OCR tutorial step 3 - Translate text

Demonstrates how to upload image files to Cloud Storage, and extract and translate text from the images by using the Vision API and Translation API.

Explore further

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

Code sample

Go


package ocr

import (
	"context"
	"encoding/json"
	"fmt"
	"log"

	"cloud.google.com/go/pubsub"
	"cloud.google.com/go/translate"
)

// TranslateText is executed when a message is published to the Cloud Pub/Sub
// topic specified by the TRANSLATE_TOPIC environment variable, and translates
// the text using the Google Translate API.
func TranslateText(ctx context.Context, event PubSubMessage) error {
	if err := setup(ctx); err != nil {
		return fmt.Errorf("setup: %v", err)
	}
	if event.Data == nil {
		return fmt.Errorf("empty data")
	}
	var message ocrMessage
	if err := json.Unmarshal(event.Data, &message); err != nil {
		return fmt.Errorf("json.Unmarshal: %v", err)
	}

	log.Printf("Translating text into %s.", message.Lang.String())
	opts := translate.Options{
		Source: message.SrcLang,
	}
	translateResponse, err := translateClient.Translate(ctx, []string{message.Text}, message.Lang, &opts)
	if err != nil {
		return fmt.Errorf("Translate: %v", err)
	}
	if len(translateResponse) == 0 {
		return fmt.Errorf("Empty Translate response")
	}
	translatedText := translateResponse[0]

	messageData, err := json.Marshal(ocrMessage{
		Text:     translatedText.Text,
		FileName: message.FileName,
		Lang:     message.Lang,
		SrcLang:  message.SrcLang,
	})
	if err != nil {
		return fmt.Errorf("json.Marshal: %v", err)
	}

	topic := pubsubClient.Topic(resultTopic)
	ok, err := topic.Exists(ctx)
	if err != nil {
		return fmt.Errorf("Exists: %v", err)
	}
	if !ok {
		topic, err = pubsubClient.CreateTopic(ctx, resultTopic)
		if err != nil {
			return fmt.Errorf("CreateTopic: %v", err)
		}
	}
	msg := &pubsub.Message{
		Data: messageData,
	}
	if _, err = topic.Publish(ctx, msg).Get(ctx); err != nil {
		return fmt.Errorf("Get: %v", err)
	}
	log.Printf("Sent translation: %q", translatedText.Text)
	return nil
}

Java


import com.google.cloud.functions.BackgroundFunction;
import com.google.cloud.functions.Context;
import com.google.cloud.pubsub.v1.Publisher;
import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.TranslateTextRequest;
import com.google.cloud.translate.v3.TranslateTextResponse;
import com.google.cloud.translate.v3.TranslationServiceClient;
import com.google.events.cloud.pubsub.v1.Message;
import com.google.protobuf.ByteString;
import com.google.pubsub.v1.ProjectTopicName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.concurrent.ExecutionException;
import java.util.logging.Level;
import java.util.logging.Logger;

public class OcrTranslateText implements BackgroundFunction<Message> {
  private static final Logger logger = Logger.getLogger(OcrTranslateText.class.getName());

  // TODO<developer> set these environment variables
  private static final String PROJECT_ID = getenv("GCP_PROJECT");
  private static final String RESULTS_TOPIC_NAME = getenv("RESULT_TOPIC");
  private static final String LOCATION_NAME = LocationName.of(PROJECT_ID, "global").toString();

  private Publisher publisher;

  public OcrTranslateText() throws IOException {
    publisher = Publisher.newBuilder(
        ProjectTopicName.of(PROJECT_ID, RESULTS_TOPIC_NAME)).build();
  }

  @Override
  public void accept(Message message, Context context) {
    OcrTranslateApiMessage ocrMessage = OcrTranslateApiMessage.fromPubsubData(
        message.getData().getBytes(StandardCharsets.UTF_8));

    String targetLang = ocrMessage.getLang();
    logger.info("Translating text into " + targetLang);

    // Translate text to target language
    String text = ocrMessage.getText();
    TranslateTextRequest request =
        TranslateTextRequest.newBuilder()
            .setParent(LOCATION_NAME)
            .setMimeType("text/plain")
            .setTargetLanguageCode(targetLang)
            .addContents(text)
            .build();

    TranslateTextResponse response;
    try (TranslationServiceClient client = TranslationServiceClient.create()) {
      response = client.translateText(request);
    } catch (IOException e) {
      // Log error (since IOException cannot be thrown by a function)
      logger.log(Level.SEVERE, "Error translating text: " + e.getMessage(), e);
      return;
    }
    if (response.getTranslationsCount() == 0) {
      return;
    }

    String translatedText = response.getTranslations(0).getTranslatedText();
    logger.info("Translated text: " + translatedText);

    // Send translated text to (subsequent) Pub/Sub topic
    String filename = ocrMessage.getFilename();
    OcrTranslateApiMessage translateMessage = new OcrTranslateApiMessage(
        translatedText, filename, targetLang);
    try {
      ByteString byteStr = ByteString.copyFrom(translateMessage.toPubsubData());
      PubsubMessage pubsubApiMessage = PubsubMessage.newBuilder().setData(byteStr).build();

      publisher.publish(pubsubApiMessage).get();
      logger.info("Text translated to " + targetLang);
    } catch (InterruptedException | ExecutionException e) {
      // Log error (since these exception types cannot be thrown by a function)
      logger.log(Level.SEVERE, "Error publishing translation save request: " + e.getMessage(), e);
    }
  }

  // Avoid ungraceful deployment failures due to unset environment variables.
  // If you get this warning you should redeploy with the variable set.
  private static String getenv(String name) {
    String value = System.getenv(name);
    if (value == null) {
      logger.warning("Environment variable " + name + " was not set");
      value = "MISSING";
    }
    return value;
  }
}

Node.js

/**
 * This function is exported by index.js, and is executed when
 * a message is published to the Cloud Pub/Sub topic specified
 * by the TRANSLATE_TOPIC environment variable. The function
 * translates text using the Google Translate API.
 *
 * @param {object} event The Cloud Pub/Sub Message object.
 * @param {string} {messageObject}.data The "data" property of the Cloud Pub/Sub
 * Message. This property will be a base64-encoded string that you must decode.
 */
exports.translateText = async event => {
  const pubsubData = event.data;
  const jsonStr = Buffer.from(pubsubData, 'base64').toString();
  const {text, filename, lang} = JSON.parse(jsonStr);

  if (!text) {
    throw new Error(
      'Text not provided. Make sure you have a "text" property in your request'
    );
  }
  if (!filename) {
    throw new Error(
      'Filename not provided. Make sure you have a "filename" property in your request'
    );
  }
  if (!lang) {
    throw new Error(
      'Language not provided. Make sure you have a "lang" property in your request'
    );
  }

  console.log(`Translating text into ${lang}`);
  const [translation] = await translate.translate(text, lang);

  console.log('Translated text:', translation);

  const messageData = {
    text: translation,
    filename: filename,
    lang: lang,
  };

  await publishResult(process.env.RESULT_TOPIC, messageData);
  console.log(`Text translated to ${lang}`);
};

Python

def translate_text(event, context):
    if event.get("data"):
        message_data = base64.b64decode(event["data"]).decode("utf-8")
        message = json.loads(message_data)
    else:
        raise ValueError("Data sector is missing in the Pub/Sub message.")

    text = validate_message(message, "text")
    filename = validate_message(message, "filename")
    target_lang = validate_message(message, "lang")
    src_lang = validate_message(message, "src_lang")

    print("Translating text into {}.".format(target_lang))
    translated_text = translate_client.translate(
        text, target_language=target_lang, source_language=src_lang
    )
    topic_name = os.environ["RESULT_TOPIC"]
    message = {
        "text": translated_text["translatedText"],
        "filename": filename,
        "lang": target_lang,
    }
    message_data = json.dumps(message).encode("utf-8")
    topic_path = publisher.topic_path(project_id, topic_name)
    future = publisher.publish(topic_path, data=message_data)
    future.result()

What's next

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