Update app.py

app.py

@@ -341,19 +341,30 @@ class TranscriptParser:
                 text, re.DOTALL
             )
             
+            self.student_data = {}
             if student_match:
-                self.student_data = {
-                    "id": student_match.group(1),
-                    "name": student_match.group(2).replace(",", ", "),
-                    "current_grade": student_match.group(3),
-                    "graduation_year": student_match.group(4),
-                    "unweighted_gpa": float(student_match.group(5)),
-                    "weighted_gpa": float(student_match.group(6)),
-                    "total_credits": float(student_match.group(7)),
-                    "community_service_hours": int(student_match.group(8))
-                }
+                try:
+                    self.student_data = {
+                        "id": student_match.group(1),
+                        "name": student_match.group(2).replace(",", ", "),
+                        "current_grade": student_match.group(3),
+                        "graduation_year": student_match.group(4),
+                        "unweighted_gpa": float(student_match.group(5)),
+                        "weighted_gpa": float(student_match.group(6)),
+                        "total_credits": float(student_match.group(7)),
+                        "community_service_hours": int(student_match.group(8))
+                    }
+                except (IndexError, AttributeError) as e:
+                    logging.warning(f"Error extracting student info: {str(e)}")
+                    # Try to get at least the name and ID
+                    if student_match.group(1) and student_match.group(2):
+                        self.student_data = {
+                            "id": student_match.group(1),
+                            "name": student_match.group(2).replace(",", ", ")
+                        }
             
             # Extract requirements with better table parsing
+            self.requirements = {}
             req_section = re.search(
                 r"Code\s*Description\s*Required\s*Waived\s*Completed\s*Status(.*?)Total\s*[\d.]+\s*[\d.]+\s*[\d.]+\s*[\d.]+%",
                 text, re.DOTALL
@@ -366,16 +377,21 @@ class TranscriptParser:
                 )
                 
                 for match in req_matches:
-                    req_code = match.group(1).strip()
-                    self.requirements[req_code] = {
-                        "description": match.group(2).strip(),
-                        "required": float(match.group(3)),
-                        "waived": float(match.group(4)),
-                        "completed": float(match.group(5)),
-                        "status": f"{match.group(6)}%"
-                    }
+                    try:
+                        req_code = match.group(1).strip()
+                        self.requirements[req_code] = {
+                            "description": match.group(2).strip(),
+                            "required": float(match.group(3)),
+                            "waived": float(match.group(4)),
+                            "completed": float(match.group(5)),
+                            "status": f"{match.group(6)}%"
+                        }
+                    except (IndexError, AttributeError) as e:
+                        logging.warning(f"Skipping requirement due to error: {str(e)}")
+                        continue
             
             # Extract course history with more flexible parsing
+            self.course_history = []
             course_section = re.search(
                 r"Requirement\s*School Year\s*GradeLv1\s*CrsNu m\s*Description(.*?)(?=Legend for Incl:|$)",
                 text, re.DOTALL
@@ -388,18 +404,22 @@ class TranscriptParser:
                 )
                 
                 for match in course_matches:
-                    self.course_history.append({
-                        "requirement_category": match.group(1).strip(),
-                        "school_year": match.group(2),
-                        "grade_level": match.group(3),
-                        "course_code": match.group(4),
-                        "description": match.group(5).strip(),
-                        "term": match.group(6),
-                        "district_number": match.group(7),
-                        "grade": match.group(8),
-                        "inclusion_status": match.group(9),
-                        "credits": match.group(10)
-                    })
+                    try:
+                        self.course_history.append({
+                            "requirement_category": match.group(1).strip(),
+                            "school_year": match.group(2),
+                            "grade_level": match.group(3),
+                            "course_code": match.group(4),
+                            "description": match.group(5).strip(),
+                            "term": match.group(6),
+                            "district_number": match.group(7),
+                            "grade": match.group(8),
+                            "inclusion_status": match.group(9),
+                            "credits": match.group(10)
+                        })
+                    except (IndexError, AttributeError) as e:
+                        logging.warning(f"Skipping course due to error: {str(e)}")
+                        continue
             
             # Identify current courses
             self._extract_current_courses()