Update app.py

app.py

@@ -38,6 +38,40 @@ shortcut_map = {
     "sxp": "saaxiib"
 }
 
+# Countries dictionary (English to Somali)
+country_map = {
+    "somalia": "Soomaaliya",
+    "ethiopia": "Itoobiya",
+    "kenya": "Kenya",
+    "djibouti": "Jabuuti",
+    "sudan": "Suudaan",
+    "south sudan": "Koonfurta Suudaan",
+    "uganda": "Ugaandha",
+    "tanzania": "Tansaaniya",
+    "egypt": "Masar",
+    "libya": "Liibiya",
+    "algeria": "Aljeeriya",
+    "morocco": "Morooko",
+    "tunisia": "Tuniisiya",
+    "eritrea": "Eriteriya",
+    "malawi": "Malaawi",
+    "mozambique": "Mosambiik",
+    "zambia": "Sambiya",
+    "zimbabwe": "Simbabwe",
+    "niger": "Niyjer",
+    "nigeria": "Nayjeeriya",
+    "united states": "Maraykanka",
+    "china": "Shiinaha",
+    "india": "Hindiya",
+    "russia": "Ruushka",
+    "united kingdom": "Boqortooyada Midowday",
+    "germany": "Jarmalka",
+    "france": "Faransiiska",
+    "japan": "Jabaan",
+    "canada": "Kanada",
+    "australia": "Australia"
+}
+
 def number_to_words(number):
     number = int(number)
     if number < 20:
@@ -86,13 +120,19 @@ def normalize_text(text):
     text = re.sub(r'(?i)(?<!\w)zamzam(?!\w)', 'samsam', text)
 
     # ➤ Bedel shortcuts - eray kasta oo qoraalka ku jira beddel
-    # Ka dhig case-insensitive beddelka
     def replace_shortcuts(match):
         word = match.group(0).lower()
         return shortcut_map.get(word, word)
     pattern = re.compile(r'\b(' + '|'.join(re.escape(k) for k in shortcut_map.keys()) + r')\b', re.IGNORECASE)
     text = pattern.sub(replace_shortcuts, text)
 
+    # ➤ Bedel magacyada waddamada
+    def replace_countries(match):
+        word = match.group(0).lower()
+        return country_map.get(word, word)
+    country_pattern = re.compile(r'\b(' + '|'.join(re.escape(k) for k in country_map.keys()) + r')\b', re.IGNORECASE)
+    text = country_pattern.sub(replace_countries, text)
+
     # ➤ Ka saar tirooyin leh koma iyo tobanle
     text = re.sub(r'(\d{1,3})(,\d{3})+', lambda m: m.group(0).replace(",", ""), text)
     text = re.sub(r'\.\d+', '', text)