DataMask

#!/usr/bin/env python3
"""
DataMask - Real-time developer-first data obfuscation engine.

Provides high-performance, utility-preserving data masking and anonymization
for sensitive payloads. Designed for seamless integration into AI pipelines,
testing environments, and analytics workloads ensuring GDPR and HIPAA compliance.

Features:
- Deterministic and randomized masking strategies for PII/PHI.
- Context-aware schema preservation for structured JSON and tabular data.
- Zero-dependency, real-time stream and batch processing capabilities.
- Built-in tokenization engine with format-preserving encryption (FPE).
- Configurable compliance presets for HIPAA, GDPR, and PCI-DSS.

Usage:
    $ python main.py --config mask_config.json --input input.json
    $ python main.py --preset hipaa --stream < raw_feed.log
"""

import enum
import hashlib
import logging
import re
from dataclasses import dataclass
from typing import Any, Dict, List, Optional, Pattern


class MaskingStrategy(enum.Enum):
    """Supported data transformation strategies."""
    REDACT = "redact"
    HASH = "hash"
    TOKENIZE = "tokenize"
    NOISE = "noise"
    SYNTHETIC = "synthetic"


@dataclass(frozen=True)
class MaskingRule:
    """Configuration rule defining target fields and applied strategy."""
    pattern: Pattern[str]
    strategy: MaskingStrategy
    salt: Optional[str] = None
    replacement: str = "[REDACTED]"


class DataMaskEngine:
    """Core engine responsible for parsing and transforming sensitive payloads."""

    def __init__(self, rules: List[MaskingRule], secret_key: str = "") -> None:
        self._rules = rules
        self._secret_key = secret_key
        self._logger = logging.getLogger("datamask.engine")

# ... the full file ships with your download