From b8e37068f60f40b22a2fabb01c5864aaab569212 Mon Sep 17 00:00:00 2001
From: PhanThanhTrung <pt.trung2@samsung.com>
Date: Mon, 11 Mar 2024 16:35:27 +0700
Subject: [PATCH] update index_in_request with doc_type
---
.../fwd_api/celery_worker/internal_task.py | 5 +-
.../celery_worker/process_result_tasks.py | 63 +++++++++----------
2 files changed, 33 insertions(+), 35 deletions(-)
diff --git a/cope2n-api/fwd_api/celery_worker/internal_task.py b/cope2n-api/fwd_api/celery_worker/internal_task.py
index 36523f5..f098d1a 100755
--- a/cope2n-api/fwd_api/celery_worker/internal_task.py
+++ b/cope2n-api/fwd_api/celery_worker/internal_task.py
@@ -193,11 +193,13 @@ def process_pdf(rq_id, sub_id, p_type, user_id, files):
raise FileContentInvalidException
for j in range(len(_b_urls)):
_b_urls[j]["doc_type"] = file["file_type"]
- _b_urls[j]["page_number"] = idx
+ _b_urls[j]["page_number"] = idx
+ _b_urls[j]["index_to_image_type"] = file["index_in_request"]
return idx, _b_urls[0]
elif extension in image_extensions:
this_url = ProcessUtil.process_image_local_file(file["file_name"], file["file_path"], new_request, user, file["file_type"], file["index_in_request"])[0]
this_url["page_number"] = idx
+ this_url["index_to_image_type"] = file["index_in_request"]
if file["file_type"]:
this_url["doc_type"] = file["file_type"]
return idx, this_url
@@ -222,6 +224,7 @@ def process_pdf(rq_id, sub_id, p_type, user_id, files):
file_meta["ai_inference_profile"] = {}
file_meta["index_in_request"] = i
file_meta["preprocessing_time"] = preprocessing_time
+ file_meta["index_to_image_type"] = b_url["index_to_image_type"]
to_queue.append((fractorized_request_id, sub_id, [b_url], user_id, p_type, file_meta))
# Send to next queue
diff --git a/cope2n-api/fwd_api/celery_worker/process_result_tasks.py b/cope2n-api/fwd_api/celery_worker/process_result_tasks.py
index 7cb8e72..28bd789 100755
--- a/cope2n-api/fwd_api/celery_worker/process_result_tasks.py
+++ b/cope2n-api/fwd_api/celery_worker/process_result_tasks.py
@@ -147,8 +147,11 @@ def process_invoice_sbt_result(rq_id, result, metadata):
rq_id = rq_id.split("_sub_")[0]
rq: SubscriptionRequest = SubscriptionRequest.objects.filter(request_id=rq_id).first()
+ image_type = metadata["doc_type"]
+ index_in_request = metadata.pop("index_to_image_type", 0)
result["metadata"] = metadata
- # status = to_status(result)
+ _update_subscription_rq_file(request_id=rq, index_in_request=index_in_request, doc_type=image_type, result=result)
+
status = result.get("status", 200)
redis_client.set_cache(rq_id, page_index, result)
done = rq.pages == redis_client.get_size(rq_id)
@@ -174,56 +177,48 @@ def process_invoice_sbt_result(rq_id, result, metadata):
rq.status = 404 # stop waiting
rq.predict_result = result
rq.save()
- _update_subscription_rq_file(request_id=rq_id)
update_user(rq)
except IndexError as e:
print(e)
print("NotFound request by requestId, %d", rq_id)
rq.ai_inference_time = 0
rq.save()
- _update_subscription_rq_file(request_id=rq_id)
except Exception as e:
print(e)
print("Fail Invoice %d", rq_id)
traceback.print_exc()
rq.ai_inference_time = 0
rq.save()
- _update_subscription_rq_file(request_id=rq_id)
return "FailInvoice"
-def _update_subscription_rq_file(request_id):
- sub_rqs = SubscriptionRequest.objects.filter(request_id=request_id).first()
- result = sub_rqs.predict_result
- if result is None:
- return
+def _update_subscription_rq_file(request_id, index_in_request, doc_type, result):
+ image = SubscriptionRequestFile.objects.filter(request=request_id, index_in_request=index_in_request, doc_type=doc_type).first()
- files = SubscriptionRequestFile.objects.filter(request=sub_rqs)
- for image in files:
- retailer_name = None
- sold_to_party = None
- purchase_date = []
- imei_number = []
- predicted_res = __get_actual_predict_result(result=result)
- if len(predicted_res)!=0:
- for elem in predicted_res:
- if elem["label"] == "retailername":
- retailer_name = elem['value']
- elif elem["label"] == "sold_to_party":
- sold_to_party = elem['value']
- elif elem["label"] == "purchase_date":
- purchase_date=elem['value']
- else:
- imei_number=elem['value']
+ retailer_name = None
+ sold_to_party = None
+ purchase_date = []
+ imei_number = []
+ predicted_res = __get_actual_predict_result(result=result)
+ if len(predicted_res)!=0:
+ for elem in predicted_res:
+ if elem["label"] == "retailername":
+ retailer_name = elem['value']
+ elif elem["label"] == "sold_to_party":
+ sold_to_party = elem['value']
+ elif elem["label"] == "purchase_date":
+ purchase_date = elem['value']
+ else:
+ imei_number = elem['value']
- _predict_result = {
- "retailername": retailer_name,
- "sold_to_party": sold_to_party,
- "purchase_date": purchase_date,
- "imei_number": imei_number
- }
- image.predict_result = _predict_result
- image.save()
+ _predict_result = {
+ "retailername": retailer_name,
+ "sold_to_party": sold_to_party,
+ "purchase_date": purchase_date,
+ "imei_number": imei_number
+ }
+ image.predict_result = _predict_result
+ image.save()
def __get_actual_predict_result(result: dict):
predicted_res = result.get('content', {}).get('document', [])