批次要求 (進階)

批次翻譯可讓您翻譯大量文字 (每個批次的限制為 100 個檔案)，並且以離線指令翻譯成最多 10 種不同的譯文語言。內容總大小不得超過 1 億個 Unicode 碼點，且必須使用 UTF-8 編碼。

事前準備

如要開始使用 Cloud Translation API，必須先準備一個已啟用 Cloud Translation API 的專案，並取得適當的憑證。您也可以安裝常用程式設計語言的用戶端程式庫，協助您呼叫 API。詳情請參閱「設定」頁面。

權限

如要進行批次翻譯，除了 Cloud Translation 權限，您還需要具備 Cloud Storage bucket 存取權。批次翻譯輸入檔案會從 Cloud Storage bucket 讀取，輸出檔案則會寫入 Cloud Storage bucket。舉例來說，如要從 bucket 讀取輸入檔案，您必須至少具備該 bucket 的讀取物件權限 (由 roles/storage.objectViewer 角色提供)。如要進一步瞭解 Cloud Storage 角色，請參閱 Cloud Storage 說明文件。

輸入檔案

僅支援以下兩種 MIME 類型：text/html (HTML) 和 text/plain (.tsv 和 .txt)。

使用 TSV 檔案

如果副檔名為 TSV，則檔案可以包含一或二個資料欄。第一個資料欄 (選用) 是文字要求的 ID。如果第一個資料欄遺失，Google 會使用輸入檔案中的資料列編號 (從 0 開始) 做為輸出檔案中的 ID。第二個資料欄是要翻譯的實際文字。為獲得最佳結果，每個資料列應小於或等於 1000 Unicode 碼點，否則可能會傳回錯誤。

使用文字或 HTML

其他支援的副檔名為文字檔 (.txt) 或 HTML，系統會將其視為一個大型文字區塊。

批次要求

發出批次翻譯要求時，您必須提供以下兩者的路徑：含有待翻譯內容的輸入設定檔 (InputConfig) 及最終翻譯的輸出位置 (OutputConfig)。您至少需要兩個不同的 Cloud Storage bucket。來源 bucket 包含待翻譯的內容，目標 bucket 則包含翻譯後產生的檔案。在翻譯程序開始之前，目標資料夾必須是空的。

處理要求時，我們會即時將結果寫入輸出位置。即使您在中途取消要求，系統仍會在 Cloud Storage 輸出位置產生輸入檔案層級的部分輸出內容。因此，您仍須支付已翻譯字元數的費用。

REST

以下範例顯示兩個送交翻譯的輸入檔案。

使用任何要求資料之前，請先修改下列項目的值：

PROJECT_NUMBER_OR_ID： Google Cloud 專案的數值或英數字元 ID

HTTP 方法和網址：

POST https://translation.googleapis.com/v3/projects/PROJECT_NUMBER_OR_ID/locations/us-central1:batchTranslateText

JSON 要求主體：

{
  "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/"
      }
   }
}

請展開以下其中一個選項，以傳送要求：

curl (Linux、macOS 或 Cloud Shell)

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI，或已使用 Cloud Shell 自動登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_NUMBER_OR_ID" \
     -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 (Windows)

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_NUMBER_OR_ID" }

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

您應該會收到如下的 JSON 回覆：

{
  "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"
  }
}

回覆會包含長時間執行作業的 ID。

Go

在試用這個範例之前，請先按照「使用用戶端程式庫的 Cloud Translation 快速入門導覽課程」中的 Go 設定操作說明進行操作。詳情請參閱「Cloud Translation Go API 參考文件」。

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

import (
	"context"
	"fmt"
	"io"

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

// 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: %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",
			},
		},
		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

在試用這個範例之前，請先按照「使用用戶端程式庫的 Cloud Translation 快速入門導覽課程」中的 Java 設定操作說明進行操作。詳情請參閱「Cloud Translation Java API 參考文件」。

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

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(450, 600);
      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

在試用這個範例之前，請先按照「使用用戶端程式庫的 Cloud Translation 快速入門導覽課程」中的 Node.js 設定操作說明進行操作。詳情請參閱「Cloud Translation Node.js API 參考文件」。

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

/**
 * 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,
      },
    },
  };

  // Setup timeout for long-running operation. Timeout specified in ms.
  const options = {timeout: 240000};
  // Batch translate text using a long-running operation with a timeout of 240000ms.
  const [operation] = await translationClient.batchTranslateText(
    request,
    options
  );

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

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

batchTranslateText();

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Cloud Translation 快速入門導覽課程」中的 Python 設定操作說明進行操作。詳情請參閱「Cloud Translation Python API 參考文件」。

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

from google.cloud import translate


def batch_translate_text(
    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",
    timeout: int = 180,
) -> translate.TranslateTextResponse:
    """Translates a batch of texts on GCS and stores the result in a GCS location.

    Args:
        input_uri: The input URI of the texts to be translated.
        output_uri: The output URI of the translated texts.
        project_id: The ID of the project that owns the destination bucket.
        timeout: The timeout for this batch translation operation.

    Returns:
        The translated texts.
    """

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

    return response

其他語言

C#：請按照用戶端程式庫頁面上的 C# 設定操作說明完成相關步驟，然後參閱「.NET 適用的 Cloud Translation 參考文件」。

PHP：請按照用戶端程式庫頁面上的 PHP 設定操作說明完成相關步驟，然後參閱「PHP 適用的 Cloud Translation 參考文件」。

Ruby：請按照用戶端程式庫頁面上的 Ruby 設定操作說明完成相關步驟操作，然後參閱「Ruby 適用的 Cloud Translation 參考文件」。

使用 AutoML 模型發出批次要求

您可以在批次要求中使用自訂模型。如果涉及多種譯文語言，可能會發生各種情況。

指定譯文語言的 AutoML 模型

REST

這個範例說明如何為譯文語言指定自訂模型。

使用任何要求資料之前，請先修改下列項目的值：

PROJECT_NUMBER_OR_ID： Google Cloud 專案的數值或英數字元 ID

HTTP 方法和網址：

POST https://translation.googleapis.com/v3/projects/PROJECT_NUMBER_OR_ID/locations/us-central1:batchTranslateText

JSON 要求主體：

{
  "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/"
      }
   }
}

請展開以下其中一個選項，以傳送要求：

curl (Linux、macOS 或 Cloud Shell)

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_NUMBER_OR_ID" \
     -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 (Windows)

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_NUMBER_OR_ID" }

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

您應該會收到如下的 JSON 回覆：

{
  "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"
  }
}

回覆會包含長時間執行作業的 ID。

Go

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

import (
	"context"
	"fmt"
	"io"

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

// 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: %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",
			},
		},
		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: %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

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

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(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

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

/**
 * 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}`,
    },
  };

  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}`);
}

batchTranslateTextWithModel();

Python

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

from google.cloud import translate


def batch_translate_text_with_model(
    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",
    model_id: str = "YOUR_MODEL_ID",
) -> translate.TranslationServiceClient:
    """Batch translate text using Translation model.
    Model can be AutoML or General[built-in] model.

    Args:
        input_uri: The input file to translate.
        output_uri: The output file to save the translation results.
        project_id: The ID of the GCP project that owns the model.
        model_id: The model ID.

    Returns:
        The response from the batch translation API.
    """

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

    return response

其他語言

C#：請按照用戶端程式庫頁面上的 C# 設定操作說明完成相關步驟，然後參閱「.NET 適用的 Cloud Translation 參考文件」。

PHP：請按照用戶端程式庫頁面上的 PHP 設定操作說明完成相關步驟，然後參閱「PHP 適用的 Cloud Translation 參考文件」。

Ruby：請按照用戶端程式庫頁面上的 Ruby 設定操作說明完成相關步驟操作，然後參閱「Ruby 適用的 Cloud Translation 參考文件」。

為多種譯文語言指定 AutoML 模型

REST

如果有多種譯文語言，可以為每種譯文語言指定自訂模型。

使用任何要求資料之前，請先修改下列項目的值：

PROJECT_NUMBER_OR_ID： Google Cloud 專案的數值或英數字元 ID

HTTP 方法和網址：

POST https://translation.googleapis.com/v3/projects/PROJECT_NUMBER_OR_ID/locations/us-central1:batchTranslateText

JSON 要求主體：

{
  "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/"
      }
   }
 }

請展開以下其中一個選項，以傳送要求：

curl (Linux、macOS 或 Cloud Shell)

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_NUMBER_OR_ID" \
     -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 (Windows)

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_NUMBER_OR_ID" }

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

您應該會收到如下的 JSON 回覆：

{
  "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"
  }
}

回覆會包含長時間執行作業的的 ID。

為譯文語言指定 AutoML 模型，但其他語言則不指定

您可以為特定譯文語言指定自訂模型，但不為其他譯文語言指定。請使用「為多種譯文語言指定自訂模型」的程式碼，修改 models 欄位，指定模型的譯文語言 (本例為 es)，並將 fr 留空：

"models": {'es':'projects/PROJECT_NUMBER_OR_ID/locations/us-central1/models/model-id'},

其中 PROJECT_NUMBER_OR_ID 是 Google Cloud 專案編號或 ID，model-id 則是您為 AutoML 模型指定的名稱。

使用詞彙表翻譯文字

REST

這個範例說明如何為譯文語言指定詞彙表。

使用任何要求資料之前，請先修改下列項目的值：

PROJECT_NUMBER_OR_ID： Google Cloud 專案的數值或英數字元 ID
glossary-id：您的詞彙表 ID，例如「my-en-to-es-glossary」

HTTP 方法和網址：

POST https://translation.googleapis.com/v3/projects/PROJECT_NUMBER_OR_ID/locations/us-central1:batchTranslateText

JSON 要求內文：

{
  "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/"
    }
  }
}

如要傳送要求，請選擇以下其中一個選項：

curl

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login 透過使用者帳戶登入 gcloud CLI，或是使用 Cloud Shell 自動登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求內文儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_NUMBER_OR_ID" \
     -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

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_NUMBER_OR_ID" }

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

您應該會收到如下的 JSON 回覆：

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

Go

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

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

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

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

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

/**
 * 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();

Python

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

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

其他語言

C#：請按照用戶端程式庫頁面上的 C# 設定操作說明完成相關步驟，然後參閱「.NET 適用的 Cloud Translation 參考文件」。

PHP：請按照用戶端程式庫頁面上的 PHP 設定操作說明完成相關步驟，然後參閱「PHP 適用的 Cloud Translation 參考文件」。

Ruby：請按照用戶端程式庫頁面上的 Ruby 設定操作說明完成相關步驟操作，然後參閱「Ruby 適用的 Cloud Translation 參考文件」。

使用 AutoML Translation 自訂模型和詞彙翻譯文字

REST

這個範例說明如何為譯文語言指定自訂模型和詞彙表。

使用任何要求資料之前，請先修改下列項目的值：

PROJECT_NUMBER_OR_ID： Google Cloud 專案的數值或英數字元 ID

HTTP 方法和網址：

POST https://translation.googleapis.com/v3/projects/PROJECT_NUMBER_OR_ID/locations/us-central1:batchTranslateText

JSON 要求內文：

{
  "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/"
    }
  }
}

如要傳送要求，請選擇以下其中一個選項：

curl

將要求內文儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_NUMBER_OR_ID" \
     -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

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_NUMBER_OR_ID" }

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

您應該會收到如下的 JSON 回覆：

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

Go

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

import (
	"context"
	"fmt"
	"io"

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

// 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: %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,
				},
			},
		},
		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: %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

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

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(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

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

/**
 * 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}`,
    },
  };

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

  // 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}`);
}

batchTranslateTextWithGlossaryAndModel();

Python

如要向 Cloud Translation 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

from google.cloud import translate


def batch_translate_text_with_glossary_and_model(
    input_uri: str,
    output_uri: str,
    project_id: str,
    model_id: str,
    glossary_id: str,
) -> translate.TranslateTextResponse:
    """Batch translate text with Glossary and Translation model.
    Args:
        input_uri: The input text to be translated.
        output_uri: The output text to be translated.
        project_id: The ID of the GCP project that owns the model.
        model_id: The ID of the model
        glossary_id: The ID of the glossary

    Returns:
        The translated text.
    """

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

    return response

其他語言

C#：請按照用戶端程式庫頁面上的 C# 設定操作說明完成相關步驟，然後參閱「.NET 適用的 Cloud Translation 參考文件」。

PHP：請按照用戶端程式庫頁面上的 PHP 設定操作說明完成相關步驟，然後參閱「PHP 適用的 Cloud Translation 參考文件」。

Ruby：請按照用戶端程式庫頁面上的 Ruby 設定操作說明完成相關步驟操作，然後參閱「Ruby 適用的 Cloud Translation 參考文件」。

作業狀態

批次要求是一項長時間執行的作業，可能需要相當長的時間才能完成。您可以輪詢這項作業的狀態來查看作業是否已完成，也可以取消該項作業。

詳情請參閱「長時間執行的作業」一文。

其他資源

如需解決常見問題或錯誤的說明，請參閱「疑難排解」頁面。

批次要求 (進階) 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

事前準備

權限

輸入檔案

使用 TSV 檔案

使用文字或 HTML

批次要求

REST

curl (Linux、macOS 或 Cloud Shell)

PowerShell (Windows)

Go

Java

Node.js

Python

其他語言

使用 AutoML 模型發出批次要求

指定譯文語言的 AutoML 模型

REST

curl (Linux、macOS 或 Cloud Shell)

PowerShell (Windows)

Go

Java

Node.js

Python

其他語言

為多種譯文語言指定 AutoML 模型

REST

curl (Linux、macOS 或 Cloud Shell)

PowerShell (Windows)

為譯文語言指定 AutoML 模型，但其他語言則不指定

使用詞彙表翻譯文字

REST

curl

PowerShell

Go

Java

Node.js

Python

其他語言

使用 AutoML Translation 自訂模型和詞彙翻譯文字

REST

curl

PowerShell

Go

Java

Node.js

Python

其他語言

作業狀態

其他資源

批次要求 (進階)