You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Fix DOCX XML structure issues"""
|
|
import zipfile
|
|
import xml.etree.ElementTree as ET
|
|
from pathlib import Path
|
|
import tempfile
|
|
import shutil
|
|
|
|
docx_path = '/sessions/dreamy-great-hypatia/mnt/mdp/Fabric prime/02_Appendix_A_Security_Privacy_Model_Fabric_Primary_v1.docx'
|
|
|
|
# Read the docx as a zip
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
# Extract
|
|
with zipfile.ZipFile(docx_path, 'r') as zip_ref:
|
|
zip_ref.extractall(tmpdir)
|
|
|
|
# Read document.xml
|
|
doc_path = Path(tmpdir) / 'word' / 'document.xml'
|
|
with open(doc_path, 'r', encoding='utf-8') as f:
|
|
content = f.read()
|
|
|
|
# The issue is likely that the document element is not properly closed
|
|
# Ensure it ends properly
|
|
if not content.strip().endswith('</w:document>'):
|
|
print("Fixing document.xml structure...")
|
|
# Remove any stray characters after the last proper closing tag
|
|
if '</w:document>' in content:
|
|
idx = content.rfind('</w:document>')
|
|
content = content[:idx + len('</w:document>')]
|
|
|
|
# Write back
|
|
with open(doc_path, 'w', encoding='utf-8') as f:
|
|
f.write(content)
|
|
|
|
# Repack the zip
|
|
with zipfile.ZipFile(docx_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
|
|
for root, dirs, files in __import__('os').walk(tmpdir):
|
|
for file in files:
|
|
file_path = Path(root) / file
|
|
arcname = file_path.relative_to(tmpdir)
|
|
zipf.write(file_path, arcname)
|
|
|
|
print(f"Fixed {docx_path}")
|