pyobo 0.12.5__tar.gz → 0.12.7__tar.gz

{pyobo-0.12.5 → pyobo-0.12.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyobo
-Version: 0.12.5
+Version: 0.12.7
 Summary: A python package for handling and generating OBO
 Keywords: snekpack,cookiecutter,ontologies,biomedical ontologies,life sciences,natural sciences,bioinformatics,cheminformatics,Open Biomedical Ontologies,OBO
 Author: Charles Tapley Hoyt
@@ -30,7 +30,6 @@ Requires-Dist: tqdm
 Requires-Dist: pyyaml
 Requires-Dist: pandas
 Requires-Dist: requests
-Requires-Dist: protmapper
 Requires-Dist: more-itertools
 Requires-Dist: more-click>=0.0.2
 Requires-Dist: humanize
@@ -43,7 +42,6 @@ Requires-Dist: bioontologies>=0.7.2
 Requires-Dist: ssslm>=0.0.13
 Requires-Dist: zenodo-client>=0.3.6
 Requires-Dist: class-resolver>=0.6.0
-Requires-Dist: psycopg2-binary
 Requires-Dist: pydantic>=2.0
 Requires-Dist: curies>=0.10.17
 Requires-Dist: curies-processing>=0.1.2
@@ -57,8 +55,11 @@ Requires-Dist: nih-reporter-downloader>=0.0.1
 Requires-Dist: typing-extensions
 Requires-Dist: rdflib
 Requires-Dist: obographs>=0.0.8
+Requires-Dist: psycopg2-binary ; extra == 'drugcentral'
 Requires-Dist: ssslm[gilda] ; extra == 'gilda'
 Requires-Dist: ssslm[gilda-slim] ; extra == 'gilda-slim'
+Requires-Dist: protmapper ; extra == 'pid'
+Requires-Dist: pyobo[drugcentral,pid] ; extra == 'sources'
 Maintainer: Charles Tapley Hoyt
 Maintainer-email: Charles Tapley Hoyt <cthoyt@gmail.com>
 Requires-Python: >=3.10
@@ -67,8 +68,11 @@ Project-URL: Documentation, https://pyobo.readthedocs.io
 Project-URL: Funding, https://github.com/sponsors/cthoyt
 Project-URL: Homepage, https://github.com/biopragmatics/pyobo
 Project-URL: Repository, https://github.com/biopragmatics/pyobo.git
+Provides-Extra: drugcentral
 Provides-Extra: gilda
 Provides-Extra: gilda-slim
+Provides-Extra: pid
+Provides-Extra: sources
 Description-Content-Type: text/markdown
 
 <!--

{pyobo-0.12.5 → pyobo-0.12.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "pyobo"
-version = "0.12.5"
+version = "0.12.7"
 description = "A python package for handling and generating OBO"
 readme = "README.md"
 authors = [
@@ -63,7 +63,6 @@ dependencies = [
     "pyyaml",
     "pandas",
     "requests",
-    "protmapper",
     "more_itertools",
     "more_click>=0.0.2",
     "humanize",
@@ -76,7 +75,6 @@ dependencies = [
     "ssslm>=0.0.13",
     "zenodo-client>=0.3.6",
     "class_resolver>=0.6.0",
-    "psycopg2-binary",
     "pydantic>=2.0",
     "curies>=0.10.17",
     "curies-processing>=0.1.2",
@@ -158,6 +156,15 @@ gilda = [
 gilda-slim = [
     "ssslm[gilda-slim]",
 ]
+sources = [
+    "pyobo[drugcentral,pid]",
+]
+drugcentral =[
+    "psycopg2-binary",
+]
+pid = [
+    "protmapper",
+]
 
 # See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#urls
 # and also https://packaging.python.org/en/latest/specifications/well-known-project-urls/
@@ -289,7 +296,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.12.5"
+current_version = "0.12.7"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?(?:\\+(?P<build>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?"
 serialize = [
     "{major}.{minor}.{patch}-{release}+{build}",

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/__init__.py

@@ -65,6 +65,7 @@ from .plugins import (
     run_nomenclature_plugin,
 )
 from .struct import (
+    Annotation,
     Obo,
     Reference,
     StanzaType,
@@ -80,6 +81,7 @@ from .utils.path import ensure_path
 from .version import get_version
 
 __all__ = [
+    "Annotation",
     "Obo",
     "Reference",
     "StanzaType",

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/cli/database.py

@@ -6,6 +6,7 @@ from collections.abc import Iterable
 from pathlib import Path
 
 import bioregistry
+import bioversions
 import click
 from more_click import verbose_option
 from tqdm.contrib.logging import logging_redirect_tqdm
@@ -97,12 +98,17 @@ def _update_database_kwargs(kwargs: DatabaseKwargs) -> DatabaseKwargs:
 
 
 @database_annotate
+@click.option("--eager-versions", is_flag=True)
 @click.pass_context
-def build(ctx: click.Context, **kwargs: Unpack[DatabaseKwargs]) -> None:
+def build(ctx: click.Context, eager_versions: bool, **kwargs: Unpack[DatabaseKwargs]) -> None:
     """Build all databases."""
     # if no_strict and zenodo:
     #    click.secho("Must be strict before uploading", fg="red")
     #    sys.exit(1)
+
+    if eager_versions:
+        bioversions.get_rows(use_tqdm=True)
+
     with logging_redirect_tqdm():
         click.secho("Collecting metadata and building", fg="cyan", bold=True)
         # note that this is the only one that needs a force=force

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/identifier_utils/api.py

@@ -287,7 +287,9 @@ def wrap_norm_prefix(f):
                 raise ValueError(f"Invalid prefix: {prefix.prefix}")
             prefix = ReferenceTuple(norm_prefix, prefix.identifier)
         else:
-            raise TypeError
+            raise TypeError(
+                f"prefix should be given as a string or reference object. Got {type(prefix)} {prefix}"
+            )
         return f(prefix, *args, **kwargs)
 
     return _wrapped

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/sources/drugcentral.py

@@ -6,7 +6,6 @@ from collections.abc import Iterable
 from contextlib import closing
 
 import bioregistry
-import psycopg2
 from pydantic import ValidationError
 from tqdm.auto import tqdm
 
@@ -42,6 +41,8 @@ class DrugCentralGetter(Obo):
 
 def iter_terms() -> Iterable[Term]:
     """Iterate over DrugCentral terms."""
+    import psycopg2
+
     with closing(psycopg2.connect(**PARAMS)) as conn:
         with closing(conn.cursor()) as cur:
             cur.execute(

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/sources/iana_media_type.py

@@ -5,14 +5,18 @@
 
 from collections.abc import Iterable
 
-from pyobo import Obo, Reference, Term, default_reference
-from pyobo.struct.typedef import term_replaced_by
+import requests
+
+from pyobo import Obo, Reference, Term, TypeDef, default_reference
+from pyobo.struct import Annotation
+from pyobo.struct.typedef import has_source, term_replaced_by
 from pyobo.utils.path import ensure_df
 
 __all__ = ["IANAGetter"]
 
 PREFIX = "iana.mediatype"
-ROOT = Term.from_triple(prefix="dcterms", identifier="MediaType", name="media type")
+ROOT_MEDIA_TYPE = Term.from_triple(prefix="dcterms", identifier="MediaType", name="media type")
+ROOT_FILE_FORMAT = Term.from_triple(prefix="dcterms", identifier="FileFormat", name="file format")
 
 #: The top-level types listed on https://www.iana.org/assignments/media-types/media-types.xhtml
 MEDIA_TYPE_GROUPS = [
@@ -31,13 +35,37 @@ MEDIA_TYPE_GROUPS = [
 GROUP_TO_CSV = {
     media_type_group: (
         f"https://www.iana.org/assignments/media-types/{media_type_group}.csv",
-        Term(reference=default_reference(PREFIX, media_type_group, media_type_group)).append_parent(
-            ROOT
-        ),
+        Term(
+            reference=Reference(prefix=PREFIX, identifier=media_type_group, name=media_type_group)
+        ).append_parent(ROOT_MEDIA_TYPE),
     )
     for media_type_group in MEDIA_TYPE_GROUPS
 }
 
+MIMETYPE_IO_URL = (
+    "https://github.com/patrickmccallum/mimetype-io/raw/refs/heads/master/src/mimeData.json"
+)
+
+
+def _get_mimetypes():
+    records = requests.get(MIMETYPE_IO_URL, timeout=5).json()
+    rv = {}
+    for record in records:
+        name = record.pop("name")
+        rv[name] = record
+    return rv
+
+
+PREDICATE = TypeDef(
+    reference=default_reference(
+        prefix=PREFIX, identifier="extension", name="appears with file extension"
+    ),
+    domain=ROOT_MEDIA_TYPE.reference,
+    range=ROOT_FILE_FORMAT.reference,
+    definition="Connects a media type with a file format that has been observed to encode it",
+    is_metadata_tag=True,
+)
+
 
 class IANAGetter(Obo):
     """An ontology representation of IANA media types (i.e. MIME types)."""
@@ -45,9 +73,10 @@ class IANAGetter(Obo):
     ontology = bioregistry_key = PREFIX
     name = "IANA Media Types"
     dynamic_version = True
-    root_terms = [t.reference for _, (_, t) in sorted(GROUP_TO_CSV.items())]
+    root_terms = [ROOT_MEDIA_TYPE.reference, ROOT_FILE_FORMAT.reference]
     typedefs = [
         term_replaced_by,
+        PREDICATE,
     ]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -55,26 +84,53 @@ class IANAGetter(Obo):
         return get_terms()
 
 
-def get_terms() -> list[Term]:
+def get_terms() -> Iterable[Term]:
     """Get IANA Media Type terms."""
+    mimetypes_data = _get_mimetypes()
+
+    filetype_to_term = {}
+    for record in mimetypes_data.values():
+        for filetype_str in record.get("fileTypes", []):
+            filetype_id = filetype_str.removeprefix(".")
+            filetype_term = Term(
+                reference=default_reference(PREFIX, identifier=filetype_id, name=filetype_str),
+                type="Instance",
+            )
+            filetype_term.append_parent(ROOT_FILE_FORMAT)
+            filetype_term.annotate_string(has_source, MIMETYPE_IO_URL)
+            filetype_to_term[filetype_str] = filetype_term
+            yield filetype_term
+
     terms: dict[str, Term] = {}
     forwards: dict[Term, str] = {}
     for key, (url, parent) in GROUP_TO_CSV.items():
         df = ensure_df(PREFIX, url=url, sep=",")
         terms[key] = parent
         for name, identifier, references in df.values:
+            mimetypes_record = mimetypes_data.get(identifier, {})
+
             if "OBSOLE" in name or "DEPRECATED" in name:
                 is_obsolete = True
             else:
                 is_obsolete = None
+
             term = Term(
                 reference=Reference(prefix=PREFIX, identifier=identifier, name=name),
                 is_obsolete=is_obsolete,
+                # TODO how to add definition source?
+                definition=mimetypes_record.get("description"),
             ).append_parent(parent)
             for reference in _process_references(references):
                 term.append_see_also_uri(reference)
             terms[identifier.casefold()] = term
 
+            for filetype_str in mimetypes_record.get("fileTypes", []):
+                term.annotate_object(
+                    PREDICATE,
+                    filetype_to_term[filetype_str],
+                    annotations=[Annotation.uri(has_source, MIMETYPE_IO_URL)],
+                )
+
             if "in favor of" in name:
                 _, _, new = name.partition("in favor of ")
                 forwards[term] = new.casefold().strip().rstrip(")").strip()
@@ -84,7 +140,7 @@ def get_terms() -> list[Term]:
             new = "application/vnd.afpc.afplinedata"
         old.append_replaced_by(terms[new].reference)
 
-    return list(terms.values())
+    yield from terms.values()
 
 
 def _process_references(cell: str) -> list[str]:

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/sources/spdx.py

@@ -55,11 +55,15 @@ def _get_term(record: dict[str, Any]) -> Term | None:
     except ValidationError:
         tqdm.write(f"invalid: {record['licenseId']}")
         return None
-    term = Term(
-        reference=reference,
-        is_obsolete=True if record.get("isDeprecatedLicenseId") else None,
-        # type="Instance",
-    ).append_parent(ROOT)
+    term = (
+        Term(
+            reference=reference,
+            is_obsolete=True if record.get("isDeprecatedLicenseId") else None,
+            # type="Instance",
+        )
+        .append_parent(ROOT)
+        .append_synonym(record["licenseId"])
+    )
     if record.get("isOsiApproved"):
         term.annotate_boolean(IS_OSI, True)
     if record.get("isFsfLibre"):
@@ -82,4 +86,4 @@ class SPDXLicenseGetter(Obo):
 
 
 if __name__ == "__main__":
-    SPDXLicenseGetter.cli(["--obo", "--owl", "--rewrite"])
+    SPDXLicenseGetter.cli()

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/struct/functional/obo_to_functional.py

@@ -39,9 +39,15 @@ def get_ofn_from_obo(
     prefix = obo_ontology.ontology
     base = f"{_BASE}/{prefix}"
     if iri is None:
-        iri = f"{base}/{prefix}.ofn"
-    if version_iri is None and obo_ontology.data_version:
-        version_iri = f"{base}/{obo_ontology.data_version}/{prefix}.ofn"
+        if obo_ontology.ontology_iri:
+            iri = obo_ontology.ontology_iri
+        else:
+            iri = f"{base}/{prefix}.ofn"
+    if version_iri is None:
+        if obo_ontology.ontology_version_iri:
+            version_iri = obo_ontology.ontology_version_iri
+        elif obo_ontology.data_version:
+            version_iri = f"{base}/{obo_ontology.data_version}/{prefix}.ofn"
     ofn_ontology = Ontology(
         iri=iri,
         version_iri=version_iri,

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/struct/obograph/export.py

@@ -70,8 +70,12 @@ def to_parsed_obograph(obo: Obo) -> og.StandardizedGraphDocument:
 
 
 def _to_parsed_graph(obo: Obo) -> og.StandardizedGraph:
+    if obo.ontology_iri:
+        ontology_iri = obo.ontology_iri
+    else:
+        ontology_iri = f"http://purl.obolibrary.org/obo/{obo.ontology}.owl"
     return og.StandardizedGraph(
-        id=f"http://purl.obolibrary.org/obo/{obo.ontology}.owl",
+        id=ontology_iri,
         meta=_get_meta(obo),
         nodes=_get_nodes(obo),
         edges=_get_edges(obo),
@@ -167,7 +171,9 @@ def _get_meta(obo: Obo) -> og.StandardizedMeta | None:
             )
         )
 
-    if obo.data_version:
+    if obo.ontology_version_iri:
+        version_iri = obo.ontology_version_iri
+    elif obo.data_version:
         version_iri = (
             f"http://purl.obolibrary.org/obo/{obo.ontology}/{obo.data_version}/{obo.ontology}.owl"
         )

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/struct/struct.py

@@ -8,6 +8,7 @@ import json
 import logging
 import os
 import sys
+import tempfile
 import warnings
 from collections import ChainMap, defaultdict
 from collections.abc import Callable, Collection, Iterable, Iterator, Mapping, Sequence
@@ -593,6 +594,10 @@ class Obo:
 
     imports: ClassVar[list[str] | None] = None
 
+    ontology_iri: ClassVar[str | None] = None
+
+    ontology_version_iri: ClassVar[str | None] = None
+
     def __post_init__(self):
         """Run post-init checks."""
         if self.ontology is None:
@@ -1021,6 +1026,15 @@ class Obo:
         ofn = get_ofn_from_obo(self)
         ofn.write_funowl(path)
 
+    def write_owl(self, path: str | Path) -> None:
+        """Write OWL, by first outputting OFN then converting with ROBOT."""
+        from bioontologies import robot
+
+        with tempfile.TemporaryDirectory() as directory:
+            ofn_path = Path(directory).joinpath("tmp.ofn")
+            self.write_ofn(ofn_path)
+            robot.convert(ofn_path, path)
+
     def write_rdf(self, path: str | Path) -> None:
         """Write as Turtle RDF."""
         from .functional.obo_to_functional import get_ofn_from_obo
@@ -2309,6 +2323,8 @@ def build_ontology(
     mailing_list: str | None = None,
     logo: str | None = None,
     repository: str | None = None,
+    ontology_iri: str | None = None,
+    ontology_version_iri: str | None = None,
 ) -> Obo:
     """Build an ontology from parts."""
     if name is None:
@@ -2368,6 +2384,8 @@ def build_ontology(
         _subsetdefs=subsetdefs,
         _property_values=properties,
         _imports=imports,
+        _ontology_iri=ontology_iri,
+        _ontology_version_iri=ontology_version_iri,
         terms=terms,
     )
 
@@ -2385,6 +2403,8 @@ def make_ad_hoc_ontology(
     _subsetdefs: list[tuple[Reference, str]] | None = None,
     _property_values: list[Annotation] | None = None,
     _imports: list[str] | None = None,
+    _ontology_iri: str | None = None,
+    _ontology_version_iri: str | None = None,
     *,
     terms: list[Term] | None = None,
 ) -> Obo:
@@ -2403,6 +2423,8 @@ def make_ad_hoc_ontology(
         subsetdefs = _subsetdefs
         property_values = _property_values
         imports = _imports
+        ontology_iri = _ontology_iri
+        ontology_version_iri = _ontology_version_iri
 
         def __post_init__(self):
             self.date = _date

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/struct/struct_utils.py

@@ -59,18 +59,32 @@ class Annotation(NamedTuple):
     value: Reference | OBOLiteral
 
     @classmethod
-    def float(cls, predicate: Reference, value: float) -> Self:
+    def float(cls, predicate: Reference | TypeDef, value: float) -> Self:
         """Return a literal property for a float."""
+        from .struct import TypeDef
+
+        if isinstance(predicate, TypeDef):
+            predicate = predicate.reference
         return cls(predicate, OBOLiteral.float(value))
 
     @classmethod
-    def uri(cls, predicate: Reference, uri: str) -> Self:
+    def uri(cls, predicate: Reference | TypeDef, uri: str) -> Self:
         """Return a literal property for a URI."""
+        from .struct import TypeDef
+
+        if isinstance(predicate, TypeDef):
+            predicate = predicate.reference
         return cls(predicate, OBOLiteral.uri(uri))
 
     @classmethod
-    def string(cls, predicate: Reference, value: str, *, language: str | None = None) -> Self:
+    def string(
+        cls, predicate: Reference | TypeDef, value: str, *, language: str | None = None
+    ) -> Self:
         """Return a literal property for a float."""
+        from .struct import TypeDef
+
+        if isinstance(predicate, TypeDef):
+            predicate = predicate.reference
         return cls(predicate, OBOLiteral.string(value, language=language))
 
     @staticmethod

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/struct/typedef.py

@@ -135,6 +135,7 @@ rdf_type = TypeDef(reference=v.rdf_type)
 subproperty_of = TypeDef(reference=v.subproperty_of)
 see_also = TypeDef(reference=v.see_also, is_metadata_tag=True)
 comment = TypeDef(reference=v.comment, is_metadata_tag=True)
+label = TypeDef(reference=v.label, is_metadata_tag=True)
 has_member = TypeDef(
     reference=Reference(prefix=RO_PREFIX, identifier="0002351", name="has member"),
 )

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/utils/misc.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import logging
-from collections.abc import Callable
+from collections.abc import Callable, Iterable
 from datetime import datetime
 
 import bioversions.utils
@@ -46,6 +46,8 @@ VERSION_PREFIXES = [
     "http://w3id.org/nfdi4ing/metadata4ing/",  # like http://w3id.org/nfdi4ing/metadata4ing/1.3.1
     "http://www.semanticweb.com/OntoRxn/",  # like http://www.semanticweb.com/OntoRxn/0.2.5
     "https://w3id.org/lehrplan/ontology/",  # like in https://w3id.org/lehrplan/ontology/1.0.0-4
+    "http://www.ebi.ac.uk/swo/version/",  # http://www.ebi.ac.uk/swo/version/6.0
+    "https://w3id.org/emi/version/",
 ]
 VERSION_PREFIX_SPLITS = [
     "http://www.ebi.ac.uk/efo/releases/v",
@@ -193,18 +195,23 @@ def _prioritize_version(
     return None
 
 
-def _get_version_from_artifact(prefix: str) -> str | None:
+def _get_getter_urls(prefix: str) -> Iterable[tuple[OntologyFormat, str]]:
     # assume that all possible files that can be downloaded
     # are in sync and have the same version
-    for ontology_format, func in ONTOLOGY_GETTERS:
-        url = func(prefix)
+    for ontology_format, get_url_func in ONTOLOGY_GETTERS:
+        url = get_url_func(prefix)
         if url is None:
             continue
+        yield ontology_format, url
+
+
+def _get_version_from_artifact(prefix: str) -> str | None:
+    for ontology_format, url in _get_getter_urls(prefix):
         # Try to peak into the file to get the version without fully downloading
-        version_func = VERSION_GETTERS.get(ontology_format)
-        if version_func is None:
+        get_version_func = VERSION_GETTERS.get(ontology_format)
+        if get_version_func is None:
             continue
-        version = version_func(prefix, url)
+        version = get_version_func(prefix, url)
         if version:
             return cleanup_version(version, prefix=prefix)
     return None

{pyobo-0.12.5 → pyobo-0.12.7}/src/pyobo/version.py

@@ -12,7 +12,7 @@ __all__ = [
     "get_version",
 ]
 
-VERSION = "0.12.5"
+VERSION = "0.12.7"
 
 
 def get_git_hash() -> str: