DocSanitizer

DocSanitizer offers a privacy-first approach to document processing with zero cloud interaction. Key capabilities include: • On-device PII censorship (emails, phones, credit cards) • Document shrinking and token optimization • Header, footer, and whitespace stripping • Local named entity recognition (NER) for person names • Offline operation with no telemetry This robust tool converts various document types (PDF, DOCX, HTML, EPUB, spreadsheets) into clean, optimized Markdown. It features a native Rust engine that ensures all processing occurs locally on your device, safeguarding sensitive information from ever leaving your control. Advanced features include automated redaction of medical and financial identifiers like NDC drug codes, ICD-10 diagnosis codes, SSNs, and IBANs, along with support for custom regex rules. DocSanitizer is ideal for individuals and organizations handling confidential data who need to prepare documents for further analysis or archiving without compromising privacy. It's built for those who prioritize data security and demand complete control over their document processing workflow, providing real-time token analytics and live previews for effective content preparation.