hub:
  db:
    type: sqlite-memory
  extraConfig:
    overrideServiceAccount: |
      import os, sys
      
      c.JupyterHub.authenticator_class = 'jupyterhub.auth.DummyAuthenticator'
      c.DummyAuthenticator.password = os.environ['LOGIN']
      c.Authenticator.admin_users = {"service-admin"}
      c.JupyterHub.service_tokens = {
          "secret-token": "service-admin",
      }
      # this script allows serviceAccountName to use dynamic naming based on {unescaped_username}"
      async def override_service_account_hook(kube_spawner):
        if kube_spawner.service_account is not None:
          kube_spawner.service_account = kube_spawner._expand_user_properties(kube_spawner.service_account)
          kube_spawner.env['USER_NAME'] = kube_spawner._expand_user_properties("{unescaped_username}")
      c.KubeSpawner.pre_spawn_hook = override_service_account_hook
      
      # setup timeout
      c.JupyterHub.cookie_max_age_days = 0.0105
      c.Authenticator.refresh_pre_spawn = True
      # c.JupyterHub.services = [
      #   {
      #       "name": "idle_culler",
      #       "admin": True,
      #       "command": [sys.executable, "-m", "jupyterhub_idle_culler", "--timeout=1800"],
      #   }
      # ]

  extraEnv:
    - name: LOGIN
      valueFrom:
        secretKeyRef:
          name: jupyter-external-secret
          key: password
  nodeSelector:
    lifecycle: Ec2Spot
  readinessProbe:
    initialDelaySeconds: 30
    periodSeconds: 10
          
proxy:
  secretToken: "*****"
  service:
    type: ClusterIP
  chp:
    nodeSelector:
      lifecycle: OnDemand    

singleuser:
  defaultUrl: "/lab"
  nodeSelector:
    lifecycle: OnDemand
  image:
    name: ghcr.io/tripl-ai/arc-jupyter
    tag: arc-jupyter_3.15.1_scala_2.12_hadoop_3.3.2_1.2.0_null_entrypoint
    pullPolicy: Always
  lifecycleHooks:
    postStart:
      exec:
        command:
          - "bash"
          - "-c"
          - >
            cp -r /opt/.jupyter $HOME/.jupyter;
            echo "git clone https://github.com/aws-samples/sql-based-etl-on-amazon-eks/spark-on-eks";
            git clone --depth 1 https://github.com/aws-samples/sql-based-etl-on-amazon-eks spark-on-eks;
            cd spark-on-eks; git filter-branch --prune-empty --subdirectory-filter spark-on-eks HEAD;

  serviceAccountName: "{username}"
  cpu:
    guarantee: 0.25
    limit: 0.5
  memory:
    guarantee: 4G
    limit: 4G
  extraEnv:
    CONF_ALLOW_EXPORT: "true"
    # JAVA_OPTS: -Xmx4G
    ETL_CONF_DATALAKE_LOC: {{codeBucket}}
    ETL_CONF_AWS_REGION: {{region}}
  storage:
    type: none
  # storage:
  #   type: dynamic
  #   capacity: 10G
  #   homeMountPath: '/home/{username}/data'
  #   # mount to EBS  
  #   dynamic:
  #     storageClass: gp2 
  profileList:
  - default: True
    display_name: "Small (default): Arc-Jupyter Development Environment"
    description: "4GB Memory & 1vCPUs"
    kubespawner_override:
      cpu_guarantee: 0.5
      cpu_limit: 1
      mem_guarantee: 4G
      mem_limit: 10G
  - display_name: "Big Arc-Jupyter Development Environment"
    description: "15GB Memory & 2vCPUs"
    kubespawner_override:
      cpu_guarantee: 0.5
      cpu_limit: 2
      mem_guarantee: 10G
      mem_limit: 15G

prePuller:
  hook:
    enabled: false 

# autoscacling setting
scheduling:
  userScheduler:
    enabled: true
    replicas: 1
cull:
  timeout: 1800

# debug:
#   enabled: true