Files
railseek6/reupload_document.py

48 lines
2.2 KiB
Python

import requests
import time
def reupload_document():
base_url = 'http://localhost:3015'
headers = {'X-API-Key': 'jleu1212', 'Content-Type': 'application/json'}
# First, delete the existing document
print('🗑️ Deleting existing document...')
response = requests.delete(f'{base_url}/documents', headers=headers, timeout=10)
print(f'Delete status: {response.status_code}')
if response.status_code == 200:
print('✅ Document deleted successfully')
# Wait a moment for deletion to complete
time.sleep(2)
# Now re-upload the test.docx with the updated processor
print('📤 Re-uploading test.docx with updated processor...')
files = {'file': ('test.docx', open('test.docx', 'rb'), 'application/vnd.openxmlformats-officedocument.wordprocessingml.document')}
upload_response = requests.post(f'{base_url}/upload', files=files, headers={'X-API-Key': 'jleu1212'}, timeout=30)
print(f'Upload status: {upload_response.status_code}')
if upload_response.status_code == 200:
print('✅ Document uploaded successfully')
print('Waiting 10 seconds for processing...')
time.sleep(10)
# Check if document now contains classification
doc_response = requests.get(f'{base_url}/documents', headers=headers, timeout=10)
if doc_response.status_code == 200:
data = doc_response.json()
if data['statuses']['processed']:
doc = data['statuses']['processed'][0]
print(f'\n📄 Updated Document:')
print(f' Content Summary: {doc["content_summary"]}')
if 'Image Classifications:' in doc['content_summary']:
print('✅ SUCCESS: Document now contains classification metadata!')
else:
print('❌ Still no classification metadata - processor may not be updated')
else:
print(f'❌ Upload failed: {upload_response.text}')
else:
print('❌ Failed to delete document')
if __name__ == '__main__':
reupload_document()