Adding product id map function

modules/mapping.py

@@ -64,4 +64,31 @@ def mapping_employee(information, json_path, normalization_rule):
 def mapping_product(information, json_path, normalization_rule):
     # Load from product JSON file
     with open(json_path, "r", encoding="utf-8") as f:
-        product_id_dict = json.load(f)
+        product_id_dict = json.load(f)
+
+    # Create cached normalized dictionary
+    normalized_cached_map = {
+        (normalization(text= product_name, normalization_rule= normalization_rule),
+         normalization(text= unit_id, normalization_rule= normalization_rule)): product_id
+         for product_id, (product_name, unit_id) in product_id_dict.items()
+    }
+    product_list = list(normalized_cached_map.keys())
+
+    for item in information:
+        # Normalize product_name and unit_id:
+        normalized_product_name = normalization(text= item["product_name"], normalization_rule= normalization_rule)
+        normalized_unit_id = normalization(text = item["unit_id"], normalization_rule= normalization_rule)
+
+        product_name_match, product_name_score, _ = process.extractOne(normalized_product_name, [k[0] for k in product_list], scorer= fuzz.token_sort_ratio)
+        unit_id_match, unit_id_score, _ = process.extractOne(normalized_unit_id, [k[1] for k in product_list], scorer= fuzz.token_sort_ratio)
+
+        # Calculate the average matching score
+        average_score = (product_name_score + unit_id_score) / 2
+
+        if average_score >=80:
+            matched_key = (product_name_match, unit_id_match)
+            item["product_id"] = normalized_cached_map[matched_key]
+        else:
+            item["product_id"] = None
+    
+    return information