use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.
the class Inspect method inspectGcsFile.
// [END dlp_inspect_file]
// [START dlp_inspect_gcs]
/**
* Inspect GCS file for Info types and wait on job completion using Google Cloud Pub/Sub
* notification
*
* @param bucketName The name of the bucket where the file resides.
* @param fileName The path to the file within the bucket to inspect (can include wildcards, eg.
* my-image.*)
* @param minLikelihood The minimum likelihood required before returning a match
* @param infoTypes The infoTypes of information to match
* @param maxFindings The maximum number of findings to report (0 = server maximum)
* @param topicId Google Cloud Pub/Sub topic Id to notify of job status
* @param subscriptionId Google Cloud Subscription to above topic to listen for job status updates
* @param projectId Google Cloud project ID
*/
private static void inspectGcsFile(String bucketName, String fileName, Likelihood minLikelihood, List<InfoType> infoTypes, int maxFindings, String topicId, String subscriptionId, String projectId) throws Exception {
// Instantiates a client
try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
CloudStorageOptions cloudStorageOptions = CloudStorageOptions.newBuilder().setFileSet(CloudStorageOptions.FileSet.newBuilder().setUrl("gs://" + bucketName + "/" + fileName)).build();
StorageConfig storageConfig = StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).build();
FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).build();
String pubSubTopic = String.format("projects/%s/topics/%s", projectId, topicId);
Action.PublishToPubSub publishToPubSub = Action.PublishToPubSub.newBuilder().setTopic(pubSubTopic).build();
Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
InspectJobConfig inspectJobConfig = InspectJobConfig.newBuilder().setStorageConfig(storageConfig).setInspectConfig(inspectConfig).addActions(action).build();
// Semi-synchronously submit an inspect job, and wait on results
CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectJob(inspectJobConfig).build();
DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
System.out.println("Job created with ID:" + dlpJob.getName());
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
// Set up a Pub/Sub subscriber to listen on the job completion status
Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.of(projectId, subscriptionId), (pubsubMessage, ackReplyConsumer) -> {
if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJob.getName())) {
// notify job completion
done.set(true);
ackReplyConsumer.ack();
}
}).build();
subscriber.startAsync();
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(1, TimeUnit.MINUTES);
// Wait for the job to become available
Thread.sleep(500);
} catch (Exception e) {
System.out.println("Unable to verify job completion.");
}
DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build());
System.out.println("Job status: " + completedJob.getState());
InspectDataSourceDetails inspectDataSourceDetails = completedJob.getInspectDetails();
InspectDataSourceDetails.Result result = inspectDataSourceDetails.getResult();
if (result.getInfoTypeStatsCount() > 0) {
System.out.println("Findings: ");
for (InfoTypeStats infoTypeStat : result.getInfoTypeStatsList()) {
System.out.print("\tInfo type: " + infoTypeStat.getInfoType().getName());
System.out.println("\tCount: " + infoTypeStat.getCount());
}
} else {
System.out.println("No findings.");
}
}
}
use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.
the class Inspect method inspectFile.
// [END dlp_inspect_string]
// [START dlp_inspect_file]
/**
* Inspect a local file
*
* @param filePath The path to a local file to inspect. Can be a text, JPG, or PNG file.
* @param minLikelihood The minimum likelihood required before returning a match
* @param maxFindings The maximum number of findings to report (0 = server maximum)
* @param infoTypes The infoTypes of information to match
* @param includeQuote Whether to include the matching string
* @param projectId Google Cloud project ID
*/
private static void inspectFile(String filePath, Likelihood minLikelihood, int maxFindings, List<InfoType> infoTypes, boolean includeQuote, String projectId) {
// Instantiates a client
try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
// detect file mime type, default to application/octet-stream
String mimeType = URLConnection.guessContentTypeFromName(filePath);
if (mimeType == null) {
mimeType = MimetypesFileTypeMap.getDefaultFileTypeMap().getContentType(filePath);
}
ByteContentItem.BytesType bytesType;
switch(mimeType) {
case "image/jpeg":
bytesType = ByteContentItem.BytesType.IMAGE_JPEG;
break;
case "image/bmp":
bytesType = ByteContentItem.BytesType.IMAGE_BMP;
break;
case "image/png":
bytesType = ByteContentItem.BytesType.IMAGE_PNG;
break;
case "image/svg":
bytesType = ByteContentItem.BytesType.IMAGE_SVG;
break;
default:
bytesType = ByteContentItem.BytesType.BYTES_TYPE_UNSPECIFIED;
break;
}
byte[] data = Files.readAllBytes(Paths.get(filePath));
ByteContentItem byteContentItem = ByteContentItem.newBuilder().setType(bytesType).setData(ByteString.copyFrom(data)).build();
ContentItem contentItem = ContentItem.newBuilder().setByteItem(byteContentItem).build();
FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).setIncludeQuote(includeQuote).build();
InspectContentRequest request = InspectContentRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectConfig(inspectConfig).setItem(contentItem).build();
InspectContentResponse response = dlpServiceClient.inspectContent(request);
InspectResult result = response.getResult();
if (result.getFindingsCount() > 0) {
System.out.println("Findings: ");
for (Finding finding : result.getFindingsList()) {
if (includeQuote) {
System.out.print("\tQuote: " + finding.getQuote());
}
System.out.print("\tInfo type: " + finding.getInfoType().getName());
System.out.println("\tLikelihood: " + finding.getLikelihood());
}
} else {
System.out.println("No findings.");
}
} catch (Exception e) {
System.out.println("Error in inspectFile: " + e.getMessage());
}
}
use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.
the class Jobs method listJobs.
// [START dlp_list_jobs]
/*
* List DLP jobs
*
* @param projectId The project ID to run the API call under
* @param filter The filter expression to use, eg. state=DONE For more information on filter
* syntax see https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs/list
* @param jobType The type of job to list (either 'INSPECT_JOB' or 'RISK_ANALYSIS_JOB')
*/
private static void listJobs(String projectId, String filter, DlpJobType jobType) throws Exception {
try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
ListDlpJobsRequest listDlpJobsRequest = ListDlpJobsRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setFilter(filter).setType(jobType).build();
DlpServiceClient.ListDlpJobsPagedResponse response = dlpServiceClient.listDlpJobs(listDlpJobsRequest);
for (DlpJob dlpJob : response.getPage().getValues()) {
System.out.println(dlpJob.getName() + " -- " + dlpJob.getState());
}
}
}
use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.
the class Jobs method deleteJob.
// [END dlp_list_jobs]
/**
* Delete a DLP Job
*
* @param projectId Google Cloud ProjectID
* @param jobId DLP Job ID
*/
// [START dlp_delete_job]
private static void deleteJob(String projectId, String jobId) {
try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
// construct complete job name
DlpJobName job = DlpJobName.of(projectId, jobId);
DeleteDlpJobRequest deleteDlpJobRequest = DeleteDlpJobRequest.newBuilder().setName(job.toString()).build();
// submit job deletion request
dlpServiceClient.deleteDlpJob(deleteDlpJobRequest);
System.out.println("Job deleted successfully.");
} catch (Exception e) {
System.err.println("Error deleting DLP job: " + e.getMessage());
}
}
use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.
the class RiskAnalysis method calculateKAnonymity.
// [END dlp_categorical_stats]
// [START dlp_k_anonymity]
/**
* Calculate k-anonymity for quasi-identifiers in a BigQuery table using the DLP API.
*
* @param projectId The Google Cloud Platform project ID to run the API call under.
* @param datasetId The BigQuery dataset to analyze.
* @param tableId The BigQuery table to analyze.
* @param quasiIds The names of columns that form a composite key ('quasi-identifiers').
* @param topicId The name of the Pub/Sub topic to notify once the job completes
* @param subscriptionId The name of the Pub/Sub subscription to use when listening for job
* completion status.
*/
private static void calculateKAnonymity(String projectId, String datasetId, String tableId, List<String> quasiIds, String topicId, String subscriptionId) throws Exception {
// Instantiates a client
try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
List<FieldId> quasiIdFields = quasiIds.stream().map(columnName -> FieldId.newBuilder().setName(columnName).build()).collect(Collectors.toList());
KAnonymityConfig kanonymityConfig = KAnonymityConfig.newBuilder().addAllQuasiIds(quasiIdFields).build();
BigQueryTable bigQueryTable = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
PrivacyMetric privacyMetric = PrivacyMetric.newBuilder().setKAnonymityConfig(kanonymityConfig).build();
String topicName = String.format("projects/%s/topics/%s", projectId, topicId);
PublishToPubSub publishToPubSub = PublishToPubSub.newBuilder().setTopic(topicName).build();
// Create action to publish job status notifications over Google Cloud Pub/Sub
Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
RiskAnalysisJobConfig riskAnalysisJobConfig = RiskAnalysisJobConfig.newBuilder().setSourceTable(bigQueryTable).setPrivacyMetric(privacyMetric).addActions(action).build();
CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setRiskJob(riskAnalysisJobConfig).build();
DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
String dlpJobName = dlpJob.getName();
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
// Set up a Pub/Sub subscriber to listen on the job completion status
Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.newBuilder().setProject(projectId).setSubscription(subscriptionId).build(), (pubsubMessage, ackReplyConsumer) -> {
if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJobName)) {
// notify job completion
done.set(true);
ackReplyConsumer.ack();
}
}).build();
subscriber.startAsync();
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(1, TimeUnit.MINUTES);
// Wait for the job to become available
Thread.sleep(500);
} catch (TimeoutException e) {
System.out.println("Unable to verify job completion.");
}
// Retrieve completed job status
DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJobName).build());
System.out.println("Job status: " + completedJob.getState());
AnalyzeDataSourceRiskDetails riskDetails = completedJob.getRiskDetails();
KAnonymityResult kanonymityResult = riskDetails.getKAnonymityResult();
for (KAnonymityHistogramBucket result : kanonymityResult.getEquivalenceClassHistogramBucketsList()) {
System.out.printf("Bucket size range: [%d, %d]\n", result.getEquivalenceClassSizeLowerBound(), result.getEquivalenceClassSizeUpperBound());
for (KAnonymityEquivalenceClass bucket : result.getBucketValuesList()) {
List<String> quasiIdValues = bucket.getQuasiIdsValuesList().stream().map(v -> v.toString()).collect(Collectors.toList());
System.out.println("\tQuasi-ID values: " + String.join(", ", quasiIdValues));
System.out.println("\tClass size: " + bucket.getEquivalenceClassSize());
}
}
} catch (Exception e) {
System.out.println("Error in calculateKAnonymity: " + e.getMessage());
}
}
Aggregations