Update app.py

app.py

@@ -54,37 +54,64 @@ def parse_transcript(file):
             if page_text:
                 text += page_text + '\n'
 
-        # GPA extraction
-        gpa_match = re.search(r'GPA[:\s]*(\d\.\d{1,2})', text, re.IGNORECASE)
-        gpa = gpa_match.group(1) if gpa_match else "N/A"
-
         # Grade level extraction
         grade_match = re.search(r'(Grade|Year)[\s:]*(\d+|Freshman|Sophomore|Junior|Senior)', text, re.IGNORECASE)
         grade_level = grade_match.group(2) if grade_match else "Unknown"
 
-        # Courses grouped by grade
+        # Enhanced GPA extraction
+        gpa_data = {'weighted': "N/A", 'unweighted': "N/A"}
+        gpa_patterns = [
+            r'Weighted GPA[\s:]*(\d\.\d{1,2})',
+            r'GPA \(Weighted\)[\s:]*(\d\.\d{1,2})',
+            r'Cumulative GPA \(Weighted\)[\s:]*(\d\.\d{1,2})',
+            r'Unweighted GPA[\s:]*(\d\.\d{1,2})',
+            r'GPA \(Unweighted\)[\s:]*(\d\.\d{1,2})',
+            r'Cumulative GPA \(Unweighted\)[\s:]*(\d\.\d{1,2})',
+            r'GPA[\s:]*(\d\.\d{1,2})'
+        ]
+        for pattern in gpa_patterns:
+            for match in re.finditer(pattern, text, re.IGNORECASE):
+                gpa_value = match.group(1)
+                if 'weighted' in pattern.lower():
+                    gpa_data['weighted'] = gpa_value
+                elif 'unweighted' in pattern.lower():
+                    gpa_data['unweighted'] = gpa_value
+                else:
+                    if gpa_data['unweighted'] == "N/A":
+                        gpa_data['unweighted'] = gpa_value
+                    if gpa_data['weighted'] == "N/A":
+                        gpa_data['weighted'] = gpa_value
+
         courses_by_grade = extract_courses_with_grade_levels(text)
 
-        output_text = f"Grade Level: {grade_level}\nGPA: {gpa}\n\nCourses by Grade Level:\n\n"
+        output_text = f"Grade Level: {grade_level}\n\n"
+        if gpa_data['weighted'] != "N/A" or gpa_data['unweighted'] != "N/A":
+            output_text += "GPA Information:\n"
+            if gpa_data['unweighted'] != "N/A":
+                output_text += f"- Unweighted GPA: {gpa_data['unweighted']}\n"
+            if gpa_data['weighted'] != "N/A":
+                output_text += f"- Weighted GPA: {gpa_data['weighted']}\n"
+        else:
+            output_text += "No GPA information found\n"
+
+        output_text += "\nCourses by Grade Level:\n"
         for level, courses in courses_by_grade.items():
-            output_text += f"Grade {level}:\n"
+            output_text += f"\nGrade {level}:\n"
             for course in courses:
                 output_text += f"- {course['course']}"
                 if 'grade' in course:
                     output_text += f" (Grade: {course['grade']})"
                 output_text += "\n"
-            output_text += "\n"
 
         return output_text, {
-            "gpa": gpa,
+            "gpa": gpa_data,
             "grade_level": grade_level,
             "courses": courses_by_grade
         }
-
     else:
         return "Unsupported file format", None
 
-    # For CSV/XLSX:
+    # For CSV/XLSX fallback
     gpa = "N/A"
     for col in ['GPA', 'Grade Point Average', 'Cumulative GPA']:
         if col in df.columns:
@@ -107,7 +134,7 @@ def parse_transcript(file):
     output_text += "\n".join(f"- {course}" for course in courses)
 
     return output_text, {
-        "gpa": gpa,
+        "gpa": {"unweighted": gpa, "weighted": "N/A"},
         "grade_level": grade_level,
         "courses": courses
     }