Merge branch 'feature/CHINARPA-3529'

冯轩
Showing 3 changed files with 109 additions and 20 deletions
src/apps/doc/management/commands/ocr_process.py
src/apps/doc/views.py
src/common/mixins.py
--- a/src/apps/doc/management/commands/ocr_process.py
View file @8f4c320
+++ b/src/apps/doc/management/commands/ocr_process.py
View file @8f4c320
@@ -1458,15 +1458,20 @@ class Command(BaseCommand, LoggerMixin):
                        # pdf下载 处理 图片存储 识别
                        for times in range(consts.RETRY_TIMES):
                            try:
-                                self.edms.download(pdf_path, doc.metadata_version_id, doc.document_scheme, business_type)
+                                if doc.application_id.startswith(consts.FIXED_APPLICATION_ID_PREFIX):
-                                self.online_log.info('{0} [edms download success] [task={1}] [times={2}] '
+                                    self.online_log.info('{0} [mo ni xia dan] [task={1}] [times={2}] '
-                                                     '[pdf_path={3}]'.format(self.e_log_base, task_str, times, pdf_path))
+                                                         '[pdf_path={3}]'.format(self.log_base, task_str,
+                                                                                 times, pdf_path))
-                                self.online_log.info('{0} [pdf to img start] [task={1}] [times={2}]'.format(
+                                else:
-                                    self.e_log_base, task_str, times))
+                                    self.edms.download(pdf_path, doc.metadata_version_id, doc.document_scheme, business_type)
-                                pdf_handler.e_contract_process()
+                                    self.online_log.info('{0} [edms download success] [task={1}] [times={2}] '
-                                self.online_log.info(
+                                                        '[pdf_path={3}]'.format(self.e_log_base, task_str, times, pdf_path))
-                                    '{0} [pdf to img end] [task={1}] [times={2}]'.format(self.e_log_base, task_str, times))
+                                    self.online_log.info('{0} [pdf to img start] [task={1}] [times={2}]'.format(
+                                        self.e_log_base, task_str, times))
+                                    pdf_handler.e_contract_process()
+                                    self.online_log.info(
+                                        '{0} [pdf to img end] [task={1}] [times={2}]'.format(self.e_log_base, task_str, times))
                            except Exception as e:
                                self.online_log.warn('{0} [download or pdf to img failed] [task={1}] [times={2}] '
                                                     '[error={3}]'.format(self.e_log_base, task_str, times,
@@ -1973,7 +1978,7 @@ class Command(BaseCommand, LoggerMixin):
                                        self.log_base, task_str, traceback.format_exc()))
                                else:
                                    self.online_log.info('{0} [process complete] [task={1}]'.format(self.log_base, task_str))
-                                    os.remove(excel_path)
+                                    # os.remove(excel_path)
                                # report新增流水真伪
                                try:
--- a/src/apps/doc/views.py
View file @8f4c320
+++ b/src/apps/doc/views.py
View file @8f4c320
@@ -17,7 +17,7 @@ from webargs import fields, validate
 from webargs.djangoparser import use_args, parser
 from settings import conf
 from common import response
-from common.mixins import GenericView
+from common.mixins import GenericView,DocGenericView
 from common.tools.file_tools import file_write
 from common.redis_cache import redis_handler as rh
 from .models import (
@@ -360,6 +360,10 @@ compare_result_args = {
 upload_pdf_args = {
    'pdf_file': fields.Raw(required=True),
+    'business_type': fields.Str(required=True),
+    'document_scheme': fields.Str(required=True),
+    'data_source': fields.Str(required=True),
+    'document_name': fields.Str(required=True),
 }
 application_information = {
@@ -1035,7 +1039,7 @@ class CompareOfflineView(GenericView):
        '''
-class DocView(GenericView, DocHandler):
+class DocView(DocGenericView, DocHandler):
    # 文件列表页
    @use_args(doc_list_args, location='querystring')
@@ -1079,6 +1083,8 @@ class DocView(GenericView, DocHandler):
            application_link = '{0}/showList/showList?entity={1}&scheme={2}&case_id={3}'.format(
                conf.BASE_URL, prefix, tmp_scheme, doc_dict['application_id'])
            doc_dict['target_url'] = application_link
+            doc_id = doc_dict.get('id')
+            doc_dict['excel_link'] = self.get_link(doc_id, business_type, file='excel')
        # total = len(doc_list)
        pagination = {'current': page, 'total': total, 'page_size': page_size}
@@ -1092,18 +1098,23 @@ class DocView(GenericView, DocHandler):
        return response.ok(data=res)
    # 上传pdf，模拟下单
-    @use_args(upload_pdf_args, location='files')
+    # @use_args(upload_pdf_args)
-    def post(self, request, args):
+    def post(self, request):
        random_int = random.randint(0, consts.TIME_NUM)
        metadata_version_id = str(int(time.time()) - random_int)
-        pdf_file = args.get('pdf_file')
+        pdf_file = request.FILES.get('pdf_file')
        if isinstance(pdf_file.name, str):
            if not pdf_file.name.endswith('pdf') and not pdf_file.name.endswith('PDF'):
                self.invalid_params(msg='invalid params: not a PDF file')
+        business_type = request.POST.get('business_type', '')
+        document_scheme = request.POST.get('document_scheme', '')
+        data_source = request.POST.get('data_source', '')
+        document_name = request.POST.get('document_name', '')
+        args = {'business_type':business_type,'document_scheme':document_scheme,'data_source':data_source,'document_name':document_name,'pdf_file':pdf_file}
        # business_type = random.choice(consts.BUSINESS_TYPE_LIST)
-        business_type = consts.BUSINESS_TYPE_LIST[0]
+        # business_type = consts.BUSINESS_TYPE_LIST[0]
        tmp_save_path = os.path.join(conf.DATA_DIR, business_type, '{0}.pdf'.format(metadata_version_id))
        file_write(pdf_file, tmp_save_path)
@@ -1126,8 +1137,8 @@ class DocView(GenericView, DocHandler):
        application_id = '{0}{1}'.format(consts.FIXED_APPLICATION_ID_PREFIX, metadata_version_id)
        upload_finish_time = timezone.now()
        # document_scheme = random.choice(consts.DOC_SCHEME_LIST)
-        document_scheme = consts.DOC_SCHEME_LIST[1]
+        # document_scheme = consts.DOC_SCHEME_LIST[1]
-        data_source = random.choice(consts.DATA_SOURCE_LIST)
+        # data_source = random.choice(consts.DATA_SOURCE_LIST)
        # UploadDocRecords.objects.create(
        #     metadata_version_id=metadata_version_id,
        #     application_id=application_id,
@@ -1166,8 +1177,25 @@ class DocView(GenericView, DocHandler):
        # 4. 选择队列进入
        is_priority = False
-        tasks = ['{0}{1}{2}'.format(prefix, consts.SPLIT_STR, doc.id)]
-        enqueue_res = rh.enqueue(tasks, is_priority)
+        classify_1 = 0
+        # 电子合同 Econtract or OVP(FSM)
+        if data_source == consts.DATA_SOURCE_LIST[2] or data_source == consts.DATA_SOURCE_LIST[3]:  
+            if document_scheme == consts.DOC_SCHEME_LIST[1]:
+                for keyword, classify_1_tmp in consts.ECONTRACT_KEYWORDS_MAP.get(prefix):
+                    if keyword in document_name:
+                        classify_1 = classify_1_tmp
+                        break
+        # FSM合同：WEP/MSI/SC
+        elif data_source == consts.DATA_SOURCE_LIST[0] and document_scheme == consts.DOC_SCHEME_LIST[0]:
+            for keyword, classify_1_tmp in consts.FSM_ECONTRACT_KEYWORDS_MAP.get(prefix):
+                if keyword in document_name:
+                    classify_1 = classify_1_tmp
+                    break 
+        # tasks = ['{0}{1}{2}'.format(prefix, consts.SPLIT_STR, doc.id)]
+        task = consts.SPLIT_STR.join([prefix, str(doc.id), str(classify_1)])
+        enqueue_res = rh.enqueue([task], is_priority)
        self.running_log.info('[mock doc upload success] [args={0}] [business_type={1}] [doc_id={2}] '
                              '[is_priority={3}] [enqueue_res={4}]'.format(args, prefix, doc.id,
--- a/src/common/mixins.py
View file @8f4c320
+++ b/src/common/mixins.py
View file @8f4c320
@@ -104,6 +104,62 @@ class GenericView(LoggerMixin, GenericExceptionMixin, GenericAPIView):
    def get_object(self):
        return None
+class DocGenericView(LoggerMixin, GenericExceptionMixin, GenericAPIView):
+    need_print_logger = True
+    def print_logger(self, request):
+        # parameters = getattr(request, request.method, {})
+        parameters = None
+        if not parameters:
+            parameters = getattr(request, 'data', {})
+        if not parameters:
+            parameters = {}
+        parameters_string = ''
+        for key, value in parameters.items():
+            parameters_string += '[%s=%s] ' % (key, value)
+        for key, value in self.kwargs.items():
+            parameters_string += '[%s=%s] ' % (key, value)
+        if request.user and not isinstance(request.user, AnonymousUser):
+            user_id = request.user.id
+        else:
+            user_id = 0
+        self.running_log.info('[%s_%s_request] with parameters [user_id=%s] %s'
+                              % (self.__class__.__name__, request.method,
+                                 user_id, parameters_string))
+    def dispatch(self, request, *args, **kwargs):
+        """
+        `.dispatch()` is pretty much the same as Django's regular dispatch,
+        but with extra hooks for startup, finalize, and exception handling.
+        """
+        self.args = args
+        self.kwargs = kwargs
+        request = self.initialize_request(request, *args, **kwargs)
+        self.request = request
+        self.headers = self.default_response_headers  # deprecate?
+        try:
+            self.initial(request, *args, **kwargs)
+            # Get the appropriate handler method
+            if request.method.lower() in self.http_method_names:
+                handler = getattr(self, request.method.lower(),
+                                  self.http_method_not_allowed)
+            else:
+                handler = self.http_method_not_allowed
+            if self.need_print_logger:
+                self.print_logger(request)
+            response = handler(request, *args, **kwargs)
+        except Exception as exc:
+            response = self.handle_exception(exc)
+        self.response = self.finalize_response(
+            request, response, *args, **kwargs)
+        return self.response
+    def get_object(self):
+        return None
 class IWABaseView: