from scripts.data_anonymizer import DataAnonymizer

# Anonymize text
anonymizer = DataAnonymizer()
result = anonymizer.anonymize("Contact John Smith at john@email.com or 555-123-4567")
print(result)
# "Contact [NAME] at [EMAIL] or [PHONE]"

# Anonymize CSV
anonymizer.anonymize_csv("customers.csv", "customers_anon.csv")

anonymizer = DataAnonymizer(
    strategy="mask",      # mask, redact, hash, fake
    reversible=False      # Enable token mapping
)

# Basic anonymization
result = anonymizer.anonymize(text)

# With specific PII types
result = anonymizer.anonymize(text, pii_types=["email", "phone"])

# Get detected PII report
result, report = anonymizer.anonymize(text, return_report=True)

text = "Email john@test.com, call 555-1234"

# Mask (default) - replace with type labels
anonymizer.strategy = "mask"
# "Email [EMAIL], call [PHONE]"

# Redact - replace with asterisks
anonymizer.strategy = "redact"
# "Email ***************, call ********"

# Hash - replace with hash
anonymizer.strategy = "hash"
# "Email a1b2c3d4, call e5f6g7h8"

# Fake - replace with realistic fake data
anonymizer.strategy = "fake"
# "Email jane@example.org, call 555-9876"

# Auto-detect PII columns
anonymizer.anonymize_csv("input.csv", "output.csv")

# Specify columns
anonymizer.anonymize_csv(
    "input.csv",
    "output.csv",
    columns=["name", "email", "phone"]
)

# Different strategies per column
anonymizer.anonymize_csv(
    "input.csv",
    "output.csv",
    column_strategies={
        "name": "fake",
        "email": "hash",
        "ssn": "redact"
    }
)

anonymizer = DataAnonymizer(reversible=True)

# Anonymize with token mapping
result = anonymizer.anonymize("John Smith: john@test.com")
mapping = anonymizer.get_mapping()

# Save mapping securely
anonymizer.save_mapping("mapping.json", encrypt=True, password="secret")

# Later, de-anonymize
anonymizer.load_mapping("mapping.json", password="secret")
original = anonymizer.deanonymize(result)

# Add custom PII pattern
anonymizer.add_pattern(
    name="employee_id",
    pattern=r"EMP-\d{6}",
    label="[EMPLOYEE_ID]"
)

# Anonymize text file
python data_anonymizer.py --input document.txt --output document_anon.txt

# Anonymize CSV
python data_anonymizer.py --input customers.csv --output customers_anon.csv

# Specific strategy
python data_anonymizer.py --input data.csv --output anon.csv --strategy fake

# Generate audit report
python data_anonymizer.py --input document.txt --report audit.json

# Specific PII types only
python data_anonymizer.py --input doc.txt --types email phone ssn

anonymizer = DataAnonymizer(strategy="mask")

log = """
Ticket #1234: Customer John Doe (john.doe@company.com) called about
billing issue. SSN on file: 123-45-6789. Callback number: 555-867-5309.
Address: 123 Oak Street, Springfield, IL 62701.
"""

result = anonymizer.anonymize(log)
print(result)
# Ticket #1234: Customer [NAME] ([EMAIL]) called about
# billing issue. SSN on file: [SSN]. Callback number: [PHONE].
# Address: [ADDRESS].

anonymizer = DataAnonymizer(strategy="hash")

# Consistent hashing for joins
anonymizer.anonymize_csv(
    "users.csv",
    "users_anon.csv",
    columns=["email", "name", "phone"]
)

anonymizer.anonymize_csv(
    "orders.csv",
    "orders_anon.csv",
    columns=["customer_email"]  # Same hash as users.email
)

anonymizer = DataAnonymizer(strategy="fake")

# Replace real PII with realistic fake data
anonymizer.anonymize_csv(
    "production_data.csv",
    "test_data.csv"
)

# Test data has same structure but fake PII

pandas>=2.0.0
faker>=18.0.0