gistfile1.txt

name: ${HOSTNAME}

# The cluster should be named with the name of the AD domain
cluster:
  name: dev-0.13.0-SNAPSHOT
# Throttling disabled for testing 
#  routing:
#    allocation:
      # Defaults to # of CPUs + 1... not a sane default with 24 core systems
#      concurrent_recoveries: 6

gateway:
  type: fs
  fs:
    location: /esgateway
  # Wait for 2 nodes to start cluster. If after 5 minutes, we don't have 2, cluster will start with 1
  recover_after_nodes: 1
  recover_after_time: 5m
  expected_nodes: 1

discovery:
  zen:
    ping:
      unicast:
        hosts: ['dm-adsearchd102.dev.local:9300', 'dm-adsearchd103.dev.local:9300']

# All of our snapshotting occurs via esindexer
index:
  gateway: 
    snapshot_interval : -1

  # We have so many shards that we need to keep translogs relatively small for recovery
  # This does result in more frequent flushes. The default is 5000 and this is per index
  translog:
    flush_threshold: 1000

  analysis :
    analyzer : 
      # This analyzer mimics verity behavior
      verity_tokenizer :
        type: pattern
        lowercase: true
        pattern: '(?:(?!\w).)+'
        stopwords: _none_ 
        flags: DOTALL
      # Analyzer is used for sorting multi-term fields
      lowercase_keyword :
        type : custom
        filter : [lowercase]
        tokenizer : keyword
      # IDOL TextMatch, PipeDelimited
      pipe_tokenizer :
        type: pattern
        lowercase: true
        pattern: '\|'
        stopwords: _none_ 
        flags: DOTALL
      # IDOL FullText
      fulltext_tokenizer :
        type : custom
        filter : [standard, lowercase, stop, porterStem]
        tokenizer : standard

path:
  logs: /opt/wsod/var/log/elasticsearch/
  data: /opt/wsod/var/data/elasticsearch/
  work: /opt/wsod/var/work/elasticsearch/