k-匿名性是数据集的一个属性，指示其记录的可重标识性。如果数据集中每个人的准标识符与该数据集中至少 k - 1 个其他人也相同，则该数据集具有 k-匿名性。 此示例演示了如何使用 Cloud DLP 计算 k-匿名性值。
包含此代码示例的文档页面
如需查看上下文中使用的代码示例，请参阅以下文档：
代码示例
C#
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using Google.Cloud.PubSub.V1;
using Newtonsoft.Json;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using static Google.Cloud.Dlp.V2.Action.Types;
using static Google.Cloud.Dlp.V2.PrivacyMetric.Types;
public class RiskAnalysisCreateKAnonymity
{
public static AnalyzeDataSourceRiskDetails.Types.KAnonymityResult KAnonymity(
string callingProjectId,
string tableProjectId,
string datasetId,
string tableId,
string topicId,
string subscriptionId,
IEnumerable<FieldId> quasiIds)
{
var dlp = DlpServiceClient.Create();
// Construct + submit the job
var KAnonymityConfig = new KAnonymityConfig
{
QuasiIds = { quasiIds }
};
var config = new RiskAnalysisJobConfig
{
PrivacyMetric = new PrivacyMetric
{
KAnonymityConfig = KAnonymityConfig
},
SourceTable = new BigQueryTable
{
ProjectId = tableProjectId,
DatasetId = datasetId,
TableId = tableId
},
Actions =
{
new Google.Cloud.Dlp.V2.Action
{
PubSub = new PublishToPubSub
{
Topic = $"projects/{callingProjectId}/topics/{topicId}"
}
}
}
};
var submittedJob = dlp.CreateDlpJob(
new CreateDlpJobRequest
{
ParentAsProjectName = new ProjectName(callingProjectId),
RiskJob = config
});
// Listen to pub/sub for the job
var subscriptionName = new SubscriptionName(callingProjectId, subscriptionId);
var subscriber = SubscriberClient.CreateAsync(
subscriptionName).Result;
// SimpleSubscriber runs your message handle function on multiple
// threads to maximize throughput.
var done = new ManualResetEventSlim(false);
subscriber.StartAsync((PubsubMessage message, CancellationToken cancel) =>
{
if (message.Attributes["DlpJobName"] == submittedJob.Name)
{
Thread.Sleep(500); // Wait for DLP API results to become consistent
done.Set();
return Task.FromResult(SubscriberClient.Reply.Ack);
}
else
{
return Task.FromResult(SubscriberClient.Reply.Nack);
}
});
done.Wait(TimeSpan.FromMinutes(10)); // 10 minute timeout; may not work for large jobs
subscriber.StopAsync(CancellationToken.None).Wait();
// Process results
var resultJob = dlp.GetDlpJob(new GetDlpJobRequest
{
DlpJobName = DlpJobName.Parse(submittedJob.Name)
});
var result = resultJob.RiskDetails.KAnonymityResult;
for (var bucketIdx = 0; bucketIdx < result.EquivalenceClassHistogramBuckets.Count; bucketIdx++)
{
var bucket = result.EquivalenceClassHistogramBuckets[bucketIdx];
Console.WriteLine($"Bucket {bucketIdx}");
Console.WriteLine($" Bucket size range: [{bucket.EquivalenceClassSizeLowerBound}, {bucket.EquivalenceClassSizeUpperBound}].");
Console.WriteLine($" {bucket.BucketSize} unique value(s) total.");
foreach (var bucketValue in bucket.BucketValues)
{
// 'UnpackValue(x)' is a prettier version of 'x.toString()'
Console.WriteLine($" Quasi-ID values: [{String.Join(',', bucketValue.QuasiIdsValues.Select(x => UnpackValue(x)))}]");
Console.WriteLine($" Class size: {bucketValue.EquivalenceClassSize}");
}
}
return result;
}
public static string UnpackValue(Value protoValue)
{
var jsonValue = JsonConvert.DeserializeObject<Dictionary<string, object>>(protoValue.ToString());
return jsonValue.Values.ElementAt(0).ToString();
}
}
Go
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
import (
"context"
"fmt"
"io"
"strings"
"time"
dlp "cloud.google.com/go/dlp/apiv2"
"cloud.google.com/go/pubsub"
dlppb "google.golang.org/genproto/googleapis/privacy/dlp/v2"
)
// riskKAnonymity computes the risk of the given columns using K Anonymity.
func riskKAnonymity(w io.Writer, projectID, dataProject, pubSubTopic, pubSubSub, datasetID, tableID string, columnNames ...string) error {
// projectID := "my-project-id"
// dataProject := "bigquery-public-data"
// pubSubTopic := "dlp-risk-sample-topic"
// pubSubSub := "dlp-risk-sample-sub"
// datasetID := "nhtsa_traffic_fatalities"
// tableID := "accident_2015"
// columnNames := "state_number" "county"
ctx := context.Background()
client, err := dlp.NewClient(ctx)
if err != nil {
return fmt.Errorf("dlp.NewClient: %v", err)
}
// Create a PubSub Client used to listen for when the inspect job finishes.
pubsubClient, err := pubsub.NewClient(ctx, projectID)
if err != nil {
return fmt.Errorf("Error creating PubSub client: %v", err)
}
defer pubsubClient.Close()
// Create a PubSub subscription we can use to listen for messages.
s, err := setupPubSub(projectID, pubSubTopic, pubSubSub)
if err != nil {
return fmt.Errorf("setupPubSub: %v", err)
}
// topic is the PubSub topic string where messages should be sent.
topic := "projects/" + projectID + "/topics/" + pubSubTopic
// Build the QuasiID slice.
var q []*dlppb.FieldId
for _, c := range columnNames {
q = append(q, &dlppb.FieldId{Name: c})
}
// Create a configured request.
req := &dlppb.CreateDlpJobRequest{
Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
Job: &dlppb.CreateDlpJobRequest_RiskJob{
RiskJob: &dlppb.RiskAnalysisJobConfig{
// PrivacyMetric configures what to compute.
PrivacyMetric: &dlppb.PrivacyMetric{
Type: &dlppb.PrivacyMetric_KAnonymityConfig_{
KAnonymityConfig: &dlppb.PrivacyMetric_KAnonymityConfig{
QuasiIds: q,
},
},
},
// SourceTable describes where to find the data.
SourceTable: &dlppb.BigQueryTable{
ProjectId: dataProject,
DatasetId: datasetID,
TableId: tableID,
},
// Send a message to PubSub using Actions.
Actions: []*dlppb.Action{
{
Action: &dlppb.Action_PubSub{
PubSub: &dlppb.Action_PublishToPubSub{
Topic: topic,
},
},
},
},
},
},
}
// Create the risk job.
j, err := client.CreateDlpJob(ctx, req)
if err != nil {
return fmt.Errorf("CreateDlpJob: %v", err)
}
fmt.Fprintf(w, "Created job: %v\n", j.GetName())
// Wait for the risk job to finish by waiting for a PubSub message.
// This only waits for 10 minutes. For long jobs, consider using a truly
// asynchronous execution model such as Cloud Functions.
ctx, cancel := context.WithTimeout(ctx, 10*time.Minute)
defer cancel()
err = s.Receive(ctx, func(ctx context.Context, msg *pubsub.Message) {
// If this is the wrong job, do not process the result.
if msg.Attributes["DlpJobName"] != j.GetName() {
msg.Nack()
return
}
msg.Ack()
time.Sleep(500 * time.Millisecond)
j, err := client.GetDlpJob(ctx, &dlppb.GetDlpJobRequest{
Name: j.GetName(),
})
if err != nil {
fmt.Fprintf(w, "GetDlpJob: %v", err)
return
}
h := j.GetRiskDetails().GetKAnonymityResult().GetEquivalenceClassHistogramBuckets()
for i, b := range h {
fmt.Fprintf(w, "Histogram bucket %v\n", i)
fmt.Fprintf(w, " Size range: [%v,%v]\n", b.GetEquivalenceClassSizeLowerBound(), b.GetEquivalenceClassSizeUpperBound())
fmt.Fprintf(w, " %v unique values total\n", b.GetBucketSize())
for _, v := range b.GetBucketValues() {
var qvs []string
for _, qv := range v.GetQuasiIdsValues() {
qvs = append(qvs, qv.String())
}
fmt.Fprintf(w, " QuasiID values: %s\n", strings.Join(qvs, ", "))
fmt.Fprintf(w, " Class size: %v\n", v.GetEquivalenceClassSize())
}
}
// Stop listening for more messages.
cancel()
})
if err != nil {
return fmt.Errorf("Receive: %v", err)
}
return nil
}
Java
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
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.Action.PublishToPubSub;
import com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails.KAnonymityResult;
import com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails.KAnonymityResult.KAnonymityEquivalenceClass;
import com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails.KAnonymityResult.KAnonymityHistogramBucket;
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.LocationName;
import com.google.privacy.dlp.v2.PrivacyMetric;
import com.google.privacy.dlp.v2.PrivacyMetric.KAnonymityConfig;
import com.google.privacy.dlp.v2.RiskAnalysisJobConfig;
import com.google.privacy.dlp.v2.Value;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.ProjectTopicName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.stream.Collectors;
class RiskAnalysisKAnonymity {
public static void main(String[] args) throws Exception {
// TODO(developer): Replace these variables before running the sample.
String projectId = "your-project-id";
String datasetId = "your-bigquery-dataset-id";
String tableId = "your-bigquery-table-id";
String topicId = "pub-sub-topic";
String subscriptionId = "pub-sub-subscription";
calculateKAnonymity(projectId, datasetId, tableId, topicId, subscriptionId);
}
public static void calculateKAnonymity(
String projectId, String datasetId, String tableId, 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 dlpServiceClient = DlpServiceClient.create()) {
// Specify the BigQuery table to analyze
BigQueryTable bigQueryTable =
BigQueryTable.newBuilder()
.setProjectId(projectId)
.setDatasetId(datasetId)
.setTableId(tableId)
.build();
// These values represent the column names of quasi-identifiers to analyze
List<String> quasiIds = Arrays.asList("Age", "Mystery");
// Configure the privacy metric for the job
List<FieldId> quasiIdFields =
quasiIds.stream()
.map(columnName -> FieldId.newBuilder().setName(columnName).build())
.collect(Collectors.toList());
KAnonymityConfig kanonymityConfig =
KAnonymityConfig.newBuilder().addAllQuasiIds(quasiIdFields).build();
PrivacyMetric privacyMetric =
PrivacyMetric.newBuilder().setKAnonymityConfig(kanonymityConfig).build();
// Create action to publish job status notifications over Google Cloud Pub/Sub
ProjectTopicName topicName = ProjectTopicName.of(projectId, topicId);
PublishToPubSub publishToPubSub =
PublishToPubSub.newBuilder().setTopic(topicName.toString()).build();
Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
// Configure the risk analysis job to perform
RiskAnalysisJobConfig riskAnalysisJobConfig =
RiskAnalysisJobConfig.newBuilder()
.setSourceTable(bigQueryTable)
.setPrivacyMetric(privacyMetric)
.addActions(action)
.build();
// Build the request to be sent by the client
CreateDlpJobRequest createDlpJobRequest =
CreateDlpJobRequest.newBuilder()
.setParent(LocationName.of(projectId, "global").toString())
.setRiskJob(riskAnalysisJobConfig)
.build();
// Send the request to the API using the client
DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
// 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();
}
// Build a request to get the completed job
GetDlpJobRequest getDlpJobRequest =
GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
// Retrieve completed job status
DlpJob completedJob = dlpServiceClient.getDlpJob(getDlpJobRequest);
System.out.println("Job status: " + completedJob.getState());
// Get the result and parse through and process the information
KAnonymityResult kanonymityResult = completedJob.getRiskDetails().getKAnonymityResult();
List<KAnonymityHistogramBucket> histogramBucketList =
kanonymityResult.getEquivalenceClassHistogramBucketsList();
for (KAnonymityHistogramBucket result : histogramBucketList) {
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(Value::toString)
.collect(Collectors.toList());
System.out.println("\tQuasi-ID values: " + String.join(", ", quasiIdValues));
System.out.println("\tClass size: " + bucket.getEquivalenceClassSize());
}
}
}
}
// 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();
}
}
}Node.js
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
// 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 projectId = 'my-project';
// The project ID the table is stored under
// This may or (for public datasets) may not equal the calling project ID
// const tableProjectId = 'my-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 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'
// A set of columns that form a composite key ('quasi-identifiers')
// const quasiIds = [{ name: 'age' }, { name: 'city' }];
async function kAnonymityAnalysis() {
const sourceTable = {
projectId: tableProjectId,
datasetId: datasetId,
tableId: tableId,
};
// Construct request for creating a risk analysis job
const request = {
parent: `projects/${projectId}/locations/global`,
riskJob: {
privacyMetric: {
kAnonymityConfig: {
quasiIds: quasiIds,
},
},
sourceTable: sourceTable,
actions: [
{
pubSub: {
topic: `projects/${projectId}/topics/${topicId}`,
},
},
],
},
};
// Create helper function for unpacking values
const getValue = obj => obj[Object.keys(obj)[0]];
// Run risk analysis job
const [topicResponse] = await pubsub.topic(topicId).get();
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);
});
setTimeout(() => {
console.log(' Waiting for DLP job to fully complete');
}, 500);
const [job] = await dlp.getDlpJob({name: jobName});
const histogramBuckets =
job.riskDetails.kAnonymityResult.equivalenceClassHistogramBuckets;
histogramBuckets.forEach((histogramBucket, histogramBucketIdx) => {
console.log(`Bucket ${histogramBucketIdx}:`);
console.log(
` Bucket size range: [${histogramBucket.equivalenceClassSizeLowerBound}, ${histogramBucket.equivalenceClassSizeUpperBound}]`
);
histogramBucket.bucketValues.forEach(valueBucket => {
const quasiIdValues = valueBucket.quasiIdsValues
.map(getValue)
.join(', ');
console.log(` Quasi-ID values: {${quasiIdValues}}`);
console.log(` Class size: ${valueBucket.equivalenceClassSize}`);
});
});
}
kAnonymityAnalysis();Python
如需了解如何安装和使用 Cloud DLP 客户端库，请参阅 Cloud DLP 客户端库。
def k_anonymity_analysis(
project,
table_project_id,
dataset_id,
table_id,
topic_id,
subscription_id,
quasi_ids,
timeout=300,
):
"""Uses the Data Loss Prevention API to compute the k-anonymity of a
column set in a Google BigQuery table.
Args:
project: The Google Cloud project id to use as a parent resource.
table_project_id: The Google Cloud project id where the BigQuery table
is stored.
dataset_id: The id of the dataset to inspect.
table_id: The id of the table to inspect.
topic_id: The name of the Pub/Sub topic to notify once the job
completes.
subscription_id: The name of the Pub/Sub subscription to use when
listening for job completion notifications.
quasi_ids: A set of columns that form a composite key.
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 concurrent.futures
# 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
# Create helper function for unpacking values
def get_values(obj):
return int(obj.integer_value)
# Instantiate a client.
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Convert the project id into a full resource id.
topic = google.cloud.pubsub.PublisherClient.topic_path(project, topic_id)
parent = f"projects/{project}/locations/global"
# Location info of the BigQuery table.
source_table = {
"project_id": table_project_id,
"dataset_id": dataset_id,
"table_id": table_id,
}
# Convert quasi id list to Protobuf type
def map_fields(field):
return {"name": field}
quasi_ids = map(map_fields, quasi_ids)
# Tell the API where to send a notification when the job is complete.
actions = [{"pub_sub": {"topic": topic}}]
# Configure risk analysis job
# Give the name of the numeric column to compute risk metrics for
risk_job = {
"privacy_metric": {"k_anonymity_config": {"quasi_ids": quasi_ids}},
"source_table": source_table,
"actions": actions,
}
# Call API to start risk analysis job
operation = dlp.create_dlp_job(request={"parent": parent, "risk_job": risk_job})
def callback(message):
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(request={"name": operation.name})
histogram_buckets = (
job.risk_details.k_anonymity_result.equivalence_class_histogram_buckets
)
# Print bucket stats
for i, bucket in enumerate(histogram_buckets):
print("Bucket {}:".format(i))
if bucket.equivalence_class_size_lower_bound:
print(
" Bucket size range: [{}, {}]".format(
bucket.equivalence_class_size_lower_bound,
bucket.equivalence_class_size_upper_bound,
)
)
for value_bucket in bucket.bucket_values:
print(
" Quasi-ID values: {}".format(
map(get_values, value_bucket.quasi_ids_values)
)
)
print(
" Class size: {}".format(
value_bucket.equivalence_class_size
)
)
subscription.set_result(None)
else:
# This is not the message we're looking for.
message.drop()
# 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)
subscription = subscriber.subscribe(subscription_path, callback)
try:
subscription.result(timeout=timeout)
except concurrent.futures.TimeoutError:
print(
"No event received before the timeout. Please verify that the "
"subscription provided is subscribed to the topic provided."
)
subscription.close()
后续步骤
如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅 Google Cloud 示例浏览器。