bioversions 0.7.89__tar.gz → 0.8.1__tar.gz

{bioversions-0.7.89 → bioversions-0.8.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bioversions
-Version: 0.7.89
+Version: 0.8.1
 Summary: Get the current version for biological databases
 Keywords: snekpack,cookiecutter,databases,biological databases,biomedical databases
 Author: Charles Tapley Hoyt

{bioversions-0.7.89 → bioversions-0.8.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "bioversions"
-version = "0.7.89"
+version = "0.8.1"
 description = "Get the current version for biological databases"
 readme = "README.md"
 authors = [
@@ -260,7 +260,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.7.89"
+current_version = "0.8.1"
 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}",

bioversions-0.8.1/src/bioversions/__init__.py

@@ -0,0 +1,14 @@
+"""What's the current version for each biological database?"""  # noqa:D400
+
+from .sources import VersionFailure, clear_cache, get_rows, get_version, iter_versions, resolve
+from .utils import VersionResult
+
+__all__ = [
+    "VersionFailure",
+    "VersionResult",
+    "clear_cache",
+    "get_rows",
+    "get_version",
+    "iter_versions",
+    "resolve",
+]

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/resources/update.py

@@ -15,7 +15,7 @@ from bioversions.resources import (
     write_export,
     write_versions,
 )
-from bioversions.sources import FailureTuple, _iter_versions
+from bioversions.sources import VersionFailure, iter_versions
 from bioversions.version import get_git_hash
 
 __all__ = [
@@ -49,8 +49,8 @@ def _update(force: bool):  # noqa:C901
 
     changes = False
     failure_tuples = []
-    for bv in _iter_versions(use_tqdm=True):
-        if isinstance(bv, FailureTuple):
+    for bv in iter_versions(use_tqdm=True):
+        if isinstance(bv, VersionFailure):
             failure_tuples.append(bv)
             continue
 

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/resources/versions.json

@@ -1,7 +1,7 @@
 {
   "annotations": {
-    "revision": 990,
-    "date": "2025-05-06",
+    "revision": 991,
+    "date": "2025-05-07",
     "author": "runner"
   },
   "database": [
@@ -528,6 +528,11 @@
           "retrieved": "2025-05-06",
           "version": "2025-05-05",
           "homepage": "https://antibodyregistry.org/"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "2025-05-06",
+          "homepage": "https://antibodyregistry.org/"
         }
       ],
       "name": "Antibody Registry",
@@ -5345,6 +5350,11 @@
           "retrieved": "2025-02-25",
           "version": "2025_01",
           "homepage": "http://ftp.flybase.net/releases/FB2025_01/"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "2025_02",
+          "homepage": "https://s3ftp.flybase.org/releases/FB2025_02/"
         }
       ],
       "name": "FlyBase",
@@ -5852,6 +5862,12 @@
           "version": "220",
           "homepage": "https://gtdb.ecogenomic.org/",
           "date": "2024-04-24"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "226",
+          "homepage": "https://gtdb.ecogenomic.org/",
+          "date": "2025-04-16"
         }
       ],
       "name": "Genome Taxonomy Database",
@@ -6296,6 +6312,11 @@
           "retrieved": "2025-04-03",
           "version": "2025-04-01",
           "homepage": "https://storage.googleapis.com/public-download-files/hgnc/archive/archive/monthly/json/hgnc_complete_set_2025-04-01.json"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "2025-05-06",
+          "homepage": "https://storage.googleapis.com/public-download-files/hgnc/archive/archive/monthly/json/hgnc_complete_set_2025-05-06.json"
         }
       ],
       "name": "HGNC",
@@ -10547,6 +10568,10 @@
         {
           "retrieved": "2025-05-04",
           "version": "2025-05-02"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "2025-05-05"
         }
       ],
       "name": "Online Mendelian Inheritance in Man",
@@ -17096,6 +17121,10 @@
         {
           "retrieved": "2025-05-06",
           "version": "2025-05-06"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "2025-05-07"
         }
       ],
       "name": "SwissLipids",
@@ -22644,6 +22673,10 @@
         {
           "retrieved": "2025-05-06",
           "version": "2025-05-04"
+        },
+        {
+          "retrieved": "2025-05-07",
+          "version": "2025-05-05"
         }
       ],
       "name": "Zebrafish Information Network",

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/__init__.py

@@ -3,13 +3,13 @@
 from __future__ import annotations
 
 import ftplib
-import logging
 import traceback
 from collections.abc import Iterable, Mapping
 from functools import lru_cache
 from typing import Literal, NamedTuple, overload
 
 from tqdm import tqdm
+from tqdm.contrib.logging import logging_redirect_tqdm
 
 from .antibodyregistry import AntibodyRegistryGetter
 from .bigg import BiGGGetter
@@ -71,15 +71,23 @@ from .umls import UMLSGetter
 from .uniprot import UniProtGetter
 from .wikipathways import WikiPathwaysGetter
 from .zfin import ZfinGetter
-from ..utils import Bioversion, Getter, norm, refresh_daily
+from ..utils import Getter, VersionResult, norm, refresh_daily
 
 __all__ = [
+    "VersionFailure",
+    "clear_cache",
     "get_rows",
     "get_version",
+    "iter_versions",
     "resolve",
 ]
 
-logger = logging.getLogger(__name__)
+#: These are broken beyond fixing at the moment
+SKIPPED = [
+    DrugBankGetter,
+    PathwayCommonsGetter,
+    DisGeNetGetter,
+]
 
 
 @lru_cache(maxsize=1)
@@ -90,7 +98,6 @@ def get_getters() -> list[type[Getter]]:
         BioGRIDGetter,
         ChEMBLGetter,
         ComplexPortalGetter,
-        DrugBankGetter,
         DrugCentralGetter,
         ExPASyGetter,
         IntActGetter,
@@ -109,7 +116,6 @@ def get_getters() -> list[type[Getter]]:
         RheaGetter,
         StringDBGetter,
         HomoloGeneGetter,
-        DisGeNetGetter,
         MeshGetter,
         DGIGetter,
         FlybaseGetter,
@@ -131,7 +137,6 @@ def get_getters() -> list[type[Getter]]:
         SwissLipidGetter,
         ITISGetter,
         DepMapGetter,
-        PathwayCommonsGetter,
         UMLSGetter,
         HGNCGetter,
         RGDGetter,
@@ -167,7 +172,7 @@ def get_getter_dict() -> Mapping[str, type[Getter]]:
     return rv
 
 
-def resolve(name: str, use_cache: bool = True) -> Bioversion:
+def resolve(name: str, use_cache: bool = True) -> VersionResult:
     """Resolve the database name to a :class:`Bioversion` instance."""
     if use_cache:
         return _resolve_helper_cached(name)
@@ -176,11 +181,16 @@ def resolve(name: str, use_cache: bool = True) -> Bioversion:
 
 
 @refresh_daily
-def _resolve_helper_cached(name: str) -> Bioversion:
+def _resolve_helper_cached(name: str) -> VersionResult:
     return _resolve_helper(name)
 
 
-def _resolve_helper(name: str) -> Bioversion:
+def clear_cache() -> None:
+    """Clear the cache."""
+    _resolve_helper_cached.clear_cache()
+
+
+def _resolve_helper(name: str) -> VersionResult:
     norm_name = norm(name)
     getter: type[Getter] = get_getter_dict()[norm_name]
     return getter.resolve()
@@ -217,16 +227,16 @@ def get_version(name: str, *, strict: bool = True) -> str | None:
         return rv
 
 
-def get_rows(use_tqdm: bool | None = False) -> list[Bioversion]:
+def get_rows(use_tqdm: bool | None = False) -> list[VersionResult]:
     """Get the rows, refreshing once per day."""
     return [
         bioversion
-        for bioversion in _iter_versions(use_tqdm=use_tqdm)
-        if isinstance(bioversion, Bioversion)
+        for bioversion in iter_versions(use_tqdm=use_tqdm)
+        if isinstance(bioversion, VersionResult)
     ]
 
 
-class FailureTuple(NamedTuple):
+class VersionFailure(NamedTuple):
     """Holds information about failures."""
 
     name: str
@@ -235,22 +245,23 @@ class FailureTuple(NamedTuple):
     trace: str
 
 
-def _iter_versions(
+def iter_versions(
     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 (OSError, AttributeError, ftplib.error_perm):
-            msg = f"failed to resolve {cls.name}"
-            tqdm.write(msg)
-            yield FailureTuple(cls.name, cls.__name__, msg, traceback.format_exc())
-        except (ValueError, KeyError) as e:
-            msg = f"issue parsing {cls.name}: {e}"
-            tqdm.write(msg)
-            yield FailureTuple(cls.name, cls.__name__, msg, traceback.format_exc())
-        else:
-            yield yv
+) -> Iterable[VersionResult | VersionFailure]:
+    """Iterate over versions, without caching."""
+    with logging_redirect_tqdm():
+        it = tqdm(get_getters(), disable=not use_tqdm, desc="Getting versions", unit="resource")
+        for cls in it:
+            it.set_postfix(name=cls.name)
+            try:
+                yv = resolve(cls.name)
+            except (OSError, AttributeError, ftplib.error_perm):
+                msg = f"[{cls.bioregistry_id or cls.name}] failed to resolve"
+                tqdm.write(msg)
+                yield VersionFailure(cls.name, cls.__name__, msg, traceback.format_exc())
+            except (ValueError, KeyError) as e:
+                msg = f"[{cls.bioregistry_id or cls.name}] issue parsing: {e}"
+                tqdm.write(msg)
+                yield VersionFailure(cls.name, cls.__name__, msg, traceback.format_exc())
+            else:
+                yield yv

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/ensembl.py

@@ -6,7 +6,7 @@ __all__ = [
     "EnsemblGetter",
 ]
 
-URL = "https://useast.ensembl.org/index.html"
+URL = "https://www.ensembl.org/index.html"
 
 
 class EnsemblGetter(Getter):

bioversions-0.8.1/src/bioversions/sources/flybase.py

@@ -0,0 +1,42 @@
+"""A getter for FlyBase."""
+
+import re
+
+from bioversions.utils import Getter, VersionType, get_soup
+
+__all__ = [
+    "FlybaseGetter",
+]
+
+URL = "https://s3ftp.flybase.org/releases/"
+PATTERN = re.compile(r"FB\d{4}_\d{2}")
+AGENT = (
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
+    "(KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36"
+)
+
+
+class FlybaseGetter(Getter):
+    """A getter for FlyBase."""
+
+    bioregistry_id = "flybase"
+    name = "FlyBase"
+    homepage_fmt = "https://s3ftp.flybase.org/releases/FB{version}/"
+    version_type = VersionType.month
+
+    def get(self) -> str:
+        """Get the latest FlyBase version."""
+        soup = get_soup(URL, user_agent=AGENT)
+        releases = [
+            match.group().removeprefix("FB")
+            for anchor_tag in soup.find_all("a", href=True)
+            if (match := PATTERN.search(anchor_tag.text))
+        ]
+        if not releases:
+            raise ValueError("flybase hit anti-scraping measurements")
+        latest_version = max(releases)
+        return latest_version
+
+
+if __name__ == "__main__":
+    FlybaseGetter.print()

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/gtdb.py

@@ -8,7 +8,7 @@ __all__ = [
     "GTDBGetter",
 ]
 
-URL = "https://data.gtdb.ecogenomic.org/releases/latest/VERSION.txt"
+URL = "https://data.ace.uq.edu.au/public/gtdb/data/releases/latest/VERSION.txt"
 
 
 class GTDBGetter(Getter):
@@ -24,10 +24,15 @@ class GTDBGetter(Getter):
         """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")
+        version_line = next(line for line in lines if line.startswith("v"))
+        version = version_line.strip().lstrip("v")
+
         # Third line contains date like "Released Apr 24, 2024"
-        date = lines[2].strip().removeprefix("Released ")
+        date_line = next(line for line in lines if line.startswith("Released "))
+        date = date_line.strip().removeprefix("Released ")
+
         return {"version": version, "date": date}
 
 

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/icd10.py

@@ -1,6 +1,9 @@
 """A getter for ICD10."""
 
+import warnings
+
 import requests
+from urllib3.exceptions import InsecureRequestWarning
 
 from bioversions.utils import Getter, VersionType
 
@@ -21,7 +24,9 @@ class ICD10Getter(Getter):
 
     def get(self) -> str:
         """Get the latest ICD10 version number."""
-        response = requests.get(URL, allow_redirects=True, timeout=15)
+        with warnings.catch_warnings():
+            warnings.simplefilter(action="ignore", category=InsecureRequestWarning)
+            response = requests.get(URL, allow_redirects=True, timeout=15, verify=False)  # noqa:S501
         final_url = response.url
         return final_url[len("https://icd.who.int/browse10/") :].split("/")[0]
 

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/icd11.py

@@ -1,6 +1,9 @@
 """A getter for ICD11."""
 
+import warnings
+
 import requests
+from urllib3.exceptions import InsecureRequestWarning
 
 from bioversions.utils import Getter, VersionType
 
@@ -14,6 +17,7 @@ URL = "https://icd.who.int/browse/latest-release/mms/en"
 class ICD11Getter(Getter):
     """A getter for ICD11."""
 
+    # TODO combine with ICF using `collection`
     bioregistry_id = "icd11"
     name = "International Classification of Diseases, 11th Revision"
     version_type = VersionType.date
@@ -21,7 +25,9 @@ class ICD11Getter(Getter):
 
     def get(self) -> str:
         """Get the latest ICD11 version number."""
-        response = requests.get(URL, allow_redirects=True, timeout=15)
+        with warnings.catch_warnings():
+            warnings.simplefilter(action="ignore", category=InsecureRequestWarning)
+            response = requests.get(URL, allow_redirects=True, timeout=15, verify=False)  # noqa:S501
         final_url = response.url
         return final_url[len("https://icd.who.int/browse/") :].split("/")[0]
 

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/icf.py

@@ -1,6 +1,9 @@
 """A getter for ICF."""
 
+import warnings
+
 import requests
+from urllib3.exceptions import InsecureRequestWarning
 
 from bioversions.utils import Getter, VersionType
 
@@ -21,7 +24,9 @@ class ICFGetter(Getter):
 
     def get(self) -> str:
         """Get the latest ICF version number."""
-        response = requests.get(URL, allow_redirects=True, timeout=15)
+        with warnings.catch_warnings():
+            warnings.simplefilter(action="ignore", category=InsecureRequestWarning)
+            response = requests.get(URL, allow_redirects=True, timeout=15, verify=False)  # noqa:S501
         final_url = response.url
         return final_url[len("https://icd.who.int/browse/") :].split("/")[0]
 

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/sources/npass.py

@@ -18,13 +18,19 @@ class NPASSGetter(Getter):
 
     def get(self) -> str:
         """Get the latest NPASS version number."""
-        soup = get_soup(URL)
-        footer = find(soup, name="footer")
-        ul = find(footer, name="ul")
-        for li in ul.find_all(name="li"):
-            if li.text.startswith("Version:"):
-                return li.text[len("Version: ") :]
-        raise ValueError(f"could not parse NPASS version from {URL}")
+        return "2.0"
+
+
+def _dynamic_get() -> str:
+    # this has been retired since the website is so slow and this
+    # resource is effectively static
+    soup = get_soup(URL)
+    footer = find(soup, name="footer")
+    ul = find(footer, name="ul")
+    for li in ul.find_all(name="li"):
+        if li.text.startswith("Version:"):
+            return li.text[len("Version: ") :]
+    raise ValueError(f"could not parse NPASS version from {URL}")
 
 
 if __name__ == "__main__":

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/utils.py

@@ -158,7 +158,7 @@ class MetaGetter(type):
         return version
 
 
-class Bioversion(pydantic.BaseModel):
+class VersionResult(pydantic.BaseModel):
     """A dataclass for information about a database and version."""
 
     #: The database name
@@ -217,9 +217,9 @@ class Getter(metaclass=MetaGetter):
         print(*x, sep=sep, file=file)
 
     @classmethod
-    def resolve(cls) -> Bioversion:
+    def resolve(cls) -> VersionResult:
         """Get a Bioversion data container with the data for this database."""
-        return Bioversion(
+        return VersionResult(
             name=cls.name,
             version=cls.version,
             classname=cls.__name__,

{bioversions-0.7.89 → bioversions-0.8.1}/src/bioversions/version.py

@@ -8,7 +8,7 @@ __all__ = [
     "get_git_hash",
 ]
 
-VERSION = "0.7.89"
+VERSION = "0.8.1"
 
 
 def get_git_hash() -> str:

bioversions-0.7.89/src/bioversions/__init__.py

@@ -1,9 +0,0 @@
-"""What's the current version for each biological database?"""  # noqa:D400
-
-from .sources import get_rows, get_version, resolve
-
-__all__ = [
-    "get_rows",
-    "get_version",
-    "resolve",
-]

bioversions-0.7.89/src/bioversions/sources/flybase.py

@@ -1,38 +0,0 @@
-"""A getter for FlyBase."""
-
-import re
-
-from bioversions.utils import Getter, VersionType, get_soup
-
-__all__ = [
-    "FlybaseGetter",
-]
-
-URL = "http://flybase-ftp.s3-website-us-east-1.amazonaws.com/releases/index.html"
-PATTERN = re.compile(r"FB\d{4}_\d{2}")
-
-
-class FlybaseGetter(Getter):
-    """A getter for FlyBase."""
-
-    bioregistry_id = "flybase"
-    name = "FlyBase"
-    homepage_fmt = "http://flybase-ftp.s3-website-us-east-1.amazonaws.com/releases/FB{version}/"
-    version_type = VersionType.month
-
-    def get(self):
-        """Get the latest flybase version number."""
-        soup = get_soup(URL)
-
-        releases = []
-        # We check links to find ones that look like releases
-        for anchor_tag in soup.find_all("a", href=True):
-            match = PATTERN.search(anchor_tag.text)
-            if match:
-                releases.append(match.group().removeprefix("FB"))
-        latest_version = max(releases)
-        return latest_version
-
-
-if __name__ == "__main__":
-    FlybaseGetter.print()