bioversions 0.5.376__py3-none-any.whl → 0.7.1__py3-none-any.whl

bioversions/slack_client.py

@@ -1,10 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Utilities for interacting with Slack."""
 
 import logging
 from functools import lru_cache
-from typing import Optional
 
 import pystow
 from slack_sdk import WebClient
@@ -18,14 +15,14 @@ logger = logging.getLogger(__name__)
 
 
 @lru_cache(maxsize=1)
-def _get_client(token: Optional[str] = None) -> Optional[WebClient]:
+def _get_client(token: str | None = None) -> WebClient | None:
     token = pystow.get_config("bioversions", "slack_api_token", passthrough=token)
     if token is None:
         return None
     return WebClient(token=token)
 
 
-def post(text: str, channel: str = "random", token: Optional[str] = None):
+def post(text: str, channel: str = "random", token: str | None = None):
     """Post the message to a given Slack channel."""
     client = _get_client(token)
     if client is None:

bioversions/sources/__init__.py

@@ -1,11 +1,13 @@
-# -*- coding: utf-8 -*-
-
 """Sources for Bioversions."""
 
+from __future__ import annotations
+
 import ftplib
 import logging
+import traceback
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
-from typing import Iterable, List, Mapping, Optional, Tuple, Type, Union
+from typing import NamedTuple
 
 from tqdm import tqdm
 
@@ -27,6 +29,7 @@ from .drugcentral import DrugCentralGetter
 from .ensembl import EnsemblGetter
 from .expasy import ExPASyGetter
 from .flybase import FlybaseGetter
+from .gtdb import GTDBGetter
 from .guidetopharmacology import GuideToPharmacologyGetter
 from .hgnc import HGNCGetter
 from .homologene import HomoloGeneGetter
@@ -60,6 +63,7 @@ from .rgd import RGDGetter
 from .rhea import RheaGetter
 from .rxnorm import RxNormGetter
 from .sgd import SgdGetter
+from .signor import SignorGetter
 from .slm import SwissLipidGetter
 from .stringdb import StringDBGetter
 from .umls import UMLSGetter
@@ -69,19 +73,19 @@ from .zfin import ZfinGetter
 from ..utils import Bioversion, Getter, norm, refresh_daily
 
 __all__ = [
-    "resolve",
     "get_rows",
     "get_version",
+    "resolve",
 ]
 
 logger = logging.getLogger(__name__)
 
 
 @lru_cache(maxsize=1)
-def get_getters() -> List[Type[Getter]]:
+def get_getters() -> list[type[Getter]]:
     """Get a list of getters."""
     # TODO replace with entrypoint lookup
-    getters: List[Type[Getter]] = [
+    getters: list[type[Getter]] = [
         BioGRIDGetter,
         ChEMBLGetter,
         ComplexPortalGetter,
@@ -137,6 +141,8 @@ def get_getters() -> List[Type[Getter]]:
         ICD10Getter,
         ICD11Getter,
         CiVICGetter,
+        GTDBGetter,
+        SignorGetter,
     ]
     getters.extend(iter_obo_getters())
     extend_ols_getters(getters)
@@ -144,7 +150,7 @@ def get_getters() -> List[Type[Getter]]:
     return getters
 
 
-def get_getter_dict() -> Mapping[str, Type[Getter]]:
+def get_getter_dict() -> Mapping[str, type[Getter]]:
     """Get a dict of getters."""
     rv = {}
     for getter in get_getters():
@@ -174,7 +180,7 @@ def _resolve_helper_cached(name: str) -> Bioversion:
 
 def _resolve_helper(name: str) -> Bioversion:
     norm_name = norm(name)
-    getter: Type[Getter] = get_getter_dict()[norm_name]
+    getter: type[Getter] = get_getter_dict()[norm_name]
     return getter.resolve()
 
 
@@ -183,31 +189,40 @@ def get_version(name: str) -> str:
     return resolve(name).version
 
 
-def get_rows(use_tqdm: Optional[bool] = False) -> List[Bioversion]:
+def get_rows(use_tqdm: bool | None = False) -> list[Bioversion]:
     """Get the rows, refreshing once per day."""
     return [
         bioversion
-        for bioversion, error in _iter_versions(use_tqdm=use_tqdm)
-        if error is None and bioversion is not None
+        for bioversion in _iter_versions(use_tqdm=use_tqdm)
+        if isinstance(bioversion, Bioversion)
     ]
 
 
+class FailureTuple(NamedTuple):
+    """Holds information about failures."""
+
+    name: str
+    clstype: str
+    message: str
+    trace: str
+
+
 def _iter_versions(
-    use_tqdm: Optional[bool] = False,
-) -> Iterable[Union[Tuple[Bioversion, None], Tuple[None, str]]]:
+    use_tqdm: bool | None = False,
+) -> Iterable[Bioversion | FailureTuple]:
     it = tqdm(get_getters(), disable=not use_tqdm)
 
     for cls in it:
         it.set_postfix(name=cls.name)
         try:
             yv = resolve(cls.name)
-        except (IOError, AttributeError, ftplib.error_perm):
+        except (OSError, AttributeError, ftplib.error_perm):
             msg = f"failed to resolve {cls.name}"
             tqdm.write(msg)
-            yield None, msg
+            yield FailureTuple(cls.name, cls.__name__, msg, traceback.format_exc())
         except ValueError as e:
             msg = f"issue parsing {cls.name}: {e}"
             tqdm.write(msg)
-            yield None, msg
+            yield FailureTuple(cls.name, cls.__name__, msg, traceback.format_exc())
         else:
-            yield yv, None
+            yield yv

bioversions/sources/antibodyregistry.py

@@ -1,13 +1,15 @@
-# -*- coding: utf-8 -*-
-
 """A getter for the Antibody Registry."""
 
-from bioversions.utils import Getter, VersionType, get_soup
+import requests
+
+from bioversions.utils import Getter, VersionType
 
 __all__ = [
     "AntibodyRegistryGetter",
 ]
 
+URL = "https://www.antibodyregistry.org/api/datainfo"
+
 
 class AntibodyRegistryGetter(Getter):
     """A getter for the Antibody Registry."""
@@ -15,12 +17,13 @@ class AntibodyRegistryGetter(Getter):
     bioregistry_id = "antibodyregistry"
     name = "Antibody Registry"
     homepage_fmt = "https://antibodyregistry.org/"
-    version_type = VersionType.semver_minor
+    version_type = VersionType.date
 
     def get(self):
         """Get the latest Antibody Registry version number."""
-        soup = get_soup("https://antibodyregistry.org/")
-        return soup.find(**{"class": "footer"}).find("a").text.lstrip("v")
+        res = requests.get(URL, timeout=3)
+        res_json = res.json()
+        return res_json["lastupdate"]
 
 
 if __name__ == "__main__":

bioversions/sources/bigg.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for BiGG."""
 
 from datetime import datetime
@@ -23,12 +21,12 @@ class BiGGGetter(Getter):
 
     def get(self):
         """Get the latest BiGG version number."""
-        res = requests.get(URL).json()
+        res = requests.get(URL, timeout=15).json()
         date = datetime.fromisoformat(res["last_updated"])
-        return dict(
-            version=res["bigg_models_version"],
-            date=date,
-        )
+        return {
+            "version": res["bigg_models_version"],
+            "date": date,
+        }
 
 
 if __name__ == "__main__":

bioversions/sources/biogrid.py

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

bioversions/sources/cellosaurus.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Cellosaurus."""
 
 import requests
@@ -24,15 +22,15 @@ class CellosaurusGetter(Getter):
     #   12:15:2022 12:00
     def get(self):
         """Get the latest Cellosaurus version number."""
-        res = requests.get(URL, stream=True)
+        res = requests.get(URL, stream=True, timeout=15)
         data = {}
         for line in res.iter_lines(decode_unicode=True):
             line = line.strip().decode("utf8")
             if not line:
                 break
-            key, value = [part.strip() for part in line.split(":", 1)]
+            key, value = (part.strip() for part in line.split(":", 1))
             data[key] = value
-        return dict(version=data["data-version"], date=data["date"])
+        return {"version": data["data-version"], "date": data["date"]}
 
 
 if __name__ == "__main__":

bioversions/sources/chebi.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for ChEBI."""
 
 from bioversions.utils import Getter, VersionType, get_soup
@@ -27,7 +25,7 @@ class ChEBIGetter(Getter):
         last = list(anchors)[-1]
         date = last.next_sibling.strip().split()[0]
         version = last.text.rstrip("/")[len("rel") :]
-        return dict(version=version, date=date)
+        return {"version": version, "date": date}
 
 
 if __name__ == "__main__":

bioversions/sources/chembl.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """A getter for ChEMBL."""
 
 import ftplib
 import io
+from typing import ClassVar
 
 from bioversions.utils import Getter, VersionType
 
@@ -23,7 +22,7 @@ class ChEMBLGetter(Getter):
     homepage_fmt = "ftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_{version}"
     date_fmt = "%d/%m/%Y"
     version_type = VersionType.sequential
-    collection = ["chembl", "chembl.target", "chembl.compound", "chembl.cell"]
+    collection: ClassVar[list[str]] = ["chembl", "chembl.target", "chembl.compound", "chembl.cell"]
 
     def get(self):
         """Get the latest ChEMBL version number."""
@@ -40,7 +39,7 @@ class ChEMBLGetter(Getter):
                 date = _removeprefix(line, DATE_PREFIX).strip()
         if version is None or date is None:
             raise ValueError
-        return dict(date=date, version=version)
+        return {"date": date, "version": version}
 
 
 def _removeprefix(s, prefix):

bioversions/sources/chemidplus.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for ChemIDplus."""
 
 import re
@@ -26,7 +24,7 @@ class ChemIDplusGetter(Getter):
         """Get the latest ChemIDplus version number."""
         latest_url = "https://ftp.nlm.nih.gov/projects/chemidlease/CurrentChemID.xml"
         headers = {"Range": "bytes=0-300"}  # leave some slack to capture date
-        r = requests.get(latest_url, headers=headers)
+        r = requests.get(latest_url, headers=headers, timeout=15)
         if r.status_code == 206:
             result = re.search(r" date=\"([0-9]{4}-[0-9]{2}-[0-9]{2})\">", r.text)
             if result:

bioversions/sources/civic.py

@@ -1,5 +1,8 @@
 """Get the version for CiVIC."""
 
+import datetime
+from typing import ClassVar
+
 import requests
 
 from bioversions.utils import Getter, VersionType
@@ -17,6 +20,7 @@ query dataReleases {
   }
 }
 """
+
 # see https://griffithlab.github.io/civic-v2/#query-dataReleases
 # and https://griffithlab.github.io/civic-v2/#definition-DownloadableFile
 
@@ -28,13 +32,14 @@ class CiVICGetter(Getter):
     date_fmt = "%d-%b-%Y"
     version_type = VersionType.date
     homepage = "https://civicdb.org"
-    collection = ["civic.gid", "civic.eid"]
+    collection: ClassVar[list[str]] = ["civic.gid", "civic.eid"]
 
-    def get(self):
+    def get(self) -> datetime.datetime:
         """Get the latest ChEMBL version number."""
-        res = requests.post(API, json={"query": GRAPHQL_QUERY})
+        res = requests.post(API, json={"query": GRAPHQL_QUERY}, timeout=15)
         # 0 element is always nightly, 1 is latest
-        return res.json()["data"]["dataReleases"][1]["name"]
+        value = res.json()["data"]["dataReleases"][1]["name"]
+        return datetime.datetime.strptime(value, "%d-%b-%Y")
 
 
 if __name__ == "__main__":

bioversions/sources/complexportal.py

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

bioversions/sources/daily.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A collection of daily updated resources that aren't assigned specific versions."""
 
 from bioversions.utils import DailyGetter

bioversions/sources/depmap.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for DepMap."""
 
 import requests
@@ -21,7 +19,7 @@ class DepMapGetter(Getter):
 
     def get(self) -> str:
         """Get the latest DepMap version number."""
-        res = requests.get(URL)
+        res = requests.get(URL, timeout=15)
         latest = next(release for release in res.json()["releaseData"] if release["isLatest"])
         return latest["releaseName"][len("DepMap Public ") :]
 

bioversions/sources/dgi.py

@@ -1,15 +1,12 @@
-# -*- coding: utf-8 -*-
-
 """A getter for the `Drug Gene Interaction Database (DGI-DB) <http://www.dgidb.org>`_."""
 
-import os
-
 import bs4
+import dateutil.parser
 import requests
 
 from bioversions.utils import Getter, VersionType
 
-DOWNLOADS_PAGE = "https://www.dgidb.org/downloads"
+GITHUB_PAGE = "https://github.com/dgidb/dgidb-v5"
 
 
 class DGIGetter(Getter):
@@ -21,14 +18,14 @@ class DGIGetter(Getter):
 
     def get(self):
         """Get the latest DGI version number."""
-        res = requests.get(DOWNLOADS_PAGE)
-        soup = bs4.BeautifulSoup(res.content, parser="lxml", features="lxml")
-        cells = list(soup.select("table#tsv_downloads tbody tr:first-child td:nth-child(2) a"))
-        if 1 != len(cells):
+        res = requests.get(GITHUB_PAGE, timeout=15)
+        soup = bs4.BeautifulSoup(res.content, features="html.parser")
+        time_tag = soup.find("relative-time")
+        if time_tag is None:
             raise ValueError
-        cell = cells[0]
-        href = cell["href"]
-        version = os.path.dirname(os.path.relpath(href, "data/monthly_tsvs"))
+        datetime_str = time_tag.attrs["datetime"]
+        dt_obj = dateutil.parser.parse(datetime_str)
+        version = dt_obj.strftime(self.date_version_fmt)
         return version
 
 

bioversions/sources/disgenet.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for DisGeNet."""
 
 import requests
@@ -22,7 +20,7 @@ class DisGeNetGetter(Getter):
 
     def get(self):
         """Get the latest DisGeNet version number."""
-        res = requests.get(URL, params={"format": "json"})
+        res = requests.get(URL, params={"format": "json"}, timeout=15)
         res_json = res.json()
         version = res_json["database_version"].split()[-1].lstrip("v")
         return {

bioversions/sources/drugbank.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for DrugBank."""
 
 from operator import itemgetter
@@ -26,10 +24,10 @@ class DrugBankGetter(Getter):
 
     def get(self):
         """Get the latest DrugBank version number."""
-        res = requests.get(URL)
+        res = requests.get(URL, timeout=15)
         res.raise_for_status()
         latest = max(res.json(), key=itemgetter("released_on"))
-        return dict(date=latest["released_on"], version=latest["version"])
+        return {"date": latest["released_on"], "version": latest["version"]}
 
     @staticmethod
     def homepage_version_transform(version: str) -> str:

bioversions/sources/drugcentral.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for DrugCentral."""
 
 from contextlib import closing
@@ -13,9 +11,9 @@ __all__ = [
 HOST = "unmtid-dbs.net"
 PORT = 5433
 USER = "drugman"
-PASSWORD = "dosage"
+PASSWORD = "dosage"  # noqa:S105
 DBNAME = "drugcentral"
-PARAMS = dict(dbname=DBNAME, user=USER, password=PASSWORD, host=HOST, port=PORT)
+PARAMS = {"dbname": DBNAME, "user": USER, "password": PASSWORD, "host": HOST, "port": PORT}
 
 
 class DrugCentralGetter(Getter):

bioversions/sources/ensembl.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for Ensembl."""
 
 from bioversions.utils import Getter, VersionType, get_soup
@@ -25,7 +23,7 @@ class EnsemblGetter(Getter):
         soup = get_soup(URL)
         manifest = soup.find(**{"class": "box-header"}).text
         version, date = manifest.rstrip(")").split("(", 1)
-        return dict(version=version.split()[-1], date=date)
+        return {"version": version.split()[-1], "date": date}
 
 
 if __name__ == "__main__":

bioversions/sources/expasy.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for ExPASy."""
 
 from datetime import datetime
@@ -12,7 +10,7 @@ __all__ = [
     "ExPASyGetter",
 ]
 
-URL = "ftp://ftp.expasy.org/databases/enzyme/enzuser.txt"
+URL = "https://ftp.expasy.org/databases/enzyme/enzuser.txt"
 
 
 class ExPASyGetter(Getter):
@@ -20,7 +18,6 @@ class ExPASyGetter(Getter):
 
     bioregistry_id = "eccode"
     name = "ExPASy"
-    # date_version_fmt = "%d-%b-%Y"
     version_type = VersionType.date
 
     def get(self) -> str:

bioversions/sources/flybase.py

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

bioversions/sources/gtdb.py

@@ -0,0 +1,35 @@
+"""A getter for GTDB."""
+
+import requests
+
+from bioversions.utils import Getter, VersionType
+
+__all__ = [
+    "GTDBGetter",
+]
+
+URL = "https://data.gtdb.ecogenomic.org/releases/latest/VERSION.txt"
+
+
+class GTDBGetter(Getter):
+    """A getter for the Genome Taxonomy Database (GTDB)."""
+
+    bioregistry_id = "gtdb"
+    name = "Genome Taxonomy Database"
+    version_type = VersionType.sequential
+    date_fmt = "%b %d, %Y"  # Format to match "Apr 24, 2024"
+    homepage_fmt = "https://gtdb.ecogenomic.org/"
+
+    def get(self):
+        """Get the latest GTDB version number from VERSION.txt."""
+        res = requests.get(URL, timeout=15)
+        lines = res.text.strip().split("\n")
+        # First line contains version like "v220"
+        version = lines[0].strip().lstrip("v")
+        # Third line contains date like "Released Apr 24, 2024"
+        date = lines[2].strip().removeprefix("Released ")
+        return {"version": version, "date": date}
+
+
+if __name__ == "__main__":
+    GTDBGetter.print()

bioversions/sources/guidetopharmacology.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """A getter for GuideToPharmacology."""
 
 import re
 from datetime import datetime
-from typing import Dict
+from typing import ClassVar
 
 from bioversions.utils import Getter, VersionType, get_soup
 
@@ -23,9 +21,9 @@ class GuideToPharmacologyGetter(Getter):
     homepage_fmt = "https://www.guidetopharmacology.org/DATA/public_iuphardb_v{version}.zip"
     date_fmt = "%Y-%m-%d"
     version_type = VersionType.year_minor
-    collection = ["iuphar.family", "iuphar.ligand", "iuphar.receptor"]
+    collection: ClassVar[list[str]] = ["iuphar.family", "iuphar.ligand", "iuphar.receptor"]
 
-    def get(self) -> Dict[str, str]:
+    def get(self) -> dict[str, str]:
         """Get the latest Guide to Pharmacology version number."""
         soup = get_soup(URL)
         text = soup.findAll("div", {"class": "contentboxfullhelp"})[4].div.ul.li.a.text

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

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """A getter for ICD10."""
 
 import requests
@@ -23,7 +21,7 @@ class ICD10Getter(Getter):
 
     def get(self) -> str:
         """Get the latest ICD10 version number."""
-        response = requests.get(URL, allow_redirects=True)
+        response = requests.get(URL, allow_redirects=True, timeout=15)
         final_url = response.url
         return final_url[len("https://icd.who.int/browse10/") :].split("/")[0]