Merge branch 'master' into readme-updates-1

biopragmatics · Dec 18, 2024 · d1e0993 · d1e0993
2 parents 6b3da3f + 1a03dc7
commit d1e0993
Show file tree

Hide file tree

Showing 18 changed files with 119 additions and 78 deletions.
diff --git a/.cruft.json b/.cruft.json
@@ -1,13 +1,14 @@
 {
   "template": "https://github.com/cthoyt/cookiecutter-snekpack",
-  "commit": "12edfcfa5f519467b5d834f0d4e706fb7cf4f065",
+  "commit": "d6ac604ce8428ddaaae55d372beef2621caed513",
   "checkout": null,
   "context": {
     "cookiecutter": {
       "package_name": "biomappings",
       "package_name_stylized": "Biomappings",
       "short_description": "Curated and predicted mappings between biomedical identifiers in different namespaces",
       "author_name": "Charles Tapley Hoyt",
+      "author_github": "cthoyt",
       "author_email": "[email protected]",
       "github_organization_name": "biopragmatics",
       "github_repository_name": "biomappings",

diff --git a/.github/FUNDING.yml b/.github/FUNDING.yml
@@ -0,0 +1,3 @@
+# https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/displaying-a-sponsor-button-in-your-repository
+github:
+  - cthoyt
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1,17 @@
+<!--
+Thanks for contributing to `biomappings`.
+To help us out with reviewing, please consider the following:
+
+- Does this pull request include a summary of the change? (See below.)
+- Does this pull request include a descriptive title?
+- Does this pull request include references to any relevant issues?
+
+Caution: the maintainers often take an active role in pull requests,
+and may push to your branch. Therefore, you should always sync your
+local copy of the repository with the remote before continuing your
+work.
+-->
+
+## Summary
+
+<!-- What's the purpose of the change? What does it do, and why? -->
diff --git a/.github/workflows/cruft.yml b/.github/workflows/cruft.yml
@@ -2,9 +2,7 @@
 
 name: Update repository with Cruft
 
-permissions:
-  contents: write
-  pull-requests: write
+permissions: {}
 
 on:
   workflow_dispatch:
@@ -13,6 +11,9 @@ on:
 
 jobs:
   update:
+    permissions:
+      contents: write
+      pull-requests: write
     runs-on: ubuntu-latest
     strategy:
       fail-fast: true

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -4,6 +4,10 @@
 
 name: Tests
 
+# by default, give the GITHUB_TOKEN no permissions
+# See https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/controlling-permissions-for-github_token
+permissions: {}
+
 on:
   push:
     branches: [ master ]
@@ -13,11 +17,16 @@ on:
 jobs:
   lint:
     name: Code Quality
+    permissions:
+      # give only read-only access to the contents of the repository
+      # this is the only permission this job requires, so keep it to the least privilege
+      # i.e., not to issues, discussions, actions, etc.
+      contents: read
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: [ "3.12", "3.9" ]
-        tox-command: ["manifest", "lint", "pyroma", "mypy"]
+        tox-command: ["lint", "pyroma", "mypy"]
     steps:
       - uses: actions/checkout@v4
       - name: "Install uv"
@@ -31,6 +40,8 @@ jobs:
 
   docs:
     name: Documentation
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -56,6 +67,8 @@ jobs:
         run: uvx -p ${{ matrix.python-version }} --with tox-uv tox -e docs-test
   tests:
     name: Tests
+    permissions:
+      contents: read
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:

diff --git a/README.md b/README.md
@@ -376,7 +376,7 @@ You only have to do the following steps once.
 
 #### Configuring your machine's connection to PyPI
 
-You have to do the following steps once per machine. 
+You have to do the following steps once per machine.
 
 ```console
 $ uv tool install keyring

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,7 +1,8 @@
-# See https://setuptools.readthedocs.io/en/latest/build_meta.html
 [build-system]
-requires = ["setuptools", "wheel"]
-build-backend = "setuptools.build_meta"
+requires = ["uv>=0.5.10,<0.6.0"]
+# The uv backend entered preview mode in https://github.com/astral-sh/uv/pull/8886/files
+# with the 0.5.0 release. See also https://github.com/astral-sh/uv/issues/3957 for tracking.
+build-backend = "uv"
 
 [project]
 name = "biomappings"
@@ -26,12 +27,15 @@ classifiers = [
     "Framework :: Pytest",
     "Framework :: tox",
     "Framework :: Sphinx",
+    "Natural Language :: English",
     "Programming Language :: Python",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3 :: Only",
+    "Typing :: Typed",
     "Topic :: Scientific/Engineering :: Chemistry",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
 ]
@@ -45,10 +49,11 @@ keywords = [
     "nlp",
 ]
 
-# License Information. This can be any valid SPDX identifiers that can be resolved
-# with URLs like https://spdx.org/licenses/MIT
-# See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license
-license = { file = "LICENSE" }
+# License Information.
+# See PEP-639 at https://peps.python.org/pep-0639/#add-license-files-key
+license-files = [
+    "LICENSE",
+]
 
 requires-python = ">=3.9"
 dependencies = [
@@ -64,7 +69,7 @@ dependencies = [
 [project.optional-dependencies]
 tests = [
     "pytest",
-    "coverage",
+    "coverage[toml]",
 ]
 docs = [
     "sphinx>=8",
@@ -99,28 +104,17 @@ exports = [
 ]
 
 # 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/
 [project.urls]
 "Bug Tracker" = "https://github.com/biopragmatics/biomappings/issues"
 Homepage = "https://github.com/biopragmatics/biomappings"
 Repository = "https://github.com/biopragmatics/biomappings.git"
 Documentation = "https://biomappings.readthedocs.io"
-
-[tool.setuptools]
-package-dir = { "" = "src" }
-
-[tool.setuptools.packages.find]
-# this implicitly sets `packages = ":find"`
-where = ["src"]  # list of folders that contain the packages (["."] by default)
-
-# See https://setuptools.pypa.io/en/latest/userguide/datafiles.html
-[tool.setuptools.package-data]
-"*" = ["*.*"]
-
+Funding = "https://github.com/sponsors/"
 
 [project.scripts]
 biomappings = "biomappings.cli:main"
 
-
 [tool.cruft]
 skip = [
     "**/__init__.py",

diff --git a/scripts/generate_chebi_mesh_mappings.py b/scripts/generate_chebi_mesh_mappings.py
@@ -26,7 +26,7 @@
             continue
         mesh_chebi_simple.append(mesh_chebi_pair)
 
-    print("Found %d CHEBI-MESH mappings." % len(mesh_chebi_simple))
+    print(f"Found {len(mesh_chebi_simple)} CHEBI-MESH mappings.")
 
     predictions = []
     n_redundant = 0
@@ -53,7 +53,7 @@
         predictions.append(pred)
 
     print(
-        "A total of %d mappings could be indirectly inferred from"
-        "INDRA ontology xrefs" % len(n_redundant)
+        f"A total of {n_redundant} mappings could be indirectly inferred from"
+        "INDRA ontology xrefs"
     )
     append_prediction_tuples(predictions, deduplicate=True, sort=True)
diff --git a/scripts/generate_cl_mesh_mappings.py b/scripts/generate_cl_mesh_mappings.py
@@ -49,7 +49,7 @@
         mappings[node] = mesh_id
 
 
-print("Found %d CL->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} CL->MESH mappings.")
 
 predictions = []
 for cl_id, mesh_id in mappings.items():

diff --git a/scripts/generate_doid_mesh_mappings.py b/scripts/generate_doid_mesh_mappings.py
@@ -57,7 +57,7 @@
                 mappings[node] = matches[0].term.id
 
 
-print("Found %d DOID->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} DOID->MESH mappings.")
 
 # We makes sure that (i) the node is not already mappable to MESH and that
 # (ii) there isn't some other node that was not already mapped to the
@@ -73,7 +73,7 @@
 cnt = Counter(mappings.values())
 mappings = {k: v for k, v in mappings.items() if cnt[v] == 1}
 
-print("Found %d filtered DOID->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} filtered DOID->MESH mappings.")
 
 # We can now add the predictions
 predictions = []

diff --git a/scripts/generate_hp_mesh_mappings.py b/scripts/generate_hp_mesh_mappings.py
@@ -66,7 +66,7 @@
             if grounding[0] == "MESH":
                 mappings[node] = matches[0].term.id
 
-print("Found %d HP->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} HP->MESH mappings.")
 
 # We makes sure that (i) the node is not already mappable to MESH and that
 # (ii) there isn't some other node that was not already mapped to the
@@ -82,7 +82,7 @@
 cnt = Counter(mappings.values())
 mappings = {k: v for k, v in mappings.items() if cnt[v] == 1}
 
-print("Found %d filtered HP->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} filtered HP->MESH mappings.")
 
 # We can now add the predictions
 predictions = []

diff --git a/scripts/generate_mondo_mesh_mappings.py b/scripts/generate_mondo_mesh_mappings.py
@@ -42,7 +42,7 @@
                 mappings[node] = matches[0].term.id
 
 
-print("Found %d MONDO->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} MONDO->MESH mappings.")
 
 mappings = {
     k: v
@@ -54,7 +54,7 @@
 
 mappings = {k: v for k, v in mappings.items() if cnt[v] == 1}
 
-print("Found %d MONDO->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} MONDO->MESH mappings.")
 
 predictions = []
 for mondo_id, mesh_id in mappings.items():

diff --git a/scripts/generate_uberon_mesh_mappings.py b/scripts/generate_uberon_mesh_mappings.py
@@ -19,7 +19,7 @@
     if matches and matches[0].term.db == "MESH":
         mappings[node] = matches[0].term.id
 
-print("Found %d UBERON->MESH mappings." % len(mappings))
+print(f"Found {len(mappings)} UBERON->MESH mappings.")
 
 predictions = []
 for uberon_id, mesh_id in mappings.items():

diff --git a/src/biomappings/gilda_utils.py b/src/biomappings/gilda_utils.py
@@ -16,10 +16,10 @@
 
 __all__ = [
     "append_gilda_predictions",
-    "iter_prediction_tuples",
     "filter_custom",
     "filter_existing_xrefs",
     "has_mapping",
+    "iter_prediction_tuples",
 ]
 
 logger = logging.getLogger(__name__)

diff --git a/src/biomappings/paper_analysis.py b/src/biomappings/paper_analysis.py
@@ -18,9 +18,9 @@
 
 __all__ = [
     "Result",
-    "get_primary_mappings",
-    "get_obo_mappings",
     "get_non_obo_mappings",
+    "get_obo_mappings",
+    "get_primary_mappings",
     "index_mappings",
 ]
 

diff --git a/src/biomappings/resources/__init__.py b/src/biomappings/resources/__init__.py
@@ -15,31 +15,31 @@
 from biomappings.utils import OVERRIDE_MIRIAM, RESOURCE_PATH, get_canonical_tuple
 
 __all__ = [
-    "MappingTuple",
     "MAPPINGS_HEADER",
-    "PredictionTuple",
     "PREDICTIONS_HEADER",
+    "MappingTuple",
     "Mappings",
-    "load_mappings",
-    "load_mappings_subset",
-    "append_true_mappings",
-    "append_true_mapping_tuples",
-    "write_true_mappings",
-    "load_false_mappings",
+    "PredictionTuple",
     "append_false_mappings",
-    "write_false_mappings",
-    "load_unsure",
-    "append_unsure_mappings",
-    "write_unsure_mappings",
-    "load_predictions",
-    "append_predictions",
     "append_prediction_tuples",
-    "write_predictions",
-    "remove_mappings",
-    "load_curators",
+    "append_predictions",
+    "append_true_mapping_tuples",
+    "append_true_mappings",
+    "append_unsure_mappings",
     "filter_predictions",
     "get_curated_filter",
+    "load_curators",
+    "load_false_mappings",
+    "load_mappings",
+    "load_mappings_subset",
+    "load_predictions",
+    "load_unsure",
     "prediction_tuples_from_semra",
+    "remove_mappings",
+    "write_false_mappings",
+    "write_predictions",
+    "write_true_mappings",
+    "write_unsure_mappings",
 ]
 
 logger = logging.getLogger(__name__)

diff --git a/src/biomappings/utils.py b/src/biomappings/utils.py
@@ -10,17 +10,17 @@
 import bioregistry
 
 __all__ = [
-    "get_git_hash",
-    "get_script_url",
-    "get_canonical_tuple",
-    "UnregisteredPrefix",
-    "UnstandardizedPrefix",
+    "CMapping",
     "InvalidIdentifier",
-    "InvalidNormIdentifier",
     "InvalidIdentifierPattern",
+    "InvalidNormIdentifier",
+    "UnregisteredPrefix",
+    "UnstandardizedPrefix",
     "check_valid_prefix_id",
+    "get_canonical_tuple",
     "get_curie",
-    "CMapping",
+    "get_git_hash",
+    "get_script_url",
 ]
 
 HERE = Path(__file__).parent.resolve()