Sanitize or redact text to ensure anonymous content

Useful linguistic manipulation of text: identify text components, document's main topics, summary & more.
Pingar Pingar
Useful linguistic manipulation of text: identify text components, document's main topics, summary & more.
Sanitize or redact text to ensure anonymous content
GetSanitizedTexts
input: string[] Documents, enum DocumentFormat
output: string[] SanitizedTextsResult

Takes as an input a list of Documents and their DocumentFormat : text or URL.
Replaces identifying entities with randomized entities. Currently sanitizes: People, Organizations, Addresses, Phone Numbers.

Sample code in C#:

PingarAPIRequest request = new PingarAPIRequest();
request.AppID = "your app id";
request.AppKey = "your app key";
request.TextAnalysis = new EntityExtractionRequest();
request.TextAnalysis.Documents = new string[] { "document text" };
request.TextAnalysis.DocumentsFormat = DocumentFormat.Text;
request.Language = Language.EN;

PingarAPIServiceSoapClient pingarAPI = new PingarAPIServiceSoapClient();
PingarAPIResponse response = pingarAPI.GetSanitizedTexts(request);
int count = 0;
if (response.Error == null)
{
    foreach (string document in response.TextAnalysis.SanitizedTextsResult)
    {
        Console.WriteLine("Sanitized Document " + count);
        Console.WriteLine(document);
        count++;
    }
}

 

Explore Pingar