Update app.py

app.py

@@ -36,9 +36,9 @@ SESSION_TIMEOUT = 3600  # 1 hour session timeout
 
 # Initialize logging
 logging.basicConfig(
-    filename='transcript_parser.log',
     level=logging.DEBUG,
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    filename='transcript_parser.log'
 )
 
 # Model configuration - Only DeepSeek
@@ -318,7 +318,7 @@ class TranscriptParser:
             logging.error(f"Error parsing transcript: {str(e)}")
             raise ValueError(f"Couldn't parse transcript: {str(e)}")
 
-    def _parse_miami_dade_format(self, text: str) -> Dict:
+    def _parse_miami_dade_format(self, text: str, strict_mode: bool = False) -> Dict:
         """Parse Miami-Dade County Public Schools transcripts."""
         # Initialize PDF reader from text (simulating the PDF structure)
         lines = [line.strip() for line in text.split('\n') if line.strip()]
@@ -328,39 +328,62 @@ class TranscriptParser:
             'student_info': {},
             'graduation_requirements': [],
             'course_history': [],
-            'summary': {}
+            'summary': {},
+            'format': 'miami_dade'  # Add format identifier
         }
         
-        # Parse student information
+        # Parse student information with more robust checks
         student_info_lines = []
-        for line in lines:
+        for i, line in enumerate(lines):
+            logging.debug(f"Processing line: {line}")  # Added debug logging
             if "DORAL ACADEMY HIGH SCHOOL" in line:
-                student_info_lines = lines[lines.index(line):lines.index(line)+5]
+                # Get the next 4 lines (or fewer if we're at the end)
+                student_info_lines = lines[i:i+5]
                 break
         
         if student_info_lines:
-            # Parse school and cohort info
-            school_info = student_info_lines[0].split('|')
-            data['student_info']['school'] = school_info[1].strip()
-            data['student_info']['district'] = school_info[2].strip()
-            
-            # Parse student name and ID
-            name_id_line = student_info_lines[1].split('-')
-            data['student_info']['student_id'] = name_id_line[0].strip()
-            data['student_info']['student_name'] = name_id_line[1].split(',')[1].strip() + " " + name_id_line[1].split(',')[0].strip()
-            
-            # Parse academic info
-            academic_info = student_info_lines[2].split('|')
-            data['student_info']['current_grade'] = academic_info[1].split(':')[1].strip()
-            data['student_info']['graduation_year'] = academic_info[2].strip()
-            data['student_info']['weighted_gpa'] = academic_info[3].split(':')[1].strip()
-            data['student_info']['community_service_date'] = academic_info[4].split(':')[1].strip()
-            data['student_info']['total_credits_earned'] = academic_info[5].split(':')[1].strip()
+            try:
+                # Parse school and cohort info - more defensive
+                school_info_parts = student_info_lines[0].split('|')
+                if len(school_info_parts) > 2:
+                    data['student_info']['school'] = school_info_parts[1].strip() if len(school_info_parts) > 1 else ''
+                    data['student_info']['district'] = school_info_parts[2].strip() if len(school_info_parts) > 2 else ''
+                
+                # Parse student name and ID - more defensive
+                if len(student_info_lines) > 1:
+                    name_id_line = student_info_lines[1].split('-')
+                    if len(name_id_line) > 1:
+                        name_parts = name_id_line[1].split(',')
+                        if len(name_parts) > 1:
+                            data['student_info']['student_id'] = name_id_line[0].strip()
+                            data['student_info']['student_name'] = name_parts[1].strip() + " " + name_parts[0].strip()
+                
+                # Parse academic info - more defensive
+                if len(student_info_lines) > 2:
+                    academic_info = student_info_lines[2].split('|')
+                    if len(academic_info) > 5:
+                        data['student_info']['current_grade'] = academic_info[1].split(':')[1].strip() if ':' in academic_info[1] else ''
+                        data['student_info']['graduation_year'] = academic_info[2].strip()
+                        data['student_info']['weighted_gpa'] = academic_info[3].split(':')[1].strip() if ':' in academic_info[3] else ''
+                        data['student_info']['community_service_date'] = academic_info[4].split(':')[1].strip() if ':' in academic_info[4] else ''
+                        data['student_info']['total_credits_earned'] = academic_info[5].split(':')[1].strip() if ':' in academic_info[5] else ''
+                        
+                # Validate we got the essential student info
+                if not data['student_info'].get('student_name'):
+                    logging.warning("Failed to parse student name")
+                    if strict_mode:
+                        raise ValueError("Could not parse student name from transcript")
+                        
+            except Exception as e:
+                logging.warning(f"Error parsing student info: {str(e)}")
+                if strict_mode:
+                    raise
         
         # Parse graduation requirements
         requirements_start = None
         requirements_end = None
         for i, line in enumerate(lines):
+            logging.debug(f"Processing line: {line}")  # Added debug logging
             if "Code" in line and "Description" in line and "Required" in line:
                 requirements_start = i + 1
             if requirements_start and "Total" in line:
@@ -369,31 +392,42 @@ class TranscriptParser:
         
         if requirements_start and requirements_end:
             for line in lines[requirements_start:requirements_end]:
-                if '|' in line:
-                    parts = [p.strip() for p in line.split('|') if p.strip()]
-                    if len(parts) >= 6:
-                        req = {
-                            'code': parts[0],
-                            'description': parts[1],
-                            'required': parts[2],
-                            'waived': parts[3],
-                            'completed': parts[4],
-                            'status': parts[5]
-                        }
-                        data['graduation_requirements'].append(req)
+                try:
+                    if '|' in line:
+                        parts = [p.strip() for p in line.split('|') if p.strip()]
+                        if len(parts) >= 6:
+                            req = {
+                                'code': parts[0],
+                                'description': parts[1],
+                                'required': parts[2],
+                                'waived': parts[3],
+                                'completed': parts[4],
+                                'status': parts[5]
+                            }
+                            data['graduation_requirements'].append(req)
+                except Exception as e:
+                    logging.warning(f"Error parsing requirement line: {line} - {str(e)}")
+                    if strict_mode:
+                        raise
             
             # Parse total line
-            total_line = lines[requirements_end]
-            total_parts = [p.strip() for p in total_line.split('|') if p.strip()]
-            if len(total_parts) >= 5:
-                data['summary']['total_required'] = total_parts[1]
-                data['summary']['total_waived'] = total_parts[2]
-                data['summary']['total_completed'] = total_parts[3]
-                data['summary']['completion_percentage'] = total_parts[4]
+            try:
+                total_line = lines[requirements_end]
+                total_parts = [p.strip() for p in total_line.split('|') if p.strip()]
+                if len(total_parts) >= 5:
+                    data['summary']['total_required'] = total_parts[1]
+                    data['summary']['total_waived'] = total_parts[2]
+                    data['summary']['total_completed'] = total_parts[3]
+                    data['summary']['completion_percentage'] = total_parts[4]
+            except Exception as e:
+                logging.warning(f"Error parsing requirements summary: {str(e)}")
+                if strict_mode:
+                    raise
         
         # Parse course history
         course_history_start = None
         for i, line in enumerate(lines):
+            logging.debug(f"Processing line: {line}")  # Added debug logging
             if "Requirement" in line and "School Year" in line and "GradeLv1" in line:
                 course_history_start = i + 1
                 break
@@ -401,38 +435,49 @@ class TranscriptParser:
         if course_history_start:
             current_requirement = None
             for line in lines[course_history_start:]:
-                if '|' in line:
-                    parts = [p.strip() for p in line.split('|') if p.strip()]
-                    
-                    # Check if this is a new requirement line
-                    if len(parts) >= 2 and parts[0] and parts[0] in [req['code'] for req in data['graduation_requirements']]:
-                        current_requirement = parts[0]
-                        parts = parts[1:]  # Remove the requirement code
-                    
-                    if len(parts) >= 9:
-                        course = {
-                            'requirement': current_requirement,
-                            'school_year': parts[0],
-                            'grade_level': parts[1],
-                            'course_number': parts[2],
-                            'description': parts[3],
-                            'term': parts[4],
-                            'district_number': parts[5],
-                            'fg': parts[6],
-                            'included': parts[7],
-                            'credits': parts[8]
-                        }
-                        data['course_history'].append(course)
+                try:
+                    if '|' in line:
+                        parts = [p.strip() for p in line.split('|') if p.strip()]
+                        
+                        # Check if this is a new requirement line
+                        if len(parts) >= 2 and parts[0] and parts[0] in [req['code'] for req in data['graduation_requirements']]:
+                            current_requirement = parts[0]
+                            parts = parts[1:]  # Remove the requirement code
+                        
+                        if len(parts) >= 9:
+                            course = {
+                                'requirement': current_requirement,
+                                'school_year': parts[0],
+                                'grade_level': parts[1],
+                                'course_number': parts[2],
+                                'description': parts[3],
+                                'term': parts[4],
+                                'district_number': parts[5],
+                                'fg': parts[6],
+                                'included': parts[7],
+                                'credits': parts[8]
+                            }
+                            data['course_history'].append(course)
+                except Exception as e:
+                    logging.warning(f"Error parsing course line: {line} - {str(e)}")
+                    if strict_mode:
+                        raise
         
         # Calculate graduation status
-        graduation_status = {
-            'total_required_credits': float(data['summary']['total_required']),
-            'total_completed_credits': float(data['summary']['total_completed']),
-            'percent_complete': float(data['summary']['completion_percentage'].replace('%', '')),
-            'remaining_credits': float(data['summary']['total_required']) - float(data['summary']['total_completed']),
-            'on_track': float(data['summary']['completion_percentage'].replace('%', '')) >= 75.0
-        }
-        data['graduation_status'] = graduation_status
+        try:
+            if data['summary'].get('total_required') and data['summary'].get('total_completed'):
+                graduation_status = {
+                    'total_required_credits': float(data['summary']['total_required']),
+                    'total_completed_credits': float(data['summary']['total_completed']),
+                    'percent_complete': float(data['summary']['completion_percentage'].replace('%', '')),
+                    'remaining_credits': float(data['summary']['total_required']) - float(data['summary']['total_completed']),
+                    'on_track': float(data['summary']['completion_percentage'].replace('%', '')) >= 75.0
+                }
+                data['graduation_status'] = graduation_status
+        except Exception as e:
+            logging.warning(f"Error calculating graduation status: {str(e)}")
+            if strict_mode:
+                raise
         
         return data