De-identify table data with infoTypes

Stay organized with collections Save and categorize content based on your preferences.

Transform findings found in columns. You can transform findings that either make up part of a cell's content or all of it. In this example, all instances of PERSON_NAME are anonymized.

Explore further

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

Code sample

Java

To learn how to install and use the client library for Cloud DLP, see Cloud DLP client libraries.


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.FieldId;
import com.google.privacy.dlp.v2.FieldTransformation;
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.LocationName;
import com.google.privacy.dlp.v2.PrimitiveTransformation;
import com.google.privacy.dlp.v2.RecordTransformations;
import com.google.privacy.dlp.v2.ReplaceWithInfoTypeConfig;
import com.google.privacy.dlp.v2.Table;
import com.google.privacy.dlp.v2.Table.Row;
import com.google.privacy.dlp.v2.Value;
import java.io.IOException;
import java.util.List;
import java.util.stream.Collectors;
import java.util.stream.Stream;

public class DeIdentifyTableInfoTypes {

  public static void deIdentifyTableInfoTypes() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    Table tableToDeIdentify =
        Table.newBuilder()
            .addHeaders(FieldId.newBuilder().setName("AGE").build())
            .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
            .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
            .addHeaders(FieldId.newBuilder().setName("FACTOID").build())
            .addRows(
                Row.newBuilder()
                    .addValues(Value.newBuilder().setStringValue("101").build())
                    .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
                    .addValues(Value.newBuilder().setStringValue("95").build())
                    .addValues(
                        Value.newBuilder()
                            .setStringValue(
                                "Charles Dickens name was a curse invented by Shakespeare.")
                            .build())
                    .build())
            .addRows(
                Row.newBuilder()
                    .addValues(Value.newBuilder().setStringValue("22").build())
                    .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
                    .addValues(Value.newBuilder().setStringValue("21").build())
                    .addValues(
                        Value.newBuilder()
                            .setStringValue("There are 14 kisses in Jane Austen's novels.")
                            .build())
                    .build())
            .addRows(
                Row.newBuilder()
                    .addValues(Value.newBuilder().setStringValue("55").build())
                    .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
                    .addValues(Value.newBuilder().setStringValue("75").build())
                    .addValues(Value.newBuilder().setStringValue("Mark Twain loved cats.").build())
                    .build())
            .build();

    deIdentifyTableInfoTypes(projectId, tableToDeIdentify);
  }

  public static Table deIdentifyTableInfoTypes(String projectId, Table tableToDeIdentify)
      throws IOException {
    // 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 what content you want the service to de-identify.
      ContentItem contentItem = ContentItem.newBuilder().setTable(tableToDeIdentify).build();

      // Specify how the content should be de-identified.
      // Select type of info to be replaced.
      InfoType infoType = InfoType.newBuilder().setName("PERSON_NAME").build();
      // Specify that findings should be replaced with corresponding info type name.
      ReplaceWithInfoTypeConfig replaceWithInfoTypeConfig =
          ReplaceWithInfoTypeConfig.getDefaultInstance();
      PrimitiveTransformation primitiveTransformation =
          PrimitiveTransformation.newBuilder()
              .setReplaceWithInfoTypeConfig(replaceWithInfoTypeConfig)
              .build();
      // Associate info type with the replacement strategy
      InfoTypeTransformation infoTypeTransformation =
          InfoTypeTransformation.newBuilder()
              .addInfoTypes(infoType)
              .setPrimitiveTransformation(primitiveTransformation)
              .build();
      InfoTypeTransformations infoTypeTransformations =
          InfoTypeTransformations.newBuilder().addTransformations(infoTypeTransformation).build();

      // Specify fields to be de-identified.
      List<FieldId> fieldIds =
          Stream.of("PATIENT", "FACTOID")
              .map(id -> FieldId.newBuilder().setName(id).build())
              .collect(Collectors.toList());

      // Associate the de-identification and conditions with the specified field.
      FieldTransformation fieldTransformation =
          FieldTransformation.newBuilder()
              .setInfoTypeTransformations(infoTypeTransformations)
              .addAllFields(fieldIds)
              .build();
      RecordTransformations transformations =
          RecordTransformations.newBuilder().addFieldTransformations(fieldTransformation).build();

      DeidentifyConfig deidentifyConfig =
          DeidentifyConfig.newBuilder().setRecordTransformations(transformations).build();

      // Combine configurations into a request for the service.
      DeidentifyContentRequest request =
          DeidentifyContentRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setItem(contentItem)
              .setDeidentifyConfig(deidentifyConfig)
              .build();

      // Send the request and receive response from the service.
      DeidentifyContentResponse response = dlp.deidentifyContent(request);

      // Print the results.
      System.out.println("Table after de-identification: " + response.getItem().getTable());

      return response.getItem().getTable();
    }
  }
}

What's next

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