Create a glossary (Advanced edition only)

Create a glossary.

Explore further

For detailed documentation that includes this code sample, see the following:

• Creating and using glossaries (Advanced)

Code sample

Go

Before trying this sample, follow the Go setup instructions in the Cloud Translation quickstart using client libraries. For more information, see the Cloud Translation Go API reference documentation.

To authenticate to Cloud Translation, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import (
	"context"
	"fmt"
	"io"

	translate "cloud.google.com/go/translate/apiv3"
	"cloud.google.com/go/translate/apiv3/translatepb"
)

// createGlossary creates a glossary to use for other operations.
func createGlossary(w io.Writer, projectID string, location string, glossaryID string, glossaryInputURI string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// glossaryID := "my-glossary-display-name"
	// glossaryInputURI := "gs://cloud-samples-data/translation/glossary.csv"

	ctx := context.Background()
	client, err := translate.NewTranslationClient(ctx)
	if err != nil {
		return fmt.Errorf("NewTranslationClient: %w", err)
	}
	defer client.Close()

	req := &translatepb.CreateGlossaryRequest{
		Parent: fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		Glossary: &translatepb.Glossary{
			Name: fmt.Sprintf("projects/%s/locations/%s/glossaries/%s", projectID, location, glossaryID),
			Languages: &translatepb.Glossary_LanguageCodesSet_{
				LanguageCodesSet: &translatepb.Glossary_LanguageCodesSet{
					LanguageCodes: []string{"en", "ja"},
				},
			},
			InputConfig: &translatepb.GlossaryInputConfig{
				Source: &translatepb.GlossaryInputConfig_GcsSource{
					GcsSource: &translatepb.GcsSource{
						InputUri: glossaryInputURI,
					},
				},
			},
		},
	}

	// The CreateGlossary operation is async.
	op, err := client.CreateGlossary(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateGlossary: %w", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %w", err)
	}

	fmt.Fprintf(w, "Created: %v\n", resp.GetName())
	fmt.Fprintf(w, "Input URI: %v\n", resp.InputConfig.GetGcsSource().GetInputUri())

	return nil
}

Java

Before trying this sample, follow the Java setup instructions in the Cloud Translation quickstart using client libraries. For more information, see the Cloud Translation Java API reference documentation.

To authenticate to Cloud Translation, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.translate.v3.CreateGlossaryMetadata;
import com.google.cloud.translate.v3.CreateGlossaryRequest;
import com.google.cloud.translate.v3.GcsSource;
import com.google.cloud.translate.v3.Glossary;
import com.google.cloud.translate.v3.GlossaryInputConfig;
import com.google.cloud.translate.v3.GlossaryName;
import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.TranslationServiceClient;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.ExecutionException;

public class CreateGlossary {

  public static void createGlossary() throws InterruptedException, ExecutionException, IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR-PROJECT-ID";
    String glossaryId = "your-glossary-display-name";
    List<String> languageCodes = new ArrayList<>();
    languageCodes.add("your-language-code");
    String inputUri = "gs://your-gcs-bucket/path/to/input/file.txt";
    createGlossary(projectId, glossaryId, languageCodes, inputUri);
  }

  // Create a equivalent term sets glossary
  // https://cloud.google.com/translate/docs/advanced/glossary#format-glossary
  public static void createGlossary(
      String projectId, String glossaryId, List<String> languageCodes, String inputUri)
      throws IOException, ExecutionException, InterruptedException {

    // 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 (TranslationServiceClient client = TranslationServiceClient.create()) {
      // Supported Locations: `global`, [glossary location], or [model location]
      // Glossaries must be hosted in `us-central1`
      // Custom Models must use the same location as your model. (us-central1)
      String location = "us-central1";
      LocationName parent = LocationName.of(projectId, location);
      GlossaryName glossaryName = GlossaryName.of(projectId, location, glossaryId);

      // Supported Languages: https://cloud.google.com/translate/docs/languages
      Glossary.LanguageCodesSet languageCodesSet =
          Glossary.LanguageCodesSet.newBuilder().addAllLanguageCodes(languageCodes).build();

      // Configure the source of the file from a GCS bucket
      GcsSource gcsSource = GcsSource.newBuilder().setInputUri(inputUri).build();
      GlossaryInputConfig inputConfig =
          GlossaryInputConfig.newBuilder().setGcsSource(gcsSource).build();

      Glossary glossary =
          Glossary.newBuilder()
              .setName(glossaryName.toString())
              .setLanguageCodesSet(languageCodesSet)
              .setInputConfig(inputConfig)
              .build();

      CreateGlossaryRequest request =
          CreateGlossaryRequest.newBuilder()
              .setParent(parent.toString())
              .setGlossary(glossary)
              .build();

      // Start an asynchronous request
      OperationFuture<Glossary, CreateGlossaryMetadata> future =
          client.createGlossaryAsync(request);

      System.out.println("Waiting for operation to complete...");
      Glossary response = future.get();
      System.out.println("Created Glossary.");
      System.out.printf("Glossary name: %s\n", response.getName());
      System.out.printf("Entry count: %s\n", response.getEntryCount());
      System.out.printf("Input URI: %s\n", response.getInputConfig().getGcsSource().getInputUri());
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Cloud Translation quickstart using client libraries. For more information, see the Cloud Translation Node.js API reference documentation.

To authenticate to Cloud Translation, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'global';
// const glossaryId = 'your-glossary-display-name';

// Imports the Google Cloud Translation library
const {TranslationServiceClient} = require('@google-cloud/translate');

// Instantiates a client
const translationClient = new TranslationServiceClient();

async function createGlossary() {
  // Construct glossary
  const glossary = {
    languageCodesSet: {
      languageCodes: ['en', 'es'],
    },
    inputConfig: {
      gcsSource: {
        inputUri: 'gs://cloud-samples-data/translation/glossary.csv',
      },
    },
    name: `projects/${projectId}/locations/${location}/glossaries/${glossaryId}`,
  };

  // Construct request
  const request = {
    parent: `projects/${projectId}/locations/${location}`,
    glossary: glossary,
  };

  // Create glossary using a long-running operation
  const [operation] = await translationClient.createGlossary(request);

  // Wait for the operation to complete
  await operation.promise();

  console.log('Created glossary:');
  console.log(`InputUri ${request.glossary.inputConfig.gcsSource.inputUri}`);
}

createGlossary();

PHP

Before trying this sample, follow the PHP setup instructions in the Cloud Translation quickstart using client libraries. For more information, see the Cloud Translation PHP API reference documentation.

To authenticate to Cloud Translation, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

use Google\Cloud\Translate\V3\Client\TranslationServiceClient;
use Google\Cloud\Translate\V3\CreateGlossaryRequest;
use Google\Cloud\Translate\V3\GcsSource;
use Google\Cloud\Translate\V3\Glossary;
use Google\Cloud\Translate\V3\Glossary\LanguageCodesSet;
use Google\Cloud\Translate\V3\GlossaryInputConfig;

/**
 * @param string $projectId     Your Google Cloud project ID.
 * @param string $glossaryId    Your glossary ID.
 * @param string $inputUri      Path to to source input (e.g. "gs://cloud-samples-data/translation/glossary.csv").
 */
function v3_create_glossary(
    string $projectId,
    string $glossaryId,
    string $inputUri
): void {
    $translationServiceClient = new TranslationServiceClient();

    $formattedParent = $translationServiceClient->locationName(
        $projectId,
        'us-central1'
    );
    $formattedName = $translationServiceClient->glossaryName(
        $projectId,
        'us-central1',
        $glossaryId
    );
    $languageCodesElement = 'en';
    $languageCodesElement2 = 'ja';
    $languageCodes = [$languageCodesElement, $languageCodesElement2];
    $languageCodesSet = new LanguageCodesSet();
    $languageCodesSet->setLanguageCodes($languageCodes);
    $gcsSource = (new GcsSource())
        ->setInputUri($inputUri);
    $inputConfig = (new GlossaryInputConfig())
        ->setGcsSource($gcsSource);
    $glossary = (new Glossary())
        ->setName($formattedName)
        ->setLanguageCodesSet($languageCodesSet)
        ->setInputConfig($inputConfig);

    try {
        $request = (new CreateGlossaryRequest())
            ->setParent($formattedParent)
            ->setGlossary($glossary);
        $operationResponse = $translationServiceClient->createGlossary($request);
        $operationResponse->pollUntilComplete();
        if ($operationResponse->operationSucceeded()) {
            $response = $operationResponse->getResult();
            printf('Created Glossary.' . PHP_EOL);
            printf('Glossary name: %s' . PHP_EOL, $response->getName());
            printf('Entry count: %s' . PHP_EOL, $response->getEntryCount());
            printf(
                'Input URI: %s' . PHP_EOL,
                $response->getInputConfig()
                    ->getGcsSource()
                    ->getInputUri()
            );
        } else {
            $error = $operationResponse->getError();
            // handleError($error)
        }
    } finally {
        $translationServiceClient->close();
    }
}

Python

Before trying this sample, follow the Python setup instructions in the Cloud Translation quickstart using client libraries. For more information, see the Cloud Translation Python API reference documentation.

To authenticate to Cloud Translation, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

from google.cloud import translate_v3 as translate


def create_glossary(
    project_id: str = "YOUR_PROJECT_ID",
    input_uri: str = "YOUR_INPUT_URI",
    glossary_id: str = "YOUR_GLOSSARY_ID",
    timeout: int = 180,
) -> translate.Glossary:
    """
    Create a equivalent term sets glossary. Glossary can be words or
    short phrases (usually fewer than five words).
    https://cloud.google.com/translate/docs/advanced/glossary#format-glossary
    """
    client = translate.TranslationServiceClient()

    # Supported language codes: https://cloud.google.com/translate/docs/languages
    source_lang_code = "en"
    target_lang_code = "ja"
    location = "us-central1"  # The location of the glossary

    name = client.glossary_path(project_id, location, glossary_id)
    language_codes_set = translate.types.Glossary.LanguageCodesSet(
        language_codes=[source_lang_code, target_lang_code]
    )

    gcs_source = translate.types.GcsSource(input_uri=input_uri)

    input_config = translate.types.GlossaryInputConfig(gcs_source=gcs_source)

    glossary = translate.types.Glossary(
        name=name, language_codes_set=language_codes_set, input_config=input_config
    )

    parent = f"projects/{project_id}/locations/{location}"
    # glossary is a custom dictionary Translation API uses
    # to translate the domain-specific terminology.
    operation = client.create_glossary(parent=parent, glossary=glossary)

    result = operation.result(timeout)
    print(f"Created: {result.name}")
    print(f"Input Uri: {result.input_config.gcs_source.input_uri}")

    return result

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.