Sep 16 - Optimize code, part 2

working_hours_calculator.py

@@ -126,11 +126,19 @@ def parse_employee_id_for_work_type(employee_id: str) -> Tuple[str, str]:
     """
     Parse employee ID to extract base ID and work type (supports SP, PW, PT, C)
     
-    Handles multiple formats:
-    - Suffix with space: "1234 SP", "1234 PW", "1234 PT", "1234 C"
-    - Suffix without space: "1234SP", "1234PW", "1234PT", "1234C"
-    - Prefix with space: "SP 1234", "PW 1234", "PT 1234", "C 1234"
-    - Prefix without space: "SP1234", "PW1234", "PT1234", "C1234"
+    Handles multiple formats — the separator may be anything that is not a letter
+    or a digit (space, dot, dash, underscore, slash, or nothing at all), because
+    imported IDs come straight from customer Excel files:
+    - Suffix: "1234SP", "1234 SP", "1234.PW", "1234-PT", "1234 . C"
+    - Prefix: "SP1234", "SP 1234", "PW.1234", "PT-1234"
+
+    This mirrors build_employee_id_regex() in utils/helpers.py (SQL filters) and
+    parseEmployeeIdWorkType() in static/js/attendance_report.js — keep the three
+    in sync, or the report, the filters and the exports disagree about who worked
+    those hours (§13).
+
+    Not a work type: "1234.5" (no code) and "1234SPX" (code runs into a word) —
+    both come back as regular with the ID unchanged.
     
     Args:
         employee_id: Employee ID string in any of the above formats
@@ -147,16 +155,19 @@ def parse_employee_id_for_work_type(employee_id: str) -> Tuple[str, str]:
     # Define work type codes
     work_type_codes = ['SP', 'PW', 'PT', 'C']
     
+    # Any run of non-alphanumeric characters may separate the ID from the code
+    # (or nothing at all): "1234SP", "1234 SP", "1234.PW", "1234 - PT".
+    # The class excludes letters, so "1234SPX" never matches.
+    separator = r'[^0-9A-Z]*'
+
     for work_type in work_type_codes:
-        # Pattern 1: Suffix with optional space - "1234 SP" or "1234SP"
-        suffix_pattern = rf'^(\d+)\s*{work_type}$'
-        suffix_match = re.match(suffix_pattern, employee_id_clean)
+        # Pattern 1: Suffix - "1234SP", "1234 SP", "1234.SP"
+        suffix_match = re.match(rf'^(\d+){separator}{work_type}$', employee_id_clean)
         if suffix_match:
             return suffix_match.group(1), work_type
-        
-        # Pattern 2: Prefix with optional space - "SP 1234" or "SP1234"
-        prefix_pattern = rf'^{work_type}\s*(\d+)$'
-        prefix_match = re.match(prefix_pattern, employee_id_clean)
+
+        # Pattern 2: Prefix - "SP1234", "SP 1234", "SP.1234"
+        prefix_match = re.match(rf'^{work_type}{separator}(\d+)$', employee_id_clean)
         if prefix_match:
             return prefix_match.group(1), work_type