Optical Character Recognition (OCR) Tutorial

const config = require('./config.json');

// 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');
const translate = new Translate();

const Buffer = require('safe-buffer').Buffer;

import base64
import json
import os

from google.cloud import pubsub_v1
from google.cloud import storage
from google.cloud import 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']

with open('config.json') as f:
    data = f.read()
config = json.loads(data)

/**
 * 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.data (Node 6) A Google Cloud Storage File object.
 * @param {object} event (Node 8+) A Google Cloud Storage File object.
 */
exports.processImage = event => {
  const file = event.data || event;

  return Promise.resolve()
    .then(() => {
      if (file.resourceState === 'not_exists') {
        // This was a deletion event, we don't want to process this
        return;
      }

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

      return detectText(file.bucket, file.name);
    })
    .then(() => {
      console.log(`File ${file.name} processed.`);
    });
};

def process_image(file, context):
    """Cloud Function triggered by Cloud Storage when a file is changed.
    Args:
        file (dict): Metadata of the changed file, provided by the triggering
                                 Cloud Storage event.
        context (google.cloud.functions.Context): Metadata of triggering event.
    Returns:
        None; the output is written to stdout and Stackdriver Logging
    """
    bucket = validate_message(file, 'bucket')
    name = validate_message(file, 'name')

    detect_text(bucket, name)

    print('File {} processed.'.format(file['name']))

/**
 * 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}
 */
function detectText(bucketName, filename) {
  let text;

  console.log(`Looking for text in image ${filename}`);
  return vision
    .textDetection(`gs://${bucketName}/${filename}`)
    .then(([detections]) => {
      const annotation = detections.textAnnotations[0];
      text = annotation ? annotation.description : '';
      console.log(`Extracted text from image (${text.length} chars)`);
      return translate.detect(text);
    })
    .then(([detection]) => {
      if (Array.isArray(detection)) {
        detection = detection[0];
      }
      console.log(`Detected language "${detection.language}" for ${filename}`);

      // Submit a message to the bus for each language we're going to translate to
      const tasks = config.TO_LANG.map(lang => {
        let topicName = config.TRANSLATE_TOPIC;
        if (detection.language === lang) {
          topicName = config.RESULT_TOPIC;
        }
        const messageData = {
          text: text,
          filename: filename,
          lang: lang,
        };

        return publishResult(topicName, messageData);
      });

      return Promise.all(tasks);
    });
}

def detect_text(bucket, filename):
    print('Looking for text in image {}'.format(filename))

    futures = []

    text_detection_response = vision_client.text_detection({
        'source': {'image_uri': 'gs://{}/{}'.format(bucket, filename)}
    })
    annotations = text_detection_response.text_annotations
    if len(annotations) > 0:
        text = annotations[0].description
    else:
        text = ''
    print('Extracted text {} from image ({} chars).'.format(text, len(text)))

    detect_language_response = translate_client.detect_language(text)
    src_lang = detect_language_response['language']
    print('Detected language {} for text {}.'.format(src_lang, text))

    # Submit a message to the bus for each target language
    for target_lang in config.get('TO_LANG', []):
        topic_name = config['TRANSLATE_TOPIC']
        if src_lang == target_lang or src_lang == 'und':
            topic_name = config['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()

/**
 * 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 value in the config.json file. The
 * function translates text using the Google Translate API.
 *
 * @param {object} event.data (Node 6) The Cloud Pub/Sub Message object.
 * @param {object} event (Node 8+) 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 = event => {
  const pubsubData = event.data.data || event.data;
  const jsonStr = Buffer.from(pubsubData, 'base64').toString();
  const payload = JSON.parse(jsonStr);

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

      console.log(`Translating text into ${payload.lang}`);
      return translate.translate(payload.text, payload.lang);
    })
    .then(([translation]) => {
      const messageData = {
        text: translation,
        filename: payload.filename,
        lang: payload.lang,
      };

      return publishResult(config.RESULT_TOPIC, messageData);
    })
    .then(() => {
      console.log(`Text translated to ${payload.lang}`);
    });
};

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 = config['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()

/**
 * 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 value in the config.json file. The
 * function saves the data packet to a file in GCS.
 *
 * @param {object} event.data (Node 6) The Cloud Pub/Sub Message object.
 * @param {object} event (Node 8+) 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 = event => {
  const pubsubData = event.data.data || event.data;
  const jsonStr = Buffer.from(pubsubData, 'base64').toString();
  const payload = JSON.parse(jsonStr);

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

      console.log(`Received request to save file ${payload.filename}`);

      const bucketName = config.RESULT_BUCKET;
      const filename = renameImageForSave(payload.filename, payload.lang);
      const file = storage.bucket(bucketName).file(filename);

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

      return file.save(payload.text);
    })
    .then(() => {
      console.log(`File saved.`);
    });
};

def save_result(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')
    lang = validate_message(message, 'lang')

    print('Received request to save file {}.'.format(filename))

    bucket_name = config['RESULT_BUCKET']
    result_filename = '{}_{}.txt'.format(filename, lang)
    bucket = storage_client.get_bucket(bucket_name)
    blob = bucket.blob(result_filename)

    print('Saving result to {} in bucket {}.'.format(result_filename,
                                                     bucket_name))

    blob.upload_from_string(text)

    print('File saved.')