use of com.google.privacy.dlp.v2.BigQueryOptions in project java-docs-samples by GoogleCloudPlatform.
the class Inspect method inspectBigquery.
// [END dlp_inspect_datastore]
// [START dlp_inspect_bigquery]
/**
* Inspect a BigQuery table
*
* @param projectId The project ID to run the API call under
* @param datasetId The ID of the dataset to inspect, e.g. 'my_dataset'
* @param tableId The ID of the table to inspect, e.g. 'my_table'
* @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 Topic ID for pubsub.
* @param subscriptionId Subscription ID for pubsub.
*/
private static void inspectBigquery(String projectId, String datasetId, String tableId, Likelihood minLikelihood, List<InfoType> infoTypes, int maxFindings, String topicId, String subscriptionId) {
// Instantiates a client
try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
// Reference to the BigQuery table
BigQueryTable tableReference = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
BigQueryOptions bigQueryOptions = BigQueryOptions.newBuilder().setTableReference(tableReference).build();
// Construct BigQuery configuration to be inspected
StorageConfig storageConfig = StorageConfig.newBuilder().setBigQueryOptions(bigQueryOptions).build();
FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).build();
ProjectTopicName topic = ProjectTopicName.of(projectId, topicId);
Action.PublishToPubSub publishToPubSub = Action.PublishToPubSub.newBuilder().setTopic(topic.toString()).build();
Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
InspectJobConfig inspectJobConfig = InspectJobConfig.newBuilder().setStorageConfig(storageConfig).setInspectConfig(inspectConfig).addActions(action).build();
// Asynchronously 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());
// Wait for job completion semi-synchronously
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
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();
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.");
}
} catch (Exception e) {
System.out.println("inspectBigquery Problems: " + e.getMessage());
}
}
Aggregations