Anleitung zur optischen Zeichenerkennung (OCR) (1. Generation)

// Get a reference to the Pub/Sub component
const {PubSub} = require('@google-cloud/pubsub');
const pubsub = new PubSub();
// Get a reference to the Cloud Storage component
const {Storage} = require('@google-cloud/storage');
const storage = new Storage();

// Get a reference to the Cloud Vision API component
const Vision = require('@google-cloud/vision');
const vision = new Vision.ImageAnnotatorClient();

// Get a reference to the Translate API component
const {Translate} = require('@google-cloud/translate').v2;
const translate = new Translate();

import base64
import json
import os
from typing import Dict, TypeVar

from google.cloud import pubsub_v1
from google.cloud import storage
from google.cloud import translate_v2 as translate
from google.cloud import vision

vision_client = vision.ImageAnnotatorClient()
translate_client = translate.Client()
publisher = pubsub_v1.PublisherClient()
storage_client = storage.Client()

project_id = os.environ["GCP_PROJECT"]

// Package ocr contains Go samples for creating OCR
// (Optical Character Recognition) Cloud functions.
package ocr

import (
	"context"
	"fmt"
	"os"
	"strings"
	"time"

	"cloud.google.com/go/pubsub"
	"cloud.google.com/go/storage"
	"cloud.google.com/go/translate"
	vision "cloud.google.com/go/vision/apiv1"
	"golang.org/x/text/language"
)

type ocrMessage struct {
	Text     string       `json:"text"`
	FileName string       `json:"fileName"`
	Lang     language.Tag `json:"lang"`
	SrcLang  language.Tag `json:"srcLang"`
}

// GCSEvent is the payload of a GCS event.
type GCSEvent struct {
	Bucket         string    `json:"bucket"`
	Name           string    `json:"name"`
	Metageneration string    `json:"metageneration"`
	ResourceState  string    `json:"resourceState"`
	TimeCreated    time.Time `json:"timeCreated"`
	Updated        time.Time `json:"updated"`
}

// PubSubMessage is the payload of a Pub/Sub event.
// See the documentation for more details:
// https://cloud.google.com/pubsub/docs/reference/rest/v1/PubsubMessage
type PubSubMessage struct {
	Data []byte `json:"data"`
}

var (
	visionClient    *vision.ImageAnnotatorClient
	translateClient *translate.Client
	pubsubClient    *pubsub.Client
	storageClient   *storage.Client

	projectID      string
	resultBucket   string
	resultTopic    string
	toLang         []string
	translateTopic string
)

func setup(ctx context.Context) error {
	projectID = os.Getenv("GCP_PROJECT")
	resultBucket = os.Getenv("RESULT_BUCKET")
	resultTopic = os.Getenv("RESULT_TOPIC")
	toLang = strings.Split(os.Getenv("TO_LANG"), ",")
	translateTopic = os.Getenv("TRANSLATE_TOPIC")

	var err error // Prevent shadowing clients with :=.

	if visionClient == nil {
		visionClient, err = vision.NewImageAnnotatorClient(ctx)
		if err != nil {
			return fmt.Errorf("vision.NewImageAnnotatorClient: %w", err)
		}
	}

	if translateClient == nil {
		translateClient, err = translate.NewClient(ctx)
		if err != nil {
			return fmt.Errorf("translate.NewClient: %w", err)
		}
	}

	if pubsubClient == nil {
		pubsubClient, err = pubsub.NewClient(ctx, projectID)
		if err != nil {
			return fmt.Errorf("translate.NewClient: %w", err)
		}
	}

	if storageClient == nil {
		storageClient, err = storage.NewClient(ctx)
		if err != nil {
			return fmt.Errorf("storage.NewClient: %w", err)
		}
	}
	return nil
}

public class OcrProcessImage implements BackgroundFunction<GcsEvent> {
  // TODO<developer> set these environment variables
  private static final String PROJECT_ID = System.getenv("GCP_PROJECT");
  private static final String TRANSLATE_TOPIC_NAME = System.getenv("TRANSLATE_TOPIC");
  private static final String[] TO_LANGS = System.getenv("TO_LANG").split(",");

  private static final Logger logger = Logger.getLogger(OcrProcessImage.class.getName());
  private static final String LOCATION_NAME = LocationName.of(PROJECT_ID, "global").toString();
  private Publisher publisher;

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

/**
 * This function is exported by index.js, and is executed when
 * a file is uploaded to the Cloud Storage bucket you created
 * for uploading images.
 *
 * @param {object} event A Google Cloud Storage File object.
 */
exports.processImage = async event => {
  const {bucket, name} = event;

  if (!bucket) {
    throw new Error(
      'Bucket not provided. Make sure you have a "bucket" property in your request'
    );
  }
  if (!name) {
    throw new Error(
      'Filename not provided. Make sure you have a "name" property in your request'
    );
  }

  await detectText(bucket, name);
  console.log(`File ${name} processed.`);
};

def process_image(file_info: dict, context: dict) -> None:
    """Cloud Function triggered by Cloud Storage when a file is changed.

    Args:
        file_info: Metadata of the changed file, provided by the
            triggering Cloud Storage event.
        context: a dictionary containing metadata about the event.

    Returns:
        None; the output is written to stdout and Stackdriver Logging.
    """
    bucket = validate_message(file_info, "bucket")
    name = validate_message(file_info, "name")

    detect_text(bucket, name)

    print("File {} processed.".format(file_info["name"]))

package ocr

import (
	"context"
	"fmt"
	"log"
)

// ProcessImage is executed when a file is uploaded to the Cloud Storage bucket you
// created for uploading images. It runs detectText, which processes the image for text.
func ProcessImage(ctx context.Context, event GCSEvent) error {
	if err := setup(ctx); err != nil {
		return fmt.Errorf("ProcessImage: %w", err)
	}
	if event.Bucket == "" {
		return fmt.Errorf("empty file.Bucket")
	}
	if event.Name == "" {
		return fmt.Errorf("empty file.Name")
	}
	if err := detectText(ctx, event.Bucket, event.Name); err != nil {
		return fmt.Errorf("detectText: %w", err)
	}
	log.Printf("File %s processed.", event.Name)
	return nil
}

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.DetectLanguageRequest;
import com.google.cloud.translate.v3.DetectLanguageResponse;
import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.TranslationServiceClient;
import com.google.cloud.vision.v1.AnnotateImageRequest;
import com.google.cloud.vision.v1.AnnotateImageResponse;
import com.google.cloud.vision.v1.Feature;
import com.google.cloud.vision.v1.Image;
import com.google.cloud.vision.v1.ImageAnnotatorClient;
import com.google.cloud.vision.v1.ImageSource;
import com.google.protobuf.ByteString;
import com.google.pubsub.v1.ProjectTopicName;
import com.google.pubsub.v1.PubsubMessage;
import functions.eventpojos.GcsEvent;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.logging.Level;
import java.util.logging.Logger;

  @Override
  public void accept(GcsEvent gcsEvent, Context context) {

    // Validate parameters
    String bucket = gcsEvent.getBucket();
    if (bucket == null) {
      throw new IllegalArgumentException("Missing bucket parameter");
    }
    String filename = gcsEvent.getName();
    if (filename == null) {
      throw new IllegalArgumentException("Missing name parameter");
    }

    detectText(bucket, filename);
  }
}

/**
 * Detects the text in an image using the Google Vision API.
 *
 * @param {string} bucketName Cloud Storage bucket name.
 * @param {string} filename Cloud Storage file name.
 * @returns {Promise}
 */
const detectText = async (bucketName, filename) => {
  console.log(`Looking for text in image ${filename}`);
  const [textDetections] = await vision.textDetection(
    `gs://${bucketName}/${filename}`
  );
  const [annotation] = textDetections.textAnnotations;
  const text = annotation ? annotation.description.trim() : '';
  console.log('Extracted text from image:', text);

  let [translateDetection] = await translate.detect(text);
  if (Array.isArray(translateDetection)) {
    [translateDetection] = translateDetection;
  }
  console.log(
    `Detected language "${translateDetection.language}" for ${filename}`
  );

  // Submit a message to the bus for each language we're going to translate to
  const TO_LANGS = process.env.TO_LANG.split(',');
  const topicName = process.env.TRANSLATE_TOPIC;

  const tasks = TO_LANGS.map(lang => {
    const messageData = {
      text: text,
      filename: filename,
      lang: lang,
    };

    // Helper function that publishes translation result to a Pub/Sub topic
    // For more information on publishing Pub/Sub messages, see this page:
    //   https://cloud.google.com/pubsub/docs/publisher
    return publishResult(topicName, messageData);
  });

  return Promise.all(tasks);
};

def detect_text(bucket: str, filename: str) -> None:
    """
    Extract the text from an image uploaded to Cloud Storage.

    Extract the text from an image uploaded to Cloud Storage, then
    publish messages requesting subscribing services translate the text
    to each target language and save the result.

    Args:
        bucket: name of GCS bucket in which the file is stored.
        filename: name of the file to be read.

    Returns:
        None; the output is written to stdout and Stackdriver Logging.
    """
    print("Looking for text in image {}".format(filename))

    futures = []

    image = vision.Image(
        source=vision.ImageSource(gcs_image_uri=f"gs://{bucket}/{filename}")
    )
    text_detection_response = vision_client.text_detection(image=image)
    annotations = text_detection_response.text_annotations
    if len(annotations) > 0:
        text = annotations[0].description
    else:
        text = ""
    print(f"Extracted text {text} from image ({len(text)} chars).")

    detect_language_response = translate_client.detect_language(text)
    src_lang = detect_language_response["language"]
    print(f"Detected language {src_lang} for text {text}.")

    # Submit a message to the bus for each target language
    to_langs = os.environ["TO_LANG"].split(",")
    for target_lang in to_langs:
        topic_name = os.environ["TRANSLATE_TOPIC"]
        if src_lang == target_lang or src_lang == "und":
            topic_name = os.environ["RESULT_TOPIC"]
        message = {
            "text": text,
            "filename": filename,
            "lang": target_lang,
            "src_lang": src_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)
        futures.append(future)
    for future in futures:
        future.result()

package ocr

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

	"cloud.google.com/go/pubsub"
	"cloud.google.com/go/vision/v2/apiv1/visionpb"
	"golang.org/x/text/language"
)

// detectText detects the text in an image using the Google Vision API.
func detectText(ctx context.Context, bucketName, fileName string) error {
	log.Printf("Looking for text in image %v", fileName)
	maxResults := 1
	image := &visionpb.Image{
		Source: &visionpb.ImageSource{
			GcsImageUri: fmt.Sprintf("gs://%s/%s", bucketName, fileName),
		},
	}
	annotations, err := visionClient.DetectTexts(ctx, image, &visionpb.ImageContext{}, maxResults)
	if err != nil {
		return fmt.Errorf("DetectTexts: %w", err)
	}
	text := ""
	if len(annotations) > 0 {
		text = annotations[0].Description
	}
	if len(annotations) == 0 || len(text) == 0 {
		log.Printf("No text detected in image %q. Returning early.", fileName)
		return nil
	}
	log.Printf("Extracted text %q from image (%d chars).", text, len(text))

	detectResponse, err := translateClient.DetectLanguage(ctx, []string{text})
	if err != nil {
		return fmt.Errorf("DetectLanguage: %w", err)
	}
	if len(detectResponse) == 0 || len(detectResponse[0]) == 0 {
		return fmt.Errorf("DetectLanguage gave empty response")
	}
	srcLang := detectResponse[0][0].Language.String()
	log.Printf("Detected language %q for text %q.", srcLang, text)

	// Submit a message to the bus for each target language
	for _, targetLang := range toLang {
		topicName := translateTopic
		if srcLang == targetLang || srcLang == "und" { // detection returns "und" for undefined language
			topicName = resultTopic
		}
		targetTag, err := language.Parse(targetLang)
		if err != nil {
			return fmt.Errorf("language.Parse: %w", err)
		}
		srcTag, err := language.Parse(srcLang)
		if err != nil {
			return fmt.Errorf("language.Parse: %w", err)
		}
		message, err := json.Marshal(ocrMessage{
			Text:     text,
			FileName: fileName,
			Lang:     targetTag,
			SrcLang:  srcTag,
		})
		if err != nil {
			return fmt.Errorf("json.Marshal: %w", err)
		}
		topic := pubsubClient.Topic(topicName)
		ok, err := topic.Exists(ctx)
		if err != nil {
			return fmt.Errorf("Exists: %w", err)
		}
		if !ok {
			topic, err = pubsubClient.CreateTopic(ctx, topicName)
			if err != nil {
				return fmt.Errorf("CreateTopic: %w", err)
			}
		}
		msg := &pubsub.Message{
			Data: []byte(message),
		}
		if _, err = topic.Publish(ctx, msg).Get(ctx); err != nil {
			return fmt.Errorf("Get: %w", err)
		}
	}
	return nil
}

private void detectText(String bucket, String filename) {
  logger.info("Looking for text in image " + filename);

  List<AnnotateImageRequest> visionRequests = new ArrayList<>();
  String gcsPath = String.format("gs://%s/%s", bucket, filename);

  ImageSource imgSource = ImageSource.newBuilder().setGcsImageUri(gcsPath).build();
  Image img = Image.newBuilder().setSource(imgSource).build();

  Feature textFeature = Feature.newBuilder().setType(Feature.Type.TEXT_DETECTION).build();
  AnnotateImageRequest visionRequest =
      AnnotateImageRequest.newBuilder().addFeatures(textFeature).setImage(img).build();
  visionRequests.add(visionRequest);

  // Detect text in an image using the Cloud Vision API
  AnnotateImageResponse visionResponse;
  try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
    visionResponse = client.batchAnnotateImages(visionRequests).getResponses(0);
    if (visionResponse == null || !visionResponse.hasFullTextAnnotation()) {
      logger.info(String.format("Image %s contains no text", filename));
      return;
    }

    if (visionResponse.hasError()) {
      // Log error
      logger.log(
          Level.SEVERE, "Error in vision API call: " + visionResponse.getError().getMessage());
      return;
    }
  } catch (IOException e) {
    // Log error (since IOException cannot be thrown by a Cloud Function)
    logger.log(Level.SEVERE, "Error detecting text: " + e.getMessage(), e);
    return;
  }

  String text = visionResponse.getFullTextAnnotation().getText();
  logger.info("Extracted text from image: " + text);

  // Detect language using the Cloud Translation API
  DetectLanguageRequest languageRequest =
      DetectLanguageRequest.newBuilder()
          .setParent(LOCATION_NAME)
          .setMimeType("text/plain")
          .setContent(text)
          .build();
  DetectLanguageResponse languageResponse;
  try (TranslationServiceClient client = TranslationServiceClient.create()) {
    languageResponse = client.detectLanguage(languageRequest);
  } catch (IOException e) {
    // Log error (since IOException cannot be thrown by a function)
    logger.log(Level.SEVERE, "Error detecting language: " + e.getMessage(), e);
    return;
  }

  if (languageResponse.getLanguagesCount() == 0) {
    logger.info("No languages were detected for text: " + text);
    return;
  }

  String languageCode = languageResponse.getLanguages(0).getLanguageCode();
  logger.info(String.format("Detected language %s for file %s", languageCode, filename));

  // Send a Pub/Sub translation request for every language we're going to translate to
  for (String targetLanguage : TO_LANGS) {
    logger.info("Sending translation request for language " + targetLanguage);
    OcrTranslateApiMessage message = new OcrTranslateApiMessage(text, filename, targetLanguage);
    ByteString byteStr = ByteString.copyFrom(message.toPubsubData());
    PubsubMessage pubsubApiMessage = PubsubMessage.newBuilder().setData(byteStr).build();
    try {
      publisher.publish(pubsubApiMessage).get();
    } catch (InterruptedException | ExecutionException e) {
      // Log error
      logger.log(Level.SEVERE, "Error publishing translation request: " + e.getMessage(), e);
      return;
    }
  }
}

/**
 * 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}`);
};

def translate_text(event: dict, context: dict) -> None:
    """
    Cloud Function triggered by PubSub when a message is received from
    a subscription.

    Translates the text in the message from the specified source language
    to the requested target language, then sends a message requesting another
    service save the result.

    Args:
        event: dictionary containing the PubSub event.
        context: a dictionary containing metadata about the event.

    Returns:
        None; the output is written to stdout and Stackdriver Logging.
    """
    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(f"Translating text into {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,
    }
    encoded_message = json.dumps(message).encode("utf-8")
    topic_path = publisher.topic_path(project_id, topic_name)
    future = publisher.publish(topic_path, data=encoded_message)
    future.result()

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: %w", 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: %w", 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: %w", 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: %w", err)
	}

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

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.protobuf.ByteString;
import com.google.pubsub.v1.ProjectTopicName;
import com.google.pubsub.v1.PubsubMessage;
import functions.eventpojos.Message;
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 pubSubMessage, Context context) {
    OcrTranslateApiMessage ocrMessage = OcrTranslateApiMessage.fromPubsubData(
        pubSubMessage.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;
  }
}

/**
 * This function is exported by index.js, and is executed when
 * a message is published to the Cloud Pub/Sub topic specified
 * by the RESULT_TOPIC environment variable. The function saves
 * the data packet to a file in GCS.
 *
 * @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.saveResult = 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(`Received request to save file ${filename}`);

  const bucketName = process.env.RESULT_BUCKET;
  const newFilename = renameImageForSave(filename, lang);
  const file = storage.bucket(bucketName).file(newFilename);

  console.log(`Saving result to ${newFilename} in bucket ${bucketName}`);

  await file.save(text);
  console.log('File saved.');
};

def save_result(event: dict, context: dict) -> None:
    """
    Cloud Function triggered by PubSub when a message is received from
    a subscription.

    Args:
        event: dictionary containing the PubSub event.
        context: a dictionary containing metadata about the event.

    Returns:
        None; the output is written to stdout and Stackdriver Logging.
    """
    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")
    lang = validate_message(message, "lang")

    print(f"Received request to save file {filename}.")

    bucket_name = os.environ["RESULT_BUCKET"]
    result_filename = f"{filename}_{lang}.txt"
    bucket = storage_client.get_bucket(bucket_name)
    blob = bucket.blob(result_filename)

    print(f"Saving result to {result_filename} in bucket {bucket_name}.")

    blob.upload_from_string(text)

    print("File saved.")

package ocr

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

// SaveResult is executed when a message is published to the Cloud Pub/Sub topic
// specified by the RESULT_TOPIC environment vairable, and saves the data packet
// to a file in GCS.
func SaveResult(ctx context.Context, event PubSubMessage) error {
	if err := setup(ctx); err != nil {
		return fmt.Errorf("ProcessImage: %w", err)
	}
	var message ocrMessage
	if event.Data == nil {
		return fmt.Errorf("Empty data")
	}
	if err := json.Unmarshal(event.Data, &message); err != nil {
		return fmt.Errorf("json.Unmarshal: %w", err)
	}
	log.Printf("Received request to save file %q.", message.FileName)

	resultFilename := fmt.Sprintf("%s_%s.txt", message.FileName, message.Lang)
	bucket := storageClient.Bucket(resultBucket)

	log.Printf("Saving result to %q in bucket %q.", resultFilename, resultBucket)

	w := bucket.Object(resultFilename).NewWriter(ctx)
	defer w.Close()
	fmt.Fprint(w, message.Text)

	log.Printf("File saved.")
	return nil
}

import com.google.cloud.functions.BackgroundFunction;
import com.google.cloud.functions.Context;
import com.google.cloud.storage.BlobId;
import com.google.cloud.storage.BlobInfo;
import com.google.cloud.storage.Storage;
import com.google.cloud.storage.StorageOptions;
import functions.eventpojos.PubsubMessage;
import java.nio.charset.StandardCharsets;
import java.util.logging.Logger;

public class OcrSaveResult implements BackgroundFunction<PubsubMessage> {
  // TODO<developer> set this environment variable
  private static final String RESULT_BUCKET = System.getenv("RESULT_BUCKET");

  private static final Storage STORAGE = StorageOptions.getDefaultInstance().getService();
  private static final Logger logger = Logger.getLogger(OcrSaveResult.class.getName());

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

    logger.info("Received request to save file " +  ocrMessage.getFilename());

    String newFileName = String.format(
        "%s_to_%s.txt", ocrMessage.getFilename(), ocrMessage.getLang());

    // Save file to RESULT_BUCKET with name newFileNaem
    logger.info(String.format("Saving result to %s in bucket %s", newFileName, RESULT_BUCKET));
    BlobInfo blobInfo = BlobInfo.newBuilder(BlobId.of(RESULT_BUCKET, newFileName)).build();
    STORAGE.create(blobInfo, ocrMessage.getText().getBytes(StandardCharsets.UTF_8));
    logger.info("File saved");
  }
}