chore: import upstream snapshot with attribution

.github/workflows/cibuildwheel.yml

@@ -0,0 +1,107 @@
+name: Build
+
+on:
+  push:
+    tags:
+      # ytf did they invent their own syntax that's almost regex?
+      # ** 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@2c98f757f13d112cf73fcf4b627249f1fffb5aae  # main
+    permissions:
+      contents: write
+      actions: read
+    with:
+      wheel-name-pattern: "spacy-*.whl"
+      pure-python: false
+    secrets:
+      gh-token: ${{ secrets.GITHUB_TOKEN }}
+
+  smoke_test:
+    name: Smoke test
+    needs: build_wheels
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+        with:
+          python-version: "3.12"
+
+      - uses: robinraju/release-downloader@daf26c55d821e836577a15f77d86ddc078948b05  # v1
+        with:
+          tag: ${{ github.ref_name }}
+          fileName: "spacy-*cp312*manylinux*x86_64*.whl"
+          out-file-path: "dist"
+
+      - name: Install from wheel
+        run: |
+          WHEEL=$(ls dist/spacy-*cp312*manylinux*x86_64*.whl | head -1)
+          pip install "$WHEEL"
+
+      - name: Test import
+        run: python -c "import spacy; print('spacy==' + spacy.__version__)"
+
+      - name: Download and load model
+        run: |
+          python -m spacy download en_core_web_sm
+          python -c "
+          import spacy
+          nlp = spacy.load('en_core_web_sm')
+          doc = nlp('Apple is looking at buying U.K. startup for \$1 billion')
+          assert len(doc.ents) > 0, 'No entities found'
+          print('Model load OK:', nlp.meta['name'], '@', nlp.meta['version'])
+          print('Entities:', [(ent.text, ent.label_) for ent in doc.ents])
+          "
+
+  upgrade_test:
+    name: Upgrade test
+    needs: build_wheels
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+        with:
+          python-version: "3.12"
+
+      - name: Install previous spaCy version
+        run: |
+          pip install "spacy>=3.8.0,<${{ github.ref_name }}" || pip install "spacy<4"
+          python -m spacy download en_core_web_sm
+          python -c "
+          import spacy
+          nlp = spacy.load('en_core_web_sm')
+          print('Pre-upgrade:', spacy.__version__, nlp.meta['name'], '@', nlp.meta['version'])
+          "
+
+      - uses: robinraju/release-downloader@daf26c55d821e836577a15f77d86ddc078948b05  # v1
+        with:
+          tag: ${{ github.ref_name }}
+          fileName: "spacy-*cp312*manylinux*x86_64*.whl"
+          out-file-path: "dist"
+
+      - name: Upgrade to new version
+        run: |
+          WHEEL=$(ls dist/spacy-*cp312*manylinux*x86_64*.whl | head -1)
+          pip install "$WHEEL"
+
+      - name: Test model still loads after upgrade
+        run: |
+          python -c "
+          import spacy
+          nlp = spacy.load('en_core_web_sm')
+          doc = nlp('Apple is looking at buying U.K. startup for \$1 billion')
+          assert len(doc.ents) > 0, 'No entities found after upgrade'
+          print('Post-upgrade:', spacy.__version__, nlp.meta['name'], '@', nlp.meta['version'])
+          print('Entities:', [(ent.text, ent.label_) for ent in doc.ents])
+          "

.github/workflows/explosionbot.yml

@@ -0,0 +1,32 @@
+name: Explosion Bot
+
+on:
+  issue_comment:
+    types:
+      - created
+      - edited
+
+permissions: {}
+
+jobs:
+  explosion-bot:
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Dump GitHub context
+        env:
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+        run: echo "$GITHUB_CONTEXT"
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
+      - name: Install and run explosion-bot
+        run: |
+          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"
+          ALLOWED_TEAMS: "spaCy"

.github/workflows/gputests.yml.disabled

@@ -0,0 +1,22 @@
+name: Weekly GPU tests
+
+on:
+  schedule:
+    - cron: '0 1 * * MON'
+
+jobs:
+  weekly-gputests:
+    strategy:
+      fail-fast: false
+      matrix:
+        branch: [master, v4]
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger buildkite build
+        uses: buildkite/trigger-pipeline-action@v1.2.0
+        env:
+          PIPELINE: explosion-ai/spacy-slow-gpu-tests
+          BRANCH: ${{ matrix.branch }}
+          MESSAGE: ":github: Weekly GPU + slow tests - triggered from a GitHub Action"
+          BUILDKITE_API_ACCESS_TOKEN: ${{ secrets.BUILDKITE_SECRET }}

.github/workflows/issue-manager.yml

@@ -0,0 +1,40 @@
+name: Issue Manager
+
+on:
+  schedule:
+    - cron: "0 0 * * *"
+  issue_comment:
+    types:
+      - created
+      - edited
+  issues:
+    types:
+      - labeled
+
+permissions: {}
+
+jobs:
+  issue-manager:
+    permissions:
+      issues: write
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: tiangolo/issue-manager@4d1b7e05935a404dc8337d30bd23be46be8bb8e5  # 0.4.0
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          config: >
+            {
+              "resolved": {
+                "delay": "P7D",
+                "message": "This issue has been automatically closed because it was answered and there was no follow-up discussion.",
+                "remove_label_on_comment": true,
+                "remove_label_on_close": true
+              },
+              "more-info-needed": {
+                "delay": "P7D",
+                "message": "This issue has been automatically closed because there has been no response to a request for more information from the original author. With only the information that is currently in the issue, there's not enough information to take action. If you're the original author, feel free to reopen the issue if you have or find the answers needed to investigate further.",
+                "remove_label_on_comment": true,
+                "remove_label_on_close": true
+              }
+            }

.github/workflows/lock.yml

@@ -0,0 +1,26 @@
+name: 'Lock Threads'
+
+on:
+  schedule:
+    - cron: '0 0 * * *'  # check every day
+  workflow_dispatch:
+
+permissions:
+  issues: write
+
+concurrency:
+  group: lock
+
+jobs:
+  action:
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: dessant/lock-threads@1bf7ec25051fe7c00bdd17e6a7cf3d7bfb7dc771  # v5
+        with:
+          process-only: 'issues'
+          issue-inactive-days: '30'
+          issue-comment: >
+            This thread has been automatically locked since there
+            has not been any recent activity after it was closed.
+            Please open a new issue for related bugs.

.github/workflows/publish_pypi.yml

@@ -0,0 +1,31 @@
+# The cibuildwheel action triggers on creation of a release, this
+# triggers on publication.
+# The expected workflow is to create a draft release and let the wheels
+# upload, and then hit 'publish', which uploads to PyPi.
+
+on:
+  release:
+    types:
+      - published
+
+permissions: {}
+
+jobs:
+  upload_pypi:
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/spacy
+    permissions:
+      id-token: write
+      contents: read
+    if: github.event_name == 'release' && github.event.action == 'published'
+    # 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@daf26c55d821e836577a15f77d86ddc078948b05  # v1
+        with:
+          tag: ${{ github.event.release.tag_name }}
+          fileName: '*'
+          out-file-path: 'dist'
+      - uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1

.github/workflows/slowtests.yml.disabled

@@ -0,0 +1,38 @@
+name: Daily slow tests
+
+on:
+  schedule:
+    - cron: '0 0 * * *'
+
+jobs:
+  daily-slowtests:
+    strategy:
+      fail-fast: false
+      matrix:
+        branch: [master, v4]
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ matrix.branch }}
+      - name: Get commits from past 24 hours
+        id: check_commits
+        run: |
+          today=$(date '+%Y-%m-%d %H:%M:%S')
+          yesterday=$(date -d "yesterday" '+%Y-%m-%d %H:%M:%S')
+          if git log --after="$yesterday" --before="$today" | grep commit ; then
+            echo run_tests=true >> $GITHUB_OUTPUT
+          else
+            echo run_tests=false >> $GITHUB_OUTPUT
+          fi
+
+      - name: Trigger buildkite build
+        if: steps.check_commits.outputs.run_tests == 'true'
+        uses: buildkite/trigger-pipeline-action@v1.2.0
+        env:
+          PIPELINE: explosion-ai/spacy-slow-tests
+          BRANCH: ${{ matrix.branch }}
+          MESSAGE: ":github: Daily slow tests - triggered from a GitHub Action"
+          BUILDKITE_API_ACCESS_TOKEN: ${{ secrets.BUILDKITE_SECRET }}

.github/workflows/spacy_universe_alert.yml

@@ -0,0 +1,28 @@
+name: spaCy universe project alert
+
+on:
+  pull_request_target:
+    paths:
+      - "website/meta/universe.json"
+
+permissions: {}
+
+jobs:
+  build:
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+
+    steps:
+      - 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
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+          CHANNEL: "#alerts-universe"
+        run: |
+          pip install slack-sdk==3.17.2 aiohttp==3.8.1
+          echo "$CHANNEL"
+          echo "$GITHUB_CONTEXT" | python .github/spacy_universe_alert.py

.github/workflows/tests.yml

@@ -0,0 +1,167 @@
+name: tests
+
+on:
+  push:
+    tags-ignore:
+      - '**'
+    branches-ignore:
+      - "spacy.io"
+      - "nightly.spacy.io"
+      - "v2.spacy.io"
+    paths-ignore:
+      - "*.md"
+      - "*.mdx"
+      - "website/**"
+  pull_request:
+    types: [opened, synchronize, reopened, edited]
+    paths-ignore:
+      - "*.md"
+      - "*.mdx"
+      - "website/**"
+
+permissions:
+  contents: read
+
+jobs:
+  validate:
+    name: Validate
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
+
+      - name: Configure Python version
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
+        with:
+          python-version: "3.10"
+
+      - name: ruff format
+        run: |
+          python -m pip install ruff -c requirements.txt
+          python -m ruff format spacy --check
+      - name: ruff isort
+        run: |
+          python -m ruff check spacy --select I
+
+  tests:
+    name: Test
+    needs: Validate
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python_version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
+
+      - name: Configure Python version
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
+        with:
+          python-version: ${{ matrix.python_version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install -U build pip setuptools
+          python -m pip install -U -r requirements.txt
+
+      - name: Build sdist
+        run: |
+          python -m build --sdist
+
+      - name: Run mypy
+        run: |
+          python -m mypy spacy
+        if: matrix.python_version != '3.7'
+
+      - name: Delete source directory and .egg-info
+        run: |
+          rm -rf spacy *.egg-info
+        shell: bash
+
+      - name: Uninstall all packages
+        run: |
+          python -m pip freeze
+          python -m pip freeze --exclude pywin32 > installed.txt
+          python -m pip uninstall -y -r installed.txt
+
+      - name: Install from sdist
+        run: |
+          SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
+          SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST
+        shell: bash
+
+      - name: Test import
+        run: python -W error -W 'ignore:Core Pydantic V1:UserWarning:pydantic' -c "import spacy"
+
+      - name: "Test download CLI"
+        run: |
+          python -m spacy download ca_core_news_sm
+          python -m spacy download ca_core_news_md
+          python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
+        if: matrix.python_version == '3.9'
+
+      - name: "Test download_url in info CLI"
+        run: |
+          python -W error -m spacy info ca_core_news_sm | grep -q download_url
+        if: matrix.python_version == '3.9'
+
+      - name: "Test no warnings on load (#11713)"
+        run: |
+          python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
+        if: matrix.python_version == '3.9'
+
+      - name: "Test convert CLI"
+        run: |
+          python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
+        if: matrix.python_version == '3.9'
+
+      - name: "Test debug config CLI"
+        run: |
+          python -m spacy init config -p ner -l ca ner.cfg
+          python -m spacy debug config ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy
+        if: matrix.python_version == '3.9'
+
+      - name: "Test debug data CLI"
+        run: |
+          # will have errors due to sparse data, check for summary in output
+          python -m spacy debug data ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy | grep -q Summary
+        if: matrix.python_version == '3.9'
+
+      - name: "Test train CLI"
+        run: |
+          python -m spacy train ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy --training.max_steps 10 --gpu-id -1
+        if: matrix.python_version == '3.9'
+
+      - name: "Test assemble CLI"
+        run: |
+          python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
+          python -m spacy assemble ner_source_sm.cfg output_dir
+        env:
+          PYTHONWARNINGS: "error,ignore::DeprecationWarning" 
+        if: matrix.python_version == '3.9'
+
+      - name: "Test assemble CLI vectors warning"
+        run: |
+          python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
+          python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
+        if: matrix.python_version == '3.9'
+
+      - name: "Install test requirements"
+        run: |
+          python -m pip install -U -r requirements.txt
+
+      - name: "Run CPU tests"
+        run: |
+          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"
+        run: |
+          python -m pip install 'spacy[apple]'
+          python -m pytest --pyargs spacy
+        if: startsWith(matrix.os, 'macos') && matrix.python_version == '3.11'

.github/workflows/universe_validation.yml

@@ -0,0 +1,35 @@
+name: universe validation
+
+on:
+  push:
+    branches-ignore:
+      - "spacy.io"
+      - "nightly.spacy.io"
+      - "v2.spacy.io"
+    paths:
+      - "website/meta/universe.json"
+  pull_request:
+    types: [opened, synchronize, reopened, edited]
+    paths:
+      - "website/meta/universe.json"
+
+permissions:
+  contents: read
+
+jobs:
+  validate:
+    name: Validate
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6
+
+      - name: Configure Python version
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
+        with:
+          python-version: "3.7"
+
+      - name: Validate website/meta/universe.json
+        run: |
+          python .github/validate_universe_json.py website/meta/universe.json