API Explorer でリクエストが成功した場合でも、新しいスキャンジョブが作成されます。スキャンジョブを制御する方法については、このトピックで後述する「検査結果を取得する」をご覧ください。JSON を使用して Cloud DLP API にリクエストを送信する方法については、JSON クイックスタートをご覧ください。
import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.cloud.pubsub.v1.AckReplyConsumer;
import com.google.cloud.pubsub.v1.MessageReceiver;
import com.google.cloud.pubsub.v1.Subscriber;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.CloudStorageOptions;
import com.google.privacy.dlp.v2.CloudStorageOptions.FileSet;
import com.google.privacy.dlp.v2.CreateDlpJobRequest;
import com.google.privacy.dlp.v2.DlpJob;
import com.google.privacy.dlp.v2.GetDlpJobRequest;
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.StorageConfig;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.stream.Collectors;
import java.util.stream.Stream;
public class InspectGcsFile {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String gcsUri = "gs://" + "your-bucket-name" + "/path/to/your/file.txt";
String topicId = "your-pubsub-topic-id";
String subscriptionId = "your-pubsub-subscription-id";
inspectGcsFile(projectId, gcsUri, topicId, subscriptionId);
}
// Inspects a file in a Google Cloud Storage Bucket.
public static void inspectGcsFile(
String projectId, String gcsUri, String topicId, String subscriptionId)
throws ExecutionException, InterruptedException, 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 the GCS file to be inspected.
CloudStorageOptions cloudStorageOptions =
CloudStorageOptions.newBuilder()
.setFileSet(FileSet.newBuilder().setUrl(gcsUri))
.build();
StorageConfig storageConfig =
StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).build();
// 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
List<InfoType> infoTypes =
Stream.of("PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER")
.map(it -> InfoType.newBuilder().setName(it).build())
.collect(Collectors.toList());
// Specify how the content should be inspected.
InspectConfig inspectConfig =
InspectConfig.newBuilder()
.addAllInfoTypes(infoTypes)
.setIncludeQuote(true)
.build();
// Specify the action that is triggered when the job completes.
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();
// Configure the long running job we want the service to perform.
InspectJobConfig inspectJobConfig =
InspectJobConfig.newBuilder()
.setStorageConfig(storageConfig)
.setInspectConfig(inspectConfig)
.addActions(action)
.build();
// Create the request for the job configured above.
CreateDlpJobRequest createDlpJobRequest =
CreateDlpJobRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setInspectJob(inspectJobConfig)
.build();
// Use the client to send the request.
final DlpJob dlpJob = dlp.createDlpJob(createDlpJobRequest);
System.out.println("Job created: " + dlpJob.getName());
// Set up a Pub/Sub subscriber to listen on the job completion status
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
ProjectSubscriptionName subscriptionName =
ProjectSubscriptionName.of(projectId, subscriptionId);
MessageReceiver messageHandler =
(PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
};
Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
subscriber.startAsync();
// Wait for job completion semi-synchronously
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(15, TimeUnit.MINUTES);
} catch (TimeoutException e) {
System.out.println("Job was not completed after 15 minutes.");
return;
} finally {
subscriber.stopAsync();
subscriber.awaitTerminated();
}
// Get the latest state of the job from the service
GetDlpJobRequest request = GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
DlpJob completedJob = dlp.getDlpJob(request);
// Parse the response and process results.
System.out.println("Job status: " + completedJob.getState());
InspectDataSourceDetails.Result result = completedJob.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());
}
}
}
// handleMessage injects the job and settableFuture into the message reciever interface
private static void handleMessage(
DlpJob job,
SettableApiFuture<Boolean> done,
PubsubMessage pubsubMessage,
AckReplyConsumer ackReplyConsumer) {
String messageAttribute = pubsubMessage.getAttributesMap().get("DlpJobName");
if (job.getName().equals(messageAttribute)) {
done.set(true);
ackReplyConsumer.ack();
} else {
ackReplyConsumer.nack();
}
}
}
// Import the Google Cloud client libraries
const DLP = require('@google-cloud/dlp');
const {PubSub} = require('@google-cloud/pubsub');
// Instantiates clients
const dlp = new DLP.DlpServiceClient();
const pubsub = new PubSub();
// The project ID to run the API call under
// const callingProjectId = process.env.GCLOUD_PROJECT;
// The name of the bucket where the file resides.
// const bucketName = 'YOUR-BUCKET';
// The path to the file within the bucket to inspect.
// Can contain wildcards, e.g. "my-image.*"
// const fileName = 'my-image.png';
// The minimum likelihood required before returning a match
// const minLikelihood = 'LIKELIHOOD_UNSPECIFIED';
// The maximum number of findings to report per request (0 = server maximum)
// const maxFindings = 0;
// The infoTypes of information to match
// const infoTypes = [{ name: 'PHONE_NUMBER' }, { name: 'EMAIL_ADDRESS' }, { name: 'CREDIT_CARD_NUMBER' }];
// The customInfoTypes of information to match
// const customInfoTypes = [{ infoType: { name: 'DICT_TYPE' }, dictionary: { wordList: { words: ['foo', 'bar', 'baz']}}},
// { infoType: { name: 'REGEX_TYPE' }, regex: '\\(\\d{3}\\) \\d{3}-\\d{4}'}];
// The name of the Pub/Sub topic to notify once the job completes
// TODO(developer): create a Pub/Sub topic to use for this
// const topicId = 'MY-PUBSUB-TOPIC'
// The name of the Pub/Sub subscription to use when listening for job
// completion notifications
// TODO(developer): create a Pub/Sub subscription to use for this
// const subscriptionId = 'MY-PUBSUB-SUBSCRIPTION'
// Get reference to the file to be inspected
const storageItem = {
cloudStorageOptions: {
fileSet: {url: `gs://${bucketName}/${fileName}`},
},
};
// Construct request for creating an inspect job
const request = {
parent: `projects/${callingProjectId}/locations/global`,
inspectJob: {
inspectConfig: {
infoTypes: infoTypes,
customInfoTypes: customInfoTypes,
minLikelihood: minLikelihood,
limits: {
maxFindingsPerRequest: maxFindings,
},
},
storageConfig: storageItem,
actions: [
{
pubSub: {
topic: `projects/${callingProjectId}/topics/${topicId}`,
},
},
],
},
};
try {
// Create a GCS File inspection job and wait for it to complete
const [topicResponse] = await pubsub.topic(topicId).get();
// Verify the Pub/Sub topic and listen for job notifications via an
// existing subscription.
const subscription = await topicResponse.subscription(subscriptionId);
const [jobsResponse] = await dlp.createDlpJob(request);
// Get the job's ID
const jobName = jobsResponse.name;
// Watch the Pub/Sub topic until the DLP job finishes
await new Promise((resolve, reject) => {
const messageHandler = message => {
if (message.attributes && message.attributes.DlpJobName === jobName) {
message.ack();
subscription.removeListener('message', messageHandler);
subscription.removeListener('error', errorHandler);
resolve(jobName);
} else {
message.nack();
}
};
const errorHandler = err => {
subscription.removeListener('message', messageHandler);
subscription.removeListener('error', errorHandler);
reject(err);
};
subscription.on('message', messageHandler);
subscription.on('error', errorHandler);
});
setTimeout(() => {
console.log('Waiting for DLP job to fully complete');
}, 500);
const [job] = await dlp.getDlpJob({name: jobName});
console.log(`Job ${job.name} status: ${job.state}`);
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.');
}
} catch (err) {
console.log(`Error in inspectGCSFile: ${err.message || err}`);
}
def inspect_gcs_file(
project,
bucket,
filename,
topic_id,
subscription_id,
info_types,
custom_dictionaries=None,
custom_regexes=None,
min_likelihood=None,
max_findings=None,
timeout=300,
):
"""Uses the Data Loss Prevention API to analyze a file on GCS.
Args:
project: The Google Cloud project id to use as a parent resource.
bucket: The name of the GCS bucket containing the file, as a string.
filename: The name of the file in the bucket, including the path, as a
string; e.g. 'images/myfile.png'.
topic_id: The id of the Cloud Pub/Sub topic to which the API will
broadcast job completion. The topic must already exist.
subscription_id: The id of the Cloud Pub/Sub subscription to listen on
while waiting for job completion. The subscription must already
exist and be subscribed to the topic.
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.
min_likelihood: A string representing the minimum likelihood threshold
that constitutes a match. One of: 'LIKELIHOOD_UNSPECIFIED',
'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE', 'LIKELY', 'VERY_LIKELY'.
max_findings: The maximum number of findings to report; 0 = no maximum.
timeout: The number of seconds to wait for a response from the API.
Returns:
None; the response from the API is printed to the terminal.
"""
# Import the client library.
import google.cloud.dlp
# This sample additionally uses Cloud Pub/Sub to receive results from
# potentially long-running operations.
import google.cloud.pubsub
# This sample also uses threading.Event() to wait for the job to finish.
import threading
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Prepare info_types by converting the list of strings into a list of
# dictionaries (protos are also accepted).
if not info_types:
info_types = ["FIRST_NAME", "LAST_NAME", "EMAIL_ADDRESS"]
info_types = [{"name": info_type} for info_type in info_types]
# Prepare custom_info_types by parsing the dictionary word lists and
# regex patterns.
if custom_dictionaries is None:
custom_dictionaries = []
dictionaries = [
{
"info_type": {"name": "CUSTOM_DICTIONARY_{}".format(i)},
"dictionary": {"word_list": {"words": custom_dict.split(",")}},
}
for i, custom_dict in enumerate(custom_dictionaries)
]
if custom_regexes is None:
custom_regexes = []
regexes = [
{
"info_type": {"name": "CUSTOM_REGEX_{}".format(i)},
"regex": {"pattern": custom_regex},
}
for i, custom_regex in enumerate(custom_regexes)
]
custom_info_types = dictionaries + regexes
# Construct the configuration dictionary. Keys which are None may
# optionally be omitted entirely.
inspect_config = {
"info_types": info_types,
"custom_info_types": custom_info_types,
"min_likelihood": min_likelihood,
"limits": {"max_findings_per_request": max_findings},
}
# Construct a storage_config containing the file's URL.
url = "gs://{}/{}".format(bucket, filename)
storage_config = {"cloud_storage_options": {"file_set": {"url": url}}}
# Convert the project id into full resource ids.
topic = google.cloud.pubsub.PublisherClient.topic_path(project, topic_id)
parent = dlp.location_path(project, 'global')
# Tell the API where to send a notification when the job is complete.
actions = [{"pub_sub": {"topic": topic}}]
# Construct the inspect_job, which defines the entire inspect content task.
inspect_job = {
"inspect_config": inspect_config,
"storage_config": storage_config,
"actions": actions,
}
operation = dlp.create_dlp_job(parent, inspect_job=inspect_job)
print("Inspection operation started: {}".format(operation.name))
# Create a Pub/Sub client and find the subscription. The subscription is
# expected to already be listening to the topic.
subscriber = google.cloud.pubsub.SubscriberClient()
subscription_path = subscriber.subscription_path(project, subscription_id)
# Set up a callback to acknowledge a message. This closes around an event
# so that it can signal that it is done and the main thread can continue.
job_done = threading.Event()
def callback(message):
try:
if message.attributes["DlpJobName"] == operation.name:
# This is the message we're looking for, so acknowledge it.
message.ack()
# Now that the job is done, fetch the results and print them.
job = dlp.get_dlp_job(operation.name)
if job.inspect_details.result.info_type_stats:
for finding in job.inspect_details.result.info_type_stats:
print(
"Info type: {}; Count: {}".format(
finding.info_type.name, finding.count
)
)
else:
print("No findings.")
# Signal to the main thread that we can exit.
job_done.set()
else:
# This is not the message we're looking for.
message.drop()
except Exception as e:
# Because this is executing in a thread, an exception won't be
# noted unless we print it manually.
print(e)
raise
subscriber.subscribe(subscription_path, callback=callback)
finished = job_done.wait(timeout=timeout)
if not finished:
print(
"No event received before the timeout. Please verify that the "
"subscription provided is subscribed to the topic provided."
)
/**
* Inspect a file stored on Google Cloud Storage , using Pub/Sub for job status notifications.
*/
use Google\Cloud\Core\ExponentialBackoff;
use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\CloudStorageOptions;
use Google\Cloud\Dlp\V2\CloudStorageOptions\FileSet;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\StorageConfig;
use Google\Cloud\Dlp\V2\Likelihood;
use Google\Cloud\Dlp\V2\DlpJob\JobState;
use Google\Cloud\Dlp\V2\InspectConfig\FindingLimits;
use Google\Cloud\Dlp\V2\Action;
use Google\Cloud\Dlp\V2\Action\PublishToPubSub;
use Google\Cloud\Dlp\V2\InspectJobConfig;
use Google\Cloud\PubSub\PubSubClient;
/** Uncomment and populate these variables in your code */
// $callingProjectId = 'The project ID to run the API call under';
// $topicId = 'The name of the Pub/Sub topic to notify once the job completes';
// $subscriptionId = 'The name of the Pub/Sub subscription to use when listening for job';
// $bucketId = 'The name of the bucket where the file resides';
// $file = 'The path to the file within the bucket to inspect. Can contain wildcards e.g. "my-image.*"';
// $maxFindings = 0; // (Optional) The maximum number of findings to report per request (0 = server maximum)
// Instantiate a client.
$dlp = new DlpServiceClient([
'projectId' => $callingProjectId,
]);
$pubsub = new PubSubClient([
'projectId' => $callingProjectId,
]);
$topic = $pubsub->topic($topicId);
// The infoTypes of information to match
$personNameInfoType = (new InfoType())
->setName('PERSON_NAME');
$creditCardNumberInfoType = (new InfoType())
->setName('CREDIT_CARD_NUMBER');
$infoTypes = [$personNameInfoType, $creditCardNumberInfoType];
// The minimum likelihood required before returning a match
$minLikelihood = likelihood::LIKELIHOOD_UNSPECIFIED;
// Specify finding limits
$limits = (new FindingLimits())
->setMaxFindingsPerRequest($maxFindings);
// Construct items to be inspected
$fileSet = (new FileSet())
->setUrl('gs://' . $bucketId . '/' . $file);
$cloudStorageOptions = (new CloudStorageOptions())
->setFileSet($fileSet);
$storageConfig = (new StorageConfig())
->setCloudStorageOptions($cloudStorageOptions);
// Construct the inspect config object
$inspectConfig = (new InspectConfig())
->setMinLikelihood($minLikelihood)
->setLimits($limits)
->setInfoTypes($infoTypes);
// Construct the action to run when job completes
$pubSubAction = (new PublishToPubSub())
->setTopic($topic->name());
$action = (new Action())
->setPubSub($pubSubAction);
// Construct inspect job config to run
$inspectJob = (new InspectJobConfig())
->setInspectConfig($inspectConfig)
->setStorageConfig($storageConfig)
->setActions([$action]);
// Listen for job notifications via an existing topic/subscription.
$subscription = $topic->subscription($subscriptionId);
// Submit request
$parent = $dlp->projectName($callingProjectId);
$job = $dlp->createDlpJob($parent, [
'inspectJob' => $inspectJob
]);
// Poll Pub/Sub using exponential backoff until job finishes
$backoff = new ExponentialBackoff(30);
$backoff->execute(function () use ($subscription, $dlp, &$job) {
printf('Waiting for job to complete' . PHP_EOL);
foreach ($subscription->pull() as $message) {
if (isset($message->attributes()['DlpJobName']) &&
$message->attributes()['DlpJobName'] === $job->getName()) {
$subscription->acknowledge($message);
// Get the updated job. Loop to avoid race condition with DLP API.
do {
$job = $dlp->getDlpJob($job->getName());
} while ($job->getState() == JobState::RUNNING);
return true;
}
}
throw new Exception('Job has not yet completed');
});
// 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) {
print('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;
default:
print('Unexpected job state. Most likely, the job is either running or has not yet started.');
}
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using Google.Cloud.PubSub.V1;
using System;
using System.Collections.Generic;
using System.Threading;
using System.Threading.Tasks;
using static Google.Cloud.Dlp.V2.InspectConfig.Types;
public class InspectGoogleCloudStorage
{
public static DlpJob InspectGCS(
string projectId,
Likelihood minLikelihood,
int maxFindings,
bool includeQuote,
IEnumerable<InfoType> infoTypes,
IEnumerable<CustomInfoType> customInfoTypes,
string bucketName,
string topicId,
string subscriptionId)
{
var inspectJob = new InspectJobConfig
{
StorageConfig = new StorageConfig
{
CloudStorageOptions = new CloudStorageOptions
{
FileSet = new CloudStorageOptions.Types.FileSet { Url = $"gs://{bucketName}/*.txt" },
BytesLimitPerFile = 1073741824
},
},
InspectConfig = new InspectConfig
{
InfoTypes = { infoTypes },
CustomInfoTypes = { customInfoTypes },
ExcludeInfoTypes = false,
IncludeQuote = includeQuote,
Limits = new FindingLimits
{
MaxFindingsPerRequest = maxFindings
},
MinLikelihood = minLikelihood
},
Actions =
{
new Google.Cloud.Dlp.V2.Action
{
// Send results to Pub/Sub topic
PubSub = new Google.Cloud.Dlp.V2.Action.Types.PublishToPubSub
{
Topic = topicId,
}
}
}
};
// Issue Create Dlp Job Request
var client = DlpServiceClient.Create();
var request = new CreateDlpJobRequest
{
InspectJob = inspectJob,
Parent = new LocationName(projectId, "global").ToString(),
};
// We need created job name
var dlpJob = client.CreateDlpJob(request);
// Get a pub/sub subscription and listen for DLP results
var fireEvent = new ManualResetEventSlim();
var subscriptionName = new SubscriptionName(projectId, subscriptionId);
var subscriber = SubscriberClient.CreateAsync(subscriptionName).Result;
subscriber.StartAsync(
(pubSubMessage, cancellationToken) =>
{
// Given a message that we receive on this subscription, we should either acknowledge or decline it
if (pubSubMessage.Attributes["DlpJobName"] == dlpJob.Name)
{
fireEvent.Set();
return Task.FromResult(SubscriberClient.Reply.Ack);
}
return Task.FromResult(SubscriberClient.Reply.Nack);
});
// We block here until receiving a signal from a separate thread that is waiting on a message indicating receiving a result of Dlp job
if (fireEvent.Wait(TimeSpan.FromMinutes(1)))
{
// Stop the thread that is listening to messages as a result of StartAsync call earlier
subscriber.StopAsync(CancellationToken.None).Wait();
// Now we can inspect full job results
var job = client.GetDlpJob(new GetDlpJobRequest { DlpJobName = new DlpJobName(projectId, dlpJob.Name) });
// Inspect Job details
Console.WriteLine($"Processed bytes: {job.InspectDetails.Result.ProcessedBytes}");
Console.WriteLine($"Total estimated bytes: {job.InspectDetails.Result.TotalEstimatedBytes}");
var stats = job.InspectDetails.Result.InfoTypeStats;
Console.WriteLine("Found stats:");
foreach (var stat in stats)
{
Console.WriteLine($"{stat.InfoType.Name}");
}
return job;
}
throw new InvalidOperationException("The wait failed on timeout");
}
}
API Explorer でリクエストが成功した場合でも、新しいスキャンジョブが作成されます。スキャンジョブを制御する方法については、このトピックで後述する検査結果を取得するをご覧ください。JSON を使用して Cloud DLP API にリクエストを送信する方法については、JSON クイックスタートをご覧ください。
import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.cloud.pubsub.v1.AckReplyConsumer;
import com.google.cloud.pubsub.v1.MessageReceiver;
import com.google.cloud.pubsub.v1.Subscriber;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.CreateDlpJobRequest;
import com.google.privacy.dlp.v2.DatastoreOptions;
import com.google.privacy.dlp.v2.DlpJob;
import com.google.privacy.dlp.v2.GetDlpJobRequest;
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.KindExpression;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.PartitionId;
import com.google.privacy.dlp.v2.StorageConfig;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.stream.Collectors;
import java.util.stream.Stream;
public class InspectDatastoreEntity {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String datastoreNamespace = "your-datastore-namespace";
String datastoreKind = "your-datastore-kind";
String topicId = "your-pubsub-topic-id";
String subscriptionId = "your-pubsub-subscription-id";
insepctDatastoreEntity(projectId, datastoreNamespace, datastoreKind, topicId, subscriptionId);
}
// Inspects a Datastore Entity.
public static void insepctDatastoreEntity(
String projectId,
String datastoreNamespce,
String datastoreKind,
String topicId,
String subscriptionId)
throws ExecutionException, InterruptedException, 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 the Datastore entity to be inspected.
PartitionId partitionId =
PartitionId.newBuilder()
.setProjectId(projectId)
.setNamespaceId(datastoreNamespce)
.build();
KindExpression kindExpression = KindExpression.newBuilder().setName(datastoreKind).build();
DatastoreOptions datastoreOptions =
DatastoreOptions.newBuilder().setKind(kindExpression).setPartitionId(partitionId).build();
StorageConfig storageConfig =
StorageConfig.newBuilder().setDatastoreOptions(datastoreOptions).build();
// 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
List<InfoType> infoTypes =
Stream.of("PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER")
.map(it -> InfoType.newBuilder().setName(it).build())
.collect(Collectors.toList());
// Specify how the content should be inspected.
InspectConfig inspectConfig =
InspectConfig.newBuilder()
.addAllInfoTypes(infoTypes)
.setIncludeQuote(true)
.build();
// Specify the action that is triggered when the job completes.
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();
// Configure the long running job we want the service to perform.
InspectJobConfig inspectJobConfig =
InspectJobConfig.newBuilder()
.setStorageConfig(storageConfig)
.setInspectConfig(inspectConfig)
.addActions(action)
.build();
// Create the request for the job configured above.
CreateDlpJobRequest createDlpJobRequest =
CreateDlpJobRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setInspectJob(inspectJobConfig)
.build();
// Use the client to send the request.
final DlpJob dlpJob = dlp.createDlpJob(createDlpJobRequest);
System.out.println("Job created: " + dlpJob.getName());
// Set up a Pub/Sub subscriber to listen on the job completion status
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
ProjectSubscriptionName subscriptionName =
ProjectSubscriptionName.of(projectId, subscriptionId);
MessageReceiver messageHandler =
(PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
};
Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
subscriber.startAsync();
// Wait for job completion semi-synchronously
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(15, TimeUnit.MINUTES);
} catch (TimeoutException e) {
System.out.println("Job was not completed after 15 minutes.");
return;
} finally {
subscriber.stopAsync();
subscriber.awaitTerminated();
}
// Get the latest state of the job from the service
GetDlpJobRequest request = GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
DlpJob completedJob = dlp.getDlpJob(request);
// Parse the response and process results.
System.out.println("Job status: " + completedJob.getState());
InspectDataSourceDetails.Result result = completedJob.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());
}
}
}
// handleMessage injects the job and settableFuture into the message reciever interface
private static void handleMessage(
DlpJob job,
SettableApiFuture<Boolean> done,
PubsubMessage pubsubMessage,
AckReplyConsumer ackReplyConsumer) {
String messageAttribute = pubsubMessage.getAttributesMap().get("DlpJobName");
if (job.getName().equals(messageAttribute)) {
done.set(true);
ackReplyConsumer.ack();
} else {
ackReplyConsumer.nack();
}
}
}
// Import the Google Cloud client libraries
const DLP = require('@google-cloud/dlp');
const {PubSub} = require('@google-cloud/pubsub');
// Instantiates clients
const dlp = new DLP.DlpServiceClient();
const pubsub = new PubSub();
// The project ID to run the API call under
// const callingProjectId = process.env.GCLOUD_PROJECT;
// The project ID the target Datastore is stored under
// This may or may not equal the calling project ID
// const dataProjectId = process.env.GCLOUD_PROJECT;
// (Optional) The ID namespace of the Datastore document to inspect.
// To ignore Datastore namespaces, set this to an empty string ('')
// const namespaceId = '';
// The kind of the Datastore entity to inspect.
// const kind = 'Person';
// The minimum likelihood required before returning a match
// const minLikelihood = 'LIKELIHOOD_UNSPECIFIED';
// The maximum number of findings to report per request (0 = server maximum)
// const maxFindings = 0;
// The infoTypes of information to match
// const infoTypes = [{ name: 'PHONE_NUMBER' }, { name: 'EMAIL_ADDRESS' }, { name: 'CREDIT_CARD_NUMBER' }];
// The customInfoTypes of information to match
// const customInfoTypes = [{ infoType: { name: 'DICT_TYPE' }, dictionary: { wordList: { words: ['foo', 'bar', 'baz']}}},
// { infoType: { name: 'REGEX_TYPE' }, regex: '\\(\\d{3}\\) \\d{3}-\\d{4}'}];
// The name of the Pub/Sub topic to notify once the job completes
// TODO(developer): create a Pub/Sub topic to use for this
// const topicId = 'MY-PUBSUB-TOPIC'
// The name of the Pub/Sub subscription to use when listening for job
// completion notifications
// TODO(developer): create a Pub/Sub subscription to use for this
// const subscriptionId = 'MY-PUBSUB-SUBSCRIPTION'
// Construct items to be inspected
const storageItems = {
datastoreOptions: {
partitionId: {
projectId: dataProjectId,
namespaceId: namespaceId,
},
kind: {
name: kind,
},
},
};
// Construct request for creating an inspect job
const request = {
parent: `projects/${callingProjectId}/locations/global`,
inspectJob: {
inspectConfig: {
infoTypes: infoTypes,
customInfoTypes: customInfoTypes,
minLikelihood: minLikelihood,
limits: {
maxFindingsPerRequest: maxFindings,
},
},
storageConfig: storageItems,
actions: [
{
pubSub: {
topic: `projects/${callingProjectId}/topics/${topicId}`,
},
},
],
},
};
try {
// Run inspect-job creation request
const [topicResponse] = await pubsub.topic(topicId).get();
// Verify the Pub/Sub topic and listen for job notifications via an
// existing subscription.
const subscription = await topicResponse.subscription(subscriptionId);
const [jobsResponse] = await dlp.createDlpJob(request);
const jobName = jobsResponse.name;
// Watch the Pub/Sub topic until the DLP job finishes
await new Promise((resolve, reject) => {
const messageHandler = message => {
if (message.attributes && message.attributes.DlpJobName === jobName) {
message.ack();
subscription.removeListener('message', messageHandler);
subscription.removeListener('error', errorHandler);
resolve(jobName);
} else {
message.nack();
}
};
const errorHandler = err => {
subscription.removeListener('message', messageHandler);
subscription.removeListener('error', errorHandler);
reject(err);
};
subscription.on('message', messageHandler);
subscription.on('error', errorHandler);
});
// Wait for DLP job to fully complete
setTimeout(() => {
console.log('Waiting for DLP job to fully complete');
}, 500);
const [job] = await dlp.getDlpJob({name: jobName});
console.log(`Job ${job.name} status: ${job.state}`);
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.');
}
} catch (err) {
console.log(`Error in inspectDatastore: ${err.message || err}`);
}
def inspect_datastore(
project,
datastore_project,
kind,
topic_id,
subscription_id,
info_types,
custom_dictionaries=None,
custom_regexes=None,
namespace_id=None,
min_likelihood=None,
max_findings=None,
timeout=300,
):
"""Uses the Data Loss Prevention API to analyze Datastore data.
Args:
project: The Google Cloud project id to use as a parent resource.
datastore_project: The Google Cloud project id of the target Datastore.
kind: The kind of the Datastore entity to inspect, e.g. 'Person'.
topic_id: The id of the Cloud Pub/Sub topic to which the API will
broadcast job completion. The topic must already exist.
subscription_id: The id of the Cloud Pub/Sub subscription to listen on
while waiting for job completion. The subscription must already
exist and be subscribed to the topic.
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.
namespace_id: The namespace of the Datastore document, if applicable.
min_likelihood: A string representing the minimum likelihood threshold
that constitutes a match. One of: 'LIKELIHOOD_UNSPECIFIED',
'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE', 'LIKELY', 'VERY_LIKELY'.
max_findings: The maximum number of findings to report; 0 = no maximum.
timeout: The number of seconds to wait for a response from the API.
Returns:
None; the response from the API is printed to the terminal.
"""
# Import the client library.
import google.cloud.dlp
# This sample additionally uses Cloud Pub/Sub to receive results from
# potentially long-running operations.
import google.cloud.pubsub
# This sample also uses threading.Event() to wait for the job to finish.
import threading
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Prepare info_types by converting the list of strings into a list of
# dictionaries (protos are also accepted).
if not info_types:
info_types = ["FIRST_NAME", "LAST_NAME", "EMAIL_ADDRESS"]
info_types = [{"name": info_type} for info_type in info_types]
# Prepare custom_info_types by parsing the dictionary word lists and
# regex patterns.
if custom_dictionaries is None:
custom_dictionaries = []
dictionaries = [
{
"info_type": {"name": "CUSTOM_DICTIONARY_{}".format(i)},
"dictionary": {"word_list": {"words": custom_dict.split(",")}},
}
for i, custom_dict in enumerate(custom_dictionaries)
]
if custom_regexes is None:
custom_regexes = []
regexes = [
{
"info_type": {"name": "CUSTOM_REGEX_{}".format(i)},
"regex": {"pattern": custom_regex},
}
for i, custom_regex in enumerate(custom_regexes)
]
custom_info_types = dictionaries + regexes
# Construct the configuration dictionary. Keys which are None may
# optionally be omitted entirely.
inspect_config = {
"info_types": info_types,
"custom_info_types": custom_info_types,
"min_likelihood": min_likelihood,
"limits": {"max_findings_per_request": max_findings},
}
# Construct a storage_config containing the target Datastore info.
storage_config = {
"datastore_options": {
"partition_id": {
"project_id": datastore_project,
"namespace_id": namespace_id,
},
"kind": {"name": kind},
}
}
# Convert the project id into full resource ids.
topic = google.cloud.pubsub.PublisherClient.topic_path(project, topic_id)
parent = dlp.location_path(project, 'global')
# Tell the API where to send a notification when the job is complete.
actions = [{"pub_sub": {"topic": topic}}]
# Construct the inspect_job, which defines the entire inspect content task.
inspect_job = {
"inspect_config": inspect_config,
"storage_config": storage_config,
"actions": actions,
}
operation = dlp.create_dlp_job(parent, inspect_job=inspect_job)
print("Inspection operation started: {}".format(operation.name))
# Create a Pub/Sub client and find the subscription. The subscription is
# expected to already be listening to the topic.
subscriber = google.cloud.pubsub.SubscriberClient()
subscription_path = subscriber.subscription_path(project, subscription_id)
# Set up a callback to acknowledge a message. This closes around an event
# so that it can signal that it is done and the main thread can continue.
job_done = threading.Event()
def callback(message):
try:
if message.attributes["DlpJobName"] == operation.name:
# This is the message we're looking for, so acknowledge it.
message.ack()
# Now that the job is done, fetch the results and print them.
job = dlp.get_dlp_job(operation.name)
if job.inspect_details.result.info_type_stats:
for finding in job.inspect_details.result.info_type_stats:
print(
"Info type: {}; Count: {}".format(
finding.info_type.name, finding.count
)
)
else:
print("No findings.")
# Signal to the main thread that we can exit.
job_done.set()
else:
# This is not the message we're looking for.
message.drop()
except Exception as e:
# Because this is executing in a thread, an exception won't be
# noted unless we print it manually.
print(e)
raise
# Register the callback and wait on the event.
subscriber.subscribe(subscription_path, callback=callback)
finished = job_done.wait(timeout=timeout)
if not finished:
print(
"No event received before the timeout. Please verify that the "
"subscription provided is subscribed to the topic provided."
)
/**
* Inspect Datastore, using Pub/Sub for job status notifications.
*/
use Google\Cloud\Core\ExponentialBackoff;
use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\DatastoreOptions;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\Action;
use Google\Cloud\Dlp\V2\Action\PublishToPubSub;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectJobConfig;
use Google\Cloud\Dlp\V2\KindExpression;
use Google\Cloud\Dlp\V2\PartitionId;
use Google\Cloud\Dlp\V2\StorageConfig;
use Google\Cloud\Dlp\V2\Likelihood;
use Google\Cloud\Dlp\V2\DlpJob\JobState;
use Google\Cloud\Dlp\V2\InspectConfig\FindingLimits;
use Google\Cloud\PubSub\PubSubClient;
/** Uncomment and populate these variables in your code */
// $callingProjectId = 'The project ID to run the API call under';
// $dataProjectId = 'The project ID containing the target Datastore';
// $topicId = 'The name of the Pub/Sub topic to notify once the job completes';
// $subscriptionId = 'The name of the Pub/Sub subscription to use when listening for job';
// $kind = 'The datastore kind to inspect';
// $namespaceId = 'The ID namespace of the Datastore document to inspect';
// $maxFindings = 0; // (Optional) The maximum number of findings to report per request (0 = server maximum)
// Instantiate clients
$dlp = new DlpServiceClient();
$pubsub = new PubSubClient();
$topic = $pubsub->topic($topicId);
// The infoTypes of information to match
$personNameInfoType = (new InfoType())
->setName('PERSON_NAME');
$phoneNumberInfoType = (new InfoType())
->setName('PHONE_NUMBER');
$infoTypes = [$personNameInfoType, $phoneNumberInfoType];
// The minimum likelihood required before returning a match
$minLikelihood = likelihood::LIKELIHOOD_UNSPECIFIED;
// Specify finding limits
$limits = (new FindingLimits())
->setMaxFindingsPerRequest($maxFindings);
// Construct items to be inspected
$partitionId = (new PartitionId())
->setProjectId($dataProjectId)
->setNamespaceId($namespaceId);
$kindExpression = (new KindExpression())
->setName($kind);
$datastoreOptions = (new DatastoreOptions())
->setPartitionId($partitionId)
->setKind($kindExpression);
// Construct the inspect config object
$inspectConfig = (new InspectConfig())
->setInfoTypes($infoTypes)
->setMinLikelihood($minLikelihood)
->setLimits($limits);
// Construct the storage config object
$storageConfig = (new StorageConfig())
->setDatastoreOptions($datastoreOptions);
// Construct the action to run when job completes
$pubSubAction = (new PublishToPubSub())
->setTopic($topic->name());
$action = (new Action())
->setPubSub($pubSubAction);
// Construct inspect job config to run
$inspectJob = (new InspectJobConfig())
->setInspectConfig($inspectConfig)
->setStorageConfig($storageConfig)
->setActions([$action]);
// Listen for job notifications via an existing topic/subscription.
$subscription = $topic->subscription($subscriptionId);
// Submit request
$parent = $dlp->projectName($callingProjectId);
$job = $dlp->createDlpJob($parent, [
'inspectJob' => $inspectJob
]);
// Poll Pub/Sub using exponential backoff until job finishes
$backoff = new ExponentialBackoff(30);
$backoff->execute(function () use ($subscription, $dlp, &$job) {
printf('Waiting for job to complete' . PHP_EOL);
foreach ($subscription->pull() as $message) {
if (isset($message->attributes()['DlpJobName']) &&
$message->attributes()['DlpJobName'] === $job->getName()) {
$subscription->acknowledge($message);
// Get the updated job. Loop to avoid race condition with DLP API.
do {
$job = $dlp->getDlpJob($job->getName());
} while ($job->getState() == JobState::RUNNING);
return true;
}
}
throw new Exception('Job has not yet completed');
});
// 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) {
print('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;
default:
print('Unexpected job state.');
}
using Google.Api.Gax.ResourceNames;
using Google.Cloud.BigQuery.V2;
using Google.Cloud.Dlp.V2;
using Google.Protobuf.WellKnownTypes;
using System;
using System.Collections.Generic;
using System.Threading;
using static Google.Cloud.Dlp.V2.InspectConfig.Types;
public class InspectCloudDataStore
{
public static object Inspect(
string projectId,
Likelihood minLikelihood,
int maxFindings,
bool includeQuote,
string kindName,
string namespaceId,
IEnumerable<InfoType> infoTypes,
IEnumerable<CustomInfoType> customInfoTypes,
string datasetId,
string tableId)
{
var inspectJob = new InspectJobConfig
{
StorageConfig = new StorageConfig
{
DatastoreOptions = new DatastoreOptions
{
Kind = new KindExpression { Name = kindName },
PartitionId = new PartitionId
{
NamespaceId = namespaceId,
ProjectId = projectId,
}
},
TimespanConfig = new StorageConfig.Types.TimespanConfig
{
StartTime = Timestamp.FromDateTime(System.DateTime.UtcNow.AddYears(-1)),
EndTime = Timestamp.FromDateTime(System.DateTime.UtcNow)
}
},
InspectConfig = new InspectConfig
{
InfoTypes = { infoTypes },
CustomInfoTypes = { customInfoTypes },
Limits = new FindingLimits
{
MaxFindingsPerRequest = maxFindings
},
ExcludeInfoTypes = false,
IncludeQuote = includeQuote,
MinLikelihood = minLikelihood
},
Actions =
{
new Google.Cloud.Dlp.V2.Action
{
// Save results in BigQuery Table
SaveFindings = new Google.Cloud.Dlp.V2.Action.Types.SaveFindings
{
OutputConfig = new OutputStorageConfig
{
Table = new Google.Cloud.Dlp.V2.BigQueryTable
{
ProjectId = projectId,
DatasetId = datasetId,
TableId = tableId
}
}
},
}
}
};
// Issue Create Dlp Job Request
var client = DlpServiceClient.Create();
var request = new CreateDlpJobRequest
{
InspectJob = inspectJob,
Parent = new LocationName(projectId, "global").ToString(),
};
// We need created job name
var dlpJob = client.CreateDlpJob(request);
var jobName = dlpJob.Name;
// Make sure the job finishes before inspecting the results.
// Alternatively, we can inspect results opportunistically, but
// for testing purposes, we want consistent outcome
var finishedJob = EnsureJobFinishes(projectId, jobName);
var bigQueryClient = BigQueryClient.Create(projectId);
var table = bigQueryClient.GetTable(datasetId, tableId);
// Return only first page of 10 rows
Console.WriteLine("DLP v2 Results:");
var firstPage = table.ListRows(new ListRowsOptions { StartIndex = 0, PageSize = 10 });
foreach (var item in firstPage)
{
Console.WriteLine($"\t {item[""]}");
}
return finishedJob;
}
private static DlpJob EnsureJobFinishes(string projectId, string jobName)
{
var client = DlpServiceClient.Create();
var request = new GetDlpJobRequest
{
DlpJobName = new DlpJobName(projectId, jobName),
};
// Simple logic that gives the job 5*30 sec at most to complete - for testing purposes only
var numOfAttempts = 5;
do
{
var dlpJob = client.GetDlpJob(request);
numOfAttempts--;
if (dlpJob.State != DlpJob.Types.JobState.Running)
{
return dlpJob;
}
Thread.Sleep(TimeSpan.FromSeconds(30));
} while (numOfAttempts > 0);
throw new InvalidOperationException("Job did not complete in time");
}
}
API Explorer でリクエストが成功した場合でも、新しいスキャンジョブが作成されます。スキャンジョブを制御する方法については、このトピックで後述する「検査結果を取得する」をご覧ください。JSON を使用して Cloud DLP API にリクエストを送信する方法については、JSON クイックスタートをご覧ください。
import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.cloud.pubsub.v1.AckReplyConsumer;
import com.google.cloud.pubsub.v1.MessageReceiver;
import com.google.cloud.pubsub.v1.Subscriber;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.BigQueryOptions;
import com.google.privacy.dlp.v2.BigQueryTable;
import com.google.privacy.dlp.v2.CreateDlpJobRequest;
import com.google.privacy.dlp.v2.DlpJob;
import com.google.privacy.dlp.v2.GetDlpJobRequest;
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.StorageConfig;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.stream.Collectors;
import java.util.stream.Stream;
public class InspectBigQueryTable {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String bigQueryDatasetId = "your-bigquery-dataset-id";
String bigQueryTableId = "your-bigquery-table-id";
String topicId = "your-pubsub-topic-id";
String subscriptionId = "your-pubsub-subscription-id";
inspectBigQueryTable(projectId, bigQueryDatasetId, bigQueryTableId, topicId, subscriptionId);
}
// Inspects a BigQuery Table
public static void inspectBigQueryTable(
String projectId,
String bigQueryDatasetId,
String bigQueryTableId,
String topicId,
String subscriptionId)
throws ExecutionException, InterruptedException, 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 the BigQuery table to be inspected.
BigQueryTable tableReference =
BigQueryTable.newBuilder()
.setProjectId(projectId)
.setDatasetId(bigQueryDatasetId)
.setTableId(bigQueryTableId)
.build();
BigQueryOptions bigQueryOptions =
BigQueryOptions.newBuilder().setTableReference(tableReference).build();
StorageConfig storageConfig =
StorageConfig.newBuilder().setBigQueryOptions(bigQueryOptions).build();
// 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
List<InfoType> infoTypes =
Stream.of("PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER")
.map(it -> InfoType.newBuilder().setName(it).build())
.collect(Collectors.toList());
// Specify how the content should be inspected.
InspectConfig inspectConfig =
InspectConfig.newBuilder()
.addAllInfoTypes(infoTypes)
.setIncludeQuote(true)
.build();
// Specify the action that is triggered when the job completes.
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();
// Configure the long running job we want the service to perform.
InspectJobConfig inspectJobConfig =
InspectJobConfig.newBuilder()
.setStorageConfig(storageConfig)
.setInspectConfig(inspectConfig)
.addActions(action)
.build();
// Create the request for the job configured above.
CreateDlpJobRequest createDlpJobRequest =
CreateDlpJobRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setInspectJob(inspectJobConfig)
.build();
// Use the client to send the request.
final DlpJob dlpJob = dlp.createDlpJob(createDlpJobRequest);
System.out.println("Job created: " + dlpJob.getName());
// Set up a Pub/Sub subscriber to listen on the job completion status
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
ProjectSubscriptionName subscriptionName =
ProjectSubscriptionName.of(projectId, subscriptionId);
MessageReceiver messageHandler =
(PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
};
Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
subscriber.startAsync();
// Wait for job completion semi-synchronously
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(15, TimeUnit.MINUTES);
} catch (TimeoutException e) {
System.out.println("Job was not completed after 15 minutes.");
return;
} finally {
subscriber.stopAsync();
subscriber.awaitTerminated();
}
// Get the latest state of the job from the service
GetDlpJobRequest request = GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
DlpJob completedJob = dlp.getDlpJob(request);
// Parse the response and process results.
System.out.println("Job status: " + completedJob.getState());
InspectDataSourceDetails.Result result = completedJob.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());
}
}
}
// handleMessage injects the job and settableFuture into the message reciever interface
private static void handleMessage(
DlpJob job,
SettableApiFuture<Boolean> done,
PubsubMessage pubsubMessage,
AckReplyConsumer ackReplyConsumer) {
String messageAttribute = pubsubMessage.getAttributesMap().get("DlpJobName");
if (job.getName().equals(messageAttribute)) {
done.set(true);
ackReplyConsumer.ack();
} else {
ackReplyConsumer.nack();
}
}
}
// Import the Google Cloud client libraries
const DLP = require('@google-cloud/dlp');
const {PubSub} = require('@google-cloud/pubsub');
// Instantiates clients
const dlp = new DLP.DlpServiceClient();
const pubsub = new PubSub();
// The project ID to run the API call under
// const callingProjectId = process.env.GCLOUD_PROJECT;
// The project ID the table is stored under
// This may or (for public datasets) may not equal the calling project ID
// const dataProjectId = process.env.GCLOUD_PROJECT;
// 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 minimum likelihood required before returning a match
// const minLikelihood = 'LIKELIHOOD_UNSPECIFIED';
// The maximum number of findings to report per request (0 = server maximum)
// const maxFindings = 0;
// The infoTypes of information to match
// const infoTypes = [{ name: 'PHONE_NUMBER' }, { name: 'EMAIL_ADDRESS' }, { name: 'CREDIT_CARD_NUMBER' }];
// The customInfoTypes of information to match
// const customInfoTypes = [{ infoType: { name: 'DICT_TYPE' }, dictionary: { wordList: { words: ['foo', 'bar', 'baz']}}},
// { infoType: { name: 'REGEX_TYPE' }, regex: '\\(\\d{3}\\) \\d{3}-\\d{4}'}];
// The name of the Pub/Sub topic to notify once the job completes
// TODO(developer): create a Pub/Sub topic to use for this
// const topicId = 'MY-PUBSUB-TOPIC'
// The name of the Pub/Sub subscription to use when listening for job
// completion notifications
// TODO(developer): create a Pub/Sub subscription to use for this
// const subscriptionId = 'MY-PUBSUB-SUBSCRIPTION'
// Construct item to be inspected
const storageItem = {
bigQueryOptions: {
tableReference: {
projectId: dataProjectId,
datasetId: datasetId,
tableId: tableId,
},
},
};
// Construct request for creating an inspect job
const request = {
parent: `projects/${callingProjectId}/locations/global`,
inspectJob: {
inspectConfig: {
infoTypes: infoTypes,
customInfoTypes: customInfoTypes,
minLikelihood: minLikelihood,
limits: {
maxFindingsPerRequest: maxFindings,
},
},
storageConfig: storageItem,
actions: [
{
pubSub: {
topic: `projects/${callingProjectId}/topics/${topicId}`,
},
},
],
},
};
try {
// Run inspect-job creation request
const [topicResponse] = await pubsub.topic(topicId).get();
// Verify the Pub/Sub topic and listen for job notifications via an
// existing subscription.
const subscription = await topicResponse.subscription(subscriptionId);
const [jobsResponse] = await dlp.createDlpJob(request);
const jobName = jobsResponse.name;
// Watch the Pub/Sub topic until the DLP job finishes
await new Promise((resolve, reject) => {
const messageHandler = message => {
if (message.attributes && message.attributes.DlpJobName === jobName) {
message.ack();
subscription.removeListener('message', messageHandler);
subscription.removeListener('error', errorHandler);
resolve(jobName);
} else {
message.nack();
}
};
const errorHandler = err => {
subscription.removeListener('message', messageHandler);
subscription.removeListener('error', errorHandler);
reject(err);
};
subscription.on('message', messageHandler);
subscription.on('error', errorHandler);
});
// Wait for DLP job to fully complete
setTimeout(() => {
console.log('Waiting for DLP job to fully complete');
}, 500);
const [job] = await dlp.getDlpJob({name: jobName});
console.log(`Job ${job.name} status: ${job.state}`);
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.');
}
} catch (err) {
console.log(`Error in inspectBigquery: ${err.message || err}`);
}
def inspect_bigquery(
project,
bigquery_project,
dataset_id,
table_id,
topic_id,
subscription_id,
info_types,
custom_dictionaries=None,
custom_regexes=None,
min_likelihood=None,
max_findings=None,
timeout=300,
):
"""Uses the Data Loss Prevention API to analyze BigQuery data.
Args:
project: The Google Cloud project id to use as a parent resource.
bigquery_project: The Google Cloud project id of the target table.
dataset_id: The id of the target BigQuery dataset.
table_id: The id of the target BigQuery table.
topic_id: The id of the Cloud Pub/Sub topic to which the API will
broadcast job completion. The topic must already exist.
subscription_id: The id of the Cloud Pub/Sub subscription to listen on
while waiting for job completion. The subscription must already
exist and be subscribed to the topic.
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.
namespace_id: The namespace of the Datastore document, if applicable.
min_likelihood: A string representing the minimum likelihood threshold
that constitutes a match. One of: 'LIKELIHOOD_UNSPECIFIED',
'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE', 'LIKELY', 'VERY_LIKELY'.
max_findings: The maximum number of findings to report; 0 = no maximum.
timeout: The number of seconds to wait for a response from the API.
Returns:
None; the response from the API is printed to the terminal.
"""
# Import the client library.
import google.cloud.dlp
# This sample additionally uses Cloud Pub/Sub to receive results from
# potentially long-running operations.
import google.cloud.pubsub
# This sample also uses threading.Event() to wait for the job to finish.
import threading
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Prepare info_types by converting the list of strings into a list of
# dictionaries (protos are also accepted).
if not info_types:
info_types = ["FIRST_NAME", "LAST_NAME", "EMAIL_ADDRESS"]
info_types = [{"name": info_type} for info_type in info_types]
# Prepare custom_info_types by parsing the dictionary word lists and
# regex patterns.
if custom_dictionaries is None:
custom_dictionaries = []
dictionaries = [
{
"info_type": {"name": "CUSTOM_DICTIONARY_{}".format(i)},
"dictionary": {"word_list": {"words": custom_dict.split(",")}},
}
for i, custom_dict in enumerate(custom_dictionaries)
]
if custom_regexes is None:
custom_regexes = []
regexes = [
{
"info_type": {"name": "CUSTOM_REGEX_{}".format(i)},
"regex": {"pattern": custom_regex},
}
for i, custom_regex in enumerate(custom_regexes)
]
custom_info_types = dictionaries + regexes
# Construct the configuration dictionary. Keys which are None may
# optionally be omitted entirely.
inspect_config = {
"info_types": info_types,
"custom_info_types": custom_info_types,
"min_likelihood": min_likelihood,
"limits": {"max_findings_per_request": max_findings},
}
# Construct a storage_config containing the target Bigquery info.
storage_config = {
"big_query_options": {
"table_reference": {
"project_id": bigquery_project,
"dataset_id": dataset_id,
"table_id": table_id,
}
}
}
# Convert the project id into full resource ids.
topic = google.cloud.pubsub.PublisherClient.topic_path(project, topic_id)
parent = dlp.location_path(project, 'global')
# Tell the API where to send a notification when the job is complete.
actions = [{"pub_sub": {"topic": topic}}]
# Construct the inspect_job, which defines the entire inspect content task.
inspect_job = {
"inspect_config": inspect_config,
"storage_config": storage_config,
"actions": actions,
}
operation = dlp.create_dlp_job(parent, inspect_job=inspect_job)
print("Inspection operation started: {}".format(operation.name))
# Create a Pub/Sub client and find the subscription. The subscription is
# expected to already be listening to the topic.
subscriber = google.cloud.pubsub.SubscriberClient()
subscription_path = subscriber.subscription_path(project, subscription_id)
# Set up a callback to acknowledge a message. This closes around an event
# so that it can signal that it is done and the main thread can continue.
job_done = threading.Event()
def callback(message):
try:
if message.attributes["DlpJobName"] == operation.name:
# This is the message we're looking for, so acknowledge it.
message.ack()
# Now that the job is done, fetch the results and print them.
job = dlp.get_dlp_job(operation.name)
if job.inspect_details.result.info_type_stats:
for finding in job.inspect_details.result.info_type_stats:
print(
"Info type: {}; Count: {}".format(
finding.info_type.name, finding.count
)
)
else:
print("No findings.")
# Signal to the main thread that we can exit.
job_done.set()
else:
# This is not the message we're looking for.
message.drop()
except Exception as e:
# Because this is executing in a thread, an exception won't be
# noted unless we print it manually.
print(e)
raise
# Register the callback and wait on the event.
subscriber.subscribe(subscription_path, callback=callback)
finished = job_done.wait(timeout=timeout)
if not finished:
print(
"No event received before the timeout. Please verify that the "
"subscription provided is subscribed to the topic provided."
)
/**
* Inspect a BigQuery table , using Pub/Sub for job status notifications.
*/
use Google\Cloud\Core\ExponentialBackoff;
use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\BigQueryOptions;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\StorageConfig;
use Google\Cloud\Dlp\V2\BigQueryTable;
use Google\Cloud\Dlp\V2\Likelihood;
use Google\Cloud\Dlp\V2\DlpJob\JobState;
use Google\Cloud\Dlp\V2\InspectConfig\FindingLimits;
use Google\Cloud\Dlp\V2\Action;
use Google\Cloud\Dlp\V2\Action\PublishToPubSub;
use Google\Cloud\Dlp\V2\InspectJobConfig;
use Google\Cloud\PubSub\PubSubClient;
/** Uncomment and populate these variables in your code */
// $callingProjectId = 'The project ID to run the API call under';
// $dataProjectId = 'The project ID containing the target Datastore';
// $topicId = 'The name of the Pub/Sub topic to notify once the job completes';
// $subscriptionId = 'The name of the Pub/Sub subscription to use when listening for job';
// $datasetId = 'The ID of the dataset to inspect';
// $tableId = 'The ID of the table to inspect';
// $columnName = 'The name of the column to compute risk metrics for, e.g. "age"';
// $maxFindings = 0; // (Optional) The maximum number of findings to report per request (0 = server maximum)
// Instantiate a client.
$dlp = new DlpServiceClient();
$pubsub = new PubSubClient();
$topic = $pubsub->topic($topicId);
// The infoTypes of information to match
$personNameInfoType = (new InfoType())
->setName('PERSON_NAME');
$creditCardNumberInfoType = (new InfoType())
->setName('CREDIT_CARD_NUMBER');
$infoTypes = [$personNameInfoType, $creditCardNumberInfoType];
// The minimum likelihood required before returning a match
$minLikelihood = likelihood::LIKELIHOOD_UNSPECIFIED;
// Specify finding limits
$limits = (new FindingLimits())
->setMaxFindingsPerRequest($maxFindings);
// Construct items to be inspected
$bigqueryTable = (new BigQueryTable())
->setProjectId($dataProjectId)
->setDatasetId($datasetId)
->setTableId($tableId);
$bigQueryOptions = (new BigQueryOptions())
->setTableReference($bigqueryTable);
$storageConfig = (new StorageConfig())
->setBigQueryOptions($bigQueryOptions);
// Construct the inspect config object
$inspectConfig = (new InspectConfig())
->setMinLikelihood($minLikelihood)
->setLimits($limits)
->setInfoTypes($infoTypes);
// Construct the action to run when job completes
$pubSubAction = (new PublishToPubSub())
->setTopic($topic->name());
$action = (new Action())
->setPubSub($pubSubAction);
// Construct inspect job config to run
$inspectJob = (new InspectJobConfig())
->setInspectConfig($inspectConfig)
->setStorageConfig($storageConfig)
->setActions([$action]);
// Listen for job notifications via an existing topic/subscription.
$subscription = $topic->subscription($subscriptionId);
// Submit request
$parent = $dlp->projectName($callingProjectId);
$job = $dlp->createDlpJob($parent, [
'inspectJob' => $inspectJob
]);
// Poll Pub/Sub using exponential backoff until job finishes
$backoff = new ExponentialBackoff(30);
$backoff->execute(function () use ($subscription, $dlp, &$job) {
printf('Waiting for job to complete' . PHP_EOL);
foreach ($subscription->pull() as $message) {
if (isset($message->attributes()['DlpJobName']) &&
$message->attributes()['DlpJobName'] === $job->getName()) {
$subscription->acknowledge($message);
// Get the updated job. Loop to avoid race condition with DLP API.
do {
$job = $dlp->getDlpJob($job->getName());
} while ($job->getState() == JobState::RUNNING);
return true;
}
}
throw new Exception('Job has not yet completed');
});
// 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) {
print('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;
default:
printf('Unexpected job state. Most likely, the job is either running or has not yet started.');
}
using Google.Api.Gax.ResourceNames;
using Google.Cloud.BigQuery.V2;
using Google.Cloud.Dlp.V2;
using Google.Protobuf.WellKnownTypes;
using System;
using System.Collections.Generic;
using System.Threading;
using static Google.Cloud.Dlp.V2.InspectConfig.Types;
public class InspectBigQuery
{
public static object Inspect(
string projectId,
Likelihood minLikelihood,
int maxFindings,
bool includeQuote,
IEnumerable<FieldId> identifyingFields,
IEnumerable<InfoType> infoTypes,
IEnumerable<CustomInfoType> customInfoTypes,
string datasetId,
string tableId)
{
var inspectJob = new InspectJobConfig
{
StorageConfig = new StorageConfig
{
BigQueryOptions = new BigQueryOptions
{
TableReference = new Google.Cloud.Dlp.V2.BigQueryTable
{
ProjectId = projectId,
DatasetId = datasetId,
TableId = tableId,
},
IdentifyingFields =
{
identifyingFields
}
},
TimespanConfig = new StorageConfig.Types.TimespanConfig
{
StartTime = Timestamp.FromDateTime(System.DateTime.UtcNow.AddYears(-1)),
EndTime = Timestamp.FromDateTime(System.DateTime.UtcNow)
}
},
InspectConfig = new InspectConfig
{
InfoTypes = { infoTypes },
CustomInfoTypes = { customInfoTypes },
Limits = new FindingLimits
{
MaxFindingsPerRequest = maxFindings
},
ExcludeInfoTypes = false,
IncludeQuote = includeQuote,
MinLikelihood = minLikelihood
},
Actions =
{
new Google.Cloud.Dlp.V2.Action
{
// Save results in BigQuery Table
SaveFindings = new Google.Cloud.Dlp.V2.Action.Types.SaveFindings
{
OutputConfig = new OutputStorageConfig
{
Table = new Google.Cloud.Dlp.V2.BigQueryTable
{
ProjectId = projectId,
DatasetId = datasetId,
TableId = tableId
}
}
},
}
}
};
// Issue Create Dlp Job Request
var client = DlpServiceClient.Create();
var request = new CreateDlpJobRequest
{
InspectJob = inspectJob,
Parent = new LocationName(projectId, "global").ToString(),
};
// We need created job name
var dlpJob = client.CreateDlpJob(request);
var jobName = dlpJob.Name;
// Make sure the job finishes before inspecting the results.
// Alternatively, we can inspect results opportunistically, but
// for testing purposes, we want consistent outcome
var finishedJob = EnsureJobFinishes(projectId, jobName);
var bigQueryClient = BigQueryClient.Create(projectId);
var table = bigQueryClient.GetTable(datasetId, tableId);
// Return only first page of 10 rows
Console.WriteLine("DLP v2 Results:");
var firstPage = table.ListRows(new ListRowsOptions { StartIndex = 0, PageSize = 10 });
foreach (var item in firstPage)
{
Console.WriteLine($"\t {item[""]}");
}
return finishedJob;
}
private static DlpJob EnsureJobFinishes(string projectId, string jobName)
{
var client = DlpServiceClient.Create();
var request = new GetDlpJobRequest
{
DlpJobName = new DlpJobName(projectId, jobName),
};
// Simple logic that gives the job 5*30 sec at most to complete - for testing purposes only
var numOfAttempts = 5;
do
{
var dlpJob = client.GetDlpJob(request);
numOfAttempts--;
if (dlpJob.State != DlpJob.Types.JobState.Running)
{
return dlpJob;
}
Thread.Sleep(TimeSpan.FromSeconds(30));
} while (numOfAttempts > 0);
throw new InvalidOperationException("Job did not complete in time");
}
}
jobId: 省略可。Cloud DLP によって返されるジョブの識別子。jobId が省略されるか空の場合、システムがジョブの ID を作成します。指定すると、ジョブにこの ID 値が割り当てられます。ジョブ ID は一意でなければならず、また大文字、小文字、数字、ハイフンを含めることができます。つまり、正規表現 [a-zA-Z\\d-]+ に一致する必要があります。
import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.cloud.pubsub.v1.AckReplyConsumer;
import com.google.cloud.pubsub.v1.MessageReceiver;
import com.google.cloud.pubsub.v1.Subscriber;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.CloudStorageOptions;
import com.google.privacy.dlp.v2.CloudStorageOptions.FileSet;
import com.google.privacy.dlp.v2.CloudStorageOptions.SampleMethod;
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.GetDlpJobRequest;
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.Likelihood;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.StorageConfig;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
public class InspectGcsFileWithSampling {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String gcsUri = "gs://" + "your-bucket-name" + "/path/to/your/file.txt";
String topicId = "your-pubsub-topic-id";
String subscriptionId = "your-pubsub-subscription-id";
inspectGcsFileWithSampling(projectId, gcsUri, topicId, subscriptionId);
}
// Inspects a file in a Google Cloud Storage Bucket.
public static void inspectGcsFileWithSampling(
String projectId, String gcsUri, String topicId, String subscriptionId)
throws ExecutionException, InterruptedException, 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 the GCS file to be inspected and sampling configuration
CloudStorageOptions cloudStorageOptions =
CloudStorageOptions.newBuilder()
.setFileSet(FileSet.newBuilder().setUrl(gcsUri))
.setBytesLimitPerFile(200)
.addFileTypes(FileType.TEXT_FILE)
.setFilesLimitPercent(90)
.setSampleMethod(SampleMethod.RANDOM_START)
.build();
StorageConfig storageConfig =
StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).build();
// 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
InfoType infoType = InfoType.newBuilder().setName("PERSON_NAME").build();
// Specify how the content should be inspected.
InspectConfig inspectConfig =
InspectConfig.newBuilder()
.addInfoTypes(infoType)
.setExcludeInfoTypes(true)
.setIncludeQuote(true)
.setMinLikelihood(Likelihood.POSSIBLE)
.build();
// Specify the action that is triggered when the job completes.
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();
// Configure the long running job we want the service to perform.
InspectJobConfig inspectJobConfig =
InspectJobConfig.newBuilder()
.setStorageConfig(storageConfig)
.setInspectConfig(inspectConfig)
.addActions(action)
.build();
// Create the request for the job configured above.
CreateDlpJobRequest createDlpJobRequest =
CreateDlpJobRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setInspectJob(inspectJobConfig)
.build();
// Use the client to send the request.
final DlpJob dlpJob = dlp.createDlpJob(createDlpJobRequest);
System.out.println("Job created: " + dlpJob.getName());
// Set up a Pub/Sub subscriber to listen on the job completion status
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
ProjectSubscriptionName subscriptionName =
ProjectSubscriptionName.of(projectId, subscriptionId);
MessageReceiver messageHandler =
(PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
};
Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
subscriber.startAsync();
// Wait for job completion semi-synchronously
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(15, TimeUnit.MINUTES);
} catch (TimeoutException e) {
System.out.println("Job was not completed after 15 minutes.");
return;
} finally {
subscriber.stopAsync();
subscriber.awaitTerminated();
}
// Get the latest state of the job from the service
GetDlpJobRequest request = GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
DlpJob completedJob = dlp.getDlpJob(request);
// Parse the response and process results.
System.out.println("Job status: " + completedJob.getState());
InspectDataSourceDetails.Result result = completedJob.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());
}
}
}
// handleMessage injects the job and settableFuture into the message reciever interface
private static void handleMessage(
DlpJob job,
SettableApiFuture<Boolean> done,
PubsubMessage pubsubMessage,
AckReplyConsumer ackReplyConsumer) {
String messageAttribute = pubsubMessage.getAttributesMap().get("DlpJobName");
if (job.getName().equals(messageAttribute)) {
done.set(true);
ackReplyConsumer.ack();
} else {
ackReplyConsumer.nack();
}
}
}
import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.cloud.pubsub.v1.AckReplyConsumer;
import com.google.cloud.pubsub.v1.MessageReceiver;
import com.google.cloud.pubsub.v1.Subscriber;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.BigQueryOptions;
import com.google.privacy.dlp.v2.BigQueryOptions.SampleMethod;
import com.google.privacy.dlp.v2.BigQueryTable;
import com.google.privacy.dlp.v2.CreateDlpJobRequest;
import com.google.privacy.dlp.v2.DlpJob;
import com.google.privacy.dlp.v2.FieldId;
import com.google.privacy.dlp.v2.GetDlpJobRequest;
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.StorageConfig;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
public class InspectBigQueryTableWithSampling {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String topicId = "your-pubsub-topic-id";
String subscriptionId = "your-pubsub-subscription-id";
inspectBigQueryTableWithSampling(projectId, topicId, subscriptionId);
}
// Inspects a BigQuery Table
public static void inspectBigQueryTableWithSampling(
String projectId, String topicId, String subscriptionId)
throws ExecutionException, InterruptedException, 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 the BigQuery table to be inspected.
BigQueryTable tableReference =
BigQueryTable.newBuilder()
.setProjectId("bigquery-public-data")
.setDatasetId("usa_names")
.setTableId("usa_1910_current")
.build();
BigQueryOptions bigQueryOptions =
BigQueryOptions.newBuilder()
.setTableReference(tableReference)
.setRowsLimit(1000)
.setSampleMethod(SampleMethod.RANDOM_START)
.addIdentifyingFields(FieldId.newBuilder().setName("name"))
.build();
StorageConfig storageConfig =
StorageConfig.newBuilder().setBigQueryOptions(bigQueryOptions).build();
// 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
InfoType infoType = InfoType.newBuilder().setName("PERSON_NAME").build();
// Specify how the content should be inspected.
InspectConfig inspectConfig =
InspectConfig.newBuilder()
.addInfoTypes(infoType)
.setIncludeQuote(true)
.build();
// Specify the action that is triggered when the job completes.
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();
// Configure the long running job we want the service to perform.
InspectJobConfig inspectJobConfig =
InspectJobConfig.newBuilder()
.setStorageConfig(storageConfig)
.setInspectConfig(inspectConfig)
.addActions(action)
.build();
// Create the request for the job configured above.
CreateDlpJobRequest createDlpJobRequest =
CreateDlpJobRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setInspectJob(inspectJobConfig)
.build();
// Use the client to send the request.
final DlpJob dlpJob = dlp.createDlpJob(createDlpJobRequest);
System.out.println("Job created: " + dlpJob.getName());
// Set up a Pub/Sub subscriber to listen on the job completion status
final SettableApiFuture<Boolean> done = SettableApiFuture.create();
ProjectSubscriptionName subscriptionName =
ProjectSubscriptionName.of(projectId, subscriptionId);
MessageReceiver messageHandler =
(PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
};
Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
subscriber.startAsync();
// Wait for job completion semi-synchronously
// For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
try {
done.get(15, TimeUnit.MINUTES);
} catch (TimeoutException e) {
System.out.println("Job was not completed after 15 minutes.");
return;
} finally {
subscriber.stopAsync();
subscriber.awaitTerminated();
}
// Get the latest state of the job from the service
GetDlpJobRequest request = GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
DlpJob completedJob = dlp.getDlpJob(request);
// Parse the response and process results.
System.out.println("Job status: " + completedJob.getState());
InspectDataSourceDetails.Result result = completedJob.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());
}
}
}
// handleMessage injects the job and settableFuture into the message reciever interface
private static void handleMessage(
DlpJob job,
SettableApiFuture<Boolean> done,
PubsubMessage pubsubMessage,
AckReplyConsumer ackReplyConsumer) {
String messageAttribute = pubsubMessage.getAttributesMap().get("DlpJobName");
if (job.getName().equals(messageAttribute)) {
done.set(true);
ackReplyConsumer.ack();
} else {
ackReplyConsumer.nack();
}
}
}
![[作成] > [ジョブまたはジョブトリガー] メニュー選択のスクリーンショット](https://cloud.google.com/dlp/docs/images/inspecting-storage-create-new.png)