How to redact Indian Aadhaar Number, Brazilian CPF number or any other such PII using azure language service.

According to this MS-Document, To identify Brazil support pt-pt, pt-br document languages.

You can use the below code which redact both Aadhar card and Brazil CPF number.

Code:

from azure.ai.textanalytics import TextAnalyticsClient
from azure.core.credentials import AzureKeyCredential


def authenticate_client():
    language_endpoint="https://xxxx.cognitiveservices.azure.com/"
    language_key="72xxxxxxx873476"
    ta_credential = AzureKeyCredential(language_key)
    text_analytics_client = TextAnalyticsClient(
            endpoint=language_endpoint, 
            credential=ta_credential)
    return text_analytics_client

client = authenticate_client()

def pii_recognition_example(client):
    documents = [
        "My Aadhaar number is 1234-5678-9101 and my CPF is 123.456.789-09"
    ]
    response = client.recognize_pii_entities(documents, language="pt-pt")
    result = [doc for doc in response if not doc.is_error]
    for doc in result:
        print("Redacted Text: {}".format(doc.redacted_text))
        for entity in doc.entities:
            print("Entity: {}".format(entity.text))
            print("tCategory: {}".format(entity.category))
            print("tConfidence Score: {}".format(entity.confidence_score))
            print("tOffset: {}".format(entity.offset))
            print("tLength: {}".format(entity.length))
pii_recognition_example(client)

Output:

Redacted Text: My Aadhaar number is ************** and my CPF is **************
Entity: 1234-5678-9101
        Category: PhoneNumber
        Confidence Score: 0.8
        Offset: 21
        Length: 14
Entity: 123.456.789-09
        Category: BRCPFNumber
        Confidence Score: 0.85
        Offset: 50
        Length: 14

Reference:
Quickstart: Detect Personally Identifying Information (PII) in text – Azure AI services | Microsoft Learn

Update:

You can get both category [INUniqueIdentificationNumber,BRCPFNumber] use the below code:

from azure.ai.textanalytics import TextAnalyticsClient
from azure.core.credentials import AzureKeyCredential

# Authenticate the client using your key and endpoint
def authenticate_client():
    language_endpoint = "https://xxx.cognitiveservices.azure.com/"
    language_key = "727xxxx9873476"
    ta_credential = AzureKeyCredential(language_key)
    text_analytics_client = TextAnalyticsClient(endpoint=language_endpoint, credential=ta_credential)
    return text_analytics_client

client = authenticate_client()

def pii_recognition_example(client):
    documents = [
        "My Aadhaar number is 4x39 xxxx9 9xx6 and my CPF is 123.456.789-09"
    ]
    
    response_pt = client.recognize_pii_entities(documents, language="pt")
    response_en = client.recognize_pii_entities(documents, language="en")
    
    result_pt = [doc for doc in response_pt if not doc.is_error]
    result_en = [doc for doc in response_en if not doc.is_error]
    
    for doc_pt, doc_en in zip(result_pt, result_en):
        # Prioritize redaction from both responses by merging
        combined_redacted_text = doc_pt.redacted_text  # Start with PT redacted text
        # Since we want both to be redacted, check and apply additional redactions from EN result
        for entity in doc_en.entities:
            if entity.text in combined_redacted_text:
                combined_redacted_text = combined_redacted_text.replace(entity.text, '*' * len(entity.text))

        print("Redacted Text (Combined): {}".format(combined_redacted_text))
        
        # Collect and display categories from both responses
        categories = set()
        for entity in doc_pt.entities:
            categories.add(entity.category)
        for entity in doc_en.entities:
            categories.add(entity.category)
        
        for category in categories:
            print("tCategory: {}".format(category))

pii_recognition_example(client)

Output:

  Redacted Text (Combined): My Aadhaar number is ************** and my CPF is **************
        Category: BRCPFNumber
        Category: INUniqueIdentificationNumber