bioimageio.spec.dataset.v0_3

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