Function deidentify

openmed/core/pii.py:1698–1897

De-identify text by detecting and redacting PII with intelligent merging. Implements multiple de-identification strategies for HIPAA compliance: - **mask**: Replace with placeholders like [NAME], [EMAIL], etc. - **remove**: Remove PII text entirely (empty string) - **replace**: Rep

(
    text: str,
    method: DeidentificationMethod = "mask",
    model_name: str = _DEFAULT_EN_MODEL,
    confidence_threshold: float = 0.7,  # Higher threshold for safety
    keep_year: bool = False,
    shift_dates: Optional[bool] = None,
    date_shift_days: Optional[int] = None,
    patient_key: Optional[str | bytes] = None,
    date_shift_max_days: Optional[int] = None,
    date_shift_secret: Optional[str | bytes] = None,
    keep_mapping: bool = False,
    config: Optional[OpenMedConfig] = None,
    use_smart_merging: bool = True,
    lang: str = "en",
    normalize_accents: Optional[bool] = None,
    use_safety_sweep: bool = True,
    *,
    consistent: bool = False,
    seed: Optional[int] = None,
    locale: Optional[str] = None,
    surrogate_vault: Optional["SurrogateVault"] = None,
    loader: Optional["ModelLoader"] = None,
    policy: Optional[str] = None,
    calibration_thresholds_path: Optional[str | Path] = None,
    custom_recognizer: Any = None,
    audit: bool = False,
    cache_results: bool = False,
    max_cache_entries: int = 128,
)

def deidentify(
    text: str,
    method: DeidentificationMethod = "mask",
    model_name: str = _DEFAULT_EN_MODEL,
    confidence_threshold: float = 0.7,  # Higher threshold for safety
    keep_year: bool = False,
    shift_dates: Optional[bool] = None,
    date_shift_days: Optional[int] = None,
    patient_key: Optional[str | bytes] = None,
    date_shift_max_days: Optional[int] = None,
    date_shift_secret: Optional[str | bytes] = None,
    keep_mapping: bool = False,
    config: Optional[OpenMedConfig] = None,
    use_smart_merging: bool = True,
    lang: str = "en",
    normalize_accents: Optional[bool] = None,
    use_safety_sweep: bool = True,
    *,
    consistent: bool = False,
    seed: Optional[int] = None,
    locale: Optional[str] = None,
    surrogate_vault: Optional["SurrogateVault"] = None,
    loader: Optional["ModelLoader"] = None,
    policy: Optional[str] = None,
    calibration_thresholds_path: Optional[str | Path] = None,
    custom_recognizer: Any = None,
    audit: bool = False,
    cache_results: bool = False,
    max_cache_entries: int = 128,
) -> DeidentificationResult | "AuditReport":
    """De-identify text by detecting and redacting PII with intelligent merging.

    Implements multiple de-identification strategies for HIPAA compliance:

    - **mask**: Replace with placeholders like [NAME], [EMAIL], etc.
    - **remove**: Remove PII text entirely (empty string)
    - **replace**: Replace with fake but realistic data
    - **hash**: Replace with consistent hashed values for entity linking
    - **format_preserve**: Replace structured identifiers with synthetic
      values that keep shape and separators, masking unsupported labels
    - **shift_dates**: Shift dates by random offset while preserving intervals

    Smart merging uses regex patterns to merge fragmented entities (e.g., dates
    split into '01' and '/15/1970' are merged into complete '01/15/1970').

    Args:
        text: Input text to de-identify
        method: De-identification method (mask, remove, replace, hash,
            shift_dates, format_preserve)
        model_name: PII detection model
        confidence_threshold: Minimum confidence for redaction (default 0.7 for safety)
        keep_year: For dates, keep the year unchanged
        shift_dates: Deprecated alias for ``method="shift_dates"``.
        date_shift_days: Specific number of days to shift when ``patient_key``
            is omitted. When ``patient_key`` is supplied, this is treated as a
            legacy maximum absolute offset bound unless ``date_shift_max_days``
            is also supplied.
        patient_key: Optional stable patient identifier used only to derive a