General backend refresh (#474)

* Update pre-commit and pyproject.toml
* Compile requirements files on commit
* Remove CI checks done by pre-commit
* More migration off python 3.8
* Rename references master -> main
* Run general pyupgrade fixes

.azure-pipelines/azure-pipelines.yml

@@ -7,36 +7,6 @@ stages:
     pool:
       vmImage: ubuntu-20.04
     steps:
-      # Run syntax validation using oldest and latest Python
-      - task: UsePythonVersion@0
-        displayName: Set up python
-        inputs:
-          versionSpec: 3.8
-
-      - bash: python .azure-pipelines/syntax-validation.py
-        displayName: Syntax validation (3.7)
-
-      - task: UsePythonVersion@0
-        displayName: Set up python
-        inputs:
-          versionSpec: 3.11
-
-      - bash: python .azure-pipelines/syntax-validation.py
-        displayName: Syntax validation (3.10)
-
-      - bash: |
-          set -eux
-          pip install --disable-pip-version-check ruff
-          python .azure-pipelines/ruff-validation.py
-        displayName: Ruff validation
-
-      - bash: |
-          set -eux
-          # install versions matching the ones in the corresponding pre-commit hook
-          pip install --disable-pip-version-check mypy==1.9.0 types-PyYAML==6.0.12 types-requests==2.31.0
-          mypy --no-strict-optional dials_data/
-        displayName: Type checking
-
       # Set up constants for further build steps
       - bash: |
           echo "##vso[task.setvariable variable=BUILD_REPOSITORY_NAME;isOutput=true]${BUILD_REPOSITORY_NAME}"
@@ -157,44 +127,47 @@ stages:
       vmImage: ubuntu-20.04
     strategy:
       matrix:
-        python38:
-          PYTHON_VERSION: 3.8
         python39:
           PYTHON_VERSION: 3.9
         python310:
           PYTHON_VERSION: 3.10
         python311:
           PYTHON_VERSION: 3.11
+        python312:
+          PYTHON_VERSION: 3.12
+
     steps:
     - template: ci.yml
   - job: macOS
     pool:
       vmImage: macOS-latest
     strategy:
       matrix:
-        python38:
-          PYTHON_VERSION: 3.8
         python39:
           PYTHON_VERSION: 3.9
         python310:
           PYTHON_VERSION: 3.10
         python311:
           PYTHON_VERSION: 3.11
+        python312:
+          PYTHON_VERSION: 3.12
+
     steps:
     - template: ci.yml
   - job: windows
     pool:
       vmImage: windows-latest
     strategy:
       matrix:
-        python38:
-          PYTHON_VERSION: 3.8
         python39:
           PYTHON_VERSION: 3.9
         python310:
           PYTHON_VERSION: 3.10
         python311:
           PYTHON_VERSION: 3.11
+        python312:
+          PYTHON_VERSION: 3.12
+
     steps:
     - template: ci-windows.yml
 
@@ -205,7 +178,7 @@ stages:
   - tests
   condition: and(succeeded(),
                  eq(dependencies.static.outputs['checks.constants.BUILD_REPOSITORY_NAME'], 'dials/data'),
-                 eq(dependencies.static.outputs['checks.constants.BUILD_SOURCEBRANCH'], 'refs/heads/master'))
+                 eq(dependencies.static.outputs['checks.constants.BUILD_SOURCEBRANCH'], 'refs/heads/main'))
   jobs:
   - job: pypi
     displayName: Publish pypi release
@@ -247,7 +220,7 @@ stages:
   - build
   - tests
   condition: and(succeeded(),
-                 eq(dependencies.static.outputs['checks.constants.BUILD_SOURCEBRANCH'], 'refs/heads/master'),
+                 eq(dependencies.static.outputs['checks.constants.BUILD_SOURCEBRANCH'], 'refs/heads/main'),
                  eq(dependencies.static.outputs['checks.constants.BUILD_REPOSITORY_NAME'], 'dials/data'))
              # only run this job in the main branch of the main repository
   jobs:

.azure-pipelines/create-hashinfo-pull-requests

@@ -17,7 +17,7 @@ echo
 
 echo "##[section]Open pull requests:"
 declare -A UPDATEBRANCHES
-for BRANCH in $(hub pr list -b master -f '%H%n'); do
+for BRANCH in $(hub pr list -b main -f '%H%n'); do
   echo ${BRANCH}
   UPDATEBRANCHES[${BRANCH}]=1
 done

.codecov.yml

@@ -12,5 +12,5 @@ coverage:
 comment:
   layout: "diff, flags"
   branches:
-    - master
+    - main
   after_n_builds: 3

.github/workflows/codeql.yml

@@ -2,9 +2,9 @@ name: "CodeQL"
 
 on:
   push:
-    branches: [ "master" ]
+    branches: ["main"]
   pull_request:
-    branches: [ "master" ]
+    branches: ["main"]
   schedule:
     - cron: "22 2 * * 3"
 
@@ -20,7 +20,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        language: [ javascript, python ]
+        language: [javascript, python]
 
     steps:
       - name: Checkout

.pre-commit-config.yaml

@@ -1,7 +1,11 @@
+ci:
+  autoupdate_schedule: quarterly
+  skip: [pip-compile]
+
 repos:
 # Syntax validation and some basic sanity checks
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.5.0
+  rev: v5.0.0
   hooks:
   - id: check-merge-conflict
   - id: check-ast
@@ -12,8 +16,8 @@ repos:
   - id: check-yaml
 
 # Linting, sorting and formatting
-- repo: https://github.com/charliermarsh/ruff-pre-commit
-  rev: v0.3.3
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.7.2
   hooks:
     - id: ruff
       args: [--fix, --exit-non-zero-on-fix]
@@ -23,8 +27,21 @@ repos:
 # Remember to change versions in .azure-pipelines/azure-pipelines.yml to match
 # the versions here.
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v1.9.0
+  rev: v1.13.0
   hooks:
   - id: mypy
     files: 'dials_data/.*\.py$'
     additional_dependencies: ['types-PyYAML==6.0.12', 'types-requests==2.31.0']
+
+- repo: https://github.com/astral-sh/uv-pre-commit
+  rev: 0.4.30
+  hooks:
+    - id: pip-compile
+      args: [pyproject.toml, -q, -o, requirements.txt]
+      files: ^(pyproject.toml|requirements(_dev|_doc)?.txt)$
+    - id: pip-compile
+      args: [pyproject.toml, -q, --extra, test, -o, requirements_dev.txt]
+      files: ^(pyproject.toml|requirements(_dev|_doc)?.txt)$
+    - id: pip-compile
+      args: [pyproject.toml, -q, --extra, doc, -o, requirements_doc.txt]
+      files: ^(pyproject.toml|requirements(_dev|_doc)?.txt)$

dials_data/cli.py

@@ -119,7 +119,7 @@ def main():
         version = dials_data.__version__ + "-dev"
     parser = argparse.ArgumentParser(
         usage="dials.data <command> [<args>]",
-        description="""DIALS regression data manager v{version}
+        description=f"""DIALS regression data manager v{version}
 
 The most commonly used commands are:
    list     List available datasets
@@ -128,7 +128,7 @@ def main():
 Each command has its own set of parameters, and you can get more information
 by running dials.data <command> --help
 
-""".format(version=version),
+""",
         formatter_class=argparse.RawTextHelpFormatter,
     )
     parser.add_argument("subcommand", help=argparse.SUPPRESS)

dials_data/datasets.py

@@ -134,11 +134,7 @@ def list_known_definitions(ds_list, quiet=False) -> None:
             size_information = "unverified dataset"
         else:
             size_information = _human_readable(get_resident_size(shortname))
-        print(
-            "{shortname}: {dataset[name]} ({size_information})".format(
-                shortname=shortname, dataset=dataset, size_information=size_information
-            )
-        )
+        print(f"{shortname}: {dataset['name']} ({size_information})")
         print(
             "{indent}{author} ({license})".format(
                 author=dataset.get("author", "unknown author"),
@@ -147,7 +143,7 @@ def list_known_definitions(ds_list, quiet=False) -> None:
             )
         )
         if dataset.get("url"):
-            print("{indent}{dataset[url]}".format(indent=indent, dataset=dataset))
+            print(f"{indent}{dataset['url']}")
         print(
             "\n{}\n".format(
                 textwrap.fill(

dials_data/download.py

@@ -10,7 +10,7 @@
 import warnings
 import zipfile
 from pathlib import Path
-from typing import Any, Optional, Union
+from typing import Any
 from urllib.parse import urlparse
 
 import py.path
@@ -104,7 +104,7 @@ def fetch_dataset(
     read_only: bool = False,
     verbose: bool = False,
     pre_scan: bool = True,
-) -> Union[bool, dict[str, Any]]:
+) -> bool | dict[str, Any]:
     """Check for the presence or integrity of the local copy of the specified
     test dataset. If the dataset is not available or out of date then attempt
     to download/update it transparently.
@@ -280,7 +280,7 @@ class DataFetcher:
     """
 
     def __init__(self, read_only: bool = False, verify: bool = True):
-        self._cache: dict[str, Optional[Path]] = {}
+        self._cache: dict[str, Path | None] = {}
         self._target_dir: Path = dials_data.datasets.repository_location()
         self._read_only: bool = read_only and os.access(self._target_dir, os.W_OK)
         self._verify: bool = verify
@@ -332,7 +332,7 @@ def __call__(self, test_data: str, pathlib=None, **kwargs):
             return self.result_filter(result=py.path.local(self._cache[test_data]))
         return self.result_filter(result=self._cache[test_data])
 
-    def _attempt_fetch(self, test_data: str) -> Optional[Path]:
+    def _attempt_fetch(self, test_data: str) -> Path | None:
         if self._read_only:
             hashinfo = fetch_dataset(test_data, pre_scan=True, read_only=True)
         else: