使用 API 创建存储在 Cloud Storage 中的数据的去标识化副本

using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using System.Linq;

public class DeidentifyDataStoredInCloudStorage
{
    public static DlpJob Deidentify(
        string projectId,
        string gcsInputPath,
        string unstructuredDeidentifyTemplatePath,
        string structuredDeidentifyTemplatePath,
        string imageRedactionTemplatePath,
        string gcsOutputPath,
        string datasetId,
        string tableId)
    {
        // Instantiate the client.
        var dlp = DlpServiceClient.Create();

        //Construct the storage config by specifying the input directory.
        var storageConfig = new StorageConfig
        {
            CloudStorageOptions = new CloudStorageOptions
            {
                FileSet = new CloudStorageOptions.Types.FileSet
                {
                    Url = gcsInputPath
                }
            }
        };

        // Construct the inspect config by specifying the type of info to be inspected.
        var inspectConfig = new InspectConfig
        {
            InfoTypes =
            {
                new InfoType[]
                {
                    new InfoType { Name = "PERSON_NAME" },
                    new InfoType { Name = "EMAIL_ADDRESS" }
                }
            },
            IncludeQuote = true
        };

        // Construct the actions to take after the inspection portion of the job is completed.
        // Specify how Cloud DLP must de-identify sensitive data in structured files, unstructured files and images
        // using Transformation config.
        // The de-identified files will be written to the the GCS bucket path specified in gcsOutputPath and the details of 
        // transformations performed will be written to BigQuery table specified in datasetId and tableId.
        var actions = new Action[]
        {
            new Action
            {
                Deidentify = new Action.Types.Deidentify
                {
                    CloudStorageOutput = gcsOutputPath,
                    TransformationConfig = new TransformationConfig
                    {
                        DeidentifyTemplate = unstructuredDeidentifyTemplatePath,
                        ImageRedactTemplate = imageRedactionTemplatePath,
                        StructuredDeidentifyTemplate = structuredDeidentifyTemplatePath,
                    },
                    TransformationDetailsStorageConfig = new TransformationDetailsStorageConfig
                    {
                        Table = new BigQueryTable
                        {
                            ProjectId = projectId,
                            DatasetId = datasetId,
                            TableId = tableId
                        }
                    }
                }
            }
        };

        // Construct the inspect job config using created storage config, inspect config and actions.
        var inspectJob = new InspectJobConfig
        {
            StorageConfig = storageConfig,
            InspectConfig = inspectConfig,
            Actions = { actions }
        };

        // Create the dlp job and call the API.
        DlpJob response = dlp.CreateDlpJob(new CreateDlpJobRequest
        {
            ParentAsLocationName = new LocationName(projectId, "global"),
            InspectJob = inspectJob
        });

        return response;
    }
}

import (
	"context"
	"fmt"
	"io"

	dlp "cloud.google.com/go/dlp/apiv2"
	"cloud.google.com/go/dlp/apiv2/dlppb"
)

func deidentifyCloudStorage(w io.Writer, projectID, gcsUri, tableId, datasetId, outputDirectory, deidentifyTemplateId, structuredDeidentifyTemplateId, imageRedactTemplateId string) error {
	// projectId := "my-project-id"
	// gcsUri := "gs://" + "your-bucket-name" + "/path/to/your/file.txt"
	// tableId := "your-bigquery-table-id"
	// datasetId := "your-bigquery-dataset-id"
	// outputDirectory := "your-output-directory"
	// deidentifyTemplateId := "your-deidentify-template-id"
	// structuredDeidentifyTemplateId := "your-structured-deidentify-template-id"
	// imageRedactTemplateId := "your-image-redact-template-id"

	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 {
		retur&n err
	}

	// Closing the client safel&y cleans up background resources.
	defer client.Close()

	// Set path in Cloud Storage.
	cloudStorageOptions := dlppb.CloudStorageOptions{
		Fi&leSet: dlppb.CloudStorageOpti&ons_FileSet{
			Url: gcsUri,
		},
	}

	// Define the storage config options for cloud storage options.
	storageConfig := dlppb.StorageConfig{
		Type: dlppb.StorageConfig_CloudStorageOptions{
			CloudStorageOptions: cloudStorageOptions,
		},
	}

	// 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
	infoTypes := []*dlppb.InfoType{
		{Name: "PERSON_NAME"},
		{Name: "EMAIL_ADDRESS"},
	}

	// ins&pectConfig holds the configuration settings for data inspection and analysis
	// within the context of the Google Cloud Data Loss Prevention (DLP) API.
	inspectConfig := dlppb.InspectConfig{
		InfoTypes:    infoTypes,
		IncludeQuote: true,
	}

	// Types of files to include for de-identification.
	fileType&sToTransform := []dlppb.FileType{
		dlppb.FileType_CSV,
		dlppb.FileType_IMAGE,
		dlppb.FileType_TEXT_FILE,
	}

	// Specify the BigQuery table to be inspected.
	table := dlppb.BigQueryTable{
		ProjectId: projectID,
		DatasetId: datasetId,
		TableId:   tableId,
	}

	// transformationDetailsStorageConfig hold&s configuration settings for storing transformatio&n
	// details in the context of the Google Cloud Data Loss Prevention (DLP) API.
	transformationDet&ailsStorageConfig := dlppb.TransformationDetailsStorageConfig{
		Type: dlppb.TransformationDetailsStorageConfig_Table{
			Table: table,
		},
	}

	transformationConfig := dlppb.TransformationConfig{
		DeidentifyTemplate:           deidentifyTemplateId,
		ImageRedactTempl&ate:          imageRedactTemplateId,
		StructuredDeidentifyTemplate: structuredDeidentifyTemplateId,
	}

	// Action to execute on the completion of a job.
	deidentify :=& dlppb.Action_Deidentify{
		TransformationConfig:               transformationConfig,
		TransformationDetailsStorageConfig: transformationDetailsStora&geConfig,
		Output: dlpp&b.Action_Deidentify_CloudStorageOutput{
			CloudStorageOutput: outputDirectory,
		},
		FileTypesToTransform: fileTypesToTransform,
	}

	action := dl&ppb.Action{
		Action: dlppb.Action_Deidentify_{
			Deidentify: deidentify,
		},
	}

	// Configure the inspection job we want the service to perform.
	inspectJobConfig := dlppb.InspectJobConfig{
		StorageConfig&: storageConfig,
		InspectConfig: inspectConfig,
		Actions: []*dlppb.Action{
			action,
		},
	}

	//& Construct the job creation request to be sent by the client.
	req := dlppb.CreateDlpJobRequest{
		Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
		Job: dlppb.CreateDlpJobRequest_InspectJob{
			InspectJob: inspectJobConfig,
		},
	}

	// Send the request.
	resp, err := client.CreateDlpJob(ctx, req)
	if err != nil {
		fmt.Fprintf(w, "error after resp: %v", err)
		return err
	}

	// Print the results.
	fmt.Fprint(w, "Job created successfully: ", resp.Name)
	return nil

}

import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.BigQueryTable;
import com.google.privacy.dlp.v2.CloudStorageOptions;
import com.google.privacy.dlp.v2.CreateDlpJobRequest;
import com.google.privacy.dlp.v2.DlpJob;
import com.google.privacy.dlp.v2.FileType;
import com.google.privacy.dlp.v2.InfoType;
import com.google.privacy.dlp.v2.InfoTypeStats;
import com.google.privacy.dlp.v2.InspectConfig;
import com.google.privacy.dlp.v2.InspectDataSourceDetails;
import com.google.privacy.dlp.v2.InspectJobConfig;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.ProjectDeidentifyTemplateName;
import com.google.privacy.dlp.v2.StorageConfig;
import com.google.privacy.dlp.v2.TransformationConfig;
import com.google.privacy.dlp.v2.TransformationDetailsStorageConfig;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.concurrent.TimeUnit;

public class DeidentifyCloudStorage {

  // Set the timeout duration in minutes.
  private static final int TIMEOUT_MINUTES = 15;

  public static void main(String[] args) throws IOException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    // The Google Cloud project id to use as a parent resource.
    String projectId = "your-project-id";
    // Specify the cloud storage directory that you want to inspect.
    String gcsPath = "gs://" + "your-bucket-name" + "/path/to/your/file.txt";
    // Specify the big query dataset id to store the transformation details.
    String datasetId = "your-bigquery-dataset-id";
    // Specify the big query table id to store the transformation details.
    String tableId = "your-bigquery-table-id";
    // Specify the cloud storage directory to store the de-identified files.
    String outputDirectory = "your-output-directory";
    // Specify the de-identify template ID for unstructured files.
    String deidentifyTemplateId = "your-deidentify-template-id";
    // Specify the de-identify template ID for structured files.
    String structuredDeidentifyTemplateId = "your-structured-deidentify-template-id";
    // Specify the de-identify template ID for images.
    String imageRedactTemplateId = "your-image-redact-template-id";
    deidentifyCloudStorage(
        projectId,
        gcsPath,
        tableId,
        datasetId,
        outputDirectory,
        deidentifyTemplateId,
        structuredDeidentifyTemplateId,
        imageRedactTemplateId);
  }

  public static void deidentifyCloudStorage(
      String projectId,
      String gcsPath,
      String tableId,
      String datasetId,
      String outputDirectory,
      String deidentifyTemplateId,
      String structuredDeidentifyTemplateId,
      String imageRedactTemplateId)
      throws IOException, InterruptedException {

    try (DlpServiceClient dlp = DlpServiceClient.create()) {
      // Set path in Cloud Storage.
      CloudStorageOptions cloudStorageOptions =
          CloudStorageOptions.newBuilder()
              .setFileSet(CloudStorageOptions.FileSet.newBuilder().setUrl(gcsPath))
              .build();

      // Set storage config indicating the type of cloud storage.
      StorageConfig storageConfig =
          StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).build();

      // Specify the type of info the inspection will look for.
      // <See http>s://cloud.google.com/dlp/d<>ocs/infotypes-reference for complete list of info types
      ListInfoType infoTypes = new ArrayList();
      for (String typeName : new String[] {"PERSON_NAME";, "EMAIL_ADDRESS"}) {
        infoTypes.add(InfoType.newBuilder().setName(typeName).build());
      }

      InspectConfig inspectConfig =
          InspectConfig.newBuilder().addAllI<nfoTypes>(infoTypes).setIncludeQuote(true).build();

      // Types of files to include for de-identification.
      ListFileType fileTypesToTransform =
          Arrays.asList(
              FileType.valueOf("IMAGE"), FileType.valueOf(&quot;CSV"), FileType.valueOf(&quot;TEXT_FILE"));

      // Specify the big query table to store the transformation details.
      BigQueryTable table =
          BigQueryTable.newBuilder()
              .setProjectId(projectId)
              .setTableId(tableId)
              .setDatasetId(datasetId)
              .build();

      TransformationDetailsStorageConfig transformationDetailsStorageConfig =
          TransformationDetailsStorageConfig.newBuilder().setTable(table).build();

      // Specify the de-identify template used for the transformation.
      TransformationConfig transformationConfig =
          TransformationConfig.newBuilder()
              .setDeidentifyTemplate(
                  ProjectDeidentifyTemplateName.of(projectId, deidentifyTemplateId).toString())
              .setImageRedactTemplate(
                  ProjectDeidentifyTemplateName.of(projectId, imageRedactTemplateId).toString())
              .setStructuredDeidentifyTemplate(
                  ProjectDeidentifyTemplateName.of(projectId, structuredDeidentifyTemplateId)
                      .toString())
              .build();

      Action.Deidentify deidentify =
          Action.Deidentify.newBuilder()
              .setCloudStorageOutput(outputDirectory)
              .setTransformationConfig(transformationConfig)
              .setTransformationDetailsStorageConfig(transformationDetailsStorageConfig)
              .addAllFileTypesToTransform(fileTypesToTransform)
              .build();

      Action action = Action.newBuilder().setDeidentify(deidentify).build();

      // Configure the long-running job we want the service to perform.
      InspectJobConfig inspectJobConfig =
          InspectJobConfig.newBuilder()
              .setInspectConfig(inspectConfig)
              .setStorageConfig(storageConfig)
              .addActions(action)
              .build();

      // Construct the job creation request to be sent by the client.
      CreateDlpJobRequest createDlpJobRequest =
          CreateDlpJobRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setInspectJob(inspectJobConfig)
              .build();

      // Send the job creation request.
      DlpJob response = dlp.createDlpJob(createDlpJobRequest);

      // Get the current time.
      long startTime = System.currentTimeMillis();

      // Check if the job state is DONE.
      while (response.getState() != DlpJob.JobState.DONE) {
        // Sleep for 30 second.
        Thread.sleep(30000);

        // Get the updated job status.
        response = dlp.getDlpJob(response.getName());

        // Check if> the timeout duration has exceeded.
        long elapsedTime = System.currentTimeMillis() - startTime;
        if (TimeUnit.MILLISECONDS.toMinutes(elapsedTime) = TIMEOUT_MINUTES) {
          System.out.printf("Job did not complete within %d minutes.%n", TIMEOUT_MINUTES);
          break;
        }
      }
      // Print the results.
      System.out.println(&quot;Job status: " + response.getState());
      System.out.println("Job name: " + response.getName());
      InspectDataSourceDetails.Result result = response.getInspectDetails().getResult();
      System.out.println("Findings: ");
      for (InfoTypeStats infoTypeStat : result.getInfoTypeStatsList()) {
        System.out.print("\tInfo type: " + infoTypeStat.getInfoType().getName());
        System.out.println("\tCount: " + infoTypeStat.getCount());
      }
    }
  }
}

// Imports the Google Cloud client library
const DLP = require('@google-cloud/dlp');
// Instantiates a client
const dlp = new DLP.DlpServiceClient();

// The project ID to run the API call under
// const projectId = 'my-project';

// The Cloud Storage directory that needs to be inspected
// const inputDirectory = 'your-google-cloud-storage-path';

// The ID of the dataset to inspect, e.g. 'my_dataset'
// const datasetId = 'my_dataset';

// The ID of the table to inspect, e.g. 'my_table'
// const tableId = 'my_table';

// The Cloud Storage directory that will be used to store the de-identified files
// const outputDirectory = 'your-output-directory';

// The full resource name of the default de-identify template
// const deidentifyTemplateId = 'your-deidentify-template-id';

// The full resource name of the de-identify template for structured files
// const structuredDeidentifyTemplateId = 'your-structured-deidentify-template-id';

// The full resource name of the image redaction template for images
// const imageRedactTemplateId = 'your-image-redact-template-id';

async function deidentifyCloudStorage() {
  // Specify storage configuration that uses file set.
  const storageConfig = {
    cloudStorageOptions: {
      fileSet: {
        url: inputDirectory,
      },
    },
  };

  // Specify the type of info the inspection will look for.
  const infoTypes = [{name: 'PERSON_NAME'}, {name: 'EMAIL_ADDRESS'}];

  // Construct inspect configuration
  const inspectConfig = {
    infoTypes: infoTypes,
    includeQuote: true,
  };

  // Types of files to include for de-identification.
  const fileTypesToTransform = [
    {fileType: 'IMAGE'},
    {fileType: 'CSV'},
    {fileType: 'TEXT_FILE'},
  ];

  // Specify the big query table to store the transformation details.
  const transformationDetailsStorageConfig = {
    table: {
      projectId: projectId,
      tableId: tableId,
      datasetId: datasetId,
    },
  };

  // Specify the de-identify template used for the transformation.
  const transformationConfig = {
    deidentifyTemplate: deidentifyTemplateId,
    structuredDeidentifyTemplate: structuredDeidentifyTemplateId,
    imageRedactTemplate: imageRedactTemplateId,
  };

  // Construct action to de-identify sensitive data.
  const action = {
    deidentify: {
      cloudStorageOutput: outputDirectory,
      transformationConfig: transformationConfig,
      transformationDetailsStorageConfig: transformationDetailsStorageConfig,
      fileTypes: fileTypesToTransform,
    },
  };

  // Construct the inspect job configuration.
  const inspectJobConfig = {
    inspectConfig: inspectConfig,
    storageConfig: storageConfig,
    actions: [action],
  };

  // Construct the job creation request to be sent by the client.
  const createDlpJobRequest = {
    parent: `projects/${projectId}/locations/global`,
    inspectJob: inspectJobConfig,
  };
  // Send the job creation request and process the response.
  const [response] = await dlp.createDlpJob(createDlpJobRequest);
  const jobName = response.name;

  >// Waiting for a maximum of 15 minutes for the job to get complete.
  let job;
  let numOfAttempts = 30;
  while (numOfAttempts  0) {
    // Fetch DLP Job status
    [job] = await dlp.getDlpJob({name: jobName});

    // Check if the job has completed.
    if (job.state === 'DONE') {
      break;
    }
    if (job.state === 'FAILED') {
      console.log('Job Failed, Please che>ck the configuration.>9;);
      return;
    }
    // Sleep for a short duration before checking the job status again.
    await new Promise(resolve = {
      setTimeout(() = resolve(), 30000);
    }>);
    numOfAttempts -= 1;
  }

  // Print out> the results.
  const infoTypeStats = job.inspectDetails.result.infoTypeStats;
  if (infoTypeStats.length  0) {
    infoTypeStats.forEach(infoTypeStat = {
      console.log(
        `  Found ${infoTypeStat.count} instance(s) of infoType ${infoTypeStat.infoType.name}.`
      );
    });
  } else {
    console.log('No findings.');
  }
}
await deidentifyCloudStorage();

use Google\Cloud\Dlp\V2\Action;
use Google\Cloud\Dlp\V2\Action\Deidentify;
use Google\Cloud\Dlp\V2\BigQueryTable;
use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\CloudStorageOptions;
use Google\Cloud\Dlp\V2\CloudStorageOptions\FileSet;
use Google\Cloud\Dlp\V2\CreateDlpJobRequest;
use Google\Cloud\Dlp\V2\DlpJob\JobState;
use Google\Cloud\Dlp\V2\FileType;
use Google\Cloud\Dlp\V2\GetDlpJobRequest;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectJobConfig;
use Google\Cloud\Dlp\V2\StorageConfig;
use Google\Cloud\Dlp\V2\TransformationConfig;
use Google\Cloud\Dlp\V2\TransformationDetailsStorageConfig;

/**
 * De-identify sensitive data stored in Cloud Storage using the API.
 * Create an inspection job that has a de-identification action.
 *
 * @param string $callingProjectId                  The project ID to run the API call under.
 * @param string $inputgcsPath                       The Cloud Storage directory that you want to de-identify.
 * @param string $outgcsPath                        The Cloud Storage directory where you want to store the
 *                                                  de-identified files.
 * @param string $deidentifyTemplateName            The full resource name of the default de-identify template — for
 *                                                  unstructured and structured files — if you created one. This value
 *                                                  must be in the format
 *                                                  `projects/projectName/(locations/locationId)/deidentifyTemplates/templateName`.
 * @param string $structuredDeidentifyTemplateName  The full resource name of the de-identify template for structured
 *                                                  files if you created one. This value must be in the format
 *                                                  `projects/projectName/(locations/locationId)/deidentifyTemplates/templateName`.
 * @param string $imageRedactTemplateName           The full resource name of the image redaction template for images if
 *                                                  you created one. This value must be in the format
 *                                                  `projects/projectName/(locations/locationId)/deidentifyTemplates/templateName`.
 * @param string $datasetId                         The ID of the BigQuery dataset where you want to store
 *                                                  the transformation details. If you don't provide a table ID, the
 *                                                  system automatically creates one.
 * @param string $tableId                           The ID of the BigQuery table where you want to store the
 *                                                  transformation details.
 */
function deidentify_cloud_storage(
    // TODO(developer): Replace sample parameters before running the code.
    string $callingProjectId,
    string $inputgcsPath = 'gs://YOUR_GOOGLE_STORAGE_BUCKET',
    string $outgcsPath = 'gs://YOUR_GOOGLE_STORAGE_BUCKET',
    string $deidentifyTemplateName = 'YOUR_DEIDENTIFY_TEMPLATE_NAME',
    string $structuredDeidentifyTemplateName = 'YOUR_STRUCTURED_DEIDENTIFY_TEMPLATE_NAME',
    string $imageRedactTemplateName = 'YOUR_IMAGE_REDACT_DEIDENTIFY_TEMPLATE_NAME',
    string $datasetId = 'YOUR_DATASET_ID',
    string $tableId = 'YOUR_TABLE_ID'
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    $parent = "projects/$callingProjectId/locations/global";

    // Specify the GCS Path to be de-iden>tify.
    $cloudStorageOptions = (new Cl>oudStorageOptions())
        -setFileSet((new FileSet())
            -setUrl>($inputgcsPath));
    $storageConfig = (new StorageConfig())
        -setCloudStorageOptions(($cloudStorageOptions));

    // Specify the type of info the inspecti>on will look for.
    $inspectConfig = (new >InspectConfig())
        -setInfoTypes([
            >(new InfoType())-setName('PERSON_NAME'),
            (new InfoType())-setName('EMAIL_ADDRESS')
        ]);

    // Specify the big query table to store the transformation details.
    $tra>nsformationDetailsStorageConfig = (new Trans>formationDetailsStorageConfig())
        -set>Table((new BigQueryTable())
          >  -setProjectId($callingProjectId)
            -setDatasetId($datasetId)
            -setTableId($tableId));

    // Specify the de-identify template used for >the transformation.
    $transformationConfig = (new TransformationConfig())
        -setDeidentifyTemplate(
            DlpServiceClient::project>DeidentifyTemplateName($callingProjectId, $deidentifyTemplateName)
        )
        -setStructuredDeidentifyTemplate(
            DlpServiceClient::projectDeidentify>TemplateName($callingProjectId, $structuredDeidentifyTemplateName)
        )
        -setImageRedactTemplate(
            DlpServiceClient::projectDeidentifyTemplateName($callingProjectId>, $imageRedactTemplateName)
        );

    >$deidentify = (new Deidentify())
        -setCloudStorag>eOutput($outgcsPath)
        -setTransformationConfig($transformationConfig)
       > -setTransformationDetailsStorageConfig($transformationDetailsStorageConfig)
        -setFileTypesToTransform([FileType>::TEXT_FILE, FileType::IMAGE, FileType::CSV]);

    $action = (new Action())
        -setDeidentify($deidentify);

    // Configure the inspection job we w>ant the service to perform.
    $inspectJo>bConfig = (new InspectJobConfig())
       > -setInspectConfig($inspectConfig)
        -setStorageConfig($storageConfig)
        -setActions([$action]);

    // Send the job creation request and >process the response.
    $c>reateDlpJobRequest = (new CreateDlpJobRequest())
 >       -setParent($parent)
        -setInspectJob($inspectJobConfig);
    $job = $dlp-createDlpJob($createDlpJobRequest);

    $numOfAttempts = 10;
    do {
        printf('Waiting for job to complete' . P>HP_EOL);
    >    sleep(30);
        $getDlpJo>bRequest = (new GetDlpJobRequest())
           > -setName($job-getName());
        $job = $dlp-getDlpJob($getDlpJobRequest);
        if ($job-getState() == JobStat>e::DONE) {
            break;
        }
        $numOfAttempts--;
    } while ($nu>mOfAttempts  0);

    // Print >finding counts.
    printf('>;Job %s status: %s' . PHP_EOL, $job-getName(), JobState::name($job-getSta>te()));
    switch (>$job-getStat>e()) {
        case JobState::DONE:
            $infoTypeStats = $job-getInspectDetails()-getResult()-getInfoTypeStats();
            if (count($infoTypeStats) === 0) {
                printf('No findings.' . PHP_EOL);
            } else {
                foreach ($infoTypeStats as $infoTypeStat) {
                    printf(
   >                     '  Found %s instance(s) o>f infoType %s&>#39; . PHP_EOL,
                        $infoTypeStat-getCount(),
                        $infoTypeStat-getInfoType()-getName()
                    );
                }
  >          }
            break;
        >case JobState::FAILED:
            printf('Job %s had errors:' . PHP_EOL, $job->getName());
            $errors = $job-getErrors();
            foreach ($errors as $error) {
                var_dump($error-getDetails());
            }
            break;
        case JobState::PENDING:
            printf('Job has not completed. Consider a longer timeout or an asynchronous execution model' . PHP_EOL);
            break;
        default:
            printf('Unexpected job state. Most likely, the job is either running or has not yet started.');
    }
}

import time
from typing import List

import google.cloud.dlp


def deidentify_cloud_storage(
    project: str,
    input_gcs_bucket: str,
    output_gcs_bucket: str,
    info_types: List[str],
    deid_template_id: str,
    structured_deid_template_id: str,
    image_redact_template_id: str,
    dataset_id: str,
    table_id: str,
    timeout: int = 300,
) -> None:
    """
    Uses the Data Loss Prevention API to de-identify files in a Google Cloud
    Storage directory.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        input_gcs_bucket: The name of google cloud storage bucket to inspect.
        output_gcs_bucket: The name of google cloud storage bucket where
            de-identified files would be stored.
        info_types: A list of strings representing info types to look for.
            A full list of info type categories can be fetched from the API.
        deid_template_id: The name of the de-identify template for
            unstructured and structured files.
        structured_deid_template_id: The name of the de-identify template
            for structured files.
        image_redact_template_id: The name of the image redaction template
            for images.
        dataset_id: The identifier of the BigQuery dataset where transformation
            details would be stored.
        table_id: The identifier of the BigQuery table where transformation
            details would be stored.
        timeout: The number of seconds to wait for a response from the API.
    """

    # Instantiate a client.
    dlp = google.cloud.dlp_v2.DlpServiceClient()

    # Construct the configuration dictionary.
    # 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.
    inspect_config = {"info_types": [{"name": info_type} for info_type in info_types]}

    # Construct cloud_storage_options dictionary with the bucket's URL.
    storage_config = {
        "cloud_storage_options": {"file_set": {"url": f"gs://{input_gcs_bucket}"}}
    }

    # Specify the big query table to store the transformation details.
    big_query_table = {
        "project_id": project,
        "dataset_id": dataset_id,
        "table_id": table_id,
    }

    # Convert the project id into a full resource id.
    parent = f"projects/{project}/locations/global"

    # Construct Transformation Configuration with de-identify Templates used
    # for transformation.
    transformation_config = {
        "deidentify_template": f"{parent}/deidentifyTemplates/{deid_template_id}",
        "structured_deidentify_template": f"{parent}/deidentifyTemplates/{structured_deid_template_id}",
        "image_redact_template": f"{parent}/deidentifyTemplates/{image_redact_template_id}",
    }

    # Tell the API where to send notification when the job is completed.
    actions = [
        {
            "deidentify": {
                "cloud_storage_output": f"gs://{output_gcs_bucket}",
                "transformation_config": transformation_config,
                "transformation_details_storage_config": {"table": big_query_table},
                "file_types_to_transform": ["IMAGE", "CSV", "TEXT_FILE"],
            }
        }
    ]

    # Construct the job definition.
    inspect_job = {
        "inspect_config": inspect_config,
        "storage_config": storage_config,
        "actions": actions,
    }

    # Call the API.
    response = dlp.create_dlp_job(
        request={
            "parent": parent,
            "inspect_job": inspect_job,
        }
    )

    job_name = response.name
    print(f"Inspection Job started : {job_name}")

    # Waiting for the job to get completed.
    job = dlp.get_dlp_job(request={"name": job_name})
    # Since the sleep time is kept as 30s, number of calls would be timeout/30.
    no_of_attempts = timeout // 30
    while no_of_attempts != 0:
        # Check if the job has completed.
        if job.state == google.cloud.dlp_v2.DlpJob.JobState.DONE:
            break
        if job.state == google.cloud.dlp_v2.DlpJob.JobState.FAILED:
            print("Job Failed, Please check the configuration.")
            break

        # Sleep for a short duration before checking the job status again.
        time.sleep(30)
        no_of_attempts -= 1

        # Get DLP job status.
        job = dlp.get_dlp_job(request={"name": job_name})

    if job.state != google.cloud.dlp_v2.DlpJob.JobState.DONE:
        print(f"Job did not complete within {timeout} minutes.")
        return

    # Print out the results.
    print(f"Job name: {job.name}")
    result = job.inspect_details.result
    print(f"Processed Bytes: {result.processed_bytes}")
    if result.info_type_stats:
        for stats in result.info_type_stats:
            print(f"Info type: {stats.info_type.name}")
            print(f"Count: {stats.count}")
    else:
        print("No findings.")