File Processing
Anonymize or pseudonymize your PDF, Word, Excel, and PowerPoint documents, Outlook emails, images, and more.
The File Processing tool is the platform’s main feature. It takes a document as input and produces an anonymized or pseudonymized version of that document as output, either preserving its original format or converting it to Markdown format.
Supported Formats
The platform supports a wide range of file formats:
| Format | File Types and Extensions |
|---|---|
.pdf | |
| Word | .docx, .doc |
| Images | .png, .jpg, jpeg |
| Excel | .xlsx, .xls, .csv |
| PowerPoint | .pptx, .ppt |
| Outlook email | .msg |
| +100 text-based files | Markdown, FEC, DSN .json, .txt |
How to Use
- Start a new session from the Sessions page, or continue working from an existing session
- Select the type of processing: anonymization or pseudonymization
- Configure any other settings you deem relevant
- Click the document import area on the right side of your screen or drag and drop your documents
- Click a document to open the editor
Processing Pipeline
When a file is uploaded, the technology performs several steps:
- Extraction of textual content
- Detection of identifying entities
- Replacement according to the selected mode (anonymization or pseudonymization)
- Generation of a new document in the original format or Markdown
Office Suite Documents
The platform offers a unique technology that pseudonymizes or anonymizes images contained within Office documents in the same way as the rest of the document. You have three options to choose from before processing to configure this feature:
- Skip processing
- Remove images from the final document (if they are not relevant to your analysis)
- Process the images
Identifying information contained in comments (including the names of comment authors) and in version tracking blocks is now treated in the same way as identifying information contained in the rest of the documents.
Export
The processed document retains its original format: a PDF input produces a PDF output, an Excel file produces an Excel file, and so on.
The document can also be exported in Markdown format, which is the preferred format, particularly when communicating with an AI assistant.
To download a document, you can:
- Click the Download .zip button in the upper-right corner of your screen on the Overview tab
- Click the Open file button on the document from the Overview tab, then click Download in the lower-right corner of your screen on the Editor tab.