Add detailed skip reasons showing why PDFs were skipped

pdf_renamer.py

@@ -59,18 +59,29 @@ def extract_names_from_pdf(pdf_path):
         grade = fields.get('Student Grade', {}).get('/V', '').strip()
         school = fields.get('Student School', {}).get('/V', '').strip()
         
-        if last_name and first_name and grade and school:
+        # Check for missing fields
-            return {
+        missing_fields = []
-                'filename': f"{last_name}_{first_name}.pdf",
+        if not last_name:
-                'last_name': last_name,
+            missing_fields.append('Last Name')
-                'first_name': first_name,
+        if not first_name:
-                'grade': grade,
+            missing_fields.append('First Name')
-                'school': school
+        if not grade:
-            }
+            missing_fields.append('Student Grade')
-        else:
+        if not school:
-            return None
+            missing_fields.append('Student School')
+        
+        if missing_fields:
+            return {'error': f'Missing or empty fields: {", ".join(missing_fields)}'}
+        
+        return {
+            'filename': f"{last_name}_{first_name}.pdf",
+            'last_name': last_name,
+            'first_name': first_name,
+            'grade': grade,
+            'school': school
+        }
     except Exception as e:
-        return None
+        return {'error': f'PDF read error: {str(e)}'}
 
 def process_job(job_id, files):
     job_queue[job_id]['status'] = 'processing'
@@ -125,7 +136,10 @@ def process_job(job_id, files):
                         pdf_path = os.path.join(root, f)
                         job_queue[job_id]['progress'] = f'Processing PDF: {f}'
                         pdf_info = extract_names_from_pdf(pdf_path)
-                        if pdf_info:
+                        if 'error' in pdf_info:
+                            processed_files.append(('skipped', f, pdf_info['error']))
+                            job_queue[job_id]['progress'] = f'Skipped {f} - {pdf_info["error"]}'
+                        else:
                             job_queue[job_id]['progress'] = f'Extracted data for {pdf_info["first_name"]} {pdf_info["last_name"]}'
                             # Create folder structure: Episode/School/Grade/
                             school_dir = os.path.join(episode_dir, pdf_info['school'])
@@ -143,14 +157,14 @@ def process_job(job_id, files):
                             processed_files.append(('success', os.path.relpath(new_path, episode_dir), new_path))
                             processed_count += 1
                             job_queue[job_id]['progress'] = f'Organized {processed_count}/{total_files} files'
-                        else:
-                            processed_files.append(('skipped', f, None))
-                            job_queue[job_id]['progress'] = f'Skipped {f} - missing required fields'
         else:
             # Single PDF
             job_queue[job_id]['progress'] = f'Processing PDF: {filename}'
             pdf_info = extract_names_from_pdf(filepath)
-            if pdf_info:
+            if 'error' in pdf_info:
+                processed_files.append(('skipped', filename, pdf_info['error']))
+                job_queue[job_id]['progress'] = f'Skipped {filename} - {pdf_info["error"]}'
+            else:
                 job_queue[job_id]['progress'] = f'Extracted data for {pdf_info["first_name"]} {pdf_info["last_name"]}'
                 # Create folder structure: Episode/School/Grade/
                 school_dir = os.path.join(episode_dir, pdf_info['school'])
@@ -168,9 +182,6 @@ def process_job(job_id, files):
                 processed_files.append(('success', os.path.relpath(new_filepath, episode_dir), new_filepath))
                 processed_count += 1
                 job_queue[job_id]['progress'] = f'Organized {processed_count}/{total_files} files'
-            else:
-                processed_files.append(('skipped', filename, None))
-                job_queue[job_id]['progress'] = f'Skipped {filename} - missing required fields'
     
     job_queue[job_id]['progress'] = 'Creating ZIP archive...'
     # Create ZIP of the entire Episode directory structure
@@ -195,7 +206,7 @@ def process_job(job_id, files):
     
     job_queue[job_id]['status'] = 'completed'
     job_queue[job_id]['processed_files'] = processed_files
-    job_queue[job_id]['skipped'] = [p[1] for p in processed_files if p[0] == 'skipped']
+    job_queue[job_id]['skipped'] = [(p[1], p[2]) for p in processed_files if p[0] == 'skipped']
 
 @app.route('/login')
 def login():
@@ -418,8 +429,8 @@ def jobs():
                 {% if job.skipped %}
                 <p><strong>Skipped Files:</strong></p>
                 <ul>
-                {% for file in job.skipped %}
+                {% for skip_info in job.skipped %}
-                    <li>{{ file }}</li>
+                    <li><strong>{{ skip_info[0] }}</strong>: {{ skip_info[1] }}</li>
                 {% endfor %}
                 </ul>
                 {% endif %}