Examples with DlpServiceClient com.google.cloud.dlp.v2.DlpServiceClient used on opensource projects

Example 1 with DlpServiceClient

use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.

the class DeIdentification method deIdentifyWithMask.

// [START dlp_deidentify_masking]
/**
 * Deidentify a string by masking sensitive information with a character using the DLP API.
 *
 * @param string The string to deidentify.
 * @param maskingCharacter (Optional) The character to mask sensitive data with.
 * @param numberToMask (Optional) The number of characters' worth of sensitive data to mask.
 *     Omitting this value or setting it to 0 masks all sensitive chars.
 * @param projectId ID of Google Cloud project to run the API under.
 */
private static void deIdentifyWithMask(String string, Character maskingCharacter, int numberToMask, String projectId) {
    // instantiate a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        ContentItem contentItem = ContentItem.newBuilder().setValue(string).build();
        CharacterMaskConfig characterMaskConfig = CharacterMaskConfig.newBuilder().setMaskingCharacter(maskingCharacter.toString()).setNumberToMask(numberToMask).build();
        // Create the deidentification transformation configuration
        PrimitiveTransformation primitiveTransformation = PrimitiveTransformation.newBuilder().setCharacterMaskConfig(characterMaskConfig).build();
        InfoTypeTransformation infoTypeTransformationObject = InfoTypeTransformation.newBuilder().setPrimitiveTransformation(primitiveTransformation).build();
        InfoTypeTransformations infoTypeTransformationArray = InfoTypeTransformations.newBuilder().addTransformations(infoTypeTransformationObject).build();
        DeidentifyConfig deidentifyConfig = DeidentifyConfig.newBuilder().setInfoTypeTransformations(infoTypeTransformationArray).build();
        // Create the deidentification request object
        DeidentifyContentRequest request = DeidentifyContentRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setDeidentifyConfig(deidentifyConfig).setItem(contentItem).build();
        // Execute the deidentification request
        DeidentifyContentResponse response = dlpServiceClient.deidentifyContent(request);
        // Print the character-masked input value
        // e.g. "My SSN is 123456789" --> "My SSN is *********"
        String result = response.getItem().getValue();
        System.out.println(result);
    } catch (Exception e) {
        System.out.println("Error in deidentifyWithMask: " + e.getMessage());
    }
}

Example 2 with DlpServiceClient

use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.

the class DeIdentification method deidentifyWithDateShift.

// [END dlp_reidentify_fpe]
// [START dlp_deidentify_date_shift]
/**
 * @param inputCsvPath The path to the CSV file to deidentify
 * @param outputCsvPath (Optional) path to the output CSV file
 * @param dateFields The list of (date) fields in the CSV file to date shift
 * @param lowerBoundDays The maximum number of days to shift a date backward
 * @param upperBoundDays The maximum number of days to shift a date forward
 * @param contextFieldId (Optional) The column to determine date shift, default : a random shift
 *     amount
 * @param wrappedKey (Optional) The encrypted ('wrapped') AES-256 key to use when shifting dates
 * @param keyName (Optional) The name of the Cloud KMS key used to encrypt ('wrap') the AES-256
 *     key
 * @param projectId ID of Google Cloud project to run the API under.
 */
private static void deidentifyWithDateShift(Path inputCsvPath, Path outputCsvPath, String[] dateFields, int lowerBoundDays, int upperBoundDays, String contextFieldId, String wrappedKey, String keyName, String projectId) throws Exception {
    // instantiate a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        // Set the maximum days to shift a day backward (lowerbound), forward (upperbound)
        DateShiftConfig.Builder dateShiftConfigBuilder = DateShiftConfig.newBuilder().setLowerBoundDays(lowerBoundDays).setUpperBoundDays(upperBoundDays);
        // If contextFieldId, keyName or wrappedKey is set: all three arguments must be valid
        if (contextFieldId != null && keyName != null && wrappedKey != null) {
            dateShiftConfigBuilder.setContext(FieldId.newBuilder().setName(contextFieldId).build());
            KmsWrappedCryptoKey kmsWrappedCryptoKey = KmsWrappedCryptoKey.newBuilder().setCryptoKeyName(keyName).setWrappedKey(ByteString.copyFrom(BaseEncoding.base64().decode(wrappedKey))).build();
            dateShiftConfigBuilder.setCryptoKey(CryptoKey.newBuilder().setKmsWrapped(kmsWrappedCryptoKey).build());
        } else if (contextFieldId != null || keyName != null || wrappedKey != null) {
            throw new IllegalArgumentException("You must set either ALL or NONE of {contextFieldId, keyName, wrappedKey}!");
        }
        // Read and parse the CSV file
        BufferedReader br = null;
        String line;
        List<Table.Row> rows = new ArrayList<>();
        List<FieldId> headers;
        br = new BufferedReader(new FileReader(inputCsvPath.toFile()));
        // convert csv header to FieldId
        headers = Arrays.stream(br.readLine().split(",")).map(header -> FieldId.newBuilder().setName(header).build()).collect(Collectors.toList());
        while ((line = br.readLine()) != null) {
            // convert csv rows to Table.Row
            rows.add(convertCsvRowToTableRow(line));
        }
        br.close();
        Table table = Table.newBuilder().addAllHeaders(headers).addAllRows(rows).build();
        List<FieldId> dateFieldIds = Arrays.stream(dateFields).map(field -> FieldId.newBuilder().setName(field).build()).collect(Collectors.toList());
        DateShiftConfig dateShiftConfig = dateShiftConfigBuilder.build();
        FieldTransformation fieldTransformation = FieldTransformation.newBuilder().addAllFields(dateFieldIds).setPrimitiveTransformation(PrimitiveTransformation.newBuilder().setDateShiftConfig(dateShiftConfig).build()).build();
        DeidentifyConfig deidentifyConfig = DeidentifyConfig.newBuilder().setRecordTransformations(RecordTransformations.newBuilder().addFieldTransformations(fieldTransformation).build()).build();
        ContentItem tableItem = ContentItem.newBuilder().setTable(table).build();
        DeidentifyContentRequest request = DeidentifyContentRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setDeidentifyConfig(deidentifyConfig).setItem(tableItem).build();
        // Execute the deidentification request
        DeidentifyContentResponse response = dlpServiceClient.deidentifyContent(request);
        // Write out the response as a CSV file
        List<FieldId> outputHeaderFields = response.getItem().getTable().getHeadersList();
        List<Table.Row> outputRows = response.getItem().getTable().getRowsList();
        List<String> outputHeaders = outputHeaderFields.stream().map(FieldId::getName).collect(Collectors.toList());
        File outputFile = outputCsvPath.toFile();
        if (!outputFile.exists()) {
            outputFile.createNewFile();
        }
        BufferedWriter bufferedWriter = new BufferedWriter(new FileWriter(outputFile));
        // write out headers
        bufferedWriter.append(String.join(",", outputHeaders) + "\n");
        // write out each row
        for (Table.Row outputRow : outputRows) {
            String row = outputRow.getValuesList().stream().map(value -> value.getStringValue()).collect(Collectors.joining(","));
            bufferedWriter.append(row + "\n");
        }
        bufferedWriter.flush();
        bufferedWriter.close();
        System.out.println("Successfully saved date-shift output to: " + outputCsvPath.getFileName());
    } catch (Exception e) {
        System.out.println("Error in deidentifyWithDateShift: " + e.getMessage());
    }
}

Example 3 with DlpServiceClient

use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.

the class Inspect method inspectDatastore.

// [END dlp_inspect_gcs]
// [START dlp_inspect_datastore]
/**
 * Inspect a Datastore kind
 *
 * @param projectId The project ID containing the target Datastore
 * @param namespaceId The ID namespace of the Datastore document to inspect
 * @param kind The kind of the Datastore entity to inspect
 * @param minLikelihood The minimum likelihood required before returning a match
 * @param infoTypes The infoTypes of information to match
 * @param maxFindings max number of findings
 * @param topicId Google Cloud Pub/Sub topic to notify job status updates
 * @param subscriptionId Google Cloud Pub/Sub subscription to above topic to receive status
 *     updates
 */
private static void inspectDatastore(String projectId, String namespaceId, String kind, Likelihood minLikelihood, List<InfoType> infoTypes, int maxFindings, String topicId, String subscriptionId) {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        // Reference to the Datastore namespace
        PartitionId partitionId = PartitionId.newBuilder().setProjectId(projectId).setNamespaceId(namespaceId).build();
        // Reference to the Datastore kind
        KindExpression kindExpression = KindExpression.newBuilder().setName(kind).build();
        DatastoreOptions datastoreOptions = DatastoreOptions.newBuilder().setKind(kindExpression).setPartitionId(partitionId).build();
        // Construct Datastore configuration to be inspected
        StorageConfig storageConfig = StorageConfig.newBuilder().setDatastoreOptions(datastoreOptions).build();
        FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
        InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).build();
        String pubSubTopic = String.format("projects/%s/topics/%s", projectId, topicId);
        Action.PublishToPubSub publishToPubSub = Action.PublishToPubSub.newBuilder().setTopic(pubSubTopic).build();
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        InspectJobConfig inspectJobConfig = InspectJobConfig.newBuilder().setStorageConfig(storageConfig).setInspectConfig(inspectConfig).addActions(action).build();
        // Asynchronously submit an inspect job, and wait on results
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectJob(inspectJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        System.out.println("Job created with ID:" + dlpJob.getName());
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.of(projectId, subscriptionId), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJob.getName())) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (Exception e) {
            System.out.println("Unable to verify job completion.");
        }
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build());
        System.out.println("Job status: " + completedJob.getState());
        InspectDataSourceDetails inspectDataSourceDetails = completedJob.getInspectDetails();
        InspectDataSourceDetails.Result result = inspectDataSourceDetails.getResult();
        if (result.getInfoTypeStatsCount() > 0) {
            System.out.println("Findings: ");
            for (InfoTypeStats infoTypeStat : result.getInfoTypeStatsList()) {
                System.out.print("\tInfo type: " + infoTypeStat.getInfoType().getName());
                System.out.println("\tCount: " + infoTypeStat.getCount());
            }
        } else {
            System.out.println("No findings.");
        }
    } catch (Exception e) {
        System.out.println("inspectDatastore Problems: " + e.getMessage());
    }
}

Example 4 with DlpServiceClient

use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.

the class Inspect method inspectBigquery.

// [END dlp_inspect_datastore]
// [START dlp_inspect_bigquery]
/**
 * Inspect a BigQuery table
 *
 * @param projectId The project ID to run the API call under
 * @param datasetId The ID of the dataset to inspect, e.g. 'my_dataset'
 * @param tableId The ID of the table to inspect, e.g. 'my_table'
 * @param minLikelihood The minimum likelihood required before returning a match
 * @param infoTypes The infoTypes of information to match
 * @param maxFindings The maximum number of findings to report (0 = server maximum)
 * @param topicId Topic ID for pubsub.
 * @param subscriptionId Subscription ID for pubsub.
 */
private static void inspectBigquery(String projectId, String datasetId, String tableId, Likelihood minLikelihood, List<InfoType> infoTypes, int maxFindings, String topicId, String subscriptionId) {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        // Reference to the BigQuery table
        BigQueryTable tableReference = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
        BigQueryOptions bigQueryOptions = BigQueryOptions.newBuilder().setTableReference(tableReference).build();
        // Construct BigQuery configuration to be inspected
        StorageConfig storageConfig = StorageConfig.newBuilder().setBigQueryOptions(bigQueryOptions).build();
        FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
        InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).build();
        ProjectTopicName topic = ProjectTopicName.of(projectId, topicId);
        Action.PublishToPubSub publishToPubSub = Action.PublishToPubSub.newBuilder().setTopic(topic.toString()).build();
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        InspectJobConfig inspectJobConfig = InspectJobConfig.newBuilder().setStorageConfig(storageConfig).setInspectConfig(inspectConfig).addActions(action).build();
        // Asynchronously submit an inspect job, and wait on results
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectJob(inspectJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        System.out.println("Job created with ID:" + dlpJob.getName());
        // Wait for job completion semi-synchronously
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.of(projectId, subscriptionId), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJob.getName())) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (Exception e) {
            System.out.println("Unable to verify job completion.");
        }
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build());
        System.out.println("Job status: " + completedJob.getState());
        InspectDataSourceDetails inspectDataSourceDetails = completedJob.getInspectDetails();
        InspectDataSourceDetails.Result result = inspectDataSourceDetails.getResult();
        if (result.getInfoTypeStatsCount() > 0) {
            System.out.println("Findings: ");
            for (InfoTypeStats infoTypeStat : result.getInfoTypeStatsList()) {
                System.out.print("\tInfo type: " + infoTypeStat.getInfoType().getName());
                System.out.println("\tCount: " + infoTypeStat.getCount());
            }
        } else {
            System.out.println("No findings.");
        }
    } catch (Exception e) {
        System.out.println("inspectBigquery Problems: " + e.getMessage());
    }
}

Example 5 with DlpServiceClient

use of com.google.cloud.dlp.v2.DlpServiceClient in project java-docs-samples by GoogleCloudPlatform.

the class Inspect method inspectString.

/**
 * [START dlp_inspect_string] Inspect a text for given InfoTypes
 *
 * @param string String to instpect
 * @param minLikelihood The minimum likelihood required before returning a match
 * @param maxFindings The maximum number of findings to report (0 = server maximum)
 * @param infoTypes The infoTypes of information to match
 * @param includeQuote Whether to include the matching string
 * @param projectId Google Cloud project ID
 */
private static void inspectString(String string, Likelihood minLikelihood, int maxFindings, List<InfoType> infoTypes, boolean includeQuote, String projectId) {
    // instantiate a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
        InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).setIncludeQuote(includeQuote).build();
        ByteContentItem byteContentItem = ByteContentItem.newBuilder().setType(ByteContentItem.BytesType.TEXT_UTF8).setData(ByteString.copyFromUtf8(string)).build();
        ContentItem contentItem = ContentItem.newBuilder().setByteItem(byteContentItem).build();
        InspectContentRequest request = InspectContentRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectConfig(inspectConfig).setItem(contentItem).build();
        InspectContentResponse response = dlpServiceClient.inspectContent(request);
        if (response.getResult().getFindingsCount() > 0) {
            System.out.println("Findings: ");
            for (Finding finding : response.getResult().getFindingsList()) {
                if (includeQuote) {
                    System.out.print("\tQuote: " + finding.getQuote());
                }
                System.out.print("\tInfo type: " + finding.getInfoType().getName());
                System.out.println("\tLikelihood: " + finding.getLikelihood());
            }
        } else {
            System.out.println("No findings.");
        }
    } catch (Exception e) {
        System.out.println("Error in inspectString: " + e.getMessage());
    }
}