function deidentify_cloud_storage()

in dlp/src/deidentify_cloud_storage.php [68:181]

• 94 lines of code
• 9 McCabe index (conditional complexity)

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-identify.
    $cloudStorageOptions = (new CloudStorageOptions())
        ->setFileSet((new FileSet())
            ->setUrl($inputgcsPath));
    $storageConfig = (new StorageConfig())
        ->setCloudStorageOptions(($cloudStorageOptions));

    // Specify the type of info the inspection 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.
    $transformationDetailsStorageConfig = (new TransformationDetailsStorageConfig())
        ->setTable((new BigQueryTable())
            ->setProjectId($callingProjectId)
            ->setDatasetId($datasetId)
            ->setTableId($tableId));

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

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

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

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

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

    $numOfAttempts = 10;
    do {
        printf('Waiting for job to complete' . PHP_EOL);
        sleep(30);
        $getDlpJobRequest = (new GetDlpJobRequest())
            ->setName($job->getName());
        $job = $dlp->getDlpJob($getDlpJobRequest);
        if ($job->getState() == JobState::DONE) {
            break;
        }
        $numOfAttempts--;
    } while ($numOfAttempts > 0);

    // Print finding counts.
    printf('Job %s status: %s' . PHP_EOL, $job->getName(), JobState::name($job->getState()));
    switch ($job->getState()) {
        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) of infoType %s' . 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.');
    }
}