feat: removed extra spaces from start and end of content (#35647)

lms/djangoapps/discussion/rest_api/discussions_notifications.py

@@ -3,7 +3,7 @@
 """
 import re
 
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup, Tag
 from django.conf import settings
 from django.utils.text import Truncator
 
@@ -380,6 +380,30 @@ def remove_html_tags(text):
     return re.sub(clean, '', text)
 
 
+def strip_empty_tags(soup):
+    """
+    Strip starting and ending empty tags from the soup object
+    """
+    def strip_tag(element, reverse=False):
+        """
+        Checks if element is empty and removes it
+        """
+        if not element.get_text(strip=True):
+            element.extract()
+            return True
+        if isinstance(element, Tag):
+            child_list = element.contents[::-1] if reverse else element.contents
+            for child in child_list:
+                if not strip_tag(child):
+                    break
+        return False
+
+    while soup.contents:
+        if not (strip_tag(soup.contents[0]) or strip_tag(soup.contents[-1], reverse=True)):
+            break
+    return soup
+
+
 def clean_thread_html_body(html_body):
     """
     Get post body with tags removed and limited to 500 characters
@@ -401,6 +425,9 @@ def clean_thread_html_body(html_body):
         for match in html_body.find_all(tag):
             match.unwrap()
 
+    if not html_body.find():
+        return str(html_body)
+
     # Replace tags that are not allowed in email
     tags_to_update = [
         {"source": "button", "target": "span"},
@@ -412,11 +439,15 @@ def clean_thread_html_body(html_body):
     for tag_dict in tags_to_update:
         for source_tag in html_body.find_all(tag_dict['source']):
             target_tag = html_body.new_tag(tag_dict['target'], **source_tag.attrs)
-            if source_tag.string:
-                target_tag.string = source_tag.string
-            source_tag.replace_with(target_tag)
+            if source_tag.contents:
+                for content in list(source_tag.contents):
+                    target_tag.append(content)
+            source_tag.insert_before(target_tag)
+            source_tag.extract()
 
     for tag in html_body.find_all(True):
         tag.attrs = {}
         tag['style'] = 'margin: 0'
+
+    html_body = strip_empty_tags(html_body)
     return str(html_body)

lms/djangoapps/discussion/rest_api/tests/test_discussions_notifications.py

@@ -179,15 +179,23 @@ def test_button_tag_replace(self):
         """
         Tests that the clean_thread_html_body function replaces the button tag with span tag
         """
-        # Tests for button replacement tag with text
         html_body = '<button class="abc">Button</button>'
         expected_output = '<span style="margin: 0">Button</span>'
         result = clean_thread_html_body(html_body)
         self.assertEqual(result, expected_output)
 
-        # Tests button tag replacement without text
+        html_body = '<p><p>abc</p><button class="abc"></button><p>abc</p></p>'
+        expected_output = '<p style="margin: 0"><p style="margin: 0">abc</p>'\
+                          '<span style="margin: 0"></span><p style="margin: 0">abc</p></p>'
+        result = clean_thread_html_body(html_body)
+        self.assertEqual(result, expected_output)
+
+    def test_button_tag_removal(self):
+        """
+        Tests button tag with no text is removed if at start or end
+        """
         html_body = '<button class="abc"></button>'
-        expected_output = '<span style="margin: 0"></span>'
+        expected_output = ''
         result = clean_thread_html_body(html_body)
         self.assertEqual(result, expected_output)
 
@@ -196,3 +204,11 @@ def test_attributes_removal_from_tag(self):
         html_body = '<p class="abc" style="color:red" aria-disabled=true>Paragraph</p>'
         result = clean_thread_html_body(html_body)
         self.assertEqual(result, '<p style="margin: 0">Paragraph</p>')
+
+    def test_strip_empty_tags(self):
+        """
+        Tests if the clean_thread_html_body function removes starting and ending empty tags
+        """
+        html_body = '<div><p></p><p>content</p><p></p></div>'
+        result = clean_thread_html_body(html_body)
+        self.assertEqual(result, '<p style="margin: 0"><p style="margin: 0">content</p></p>')