Update nat_datasets.py

nat_datasets.py

@@ -48,27 +48,27 @@ match1_done = 0
 
 
 def new_func(value, ar_tab):
-    # ---
-    ar_country = ar_tab.get("men", "")
-    # ---
-    if ar_country and ar_country in value:
-        return ar_country, "{NAT_MEN}"
-    # ---
-    ar_country2 = ar_tab.get("womens", "")
-    # ---
-    if ar_country2 and ar_country2 in value:
-        return ar_country2, "{NAT_WOMENS}"
-    # ---
-    ar_country3 = ar_tab.get("women", "")
-    # ---
-    if ar_country3 and ar_country2 in value:
-        return ar_country3, "{NAT_WOMEN}"
-    # ---
-    ar_country4 = ar_tab.get("man", "")
-    # ---
-    if ar_country4 and ar_country2 in value:
-        return ar_country4, "{NAT_MAN}"
-    # ---
+    # List of possible keys and their corresponding tags
+    patterns = [
+        ("men", "{NAT_MEN}"),
+        ("womens", "{NAT_WOMENS}"),
+        ("women", "{NAT_WOMEN}"),
+        ("man", "{NAT_MAN}"),
+    ]
+
+    # Iterate through the patterns
+    for key, tag in patterns:
+        country = ar_tab.get(key, "")
+        if not country:
+            continue
+        # ---
+        country2 = f"ال{country}".replace(" ", " ال")
+        # ---
+        if country2 in value:
+            return country2, tag
+        elif country in value:
+            return country, tag
+
     return "", ""
 
 
@@ -103,8 +103,11 @@ for tab in tqdm.tqdm(data):
     if not NAT_PATTERN:
         continue
     # ---
-    key1 = re.sub(rf'\b{re.escape(en_country)}\b', EN_NAT_PATTERN, key, re.IGNORECASE)
-    value1 = re.sub(rf'\b{re.escape(ar_country)}\b', NAT_PATTERN, value, re.IGNORECASE)
+    key1 = re.sub(rf'\b{re.escape(en_country)}\b', EN_NAT_PATTERN, f" {key} ", re.IGNORECASE)
+    key1 = key1.strip()
+    # ---
+    value1 = re.sub(rf'\b{re.escape(ar_country)}\b', NAT_PATTERN, f" {value} ", re.IGNORECASE)
+    value1 = value1.strip()
     # ---
     # if EN_NAT_PATTERN in key1 and NAT_PATTERN in value1:
     # ---