Merge pull request #34 from Code4GovTech/sasi_dev_v2fix

code revert

v2_app.py

@@ -27,13 +27,15 @@ def get_issues_by_owner_id_v2(owner, issue):
 
         dmp_issue_id = SUPABASE_DB.client.table('dmp_issues').select('*').like('issue_url', f'%{url}%').eq('id', issue).execute()
         if not dmp_issue_id.data:
-          return jsonify({'error': "No data found"}), 500
+          print(f"url....{url}....{issue}")
+          return jsonify({'error': "No data found in dmp_issue"}), 500
 
         dmp_issue_id = dmp_issue_id.data[0]        
         response = SUPABASE_DB.client.table('dmp_issue_updates').select('*').eq('dmp_id', dmp_issue_id['id']).execute()
 
         if not response.data:
-            return jsonify({'error': "No data found"}), 500
+            print(f"dmp_issue_id....{response}....{dmp_issue_id}")
+            return jsonify({'error': "No data found in dmp_issue_updates"}), 500
 
         data = response.data
 

v2_utils.py

@@ -27,7 +27,29 @@ def define_link_data(usernames):
         logging.info(f"{e}---define_link_data")
         return []
 
+def remove_unmatched_tags(text):
+    try:
+       # Remove unmatched closing tags at the beginning of the string
+        text = re.sub(r'^\s*</[^>]+>\s*', '', text)
+
+        # Regex pattern to find matched or unmatched tags
+        pattern = re.compile(r'(<([^>]+)>.*?</\2>)|(<[^/][^>]*>.*)', re.DOTALL)
+        matches = pattern.findall(text)
+
+        cleaned_text = ''
+        for match in matches:
+            if match[0]:  # Full matched <tag>...</tag> pairs
+                cleaned_text += match[0]
+            elif match[2]:  # Unmatched opening <tag> tags
+                cleaned_text += match[2]
 
+        return cleaned_text
+    except Exception as e:
+        print(e)
+        return text
+
+
+
 
 def week_data_formatter(html_content, type):
 
@@ -46,7 +68,7 @@ def week_data_formatter(html_content, type):
                 task_list_html = tasks_per_week[i] if i < len(tasks_per_week) else ""
                 weekly_updates.append({
                     'week': i + 1,
-                    'content': re.sub(r'<[^>]+>', '',task_list_html).strip()
+                    'content': remove_unmatched_tags(task_list_html)
 
                 })
             return weekly_updates