import re
from typing import Dict, Any, Tuple, List

# PII / PHI Redaction Patterns for HIPAA, ABDM, GDPR Compliance
PII_PATTERNS = [
    # 1. India Aadhaar 12-Digit Number
    (r"\b[2-9]\d{3}[-\s]?\d{4}[-\s]?\d{4}\b", "[REDACTED_AADHAAR]"),

    # 2. India ABHA Health ID 14-Digit Number
    (r"\b\d{2}[-\s]?\d{4}[-\s]?\d{4}[-\s]?\d{4}\b", "[REDACTED_ABHA_ID]"),

    # 3. Phone Numbers (Indian +91, 10-digit, US/Intl)
    (r"\b(?:\+?91[-\s]?)?[6-9]\d{9}\b", "[REDACTED_PHONE]"),
    (r"\b(?:\+?1[-\s]?)?\(?\d{3}\)?[-\s]?\d{3}[-\s]?\d{4}\b", "[REDACTED_PHONE]"),

    # 4. Email Addresses
    (r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b", "[REDACTED_EMAIL]"),

    # 5. Social Security Number (US SSN)
    (r"\b\d{3}[-\s]?\d{2}[-\s]?\d{4}\b", "[REDACTED_SSN]"),

    # 6. Credit Card / Debit Card Numbers (16 digits)
    (r"\b(?:\d{4}[-\s]?){3}\d{4}\b", "[REDACTED_PAYMENT]")
]


def anonymize_phi_text(text: str) -> Tuple[str, List[str]]:
    """
    Scrubs sensitive PII/PHI identifiers from text before cloud storage or public broadcast.
    Returns (anonymized_text, list_of_redacted_types).
    """
    if not text or not text.strip():
        return text, []

    scrubbed_text = text
    redacted_categories: List[str] = []

    for pattern, replacement in PII_PATTERNS:
        matches = re.findall(pattern, scrubbed_text, re.IGNORECASE)
        if matches:
            category_name = replacement.replace("[", "").replace("]", "").replace("REDACTED_", "")
            if category_name not in redacted_categories:
                redacted_categories.append(category_name)
            scrubbed_text = re.sub(pattern, replacement, scrubbed_text, flags=re.IGNORECASE)

    return scrubbed_text, redacted_categories