대형 커스텀 사전 감지기 만들기

using System;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;

public class CreateStoredInfoTypes
{
    public static StoredInfoType Create(
        string projectId,
        string outputPath,
        string storedInfoTypeId)
    {
        // Instantiate the dlp client.
        var dlp = DlpServiceClient.Create();

        // Construct the stored infotype config by specifying the public table and 
        // cloud storage output path.
        var storedInfoTypeConfig = new StoredInfoTypeConfig
        {
            DisplayName = "Github Usernames",
            Description = "Dictionary of Github usernames used in commits.",
            LargeCustomDictionary = new LargeCustomDictionaryConfig
            {
                BigQueryField = new BigQueryField
                {
                    Table = new BigQueryTable
                    {
                        DatasetId = "samples",
                        ProjectId = "bigquery-public-data",
                        TableId = "github_nested"
                    },
                    Field = new FieldId
                    {
                        Name = "actor"
                    }
                },
                OutputPath = new CloudStoragePath
                {
                    Path = outputPath
                }
            },
        };

        // Construct the request.
        var request = new CreateStoredInfoTypeRequest
        {
            ParentAsLocationName = new LocationName(projectId, "global"),
            Config = storedInfoTypeConfig,
            StoredInfoTypeId = storedInfoTypeId
        };

        // Call the API.
        StoredInfoType response = dlp.CreateStoredInfoType(request);

        // Inspect the response.
        Console.WriteLine($"Created the stored infotype at path: {response.Name}");

        return response;
    }
}

import (
	"context"
	"fmt"
	"io"

	dlp "cloud.google.com/go/dlp/apiv2"
	"cloud.google.com/go/dlp/apiv2/dlppb"
)

// createStoredInfoType creates a custom stored info type based on your input data.
func createStoredInfoType(w io.Writer, projectID, outputPath string) error {
	// projectId := "my-project-id"
	// outputPath := "gs://" + "your-bucket-name" + "path/to/directory"

	ctx := context.Background()

	// Initialize a client once and reuse it to send multiple requests. Clients
	// are safe to use across goroutines. When the client is no longer needed,
	// call the Close method to cleanup its resources.
	client, err := dlp.NewClient(ctx)
	if err != nil {
		return err
	}

	// Closing the client safely cleans up background resources.
	defer client.Close()

	// Specify the name you want to give the dictionary.
	displayName := "Github Usernames"

	// Specify a description of the dictionary.
	description := "Dictionary of GitHub usernames used in commits"

	// Specify the path to the location in a Cloud Storage
	// bucket to store the created dictionary.
	cloudStoragePath := &dlppb.CloudStoragePath{
		Path: outputPath,
	}

	// Specify your term list is stored in BigQuery.
	bigQueryField := &dlppb.BigQueryField{
		Table: &dlppb.BigQueryTable{
			ProjectId: "bigquery-public-data",
			DatasetId: "samples",
			TableId:   "github_nested",
		},
		Field: &dlppb.FieldId{
			Name: "actor",
		},
	}

	// Specify the configuration of the large custom dictionary.
	largeCustomDictionaryConfig := &dlppb.LargeCustomDictionaryConfig{
		OutputPath: cloudStoragePath,
		Source: &dlppb.LargeCustomDictionaryConfig_BigQueryField{
			BigQueryField: bigQueryField,
		},
	}

	// Specify the configuration for stored infoType.
	storedInfoTypeConfig := &dlppb.StoredInfoTypeConfig{
		DisplayName: displayName,
		Description: description,
		Type: &dlppb.StoredInfoTypeConfig_LargeCustomDictionary{
			LargeCustomDictionary: largeCustomDictionaryConfig,
		},
	}

	// Combine configurations into a request for the service.
	req := &dlppb.CreateStoredInfoTypeRequest{
		Parent:           fmt.Sprintf("projects/%s/locations/global", projectID),
		Config:           storedInfoTypeConfig,
		StoredInfoTypeId: "github-usernames",
	}

	// Send the request and receive response from the service.
	resp, err := client.CreateStoredInfoType(ctx, req)
	if err != nil {
		return err
	}

	// Print the result.
	fmt.Fprintf(w, "output: %v", resp.Name)
	return nil

}

import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.BigQueryField;
import com.google.privacy.dlp.v2.BigQueryTable;
import com.google.privacy.dlp.v2.CloudStoragePath;
import com.google.privacy.dlp.v2.CreateStoredInfoTypeRequest;
import com.google.privacy.dlp.v2.FieldId;
import com.google.privacy.dlp.v2.LargeCustomDictionaryConfig;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.StoredInfoType;
import com.google.privacy.dlp.v2.StoredInfoTypeConfig;
import java.io.IOException;

public class CreateStoredInfoType {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.

    //The Google Cloud project id to use as a parent resource.
    String projectId = "your-project-id";
    // The path to the location in a GCS bucket to store the created dictionary.
    String outputPath = "gs://" + "your-bucket-name" + "path/to/directory";
    createStoredInfoType(projectId, outputPath);
  }

  // Creates a custom stored info type that contains GitHub usernames used in commits.
  public static void createStoredInfoType(String projectId, String outputPath)
      throws IOException {
    try (DlpServiceClient dlp = DlpServiceClient.create()) {

      // Optionally set a display name and a description.
      String displayName = "GitHub usernames";
      String description = "Dictionary of GitHub usernames used in commits";

      // The output path where the custom dictionary containing the GitHub usernames will be stored.
      CloudStoragePath cloudStoragePath =
          CloudStoragePath.newBuilder()
              .setPath(outputPath)
              .build();

      // The reference to the table containing the GitHub usernames.
      BigQueryTable table = BigQueryTable.newBuilder()
              .setProjectId("bigquery-public-data")
              .setDatasetId("samples")
              .setTableId("github_nested")
              .build();

      // The reference to the BigQuery field that contains the GitHub usernames.
      BigQueryField bigQueryField = BigQueryField.newBuilder()
              .setTable(table)
              .setField(FieldId.newBuilder().setName("actor").build())
              .build();

      LargeCustomDictionaryConfig largeCustomDictionaryConfig =
          LargeCustomDictionaryConfig.newBuilder()
              .setOutputPath(cloudStoragePath)
              .setBigQueryField(bigQueryField)
              .build();

      StoredInfoTypeConfig storedInfoTypeConfig = StoredInfoTypeConfig.newBuilder()
              .setDisplayName(displayName)
              .setDescription(description)
              .setLargeCustomDictionary(largeCustomDictionaryConfig)
              .build();

      // Combine configurations into a request for the service.
      CreateStoredInfoTypeRequest createStoredInfoType = CreateStoredInfoTypeRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setConfig(storedInfoTypeConfig)
              .setStoredInfoTypeId("github-usernames")
              .build();

      // Send the request and receive response from the service.
      StoredInfoType response = dlp.createStoredInfoType(createStoredInfoType);

      // Print the results.
      System.out.println("Created Stored InfoType: " + response.getName());
    }
  }
}

// Import the required libraries
const dlp = require('@google-cloud/dlp');

// Create a DLP client
const dlpClient = new dlp.DlpServiceClient();

// The project ID to run the API call under.
// const projectId = "your-project-id";

// The identifier for the stored infoType
// const infoTypeId = 'github-usernames';

// The path to the location in a Cloud Storage bucket to store the created dictionary
// const outputPath = 'cloud-bucket-path';

// The project ID the table is stored under
// This may or (for public datasets) may not equal the calling project ID
// const dataProjectId = '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';

// Field ID to be used for constructing dictionary
// const fieldName = 'field_name';

async function createStoredInfoType() {
  // The name you want to give the dictionary.
  const displayName = 'GitHub usernames';
  // A description of the dictionary.
  const description = 'Dictionary of GitHub usernames used in commits';

  // Specify configuration for the large custom dictionary
  const largeCustomDictionaryConfig = {
    outputPath: {
      path: outputPath,
    },
    bigQueryField: {
      table: {
        datasetId: datasetId,
        projectId: dataProjectId,
        tableId: tableId,
      },
      field: {
        name: fieldName,
      },
    },
  };

  // Stored infoType configuration that uses large custom dictionary.
  const storedInfoTypeConfig = {
    displayName: displayName,
    description: description,
    largeCustomDictionary: largeCustomDictionaryConfig,
  };

  // Construct the job creation request to be sent by the client.
  const request = {
    parent: `projects/${projectId}/locations/global`,
    config: storedInfoTypeConfig,
    storedInfoTypeId: infoTypeId,
  };

  // Send the job creation request and process the response.
  const [response] = await dlpClient.createStoredInfoType(request);

  // Print results
  console.log(`InfoType stored successfully: ${response.name}`);
}
await createStoredInfoType();

use Google\Cloud\Dlp\V2\BigQueryField;
use Google\Cloud\Dlp\V2\BigQueryTable;
use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\CloudStoragePath;
use Google\Cloud\Dlp\V2\CreateStoredInfoTypeRequest;
use Google\Cloud\Dlp\V2\FieldId;
use Google\Cloud\Dlp\V2\LargeCustomDictionaryConfig;
use Google\Cloud\Dlp\V2\StoredInfoTypeConfig;

/**
 * Create a stored infoType.
 *
 * @param string $callingProjectId  The Google Cloud Project ID to run the API call under.
 * @param string $outputgcsPath     The path to the location in a Cloud Storage bucket to store the created dictionary.
 * @param string $storedInfoTypeId  The name of the custom stored info type.
 * @param string $displayName       The human-readable name to give the stored infoType.
 * @param string $description       A description for the stored infoType to be created.
 */
function create_stored_infotype(
    string $callingProjectId,
    string $outputgcsPath,
    string $storedInfoTypeId,
    string $displayName,
    string $description
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    // The reference to the table containing the GitHub usernames.
    // The reference to the BigQuery field that contains the GitHub usernames.
    // Note: we have used public data
    $bigQueryField = (new BigQueryField())
        ->setTable((new BigQueryTable())
            ->setDatasetId('samples')
            ->setProjectId('bigquery-public-data')
            ->setTableId('github_nested'))
        ->setField((new FieldId())
            ->setName('actor'));

    $largeCustomDictionaryConfig = (new LargeCustomDictionaryConfig())
        // The output path where the custom dictionary containing the GitHub usernames will be stored.
        ->setOutputPath((new CloudStoragePath())
            ->setPath($outputgcsPath))
        ->setBigQueryField($bigQueryField);

    // Configure the StoredInfoType we want the service to perform.
    $storedInfoTypeConfig = (new StoredInfoTypeConfig())
        ->setDisplayName($displayName)
        ->setDescription($description)
        ->setLargeCustomDictionary($largeCustomDictionaryConfig);

    // Send the stored infoType creation request and process the response.
    $parent = "projects/$callingProjectId/locations/global";
    $createStoredInfoTypeRequest = (new CreateStoredInfoTypeRequest())
        ->setParent($parent)
        ->setConfig($storedInfoTypeConfig)
        ->setStoredInfoTypeId($storedInfoTypeId);
    $response = $dlp->createStoredInfoType($createStoredInfoTypeRequest);

    // Print results.
    printf('Successfully created Stored InfoType : %s', $response->getName());
}

import google.cloud.dlp


def create_stored_infotype(
    project: str,
    stored_info_type_id: str,
    output_bucket_name: str,
) -> None:
    """Uses the Data Loss Prevention API to create stored infoType.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        stored_info_type_id: The identifier for large custom dictionary.
        output_bucket_name: The name of the bucket in Google Cloud Storage
            that would store the created dictionary.
    """

    # Instantiate a client.
    dlp = google.cloud.dlp_v2.DlpServiceClient()

    # Construct the stored infoType Configuration dictionary. This example creates
    # a stored infoType from a term list stored in a publicly available BigQuery
    # database (bigquery-public-data.samples.github_nested).
    # The database contains all GitHub usernames used in commits.
    stored_info_type_config = {
        "display_name": "GitHub usernames",
        "description": "Dictionary of GitHub usernames used in commits",
        "large_custom_dictionary": {
            "output_path": {"path": f"gs://{output_bucket_name}"},
            # We can either use bigquery field or gcs file as a term list input option.
            "big_query_field": {
                "table": {
                    "project_id": "bigquery-public-data",
                    "dataset_id": "samples",
                    "table_id": "github_nested",
                },
                "field": {"name": "actor"},
            },
        },
    }

    # Convert the project id into a full resource id.
    parent = f"projects/{project}/locations/global"

    # Call the API.
    response = dlp.create_stored_info_type(
        request={
            "parent": parent,
            "config": stored_info_type_config,
            "stored_info_type_id": stored_info_type_id,
        }
    )

    # Print the result
    print(f"Created Stored InfoType: {response.name}")

using System;
using Google.Cloud.Dlp.V2;
using