The first doc is the file i uploaded and then started chatting and the 2nd doc is the whole conversation, now do it where it stopped
/home/daytona/skills/docx
cd /home/daytona/skills/docx/scripts/office && python soffice.py --headless --convert-to docx "/home/daytona/workspace/attachments/2027b77e-e5ed-4e5a-83d9-492f5b30565f/山东医药大学_一带一路\"下中医药文化的新媒体传播_2026年06月08日20时21分25秒.doc" && echo "Done"
ls "/home/daytona/workspace/attachments/2027b77e-e5ed-4e5a-83d9-492f5b30565f/" && file "/home/daytona/workspace/attachments/2027b77e-e5ed-4e5a-83d9-492f5b30565f/山东医药大学_一带一路\"下中医药文化的新媒体传播_2026年06月08日20时21分25秒.doc"
DOCFILE=$(ls "/home/daytona/workspace/attachments/2027b77e-e5ed-4e5a-83d9-492f5b30565f/" | grep "\.doc$") && echo "File: $DOCFILE" && cp "/home/daytona/workspace/attachments/2027b77e-e5ed-4e5a-83d9-492f5b30565f/$DOCFILE" /home/daytona/workspace/original.doc && python /home/daytona/skills/docx/scripts/office/soffice.py --headless --convert-to docx /home/daytona/workspace/original.doc && echo "Conversion done"
# Try antiword to read the .doc file antiword /home/daytona/workspace/original.doc 2>/dev/null | head -200 || echo "antiword not available" # Try catdoc catdoc /home/daytona/workspace/original.doc 2>/dev/null | head -200 || echo "catdoc not available"
# Try pandoc to read .doc pandoc /home/daytona/workspace/original.doc -t plain 2>/dev/null | head -300 || echo "Pandoc failed" # Also try reading bytes to see what format it is python3 -c " with open('/home/daytona/workspace/original.doc', 'rb') as f: header = f.read(8) print('Header bytes:', header.hex()) print('Header:', header) "
python3 -c " import re with open('/home/daytona/workspace/original.doc', 'r', encoding='utf-8', errors='ignore') as f: content = f.read() # Strip HTML tags text = re.sub(r'<[^>]+>', '', content) text = re.sub(r' ', ' ', text) text = re.sub(r'<', '<', text) text = re.sub(r'>', '>', text) text = re.sub(r'&', '&', text) text = re.sub(r'\n\s*\n\s*\n', '\n\n', text) print(text[:8000]) "
python3 -c " import re with open('/home/daytona/workspace/original.doc', 'r', encoding='utf-8', errors='ignore') as f: content = f.read() text = re.sub(r'<[^>]+>', '', content) text = re.sub(r' ', ' ', text) text = re.sub(r'<', '<', text) text = re.sub(r'>', '>', text) text = re.sub(r'&', '&', text) text = re.sub(r'\n\s*\n\s*\n', '\n\n', text) print(text[8000:16000]) " && echo "---DONE---"
python3 -c " import re with open('/home/daytona/workspace/original.doc', 'r', encoding='utf-8', errors='ignore') as f: content = f.read() text = re.sub(r'<[^>]+>', '', content) text = re.sub(r' ', ' ', text) text = re.sub(r'<', '<', text) text = re.sub(r'>', '>', text) text = re.sub(r'&', '&', text) text = re.sub(r'\n\s*\n\s*\n', '\n\n', text) print(len(text)) print('---16000 onwards---') print(text[16000:]) "