ci: Update Pandoc version from 2.x to 3.x

.github/workflows/main.yml

@@ -31,7 +31,7 @@ jobs:
       - name: Install pandoc
         uses: r-lib/actions/setup-pandoc@v2
         with:
-          pandoc-version: "2.9.2"
+          pandoc-version: "3.12.1"
       - name: Install tox
         run: python -m pip install -U pip tox
       - name: Info

pelican/tests/content/wordpress_content_decoded

@@ -32,14 +32,12 @@ consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
 cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
 proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</li>
 </ul>
-<pre>
-<code>
+<pre><code>
   a = [1, 2, 3]
   b = [4, 5, 6]
   for i in zip(a, b):
     print i
-</code>
-</pre>
+</code></pre>
 <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
 tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
 quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo

pelican/tools/pelican_import.py

@@ -107,6 +107,10 @@ def decode_wp_content(content, br=True):
 
         content = _multi_replace(pre_tags, content)
 
+    # Pandoc >= 3 only treats <pre><code> as a code block when the tags are adjacent
+    content = re.sub(r"<pre([^>]*)>\s*<code", r"<pre\1><code", content)
+    content = re.sub(r"</code>\s*</pre>", "</code></pre>", content)
+
     # convert [caption] tags into <figure>
     content = re.sub(
         r"\[caption(?:.*?)(?:caption=\"(.*?)\")?\]"