Escape reserved HTML characters in og:description (#120)

Co-authored-by: Adam Turner <9087854+AA-Turner@users.noreply.github.com>

Author: markpeek

sphinxext/opengraph/_description_parser.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import html
 import string
 from typing import TYPE_CHECKING
 
@@ -69,6 +70,9 @@ def dispatch_visit(self, node: nodes.Element) -> None:
         if len(node.children) == 0:
             text = node.astext().replace('\r', '').replace('\n', ' ').strip()
 
+            # Ensure string contains HTML-safe characters
+            text = html.escape(text, quote=True)
+
             # Remove double spaces
             while text.find('  ') != -1:
                 text = text.replace('  ', ' ')

tests/roots/test-meta-name-description-escape/conf.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+extensions = ['sphinxext.opengraph']
+
+master_doc = 'index'
+exclude_patterns = ['_build']
+
+html_theme = 'basic'
+
+ogp_site_url = 'http://example.org/en/latest/'
+
+enable_meta_description = True

tests/roots/test-meta-name-description-escape/index.rst

@@ -0,0 +1,4 @@
+Lorem <ipsum> dolor sit amet, "consectetur" adipiscing elit.
+Suspendisse at lorem ornare, fringilla massa nec, venenatis mi.
+Donec erat sapien, tincidunt nec rhoncus nec, scelerisque id diam.
+Orci varius natoque penatibus et magnis dis parturient mauris.

tests/test_options.py

@@ -19,6 +19,11 @@ def get_tag_content(tags, tag_type, kind='property', prefix='og'):
     return get_tag(tags, tag_type, kind, prefix).get('content', '')
 
 
+def get_tag_content_text(tags, tag_type, kind='property', prefix='og'):
+    # Gets the content of a specific ogp tag
+    return get_tag(tags, tag_type, kind, prefix).get_text('content', '')
+
+
 def get_meta_description(tags):
     tag = next(tag for tag in tags if tag.get('name') == 'description')
     return tag.get('content', '')
@@ -45,6 +50,15 @@ def test_meta_name_description(meta_tags):
     assert description == og_description
 
 
+@pytest.mark.sphinx('html', testroot='meta-name-description-escape')
+def test_meta_name_description_escape(meta_tags):
+    og_description = get_tag_content(meta_tags, 'description')
+    og_description_text = get_tag_content_text(meta_tags, 'description')
+
+    assert '<' in og_description
+    assert '<' not in og_description_text
+
+
 @pytest.mark.sphinx('html', testroot='meta-name-description-manual-description')
 def test_meta_name_manual_description(meta_tags):
     og_description = get_tag_content(meta_tags, 'description')