bioimageio.spec.dataset.v0_3

  1from typing import TYPE_CHECKING, Any, ClassVar, Dict, Literal, Optional, cast
  2
  3from pydantic import model_validator
  4
  5from .._internal.common_nodes import InvalidDescr
  6from .._internal.io import FileDescr as FileDescr
  7from .._internal.io_basics import Sha256 as Sha256
  8from .._internal.types import FAIR
  9from .._internal.url import HttpUrl as HttpUrl
 10from ..generic.v0_3 import VALID_COVER_IMAGE_EXTENSIONS as VALID_COVER_IMAGE_EXTENSIONS
 11from ..generic.v0_3 import Author as Author
 12from ..generic.v0_3 import BadgeDescr as BadgeDescr
 13from ..generic.v0_3 import BioimageioConfig as BioimageioConfig
 14from ..generic.v0_3 import CiteEntry as CiteEntry
 15from ..generic.v0_3 import Config as Config
 16from ..generic.v0_3 import DeprecatedLicenseId as DeprecatedLicenseId
 17from ..generic.v0_3 import Doi as Doi
 18from ..generic.v0_3 import (
 19    GenericDescrBase,
 20    LinkedResourceBase,
 21    _author_conv,  # pyright: ignore[reportPrivateUsage]
 22    _maintainer_conv,  # pyright: ignore[reportPrivateUsage]
 23)
 24from ..generic.v0_3 import LicenseId as LicenseId
 25from ..generic.v0_3 import LinkedResource as LinkedResource
 26from ..generic.v0_3 import Maintainer as Maintainer
 27from ..generic.v0_3 import OrcidId as OrcidId
 28from ..generic.v0_3 import RelativeFilePath as RelativeFilePath
 29from ..generic.v0_3 import ResourceId as ResourceId
 30from ..generic.v0_3 import Uploader as Uploader
 31from ..generic.v0_3 import Version as Version
 32from .v0_2 import DatasetDescr as DatasetDescr02
 33
 34
 35class DatasetId(ResourceId):
 36    pass
 37
 38
 39class DatasetDescr(GenericDescrBase):
 40    """A bioimage.io dataset resource description file (dataset RDF) describes a dataset relevant to bioimage
 41    processing.
 42    """
 43
 44    implemented_type: ClassVar[Literal["dataset"]] = "dataset"
 45    if TYPE_CHECKING:
 46        type: Literal["dataset"] = "dataset"
 47    else:
 48        type: Literal["dataset"]
 49
 50    id: Optional[DatasetId] = None
 51    """bioimage.io-wide unique resource identifier
 52    assigned by bioimage.io; version **un**specific."""
 53
 54    parent: Optional[DatasetId] = None
 55    """The description from which this one is derived"""
 56
 57    source: FAIR[Optional[HttpUrl]] = None
 58    """"URL to the source of the dataset."""
 59
 60    @model_validator(mode="before")
 61    @classmethod
 62    def _convert(cls, data: Dict[str, Any], /) -> Dict[str, Any]:
 63        if (
 64            data.get("type") == "dataset"
 65            and isinstance(fv := data.get("format_version"), str)
 66            and fv.startswith("0.2.")
 67        ):
 68            old = DatasetDescr02.load(data)
 69            if isinstance(old, InvalidDescr):
 70                return data
 71
 72            return cast(
 73                Dict[str, Any],
 74                (cls if TYPE_CHECKING else dict)(
 75                    attachments=(
 76                        []
 77                        if old.attachments is None
 78                        else [FileDescr(source=f) for f in old.attachments.files]
 79                    ),
 80                    authors=[
 81                        _author_conv.convert_as_dict(a) for a in old.authors
 82                    ],  # pyright: ignore[reportArgumentType]
 83                    badges=old.badges,
 84                    cite=[
 85                        {"text": c.text, "doi": c.doi, "url": c.url} for c in old.cite
 86                    ],  # pyright: ignore[reportArgumentType]
 87                    config=old.config,  # pyright: ignore[reportArgumentType]
 88                    covers=old.covers,
 89                    description=old.description,
 90                    documentation=old.documentation,
 91                    format_version="0.3.0",
 92                    git_repo=old.git_repo,  # pyright: ignore[reportArgumentType]
 93                    icon=old.icon,
 94                    id=None if old.id is None else DatasetId(old.id),
 95                    license=old.license,  # type: ignore
 96                    links=old.links,
 97                    maintainers=[
 98                        _maintainer_conv.convert_as_dict(m) for m in old.maintainers
 99                    ],  # pyright: ignore[reportArgumentType]
100                    name=old.name,
101                    source=old.source,
102                    tags=old.tags,
103                    type=old.type,
104                    uploader=old.uploader,
105                    version=old.version,
106                    **(old.model_extra or {}),
107                ),
108            )
109
110        return data
111
112
113class LinkedDataset(LinkedResourceBase):
114    """Reference to a bioimage.io dataset."""
115
116    id: DatasetId
117    """A valid dataset `id` from the bioimage.io collection."""