bioversions 0.5.320__py3-none-any.whl → 0.7.1__py3-none-any.whl

bioversions/sources/hgnc.py

@@ -1,10 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """A getter for HGNC."""
 
 import logging
 
-from bioversions.utils import Getter, VersionType, get_soup
+import requests
+
+from bioversions.utils import Getter, VersionType
 
 __all__ = [
     "HGNCGetter",
@@ -12,8 +12,9 @@ __all__ = [
 
 logger = logging.getLogger(__name__)
 
-PATH = "https://ftp.ebi.ac.uk/pub/databases/genenames/new/archive/monthly/json/"
-PREFIX = "hgnc_complete_set_"
+PATH = "https://storage.googleapis.com/public-download-files/hgnc/archive/archive/monthly/json/"
+URL = "https://storage.googleapis.com/storage/v1/b/public-download-files/o?prefix=hgnc/archive/archive/monthly"
+PREFIX = "hgnc/archive/archive/monthly/json/hgnc_complete_set_"
 SUFFIX = ".json"
 
 
@@ -22,20 +23,18 @@ class HGNCGetter(Getter):
 
     bioregistry_id = "hgnc"
     name = "HGNC"
-    homepage_fmt = (
-        "http://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/"
-        "archive/monthly/json/hgnc_complete_set_{version}.json"
-    )
+    homepage_fmt = PATH + "hgnc_complete_set_{version}.json"
 
     version_type = VersionType.date
 
     def get(self) -> str:
-        """Get the latest HGNC version number."""
-        soup = get_soup(PATH)
+        """Get the latest monthly HGNC version number."""
+        res = requests.get(URL, timeout=5)
+        items = res.json()["items"]
         return max(
-            anchor.attrs["href"][len(PREFIX) : -len(SUFFIX)]
-            for anchor in soup.find_all("a")
-            if anchor.attrs["href"].startswith(PREFIX)
+            item["name"].removeprefix(PREFIX).removesuffix(SUFFIX)
+            for item in items
+            if (name := item["name"]).startswith(PREFIX) and name.endswith(SUFFIX)
         )
 
 

bioversions/sources/homologene.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for HomoloGene."""
 
 import requests

bioversions/sources/icd10.py

@@ -0,0 +1,30 @@
+"""A getter for ICD10."""
+
+import requests
+
+from bioversions.utils import Getter, VersionType
+
+__all__ = [
+    "ICD10Getter",
+]
+
+URL = "https://icd.who.int/browse10/"
+
+
+class ICD10Getter(Getter):
+    """A getter for ICD10."""
+
+    bioregistry_id = "icd10"
+    name = "International Classification of Diseases, 10th Revision"
+    version_type = VersionType.date
+    date_version_fmt = "%Y"
+
+    def get(self) -> str:
+        """Get the latest ICD10 version number."""
+        response = requests.get(URL, allow_redirects=True, timeout=15)
+        final_url = response.url
+        return final_url[len("https://icd.who.int/browse10/") :].split("/")[0]
+
+
+if __name__ == "__main__":
+    ICD10Getter.print()

bioversions/sources/icd11.py

@@ -0,0 +1,30 @@
+"""A getter for ICD11."""
+
+import requests
+
+from bioversions.utils import Getter, VersionType
+
+__all__ = [
+    "ICD11Getter",
+]
+
+URL = "https://icd.who.int/browse/latest-release/mms/en"
+
+
+class ICD11Getter(Getter):
+    """A getter for ICD11."""
+
+    bioregistry_id = "icd11"
+    name = "International Classification of Diseases, 11th Revision"
+    version_type = VersionType.date
+    date_version_fmt = "%Y-%m"
+
+    def get(self) -> str:
+        """Get the latest ICD11 version number."""
+        response = requests.get(URL, allow_redirects=True, timeout=15)
+        final_url = response.url
+        return final_url[len("https://icd.who.int/browse/") :].split("/")[0]
+
+
+if __name__ == "__main__":
+    ICD11Getter.print()

bioversions/sources/icf.py

@@ -0,0 +1,30 @@
+"""A getter for ICF."""
+
+import requests
+
+from bioversions.utils import Getter, VersionType
+
+__all__ = [
+    "ICFGetter",
+]
+
+URL = "https://icd.who.int/browse/latest-release/icf/en"
+
+
+class ICFGetter(Getter):
+    """A getter for ICF."""
+
+    bioregistry_id = "icf"
+    name = "International Classification of Functioning, Disability and Health"
+    version_type = VersionType.date
+    date_version_fmt = "%Y-%m"
+
+    def get(self) -> str:
+        """Get the latest ICF version number."""
+        response = requests.get(URL, allow_redirects=True, timeout=15)
+        final_url = response.url
+        return final_url[len("https://icd.who.int/browse/") :].split("/")[0]
+
+
+if __name__ == "__main__":
+    ICFGetter.print()

bioversions/sources/intact.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for IntAct."""
 
 from bioversions.utils import Getter, VersionType, _get_ftp_date_version

bioversions/sources/interpro.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for InterPro."""
 
 import re
@@ -35,7 +33,7 @@ class InterProGetter(Getter):
                 if line.startswith("Release") and not line.startswith("Release Notes"):
                     line = line[len("Release ") :]
                     version, rest = line.split(",", 1)
-                    return dict(version=version, date=_process_line(rest))
+                    return {"version": version, "date": _process_line(rest)}
         raise ValueError
 
 

bioversions/sources/itis.py

@@ -1,16 +1,16 @@
-# -*- coding: utf-8 -*-
-
 """A getter for ITIS."""
 
-from typing import Mapping
+import datetime
+
+import requests
 
-from bioversions.utils import Getter, VersionType, get_soup
+from bioversions.utils import Getter, VersionType
 
 __all__ = [
     "ITISGetter",
 ]
 
-URL = "https://itis.gov/downloads/index.html"
+URL = "https://www.itis.gov/DisplayPresentDate"
 
 
 class ITISGetter(Getter):
@@ -18,19 +18,12 @@ class ITISGetter(Getter):
 
     bioregistry_id = "itis"
     name = "ITIS"
-    date_fmt = "%d-%B-%Y"
     version_type = VersionType.date
 
-    def get(self) -> Mapping[str, str]:
+    def get(self) -> datetime.datetime:
         """Get the latest ITIS version number."""
-        soup = get_soup(URL)
-        cells = soup.find_all("td")
-        for cell in cells:
-            if "Database download files are currently from the " not in cell.text:
-                continue
-            bolds = list(cell.find_all("b"))
-            return bolds[1].text
-        raise ValueError
+        res = requests.get(URL, timeout=3).text
+        return datetime.datetime.strptime(res, "%d-%b-%Y")
 
 
 if __name__ == "__main__":

bioversions/sources/kegg.py

@@ -1,8 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """A getter for KEGG."""
 
-from typing import Mapping
+from collections.abc import Mapping
+from typing import ClassVar
+
+import bioregistry
 
 from bioversions.utils import Getter, VersionType, get_soup
 
@@ -16,19 +17,19 @@ URL = "https://www.kegg.jp/kegg/docs/relnote.html"
 class KEGGGetter(Getter):
     """A getter for KEGG."""
 
-    bioregistry_id = "kegg.pathway"
     name = "KEGG"
     date_fmt = "%B %d, %Y"
     version_type = VersionType.semver_minor
+    collection: ClassVar[list[str]] = ["kegg", *bioregistry.get_has_parts("kegg")]
 
     def get(self) -> Mapping[str, str]:
         """Get the latest KEGG version number."""
         soup = get_soup(URL)
         header = soup.find("h4")
         sibling = header.next_sibling.strip()
-        version, date = [part.strip() for part in sibling.split(",", 1)]
+        version, date = (part.strip() for part in sibling.split(",", 1))
         version = version[len("Release ") :]
-        return dict(version=version, date=date)
+        return {"version": version, "date": date}
 
 
 if __name__ == "__main__":

bioversions/sources/mesh.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for MeSH."""
 
 import ftplib
@@ -10,6 +8,10 @@ __all__ = [
     "MeshGetter",
 ]
 
+#: In 2024 and before, these were .gz, but after
+#: became .xml files
+SUFFIXES = [".xml", ".xml.gz", ".gz"]
+
 
 class MeshGetter(Getter):
     """A getter for MeSH."""
@@ -24,9 +26,12 @@ class MeshGetter(Getter):
         with ftplib.FTP("nlmpubs.nlm.nih.gov") as ftp:
             ftp.login()
             ftp.cwd("/online/mesh/MESH_FILES/xmlmesh/")
-            for name, _ in ftp.mlsd():
-                if name.startswith("desc") and name.endswith(".gz"):
-                    return name[len("desc") : -len(".gz")]
+            names = [name for name, _ in ftp.mlsd()]
+
+        for name in names:
+            for suffix in SUFFIXES:
+                if name.startswith("desc") and name.endswith(suffix):
+                    return name[len("desc") : -len(suffix)]
         raise ValueError
 
 

bioversions/sources/mgi.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for the Mouse Genome Database."""
 
 from bioversions.utils import Getter, VersionType, get_soup

bioversions/sources/mirbase.py

@@ -1,8 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """A getter for miRBase."""
 
-from bioversions.utils import Getter, VersionType
+from typing import ClassVar
+
+from bioversions.utils import Getter, VersionType, get_soup
 
 __all__ = [
     "MirbaseGetter",
@@ -18,14 +18,20 @@ class MirbaseGetter(Getter):
     name = "miRBase"
     homepage_fmt = "https://www.mirbase.org/download/PREVIOUS_RELEASES/{version}"
     version_type = VersionType.semver_minor
+    collection: ClassVar[list[str]] = ["mirbase", "mirbase.family", "mirbase.mature"]
 
     def get(self):
         """Get the latest miRBase version number."""
         return "22.1"
-        # Old code, doesn't work anymore because miRBase site deleted most of their FTP server and downloads
-        # url = "http://www.mirbase.org/download_readme/"
-        # soup = get_soup(url, verify=False)
-        # return soup.find("p").text.splitlines()[0].split()[-1]
+
+
+def _old():
+    """Get miRBase version number from the old server."""
+    # Old code, doesn't work anymore because miRBase site deleted
+    # most of their FTP server and downloads
+    url = "http://www.mirbase.org/download_readme/"
+    soup = get_soup(url, verify=False)
+    return soup.find("p").text.splitlines()[0].split()[-1]
 
 
 if __name__ == "__main__":

bioversions/sources/moalmanac.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for the Molecular Oncology Almanac."""
 
 from ..utils import Getter, VersionType, get_soup

bioversions/sources/msigdb.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for MSigDB."""
 
 from bioversions.utils import Getter, VersionType, get_soup

bioversions/sources/ncit.py

@@ -1,9 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """A getter for the NCI Thesaurus."""
 
 import re
-from typing import Dict
 
 from ..utils import Getter, VersionType, get_soup
 
@@ -25,7 +22,7 @@ class NCItGetter(Getter):
     date_fmt = "%Y-%m-%d"
     version_type = VersionType.other
 
-    def get(self) -> Dict[str, str]:
+    def get(self) -> dict[str, str]:
         """Get the latest NCIt version number."""
         soup = get_soup(URL)
         version_str = soup.find("span", {"class": "vocabularynamelong_ncit"}).contents[0]

bioversions/sources/npass.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for NPASS."""
 
 from bioversions.utils import Getter, VersionType, get_soup

bioversions/sources/obo.py

@@ -1,17 +1,15 @@
-# -*- coding: utf-8 -*-
-
 """Getters for OBO ontologies."""
 
-from typing import Iterable, Type
+from collections.abc import Iterable
 
 from bioversions.utils import Getter, OBOFoundryGetter, VersionType
 
 __all__ = [
-    "iter_obo_getters",
     "ChebiGetter",
-    "GoGetter",
     "DoidGetter",
+    "GoGetter",
     "PrGetter",
+    "iter_obo_getters",
 ]
 
 
@@ -56,7 +54,7 @@ class PrGetter(OBOFoundryGetter):
     homepage_fmt = "https://proconsortium.org/download/release_{version}/"
 
 
-def iter_obo_getters() -> Iterable[Type[Getter]]:
+def iter_obo_getters() -> Iterable[type[Getter]]:
     """Iterate over OBO getters."""
     yield from OBOFoundryGetter.__subclasses__()
 

bioversions/sources/ols.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Get versions from the OLS."""
 
 import logging
-from typing import Iterable, List, Mapping, Optional, Type, Union
+from collections.abc import Iterable, Mapping
 
 import bioregistry
 from bioregistry.external.ols import get_ols_processing
@@ -16,7 +14,7 @@ logger = logging.getLogger(__name__)
 ols_processing = get_ols_processing()
 
 
-def _get_version_type(bioregistry_id: str) -> Optional[VersionType]:
+def _get_version_type(bioregistry_id: str) -> VersionType | None:
     ols_id = bioregistry.get_ols_prefix(bioregistry_id)
     ols_config = ols_processing.get(ols_id)
     if ols_config is None:
@@ -33,7 +31,7 @@ def _get_version_type(bioregistry_id: str) -> Optional[VersionType]:
         return None
 
 
-def make_ols_getter(bioregistry_id: str) -> Optional[Type[Getter]]:
+def make_ols_getter(bioregistry_id: str) -> type[Getter] | None:
     """Make a getter from OLS."""
     ols_id = bioregistry.get_ols_prefix(bioregistry_id)
     if ols_id is None:
@@ -66,14 +64,14 @@ def make_ols_getter(bioregistry_id: str) -> Optional[Type[Getter]]:
         name = _name
         version_type = _version_type  # type:ignore
 
-        def get(self) -> Union[str, Mapping[str, str]]:
+        def get(self) -> str | Mapping[str, str]:
             """Get the version from the Bioregistry."""
             return version
 
     return OlsGetter
 
 
-def iter_ols_getters() -> Iterable[Type[Getter]]:
+def iter_ols_getters() -> Iterable[type[Getter]]:
     """Iterate over OLS getters."""
     for bioregistry_id in bioregistry.read_registry():
         yv = make_ols_getter(bioregistry_id)
@@ -81,7 +79,7 @@ def iter_ols_getters() -> Iterable[Type[Getter]]:
             yield yv
 
 
-def extend_ols_getters(getters: List[Type[Getter]]) -> None:
+def extend_ols_getters(getters: list[type[Getter]]) -> None:
     """Extend the getters, without adding duplicates."""
     for ols_getter in iter_ols_getters():
         if any(getter.bioregistry_id == ols_getter.bioregistry_id for getter in getters):

bioversions/sources/omim.py

@@ -0,0 +1,33 @@
+"""A getter for the OMIM."""
+
+import datetime
+from typing import ClassVar
+
+from bioversions.utils import Getter, VersionType, get_soup
+
+__all__ = [
+    "OMIMGetter",
+]
+
+
+class OMIMGetter(Getter):
+    """A getter for OMIM."""
+
+    name = "Online Mendelian Inheritance in Man"
+    version_type = VersionType.date
+    collection: ClassVar[list[str]] = ["omim.ps", "omim"]
+
+    def get(self) -> datetime.datetime:
+        """Get the latest OMIM version number."""
+        soup = get_soup("https://omim.org/")
+        for tag in soup.find_all("h5"):
+            text = tag.text.strip()
+            if text.startswith("Updated"):
+                rv = text[len("Updated") :].strip()
+                rv = rv.replace("nd", "").replace("st", "").replace("rd", "").replace("th", "")
+                return datetime.datetime.strptime(rv, "%B %d, %Y")
+        raise ValueError
+
+
+if __name__ == "__main__":
+    OMIMGetter.print()

bioversions/sources/oncotree.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for OncoTree."""
 
 import requests
@@ -22,10 +20,12 @@ class OncoTreeGetter(Getter):
 
     def get(self) -> str:
         """Get the latest OncoTree version number."""
-        res = requests.get("http://oncotree.mskcc.org/api/versions", params={"format": "json"})
+        res = requests.get(
+            "http://oncotree.mskcc.org/api/versions", params={"format": "json"}, timeout=5
+        )
         res_json = res.json()
         version = next(
-            (r["release_date"] for r in res_json if r["api_identifier"] == "oncotree_latest_stable")
+            r["release_date"] for r in res_json if r["api_identifier"] == "oncotree_latest_stable"
         )
         return version
 

bioversions/sources/pathbank.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for PathBank."""
 
 from bioversions.utils import Getter, VersionType, get_soup

bioversions/sources/pathwaycommons.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Pathway Commons."""
 
 from bioversions.utils import Getter, VersionType, get_soup

bioversions/sources/pfam.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Rfam."""
 
 import ftplib

bioversions/sources/pombase.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for PomBase."""
 
 from bioversions.utils import Getter, VersionType, get_soup

bioversions/sources/pr.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for the Protein Ontology."""
 
 from bioversions.utils import Getter, VersionType, get_soup
@@ -26,7 +24,7 @@ class PRGetter(Getter):
         rows = soup.find("table", **{"class": "nrm11"}).find_all("tr")
         row = list(rows)[2]
         version_cell, date_cell, *_ = list(row.find_all("td"))
-        return dict(version=version_cell.text.strip(), date=date_cell.text.strip())
+        return {"version": version_cell.text.strip(), "date": date_cell.text.strip()}
 
 
 if __name__ == "__main__":

bioversions/sources/pubchem.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for PubChem."""
 
 import datetime

bioversions/sources/reactome.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Reactome."""
 
 from ..utils import Getter, VersionType, get_soup

bioversions/sources/rfam.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Rfam."""
 
 from bioversions.utils import Getter, VersionType, _get_ftp_version

bioversions/sources/rgd.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for RGD."""
 
 import requests
@@ -10,7 +8,7 @@ __all__ = [
     "RGDGetter",
 ]
 
-URL = "https://download.rgd.mcw.edu/data_release/GENES.RAT.txt"
+URL = "https://download.rgd.mcw.edu/data_release/GENES_RAT.txt"
 
 
 class RGDGetter(Getter):

bioversions/sources/rhea.py

@@ -1,9 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Rhea."""
 
 import requests
-import requests_ftp
 
 from bioversions.utils import Getter, VersionType
 
@@ -11,9 +8,7 @@ __all__ = [
     "RheaGetter",
 ]
 
-requests_ftp.monkeypatch_session()
-
-VERSION_FILE = "ftp://ftp.expasy.org/databases/rhea/rhea-release.properties"
+VERSION_FILE = "https://ftp.expasy.org/databases/rhea/rhea-release.properties"
 
 
 class RheaGetter(Getter):

bioversions/sources/rxnorm.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for RxNorm."""
 
 from datetime import datetime
@@ -24,7 +22,7 @@ class RxNormGetter(Getter):
     def get(self) -> datetime:
         """Get the latest RxNorm version number."""
         soup = get_soup(URL)
-        raw_version = soup.find("th", {"class": "current"}).contents[2]
+        raw_version = soup.find("th", {"class": "current"}).contents[2].strip()
         raw_fmt = "%B %d, %Y"
         return datetime.strptime(raw_version, raw_fmt)
 

bioversions/sources/sgd.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for SGD."""
 
 import requests