Solicitações em lote (avançado)

Com a tradução em lote, é possível traduzir grandes quantidades de texto (com um limite de 1.000 arquivos por lote) e até 10 idiomas de chegada diferentes em um comando off-line. O tamanho total do conteúdo precisa ter no máximo 100 milhões pontos de código Unicode e precisa usar a codificação UTF-8.

Antes de começar

Antes de começar a usar a API Cloud Translation, é preciso ter um projeto em que ela esteja ativada e as credenciais apropriadas. Você também pode instalar bibliotecas de cliente para linguagens de programação comuns para ajudá-lo a fazer chamadas para a API.

Para ver mais informações, consulte a página Configuração.

Permissões

Para traduções em lote, você precisa ter acesso aos buckets do Cloud Storage e também as permissões do Cloud Translation. Os arquivos de entrada de tradução em lote são lidos em um bucket do Cloud Storage, enquanto os de saída são gravados nesses buckets. Por exemplo, para ler arquivos de entrada de um bucket, é preciso ter no mínimo permissões de leitura de objetos, fornecidas pelo papel roles/storage.objectViewer, no bucket. Para mais informações sobre esses papéis, consulte a documentação do Cloud Storage

Arquivo de entrada

Apenas dois tipos MIME são compatíveis: text/html (HTML) e text/plain (.tsv e .txt).

Como usar um arquivo TSV

Se uma extensão de arquivo for .tsv, ela poderá conter uma ou duas colunas. A primeira coluna (opcional) é o ID da solicitação de texto. Se a primeira coluna estiver ausente, o Google usará o número da linha (com base em 0) do arquivo de entrada como o ID no arquivo de saída. A segunda coluna é o texto real a ser traduzido. Para melhores resultados, cada linha precisa ser menor ou igual a 10.000 pontos de código Unicode, caso contrário, um erro pode ser retornado.

Como usar texto ou HTML

As outras extensões de arquivo compatíveis são arquivos de texto (.txt) ou HTML, que são tratados como uma parte de texto grande e única.

Solicitação em lote

Com uma solicitação de tradução em lote, você fornece o caminho tanto para um arquivo de configuração de entrada (InputConfig) com o conteúdo a ser traduzido quanto para um local de saída (OutputConfig) para a tradução final. Você precisa de pelo menos dois intervalos diferentes do Cloud Storage. O intervalo de origem tem o conteúdo a ser traduzido e o de destino contém os arquivos traduzidos resultantes. O bucket de destino precisa estar vazio antes do início do processo de tradução.

Conforme a solicitação é processada, gravamos os resultados no local de saída em tempo real. Mesmo se você cancelar a solicitação na metade, a saída parcial no nível do arquivo de entrada ainda será produzida no local do Cloud Storage de saída. Por isso, o número de caracteres traduzidos ainda é cobrado.

REST e LINHA DE CMD

Neste exemplo, mostramos dois arquivos de entrada enviados para tradução.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-number-or-id: pelo número ou o código do seu projeto do Google Cloud

Método HTTP e URL:

POST https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

Corpo JSON da solicitação:

{
  "sourceLanguageCode": "en",
  "targetLanguageCodes": ["es", "fr"],
  "inputConfigs": [
   {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name1"
      }
    },
    {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name2"
      }
    }
  ],
  "outputConfig": {
      "gcsDestination": {
        "outputUriPrefix": "gs://bucket-name-destination/"
      }
   }
}

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

PowerShell

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText " | Select-Object -Expand Content

Você receberá uma resposta JSON semelhante a esta:

{
  "name": "projects/project-number/locations/us-central1/operations/20191107-08251564068323-5d3895ce-0000-2067-864c-001a1136fb06",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.translation.v3.BatchTranslateMetadata",
    "state": "RUNNING"
  }
}
A resposta contém o ID para uma operação de longa duração.

C#

Antes de testar esta amostra, siga as instruções de configuração para C# no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para C#.


using System;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Translate.V3;

namespace GoogleCloudSamples
{
    public static class BatchTranslateText
    {
        /// <summary>
        /// Translates a batch of texts on GCS and stores the result in a GCS location.
        /// </summary>
        /// <param name="projectId">Your Google Cloud Project ID.</param>
        /// <param name="location">Region.</param>
        /// <param name="inputUri">The GCS path where input configuration is stored.</param>
        /// <param name="outputUri">The GCS path for translation output.</param>
        /// <param name="sourceLanguage">Source language code.</param>
        /// <param name="targetLanguage">Target language code.</param>
        public static void BatchTranslateTextSample(string inputUri = "gs://cloud-samples-data/text.txt",
            string outputUri = "gs://YOUR_BUCKET_ID/path_to_store_results/",
            string projectId = "[Google Cloud Project ID]",
            string location = "us-central1",
            string sourceLanguage = "en",
            string targetLanguage = "ja")
        {
            TranslationServiceClient translationServiceClient = TranslationServiceClient.Create();
            BatchTranslateTextRequest request = new BatchTranslateTextRequest
            {
                ParentAsLocationName = new LocationName(projectId, location),
                SourceLanguageCode = sourceLanguage,
                TargetLanguageCodes =
                {
                    targetLanguage,
                },
                InputConfigs =
                {
                    new InputConfig
                    {
                        GcsSource = new GcsSource
                        {
                            InputUri = inputUri,
                        },
                        MimeType = "text/plain",
                    },
                },
                OutputConfig = new OutputConfig
                {
                    GcsDestination = new GcsDestination
                    {
                        OutputUriPrefix = outputUri,
                    },
                },
            };
            // Poll until the returned long-running operation is completed.
            BatchTranslateResponse response = translationServiceClient.BatchTranslateText(request).PollUntilCompleted().Result;
            Console.WriteLine($"Total Characters: {response.TotalCharacters}");
            Console.WriteLine($"Translated Characters: {response.TranslatedCharacters}");
        }
    }

Go

Antes de testar esta amostra, siga as instruções de configuração para Go no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Go.

import (
	"context"
	"fmt"
	"io"

	translate "cloud.google.com/go/translate/apiv3"
	translatepb "google.golang.org/genproto/googleapis/cloud/translate/v3"
)

// batchTranslateText translates a large volume of text in asynchronous batch mode.
func batchTranslateText(w io.Writer, projectID string, location string, inputURI string, outputURI string, sourceLang string, targetLang 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"

	ctx := context.Background()
	client, err := translate.NewTranslationClient(ctx)
	if err != nil {
		return fmt.Errorf("NewTranslationClient: %v", 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",
			},
		},
		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: %v", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

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

	fmt.Fprintf(w, "Total characters: %v\n", resp.GetTotalCharacters())
	fmt.Fprintf(w, "Translated characters: %v\n", resp.GetTranslatedCharacters())

	return nil
}

Java

Antes de testar esta amostra, siga as instruções de configuração para Java no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Java.

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.InputConfig;
import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.OutputConfig;
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 BatchTranslateText {

  public static void batchTranslateText()
      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/";
    batchTranslateText(projectId, sourceLanguage, targetLanguage, inputUri, outputUri);
  }

  // Batch translate text
  public static void batchTranslateText(
      String projectId,
      String sourceLanguage,
      String targetLanguage,
      String inputUri,
      String outputUri)
      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: `us-central1`
      LocationName parent = LocationName.of(projectId, "us-central1");

      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();

      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(outputUri).build();
      OutputConfig outputConfig =
          OutputConfig.newBuilder().setGcsDestination(gcsDestination).build();

      BatchTranslateTextRequest request =
          BatchTranslateTextRequest.newBuilder()
              .setParent(parent.toString())
              .setSourceLanguageCode(sourceLanguage)
              .addTargetLanguageCodes(targetLanguage)
              .addInputConfigs(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      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(300, 450);
      BatchTranslateResponse response = future.get(randomNumber, TimeUnit.SECONDS);

      System.out.printf("Total Characters: %s\n", response.getTotalCharacters());
      System.out.printf("Translated Characters: %s\n", response.getTranslatedCharacters());
    }
  }
}

Node.js

Antes de testar esta amostra, siga as instruções de configuração para Node.js no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Node.js.

/**
 * 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/';

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

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

  try {
    // Batch translate text using a long-running operation
    const [operation] = await translationClient.batchTranslateText(request);

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

    console.log(`Total Characters: ${response.totalCharacters}`);
    console.log(`Translated Characters: ${response.translatedCharacters}`);
  } catch (error) {
    console.error(error.details);
  }
}

batchTranslateText();

PHP

Antes de testar esta amostra, siga as instruções de configuração para PHP no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para PHP.

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\TranslationServiceClient;

$translationServiceClient = new TranslationServiceClient();

/** Uncomment and populate these variables in your code */
// $inputUri = 'gs://cloud-samples-data/text.txt';
// $outputUri = 'gs://YOUR_BUCKET_ID/path_to_store_results/';
// $projectId = '[Google Cloud Project ID]';
// $location = 'us-central1';
// $sourceLang = 'en';
// $targetLang = 'ja';
$targetLanguageCodes = [$targetLang];
$gcsSource = (new GcsSource())
    ->setInputUri($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);

try {
    $operationResponse = $translationServiceClient->batchTranslateText(
        $formattedParent,
        $sourceLang,
        $targetLanguageCodes,
        $inputConfigs,
        $outputConfig
    );
    $operationResponse->pollUntilComplete();
    if ($operationResponse->operationSucceeded()) {
        $response = $operationResponse->getResult();
        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

Antes de testar esta amostra, siga as instruções de configuração para Python no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Python.

from google.cloud import translate

def batch_translate_text(
    input_uri="gs://YOUR_BUCKET_ID/path/to/your/file.txt",
    output_uri="gs://YOUR_BUCKET_ID/path/to/save/results/",
    project_id="YOUR_PROJECT_ID",
    timeout=180,
):
    """Translates a batch of texts on GCS and stores the result in a GCS location."""

    client = translate.TranslationServiceClient()

    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}"

    # Supported language codes: https://cloud.google.com/translate/docs/language
    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],
            "output_config": output_config,
        }
    )

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

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

Ruby

Antes de testar esta amostra, siga as instruções de configuração para Ruby no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Ruby.

require "google/cloud/translate"

# input_uri = "gs://cloud-samples-data/text.txt"
# output_uri = "gs://YOUR_BUCKET_ID/path_to_store_results/"
# project_id = "[Google Cloud Project ID]"
# location_id = "[LOCATION ID]"

source_lang = "en"
target_lang = "ja"
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"

client = Google::Cloud::Translate.translation_service

parent = client.location_path project: project_id, location: location_id
input_config = {
  mime_type:  mime_type,
  gcs_source: { input_uri: input_uri }
}
output_config = {
  gcs_destination: { output_uri_prefix: output_uri }
}

operation = client.batch_translate_text(
  parent:                parent,
  source_language_code:  source_lang,
  target_language_codes: [target_lang],
  input_configs:         [input_config],
  output_config:         output_config
)

# Wait until the long running operation is done
operation.wait_until_done!

response = operation.response

puts "Total Characters: #{response.total_characters}"
puts "Translated Characters: #{response.translated_characters}"

Como fazer uma solicitação em lote usando um modelo de AutoML

É possível usar um modelo personalizado para solicitações em lote. Há diversas situações que envolvem vários idiomas de chegada.

Como especificar um modelo de AutoML para o idioma de chegada

REST e linha de comando

Este exemplo mostra como especificar um modelo personalizado para o idioma de chegada.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-number-or-id: pelo número ou o código do seu projeto do Google Cloud

Método HTTP e URL:

POST https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

Corpo JSON da solicitação:

{
  "models":{"es":"projects/project-number-or-id/locations/us-central1/models/model-id"},
  "sourceLanguageCode": "en",
  "targetLanguageCodes": ["es"],
  "inputConfigs": [
   {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name1"
      }
    },
    {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name2"
      }
    }
  ],
  "outputConfig": {
      "gcsDestination": {
        "outputUriPrefix": "gs://bucket-name-destination/"
      }
   }
}

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

PowerShell

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText " | Select-Object -Expand Content

Você receberá uma resposta JSON semelhante a esta:

{
  "name": "projects/project-number/locations/us-central1/operations/20190725-08251564068323-5d3895ce-0000-2067-864c-001a1136fb06",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.translation.v3.BatchTranslateMetadata",
    "state": "RUNNING"
  }
}
A resposta contém o ID para uma operação de longa duração.

C#

Antes de testar esta amostra, siga as instruções de configuração para C# no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para C#.


using Google.Api.Gax.ResourceNames;
using Google.Cloud.Translate.V3;
using System;

namespace GoogleCloudSamples
{
    public static class BatchTranslateTextWithModel
    {
        /// <summary>
        /// Batch translate text using Translation model.
        /// Model can be AutoML or General[built-in] model.
        /// </summary>
        /// <param name="targetLanguage">Target language code.</param>
        /// <param name="sourceLanguage">Required. Source language code.</param>
        /// <param name="modelId">A model is used for Translation.
        /// <param name="projectId">Your Google Cloud Project ID.</param>
        /// <param name="inputUri">The GCS path where input configuration is stored.</param>
        /// <param name="outputUri">The GCS path for translation output.</param>
        /// <param name="location"> Region.</param>
        public static void BatchTranslateTextWithModelSample(
            string inputUri = "gs://cloud-samples-data/translation/custom_model_text.txt'",
            string outputUri = "gs://YOUR_BUCKET_ID/path_to_store_results/",
            string projectId = "[Google Cloud Project ID]",
            string location = "us-central1",
            string targetLanguage = "ja",
            string sourceLanguage = "en",
            string modelId = "[YOUR-MODEL-ID]")
        {
            TranslationServiceClient translationServiceClient = TranslationServiceClient.Create();
            string modelPath = $"projects/{projectId}/locations/{location}/models/{modelId}";

            BatchTranslateTextRequest request = new BatchTranslateTextRequest
            {
                ParentAsLocationName = new LocationName(projectId, location),
                SourceLanguageCode = sourceLanguage,
                TargetLanguageCodes =
                {
                    // Target language code.
                    targetLanguage,
                },
                InputConfigs =
                {
                    new InputConfig
                    {
                        GcsSource = new GcsSource
                        {
                            InputUri = inputUri,
                        },
                        MimeType = "text/plain",
                    },
                },
                OutputConfig = new OutputConfig
                {
                    GcsDestination = new GcsDestination
                    {
                        OutputUriPrefix = outputUri,
                    },
                },
                Models =
                {
                    // A model is used for Translation.
                    { targetLanguage,  modelPath},
                },
            };
            // Poll until the returned long-running operation is completed.
            BatchTranslateResponse response = translationServiceClient.BatchTranslateText(request).PollUntilCompleted().Result;
            Console.WriteLine($"Total Characters: {response.TotalCharacters}");
            Console.WriteLine($"Translated Characters: {response.TranslatedCharacters}");
        }
    }

Go

Antes de testar esta amostra, siga as instruções de configuração para Go no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Go.

import (
	"context"
	"fmt"
	"io"

	translate "cloud.google.com/go/translate/apiv3"
	translatepb "google.golang.org/genproto/googleapis/cloud/translate/v3"
)

// batchTranslateTextWithModel translates a large volume of text in asynchronous batch mode.
func batchTranslateTextWithModel(w io.Writer, projectID string, location string, inputURI string, outputURI string, sourceLang string, targetLang string, modelID 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 := "de"
	// modelID := "your-model-id"

	ctx := context.Background()
	client, err := translate.NewTranslationClient(ctx)
	if err != nil {
		return fmt.Errorf("NewTranslationClient: %v", 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",
			},
		},
		OutputConfig: &translatepb.OutputConfig{
			Destination: &translatepb.OutputConfig_GcsDestination{
				GcsDestination: &translatepb.GcsDestination{
					OutputUriPrefix: outputURI,
				},
			},
		},
		Models: map[string]string{
			targetLang: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		},
	}

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

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

	fmt.Fprintf(w, "Total characters: %v\n", resp.GetTotalCharacters())
	fmt.Fprintf(w, "Translated characters: %v\n", resp.GetTranslatedCharacters())

	return nil
}

Java

Antes de testar esta amostra, siga as instruções de configuração para Java no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Java.

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.InputConfig;
import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.OutputConfig;
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 BatchTranslateTextWithModel {

  public static void batchTranslateTextWithModel()
      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 modelId = "YOUR-MODEL-ID";
    batchTranslateTextWithModel(
        projectId, sourceLanguage, targetLanguage, inputUri, outputUri, modelId);
  }

  // Batch translate text using AutoML Translation model
  public static void batchTranslateTextWithModel(
      String projectId,
      String sourceLanguage,
      String targetLanguage,
      String inputUri,
      String outputUri,
      String modelId)
      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 model used in the request
      String modelPath =
          String.format("projects/%s/locations/%s/models/%s", projectId, location, modelId);

      // 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)
              .putModels(targetLanguage, modelPath)
              .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(300, 450);
      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

Antes de testar esta amostra, siga as instruções de configuração para Node.js no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Node.js.

/**
 * 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 modelId = 'YOUR_MODEL_ID';

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

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

  try {
    // Create a job using a long-running operation
    const [operation] = await client.batchTranslateText(request);

    // 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}`);
  } catch (error) {
    console.error(error.details);
  }
}

batchTranslateTextWithModel();

PHP

Antes de testar esta amostra, siga as instruções de configuração para PHP no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para PHP.

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\TranslationServiceClient;

$translationServiceClient = new TranslationServiceClient();

/** Uncomment and populate these variables in your code */
// $inputUri = 'gs://cloud-samples-data/text.txt';
// $outputUri = 'gs://YOUR_BUCKET_ID/path_to_store_results/';
// $projectId = '[Google Cloud Project ID]';
// $location = 'us-central1';
// $targetLanguage = 'en';
// $sourceLanguage = 'de';
// $modelId = '{your-model-id}';
$modelPath = sprintf(
    'projects/%s/locations/%s/models/%s',
    $projectId,
    $location,
    $modelId
);
$targetLanguageCodes = [$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);
$models = ['ja' => $modelPath];

try {
    $operationResponse = $translationServiceClient->batchTranslateText(
        $formattedParent,
        $sourceLanguage,
        $targetLanguageCodes,
        $inputConfigs,
        $outputConfig,
        ['models' => $models]
    );
    $operationResponse->pollUntilComplete();
    if ($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

Antes de testar esta amostra, siga as instruções de configuração para Python no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Python.

from google.cloud import translate

def batch_translate_text_with_model(
    input_uri="gs://YOUR_BUCKET_ID/path/to/your/file.txt",
    output_uri="gs://YOUR_BUCKET_ID/path/to/save/results/",
    project_id="YOUR_PROJECT_ID",
    model_id="YOUR_MODEL_ID",
):
    """Batch translate text using Translation model.
     Model can be AutoML or General[built-in] model. """

    client = translate.TranslationServiceClient()

    # Supported file types: https://cloud.google.com/translate/docs/supported-formats
    gcs_source = {"input_uri": input_uri}
    location = "us-central1"

    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}"

    model_path = "projects/{}/locations/{}/models/{}".format(
        project_id, location, model_id  # The location of AutoML model.
    )

    # Supported language codes: https://cloud.google.com/translate/docs/languages
    models = {"ja": model_path}  # takes a 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],
            "output_config": output_config,
            "models": models,
        }
    )

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

    # Display the translation for each input text provided.
    print("Total Characters: {}".format(response.total_characters))
    print("Translated Characters: {}".format(response.translated_characters))

Ruby

Antes de testar esta amostra, siga as instruções de configuração para Ruby no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Ruby.

require "google/cloud/translate"

# input_uri = "gs://cloud-samples-data/text.txt"
# output_uri = "gs://YOUR_BUCKET_ID/path_to_store_results/"
# project_id = "[Google Cloud Project ID]"
# location_id = "[LOCATION ID]"
# model_id = "[MODEL ID]"

source_lang = "en"
target_lang = "ja"
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"

client = Google::Cloud::Translate.translation_service

parent = client.location_path project: project_id, location: location_id
model = "projects/#{project_id}/locations/#{location_id}/models/#{model_id}"
models = { target_lang => model }
input_config = {
  mime_type:  mime_type,
  gcs_source: { input_uri: input_uri }
}
output_config = {
  gcs_destination: { output_uri_prefix: output_uri }
}

operation = client.batch_translate_text(
  parent:                parent,
  source_language_code:  source_lang,
  target_language_codes: [target_lang],
  input_configs:         [input_config],
  output_config:         output_config,
  models:                models
)

# Wait until the long running operation is done
operation.wait_until_done!

response = operation.response

puts "Total Characters: #{response.total_characters}"
puts "Translated Characters: #{response.translated_characters}"

Como especificar modelos AutoML para vários idiomas de chegada

REST e linha de comando

Com vários idiomas de chegada, é possível especificar um modelo personalizado para cada um deles.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-number-or-id: pelo número ou o código do seu projeto do Google Cloud

Método HTTP e URL:

POST https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

Corpo JSON da solicitação:

{
  "models":{
    "es":"projects/project-number-or-id/locations/us-central1/models/model-id1",
    "fr":"projects/project-number-or-id/locations/us-central1/models/model-id2"},
  "sourceLanguageCode": "en",
  "targetLanguageCodes": ["es", "fr"],
  "inputConfigs": [
   {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name1"
      }
    },
    {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name2"
      }
    }
  ],
  "outputConfig": {
      "gcsDestination": {
        "outputUriPrefix": "gs://bucket-name-destination/"
      }
   }
 }

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

PowerShell

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText " | Select-Object -Expand Content

Você receberá uma resposta JSON semelhante a esta:

{
  "name": "projects/project-number/locations/us-central1/operations/20191105-08251564068323-5d3895ce-0000-2067-864c-001a1136fb06",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.translation.v3.BatchTranslateMetadata",
    "state": "RUNNING"
  }
}
A resposta contém o código para uma operação de longa duração.

Como especificar um modelo de AutoML para um idioma de chegada e não para outros

É possível determinar um modelo personalizado para um idioma de chegada específico sem fazer o mesmo com um modelo para os outros idiomas de chegada. Para usar o código para especificar modelos personalizados para vários idiomas de chegada, basta mudar o campo models e determinar o idioma de chegada para o modelo, es neste exemplo, e deixar fr não especificado:

  • "models": {'es':'projects/project-number-or-id/locations/us-central1/models/model-id'},

em que project-number-or-id é o número ou ID do projeto do Google Cloud, e model-id é o nome dado ao modelo de AutoML.

Como traduzir textos usando um glossário

REST e linha de comando

Este exemplo mostra como especificar um glossário para o idioma de chegada.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-number-or-id: pelo número ou código do seu projeto do Google Cloud
  • glossary-id: pelo código de glossário, por exemplo, "my-en-to-es-glossary"

Método HTTP e URL:

POST https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

Corpo JSON da solicitação:

{
  "sourceLanguageCode": "en",
  "targetLanguageCodes": ["es"],
  "glossaries": {
    "es": {
      "glossary": "projects/project-number-or-id/locations/us-central1/glossaries/glossary-id"
    }
  },
  "inputConfigs": [{
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name1"
      }
    },
    {
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name2"
      }
    }
  ],
  "outputConfig": {
    "gcsDestination": {
      "outputUriPrefix": "gs://bucket-name-destination/"
    }
  }
}

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

PowerShell

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText " | Select-Object -Expand Content

Você receberá uma resposta JSON semelhante a esta:

{
  "name": "projects/project-number/locations/us-central1/operations/operation-id",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.translation.v3.BatchTranslateMetadata",
    "state": "RUNNING"
  }
}

C#

Antes de testar esta amostra, siga as instruções de configuração para C# no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para C#.


using Google.Api.Gax.ResourceNames;
using Google.Cloud.Translate.V3;
using System;

namespace GoogleCloudSamples
{
    public static class BatchTranslateTextWithGlossary
    {
        /// <summary>
        /// Translates a batch of texts on GCS and stores the result in a GCS location.
        /// Glossary is applied for translation.
        /// </summary>
        /// <param name="inputUri">The GCS path where input configuration is stored.</param>
        /// <param name="outputUri">The GCS path for translation output.</param>
        /// <param name="projectId">Your Google Cloud Project ID.</param>
        /// <param name="location">Region.</param>
        /// <param name="glossaryId">Required. Translation Glossary ID.</param>
        /// <param name="targetLanguage">Target language code.</param>
        /// <param name="sourceLanguage">Source language code.</param>
        public static void BatchTranslateTextWithGlossarySample(
            string inputUri = "gs://cloud-samples-data/text.txt",
            string outputUri = "gs://YOUR_BUCKET_ID/path_to_store_results/",
            string projectId = "[Google Cloud Project ID]",
            string location = "us-central1",
            string glossaryId = "[YOUR_GLOSSARY_ID]",
            string targetLanguage = "en",
            string sourceLanguage = "ja")
        {
            TranslationServiceClient translationServiceClient = TranslationServiceClient.Create();

            string glossaryPath = $"projects/{projectId}/locations/{location}/glossaries/{glossaryId}";
            BatchTranslateTextRequest request = new BatchTranslateTextRequest
            {
                ParentAsLocationName = new LocationName(projectId, location),
                SourceLanguageCode = sourceLanguage,
                TargetLanguageCodes =
                {
                    // Target language code.
                    targetLanguage,
                },
                InputConfigs =
                {
                    new InputConfig
                    {
                        GcsSource = new GcsSource
                        {
                            InputUri = inputUri,
                        },
                        MimeType = "text/plain",
                    },
                },
                OutputConfig = new OutputConfig
                {
                    GcsDestination = new GcsDestination
                    {
                        OutputUriPrefix = outputUri,
                    },
                },
                Glossaries =
                {
                    {
                        targetLanguage, new TranslateTextGlossaryConfig
                        {
                            Glossary = glossaryPath,
                        }
                    },
                },
            };
            // Poll until the returned long-running operation is completed.
            BatchTranslateResponse response = translationServiceClient.BatchTranslateText(request).PollUntilCompleted().Result;
            Console.WriteLine($"Total Characters: {response.TotalCharacters}");
            Console.WriteLine($"Translated Characters: {response.TranslatedCharacters}");
        }
    }

Go

Antes de testar esta amostra, siga as instruções de configuração para Go no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Go.

import (
	"context"
	"fmt"
	"io"

	translate "cloud.google.com/go/translate/apiv3"
	translatepb "google.golang.org/genproto/googleapis/cloud/translate/v3"
)

// 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: %v", 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: %v", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

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

	fmt.Fprintf(w, "Total characters: %v\n", resp.GetTotalCharacters())
	fmt.Fprintf(w, "Translated characters: %v\n", resp.GetTranslatedCharacters())

	return nil
}

Java

Antes de testar esta amostra, siga as instruções de configuração para Java no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Java.

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(300, 450);
      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

Antes de testar esta amostra, siga as instruções de configuração para Node.js no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Node.js.

/**
 * 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}`,
      },
    },
  };

  try {
    // Create a job using a long-running operation
    const [operation] = await client.batchTranslateText(request);

    // 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}`);
  } catch (error) {
    console.error(error.details);
  }
}

batchTranslateTextWithGlossary();

PHP

Antes de testar esta amostra, siga as instruções de configuração para PHP no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para PHP.

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;
use Google\Cloud\Translate\V3\TranslationServiceClient;

$translationServiceClient = new TranslationServiceClient();

/** Uncomment and populate these variables in your code */
// $inputUri = 'gs://cloud-samples-data/text.txt';
// $outputUri = 'gs://YOUR_BUCKET_ID/path_to_store_results/';
// $projectId = '[Google Cloud Project ID]';
// $location = 'us-central1';
// $glossaryId = '[YOUR_GLOSSARY_ID]';
// $targetLanguage = 'en';
// $sourceLanguage = 'de';
$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 {
    $operationResponse = $translationServiceClient->batchTranslateText(
        $formattedParent,
        $sourceLanguage,
        $targetLanguageCodes,
        $inputConfigs,
        $outputConfig,
        ['glossaries' => $glossaries]
    );
    $operationResponse->pollUntilComplete();
    if ($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

Antes de testar esta amostra, siga as instruções de configuração para Python no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Python.

from google.cloud import translate

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

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

Ruby

Antes de testar esta amostra, siga as instruções de configuração para Ruby no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Ruby.

require "google/cloud/translate"

# input_uri = "gs://cloud-samples-data/text.txt"
# output_uri = "gs://YOUR_BUCKET_ID/path_to_store_results/"
# project_id = "[Google Cloud Project ID]"
# location_id = "[LOCATION ID]"
# glossary_id = "[YOUR_GLOSSARY_ID]"

source_lang = "en"
target_lang = "ja"
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"

client = Google::Cloud::Translate.translation_service

parent = client.location_path project: project_id, location: location_id
glossary_path = client.glossary_path project:  project_id,
                                     location: location_id,
                                     glossary: glossary_id
glossaries = {
  target_lang => { glossary: glossary_path }
}
input_config = {
  mime_type:  mime_type,
  gcs_source: { input_uri: input_uri }
}
output_config = {
  gcs_destination: { output_uri_prefix: output_uri }
}

operation = client.batch_translate_text(
  parent:                parent,
  source_language_code:  source_lang,
  target_language_codes: [target_lang],
  input_configs:         [input_config],
  output_config:         output_config,
  glossaries:            glossaries
)

# Wait until the long running operation is done
operation.wait_until_done!

response = operation.response

puts "Total Characters: #{response.total_characters}"
puts "Translated Characters: #{response.translated_characters}"

Como traduzir textos usando um glossário e um modelo personalizado do AutoML Translation

REST e linha de comando

Este exemplo mostra como especificar um modelo e um glossário personalizados para o idioma de chegada.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-number-or-id: pelo número ou o código do seu projeto do Google Cloud

Método HTTP e URL:

POST https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

Corpo JSON da solicitação:

{
  "models": {
    "es": "projects/project_number_or_id/locations/us-central1/models/model-id"
  },
  "sourceLanguageCode": "en",
  "targetLanguageCodes": ["es"],
  "glossaries": {
    "es": {
      "glossary": "projects/project_number_or_id/locations/us-central1/glossaries/glossary-id"
    }
  },
  "inputConfigs": [{
      "gcsSource": {
        "inputUri": "gs://bucket-name-source/input-file-name"
      }
    },
    {
      "gcsSource": {
      "inputUri": "gs://bucket-name-source/input-file-name2"
      }
    }
  ],
  "outputConfig": {
    "gcsDestination": {
      "outputUriPrefix": "gs://bucket-name-destination/"
    }
  }
}

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText

PowerShell

Salve o corpo da solicitação em um arquivo chamado request.json e execute o comando a seguir:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:batchTranslateText " | Select-Object -Expand Content

Você receberá uma resposta JSON semelhante a esta:

{
  "name": "projects/project-number/locations/us-central1/operations/operation-id",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.translation.v3.BatchTranslateMetadata",
    "state": "RUNNING"
  }
}

C#

Antes de testar esta amostra, siga as instruções de configuração para C# no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para C#.


using Google.Api.Gax.ResourceNames;
using Google.Cloud.Translate.V3;
using System;

namespace GoogleCloudSamples
{
    public static class BatchTranslateTextWithGlossaryAndModel
    {
        /// <summary>
        /// Translates a batch of texts on GCS and stores the result in a GCS location.
        /// Glossary is applied for translation.
        /// A model is used for translation. Can be AutoML or General (built-in) Model.
        /// </summary>
        /// <param name="targetLanguage">Target language code.</param>
        /// <param name="sourceLanguage">Source language code.</param>
        /// <param name="modelId">Translation model ID.</param>
        /// <param name="glossaryId">Translation Glossary ID.</param>
        /// <param name="projectId">Your Google Cloud Project ID.</param>
        /// <param name="location"> Region.</param>
        /// <param name="inputUri">The GCS path where input configuration is stored.</param>
        /// <param name="outputUri">The GCS path for translation output.</param>
        public static void BatchTranslateTextWithGlossaryAndModelSample(
            string inputUri = "gs://cloud-samples-data/translation/text_with_custom_model_and_glossary.txt",
            string outputUri = "gs://YOUR_BUCKET_ID/path_to_store_results/",
            string projectId = "[Google Cloud Project ID]",
            string location = "us-central1",
            string targetLanguage = "ja",
            string sourceLanguage = "en",
            string modelId = "[YOUR-MODEL-ID]",
            string glossaryId = "[YOUR_GLOSSARY_ID]")
        {
            TranslationServiceClient translationServiceClient = TranslationServiceClient.Create();

            string modelPath = $"projects/{projectId}/locations/{location}/models/{modelId}";
            string glossaryPath = $"projects/{projectId}/locations/{location}/glossaries/{glossaryId}";

            BatchTranslateTextRequest request = new BatchTranslateTextRequest
            {
                ParentAsLocationName = new LocationName(projectId, location),
                SourceLanguageCode = sourceLanguage,
                TargetLanguageCodes =
                {
                    // Target language code.
                    targetLanguage,
                },
                InputConfigs =
                {
                    new InputConfig
                    {
                        GcsSource = new GcsSource
                        {
                            InputUri = inputUri,
                        },
                        MimeType = "text/plain",
                    },
                },
                OutputConfig = new OutputConfig
                {
                    GcsDestination = new GcsDestination
                    {
                        OutputUriPrefix = outputUri,
                    },
                },
                Models =
                {
                    // A model is used for Translation.
                    { targetLanguage, modelPath },
                },
                Glossaries =
                {
                    {
                        targetLanguage, new TranslateTextGlossaryConfig
                        {
                            Glossary = glossaryPath,
                        }
                    },
                },
            };
            // Poll until the returned long-running operation is completed.
            BatchTranslateResponse response = translationServiceClient.BatchTranslateText(request).PollUntilCompleted().Result;
            Console.WriteLine($"Total Characters: {response.TotalCharacters}");
            Console.WriteLine($"Translated Characters: {response.TranslatedCharacters}");
        }
    }

Go

Antes de testar esta amostra, siga as instruções de configuração para Go no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Go.

import (
	"context"
	"fmt"
	"io"

	translate "cloud.google.com/go/translate/apiv3"
	translatepb "google.golang.org/genproto/googleapis/cloud/translate/v3"
)

// batchTranslateTextWithGlossaryAndModel translates a large volume of text in asynchronous batch mode.
func batchTranslateTextWithGlossaryAndModel(w io.Writer, projectID string, location string, inputURI string, outputURI string, sourceLang string, targetLang string, glossaryID string, modelID 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"
	// modelID := "your-model-id"

	ctx := context.Background()
	client, err := translate.NewTranslationClient(ctx)
	if err != nil {
		return fmt.Errorf("NewTranslationClient: %v", 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,
				},
			},
		},
		Models: map[string]string{
			targetLang: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		},
	}

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

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

	fmt.Fprintf(w, "Total characters: %v\n", resp.GetTotalCharacters())
	fmt.Fprintf(w, "Translated characters: %v\n", resp.GetTranslatedCharacters())

	return nil
}

Java

Antes de testar esta amostra, siga as instruções de configuração para Java no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Java.

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 BatchTranslateTextWithGlossaryAndModel {

  public static void batchTranslateTextWithGlossaryAndModel()
      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";
    String modelId = "YOUR-MODEL-ID";
    batchTranslateTextWithGlossaryAndModel(
        projectId, sourceLanguage, targetLanguage, inputUri, outputUri, glossaryId, modelId);
  }

  // Batch translate text with Model and Glossary
  public static void batchTranslateTextWithGlossaryAndModel(
      String projectId,
      String sourceLanguage,
      String targetLanguage,
      String inputUri,
      String outputUri,
      String glossaryId,
      String modelId)
      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();

      // Configure the model used in the request
      String modelPath =
          String.format("projects/%s/locations/%s/models/%s", projectId, location, modelId);

      // 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)
              .putModels(targetLanguage, modelPath)
              .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(300, 450);
      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

Antes de testar esta amostra, siga as instruções de configuração para Node.js no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Node.js.

/**
 * 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';
// const modelId = 'YOUR_MODEL_ID';

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

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

  try {
    // Create a job using a long-running operation
    const [operation] = await client.batchTranslateText(request);

    // Wait for 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}`);
  } catch (error) {
    console.error(error.details);
  }
}

batchTranslateTextWithGlossaryAndModel();

PHP

Antes de testar esta amostra, siga as instruções de configuração para PHP no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para PHP.

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;
use Google\Cloud\Translate\V3\TranslationServiceClient;

$translationServiceClient = new TranslationServiceClient();

/** Uncomment and populate these variables in your code */
// $inputUri = 'gs://cloud-samples-data/text.txt';
// $outputUri = 'gs://YOUR_BUCKET_ID/path_to_store_results/';
// $projectId = '[Google Cloud Project ID]';
// $location = 'us-central1';
// $targetLanguage = 'en';
// $sourceLanguage = 'de';
// $modelId = '{your-model-id}';
// $glossaryId = '[YOUR_GLOSSARY_ID]';
$glossaryPath = $translationServiceClient->glossaryName(
    $projectId,
    $location,
    $glossaryId
);
$modelPath = sprintf(
    'projects/%s/locations/%s/models/%s',
    $projectId,
    $location,
    $modelId
);
$targetLanguageCodes = [$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);
$models = ['ja' => $modelPath];
$glossariesItem = (new TranslateTextGlossaryConfig())
    ->setGlossary($glossaryPath);
$glossaries = ['ja' => $glossariesItem];

try {
    $operationResponse = $translationServiceClient->batchTranslateText(
        $formattedParent,
        $sourceLanguage,
        $targetLanguageCodes,
        $inputConfigs,
        $outputConfig,
        [
            'models' => $models,
            'glossaries' => $glossaries
        ]
    );
    $operationResponse->pollUntilComplete();
    if ($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

Antes de testar esta amostra, siga as instruções de configuração para Python no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Python.

from google.cloud import translate

def batch_translate_text_with_glossary_and_model(
    input_uri="gs://YOUR_BUCKET_ID/path/to/your/file.txt",
    output_uri="gs://YOUR_BUCKET_ID/path/to/save/results/",
    project_id="YOUR_PROJECT_ID",
    model_id="YOUR_MODEL_ID",
    glossary_id="YOUR_GLOSSARY_ID",
):
    """
    Batch translate text with Glossary and Translation model
    """

    client = translate.TranslationServiceClient()

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

    target_language_codes = ["ja"]
    gcs_source = {"input_uri": input_uri}

    # Optional. Can be "text/plain" or "text/html".
    mime_type = "text/plain"
    input_configs_element = {"gcs_source": gcs_source, "mime_type": mime_type}
    input_configs = [input_configs_element]
    gcs_destination = {"output_uri_prefix": output_uri}
    output_config = {"gcs_destination": gcs_destination}
    parent = f"projects/{project_id}/locations/{location}"
    model_path = "projects/{}/locations/{}/models/{}".format(
        project_id, "us-central1", model_id
    )
    models = {"ja": model_path}

    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": target_language_codes,
            "input_configs": input_configs,
            "output_config": output_config,
            "models": models,
            "glossaries": glossaries,
        }
    )

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

    # Display the translation for each input text provided
    print("Total Characters: {}".format(response.total_characters))
    print("Translated Characters: {}".format(response.translated_characters))

Ruby

Antes de testar esta amostra, siga as instruções de configuração para Ruby no Guia de início rápido do Translation: como usar bibliotecas de cliente. Saiba mais na documentação de referência da API Translation para Ruby.

require "google/cloud/translate"

# input_uri = "gs://cloud-samples-data/text.txt"
# output_uri = "gs://YOUR_BUCKET_ID/path_to_store_results/"
# project_id = "[Google Cloud Project ID]"
# location_id = "[LOCATION ID]"
# model_id = "[MODEL ID]"
# glossary_id = "[YOUR_GLOSSARY_ID]"

source_lang = "en"
target_lang = "ja"
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"

client = Google::Cloud::Translate.translation_service

parent = client.location_path project: project_id, location: location_id
glossary_path = client.glossary_path project:  project_id,
                                     location: location_id,
                                     glossary: glossary_id
model = "projects/#{project_id}/locations/#{location_id}/models/#{model_id}"
models = { target_lang => model }
glossaries = {
  target_lang => { glossary: glossary_path }
}
input_config = {
  mime_type:  mime_type,
  gcs_source: { input_uri: input_uri }
}
output_config = {
  gcs_destination: { output_uri_prefix: output_uri }
}

operation = client.batch_translate_text(
  parent:                parent,
  source_language_code:  source_lang,
  target_language_codes: [target_lang],
  input_configs:         [input_config],
  output_config:         output_config,
  models:                models,
  glossaries:            glossaries
)

# Wait until the long running operation is done
operation.wait_until_done!

response = operation.response

puts "Total Characters: #{response.total_characters}"
puts "Translated Characters: #{response.translated_characters}"

Status da operação

Uma solicitação em lote é uma operação de longa duração, por isso, pode levar um tempo considerável para ser concluída. É possível pesquisar o status dessa operação para ver se ela foi concluída ou cancelá-la.

Para mais informações, consulte Operações de longa duração.