Translate text with glossary in batches (Advanced edition only)

Translate a large volume of text with glossary

Explore further

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

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"
)

// batchTranslateTextWithGlossary translates a large volume of text in asynchronous batch mode.
func batchTranslateTextWithGlossary(w io.Writer, projectID string, location string, inputURI string, outputURI string, sourceLang string, targetLang string, glossaryID string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// inputURI := "gs://cloud-samples-data/text.txt"
	// outputURI := "gs://YOUR_BUCKET_ID/path_to_store_results/"
	// sourceLang := "en"
	// targetLang := "ja"
	// glossaryID := "your-glossary-id"

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

	req := &translatepb.BatchTranslateTextRequest{
		Parent:              fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		SourceLanguageCode:  sourceLang,
		TargetLanguageCodes: []string{targetLang},
		InputConfigs: []*translatepb.InputConfig{
			{
				Source: &translatepb.InputConfig_GcsSource{
					GcsSource: &translatepb.GcsSource{InputUri: inputURI},
				},
				// Optional. Can be "text/plain" or "text/html".
				MimeType: "text/plain",
			},
		},
		Glossaries: map[string]*translatepb.TranslateTextGlossaryConfig{
			targetLang: {
				Glossary: fmt.Sprintf("projects/%s/locations/%s/glossaries/%s", projectID, location, glossaryID),
			},
		},
		OutputConfig: &translatepb.OutputConfig{
			Destination: &translatepb.OutputConfig_GcsDestination{
				GcsDestination: &translatepb.GcsDestination{
					OutputUriPrefix: outputURI,
				},
			},
		},
	}

	// The BatchTranslateText operation is async.
	op, err := client.BatchTranslateText(ctx, req)
	if err != nil {
		return fmt.Errorf("BatchTranslateText: %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, "Total characters: %v\n", resp.GetTotalCharacters())
	fmt.Fprintf(w, "Translated characters: %v\n", resp.GetTranslatedCharacters())

	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.BatchTranslateMetadata;
import com.google.cloud.translate.v3.BatchTranslateResponse;
import com.google.cloud.translate.v3.BatchTranslateTextRequest;
import com.google.cloud.translate.v3.GcsDestination;
import com.google.cloud.translate.v3.GcsSource;
import com.google.cloud.translate.v3.GlossaryName;
import com.google.cloud.translate.v3.InputConfig;
import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.OutputConfig;
import com.google.cloud.translate.v3.TranslateTextGlossaryConfig;
import com.google.cloud.translate.v3.TranslationServiceClient;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.ThreadLocalRandom;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class BatchTranslateTextWithGlossary {

  public static void batchTranslateTextWithGlossary()
      throws InterruptedException, ExecutionException, IOException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR-PROJECT-ID";
    // Supported Languages: https://cloud.google.com/translate/docs/languages
    String sourceLanguage = "your-source-language";
    String targetLanguage = "your-target-language";
    String inputUri = "gs://your-gcs-bucket/path/to/input/file.txt";
    String outputUri = "gs://your-gcs-bucket/path/to/results/";
    String glossaryId = "your-glossary-display-name";
    batchTranslateTextWithGlossary(
        projectId, sourceLanguage, targetLanguage, inputUri, outputUri, glossaryId);
  }

  // Batch Translate Text with a Glossary.
  public static void batchTranslateTextWithGlossary(
      String projectId,
      String sourceLanguage,
      String targetLanguage,
      String inputUri,
      String outputUri,
      String glossaryId)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {

    // 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);

      // Configure the source of the file from a GCS bucket
      GcsSource gcsSource = GcsSource.newBuilder().setInputUri(inputUri).build();
      // Supported Mime Types: https://cloud.google.com/translate/docs/supported-formats
      InputConfig inputConfig =
          InputConfig.newBuilder().setGcsSource(gcsSource).setMimeType("text/plain").build();

      // Configure where to store the output in a GCS bucket
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(outputUri).build();
      OutputConfig outputConfig =
          OutputConfig.newBuilder().setGcsDestination(gcsDestination).build();

      // Configure the glossary used in the request
      GlossaryName glossaryName = GlossaryName.of(projectId, location, glossaryId);
      TranslateTextGlossaryConfig glossaryConfig =
          TranslateTextGlossaryConfig.newBuilder().setGlossary(glossaryName.toString()).build();

      // Build the request that will be sent to the API
      BatchTranslateTextRequest request =
          BatchTranslateTextRequest.newBuilder()
              .setParent(parent.toString())
              .setSourceLanguageCode(sourceLanguage)
              .addTargetLanguageCodes(targetLanguage)
              .addInputConfigs(inputConfig)
              .setOutputConfig(outputConfig)
              .putGlossaries(targetLanguage, glossaryConfig)
              .build();

      // Start an asynchronous request
      OperationFuture<BatchTranslateResponse, BatchTranslateMetadata> future =
          client.batchTranslateTextAsync(request);

      System.out.println("Waiting for operation to complete...");

      // random number between 300 - 450 (maximum allowed seconds)
      long randomNumber = ThreadLocalRandom.current().nextInt(450, 600);
      BatchTranslateResponse response = future.get(randomNumber, TimeUnit.SECONDS);

      // Display the translation for each input text provided
      System.out.printf("Total Characters: %s\n", response.getTotalCharacters());
      System.out.printf("Translated Characters: %s\n", response.getTranslatedCharacters());
    }
  }
}

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 = 'us-central1';
// const inputUri = 'gs://cloud-samples-data/text.txt';
// const outputUri = 'gs://YOUR_BUCKET_ID/path_to_store_results/';
// const glossaryId = 'YOUR_GLOSSARY_ID';

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

// Instantiates a client
const client = new TranslationServiceClient();
async function batchTranslateTextWithGlossary() {
  // Construct request
  const request = {
    parent: `projects/${projectId}/locations/${location}`,
    sourceLanguageCode: 'en',
    targetLanguageCodes: ['es'],
    inputConfigs: [
      {
        mimeType: 'text/plain', // mime types: text/plain, text/html
        gcsSource: {
          inputUri: inputUri,
        },
      },
    ],
    outputConfig: {
      gcsDestination: {
        outputUriPrefix: outputUri,
      },
    },
    glossaries: {
      es: {
        glossary: `projects/${projectId}/locations/${location}/glossaries/${glossaryId}`,
      },
    },
  };

  const options = {timeout: 240000};
  // Create a job using a long-running operation
  const [operation] = await client.batchTranslateText(request, options);

  // Wait for the operation to complete
  const [response] = await operation.promise();

  // Display the translation for each input text provided
  console.log(`Total Characters: ${response.totalCharacters}`);
  console.log(`Translated Characters: ${response.translatedCharacters}`);
}

batchTranslateTextWithGlossary();

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\BatchTranslateTextRequest;
use Google\Cloud\Translate\V3\Client\TranslationServiceClient;
use Google\Cloud\Translate\V3\GcsDestination;
use Google\Cloud\Translate\V3\GcsSource;
use Google\Cloud\Translate\V3\InputConfig;
use Google\Cloud\Translate\V3\OutputConfig;
use Google\Cloud\Translate\V3\TranslateTextGlossaryConfig;

/**
 * @param string $inputUri      Path to to source input (e.g. "gs://cloud-samples-data/text.txt").
 * @param string $outputUri     Path to store results (e.g. "gs://YOUR_BUCKET_ID/results/").
 * @param string $projectId     Your Google Cloud project ID.
 * @param string $location      Project location (e.g. us-central1)
 * @param string $glossaryId    Your glossary ID.
 * @param string $targetLanguage    Language to translate to.
 * @param string $sourceLanguage    Language of the source.
 */
function v3_batch_translate_text_with_glossary(
    string $inputUri,
    string $outputUri,
    string $projectId,
    string $location,
    string $glossaryId,
    string $targetLanguage,
    string $sourceLanguage
): void {
    $translationServiceClient = new TranslationServiceClient();

    $glossaryPath = $translationServiceClient->glossaryName(
        $projectId,
        $location,
        $glossaryId
    );
    $targetLanguageCodes = [$targetLanguage];
    $gcsSource = (new GcsSource())
        ->setInputUri($inputUri);

    // Optional. Can be "text/plain" or "text/html".
    $mimeType = 'text/plain';
    $inputConfigsElement = (new InputConfig())
        ->setGcsSource($gcsSource)
        ->setMimeType($mimeType);
    $inputConfigs = [$inputConfigsElement];
    $gcsDestination = (new GcsDestination())
        ->setOutputUriPrefix($outputUri);
    $outputConfig = (new OutputConfig())
        ->setGcsDestination($gcsDestination);
    $formattedParent = $translationServiceClient->locationName(
        $projectId,
        $location
    );
    $glossariesItem = (new TranslateTextGlossaryConfig())
        ->setGlossary($glossaryPath);
    $glossaries = ['ja' => $glossariesItem];

    try {
        $request = (new BatchTranslateTextRequest())
            ->setParent($formattedParent)
            ->setSourceLanguageCode($sourceLanguage)
            ->setTargetLanguageCodes($targetLanguageCodes)
            ->setInputConfigs($inputConfigs)
            ->setOutputConfig($outputConfig)
            ->setGlossaries($glossaries);
        $operationResponse = $translationServiceClient->batchTranslateText($request);
        $operationResponse->pollUntilComplete();
        if ($operationResponse->operationSucceeded()) {
            $response = $operationResponse->getResult();
            // Display the translation for each input text provided
            printf('Total Characters: %s' . PHP_EOL, $response->getTotalCharacters());
            printf('Translated Characters: %s' . PHP_EOL, $response->getTranslatedCharacters());
        } else {
            $error = $operationResponse->getError();
            print($error->getMessage());
        }
    } 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


def batch_translate_text_with_glossary(
    input_uri: str = "gs://YOUR_BUCKET_ID/path/to/your/file.txt",
    output_uri: str = "gs://YOUR_BUCKET_ID/path/to/save/results/",
    project_id: str = "YOUR_PROJECT_ID",
    glossary_id: str = "YOUR_GLOSSARY_ID",
    timeout: int = 320,
) -> translate.TranslateTextResponse:
    """Translates a batch of texts on GCS and stores the result in a GCS location.
    Glossary is applied for translation.

    Args:
        input_uri (str): The input file to translate.
        output_uri (str): The output file to save the translations to.
        project_id (str): The ID of the GCP project that owns the location.
        glossary_id (str): The ID of the glossary to use.
        timeout (int): The amount of time, in seconds, to wait for the operation to complete.

    Returns:
        The response from the batch.
    """

    client = translate.TranslationServiceClient()

    # Supported language codes: https://cloud.google.com/translate/docs/languages
    location = "us-central1"

    # Supported file types: https://cloud.google.com/translate/docs/supported-formats
    gcs_source = {"input_uri": input_uri}

    input_configs_element = {
        "gcs_source": gcs_source,
        "mime_type": "text/plain",  # Can be "text/plain" or "text/html".
    }
    gcs_destination = {"output_uri_prefix": output_uri}
    output_config = {"gcs_destination": gcs_destination}

    parent = f"projects/{project_id}/locations/{location}"

    # glossary is a custom dictionary Translation API uses
    # to translate the domain-specific terminology.
    glossary_path = client.glossary_path(
        project_id, "us-central1", glossary_id  # The location of the glossary
    )

    glossary_config = translate.TranslateTextGlossaryConfig(glossary=glossary_path)

    glossaries = {"ja": glossary_config}  # target lang as key

    operation = client.batch_translate_text(
        request={
            "parent": parent,
            "source_language_code": "en",
            "target_language_codes": ["ja"],  # Up to 10 language codes here.
            "input_configs": [input_configs_element],
            "glossaries": glossaries,
            "output_config": output_config,
        }
    )

    print("Waiting for operation to complete...")
    response = operation.result(timeout)

    print(f"Total Characters: {response.total_characters}")
    print(f"Translated Characters: {response.translated_characters}")

    return response

What's next

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