pymetadata 0.6.2__tar.gz → 0.6.3__tar.gz

{pymetadata-0.6.2 → pymetadata-0.6.3}/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.6.2"
+current_version = "0.6.3"
 commit = true
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]

{pymetadata-0.6.2 → pymetadata-0.6.3}/.github/workflows/ci-cd.yml

@@ -26,7 +26,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python-version: ["3.11", "3.12", "3.13", "3.14"]
+        python-version: ["3.11", "3.12", "3.13", "3.14", "3.15"]
         # linux covers the full range, windows and macos only the newest version
         exclude:
           - os: windows-latest
@@ -35,12 +35,16 @@ jobs:
             python-version: "3.12"
           - os: windows-latest
             python-version: "3.13"
+          - os: windows-latest
+            python-version: "3.14"
           - os: macos-latest
             python-version: "3.11"
           - os: macos-latest
             python-version: "3.12"
           - os: macos-latest
             python-version: "3.13"
+          - os: macos-latest
+            python-version: "3.14"
 
     steps:
     - uses: actions/checkout@v7

{pymetadata-0.6.2 → pymetadata-0.6.3}/CITATION.cff

@@ -8,7 +8,7 @@ authors:
     given-names: "Matthias"
     orcid: "https://orcid.org/0000-0003-1725-179X"
     affiliation: "Humboldt-University Berlin, Faculty of Life Science, Institute for Biology, Biology, Berlin; University Lübeck; University Hospital Schleswig-Holstein, Campus Lübeck, First Department of Medicine, Germany"
-version: "0.6.2"
+version: "0.6.3"
 date-released: "2026-09-07"
 doi: "10.5281/zenodo.5308801"
 license: MIT

{pymetadata-0.6.2 → pymetadata-0.6.3}/CLAUDE.md

@@ -22,7 +22,7 @@ uv run pre-commit install
 pytest                          # all tests
 pytest tests/test_omex.py       # single file
 pytest tests/test_omex.py::test_entry_from_dict   # single test
-tox r -e py3.14                 # single tox env (py3.11-3.14 available)
+tox r -e py3.15                 # single tox env (py3.11-3.15 available)
 tox run-parallel                # full matrix + ty
 
 # lint / format / types

{pymetadata-0.6.2 → pymetadata-0.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: pymetadata
-Version: 0.6.2
+Version: 0.6.3
 Summary: pymetadata are python utilities for working with metadata.
 Project-URL: Homepage, https://matthiaskoenig.github.io/pymetadata
 Project-URL: Documentation, https://matthiaskoenig.github.io/pymetadata
@@ -20,6 +20,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
@@ -37,7 +38,7 @@ Requires-Dist: pytest>=9.1.1; extra == 'dev'
 Requires-Dist: ruff>=0.16.6; extra == 'dev'
 Requires-Dist: tox>=4.61.2; extra == 'dev'
 Requires-Dist: ty>=0.0.78; extra == 'dev'
-Requires-Dist: zensical>=0.0.59; extra == 'dev'
+Requires-Dist: zensical>=0.0.60; extra == 'dev'
 Provides-Extra: ontology
 Requires-Dist: pronto>=2.7.3; extra == 'ontology'
 Description-Content-Type: text/markdown

{pymetadata-0.6.2 → pymetadata-0.6.3}/docs/development.md

@@ -27,7 +27,7 @@ A pull request can only be merged once the four required checks are green:
 
 | check   | workflow      | content                                                              |
 | ------- | ------------- | -------------------------------------------------------------------- |
-| `tests` | `ci-cd.yml`   | the test matrix, linux, macos and windows with python 3.11 to 3.14    |
+| `tests` | `ci-cd.yml`   | the test matrix, linux, macos and windows with python 3.11 to 3.15    |
 | `ruff`  | `ruff.yml`    | `ruff check` and `ruff format --check`                                |
 | `ty`    | `ty.yml`      | `tox r -e ty`                                                         |
 | `docs`  | `docs.yml`    | the zensical build including the api reference and the agent files    |
@@ -118,16 +118,16 @@ From now on every commit is checked with ruff (lint and format) and ty, i.e., th
 
 The tests are written with pytest, tox runs them against every supported python version.
 
-The tox environments are named after the interpreter (`py3.11` to `py3.14`, see `envlist` in `tox.ini`), a single one is run with
+The tox environments are named after the interpreter (`py3.11` to `py3.15`, see `envlist` in `tox.ini`), a single one is run with
 ```bash
-tox r -e py3.14
+tox r -e py3.15
 ```
 and the complete matrix, including the `ty` environment, in parallel with
 ```bash
 tox run-parallel
 ```
 
-This needs the interpreters to be available, which uv installs with `uv python install 3.11 3.12 3.13 3.14`. Continuous integration runs the same environments as `uvx --with tox-uv tox -e py3.14`.
+This needs the interpreters to be available, which uv installs with `uv python install 3.11 3.12 3.13 3.14 3.15`. Continuous integration runs the same environments as `uvx --with tox-uv tox -e py3.15`.
 
 To run the tests directly against the development environment use
 

{pymetadata-0.6.2 → pymetadata-0.6.3}/docs/installation.md

@@ -1,6 +1,6 @@
 # Installation
 
-`pymetadata` requires python >= 3.11 and is available from [pypi](https://pypi.python.org/pypi/pymetadata). It is pure python without compiled dependencies, so the installation is the same on Linux, macOS and Windows.
+`pymetadata` requires python >= 3.11 and is available from [pypi](https://pypi.python.org/pypi/pymetadata). It is pure python and tested with python 3.11 to 3.15 on Linux, macOS and Windows. The only compiled dependency is `pydantic-core`, which comes with [pydantic](https://docs.pydantic.dev/) and is installed from a wheel; for python 3.15 these wheels are part of pydantic 2.14, with an older pydantic it is built from source, which requires a Rust toolchain.
 
 ## With uv
 

{pymetadata-0.6.2 → pymetadata-0.6.3}/pyproject.toml

@@ -24,6 +24,7 @@ classifiers = [
 	"Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
 	"Programming Language :: Python :: Implementation :: CPython",
 	"Topic :: Scientific/Engineering",
 	"Topic :: Scientific/Engineering :: Bio-Informatics",
@@ -57,7 +58,7 @@ dev = [
     "tox>=4.61.2",
     "pytest>=9.1.1",
     "pytest-cov>=7.1.0",
-    "zensical>=0.0.59",
+    "zensical>=0.0.60",
     "mkdocstrings-python>=2.0.8",
 ]
 

pymetadata-0.6.3/release-notes/0.6.3.md

@@ -0,0 +1,16 @@
+# Release notes for pymetadata 0.6.3
+![pymetadata](./docs/images/favicon/pymetadata-100x100-300dpi.png)
+
+We are pleased to release the next version of pymetadata including the
+following changes:
+
+## Features
+- support for python 3.15, which is part of the test matrix and the tox environments
+
+## Fixes
+- `UnichemQuery` works with the current UniChem web service again, which changed the fields of a source (`lastChecked` and `srcLastUpdated` are new, `lastUpdated`, `srcReleaseDate` and `srcReleaseNumber` were removed). Only `sourceID` and `name` of a `UnichemSource` are required now and `UnichemSource.from_dict` ignores unknown fields, so such a change, or a cache written by an older version, no longer breaks the queries
+
+## Development
+- the development environment requires zensical 0.0.60, the version the documentation is built with
+
+Your pymetadata team

{pymetadata-0.6.2 → pymetadata-0.6.3}/src/pymetadata/__init__.py

@@ -7,7 +7,7 @@ from pathlib import Path
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 
 __author__ = "Matthias Koenig"
-__version__ = "0.6.2"
+__version__ = "0.6.3"
 
 
 program_name: str = "pymetadata"

{pymetadata-0.6.2 → pymetadata-0.6.3}/src/pymetadata/webservices/unichem.py

@@ -17,9 +17,9 @@ See <https://www.ebi.ac.uk/unichem/info/webservices>.
 import contextlib
 import logging
 import urllib.parse
-from dataclasses import dataclass, field
+from dataclasses import dataclass, field, fields
 from pathlib import Path
-from typing import ClassVar
+from typing import Any, ClassVar
 
 import pymetadata
 from pymetadata.cache import (
@@ -37,34 +37,62 @@ logger = logging.getLogger(__name__)
 
 @dataclass
 class UnichemSource:
-    """Unichem source.
-
-    src_id (the src_id for this source),
-    src_url (the main home page of the source),
-    name (the unique name for the source in UniChem, always lower case),
-    name_long (the full name of the source, as defined by the source),
-    name_label (A name for the source suitable for use as a 'label' for the source within a web-page. Correct case setting for source, and always less than 30 characters),
-    description (a description of the content of the source),
-    base_id_url_available (an flag indicating whether this source provides a valid base_id_url for creating cpd-specific links [1=yes, 0=no]).
-    base_id_url (the base url for constructing hyperlinks to this source [append an identifier from this source to the end of this url to create a valid url to a specific page for this cpd], unless aux_for_url=1),
-    aux_for_url (A flag to indicate whether the aux_src field should be used to create hyperlinks instead of the src_compound_id [1=yes, 0=no]
+    """Database known to UniChem, see the `sources` endpoint of the web service.
+
+    Only `sourceID` and `name` are required. UniChem adds and removes the
+    descriptive fields without notice, so they are optional, and
+    `UnichemSource.from_dict` ignores fields which are not declared here.
+
+    Attributes:
+        sourceID: id of the source in UniChem
+        name: unique name of the source in UniChem, always lower case
+        nameLabel: name suitable as label of the source, in the case used by
+            the source
+        nameLong: full name of the source, as defined by the source
+        srcUrl: home page of the source
+        baseIdUrl: base url for links to a compound in the source; the
+            identifier of the compound is appended or replaces `{$id}`
+        description: description of the content of the source
+        UCICount: number of UniChem compound identifiers in the source
+        created: date the source was added to UniChem
+        lastChecked: date UniChem checked the source for an update
+        srcLastUpdated: date of the last update of the source
+        srcDetails: details on the source
+        updateComments: comments on the update of the source
+        private: the source is not public
     """
 
     sourceID: int
-    srcUrl: str
     name: str
-    nameLabel: str = field(repr=False)
-    nameLong: str = field(repr=False)
-    UCICount: int = field(repr=False)
-    baseIdUrl: str = field(repr=False)
-    description: str = field(repr=False)
-    created: str = field(repr=False)
-    lastUpdated: str = field(repr=False)
-    srcDetails: str = field(repr=False)
-    srcReleaseDate: str = field(repr=False)
-    srcReleaseNumber: int = field(repr=False)
-    updateComments: str = field(repr=False)
-    private: bool = field(repr=False)
+    nameLabel: str | None = field(default=None, repr=False)
+    nameLong: str | None = field(default=None, repr=False)
+    srcUrl: str | None = None
+    baseIdUrl: str | None = field(default=None, repr=False)
+    description: str | None = field(default=None, repr=False)
+    UCICount: int | None = field(default=None, repr=False)
+    created: str | None = field(default=None, repr=False)
+    lastChecked: str | None = field(default=None, repr=False)
+    srcLastUpdated: str | None = field(default=None, repr=False)
+    srcDetails: str | None = field(default=None, repr=False)
+    updateComments: str | None = field(default=None, repr=False)
+    private: bool | None = field(default=None, repr=False)
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "UnichemSource":
+        """Create a source from a source of the web service or of the cache.
+
+        Args:
+            data: fields of the source, fields unknown to `UnichemSource` are
+                ignored
+
+        Returns:
+            The source.
+        """
+        names = {f.name for f in fields(cls)}
+        unknown = sorted(set(data) - names)
+        if unknown:
+            logger.debug("Ignored fields of UniChem source: %s", unknown)
+        return cls(**{k: v for k, v in data.items() if k in names})
 
 
 class UnichemQuery:
@@ -117,7 +145,7 @@ class UnichemQuery:
                 data = read_json_cache(
                     unichem_sources_path, max_age=CACHE_DURATION_ONTOLOGY
                 )
-                return {int(k): UnichemSource(**v) for k, v in data.items()}
+                return {int(k): UnichemSource.from_dict(v) for k, v in data.items()}
 
         url = "https://www.ebi.ac.uk/unichem/api/v1/sources/"
         try:
@@ -131,11 +159,13 @@ class UnichemQuery:
                     unichem_sources_path, reason=str(err)
                 )
                 if fallback is not None:
-                    return {int(k): UnichemSource(**v) for k, v in fallback.items()}
+                    return {
+                        int(k): UnichemSource.from_dict(v) for k, v in fallback.items()
+                    }
             raise
 
         sources_list: list[UnichemSource] = [
-            UnichemSource(**v) for v in data["sources"]
+            UnichemSource.from_dict(v) for v in data["sources"]
         ]
         sources = {source.sourceID: source for source in sources_list}
 
@@ -219,9 +249,6 @@ class UnichemQuery:
                 accession = item["src_compound_id"]
                 if source.baseIdUrl:
                     # create and clean url
-                    if not source.baseIdUrl:
-                        continue
-
                     url = f"{source.baseIdUrl}{accession}"
 
                     url_accession = urllib.parse.quote(accession)

{pymetadata-0.6.2 → pymetadata-0.6.3}/tests/test_unichem.py

@@ -8,6 +8,48 @@ import requests
 from pymetadata.webservices.unichem import UnichemQuery, UnichemSource
 
 
+def test_source_from_dict_current_fields() -> None:
+    """Test creating a source from the fields UniChem answers with."""
+    source = UnichemSource.from_dict(
+        {
+            "UCICount": 29916004,
+            "baseIdUrl": "https://www.surechembl.org/chemical/",
+            "created": None,
+            "description": "SureChEMBL extracts chemistry from patents.",
+            "lastChecked": "2026-09-15",
+            "name": "surechembl",
+            "nameLabel": "SureChEMBL",
+            "nameLong": "SureChEMBL",
+            "private": False,
+            "sourceID": 15,
+            "srcDetails": None,
+            "srcLastUpdated": "2026-09-12 00:49:52",
+            "srcUrl": "https://www.surechembl.org/",
+            "updateComments": None,
+        }
+    )
+    assert source.sourceID == 15
+    assert source.name == "surechembl"
+    assert source.baseIdUrl == "https://www.surechembl.org/chemical/"
+    assert source.lastChecked == "2026-09-15"
+    assert source.srcLastUpdated == "2026-09-12 00:49:52"
+
+
+def test_source_from_dict_schema_changes() -> None:
+    """Test that added and removed fields of UniChem do not break a source.
+
+    UniChem changed the fields of a source without notice, e.g., `lastChecked`
+    appeared and `srcReleaseNumber` disappeared.
+    """
+    source = UnichemSource.from_dict(
+        {"sourceID": 1, "name": "chembl", "srcReleaseNumber": 1, "newField": "x"}
+    )
+    assert source.sourceID == 1
+    assert source.name == "chembl"
+    assert source.baseIdUrl is None
+    assert not hasattr(source, "newField")
+
+
 def test_get_sources(tmp_path: Path) -> None:
     """Test retrieving sources."""
     cache_path: Path = tmp_path

{pymetadata-0.6.2 → pymetadata-0.6.3}/tox.ini

@@ -1,5 +1,5 @@
 [tox]
-envlist = ty, py3.{11,12,13,14}
+envlist = ty, py3.{11,12,13,14,15}
 
 [testenv]
 package = wheel