filetype.yaml

---
name: filetype
version: 1.0
id: https://datatractor.github.io/schema/main/datatractor_schema/filetype
prefixes:
    linkml: https://w3id.org/linkml/
    schema_org: http://schema.org/
    datatractor_schema: https://datatractor.github.io/schema/main/datatractor_schema/
default_prefix: datatractor_schema
emit_prefixes:
    - datatractor_schema
imports:
    - linkml:types
    - base
default_range: string
description: >-
    This file describes the `FileType` model from the Datatractor Schema.


classes:
    FileType:
        description: >-
            A specific encoding of data for storage purposes. A `FileType` is defined
            by a set of common characteristics and expectations, that can be assumed
            for all files of a given file type.
        close_mappings:
            - schema_org:fileFormat
            - schema_org:encodingFormat
        slots:
            - id
            - description
            - name
            - subject
        attributes:
            associated_vendors:
                slot_uri: schema_org:vendor
                multivalued: true
                description: >-
                    A list of software or instrument vendors that can be associated
                    with this particular `FileType`.
            associated_instruments:
                multivalued: true
                description: >-
                    A list of any instruments, or classes of instruments, that typically
                    create the data encoded into this `FileType`.
            associated_software:
                multivalued: true
                description: >-
                    A list of any known software (proprietary or otherwise) that produces
                    such `FileType`.
            associated_file_extensions:
                multivalued: true
                description: >-
                    A list of any known file extensions that files of this `FileType`
                    are found with. These may be used as a hint for `FileType` detection.
                    Should omit the leading `'.'`, e.g. 'json' or 'txt'.
                pattern: ^[A-z,0-9]*[A-z,0-9,.]+[A-z,0-9]$
            base_formats:
                multivalued: true
                range: FileType
                description: >-
                    A list of any particular underlying generic formats which this
                    `FileType` is based on, e.g., CSV, JSON, HDF5, XML.
            associated_standards:
                multivalued: true
                description: >-
                    A list of any particular well-defined file format standards relevant
                    to this `FileType`, e.g., CIF, NeXus, then it can be listed here.
            registered_extractors:
                multivalued: true
                pattern: ^[a-z]+[a-z,0-9,-]*[a-z,0-9]+$
                description: >-
                    A slot for an automatically-generated enumeration of `Extractor`
                    IDs that support this file type. This slot should be auto-populated
                    by a registry.