Updating logic for parsing scheme names for detailed CAS reports, handling erstwhile and non-demat suffixes

Author: hitesh-tarani

casparser/process/cas_detailed.py

@@ -118,6 +118,13 @@ def get_transaction_type(
     return txn_type, dividend_rate
 
 
+def get_parsed_scheme_name(scheme) -> str:
+    scheme = re.sub(r"\((formerly|erstwhile).+?\)", "", scheme, flags=re.I | re.DOTALL).strip()
+    scheme = re.sub(r"\((Demat|Non-Demat).*", "", scheme, flags=re.I | re.DOTALL).strip()
+    scheme = re.sub(r"\s+", " ", scheme).strip()
+    return re.sub(r"[^a-zA-Z0-9_)]+$", "", scheme).strip()
+
+
 def parse_transaction(line) -> Optional[ParsedTransaction]:
     for regex in (TRANSACTION_RE1, TRANSACTION_RE2, TRANSACTION_RE3):
         if m := re.search(regex, line, re.DOTALL | re.MULTILINE | re.I):
@@ -189,9 +196,7 @@ def process_detailed_text(text):
         elif m := re.search(SCHEME_RE, line, re.DOTALL | re.MULTILINE | re.I):
             if current_folio is None:
                 raise CASParseError("Layout Error! Scheme found before folio entry.")
-            scheme = re.sub(r"\(formerly.+?\)", "", m.group("name"), flags=re.I | re.DOTALL).strip()
-            scheme = re.sub(r"\s+", " ", scheme).strip()
-            scheme = re.sub(r"\W+$", "", scheme).strip()
+            scheme = get_parsed_scheme_name(m.group("name"))
             if curr_scheme_data is None or curr_scheme_data.scheme != scheme:
                 if curr_scheme_data:
                     folios[current_folio].schemes.append(curr_scheme_data)

tests/test_process.py

@@ -4,7 +4,7 @@
 
 from casparser.exceptions import CASParseError, HeaderParseError
 from casparser.process import process_cas_text
-from casparser.process.cas_detailed import parse_header, get_transaction_type
+from casparser.process.cas_detailed import parse_header, get_transaction_type, get_parsed_scheme_name
 from casparser.process.cas_detailed import ParsedTransaction, parse_transaction
 from casparser.process.cas_summary import parse_header as parse_summary_header
 from casparser.process.utils import isin_search
@@ -94,6 +94,23 @@ def test_dividend_transactions(self):
             Decimal("0.0241"),
         )
 
+    def test_parsed_scheme_name(self):
+        assert get_parsed_scheme_name(
+            "Axis Long Term Equity Fund - Direct Growth") == "Axis Long Term Equity Fund - Direct Growth"
+        assert get_parsed_scheme_name(
+            "Axis Bluechip Fund - Regular Growth ") == "Axis Bluechip Fund - Regular Growth"
+        assert get_parsed_scheme_name(
+            "HSBC Corporate Bond Fund - Regular Growth (Formerly known as L&T Triple Ace Bond Fund - Growth)") == \
+            "HSBC Corporate Bond Fund - Regular Growth"
+        assert get_parsed_scheme_name(
+            "Bandhan ELSS Tax saver Fund-Growth-(Regular Plan)"
+            "(erstwhile Bandhan Tax Advantage ELSS Fund-Growth-Regular Plan)") == \
+               "Bandhan ELSS Tax saver Fund-Growth-(Regular Plan)"
+        assert get_parsed_scheme_name(
+            "Bandhan Liquid Fund-Growth-(Regular Plan) (erstwhile IDFC Cash Fund-Growth-Regular Plan) (Non-Demat) ") == \
+               "Bandhan Liquid Fund-Growth-(Regular Plan)"
+
+
     def test_isin_search(self):
         isin, amfi, scheme_type = isin_search(
             "Axis Long Term Equity Fund - Direct Growth", "KFINTECH", "128TSDGG"