truenas/library/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: 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: fscrawlerConfig
    label: ""
    group: FSCrawler Configuration
    schema:
      type: dict
      attrs:
        - variable: imageSelector
          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: "ocrImage"
            required: true
            enum:
              - value: "ocrImage"
                description: With OCR Support - Elasticsearch 7 and 8
              - value: "noocrImage"
                description: Without OCR Support - Elasticsearch 7 and 8
        - variable: jobName
          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: additionalEnvs
          label: Additional Environment Variables
          description: Configure additional environment variables for FSCrawler.
          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
                        required: true

  - variable: fscrawlerNetwork
    label: ""
    group: Network Configuration
    schema:
      type: dict
      attrs:
        - variable: enableRestApiService
          label: Enable Rest API Service
          description: |
            Enable Rest API Service for FSCrawler.</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: boolean
            default: false
        - variable: restPort
          label: Rest Port
          description: The port to use for the Rest API Service.
          schema:
            type: int
            show_if: [["enableRestApiService", "=", true]]
            default: 30084
            min: 9000
            max: 65535
            required: true
        - variable: hostNetwork
          label: Host Network
          description: |
            Bind to the host network. It's recommended to keep this disabled.
          schema:
            type: boolean
            default: false

  - variable: fscrawlerStorage
    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: "ixVolume"
                  enum:
                    - value: "hostPath"
                      description: Host Path (Path that already exists on the system)
                    - value: "ixVolume"
                      description: ixVolume (Dataset created automatically by the system)
              - variable: datasetName
                label: Dataset Name
                schema:
                  type: string
                  show_if: [["type", "=", "ixVolume"]]
                  required: true
                  hidden: true
                  immutable: true
                  default: "jobs"
                  $ref:
                    - "normalize/ixVolume"
              - variable: hostPath
                label: Host Path
                schema:
                  type: hostpath
                  show_if: [["type", "=", "hostPath"]]
                  immutable: true
                  required: true
        - variable: additionalStorages
          label: Additional Storage
          description: Additional storage for FSCrawler.
          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.
                      schema:
                        type: string
                        required: true
                        default: "ixVolume"
                        enum:
                          - value: "hostPath"
                            description: Host Path (Path that already exists on the system)
                          - value: "ixVolume"
                            description: ixVolume (Dataset created automatically by the system)
                    - variable: mountPath
                      label: Mount Path
                      description: The path inside the container to mount the storage.
                      schema:
                        type: path
                        required: true
                    - variable: hostPath
                      label: Host Path
                      description: The host path to use for storage.
                      schema:
                        type: hostpath
                        show_if: [["type", "=", "hostPath"]]
                        required: true
                    - variable: datasetName
                      label: Dataset Name
                      description: The name of the dataset to use for storage.
                      schema:
                        type: string
                        show_if: [["type", "=", "ixVolume"]]
                        required: true
                        immutable: true
                        default: "storage_entry"
                        $ref:
                          - "normalize/ixVolume"

  - variable: resources
    group: Resources Configuration
    label: ""
    schema:
      type: dict
      attrs:
        - variable: limits
          label: Limits
          schema:
            type: dict
            attrs:
              - variable: cpu
                label: CPU
                description: CPU limit for FSCrawler.
                schema:
                  type: string
                  max_length: 6
                  valid_chars: '^(0\.[1-9]|[1-9][0-9]*)(\.[0-9]|m?)$'
                  valid_chars_error: |
                    Valid CPU limit formats are</br>
                    - Plain Integer - eg. 1</br>
                    - Float - eg. 0.5</br>
                    - Milicpu - eg. 500m
                  default: "4000m"
                  required: true
              - variable: memory
                label: Memory
                description: Memory limit for FSCrawler.
                schema:
                  type: string
                  max_length: 12
                  valid_chars: '^[1-9][0-9]*([EPTGMK]i?|e[0-9]+)?$'
                  valid_chars_error: |
                    Valid Memory limit formats are</br>
                    - Suffixed with E/P/T/G/M/K - eg. 1G</br>
                    - Suffixed with Ei/Pi/Ti/Gi/Mi/Ki - eg. 1Gi</br>
                    - Plain Integer in bytes - eg. 1024</br>
                    - Exponent - eg. 134e6
                  default: "8Gi"
                  required: true