e-contract part 1

@@ -1773,3 +1773,21 @@ APPLICANT_TYPE_MAP = {
 }
 }
 
 
 APPLICANT_TYPE_ORDER = ['Borrower', 'Co-Borrower', 'Guarantor', 'Mortgager']
 APPLICANT_TYPE_ORDER = ['Borrower', 'Co-Borrower', 'Guarantor', 'Mortgager']
+
+FILE_NAME_PREFIX_MAP = {
+    AFC_PREFIX: [
+        ((CONTRACT_CLASSIFY, 0), '{0}_电子签署-汽车抵押贷款合同'),
+        ((HMH_CLASSIFY, 0), '{0}_电子签署-抵押登记豁免函'),
+    ],
+    HIL_PREFIX: [
+        ((HIL_CONTRACT_1_CLASSIFY, HIL_CONTRACT_3_CLASSIFY), '{0}_电子签署-售后回租合同'),
+        ((HIL_CONTRACT_2_CLASSIFY, 0), '{0}_电子签署-汽车租赁抵押合同'),
+        ((HMH_CLASSIFY, 0), '{0}_电子签署-抵押登记豁免函'),
+    ]
+}
+
+HIL_CONTRACT_TYPE_MAP = {
+    str(HIL_CONTRACT_1_CLASSIFY): 0,
+    str(HIL_CONTRACT_2_CLASSIFY): 2,
+    str(HIL_CONTRACT_3_CLASSIFY): 1,
+}
\ No newline at end of file

@@ -789,3 +789,24 @@ class HILCACompareResultRecord(models.Model):
         db_table = 'hil_ca_compare_result_record'
         db_table = 'hil_ca_compare_result_record'
 
 
 
 
+class HILContract(models.Model):
+    id = models.AutoField(primary_key=True, verbose_name="id")  # 主键
+    application_id = models.CharField(max_length=64, verbose_name="申请id")  # 索引
+    create_time = models.DateTimeField(auto_now_add=True, verbose_name='创建时间')
+
+    class Meta:
+        managed = False
+        db_table = 'hil_contract'
+
+
+class AFCContract(models.Model):
+    id = models.AutoField(primary_key=True, verbose_name="id")  # 主键
+    application_id = models.CharField(max_length=64, verbose_name="申请id")  # 索引
+    create_time = models.DateTimeField(auto_now_add=True, verbose_name='创建时间')
+
+    class Meta:
+        managed = False
+        db_table = 'afc_contract'
+        situ_db_label = 'afc'
+
+

+import os
 import base64
 import base64
 import requests
 import requests
 from common.redis_cache import redis_handler as rh
 from common.redis_cache import redis_handler as rh
@@ -44,7 +45,6 @@ class ECM:
                               "b_coborrower_id", "b_coborrower_name", "b_guarantor_id", "b_guarantor_name",
                               "b_coborrower_id", "b_coborrower_name", "b_guarantor_id", "b_guarantor_name",
                               "b_frontend_partner", "b_dealer_code", "b_dealer_name", "b_input_date", "b_comment",
                               "b_frontend_partner", "b_dealer_code", "b_dealer_name", "b_input_date", "b_comment",
                               "b_contract_no", "b_location"]
                               "b_contract_no", "b_location"]
-        self.contract_prefix = '电子'
 
 
     def update_oauth_token(self):
     def update_oauth_token(self):
         response = requests.post(self.oauth_url, headers=self.oauth_headers, data=self.oauth_payload, verify=False)
         response = requests.post(self.oauth_url, headers=self.oauth_headers, data=self.oauth_payload, verify=False)
@@ -69,9 +69,9 @@ class ECM:
     def get_headers(self):
     def get_headers(self):
         return {'Authorization': '{0} {1}'.format(self.token_type, self.get_oauth_token())}
         return {'Authorization': '{0} {1}'.format(self.token_type, self.get_oauth_token())}
 
 
-    def search(self, application_id, business_type):
+    def search(self, application_id, business_type, prefix):
         sql = "select * from {0} where b_application_no='{1}' and object_name like '{2}%'".format(
         sql = "select * from {0} where b_application_no='{1}' and object_name like '{2}%'".format(
-            self.settlement_type, application_id, self.contract_prefix)
+            self.settlement_type, application_id, prefix)
         search_args = {
         search_args = {
             "userName": self.username,
             "userName": self.username,
             "password": self.pwd,
             "password": self.pwd,
@@ -96,7 +96,6 @@ class ECM:
                 result.append((object_name, object_id))
                 result.append((object_name, object_id))
         return result
         return result
 
 
-
     def download(self, save_path, object_id, document_scheme, business_type):
     def download(self, save_path, object_id, document_scheme, business_type):
         doc_type, _, _ = self.doc_type_map.get(document_scheme)
         doc_type, _, _ = self.doc_type_map.get(document_scheme)
         download_json = {
         download_json = {

@@ -36,12 +36,14 @@ from .models import (
     AFCSECompareResultRecord,
     AFCSECompareResultRecord,
     HILCACompareResultRecord,
     HILCACompareResultRecord,
     HILSECompareResultRecord,
     HILSECompareResultRecord,
+    HILContract,
+    AFCContract,
 )
 )
 from .named_enum import ErrorType
 from .named_enum import ErrorType
 from .mixins import DocHandler
 from .mixins import DocHandler
 from . import consts
 from . import consts
 from apps.account.authentication import OAuth2AuthenticationWithUser
 from apps.account.authentication import OAuth2AuthenticationWithUser
-from celery_compare.tasks import compare
+from celery_compare.tasks import compare, forwarding_station
 
 
 
 
 class CustomDate(fields.Date):
 class CustomDate(fields.Date):
@@ -1164,5 +1166,11 @@ class SEContractView(GenericView):
     # pos上传e-contract信息接口 SE
     # pos上传e-contract信息接口 SE
     @use_args(se_contract_args, location='data')
     @use_args(se_contract_args, location='data')
     def post(self, request, args):
     def post(self, request, args):
-        self.running_log.info('e-contract in')
+        contract_info = args.get('content', {})
+        application_id = contract_info.get('applicationId', '')
+        entity = contract_info.get('applicationEntity', '')
+        table_class = HILContract if entity == consts.HIL_PREFIX else AFCContract
+        table_class.objects.create(application_id=application_id)
+        forwarding_station.apply_async((application_id, entity), queue='queue_compare', countdown=conf.DELAY_SECONDS)
+        self.running_log.info('[e-contract] [application_id={0}] [entity={1}]'.format(application_id, entity))
         return response.ok()
         return response.ok()

@@ -27,10 +27,13 @@ from apps.doc.models import (
     AFCCACompareResult,
     AFCCACompareResult,
     HILSECompareResult,
     HILSECompareResult,
     HILCACompareResult,
     HILCACompareResult,
+    AFCDoc,
+    HILDoc
 )
 )
 from apps.doc import consts
 from apps.doc import consts
 from apps.doc.ocr.gcap import gcap
 from apps.doc.ocr.gcap import gcap
 from apps.doc.ocr.cms import cms
 from apps.doc.ocr.cms import cms
+from apps.doc.ocr.ecm import ECM, rh
 from apps.doc.exceptions import GCAPException
 from apps.doc.exceptions import GCAPException
 from apps.doc.named_enum import RequestTeam, RequestTrigger, ProcessName, ErrorType
 from apps.doc.named_enum import RequestTeam, RequestTrigger, ProcessName, ErrorType
 from common.tools.comparison import cp
 from common.tools.comparison import cp
@@ -38,9 +41,11 @@ from common.tools.des import decode_des
 
 
 compare_log = logging.getLogger('compare')
 compare_log = logging.getLogger('compare')
 log_base = '[Compare]'
 log_base = '[Compare]'
+e_log_base = '[e-contract]'
 empty_str = ''
 empty_str = ''
 empty_error_type = 1000
 empty_error_type = 1000
 des_key = conf.CMS_DES_KEY
 des_key = conf.CMS_DES_KEY
+ecm = ECM()
 
 
 
 
 def rotate_bound(image, angle):
 def rotate_bound(image, angle):
@@ -1867,4 +1872,32 @@ def compare(application_id, application_entity, uniq_seq, ocr_res_id, is_ca=True
         se_compare(application_id, application_entity, ocr_res_id, last_obj, ocr_res_dict, is_cms)
         se_compare(application_id, application_entity, ocr_res_id, last_obj, ocr_res_dict, is_cms)
 
 
 
 
-
+@app.task
+def forwarding_station(application_id, entity):
+    compare_log.info('{0} [forward start] [application_id={1}] [entity={2}]'.format(e_log_base, application_id, entity))
+    doc_class = HILDoc if entity in consts.HIL_SET else AFCDoc
+    entity_prefix = consts.HIL_PREFIX if entity in consts.HIL_SET else consts.AFC_PREFIX
+    for (classify_1, classify_2), prefix in consts.FILE_NAME_PREFIX_MAP.get(entity):
+        try:
+            file_list = ecm.search(application_id, entity, prefix.format(application_id))  # TODO 获取最新文件
+        except Exception as e:
+            compare_log.error('{0} [search failed] [application_id={1}] [entity={2}] [error={3}]'.format(
+                e_log_base, application_id, entity, traceback.format_exc()))
+        else:
+            compare_log.info('{0} [search end] [application_id={1}] [entity={2}] [file_list={3}]'.format(
+                e_log_base, application_id, entity, file_list))
+            for object_name, object_id in file_list:
+                doc = doc_class.objects.create(
+                    metadata_version_id=object_id,
+                    application_id=application_id,
+                    document_name=object_name,
+                    document_scheme='SETTLEMENT',
+                    data_source='POS',
+                    upload_finish_time=datetime.now(),
+                )
+                task = consts.SPLIT_STR.join([entity_prefix, str(doc.id), str(classify_1), str(classify_2)])
+                enqueue_res = rh.enqueue([task], False)
+                compare_log.info('{0} [upload success] [res={1}] [application_id={2}] [entity={3}] [object_name={4}] '
+                                 '[object_id={5}] [doc_id={6}]'.format(e_log_base, enqueue_res, application_id, entity,
+                                                                       object_name, object_id, doc.id))
+    compare_log.info('{0} [forward end] [application_id={1}] [entity={2}]'.format(e_log_base, application_id, entity))

+# -*- coding: utf-8 -*-
+# @Author        : lk
+# @Email         : 9428.al@gmail.com
+# @Created Date  : 2021-06-29 17:43:46
+# @Last Modified : 2021-09-07 14:11:25
+# @Description   :
+
+from .get_char import Finder
+
+
+def predict(pdf_info):
+    # 输入是整个 PDF 中的信息
+    f = Finder(pdf_info)
+    results = f.get_info()
+
+    return results
+
+

+# -*- coding: utf-8 -*-
+# @Author        : lk
+# @Email         : 9428.al@gmail.com
+# @Created Date  : 2021-06-29 17:43:46
+# @Last Modified : 2021-11-03 16:07:36
+# @Description   :
+
+from .get_char import Finder
+
+
+def predict(pdf_info, file_cls):
+    """Summary
+    
+    Args:
+        pdf_info (TYPE): Description
+        file_cls (TYPE): file_cls = 0: 售后回租合同; file_cls = 1: 车辆处置协议; file_cls = 2: 车辆租赁抵押合同
+    
+    Returns:
+        TYPE: Description
+    """
+
+    # 0: 售后回租合同
+    pdf_info_0 = []
+    for pno in pdf_info:
+        for block in pdf_info[f'{pno}']['blocks']:
+            if block['type'] != 0:
+                continue
+            for line in block['lines']:
+                for span in line['spans']:
+                    bbox, text = span['bbox'], span['text']
+                    if '售后回租合同_' in text:
+                        pdf_info_0.append(pdf_info[pno])
+
+    # 1: 车辆处置协议
+    pdf_info_1 = []
+    for pno in pdf_info:
+        for block in pdf_info[f'{pno}']['blocks']:
+            if block['type'] != 0:
+                continue
+            for line in block['lines']:
+                for span in line['spans']:
+                    bbox, text = span['bbox'], span['text']
+                    if '售后回租合同附件一' in text:
+                        pdf_info_1.append(pdf_info[pno])
+
+    # 2: 车辆租赁抵押合同
+    pdf_info_2 = []
+    for pno in pdf_info:
+        for block in pdf_info[f'{pno}']['blocks']:
+            if block['type'] != 0:
+                continue
+            for line in block['lines']:
+                for span in line['spans']:
+                    bbox, text = span['bbox'], span['text']
+                    if '车辆租赁抵押合同_' in text:
+                        pdf_info_2.append(pdf_info[pno])
+
+    is_clczxy = False
+    # 如果 pdf_info_1 == 4 页，则说明此时输入包含了车辆处置协议
+    if len(pdf_info_1) == 4 and file_cls == 1 and len(pdf_info_0) != 0:
+        is_clczxy = True
+        pdf_info = dict()
+        for pno, page_info in enumerate(pdf_info_1):
+            pdf_info[str(pno)] = page_info
+
+    f = Finder(pdf_info)
+    if file_cls == 0:
+        results = f.get_info()
+    if file_cls == 1:
+        # 提取信息 ———— 车辆处置协议
+        results = f.get_info_1()
+    if file_cls == 2:
+        # 提取信息 ———— 车辆租赁抵押合同
+        results = f.get_info_2()
+
+    if is_clczxy == True:
+        for key in results:
+            if results[key]['page'] is not None:
+                results[key]['page'] = str(int(results[key]['page'])+6)
+
+    for key in results:
+        if results[key]['page'] is not None:
+            results[key]['page'] = 'page_' + str(int(results[key]['page'])+1)
+    return results

+import pyodbc
+
+afc_sql = """
+    create table afc_contract
+    (
+       id bigint identity primary key,
+       application_id nvarchar(64) not null,
+       create_time datetime not null
+    );
+    
+    create index afc_contract_application_id_index
+       on afc_contract (application_id);
+"""
+
+hil_sql = """
+    create table hil_contract
+    (
+       id bigint identity primary key,
+       application_id nvarchar(64) not null,
+       create_time datetime not null
+    );
+    
+    create index hil_contract_application_id_index
+       on hil_contract (application_id);
+"""
+
+hil_cnxn = pyodbc.connect('DRIVER={ODBC Driver 17 for SQL Server};', autocommit=True)
+
+hil_cursor = hil_cnxn.cursor()
+hil_cursor.execute(hil_sql)
+
+hil_cursor.close()
+hil_cnxn.close()
+
+afc_cnxn = pyodbc.connect('DRIVER={ODBC Driver 17 for SQL Server};', autocommit=True)
+
+afc_cursor = afc_cnxn.cursor()
+afc_cursor.execute(afc_sql)
+
+afc_cursor.close()
+afc_cnxn.close()

 import os
 import os
+import json
 import cv2
 import cv2
 import shutil
 import shutil
 import fitz
 import fitz
@@ -35,6 +36,8 @@ class PDFHandler:
         self.suffix = self.get_suffix(document_name)
         self.suffix = self.get_suffix(document_name)
         self.is_ebank = False
         self.is_ebank = False
         self.page_text_list = []
         self.page_text_list = []
+        self.pdf_info = {}
+        self.img_path_pno_list = []
 
 
     def get_suffix(self, file_name):
     def get_suffix(self, file_name):
         if file_name is None:
         if file_name is None:
@@ -296,6 +299,17 @@ class PDFHandler:
         self.is_ebank = True
         self.is_ebank = True
         self.page_text_list = page_text_list
         self.page_text_list = page_text_list
 
 
+    def e_contract_process(self):
+        with fitz.Document(self.path) as pdf:
+            for pno in range(pdf.pageCount):
+                page = pdf.loadPage(pno)
+                self.pdf_info[str(pno)] = json.loads(page.getText('json'))
+
+                pix = page.getPixmap()
+                img_save_path = self.get_img_save_path(page.number)
+                self.img_path_pno_list.append((img_save_path, 'page_{0}'.format(str(pno+1))))
+                pix.writePNG(img_save_path)
+
     def extract_image(self, max_img_count=None):
     def extract_image(self, max_img_count=None):
         self.img_path_list = []
         self.img_path_list = []
         self.xref_set = set()
         self.xref_set = set()

@@ -14,3 +14,5 @@ DEALER_CODE = ocr_group
 
 
 BASE_URL = https://li19dkocruat02vm.bmwgroup.net
 BASE_URL = https://li19dkocruat02vm.bmwgroup.net
 
 
+DELAY_SECONDS = 60
+

@@ -13,3 +13,5 @@ EDMS_UPLOAD_URL = https://edms-test.bmw.com/FH/FileHold/DocumentRepository/Uploa
 DEALER_CODE = ocr_situ_group
 DEALER_CODE = ocr_situ_group
 
 
 BASE_URL = https://staging-bmw-ocr.situdata.com
 BASE_URL = https://staging-bmw-ocr.situdata.com
+
+DELAY_SECONDS = 60
\ No newline at end of file

@@ -13,3 +13,5 @@ EDMS_UPLOAD_URL = http://sccn0637.bmwgroup.net/FH/FileHold/DocumentRepository/Up
 DEALER_CODE = ocr_situ_group
 DEALER_CODE = ocr_situ_group
 
 
 BASE_URL = https://li19dkocruat01vm.bmwgroup.net
 BASE_URL = https://li19dkocruat01vm.bmwgroup.net
+
+DELAY_SECONDS = 60
\ No newline at end of file