{ "steps": [ { "tool": "text_clean", "enabled": true, "options": { "trim": true, "collapse_whitespace": true, "fold_smart_chars": true, "strip_zero_width": true } }, { "tool": "format_standardize", "enabled": true, "options": { "column_types": { "Invoice_Date": "date", "Due_Date": "date", "Amount": "currency", "Email": "email" } } }, { "tool": "missing", "enabled": true, "options": { "strategy": "none", "standardize_sentinels": true, "sentinels": ["—", "-", "?", "(blank)", "TBD", "unknown", "(none)", "N/A", "#N/A"] } }, { "tool": "dedup", "enabled": true, "options": { "survivor_rule": "most_complete", "merge": true, "strategies": [ { "columns": [ {"column": "Invoice", "algorithm": "exact", "threshold": 100} ] } ] } } ] }