Fixed sitemap URLs (#495)

* Corrected sitemap URLs

* Wrote sitemap checker script.

* Revert "Corrected sitemap URLs"

This reverts commit 69c732a.

* Add sitemap check to CI.

* Removed old GHA dependency.

* Fixed path to script.

* Moved sitemap test to build step.

* Added debugging info.

* More debugging.

* Fixed path issue.

* Corrected sitemap URLs

.github/scripts/check_sitemap.py

@@ -0,0 +1,31 @@
+import xml.etree.ElementTree as ET
+import urllib.request
+
+NS = {"a": "http://www.sitemaps.org/schemas/sitemap/0.9"}
+TOLERANCE = 0.8
+
+
+def discover_urls():
+    tree = ET.parse("doc/build/html/sitemap.xml")
+    root = tree.getroot()
+    return [node.find("a:loc", NS).text for node in root.findall("a:url", NS)]
+
+
+def test_urls(urls):
+    passed = 0
+    for url in urls:
+        code = 404
+        try:
+            code = urllib.request.urlopen(url).getcode()
+        except urllib.error.HTTPError as e:
+            print(url, e)
+        if code == 200:
+            passed += 1
+        else:
+            print(url, code)
+    if passed / len(urls) < TOLERANCE:
+        raise ValueError(f"Too many URLs failed")
+
+
+if __name__ == "__main__":
+    test_urls(discover_urls())

.github/workflows/main.yml

@@ -101,13 +101,7 @@ jobs:
         with: 
           python-version: 3.12
       - run: pip install . montepy[doc,build]
-      - uses: mathieudutour/github-tag-action@v6.2
-        name: Get next version number
-        id: version_num
-        with: 
-          dry_run: True
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-      - run: sphinx-build doc/source/ doc/build/ -W --keep-going -E
+      - run: sphinx-build doc/source/ doc/build/html -W --keep-going -E
         name: Build site strictly
       - uses: actions/upload-artifact@v4
         with:
@@ -121,6 +115,8 @@ jobs:
         run: |
              cd doc
              make linkcheck
+      - name: test sitemap
+        run: python .github/scripts/check_sitemap.py 
 
   format-test:
     runs-on: ubuntu-latest

doc/source/conf.py

@@ -45,6 +45,7 @@
 html_logo = "monty.svg"
 
 html_baseurl = "https://www.montepy.org/"
+sitemap_url_scheme = "{link}"
 html_extra_path = ["robots.txt"]
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.