From d27a7ec9d2b31de7ff1b7f0a42aa311b2950f29b Mon Sep 17 00:00:00 2001 From: TannedCung Date: Fri, 21 Jun 2024 10:48:02 +0700 Subject: [PATCH] Add: refill S3 image by redemption script --- .../migrate-datebase-fillup-images.py | 174 ++++++++++++++++++ 1 file changed, 174 insertions(+) create mode 100644 cope2n-api/fwd_api/management/commands/migrate-datebase-fillup-images.py diff --git a/cope2n-api/fwd_api/management/commands/migrate-datebase-fillup-images.py b/cope2n-api/fwd_api/management/commands/migrate-datebase-fillup-images.py new file mode 100644 index 0000000..bdcf633 --- /dev/null +++ b/cope2n-api/fwd_api/management/commands/migrate-datebase-fillup-images.py @@ -0,0 +1,174 @@ +from django.core.management.base import BaseCommand +from tqdm import tqdm +from fwd_api.models import SubscriptionRequestFile, SubscriptionRequest +from fwd_api.exception.exceptions import InvalidException +from fwd_api.utils.s3 import MinioS3Client + +import copy +import os +import glob +import traceback +import copy +import json +from django.utils import timezone + +IMAGE_DIRS = ["/external_data/SGGE", "/external_data/zipsGwp1", "/external_data/zipsGwp2", "/external_data/zipsGwp3", "/external_data/zipsGwp4", "/external_data/zipsEvoucher"] +# IMAGE_DIRS = ["/external_data/SGGE"] +image_extensions = ['*.jpg', '*.jpeg', '*.png', '*.gif'] +pdf_extensions = ['*.pdf'] + +class Command(BaseCommand): + help = 'Refactor database for image level' + + def add_arguments(self, parser): + # Add your command-line arguments here + parser.add_argument('start', type=str, help='start date, sample: 2023-01-02T00:00:00+0700') + parser.add_argument('end', type=str, help='end date, sample: 2023-01-03T00:00:00+0700') + + def _prepare_data(self, redemtion_dirs): + prepared_data = {} # {"redemption_id": {"image_paths": []}, "pages": 1} + for redemtion_dir in redemtion_dirs: + redemptions = os.listdir(redemtion_dir) + for redemption in redemptions: + files_in_dir = [] + for ext in image_extensions + pdf_extensions: + files_in_dir.extend(glob.glob(os.path.join(redemtion_dir, redemption, ext))) + redemption = redemption.replace("Data", "") + if prepared_data.get(redemption, None): + prepared_data[redemption]["image_paths"] += files_in_dir + prepared_data[redemption]["pages"] += len(files_in_dir) + else: + prepared_data[redemption] = {"image_paths": files_in_dir, "pages": len(files_in_dir)} + + return prepared_data + + def _add_error(self, result, error, redemption_id): + if not result.get("Error", None): + result["Error"] = {} + if result["Error"].get(error, None): + result["Error"][error].add(redemption_id) + else: + result["Error"][error] = set([redemption_id]) + + def _add_info(self, result, info, redemption_id): + if not result.get("Info", None): + result["Info"] = {} + if result["Info"].get(info, None): + result["Info"][info].add(redemption_id) + else: + result["Info"][info] = set([redemption_id]) + + def _add_warning(self, result, warn, redemption_id): + if not result.get("Warning", None): + result["Warning"] = {} + if result["Warning"].get(warn, None): + result["Warning"][warn].add(redemption_id) + else: + result["Warning"][warn] = set([redemption_id]) + + def _try_find_doc_type(self, file_paths): + doc_types = {"invoice": [], + "imei": [], + "undefined": []} + for file_path in file_paths: + if "invoice" in os.path.basename(file_path): + doc_types["invoice"].append(file_path) + elif "imei" in os.path.basename(file_path): + doc_types["imei"].append(file_path) + else: + doc_types["undefined"].append(file_path) + return doc_types + + def process_request(self, request, data, result, s3_client): + if not request.predict_result: + # self.stdout.write(self.style.WARNING(f"Key predict_result not found in {request.request_id}")) + return + if request.predict_result.get("status", 200) != 200: + # self.stdout.write(self.style.WARNING(f"Not a sucess request {request.request_id}")) + return + # Find to coresponding redemption_ID + self._add_info(result, "[OCR]: redemptions", request.redemption_id) + if request.redemption_id not in list(data.keys()): + self._add_error(result, "[OCR]: Not found redemption_ID", request.redemption_id) + return + if request.pages != data[request.redemption_id]["pages"]: + self._add_error(result, "[SBT]: Mismatch files number in a request", request.redemption_id) + return + + file_paths_by_doc_type = self._try_find_doc_type(data[request.redemption_id]["image_paths"]) + if len(file_paths_by_doc_type["undefined"]) > 0: + self._add_warning(result, "[SBT]: Undefined doc type", request.redemption_id) + + if len(request.request_id.split(".")[0].split("_")) < 2: + return + images = SubscriptionRequestFile.objects.filter(request=request, file_category="Origin") + + for i, image in enumerate(images): + if image.doc_type not in ["imei", "invoice"]: + self._add_error(result, "[OCR]: Weird doc type", request.redemption_id) + continue + try: + if len(file_paths_by_doc_type[image.doc_type]) > 0: + local_file_path = file_paths_by_doc_type[image.doc_type].pop(0) + else: + local_file_path = file_paths_by_doc_type["undefined"].pop(0) + predir = "sbt_invoice" + s3_key = os.path.join(predir, request.request_id, image.file_name) + # s3_client.upload_file(local_file_path, s3_key) + result['total'] += 1 + self._add_info(result, "[OCR]: Success", request.redemption_id) + except IndexError as e: + self._add_error(result, "[OCR]: Mismatch doc type", request.redemption_id) + continue + except Exception as e: + self.stdout.write(self.style.ERROR(f"Request: {request.request_id} failed with {e}")) + print(traceback.format_exc()) + result['failed'] += 1 + self._add_info(result, "[OCR]: Failed", request.redemption_id) + continue + data.pop(request.redemption_id, None) + + def handle(self, *args, **options): + start = options['start'] + end = options['end'] + result = {'total':0, + 'failed':0} + # TODO: redemption ID is not null on filter + if start or end: + try: + start_date = timezone.datetime.strptime(start, '%Y-%m-%dT%H:%M:%S%z') # We care only about day precision only + end_date = timezone.datetime.strptime(end, '%Y-%m-%dT%H:%M:%S%z') + except Exception as e: + print(f"[INFO]: start: {start}") + print(f"[INFO]: end: {end}") + raise InvalidException(excArgs="Date format") + subcription_iter = SubscriptionRequest.objects.filter(created_at__range=(start_date, end_date), redemption_id__isnull=False) + else: + subcription_iter = SubscriptionRequest.objects.filter(redemption_id__isnull=False) + print(f"[INFO]: Preparing data for filling up...") + prepared_data = self._prepare_data(IMAGE_DIRS) + print(f"[INFO]: Prepared data, total: {len(list(prepared_data.keys()))}") + prepared_data_copy = copy.deepcopy(prepared_data) + s3_client = MinioS3Client( + # endpoint='http://107.120.133.27:9884', + access_key='AKIA3AFPFVWZHTZHB6FW', + secret_key='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', + bucket_name='ocr-sds' + ) + # file = open("modified.txt", "w") + for request in tqdm(subcription_iter.iterator()): + self.process_request(request, prepared_data_copy, result, s3_client) + # file.close() + self.stdout.write(self.style.SUCCESS('Sample Django management command executed successfully! total/failed: {}/{}'.format(result['total'], result['failed']))) + # print(f"[INFO]: result: {result}") + for err in result.get("Error", []): + print("[INFO]: Error: {}: {}".format(err, len(result["Error"][err]))) + result["Error"][err] = list(result["Error"][err]) + for info in result.get("Info", []): + print("[INFO]: Info: {}: {}".format(info, len(result["Info"][info]))) + result["Info"][info] = list(result["Info"][info]) + for warn in result.get("Warning", []): + print("[INFO]: Warning: {}: {}".format(warn, len(result["Warning"][warn]))) + result["Warning"][warn] = list(result["Warning"][warn]) + with open("result.json", "w") as outfile: + json.dump(result, outfile) \ No newline at end of file