Merge branch 'feature/fsm-contract' into fix/report_ca

@@ -11,7 +11,7 @@ PAGE_SIZE_DEFAULT = 10
 FIXED_APPLICATION_ID_PREFIX = 'CH-S'
 
 DOC_SCHEME_LIST = ['ACCEPTANCE', 'SETTLEMENT', 'CONTRACTMANAGEMENT']
-DATA_SOURCE_LIST = ['POS', 'EAPP', 'ECONTRACT']
+DATA_SOURCE_LIST = ['POS', 'EAPP', 'ECONTRACT', 'OVP']
 COMPARE_DOC_SCHEME_LIST = ['CA', 'SE']
 
 HIL_PREFIX = 'HIL'

@@ -1476,7 +1476,8 @@ class Command(BaseCommand, LoggerMixin):
 
                         # AFC合同
                         if classify_1_str == str(consts.CONTRACT_CLASSIFY):
-                            ocr_result = afc_predict(pdf_handler.pdf_info)
+                            is_fsm = doc.data_source == consts.DATA_SOURCE_LIST[3]
+                            ocr_result = afc_predict(pdf_handler.pdf_info, is_fsm=is_fsm)
                             page_res = {}
                             for page_num, page_info in ocr_result.get('page_info', {}).items():
                                 if isinstance(page_num, str) and page_num.startswith('page_'):
@@ -1499,8 +1500,9 @@ class Command(BaseCommand, LoggerMixin):
                             }
                         # HIL合同
                         elif classify_1_str in consts.HIL_CONTRACT_TYPE_MAP:
+                            is_fsm = doc.data_source == consts.DATA_SOURCE_LIST[3]
                             file_type_1 = consts.HIL_CONTRACT_TYPE_MAP.get(classify_1_str)
-                            ocr_result_1 = hil_predict(pdf_handler.pdf_info, file_type_1)
+                            ocr_result_1 = hil_predict(pdf_handler.pdf_info, file_type_1, is_fsm=is_fsm)
                             rebuild_res_1 = {}
                             page_res = {}
                             for field_name, field_info in ocr_result_1.items():
@@ -1526,8 +1528,8 @@ class Command(BaseCommand, LoggerMixin):
                                         'page_info': page_info
                                     }
                         # hmh
-                        else:
-                            pass
+                        # else:
+                        #     pass
 
 
                         contract_res = {}

@@ -36,6 +36,7 @@ class RequestTrigger(NamedEnum):
     DOCUPLOAD = (3, 'Document Upload')
     SUBMITING = (4, 'Submiting')
     UPLOADING = (5, 'Uploading')
+    OVP = (6, 'OVP')
 
 
 class FailureReason(NamedEnum):

@@ -602,8 +602,9 @@ class UploadDocView(GenericView, DocHandler):
         is_zip = False
 
         classify_1 = 0
-        # 电子合同
-        if data_source == consts.DATA_SOURCE_LIST[-1] and document_scheme == consts.DOC_SCHEME_LIST[1]:
+        # 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

@@ -6,6 +6,7 @@
 # @Description   :
 
 from .get_char import Finder
+from .get_char_fsm import Finder as FSMFinder
 import numpy as np
 
 
@@ -23,7 +24,7 @@ def extract_info(ocr_results):
     return {'page_1': {'合同编号': contract_no}}
 
 
-def predict(pdf_info, is_qrs=False):
+def predict(pdf_info, is_qrs=False, is_fsm=False):
     ocr_results = {}
     for pno in pdf_info:
         ocr_results[pno] = {}
@@ -50,6 +51,9 @@ def predict(pdf_info, is_qrs=False):
         results = extract_info(ocr_results)
     else:
         # 输入是整个 PDF 中的信息
+        if is_fsm:
+            f = FSMFinder(pdf_info, ocr_results=ocr_results) 
+        else:
             f = Finder(pdf_info, ocr_results=ocr_results)
         results = f.get_info()
     return results

@@ -6,9 +6,10 @@
 # @Description   :
 
 from .get_char import Finder
+from .get_char_fsm import Finder as FSMFinder
 
 
-def predict(pdf_info, file_cls):
+def predict(pdf_info, file_cls, is_fsm=False):
     """Summary
 
     Args:
@@ -58,6 +59,10 @@ def predict(pdf_info, file_cls):
         pdf_info = dict()
         for pno, page_info in enumerate(pdf_info_1):
             pdf_info[str(pno)] = page_info
+
+    if is_fsm:
+        f = FSMFinder(pdf_info) 
+    else:
         f = Finder(pdf_info)
     if file_cls == 0:
         results = f.get_info()