Add lazy spaCy CLI loading and static launcher

.github/workflows/cibuildwheel.yml

@@ -7,9 +7,12 @@ on:
       # ** matches 'zero or more of any character'
       - 'release-v[0-9]+.[0-9]+.[0-9]+**'
       - 'prerelease-v[0-9]+.[0-9]+.[0-9]+**'
+
+permissions: {}
+
 jobs:
   build_wheels:
-    uses: explosion/gha-cibuildwheel/.github/workflows/cibuildwheel.yml@main
+    uses: explosion/gha-cibuildwheel/.github/workflows/cibuildwheel.yml@2c98f757f13d112cf73fcf4b627249f1fffb5aae  # main
     permissions:
       contents: write
       actions: read

.github/workflows/explosionbot.yml

@@ -6,6 +6,8 @@ on:
       - created
       - edited
 
+permissions: {}
+
 jobs:
   explosion-bot:
     if: github.repository_owner == 'explosion'
@@ -15,13 +17,15 @@ jobs:
         env:
           GITHUB_CONTEXT: ${{ toJson(github) }}
         run: echo "$GITHUB_CONTEXT"
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
       - name: Install and run explosion-bot
         run: |
-          pip install git+https://${{ secrets.EXPLOSIONBOT_TOKEN }}@github.com/explosion/explosion-bot
+          git config --global url."https://x-access-token:${EXPLOSIONBOT_TOKEN}@github.com/".insteadOf "https://github.com/"
+          pip install git+https://github.com/explosion/explosion-bot
           python -m explosionbot
         env:
+          EXPLOSIONBOT_TOKEN: ${{ secrets.EXPLOSIONBOT_TOKEN }}
           INPUT_TOKEN: ${{ secrets.EXPLOSIONBOT_TOKEN }}
           INPUT_BK_TOKEN: ${{ secrets.BUILDKITE_SECRET }}
           ENABLED_COMMANDS: "test_gpu,test_slow,test_slow_gpu"

.github/workflows/issue-manager.yml

@@ -11,12 +11,16 @@ on:
     types:
       - labeled
 
+permissions: {}
+
 jobs:
   issue-manager:
+    permissions:
+      issues: write
     if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
-      - uses: tiangolo/issue-manager@0.4.0
+      - uses: tiangolo/issue-manager@4d1b7e05935a404dc8337d30bd23be46be8bb8e5  # 0.4.0
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           config: >

.github/workflows/lock.yml

@@ -16,7 +16,7 @@ jobs:
     if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
-      - uses: dessant/lock-threads@v5
+      - uses: dessant/lock-threads@1bf7ec25051fe7c00bdd17e6a7cf3d7bfb7dc771  # v5
         with:
           process-only: 'issues'
           issue-inactive-days: '30'

.github/workflows/publish_pypi.yml

@@ -8,6 +8,8 @@ on:
     types:
       - published
 
+permissions: {}
+
 jobs:
   upload_pypi:
     runs-on: ubuntu-latest
@@ -21,7 +23,7 @@ jobs:
     # or, alternatively, upload to PyPI on every tag starting with 'v' (remove on: release above to use this)
     # if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: robinraju/release-downloader@v1
+      - uses: robinraju/release-downloader@daf26c55d821e836577a15f77d86ddc078948b05  # v1
         with:
           tag: ${{ github.event.release.tag_name }}
           fileName: '*'

.github/workflows/spacy_universe_alert.yml

@@ -5,21 +5,16 @@ on:
     paths:
       - "website/meta/universe.json"
 
+permissions: {}
+
 jobs:
   build:
     if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
 
     steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-          PR_NUMBER: ${{github.event.number}}
-        run: |
-          echo "$GITHUB_CONTEXT"
-
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
         with:
           python-version: '3.10'
       - name: Install Bernadette app dependency and send an alert

.github/workflows/tests.yml

@@ -19,56 +19,47 @@ on:
       - "*.mdx"
       - "website/**"
 
+permissions: {}
+
 jobs:
   validate:
     name: Validate
     if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
       - name: Check out repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
 
       - name: Configure Python version
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
         with:
           python-version: "3.10"
 
-      - name: black
-        run: |
-          python -m pip install black -c requirements.txt
-          python -m black spacy --check
-      - name: isort
+      - name: ruff format
         run: |
-          python -m pip install isort -c requirements.txt
-          python -m isort spacy --check
-      - name: flake8
+          python -m pip install ruff -c requirements.txt
+          python -m ruff format spacy --check
+      - name: ruff isort
         run: |
-          python -m pip install flake8==5.0.4
-          python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics
-          # Unfortunately cython-lint isn't working after the shift to Cython 3.
-          #- name: cython-lint
-          #  run: |
-          #    python -m pip install cython-lint -c requirements.txt
-          #    # E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
-          #    cython-lint spacy --ignore E501,W291,E266
+          python -m ruff check spacy --select I
 
   tests:
     name: Test
     needs: Validate
     strategy:
-      fail-fast: true
+      fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python_version: ["3.10", "3.11", "3.12", "3.13"]
+        python_version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
 
     runs-on: ${{ matrix.os }}
 
     steps:
       - name: Check out repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
 
       - name: Configure Python version
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
         with:
           python-version: ${{ matrix.python_version }}
 
@@ -104,7 +95,7 @@ jobs:
         shell: bash
 
       - name: Test import
-        run: python -W error -c "import spacy"
+        run: python -W error -W 'ignore:Core Pydantic V1:UserWarning:pydantic' -c "import spacy"
 
       - name: "Test download CLI"
         run: |
@@ -165,7 +156,7 @@ jobs:
 
       - name: "Run CPU tests"
         run: |
-          python -m pytest --pyargs spacy -W error
+          python -m pytest --pyargs spacy -W error -W 'ignore:Core Pydantic V1:UserWarning:pydantic'
         if: "!(startsWith(matrix.os, 'macos') && matrix.python_version == '3.11')"
 
       - name: "Run CPU tests with thinc-apple-ops"

.github/workflows/universe_validation.yml

@@ -13,17 +13,19 @@ on:
     paths:
       - "website/meta/universe.json"
 
+permissions: {}
+
 jobs:
   validate:
     name: Validate
     if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
       - name: Check out repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
 
       - name: Configure Python version
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
         with:
           python-version: "3.7"
 

.pre-commit-config.yaml

@@ -1,13 +1,7 @@
 repos:
--   repo: https://github.com/ambv/black
-    rev: 22.3.0
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.0
     hooks:
-    - id: black
-      language_version: python3.7
-      additional_dependencies: ['click==8.0.4']
--   repo: https://github.com/pycqa/flake8
-    rev: 5.0.4
-    hooks:
-    - id: flake8
-      args:
-        - "--config=setup.cfg"
+    - id: ruff
+      args: ['--fix']
+    - id: ruff-format

MANIFEST.in

@@ -1,4 +1,5 @@
 recursive-include spacy *.pyi *.pyx *.pxd *.txt *.cfg *.jinja *.toml *.hh
+recursive-include spacy_cli *.json
 include LICENSE
 include README.md
 include pyproject.toml

lint.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+# Local lint script matching the CI Validate job + mypy type checks.
+# Fixes formatting and import sorting in-place, then re-verifies in
+# check mode to catch any conflicts between the two, and runs mypy.
+set -euo pipefail
+
+err=0
+
+echo "==> ruff format (auto-fixing)"
+python -m ruff format spacy
+
+echo "==> ruff isort (auto-fixing)"
+python -m ruff check spacy --select I --fix
+
+echo "==> ruff format (verify)"
+if ! python -m ruff format spacy --check; then
+    echo "FAIL: isort fix broke formatting"
+    err=1
+fi
+
+echo "==> ruff isort (verify)"
+if ! python -m ruff check spacy --select I; then
+    echo "FAIL: format fix broke import sorting"
+    err=1
+fi
+
+echo "==> mypy"
+if ! python -m mypy spacy; then
+    err=1
+fi
+
+if [ "$err" -ne 0 ]; then
+    echo "FAIL: see errors above"
+    exit 1
+fi
+
+echo "OK: all checks passed"

pyproject.toml

@@ -5,7 +5,7 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=8.3.4,<8.4.0",
+    "thinc>=8.3.12,<8.4.0",
     "numpy>=2.0.0,<3.0.0"
 ]
 build-backend = "setuptools.build_meta"
@@ -62,5 +62,13 @@ repair-wheel-command = "delocate-wheel --require-archs {delocate_archs} -w {dest
 [tool.cibuildwheel.pyodide]
 
 
-[tool.isort]
-profile = "black"
+[tool.ruff]
+line-length = 88
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "C", "B", "B9"]
+ignore = ["E203", "E266", "E501", "E731", "E741", "F541"]
+
+[tool.ruff.lint.isort]
+combine-as-imports = true
+split-on-trailing-comma = true

requirements.txt

@@ -3,19 +3,19 @@ spacy-legacy>=3.0.11,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
-thinc>=8.3.4,<8.4.0
-ml_datasets>=0.2.0,<0.3.0
+thinc>=8.3.12,<8.4.0
+ml_datasets>=0.2.1,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.2.0
-srsly>=2.4.3,<3.0.0
+srsly>=2.5.3,<3.0.0
 catalogue>=2.0.6,<2.1.0
-typer-slim>=0.3.0,<1.0.0
-weasel>=0.4.2,<0.5.0
+typer>=0.3.0,<1.0.0
+weasel>=1.0.0,<2.0.0
 # Third party dependencies
 numpy>=2.0.0,<3.0.0
 requests>=2.13.0,<3.0.0
 tqdm>=4.38.0,<5.0.0
-pydantic>=1.7.4,!=1.8,!=1.8.1,<3.0.0
+pydantic>=2.0.0,<3.0.0
 jinja2
 # Official Python utilities
 setuptools
@@ -26,13 +26,12 @@ cython>=3.0,<4.0
 pytest>=5.2.0,!=7.1.0
 pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
-flake8>=3.8.0,<6.0.0
 hypothesis>=3.27.0,<7.0.0
 mypy>=1.5.0,<1.6.0; platform_machine != "aarch64" and python_version >= "3.8"
 types-mock>=0.1.1
 types-setuptools>=57.0.0
 types-requests
 types-setuptools>=57.0.0
-black>=25.0.0
+ruff>=0.9.0
 cython-lint>=0.15.0
-isort>=5.0,<6.0
+confection>=1.1.0,<2.0.0