Run check-html-ids.py in CI

Author: StanFromIreland

.github/workflows/reusable-docs.yml

@@ -75,6 +75,47 @@ jobs:
           --fail-if-regression \
           --fail-if-improved \
           --fail-if-new-news-nit
+    - name: 'Collect HTML IDs'
+      run: python Doc/tools/check-html-ids.py collect Doc/build/html -o Doc/build/html-ids-head.json.gz
+    - name: 'Upload HTML IDs'
+      uses: actions/upload-artifact@v6
+      with:
+        name: html-ids-head
+        path: Doc/build/html-ids-head.json.gz
+
+  check-html-ids:
+    name: 'Check for removed HTML IDs'
+    needs: build-doc
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+    - name: 'Check out base commit'
+      uses: actions/checkout@v6
+      with:
+        persist-credentials: false
+        ref: ${{ github.event.pull_request.base.sha || github.event.before }}
+    - name: 'Set up Python'
+      uses: actions/setup-python@v6
+      with:
+        python-version: '3'
+        cache: 'pip'
+        cache-dependency-path: 'Doc/requirements.txt'
+    - name: 'Install build dependencies'
+      run: make -C Doc/ venv
+    - name: 'Build HTML documentation'
+      run: make -C Doc/ SPHINXOPTS="--quiet" html
+    - name: 'Collect HTML IDs'
+      run: python Doc/tools/check-html-ids.py collect Doc/build/html -o /tmp/html-ids-base.json.gz
+    - name: 'Download PR base HTML IDs'
+      uses: actions/download-artifact@v6
+      with:
+        name: html-ids-head
+        path: /tmp
+    - name: 'Check for removed HTML IDs'
+      run: >-
+        python Doc/tools/check-html-ids.py check
+        /tmp/html-ids-base.json.gz /tmp/html-ids-head.json.gz
+        --exclude-file Doc/tools/removed-html-ids.txt
 
   # Run "doctest" on HEAD as new syntax doesn't exist in the latest stable release
   doctest:

Doc/tools/check-html-ids.py

@@ -1,4 +1,7 @@
-from compression import gzip
+try:
+    from compression import gzip
+except ImportError:
+    import gzip
 import concurrent.futures
 from pathlib import Path
 import html.parser

Doc/tools/removed-html-ids.txt

@@ -0,0 +1 @@
+# HTML IDs excluded from the Doc/tools/check-html-ids.py check