2023-11-30 11:19:06 +00:00
|
|
|
import io
|
|
|
|
import os
|
|
|
|
import traceback
|
2023-12-12 05:54:34 +00:00
|
|
|
import pathlib
|
2023-12-08 12:49:00 +00:00
|
|
|
import json
|
2023-11-30 11:19:06 +00:00
|
|
|
|
|
|
|
from PIL import Image, ExifTags
|
|
|
|
from django.core.files.uploadedfile import TemporaryUploadedFile
|
|
|
|
|
|
|
|
from fwd import settings
|
|
|
|
from fwd_api.constant.common import allowed_file_extensions
|
|
|
|
from fwd_api.exception.exceptions import GeneralException, RequiredFieldException, InvalidException, \
|
2024-01-09 12:41:17 +00:00
|
|
|
ServiceUnavailableException, FileFormatInvalidException, LimitReachedException, InvalidDecompressedSizeException, RequiredColumnException
|
2024-01-17 09:28:50 +00:00
|
|
|
from fwd_api.models import SubscriptionRequest, OcrTemplate, FeedbackRequest, SubscriptionRequestFile
|
2023-12-15 05:43:19 +00:00
|
|
|
from fwd_api.utils import process as ProcessUtil
|
|
|
|
from fwd_api.utils.crypto import image_authenticator
|
2023-12-12 05:54:34 +00:00
|
|
|
from fwd_api.utils.image import resize
|
2023-11-30 11:19:06 +00:00
|
|
|
from ..celery_worker.client_connector import c_connector
|
2023-12-11 13:15:48 +00:00
|
|
|
import imagesize
|
2024-01-09 12:41:17 +00:00
|
|
|
import csv
|
|
|
|
|
|
|
|
def validate_feedback_file(csv_file_path):
|
|
|
|
required_columns = ['redemptionNumber', 'requestId', 'imeiNumber', 'imeiNumber2', 'Purchase Date', 'retailer', 'Sold to party', 'timetakenmilli']
|
|
|
|
missing_columns = []
|
|
|
|
|
|
|
|
with open(csv_file_path, 'r') as file:
|
|
|
|
reader = csv.DictReader(file)
|
|
|
|
|
|
|
|
# Check if all required columns are present
|
|
|
|
for column in required_columns:
|
|
|
|
if column not in reader.fieldnames:
|
|
|
|
missing_columns.append(column)
|
|
|
|
|
|
|
|
if missing_columns:
|
|
|
|
raise RequiredColumnException(excArgs=str(missing_columns))
|
2023-11-30 11:19:06 +00:00
|
|
|
|
|
|
|
def validate_list_file(files, max_file_num=settings.MAX_UPLOAD_FILES_IN_A_REQUEST, min_file_num=1, file_field="files"):
|
|
|
|
total_file_size = 0
|
|
|
|
if len(files) < min_file_num:
|
|
|
|
raise RequiredFieldException(excArgs=file_field)
|
|
|
|
if len(files) > max_file_num:
|
|
|
|
raise LimitReachedException(excArgs=(f'Number of {file_field}', str(max_file_num), ''))
|
|
|
|
|
|
|
|
for f in files:
|
|
|
|
if not isinstance(f, TemporaryUploadedFile):
|
|
|
|
# print(f'[DEBUG]: {f.name}')
|
|
|
|
raise InvalidException(excArgs="files")
|
2023-12-05 05:59:06 +00:00
|
|
|
extension = f.name.split(".")[-1].lower() in allowed_file_extensions
|
2023-11-30 11:19:06 +00:00
|
|
|
if not extension or "." not in f.name:
|
2023-12-26 11:44:03 +00:00
|
|
|
raise FileFormatInvalidException(excArgs=list(allowed_file_extensions))
|
2023-11-30 11:19:06 +00:00
|
|
|
if f.size > settings.MAX_UPLOAD_SIZE_OF_A_FILE:
|
|
|
|
raise LimitReachedException(excArgs=('A file', str(settings.MAX_UPLOAD_SIZE_OF_A_FILE / 1024 / 1024), 'MB'))
|
|
|
|
total_file_size += f.size
|
|
|
|
if total_file_size > settings.MAX_UPLOAD_FILE_SIZE_OF_A_REQUEST:
|
|
|
|
raise LimitReachedException(excArgs=('Total size of all files', str(settings.MAX_UPLOAD_SIZE_OF_A_FILE / 1024 / 1024), 'MB'))
|
|
|
|
|
|
|
|
|
2024-01-09 12:41:17 +00:00
|
|
|
def validate_csv_feedback(files, max_file_num=1, min_file_num=1, file_field="csv files"):
|
|
|
|
total_file_size = 0
|
|
|
|
if len(files) < min_file_num:
|
|
|
|
raise RequiredFieldException(excArgs=file_field)
|
|
|
|
if len(files) > max_file_num:
|
|
|
|
raise LimitReachedException(excArgs=(f'Number of {file_field}', str(max_file_num), ''))
|
|
|
|
|
|
|
|
for f in files:
|
|
|
|
if not isinstance(f, TemporaryUploadedFile):
|
|
|
|
# print(f'[DEBUG]: {f.name}')
|
|
|
|
raise InvalidException(excArgs="files")
|
|
|
|
extension = f.name.split(".")[-1].lower() in ["csv"]
|
|
|
|
if not extension or "." not in f.name:
|
|
|
|
raise FileFormatInvalidException(excArgs=[".csv"])
|
|
|
|
if f.size > settings.MAX_UPLOAD_SIZE_OF_A_FILE:
|
|
|
|
raise LimitReachedException(excArgs=('A file', str(settings.MAX_UPLOAD_SIZE_OF_A_FILE / 1024 / 1024), 'MB'))
|
|
|
|
total_file_size += f.size
|
|
|
|
if total_file_size > settings.MAX_UPLOAD_FILE_SIZE_OF_A_REQUEST:
|
|
|
|
raise LimitReachedException(excArgs=('Total size of all files', str(settings.MAX_UPLOAD_SIZE_OF_A_FILE / 1024 / 1024), 'MB'))
|
|
|
|
|
2023-11-30 11:19:06 +00:00
|
|
|
def get_file(file_path: str):
|
|
|
|
try:
|
|
|
|
return open(file_path, 'rb')
|
|
|
|
except Exception as e:
|
|
|
|
print(e)
|
|
|
|
raise GeneralException("System")
|
|
|
|
|
|
|
|
|
|
|
|
def get_template_folder_path(tem: OcrTemplate):
|
|
|
|
tem_id = str(tem.id)
|
|
|
|
sub_id = str(tem.subscription.id)
|
|
|
|
user_id = str(tem.subscription.user.id)
|
|
|
|
return os.path.join(settings.MEDIA_ROOT, 'users', user_id, "subscriptions", sub_id, "templates", tem_id)
|
|
|
|
|
|
|
|
|
|
|
|
def get_folder_path(rq: SubscriptionRequest):
|
|
|
|
from celery.utils.log import get_task_logger
|
|
|
|
logger = get_task_logger(__name__)
|
|
|
|
|
|
|
|
request_id = str(rq.request_id)
|
|
|
|
logger.info(f"[DEBUG]: rq.process_type: {rq.process_type}")
|
|
|
|
p_type = ProcessUtil.map_process_type_to_folder_name(int(rq.process_type))
|
|
|
|
sub_id = str(rq.subscription.id)
|
|
|
|
user_id = str(rq.subscription.user.id)
|
|
|
|
|
|
|
|
return os.path.join(settings.MEDIA_ROOT, 'users', user_id, "subscriptions", sub_id, 'requests', p_type, request_id)
|
|
|
|
|
|
|
|
|
|
|
|
def save_byte_file(file_name: str, rq: SubscriptionRequest, file_bytes):
|
|
|
|
folder_path = get_folder_path(rq)
|
|
|
|
is_exist = os.path.exists(folder_path)
|
|
|
|
if not is_exist:
|
|
|
|
# Create a new directory because it does not exist
|
|
|
|
os.makedirs(folder_path)
|
|
|
|
file_path = os.path.join(folder_path, file_name)
|
|
|
|
with open(file_path, 'wb+') as w:
|
|
|
|
w.write(file_bytes)
|
|
|
|
|
|
|
|
return file_path
|
|
|
|
|
|
|
|
def save_file(file_name: str, rq: SubscriptionRequest, file: TemporaryUploadedFile):
|
|
|
|
folder_path = get_folder_path(rq)
|
|
|
|
is_exist = os.path.exists(folder_path)
|
|
|
|
if not is_exist:
|
|
|
|
# Create a new directory because it does not exist
|
|
|
|
os.makedirs(folder_path)
|
|
|
|
file_path = os.path.join(folder_path, file_name)
|
|
|
|
f = open(file_path, 'wb+')
|
|
|
|
|
|
|
|
for chunk in file.chunks():
|
|
|
|
f.write(chunk)
|
|
|
|
f.close()
|
|
|
|
|
|
|
|
return file_path
|
|
|
|
|
2023-12-08 12:49:00 +00:00
|
|
|
def save_json_file(file_name: str, rq: SubscriptionRequest, data: dict):
|
|
|
|
folder_path = get_folder_path(rq)
|
|
|
|
is_exist = os.path.exists(folder_path)
|
|
|
|
if not is_exist:
|
|
|
|
# Create a new directory because it does not exist
|
|
|
|
os.makedirs(folder_path)
|
|
|
|
file_path = os.path.join(folder_path, file_name)
|
|
|
|
with open(file_path, "w") as json_file:
|
|
|
|
json.dump(data, json_file)
|
|
|
|
return file_path
|
2023-11-30 11:19:06 +00:00
|
|
|
|
2024-01-09 12:41:17 +00:00
|
|
|
def save_feedback_file(file_name: str, rq: FeedbackRequest, uploaded_file: dict):
|
|
|
|
user_id = str(rq.subscription.user.id)
|
|
|
|
feedback_id = str(rq.id)
|
|
|
|
|
2024-01-17 09:28:50 +00:00
|
|
|
folder_path = os.path.join(settings.MEDIA_ROOT, 'users', user_id, "feedbacks", feedback_id)
|
2024-01-09 12:41:17 +00:00
|
|
|
os.makedirs(folder_path, exist_ok = True)
|
|
|
|
|
|
|
|
file_path = os.path.join(folder_path, file_name)
|
|
|
|
with uploaded_file.open() as file:
|
|
|
|
# Read the contents of the file
|
|
|
|
file_contents = file.read().decode('utf-8')
|
|
|
|
with open(file_path, 'w', newline='') as csvfile:
|
|
|
|
csvfile.write(file_contents)
|
|
|
|
return file_path
|
|
|
|
|
2023-11-30 11:19:06 +00:00
|
|
|
def delete_file_with_path(file_path: str) -> bool:
|
|
|
|
try:
|
|
|
|
os.remove(file_path)
|
|
|
|
return True
|
|
|
|
except Exception as e:
|
|
|
|
print(e)
|
|
|
|
return False
|
|
|
|
|
|
|
|
|
|
|
|
def save_template_file(file_name: str, rq: OcrTemplate, file: TemporaryUploadedFile, quality):
|
|
|
|
try:
|
|
|
|
folder_path = get_template_folder_path(rq)
|
|
|
|
is_exist = os.path.exists(folder_path)
|
|
|
|
if not is_exist:
|
|
|
|
# Create a new directory because it does not exist
|
|
|
|
os.makedirs(folder_path)
|
|
|
|
return save_file_with_path(file_name, file, quality, folder_path)
|
|
|
|
except Exception as e:
|
|
|
|
print(e)
|
|
|
|
raise ServiceUnavailableException()
|
|
|
|
|
2024-01-17 09:28:50 +00:00
|
|
|
def save_file_with_path(file_name: str, file: TemporaryUploadedFile, quality, folder_path: str):
|
2023-12-12 05:54:34 +00:00
|
|
|
try:
|
|
|
|
file_path = os.path.join(folder_path, file_name)
|
|
|
|
extension = file_name.split(".")[-1]
|
|
|
|
if extension.lower() == "pdf":
|
|
|
|
save_pdf(file_path, file)
|
|
|
|
else:
|
|
|
|
save_img(file_path, file, quality)
|
|
|
|
except InvalidDecompressedSizeException as e:
|
|
|
|
raise e
|
|
|
|
except Exception as e:
|
|
|
|
print(e)
|
|
|
|
raise ServiceUnavailableException()
|
|
|
|
return file_path
|
|
|
|
|
2023-11-30 11:19:06 +00:00
|
|
|
|
2024-01-17 09:28:50 +00:00
|
|
|
def resize_and_save_file(file_name: str, rq: SubscriptionRequest, file: TemporaryUploadedFile, quality: int):
|
2023-11-30 11:19:06 +00:00
|
|
|
try:
|
|
|
|
folder_path = get_folder_path(rq)
|
2023-12-12 05:54:34 +00:00
|
|
|
pathlib.Path(folder_path).mkdir(exist_ok=True, parents=True)
|
2024-01-17 09:28:50 +00:00
|
|
|
# request_file: SubscriptionRequestFile = SubscriptionRequestFile(
|
|
|
|
# file_name = file_name,
|
|
|
|
# file_path = os.path.join(folder_path, file_name),
|
|
|
|
# doc_type = doc_type,
|
|
|
|
# origin_name = file.name,
|
|
|
|
# request = rq,
|
|
|
|
# index_in_request= index_in_request
|
|
|
|
# )
|
|
|
|
# request_file.save()
|
2023-11-30 11:19:06 +00:00
|
|
|
return save_file_with_path(file_name, file, quality, folder_path)
|
2023-12-11 13:15:48 +00:00
|
|
|
except InvalidDecompressedSizeException as e:
|
|
|
|
raise e
|
2023-11-30 11:19:06 +00:00
|
|
|
except Exception as e:
|
|
|
|
print(f"[ERROR]: {e}")
|
|
|
|
raise ServiceUnavailableException()
|
|
|
|
|
2023-12-05 05:59:06 +00:00
|
|
|
def save_to_S3(file_name, rq, local_file_path):
|
2023-11-30 11:19:06 +00:00
|
|
|
try:
|
|
|
|
file_path = get_folder_path(rq)
|
2023-12-25 03:32:09 +00:00
|
|
|
request_id = rq.request_id
|
2023-11-30 11:19:06 +00:00
|
|
|
assert len(file_path.split("/")) >= 2, "file_path must have at least process type and request id"
|
|
|
|
s3_key = os.path.join(file_path.split("/")[-2], file_path.split("/")[-1], file_name)
|
2023-12-25 03:32:09 +00:00
|
|
|
c_connector.upload_file_to_s3((local_file_path, s3_key, request_id))
|
2023-12-25 11:48:50 +00:00
|
|
|
c_connector.remove_local_file((local_file_path, request_id))
|
2023-12-05 05:59:06 +00:00
|
|
|
return s3_key
|
2023-11-30 11:19:06 +00:00
|
|
|
except Exception as e:
|
|
|
|
print(f"[ERROR]: {e}")
|
|
|
|
raise ServiceUnavailableException()
|
|
|
|
|
2024-01-09 12:41:17 +00:00
|
|
|
def save_feedback_to_S3(file_name, id, local_file_path):
|
|
|
|
try:
|
2024-01-17 09:28:50 +00:00
|
|
|
# print(f"[DEBUG]: Uploading feedback to S3 with local path {local_file_path}, id: {id}, file_name: {file_name}")
|
|
|
|
assert len(local_file_path.split("/")) >= 3, "file_path must have at least feedback_folder and feedback_id"
|
|
|
|
# s3_key = os.path.join(local_file_path.split("/")[-3], local_file_path.split("/")[-2], file_name)
|
|
|
|
s3_key = os.path.join("feedback", local_file_path.split("/")[-2], file_name)
|
|
|
|
# print(f"[DEBUG]: Uploading feedback to S3 with s3_key {s3_key}")
|
2024-01-09 12:41:17 +00:00
|
|
|
c_connector.upload_feedback_to_s3((local_file_path, s3_key, id))
|
|
|
|
c_connector.remove_local_file((local_file_path, id))
|
|
|
|
return s3_key
|
|
|
|
except Exception as e:
|
|
|
|
print(f"[ERROR]: {e}")
|
|
|
|
raise ServiceUnavailableException()
|
|
|
|
|
2023-11-30 11:19:06 +00:00
|
|
|
def save_file_with_path(file_name: str, file: TemporaryUploadedFile, quality, folder_path):
|
|
|
|
try:
|
2023-12-12 11:51:32 +00:00
|
|
|
file_path = os.path.join(folder_path, file_name)
|
|
|
|
extension = file_name.split(".")[-1]
|
2023-11-30 11:19:06 +00:00
|
|
|
|
2023-12-12 11:51:32 +00:00
|
|
|
if extension in ['pdf', 'PDF']:
|
|
|
|
save_pdf(file_path, file)
|
|
|
|
else:
|
|
|
|
save_img(file_path, file, quality)
|
2023-12-11 13:15:48 +00:00
|
|
|
except InvalidDecompressedSizeException as e:
|
|
|
|
raise e
|
2023-11-30 11:19:06 +00:00
|
|
|
except Exception as e:
|
|
|
|
print(e)
|
|
|
|
raise ServiceUnavailableException()
|
|
|
|
return file_path
|
|
|
|
|
|
|
|
def save_pdf(file_path: str, file: TemporaryUploadedFile):
|
|
|
|
f = open(file_path, 'wb+')
|
|
|
|
for chunk in file.chunks():
|
|
|
|
f.write(chunk)
|
|
|
|
f.close()
|
|
|
|
|
|
|
|
|
|
|
|
def save_img(file_path: str, file: TemporaryUploadedFile, quality):
|
2023-12-11 13:15:48 +00:00
|
|
|
with open(file.temporary_file_path(), "rb") as fs:
|
|
|
|
input_file = io.BytesIO(fs.read())
|
|
|
|
width, height = imagesize.get(input_file)
|
|
|
|
if width > settings.MAX_PIXEL_IN_A_FILE or height > settings.MAX_PIXEL_IN_A_FILE:
|
|
|
|
raise InvalidDecompressedSizeException(excArgs=(str(width), str(height), str(settings.MAX_PIXEL_IN_A_FILE)))
|
|
|
|
|
2023-11-30 11:19:06 +00:00
|
|
|
with open(file.temporary_file_path(), "rb") as fs:
|
|
|
|
input_file = io.BytesIO(fs.read())
|
|
|
|
image = Image.open(input_file)
|
|
|
|
|
|
|
|
# read orient from metadata. WindowsPhoto keep the origin
|
|
|
|
for orientation in ExifTags.TAGS.keys():
|
|
|
|
if ExifTags.TAGS[orientation] == 'Orientation':
|
|
|
|
break
|
|
|
|
try:
|
|
|
|
e = image._getexif() # returns None if no EXIF data
|
|
|
|
if e:
|
|
|
|
exif = dict(e.items())
|
|
|
|
if orientation in exif:
|
|
|
|
orientation = exif[orientation]
|
|
|
|
if orientation == 3:
|
|
|
|
image = image.transpose(Image.ROTATE_180)
|
|
|
|
elif orientation == 6:
|
|
|
|
image = image.transpose(Image.ROTATE_270)
|
|
|
|
elif orientation == 8:
|
|
|
|
image = image.transpose(Image.ROTATE_90)
|
|
|
|
except Exception as ex:
|
|
|
|
print(ex)
|
|
|
|
print("Rotation Error")
|
|
|
|
traceback.print_exc()
|
2023-12-12 05:54:34 +00:00
|
|
|
|
|
|
|
image = resize(image, max_w=settings.TARGET_MAX_IMAGE_SIZE[0], max_h=settings.TARGET_MAX_IMAGE_SIZE[1])
|
|
|
|
image = image.convert('RGB')
|
|
|
|
image.save(file_path, optimize=True, quality=quality)
|
2023-11-30 11:19:06 +00:00
|
|
|
|
|
|
|
def build_media_url(folder: str, uid: str, file_name: str = None) -> str:
|
|
|
|
token = image_authenticator.generate_img_token()
|
|
|
|
if not file_name:
|
|
|
|
return '{base_url}/api/ctel/media/{folder}/{uid}/?token={token}'.format(folder=folder, uid=uid,
|
|
|
|
base_url=settings.BASE_URL,
|
|
|
|
token=token)
|
|
|
|
return '{base_url}/api/ctel/media/{folder}/{uid}/?file_name={file_name}&token={token}'.format(folder=folder,
|
|
|
|
uid=uid,
|
|
|
|
file_name=file_name,
|
|
|
|
base_url=settings.BASE_URL,
|
|
|
|
token=token)
|
|
|
|
|
|
|
|
|
|
|
|
def build_url(folder: str, data_id: str, user_id: int, file_name: str = None) -> str:
|
|
|
|
token = image_authenticator.generate_img_token(user_id)
|
|
|
|
if not file_name:
|
|
|
|
return '{base_url}/api/ctel/media/{folder}/{uid}/?token={token}'.format(folder=folder, uid=data_id,
|
|
|
|
base_url=settings.BASE_URL,
|
|
|
|
token=token)
|
|
|
|
return '{base_url}/api/ctel/media/{folder}/{uid}/?file_name={file_name}&token={token}'.format(folder=folder,
|
|
|
|
uid=data_id,
|
|
|
|
file_name=file_name,
|
|
|
|
base_url=settings.BASE_URL,
|
|
|
|
token=token)
|
|
|
|
def build_media_url_v2(media_id: str, user_id: int, sub_id: int, u_sync_id: str) -> str:
|
|
|
|
token = image_authenticator.generate_img_token_v2(user_id, sub_id, u_sync_id)
|
|
|
|
return f'{settings.BASE_URL}/api/ctel/v2/media/request/{media_id}/?token={token}'
|