EmrEtlRunner: added hadoop_elasticsearch to config.yml.sample (closes #…

…2124)

3-enrich/emr-etl-runner/config/config.yml.sample

@@ -50,8 +50,9 @@ collectors:
 enrich:
   job_name: Snowplow ETL # Give your job a name
   versions:
-    hadoop_enrich: 1.2.0 # Version of the Hadoop Enrichment process
-    hadoop_shred: 0.5.0 # Version of the Hadoop Shredding process
+    hadoop_enrich: 1.3.0 # Version of the Hadoop Enrichment process
+    hadoop_shred: 0.6.0 # 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:
@@ -80,6 +81,19 @@ storage:
       password: ADD HERE
       maxerror: # Not required for Postgres
       comprows: # Not required for Postgres
+    - name: "My Elasticsearch database"
+      type: elasticsearch
+      host: ADD HERE # The Elasticsearch endpoint
+      database: ADD HERE # Name of index
+      port: 9200 # Default Elasticsearch port - change to 80 if using Amazon Elasticsearch Service
+      sources: # Leave blank to write the bad rows created in this run to Elasticsearch, or explicitly provide an array of bad row buckets like ["s3://my-enriched-bucket/bad/run=2015-10-06-15-25-53"]
+      ssl_mode: # Not required for Elasticsearch
+      table: ADD HERE # Name of type
+      username: # Not required for Elasticsearch
+      password: # Not required for Elasticsearch
+      es_nodes_wan_only: false # Set to true if using Amazon Elasticsearch Service
+      maxerror: # Not required for Elasticsearch
+      comprows: # Not required for Elasticsearch
 monitoring:
   tags: {} # Name-value pairs describing this job
   logging: