apps/ix-dev/community/fscrawler/questions.yaml

groups:
  - name: FSCrawler Configuration
    description: Configure FSCrawler
  - name: Network Configuration
    description: Configure Network for FSCrawler
  - name: Storage Configuration
    description: Configure Storage for FSCrawler
  - name: Labels Configuration
    description: Configure Labels for FSCrawler
  - name: Resources Configuration
    description: Configure Resources for FSCrawler

questions:
  - variable: TZ
    group: FSCrawler Configuration
    label: Timezone
    schema:
      type: string
      default: Etc/UTC
      required: true
      $ref:
        - definitions/timezone

  - variable: fscrawler
    label: ""
    group: FSCrawler Configuration
    schema:
      type: dict
      attrs:
        - variable: image_selector
          label: Image
          description: |
            The image to use for FSCrawler.</br>
            Images with OCR support are a lot larger than images without OCR support.</br>
            Approximate image sizes:</br>
            - With OCR Support: 1.2GB</br>
            - Without OCR Support: 0.5GB
          schema:
            type: string
            default: "image"
            required: true
            enum:
              - value: "image"
                description: With OCR Support - Elasticsearch 7 and 8
              - value: "no_ocr_image"
                description: Without OCR Support - Elasticsearch 7 and 8
        - variable: job_name
          label: Job Name
          description: |
            The name of the FSCrawler job to run. </br>
            A _settings.yaml file in the directory named after the job name will have to be manually created.
          schema:
            type: string
            default: ""
            required: true
        - variable: loop
          label: Loop
          description: |
            The number of times to run the job.</br>
            https://fscrawler.readthedocs.io/en/latest/admin/cli-options.html#loop </br>
            -1 means run forever. </br>
            0 means never run. </br>
          schema:
            type: int
            default: -1
            required: true
            min: -1
        - variable: restart
          label: Restart
          description: |
            Restart the job from the beginning.</br>
            https://fscrawler.readthedocs.io/en/latest/admin/cli-options.html#restart
          schema:
            type: boolean
            default: false
        - variable: additional_envs
          label: Additional Environment Variables
          schema:
            type: list
            default: []
            items:
              - variable: env
                label: Environment Variable
                schema:
                  type: dict
                  attrs:
                    - variable: name
                      label: Name
                      schema:
                        type: string
                        required: true
                    - variable: value
                      label: Value
                      schema:
                        type: string

  - variable: network
    label: ""
    group: Network Configuration
    schema:
      type: dict
      attrs:
        - variable: rest_port
          label: REST Port
          description: |
            Enable Rest API Service for FSCrawler by setting bind mode to something other than None.</br>
            https://fscrawler.readthedocs.io/en/latest/admin/fs/rest.html</br>
            Additional configuration is needed in the job file. Check the Notes card
            after installation for more information.
          schema:
            type: dict
            attrs:
              - variable: bind_mode
                label: Port Bind Mode
                description: |
                  The port bind mode.</br>
                  - Publish: The port will be published on the host for external access.</br>
                  - Expose: The port will be exposed for inter-container communication.</br>
                  - None: The port will not be exposed or published.</br>
                  Note: If the Dockerfile defines an EXPOSE directive,
                  the port will still be exposed for inter-container communication regardless of this setting.
                schema:
                  type: string
                  default: ""
                  enum:
                    - value: "published"
                      description: Publish port on the host for external access
                    - value: "exposed"
                      description: Expose port for inter-container communication
                    - value: ""
                      description: None
              - variable: port_number
                label: Port Number
                schema:
                  type: int
                  default: 30084
                  min: 1
                  max: 65535
                  required: true
              - variable: host_ips
                label: Host IPs
                description: IPs on the host to bind this port
                schema:
                  type: list
                  show_if: [["bind_mode", "=", "published"]]
                  default: []
                  items:
                    - variable: host_ip
                      label: Host IP
                      schema:
                        type: string
                        required: true
                        $ref:
                          - definitions/node_bind_ip
        - variable: host_network
          label: Host Network
          description: |
            Bind to the host network. It's recommended to keep this disabled.
          schema:
            type: boolean
            default: false
  - variable: storage
    label: ""
    group: Storage Configuration
    schema:
      type: dict
      attrs:
        - variable: jobs
          label: FSCrawler Jobs Storage
          description: The path to store FSCrawler Jobs.
          schema:
            type: dict
            attrs:
              - variable: type
                label: Type
                description: |
                  ixVolume: Is dataset created automatically by the system.</br>
                  Host Path: Is a path that already exists on the system.
                schema:
                  type: string
                  required: true
                  default: "ix_volume"
                  enum:
                    - value: "host_path"
                      description: Host Path (Path that already exists on the system)
                    - value: "ix_volume"
                      description: ixVolume (Dataset created automatically by the system)
              - variable: ix_volume_config
                label: ixVolume Configuration
                description: The configuration for the ixVolume dataset.
                schema:
                  type: dict
                  show_if: [["type", "=", "ix_volume"]]
                  $ref:
                    - "normalize/ix_volume"
                  attrs:
                    - variable: acl_enable
                      label: Enable ACL
                      description: Enable ACL for the storage.
                      schema:
                        type: boolean
                        default: false
                    - variable: dataset_name
                      label: Dataset Name
                      description: The name of the dataset to use for storage.
                      schema:
                        type: string
                        required: true
                        hidden: true
                        default: "jobs"
                    - variable: acl_entries
                      label: ACL Configuration
                      schema:
                        type: dict
                        show_if: [["acl_enable", "=", true]]
                        attrs: []
              - variable: host_path_config
                label: Host Path Configuration
                schema:
                  type: dict
                  show_if: [["type", "=", "host_path"]]
                  attrs:
                    - variable: acl_enable
                      label: Enable ACL
                      description: Enable ACL for the storage.
                      schema:
                        type: boolean
                        default: false
                    - variable: acl
                      label: ACL Configuration
                      schema:
                        type: dict
                        show_if: [["acl_enable", "=", true]]
                        attrs: []
                        $ref:
                          - "normalize/acl"
                    - variable: path
                      label: Host Path
                      description: The host path to use for storage.
                      schema:
                        type: hostpath
                        show_if: [["acl_enable", "=", false]]
                        required: true
        - variable: additional_storage
          label: Additional Storage
          schema:
            type: list
            default: []
            items:
              - variable: storageEntry
                label: Storage Entry
                schema:
                  type: dict
                  attrs:
                    - variable: type
                      label: Type
                      description: |
                        ixVolume: Is dataset created automatically by the system.</br>
                        Host Path: Is a path that already exists on the system.</br>
                        SMB Share: Is a SMB share that is mounted to as a volume.
                      schema:
                        type: string
                        required: true
                        default: "ix_volume"
                        enum:
                          - value: "host_path"
                            description: Host Path (Path that already exists on the system)
                          - value: "ix_volume"
                            description: ixVolume (Dataset created automatically by the system)
                          - value: "cifs"
                            description: SMB/CIFS Share (Mounts a volume to a SMB share)
                    - variable: read_only
                      label: Read Only
                      description: Mount the volume as read only.
                      schema:
                        type: boolean
                        default: false
                    - variable: mount_path
                      label: Mount Path
                      description: The path inside the container to mount the storage.
                      schema:
                        type: path
                        required: true
                    - variable: host_path_config
                      label: Host Path Configuration
                      schema:
                        type: dict
                        show_if: [["type", "=", "host_path"]]
                        attrs:
                          - variable: acl_enable
                            label: Enable ACL
                            description: Enable ACL for the storage.
                            schema:
                              type: boolean
                              default: false
                          - variable: acl
                            label: ACL Configuration
                            schema:
                              type: dict
                              show_if: [["acl_enable", "=", true]]
                              attrs: []
                              $ref:
                                - "normalize/acl"
                          - variable: path
                            label: Host Path
                            description: The host path to use for storage.
                            schema:
                              type: hostpath
                              show_if: [["acl_enable", "=", false]]
                              required: true
                    - variable: ix_volume_config
                      label: ixVolume Configuration
                      description: The configuration for the ixVolume dataset.
                      schema:
                        type: dict
                        show_if: [["type", "=", "ix_volume"]]
                        $ref:
                          - "normalize/ix_volume"
                        attrs:
                          - variable: acl_enable
                            label: Enable ACL
                            description: Enable ACL for the storage.
                            schema:
                              type: boolean
                              default: false
                          - variable: dataset_name
                            label: Dataset Name
                            description: The name of the dataset to use for storage.
                            schema:
                              type: string
                              required: true
                              default: "storage_entry"
                          - variable: acl_entries
                            label: ACL Configuration
                            schema:
                              type: dict
                              show_if: [["acl_enable", "=", true]]
                              attrs: []
                    - variable: cifs_config
                      label: SMB Configuration
                      description: The configuration for the SMB dataset.
                      schema:
                        type: dict
                        show_if: [["type", "=", "cifs"]]
                        attrs:
                          - variable: server
                            label: Server
                            description: The server to mount the SMB share.
                            schema:
                              type: string
                              required: true
                          - variable: path
                            label: Path
                            description: The path to mount the SMB share.
                            schema:
                              type: string
                              required: true
                          - variable: username
                            label: Username
                            description: The username to use for the SMB share.
                            schema:
                              type: string
                              required: true
                          - variable: password
                            label: Password
                            description: The password to use for the SMB share.
                            schema:
                              type: string
                              required: true
                              private: true
                          - variable: domain
                            label: Domain
                            description: The domain to use for the SMB share.
                            schema:
                              type: string
  - variable: labels
    label: ""
    group: Labels Configuration
    schema:
      type: list
      default: []
      items:
        - variable: label
          label: Label
          schema:
            type: dict
            attrs:
              - variable: key
                label: Key
                schema:
                  type: string
                  required: true
              - variable: value
                label: Value
                schema:
                  type: string
                  required: true
              - variable: containers
                label: Containers
                description: Containers where the label should be applied
                schema:
                  type: list
                  items:
                    - variable: container
                      label: Container
                      schema:
                        type: string
                        required: true
                        enum:
                          - value: fscrawler
                            description: fscrawler
  - variable: resources
    label: ""
    group: Resources Configuration
    schema:
      type: dict
      attrs:
        - variable: limits
          label: Limits
          schema:
            type: dict
            attrs:
              - variable: cpus
                label: CPUs
                description: CPUs limit for FSCrawler.
                schema:
                  type: int
                  default: 2
                  required: true
              - variable: memory
                label: Memory (in MB)
                description: Memory limit for FSCrawler.
                schema:
                  type: int
                  default: 4096
                  required: true