Skip to content

周伟奇 / bmw-ocr

Go to a project
Toggle navigation
Toggle navigation pinning
9b2170ec by 周伟奇
Options

prune

1 parent 3ff06858
Inline Side-by-side
Showing 3 changed files with 79 additions and 79 deletions
src/apps/doc/management/commands/ocr_process.py
......@@ -837,7 +837,7 @@ class Command(BaseCommand, LoggerMixin):
# 重构Excel文件
# src_excel_path = os.path.join(doc_data_path, 'src.xlsx')
# wb.save(src_excel_path)
count_list = wb.rebuild(merged_bs_summary, license_summary, res_list, doc.document_scheme)
wb.rebuild(merged_bs_summary, license_summary, res_list, doc.document_scheme)
wb.save(excel_path)
except Exception as e:
......@@ -878,9 +878,9 @@ class Command(BaseCommand, LoggerMixin):
try:
doc.end_time = timezone.now()
doc.duration = min((doc.end_time - doc.start_time).seconds, 32760)
for field, count in count_list:
if hasattr(doc, field):
setattr(doc, field, count)
# for field, count in count_list:
# if hasattr(doc, field):
# setattr(doc, field, count)
doc.save()
except Exception as e:
self.online_log.error('{0} [process error (db save)] [task={1}] [error={2}]'.format(
......
src/apps/doc/ocr/wb.py
......@@ -633,12 +633,12 @@ class BSWorkbook(Workbook):
for sheet in sheets_list:
self.remove(self.get_sheet_by_name(sheet))
def license_rebuild(self, license_summary, document_scheme, count_list):
for classify, (_, name, field_order, side_diff, scheme_diff, field_str) in consts.LICENSE_ORDER:
def license_rebuild(self, license_summary, document_scheme):
for classify, (_, name, field_order, side_diff, scheme_diff, _) in consts.LICENSE_ORDER:
license_list = license_summary.get(classify)
if not license_list:
continue
count = 0
# count = 0
ws = self.create_sheet(name)
if scheme_diff and document_scheme == consts.DOC_SCHEME_LIST[1]:
classify = consts.MVC_CLASSIFY_SE
......@@ -653,8 +653,8 @@ class BSWorkbook(Workbook):
else:
ws.append((write_field, field_value))
ws.append((None, ))
count += 1
count_list.append((field_str, count))
# count += 1
# count_list.append((field_str, count))
def simple_license_rebuild(self, license_summary, document_scheme):
# for ic_license_dict in license_summary.get(consts.IC_CLASSIFY, []):
......@@ -708,13 +708,13 @@ class BSWorkbook(Workbook):
self.remove(self.get_sheet_by_name('Sheet'))
def rebuild(self, bs_summary, license_summary, res_list, document_scheme):
count_list = [(consts.MODEL_FIELD_BS, len(self.sheetnames) - 1)]
# count_list = [(consts.MODEL_FIELD_BS, len(self.sheetnames) - 1)]
if document_scheme == consts.DOC_SCHEME_LIST[1]:
self.license_rebuild(license_summary, document_scheme, count_list)
self.license_rebuild(license_summary, document_scheme)
self.bs_rebuild(bs_summary)
else:
self.bs_rebuild(bs_summary)
self.license_rebuild(license_summary, document_scheme, count_list)
self.license_rebuild(license_summary, document_scheme)
self.res_sheet(res_list)
self.remove_base_sheet()
return count_list
# return count_list
......
src/apps/doc/views.py
......@@ -16,7 +16,7 @@ from common import response
from common.mixins import GenericView
from common.tools.file_tools import file_write
from common.redis_cache import redis_handler as rh
from .models import UploadDocRecords, DocStatus, PriorityApplication, GCAPRecords, AFCComparisonInfo, HILComparisonInfo
from .models import DocStatus, PriorityApplication, GCAPRecords, AFCComparisonInfo, HILComparisonInfo
from .mixins import DocHandler
from . import consts
from apps.account.authentication import OAuth2AuthenticationWithUser
......@@ -288,64 +288,64 @@ class UploadDocView(GenericView, DocHandler):
@use_args(doc_upload_args, location='data')
def post(self, request, args):
application_data = args.get('applicationData')
applicant_data = args.get('applicantData')
# applicant_data = args.get('applicantData')
document = args.get('document')
business_type = document.get('businessType')
application_id = application_data.get('applicationId')
document_scheme = document.get('documentScheme')
data_source = document.get('dataSource')
document_name = document.get('documentName')
main_name = self.get_name(applicant_data, 'mainApplicantName', 16)
co_name = self.get_name(applicant_data, 'coApplicantName', 16)
g1_name = self.get_name(applicant_data, 'guarantor1Name', 16)
g2_name = self.get_name(applicant_data, 'guarantor2Name', 16)
try:
# 1. 上传信息记录
UploadDocRecords.objects.create(
metadata_version_id=document.get('metadataVersionId'),
application_id=application_id,
main_applicant=main_name,
co_applicant=co_name,
guarantor_1=g1_name,
guarantor_2=g2_name,
document_name=document_name,
document_scheme=document_scheme,
business_type=business_type,
data_source=data_source,
upload_finish_time=document.get('uploadFinishTime'),
)
except IntegrityError as e:
self.running_log.info('[doc upload fail] [args={0}] [err={1}]'.format(args, e))
self.invalid_params(msg='metadataVersionId repeat')
else:
data_source = self.fix_data_source(data_source)
if data_source == consts.DATA_SOURCE_LIST[1]:
if isinstance(document_name, str):
if document_name.endswith('-证书.pdf') or document_name.endswith('-证书'):
self.running_log.info('[doc upload success] [eapp license skip] [args={0}]'.format(args))
return response.ok()
# 2. 根据业务类型分库存储
doc_class, prefix = self.get_doc_class(business_type)
doc = doc_class.objects.create(
metadata_version_id=document.get('metadataVersionId'),
application_id=application_id,
# main_applicant=applicant_data.get('mainApplicantName'),
# co_applicant=applicant_data.get('coApplicantName'),
# guarantor_1=applicant_data.get('guarantor1Name'),
# guarantor_2=applicant_data.get('guarantor2Name'),
document_name=document.get('documentName'),
document_scheme=self.fix_scheme(document_scheme),
data_source=self.fix_data_source(data_source),
upload_finish_time=document.get('uploadFinishTime'),
)
# 3. 选择队列进入
is_priority = PriorityApplication.objects.filter(application_id=application_id, on_off=True).exists()
tasks = ['{0}{1}{2}'.format(prefix, consts.SPLIT_STR, doc.id)]
enqueue_res = rh.enqueue(tasks, is_priority)
self.running_log.info('[doc upload success] [args={0}] [business_type={1}] [doc_id={2}] '
'[is_priority={3}] [enqueue_res={4}]'.format(args, prefix, doc.id,
is_priority, enqueue_res))
return response.ok()
# main_name = self.get_name(applicant_data, 'mainApplicantName', 16)
# co_name = self.get_name(applicant_data, 'coApplicantName', 16)
# g1_name = self.get_name(applicant_data, 'guarantor1Name', 16)
# g2_name = self.get_name(applicant_data, 'guarantor2Name', 16)
# try:
# # 1. 上传信息记录
# UploadDocRecords.objects.create(
# metadata_version_id=document.get('metadataVersionId'),
# application_id=application_id,
# main_applicant=main_name,
# co_applicant=co_name,
# guarantor_1=g1_name,
# guarantor_2=g2_name,
# document_name=document_name,
# document_scheme=document_scheme,
# business_type=business_type,
# data_source=data_source,
# upload_finish_time=document.get('uploadFinishTime'),
# )
# except IntegrityError as e:
# self.running_log.info('[doc upload fail] [args={0}] [err={1}]'.format(args, e))
# self.invalid_params(msg='metadataVersionId repeat')
# else:
data_source = self.fix_data_source(data_source)
if data_source == consts.DATA_SOURCE_LIST[1]:
if isinstance(document_name, str):
if document_name.endswith('-证书.pdf') or document_name.endswith('-证书'):
self.running_log.info('[doc upload success] [eapp license skip] [args={0}]'.format(args))
return response.ok()
# 2. 根据业务类型分库存储
doc_class, prefix = self.get_doc_class(business_type)
doc = doc_class.objects.create(
metadata_version_id=document.get('metadataVersionId'),
application_id=application_id,
# main_applicant=applicant_data.get('mainApplicantName'),
# co_applicant=applicant_data.get('coApplicantName'),
# guarantor_1=applicant_data.get('guarantor1Name'),
# guarantor_2=applicant_data.get('guarantor2Name'),
document_name=document.get('documentName'),
document_scheme=self.fix_scheme(document_scheme),
data_source=self.fix_data_source(data_source),
upload_finish_time=document.get('uploadFinishTime'),
)
# 3. 选择队列进入
is_priority = PriorityApplication.objects.filter(application_id=application_id, on_off=True).exists()
tasks = ['{0}{1}{2}'.format(prefix, consts.SPLIT_STR, doc.id)]
enqueue_res = rh.enqueue(tasks, is_priority)
self.running_log.info('[doc upload success] [args={0}] [business_type={1}] [doc_id={2}] '
'[is_priority={3}] [enqueue_res={4}]'.format(args, prefix, doc.id,
is_priority, enqueue_res))
return response.ok()
post.openapi_doc = '''
tags: [doc]
......@@ -590,19 +590,19 @@ class DocView(GenericView, DocHandler):
upload_finish_time = timezone.now()
document_scheme = random.choice(consts.DOC_SCHEME_LIST)
data_source = random.choice(consts.DATA_SOURCE_LIST)
UploadDocRecords.objects.create(
metadata_version_id=metadata_version_id,
application_id=application_id,
main_applicant='',
co_applicant='',
guarantor_1='',
guarantor_2='',
document_name=application_id,
document_scheme=document_scheme,
business_type=business_type,
data_source=data_source,
upload_finish_time=upload_finish_time,
)
# UploadDocRecords.objects.create(
# metadata_version_id=metadata_version_id,
# application_id=application_id,
# main_applicant='',
# co_applicant='',
# guarantor_1='',
# guarantor_2='',
# document_name=application_id,
# document_scheme=document_scheme,
# business_type=business_type,
# data_source=data_source,
# upload_finish_time=upload_finish_time,
# )
# 2. 根据业务类型分库存储
doc_class, prefix = self.get_doc_class(business_type)
......
Styling with Markdown is supported
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!