If found total_annual_dollar_based_charges and could be divisible by 52 or 12,

then set the fund name and share name to be document production name

core/data_extraction.py

@@ -289,6 +289,7 @@ class DataExtraction:
         data_list = self.supplement_ttr_pension(data_list)
         data_list = self.align_fund_share_name(data_list)
         data_list = self.supplement_minimum_initial_investment(data_list)
+        data_list = self.check_total_annual_dollar_based_charges(data_list)
         data_list, datapoint_list_with_production_name = self.post_adjust_for_value_with_production_name(data_list)
         data_list = self.remove_duplicate_data(data_list)
         if "management_fee" not in datapoint_list_with_production_name and "management_fee_and_costs" not in datapoint_list_with_production_name:
@@ -503,6 +504,36 @@ class DataExtraction:
                         pass
         return data_list
     
+    def check_total_annual_dollar_based_charges(self, data_list: list):
+        """
+        If found total_annual_dollar_based_charges and could be divisible by 52 or 12,
+        then set the fund name and share name to be document production name.
+        """
+        for data_dict in data_list:
+            extract_data = data_dict.get("extract_data", {})
+            data = extract_data.get("data", [])
+            found = False
+            for data_item in data:
+                keys = list(data_item.keys())
+                fund_name = data_item.get("fund_name", "")
+                share_name = data_item.get("share_name", "")
+                if len(fund_name) == 0:
+                    continue
+                if "total_annual_dollar_based_charges" in keys:
+                    value = data_item.get("total_annual_dollar_based_charges", -1)
+                    if len(str(value)) > 0:
+                        value_divide_52 = value / 52
+                        value_divide_12 = value / 12
+                        if (value_divide_52 == round(value_divide_52, 4)) or \
+                            (value_divide_12 == round(value_divide_12, 4)):
+                            data_item["fund_name"] = self.document_production
+                            data_item["share_name"] = self.document_production
+                            found = True
+                            break
+            if found:
+                break
+        return data_list
+    
     def post_adjust_for_value_with_production_name(self, data_list: list):
         """
         If some datapoint with production name, then each fund/ share class in the same document for the datapoint should be with same value.

main.py

@@ -1448,7 +1448,7 @@ def get_aus_prospectus_document_category():
 
 
 def test_post_adjust_extract_data():
-    doc_id = "462780211"
+    doc_id = "448576924"
     pdf_folder: str = r"/data/aus_prospectus/pdf/"
     output_pdf_text_folder: str = r"/data/aus_prospectus/output/pdf_text/"
     output_extract_data_child_folder: str = (
@@ -1538,7 +1538,7 @@ if __name__ == "__main__":
         with open(document_sample_file, "r", encoding="utf-8") as f:
             special_doc_id_list = [doc_id.strip() for doc_id in f.readlines()
                                     if len(doc_id.strip()) > 0]
-        # special_doc_id_list = ["420339794"]
+        # special_doc_id_list = ["448576924"]
         pdf_folder: str = r"/data/aus_prospectus/pdf/"
         output_pdf_text_folder: str = r"/data/aus_prospectus/output/pdf_text/"
         output_extract_data_child_folder: str = (