storange loader with snowplow_emr_r91_stonehenge_rc9 version?
