PII Redaction

redaction:
  rules:
    - name: internal_id
      pattern: "INTERNAL-[A-Z0-9]{12}"
      replace: "[REDACTED:internal_id]"
    - name: mrn
      pattern: "MRN-\\d{10}"
      replace: "[REDACTED:mrn]"

from provenlog import Redactor

redactor = Redactor.default()
clean, count = redactor.redact_string("Contact john@example.com or call 555-123-4567")
# clean = "Contact [REDACTED:email] or call [REDACTED:phone]"
# count = 2

import re
from provenlog import Redactor, RedactionRule

redactor = Redactor.default_with_rules([
    RedactionRule("mrn", re.compile(r"MRN-\d{10}"), "[REDACTED:mrn]"),
    RedactionRule("employee_id", re.compile(r"EMP-[A-Z0-9]{8}"), "[REDACTED:employee_id]"),
])
clean, count = redactor.redact_string("Patient MRN-1234567890")
# clean = "Patient [REDACTED:mrn]"