document_redaction / tools /example_cli_calls.txt
seanpedrickcase's picture
Repaired Dockerfile hopefully finally
881a64f
raw
history blame
769 Bytes
python cli_redact.py --help
python cli_redact.py \
--input_file "documents/confidential-report.pdf" \
--output_dir "output/redacted_reports/" \
--ocr_method "Local OCR model - PDFs without selectable text" \
--pii_detector "Local" \
--page_min 2 \
--page_max 10 \
--allow_list "config/project_allowlist.csv"
python your_cli_script.py \
--input_file "data/customer_data.xlsx" \
--output_dir "output/anonymised_data/" \
--anon_strat "redact" \
--columns "Customer Name" "Email" \
--excel_sheets "Q3-Data"
python your_cli_script.py \
--input_file "legal_docs/legal_agreement.docx" \
--output_dir "output/anonymised_docs/" \
--anon_strat "encrypt" \
--deny_list "config/codenames.csv" \
--language "en"