89 lines
2.8 KiB
Python
89 lines
2.8 KiB
Python
|
from flask_restx import Namespace, Resource, fields
|
||
|
|
from flask import request, jsonify, current_app as app, send_file
|
||
|
|
from ...services.ocr import OCRService
|
||
|
|
from ...utils.decorators.auth import protected_route
|
||
|
|
from .models.errors import error_404, error_500
|
||
|
|
from .models.response import response
|
||
|
|
import json
|
||
|
|
import os
|
||
|
|
import numpy as np
|
||
|
|
from werkzeug.datastructures import FileStorage
|
||
|
|
|
||
|
|
api = Namespace('OCR',
|
||
|
|
description='Description',
|
||
|
|
path='/v2/api/tools/ocr')
|
||
|
|
|
||
|
|
upload_parser = api.parser()
|
||
|
|
upload_parser.add_argument('file', location='files',
|
||
|
|
type=FileStorage, required=True)
|
||
|
|
# OCR Data Model
|
||
|
|
ocr_model = api.model('OCR', {
|
||
|
|
'format': fields.String(required=True),
|
||
|
|
'data': fields.String(required=False),
|
||
|
|
|
||
|
|
})
|
||
|
|
|
||
|
|
success_response = api.clone('OCR Model Response', response, {
|
||
|
|
'model': fields.Nested(ocr_model)
|
||
|
|
})
|
||
|
|
|
||
|
|
|
||
|
|
@api.route('')
|
||
|
|
@api.doc(security='apikey')
|
||
|
|
class OCRResource(Resource):
|
||
|
|
@api.doc('get_text')
|
||
|
|
@api.expect(upload_parser)
|
||
|
|
@protected_route
|
||
|
|
def post(self):
|
||
|
|
output_format = request.get_json().get('format')
|
||
|
|
|
||
|
|
if not output_format:
|
||
|
|
output_format = 'txt'
|
||
|
|
|
||
|
|
args = upload_parser.parse_args()
|
||
|
|
|
||
|
|
try:
|
||
|
|
if 'file' not in args:
|
||
|
|
raise ValueError("Invalid file")
|
||
|
|
|
||
|
|
file = args['file']
|
||
|
|
|
||
|
|
if file.filename == '':
|
||
|
|
raise ValueError("Invalid file")
|
||
|
|
|
||
|
|
if file:
|
||
|
|
# Save the uploaded file to the UPLOAD_FOLDER
|
||
|
|
filename = os.path.join(file.filename)
|
||
|
|
file.save(filename)
|
||
|
|
ocr_service = OCRService(image_directory='',
|
||
|
|
export_directory=os.path.join(app.config['UPLOAD_FOLDER']),
|
||
|
|
language='en')
|
||
|
|
output_format = 'text'
|
||
|
|
result = ocr_service.read_text(filename, output_format=output_format)
|
||
|
|
if output_format == 'text':
|
||
|
|
txt_file, message = result
|
||
|
|
if txt_file:
|
||
|
|
|
||
|
|
return send_file(os.path.join("..",'..','..', txt_file), mimetype='text/plain', as_attachment=True, download_name=txt_file)
|
||
|
|
else:
|
||
|
|
return jsonify(error=message)
|
||
|
|
|
||
|
|
elif output_format == 'json':
|
||
|
|
json_data, message = result
|
||
|
|
if json_data:
|
||
|
|
result_json = json.dumps(json_data, default=np_encoder)
|
||
|
|
return {'model': {
|
||
|
|
'format': output_format,
|
||
|
|
'data': result_json
|
||
|
|
}}
|
||
|
|
api.abort(code=500, message="Invalid Format", error=True)
|
||
|
|
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
api.abort(code=500, message="Something went wrong", error=True)
|
||
|
|
|
||
|
|
|
||
|
|
def np_encoder(object):
|
||
|
|
if isinstance(object, np.generic):
|
||
|
|
return object.item()
|