Examples with InfoType com.google.privacy.dlp.v2.InfoType used on opensource projects

Example 11 with InfoType

use of com.google.privacy.dlp.v2.InfoType in project java-docs-samples by GoogleCloudPlatform.

the class Triggers method main.

// [END dlp_delete_trigger]
/**
 * Command line application to crate, list and delete triggers.
 */
public static void main(String[] args) throws Exception {
    OptionGroup optionsGroup = new OptionGroup();
    optionsGroup.setRequired(true);
    Option createTriggerOption = new Option("c", "create", false, "Create trigger to scan a GCS bucket");
    optionsGroup.addOption(createTriggerOption);
    Option listTriggersOption = new Option("l", "list", false, "List triggers");
    optionsGroup.addOption(listTriggersOption);
    Option deleteTriggerOption = new Option("d", "delete", false, "Delete trigger");
    optionsGroup.addOption(deleteTriggerOption);
    Options commandLineOptions = new Options();
    commandLineOptions.addOptionGroup(optionsGroup);
    Option bucketNameOption = Option.builder("bucketName").hasArg(true).required(false).build();
    commandLineOptions.addOption(bucketNameOption);
    Option gcsFileNameOption = Option.builder("fileName").hasArg(true).required(false).build();
    commandLineOptions.addOption(gcsFileNameOption);
    Option minLikelihoodOption = Option.builder("minLikelihood").hasArg(true).required(false).build();
    commandLineOptions.addOption(minLikelihoodOption);
    Option maxFindingsOption = Option.builder("maxFindings").hasArg(true).required(false).build();
    commandLineOptions.addOption(maxFindingsOption);
    Option infoTypesOption = Option.builder("infoTypes").hasArg(true).required(false).build();
    infoTypesOption.setArgs(Option.UNLIMITED_VALUES);
    commandLineOptions.addOption(infoTypesOption);
    Option projectIdOption = Option.builder("projectId").hasArg(true).required(false).build();
    commandLineOptions.addOption(projectIdOption);
    Option triggerIdOption = Option.builder("triggerId").hasArg(true).required(false).build();
    commandLineOptions.addOption(triggerIdOption);
    Option displayNameOption = Option.builder("displayName").hasArg(true).required(false).build();
    commandLineOptions.addOption(displayNameOption);
    Option descriptionOption = Option.builder("description").hasArg(true).required(false).build();
    commandLineOptions.addOption(descriptionOption);
    Option scanPeriodOption = Option.builder("scanPeriod").hasArg(true).required(false).build();
    commandLineOptions.addOption(scanPeriodOption);
    CommandLineParser parser = new DefaultParser();
    HelpFormatter formatter = new HelpFormatter();
    CommandLine cmd;
    try {
        cmd = parser.parse(commandLineOptions, args);
    } catch (ParseException e) {
        System.out.println(e.getMessage());
        formatter.printHelp(DeIdentification.class.getName(), commandLineOptions);
        System.exit(1);
        return;
    }
    String projectId = cmd.getOptionValue(projectIdOption.getOpt(), ServiceOptions.getDefaultProjectId());
    if (cmd.hasOption("c")) {
        Likelihood minLikelihood = Likelihood.valueOf(cmd.getOptionValue(minLikelihoodOption.getOpt(), Likelihood.LIKELIHOOD_UNSPECIFIED.name()));
        int maxFindings = Integer.parseInt(cmd.getOptionValue(maxFindingsOption.getOpt(), "0"));
        String triggerId = cmd.getOptionValue(triggerIdOption.getOpt());
        String displayName = cmd.getOptionValue(displayNameOption.getOpt(), "");
        String description = cmd.getOptionValue(descriptionOption.getOpt(), "");
        String bucketName = cmd.getOptionValue(bucketNameOption.getOpt());
        String fileName = cmd.getOptionValue(gcsFileNameOption.getOpt());
        int scanPeriod = Integer.valueOf(cmd.getOptionValue(scanPeriodOption.getOpt()));
        List<InfoType> infoTypesList = new ArrayList<>();
        if (cmd.hasOption(infoTypesOption.getOpt())) {
            infoTypesList = new ArrayList<>();
            String[] infoTypes = cmd.getOptionValues(infoTypesOption.getOpt());
            for (String infoType : infoTypes) {
                infoTypesList.add(InfoType.newBuilder().setName(infoType).build());
            }
        }
        createTrigger(triggerId, displayName, description, bucketName, fileName, scanPeriod, infoTypesList, minLikelihood, maxFindings, projectId);
    } else if (cmd.hasOption("l")) {
        // list triggers
        listTriggers(projectId);
    } else if (cmd.hasOption("d")) {
        String triggerId = cmd.getOptionValue(triggerIdOption.getOpt());
        deleteTrigger(projectId, triggerId);
    }
}

Example 12 with InfoType

use of com.google.privacy.dlp.v2.InfoType in project java-docs-samples by GoogleCloudPlatform.

the class DeIdentification method reIdentifyWithFpe.

// [END dlp_deidentify_fpe]
// [START dlp_reidentify_fpe]
/**
 * Reidentify a string by encrypting sensitive information while preserving format.
 *
 * @param string The string to reidentify.
 * @param alphabet The set of characters used when encrypting the input. For more information, see
 *     cloud.google.com/dlp/docs/reference/rest/v2/content/deidentify
 * @param keyName The name of the Cloud KMS key to use when decrypting the wrapped key.
 * @param wrappedKey The encrypted (or "wrapped") AES-256 encryption key.
 * @param projectId ID of Google Cloud project to run the API under.
 * @param surrogateType The name of the surrogate custom info type to used during the encryption
 *     process.
 */
private static void reIdentifyWithFpe(String string, FfxCommonNativeAlphabet alphabet, String keyName, String wrappedKey, String projectId, String surrogateType) {
    // instantiate a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        ContentItem contentItem = ContentItem.newBuilder().setValue(string).build();
        InfoType surrogateTypeObject = InfoType.newBuilder().setName(surrogateType).build();
        // Create the format-preserving encryption (FPE) configuration
        KmsWrappedCryptoKey kmsWrappedCryptoKey = KmsWrappedCryptoKey.newBuilder().setWrappedKey(ByteString.copyFrom(BaseEncoding.base64().decode(wrappedKey))).setCryptoKeyName(keyName).build();
        CryptoKey cryptoKey = CryptoKey.newBuilder().setKmsWrapped(kmsWrappedCryptoKey).build();
        CryptoReplaceFfxFpeConfig cryptoReplaceFfxFpeConfig = CryptoReplaceFfxFpeConfig.newBuilder().setCryptoKey(cryptoKey).setCommonAlphabet(alphabet).setSurrogateInfoType(surrogateTypeObject).build();
        // Create the deidentification transformation configuration
        PrimitiveTransformation primitiveTransformation = PrimitiveTransformation.newBuilder().setCryptoReplaceFfxFpeConfig(cryptoReplaceFfxFpeConfig).build();
        InfoTypeTransformation infoTypeTransformationObject = InfoTypeTransformation.newBuilder().setPrimitiveTransformation(primitiveTransformation).addInfoTypes(surrogateTypeObject).build();
        InfoTypeTransformations infoTypeTransformationArray = InfoTypeTransformations.newBuilder().addTransformations(infoTypeTransformationObject).build();
        // Create the inspection config
        CustomInfoType customInfoType = CustomInfoType.newBuilder().setInfoType(surrogateTypeObject).setSurrogateType(SurrogateType.newBuilder().build()).build();
        InspectConfig inspectConfig = InspectConfig.newBuilder().addCustomInfoTypes(customInfoType).build();
        // Create the reidentification request object
        DeidentifyConfig reidentifyConfig = DeidentifyConfig.newBuilder().setInfoTypeTransformations(infoTypeTransformationArray).build();
        ReidentifyContentRequest request = ReidentifyContentRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setReidentifyConfig(reidentifyConfig).setInspectConfig(inspectConfig).setItem(contentItem).build();
        // Execute the deidentification request
        ReidentifyContentResponse response = dlpServiceClient.reidentifyContent(request);
        // Print the reidentified input value
        // e.g. "My SSN is 7261298621" --> "My SSN is 123456789"
        String result = response.getItem().getValue();
        System.out.println(result);
    } catch (Exception e) {
        System.out.println("Error in reidentifyWithFpe: " + e.getMessage());
    }
}

Example 13 with InfoType

use of com.google.privacy.dlp.v2.InfoType in project java-docs-samples by GoogleCloudPlatform.

the class Inspect method inspectGcsFile.

// [END dlp_inspect_file]
// [START dlp_inspect_gcs]
/**
 * Inspect GCS file for Info types and wait on job completion using Google Cloud Pub/Sub
 * notification
 *
 * @param bucketName The name of the bucket where the file resides.
 * @param fileName The path to the file within the bucket to inspect (can include wildcards, eg.
 *     my-image.*)
 * @param minLikelihood The minimum likelihood required before returning a match
 * @param infoTypes The infoTypes of information to match
 * @param maxFindings The maximum number of findings to report (0 = server maximum)
 * @param topicId Google Cloud Pub/Sub topic Id to notify of job status
 * @param subscriptionId Google Cloud Subscription to above topic to listen for job status updates
 * @param projectId Google Cloud project ID
 */
private static void inspectGcsFile(String bucketName, String fileName, Likelihood minLikelihood, List<InfoType> infoTypes, int maxFindings, String topicId, String subscriptionId, String projectId) throws Exception {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        CloudStorageOptions cloudStorageOptions = CloudStorageOptions.newBuilder().setFileSet(CloudStorageOptions.FileSet.newBuilder().setUrl("gs://" + bucketName + "/" + fileName)).build();
        StorageConfig storageConfig = StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).build();
        FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
        InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).build();
        String pubSubTopic = String.format("projects/%s/topics/%s", projectId, topicId);
        Action.PublishToPubSub publishToPubSub = Action.PublishToPubSub.newBuilder().setTopic(pubSubTopic).build();
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        InspectJobConfig inspectJobConfig = InspectJobConfig.newBuilder().setStorageConfig(storageConfig).setInspectConfig(inspectConfig).addActions(action).build();
        // Semi-synchronously submit an inspect job, and wait on results
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectJob(inspectJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        System.out.println("Job created with ID:" + dlpJob.getName());
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.of(projectId, subscriptionId), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJob.getName())) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (Exception e) {
            System.out.println("Unable to verify job completion.");
        }
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build());
        System.out.println("Job status: " + completedJob.getState());
        InspectDataSourceDetails inspectDataSourceDetails = completedJob.getInspectDetails();
        InspectDataSourceDetails.Result result = inspectDataSourceDetails.getResult();
        if (result.getInfoTypeStatsCount() > 0) {
            System.out.println("Findings: ");
            for (InfoTypeStats infoTypeStat : result.getInfoTypeStatsList()) {
                System.out.print("\tInfo type: " + infoTypeStat.getInfoType().getName());
                System.out.println("\tCount: " + infoTypeStat.getCount());
            }
        } else {
            System.out.println("No findings.");
        }
    }
}

Example 14 with InfoType

use of com.google.privacy.dlp.v2.InfoType in project java-docs-samples by GoogleCloudPlatform.

the class Inspect method inspectFile.

// [END dlp_inspect_string]
// [START dlp_inspect_file]
/**
 * Inspect a local file
 *
 * @param filePath The path to a local file to inspect. Can be a text, JPG, or PNG file.
 * @param minLikelihood The minimum likelihood required before returning a match
 * @param maxFindings The maximum number of findings to report (0 = server maximum)
 * @param infoTypes The infoTypes of information to match
 * @param includeQuote Whether to include the matching string
 * @param projectId Google Cloud project ID
 */
private static void inspectFile(String filePath, Likelihood minLikelihood, int maxFindings, List<InfoType> infoTypes, boolean includeQuote, String projectId) {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        // detect file mime type, default to application/octet-stream
        String mimeType = URLConnection.guessContentTypeFromName(filePath);
        if (mimeType == null) {
            mimeType = MimetypesFileTypeMap.getDefaultFileTypeMap().getContentType(filePath);
        }
        ByteContentItem.BytesType bytesType;
        switch(mimeType) {
            case "image/jpeg":
                bytesType = ByteContentItem.BytesType.IMAGE_JPEG;
                break;
            case "image/bmp":
                bytesType = ByteContentItem.BytesType.IMAGE_BMP;
                break;
            case "image/png":
                bytesType = ByteContentItem.BytesType.IMAGE_PNG;
                break;
            case "image/svg":
                bytesType = ByteContentItem.BytesType.IMAGE_SVG;
                break;
            default:
                bytesType = ByteContentItem.BytesType.BYTES_TYPE_UNSPECIFIED;
                break;
        }
        byte[] data = Files.readAllBytes(Paths.get(filePath));
        ByteContentItem byteContentItem = ByteContentItem.newBuilder().setType(bytesType).setData(ByteString.copyFrom(data)).build();
        ContentItem contentItem = ContentItem.newBuilder().setByteItem(byteContentItem).build();
        FindingLimits findingLimits = FindingLimits.newBuilder().setMaxFindingsPerRequest(maxFindings).build();
        InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).setMinLikelihood(minLikelihood).setLimits(findingLimits).setIncludeQuote(includeQuote).build();
        InspectContentRequest request = InspectContentRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setInspectConfig(inspectConfig).setItem(contentItem).build();
        InspectContentResponse response = dlpServiceClient.inspectContent(request);
        InspectResult result = response.getResult();
        if (result.getFindingsCount() > 0) {
            System.out.println("Findings: ");
            for (Finding finding : result.getFindingsList()) {
                if (includeQuote) {
                    System.out.print("\tQuote: " + finding.getQuote());
                }
                System.out.print("\tInfo type: " + finding.getInfoType().getName());
                System.out.println("\tLikelihood: " + finding.getLikelihood());
            }
        } else {
            System.out.println("No findings.");
        }
    } catch (Exception e) {
        System.out.println("Error in inspectFile: " + e.getMessage());
    }
}

Example 15 with InfoType

use of com.google.privacy.dlp.v2.InfoType in project java-docs-samples by GoogleCloudPlatform.

the class RiskAnalysis method main.

// [END dlp_k_map]
/**
 * Command line application to perform risk analysis using the Data Loss Prevention API. Supported
 * data format: BigQuery tables
 */
public static void main(String[] args) throws Exception {
    OptionGroup optionsGroup = new OptionGroup();
    optionsGroup.setRequired(true);
    Option numericalAnalysisOption = new Option("n", "numerical");
    optionsGroup.addOption(numericalAnalysisOption);
    Option categoricalAnalysisOption = new Option("c", "categorical");
    optionsGroup.addOption(categoricalAnalysisOption);
    Option kanonymityOption = new Option("a", "kAnonymity");
    optionsGroup.addOption(kanonymityOption);
    Option kmapOption = new Option("m", "kAnonymity");
    optionsGroup.addOption(kmapOption);
    Option ldiversityOption = new Option("l", "lDiversity");
    optionsGroup.addOption(ldiversityOption);
    Options commandLineOptions = new Options();
    commandLineOptions.addOptionGroup(optionsGroup);
    Option datasetIdOption = Option.builder("datasetId").hasArg(true).required(false).build();
    commandLineOptions.addOption(datasetIdOption);
    Option tableIdOption = Option.builder("tableId").hasArg(true).required(false).build();
    commandLineOptions.addOption(tableIdOption);
    Option projectIdOption = Option.builder("projectId").hasArg(true).required(false).build();
    commandLineOptions.addOption(projectIdOption);
    Option topicIdOption = Option.builder("topicId").hasArg(true).required(false).build();
    commandLineOptions.addOption(topicIdOption);
    Option subscriptionIdOption = Option.builder("subscriptionId").hasArg(true).required(false).build();
    commandLineOptions.addOption(subscriptionIdOption);
    Option columnNameOption = Option.builder("columnName").hasArg(true).required(false).build();
    commandLineOptions.addOption(columnNameOption);
    Option sensitiveAttributeOption = Option.builder("sensitiveAttribute").hasArg(true).required(false).build();
    commandLineOptions.addOption(sensitiveAttributeOption);
    Option regionCodeOption = Option.builder("regionCode").hasArg(true).required(false).build();
    commandLineOptions.addOption(regionCodeOption);
    Option quasiIdColumnNamesOption = Option.builder("quasiIdColumnNames").hasArg(true).required(false).build();
    quasiIdColumnNamesOption.setArgs(Option.UNLIMITED_VALUES);
    commandLineOptions.addOption(quasiIdColumnNamesOption);
    Option infoTypesOption = Option.builder("infoTypes").hasArg(true).required(false).build();
    infoTypesOption.setArgs(Option.UNLIMITED_VALUES);
    commandLineOptions.addOption(infoTypesOption);
    CommandLineParser parser = new DefaultParser();
    HelpFormatter formatter = new HelpFormatter();
    CommandLine cmd;
    try {
        cmd = parser.parse(commandLineOptions, args);
    } catch (ParseException e) {
        System.out.println(e.getMessage());
        formatter.printHelp(RiskAnalysis.class.getName(), commandLineOptions);
        System.exit(1);
        return;
    }
    String datasetId = cmd.getOptionValue(datasetIdOption.getOpt());
    String tableId = cmd.getOptionValue(tableIdOption.getOpt());
    // use default project id when project id is not specified
    String projectId = cmd.getOptionValue(projectIdOption.getOpt(), ServiceOptions.getDefaultProjectId());
    String regionCode = cmd.getOptionValue(regionCodeOption.getOpt(), "US");
    String topicId = cmd.getOptionValue(topicIdOption.getOpt());
    String subscriptionId = cmd.getOptionValue(subscriptionIdOption.getOpt());
    List<InfoType> infoTypesList = Collections.emptyList();
    if (cmd.hasOption(infoTypesOption.getOpt())) {
        infoTypesList = new ArrayList<>();
        String[] infoTypes = cmd.getOptionValues(infoTypesOption.getOpt());
        for (String infoType : infoTypes) {
            infoTypesList.add(InfoType.newBuilder().setName(infoType).build());
        }
    }
    if (cmd.hasOption("n")) {
        // numerical stats analysis
        String columnName = cmd.getOptionValue(columnNameOption.getOpt());
        numericalStatsAnalysis(projectId, datasetId, tableId, columnName, topicId, subscriptionId);
    } else if (cmd.hasOption("c")) {
        // categorical stats analysis
        String columnName = cmd.getOptionValue(columnNameOption.getOpt());
        categoricalStatsAnalysis(projectId, datasetId, tableId, columnName, topicId, subscriptionId);
    } else if (cmd.hasOption("a")) {
        // k-anonymity analysis
        List<String> quasiIdColumnNames = Arrays.asList(cmd.getOptionValues(quasiIdColumnNamesOption.getOpt()));
        calculateKAnonymity(projectId, datasetId, tableId, quasiIdColumnNames, topicId, subscriptionId);
    } else if (cmd.hasOption("m")) {
        // k-map analysis
        List<String> quasiIdColumnNames = Arrays.asList(cmd.getOptionValues(quasiIdColumnNamesOption.getOpt()));
        calculateKMap(projectId, datasetId, tableId, quasiIdColumnNames, infoTypesList, regionCode, topicId, subscriptionId);
    } else if (cmd.hasOption("l")) {
        // l-diversity analysis
        String sensitiveAttribute = cmd.getOptionValue(sensitiveAttributeOption.getOpt());
        List<String> quasiIdColumnNames = Arrays.asList(cmd.getOptionValues(quasiIdColumnNamesOption.getOpt()));
        calculateLDiversity(projectId, datasetId, tableId, sensitiveAttribute, quasiIdColumnNames, topicId, subscriptionId);
    }
}