Update app.py

app.py

@@ -370,7 +370,7 @@ class TranscriptParser:
                 parsed_data['student_info']['year_of_graduation'] = yog_match.group(1)
             
             # Improved GPA extraction with more flexible patterns
-            gpa_matches = re.findall(r"(?:UNWEIGHTED|WEIGHTED)\s*GPA\s*([\d.]+)", text, re.IGNORECASE)
+            gpa_matches = re.findall(r"(?:UN.?WEIGHTED|WEIGHTED)\s*GPA\s*([\d.]+)", text, re.IGNORECASE)
             if len(gpa_matches) >= 1:
                 parsed_data['student_info']['unweighted_gpa'] = float(gpa_matches[0])
             if len(gpa_matches) >= 2:
@@ -413,11 +413,12 @@ class TranscriptParser:
                 }
             
             # Extract assessments with more flexible pattern
-            assess_pattern = re.compile(r"Z-ASSESSMENT:\s*(.*?)\s*\|\s*(.*?)\s*\|\s*(\w+)\s*\|\s*(\d+)\s*%", re.IGNORECASE)
+            assess_pattern = re.compile(r"Z-([^\|]+)\s*\|\s*([^\|]*)\s*\|\s*([^\|]*)\s*\|\s*([^\|]*)\s*%", re.IGNORECASE)
             for match in assess_pattern.finditer(text):
                 name = f"Assessment: {match.group(1).strip()}"
-                status = match.group(3).strip()
-                parsed_data['assessments'][name] = status
+                status = match.group(3).strip() if match.group(3) else ""
+                if status:
+                    parsed_data['assessments'][name] = status
             
             # Handle other Z items
             for z_item in ["Community Service Hours", "GPA"]:
@@ -427,9 +428,9 @@ class TranscriptParser:
                     parsed_data['assessments'][z_item] = status
             
             # Extract course history with more robust pattern
-            course_history_section = re.search(r"REQUIREMENT.*?SCHOOL YEAR.*?GRADELV1.*?CRSNUM.*?DESCRIPTION.*?TERM.*?DSTNUMBER.*?FG.*?INCL.*?CREDITS(.*?)(?:\n\s*\n|$)", text, re.DOTALL | re.IGNORECASE)
+            course_history_section = re.search(r"Requirement.*?School Year.*?GradeLv1.*?CrsNum.*?Description.*?Term.*?DstNumber.*?FG.*?Incl.*?Credits(.*?)(?:\n\s*\n|$)", text, re.DOTALL | re.IGNORECASE)
             if course_history_section:
-                course_lines = [line.strip() for line in course_history_section.group(1).split('\n') if line.strip()]
+                course_lines = [line.strip() for line in course_history_section.group(1).split('\n') if line.strip() and '|' in line]
                 for line in course_lines:
                     parts = [part.strip() for part in line.split('|')]
                     if len(parts) >= 9:
@@ -445,6 +446,9 @@ class TranscriptParser:
                             'included': parts[8] if len(parts) > 8 else "",
                             'credits': parts[9] if len(parts) > 9 else "0"
                         }
+                        # Handle "inProgress" credits
+                        if "inProgress" in course['credits'].lower():
+                            course['credits'] = "0"
                         parsed_data['course_history'].append(course)
             
             return parsed_data
@@ -500,7 +504,7 @@ class TranscriptParser:
 # ========== ENHANCED ANALYSIS FUNCTIONS ==========
 def analyze_gpa(parsed_data: Dict) -> str:
     try:
-        gpa = float(parsed_data['student_info'].get('weighted_gpa', 0))
+        gpa = float(parsed_data.get('student_info', {}).get('weighted_gpa', 0))
         if gpa >= 4.5:
             return "🌟 Excellent GPA! You're in the top tier of students."
         elif gpa >= 3.5: