De-identify data: Redacting with matched input values

Uses the Data Loss Prevention API to de-identify sensitive data in a string by redacting matched input values.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

C#

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  using 
  
 System 
 ; 
 using 
  
 System.Collections.Generic 
 ; 
 using 
  
  Google.Api.Gax.ResourceNames 
 
 ; 
 using 
  
  Google.Cloud.Dlp.V2 
 
 ; 
 public 
  
 class 
  
 DeidentifyDataUsingRedactWithMatchedInputValues 
 { 
  
 public 
  
 static 
  
 DeidentifyContentResponse 
  
 Deidentify 
 ( 
  
 string 
  
 projectId 
 , 
  
 string 
  
 text 
 , 
  
 IEnumerable<InfoType> 
  
 infoTypes 
  
 = 
  
 null 
 ) 
  
 { 
  
 // Instantiate the client. 
  
 var 
  
 dlp 
  
 = 
  
  DlpServiceClient 
 
 . 
  Create 
 
 (); 
  
 // Construct inspect config. 
  
 var 
  
 inspectConfig 
  
 = 
  
 new 
  
  InspectConfig 
 
  
 { 
  
 InfoTypes 
  
 = 
  
 { 
  
 infoTypes 
  
 ?? 
  
 new 
  
  InfoType 
 
 [] 
  
 { 
  
 new 
  
  InfoType 
 
  
 { 
  
 Name 
  
 = 
  
 "EMAIL_ADDRESS" 
  
 } 
  
 } 
  
 }, 
  
 }; 
  
 // Construct redact config. 
  
 var 
  
 redactConfig 
  
 = 
  
 new 
  
  RedactConfig 
 
 (); 
  
 // Construct deidentify config using redact config. 
  
 var 
  
 deidentifyConfig 
  
 = 
  
 new 
  
  DeidentifyConfig 
 
  
 { 
  
 InfoTypeTransformations 
  
 = 
  
 new 
  
  InfoTypeTransformations 
 
  
 { 
  
 Transformations 
  
 = 
  
 { 
  
 new 
  
 InfoTypeTransformations 
 . 
 Types 
 . 
 InfoTypeTransformation 
  
 { 
  
 PrimitiveTransformation 
  
 = 
  
 new 
  
  PrimitiveTransformation 
 
  
 { 
  
 RedactConfig 
  
 = 
  
 redactConfig 
  
 } 
  
 } 
  
 } 
  
 } 
  
 }; 
  
 // Construct a request. 
  
 var 
  
 request 
  
 = 
  
 new 
  
  DeidentifyContentRequest 
 
  
 { 
  
 ParentAsLocationName 
  
 = 
  
 new 
  
  LocationName 
 
 ( 
 projectId 
 , 
  
 "global" 
 ), 
  
 DeidentifyConfig 
  
 = 
  
 deidentifyConfig 
 , 
  
 InspectConfig 
  
 = 
  
 inspectConfig 
 , 
  
 Item 
  
 = 
  
 new 
  
  ContentItem 
 
  
 { 
  
 Value 
  
 = 
  
 text 
  
 } 
  
 }; 
  
 // Call the API. 
  
 var 
  
 response 
  
 = 
  
 dlp 
 . 
 DeidentifyContent 
 ( 
 request 
 ); 
  
 // Check the deidentified content. 
  
 Console 
 . 
 WriteLine 
 ( 
 $"Deidentified content: {response.Item. Value 
}" 
 ); 
  
 return 
  
 response 
 ; 
  
 } 
 } 
 

Go

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  import 
  
 ( 
  
 "context" 
  
 "fmt" 
  
 "io" 
  
 dlp 
  
 "cloud.google.com/go/dlp/apiv2" 
  
 "cloud.google.com/go/dlp/apiv2/dlppb" 
 ) 
 // deidentifyWithRedact de-identify the data by redacting with matched input values 
 func 
  
 deidentifyWithRedact 
 ( 
 w 
  
 io 
 . 
 Writer 
 , 
  
 projectID 
 , 
  
 inputStr 
  
 string 
 , 
  
 infoTypeNames 
  
 [] 
 string 
 ) 
  
 error 
  
 { 
  
 // projectID := "my-project-id" 
  
 // inputStr := "My name is Alicia Abernathy, and my email address is aabernathy@example.com." 
  
 // infoTypeNames := []string{"EMAIL_ADDRESS"} 
  
 ctx 
  
 := 
  
 context 
 . 
 Background 
 () 
  
 // Initialize a client once and reuse it to send multiple requests. Clients 
  
 // are safe to use across goroutines. When the client is no longer needed, 
  
 // call the Close method to cleanup its resources. 
  
 client 
 , 
  
 err 
  
 := 
  
 dlp 
 . 
  NewClient 
 
 ( 
 ctx 
 ) 
  
 if 
  
 err 
  
 != 
  
 nil 
  
 { 
  
 return 
  
 fmt 
 . 
 Errorf 
 ( 
 "dlp.NewClient: %w" 
 , 
  
 err 
 ) 
  
 } 
  
 // Closing the client safely cleans up background resources. 
  
 defer 
  
 client 
 . 
  Close 
 
 () 
  
 // Specify the content to be inspected. 
  
 contentItem 
  
 := 
  
& dlppb 
 . 
 ContentItem 
 { 
  
 DataItem 
 : 
  
& dlppb 
 . 
 ContentItem_Value 
 { 
  
 Value 
 : 
  
 inputStr 
 , 
  
 }, 
  
 } 
  
 // Specify the type of info the inspection will look for. 
  
 // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types 
  
 var 
  
 infoTypes 
  
 [] 
 * 
 dlppb 
 . 
 InfoType 
  
 for 
  
 _ 
 , 
  
 it 
  
 := 
  
 range 
  
 infoTypeNames 
  
 { 
  
 infoTypes 
  
 = 
  
 append 
 ( 
 infoTypes 
 , 
  
& dlppb 
 . 
 InfoType 
 { 
 Name 
 : 
  
 it 
 }) 
  
 } 
  
 inspectConfig 
  
 := 
  
& dlppb 
 . 
 InspectConfig 
 { 
  
 InfoTypes 
 : 
  
 infoTypes 
 , 
  
 } 
  
 // Define type of de-identification. 
  
 primitiveTransformation 
  
 := 
  
& dlppb 
 . 
 PrimitiveTransformation 
 { 
  
 Transformation 
 : 
  
& dlppb 
 . 
 PrimitiveTransformation_RedactConfig 
 { 
  
 RedactConfig 
 : 
  
& dlppb 
 . 
 RedactConfig 
 {}, 
  
 }, 
  
 } 
  
 // Associate de-identification type with info type. 
  
 transformation 
  
 := 
  
& dlppb 
 . 
 InfoTypeTransformations_InfoTypeTransformation 
 { 
  
 InfoTypes 
 : 
  
 infoTypes 
 , 
  
 PrimitiveTransformation 
 : 
  
 primitiveTransformation 
 , 
  
 } 
  
 // Construct the configuration for the Redact request and list all desired transformations. 
  
 redactConfig 
  
 := 
  
& dlppb 
 . 
 DeidentifyConfig 
 { 
  
 Transformation 
 : 
  
& dlppb 
 . 
 DeidentifyConfig_InfoTypeTransformations 
 { 
  
 InfoTypeTransformations 
 : 
  
& dlppb 
 . 
 InfoTypeTransformations 
 { 
  
 Transformations 
 : 
  
 [] 
 * 
 dlppb 
 . 
 InfoTypeTransformations_InfoTypeTransformation 
 { 
  
 transformation 
 , 
  
 }, 
  
 }, 
  
 }, 
  
 } 
  
 // Create a configured request. 
  
 req 
  
 := 
  
& dlppb 
 . 
 DeidentifyContentRequest 
 { 
  
 Parent 
 : 
  
 fmt 
 . 
 Sprintf 
 ( 
 "projects/%s/locations/global" 
 , 
  
 projectID 
 ), 
  
 DeidentifyConfig 
 : 
  
 redactConfig 
 , 
  
 InspectConfig 
 : 
  
 inspectConfig 
 , 
  
 Item 
 : 
  
 contentItem 
 , 
  
 } 
  
 // Send the request. 
  
 resp 
 , 
  
 err 
  
 := 
  
 client 
 . 
 DeidentifyContent 
 ( 
 ctx 
 , 
  
 req 
 ) 
  
 if 
  
 err 
  
 != 
  
 nil 
  
 { 
  
 return 
  
 err 
  
 } 
  
 // Print the result. 
  
 fmt 
 . 
 Fprintf 
 ( 
 w 
 , 
  
 "output: %v" 
 , 
  
 resp 
 . 
 GetItem 
 (). 
 GetValue 
 ()) 
  
 return 
  
 nil 
 } 
 

Java

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  import 
  
 com.google.cloud.dlp.v2. DlpServiceClient 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. ContentItem 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. DeidentifyConfig 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. DeidentifyContentRequest 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. DeidentifyContentResponse 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. InfoType 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. InfoTypeTransformations 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. InfoTypeTransformations 
. InfoTypeTransformation 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. InspectConfig 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. LocationName 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. PrimitiveTransformation 
 
 ; 
 import 
  
 com.google.privacy.dlp.v2. RedactConfig 
 
 ; 
 public 
  
 class 
 DeIdentifyWithRedaction 
  
 { 
  
 public 
  
 static 
  
 void 
  
 main 
 ( 
 String 
 [] 
  
 args 
 ) 
  
 throws 
  
 Exception 
  
 { 
  
 // TODO(developer): Replace these variables before running the sample. 
  
 String 
  
 projectId 
  
 = 
  
 "your-project-id" 
 ; 
  
 String 
  
 textToInspect 
  
 = 
  
 "My name is Alicia Abernathy, and my email address is aabernathy@example.com." 
 ; 
  
 deIdentifyWithRedaction 
 ( 
 projectId 
 , 
  
 textToInspect 
 ); 
  
 } 
  
 // Inspects the provided text. 
  
 public 
  
 static 
  
 void 
  
 deIdentifyWithRedaction 
 ( 
 String 
  
 projectId 
 , 
  
 String 
  
 textToRedact 
 ) 
  
 { 
  
 // Initialize client that will be used to send requests. This client only needs to be created 
  
 // once, and can be reused for multiple requests. After completing all of your requests, call 
  
 // the "close" method on the client to safely clean up any remaining background resources. 
  
 try 
  
 ( 
  DlpServiceClient 
 
  
 dlp 
  
 = 
  
  DlpServiceClient 
 
 . 
 create 
 ()) 
  
 { 
  
 // Specify the content to be inspected. 
  
  ContentItem 
 
  
 item 
  
 = 
  
  ContentItem 
 
 . 
 newBuilder 
 (). 
 setValue 
 ( 
 textToRedact 
 ). 
 build 
 (); 
  
 // Specify the type of info the inspection will look for. 
  
 // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types 
  
  InfoType 
 
  
 infoType 
  
 = 
  
  InfoType 
 
 . 
 newBuilder 
 (). 
 setName 
 ( 
 "EMAIL_ADDRESS" 
 ). 
 build 
 (); 
  
  InspectConfig 
 
  
 inspectConfig 
  
 = 
  
  InspectConfig 
 
 . 
 newBuilder 
 (). 
 addInfoTypes 
 ( 
 infoType 
 ). 
 build 
 (); 
  
 // Define type of deidentification. 
  
  PrimitiveTransformation 
 
  
 primitiveTransformation 
  
 = 
  
  PrimitiveTransformation 
 
 . 
 newBuilder 
 () 
  
 . 
  setRedactConfig 
 
 ( 
  RedactConfig 
 
 . 
 getDefaultInstance 
 ()) 
  
 . 
 build 
 (); 
  
 // Associate deidentification type with info type. 
  
  InfoTypeTransformation 
 
  
 transformation 
  
 = 
  
  InfoTypeTransformation 
 
 . 
 newBuilder 
 () 
  
 . 
 addInfoTypes 
 ( 
 infoType 
 ) 
  
 . 
 setPrimitiveTransformation 
 ( 
 primitiveTransformation 
 ) 
  
 . 
 build 
 (); 
  
 // Construct the configuration for the Redact request and list all desired transformations. 
  
  DeidentifyConfig 
 
  
 redactConfig 
  
 = 
  
  DeidentifyConfig 
 
 . 
 newBuilder 
 () 
  
 . 
 setInfoTypeTransformations 
 ( 
  
  InfoTypeTransformations 
 
 . 
 newBuilder 
 (). 
  addTransformations 
 
 ( 
 transformation 
 )) 
  
 . 
 build 
 (); 
  
 // Construct the Redact request to be sent by the client. 
  
  DeidentifyContentRequest 
 
  
 request 
  
 = 
  
  DeidentifyContentRequest 
 
 . 
 newBuilder 
 () 
  
 . 
 setParent 
 ( 
  LocationName 
 
 . 
 of 
 ( 
 projectId 
 , 
  
 "global" 
 ). 
 toString 
 ()) 
  
 . 
 setItem 
 ( 
 item 
 ) 
  
 . 
 setDeidentifyConfig 
 ( 
 redactConfig 
 ) 
  
 . 
 setInspectConfig 
 ( 
 inspectConfig 
 ) 
  
 . 
 build 
 (); 
  
 // Use the client to send the API request. 
  
  DeidentifyContentResponse 
 
  
 response 
  
 = 
  
 dlp 
 . 
 deidentifyContent 
 ( 
 request 
 ); 
  
 // Parse the response and process results 
  
 System 
 . 
 out 
 . 
 println 
 ( 
 "Text after redaction: " 
  
 + 
  
 response 
 . 
  getItem 
 
 (). 
 getValue 
 ()); 
  
 } 
  
 catch 
  
 ( 
 Exception 
  
 e 
 ) 
  
 { 
  
 System 
 . 
 out 
 . 
 println 
 ( 
 "Error during inspectString: \n" 
  
 + 
  
 e 
 . 
 toString 
 ()); 
  
 } 
  
 } 
 } 
 

Node.js

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  // Imports the Google Cloud Data Loss Prevention library 
 const 
  
 DLP 
  
 = 
  
 require 
 ( 
 ' @google-cloud/dlp 
' 
 ); 
 // Instantiates a client 
 const 
  
 dlp 
  
 = 
  
 new 
  
 DLP 
 . 
  DlpServiceClient 
 
 (); 
 // TODO(developer): Replace these variables before running the sample. 
 // const projectId = "your-project-id"; 
 // The string to deidentify 
 // const string = 
 //   'My name is Alicia Abernathy, and my email address is aabernathy@example.com.'; 
 // The infoTypes of information to match 
 // See https://cloud.google.com/dlp/docs/concepts-infotypes for more information 
 // about supported infoTypes. 
 // const infoTypes = [{name: 'EMAIL_ADDRESS'}]; 
 async 
  
 function 
  
 deIdentifyRedaction 
 () 
  
 { 
  
 // Construct deidentify configuration 
  
 const 
  
 deidentifyConfig 
  
 = 
  
 { 
  
 infoTypeTransformations 
 : 
  
 { 
  
 transformations 
 : 
  
 [ 
  
 { 
  
 infoTypes 
 : 
  
 infoTypes 
 , 
  
 primitiveTransformation 
 : 
  
 { 
  
 redactConfig 
 : 
  
 {}, 
  
 }, 
  
 }, 
  
 ], 
  
 }, 
  
 }; 
  
 // Construct inspect configuration 
  
 const 
  
 inspectConfig 
  
 = 
  
 { 
  
 infoTypes 
 : 
  
 infoTypes 
 , 
  
 }; 
  
 // Construct Item 
  
 const 
  
 item 
  
 = 
  
 { 
  
 value 
 : 
  
 string 
 , 
  
 }; 
  
 // Combine configurations into a request for the service. 
  
 const 
  
 request 
  
 = 
  
 { 
  
 parent 
 : 
  
 `projects/ 
 ${ 
 projectId 
 } 
 /locations/global` 
 , 
  
 item 
 , 
  
 deidentifyConfig 
 , 
  
 inspectConfig 
 , 
  
 }; 
  
 // Send the request and receive response from the service 
  
 const 
  
 [ 
 response 
 ] 
  
 = 
  
 await 
  
 dlp 
 . 
 deidentifyContent 
 ( 
 request 
 ); 
  
 // Print the results 
  
 console 
 . 
 log 
 ( 
 `Text after redaction: 
 ${ 
 response 
 . 
 item 
 . 
 value 
 } 
 ` 
 ); 
 } 
 deIdentifyRedaction 
 (); 
 

PHP

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  use Google\Cloud\Dlp\V2\Client\DlpServiceClient; 
 use Google\Cloud\Dlp\V2\ContentItem; 
 use Google\Cloud\Dlp\V2\DeidentifyConfig; 
 use Google\Cloud\Dlp\V2\DeidentifyContentRequest; 
 use Google\Cloud\Dlp\V2\InfoType; 
 use Google\Cloud\Dlp\V2\InfoTypeTransformations; 
 use Google\Cloud\Dlp\V2\InfoTypeTransformations\InfoTypeTransformation; 
 use Google\Cloud\Dlp\V2\InspectConfig; 
 use Google\Cloud\Dlp\V2\PrimitiveTransformation; 
 use Google\Cloud\Dlp\V2\RedactConfig; 
 /** 
 * De-identify data: Redacting with matched input values 
 * Uses the Data Loss Prevention API to de-identify sensitive data in a string by redacting matched input values. 
 * 
 * @param string $callingProjectId      The Google Cloud project id to use as a parent resource. 
 * @param string $textToInspect         The string to deidentify (will be treated as text). 
 */ 
 function deidentify_redact( 
 // TODO(developer): Replace sample parameters before running the code. 
 string $callingProjectId, 
 string $textToInspect = 'My name is Alicia Abernathy, and my email address is aabernathy@example.com.' 
 ): void { 
 // Instantiate a client. 
 $dlp = new DlpServiceClient(); 
 // Specify the content to be de-identify. 
 $contentItem = (new ContentItem()) 
 ->setValue($textToInspect); 
 // Specify the type of info the inspection will look for. 
 $infoType = (new InfoType()) 
 ->setName('EMAIL_ADDRESS'); 
 $inspectConfig = (new InspectConfig()) 
 ->setInfoTypes([$infoType]); 
 // Define type of de-identification. 
 $primitiveTransformation = (new PrimitiveTransformation()) 
 ->setRedactConfig(new RedactConfig()); 
 // Associate de-identification type with info type. 
 $transformation = (new InfoTypeTransformation()) 
 ->setInfoTypes([$infoType]) 
 ->setPrimitiveTransformation($primitiveTransformation); 
 // Construct the configuration for the Redact request and list all desired transformations. 
 $deidentifyConfig = (new DeidentifyConfig()) 
 ->setInfoTypeTransformations((new InfoTypeTransformations()) 
 ->setTransformations([$transformation])); 
 $parent = "projects/$callingProjectId/locations/global"; 
 // Run request 
 $deidentifyContentRequest = (new DeidentifyContentRequest()) 
 ->setParent($parent) 
 ->setDeidentifyConfig($deidentifyConfig) 
 ->setInspectConfig($inspectConfig) 
 ->setItem($contentItem); 
 $response = $dlp->deidentifyContent($deidentifyContentRequest); 
 // Print results 
 printf('Text after redaction: %s', $response->getItem()->getValue()); 
 } 
 

Python

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries .

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  from 
  
 typing 
  
 import 
 List 
 import 
  
 google.cloud.dlp 
 def 
  
 deidentify_with_redact 
 ( 
 project 
 : 
 str 
 , 
 input_str 
 : 
 str 
 , 
 info_types 
 : 
 List 
 [ 
 str 
 ], 
 ) 
 - 
> None 
 : 
  
 """Uses the Data Loss Prevention API to deidentify sensitive data in a 
 string by redacting matched input values. 
 Args: 
 project: The Google Cloud project id to use as a parent resource. 
 input_str: The string to deidentify (will be treated as text). 
 info_types: A list of strings representing info types to look for. 
 Returns: 
 None; the response from the API is printed to the terminal. 
 """ 
 # Instantiate a client 
 dlp 
 = 
 google 
 . 
 cloud 
 . 
  dlp_v2 
 
 . 
  DlpServiceClient 
 
 () 
 # Convert the project id into a full resource id. 
 parent 
 = 
 f 
 "projects/ 
 { 
 project 
 } 
 /locations/global" 
 # Construct inspect configuration dictionary 
 inspect_config 
 = 
 { 
 "info_types" 
 : 
 [{ 
 "name" 
 : 
 info_type 
 } 
 for 
 info_type 
 in 
 info_types 
 ]} 
 # Construct deidentify configuration dictionary 
 deidentify_config 
 = 
 { 
 "info_type_transformations" 
 : 
 { 
 "transformations" 
 : 
 [{ 
 "primitive_transformation" 
 : 
 { 
 "redact_config" 
 : 
 {}}}] 
 } 
 } 
 # Construct item 
 item 
 = 
 { 
 "value" 
 : 
 input_str 
 } 
 # Call the API 
 response 
 = 
 dlp 
 . 
  deidentify_content 
 
 ( 
 request 
 = 
 { 
 "parent" 
 : 
 parent 
 , 
 "deidentify_config" 
 : 
 deidentify_config 
 , 
 "inspect_config" 
 : 
 inspect_config 
 , 
 "item" 
 : 
 item 
 , 
 } 
 ) 
 # Print out the results. 
 print 
 ( 
 response 
 . 
 item 
 . 
 value 
 ) 
 

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser .

Create a Mobile Website
View Site in Mobile | Classic
Share by: