document_.py update

document_.py

@@ -151,7 +151,8 @@ class DocumentPreReview():
         scrutinize_dict = {}
         scrutinize_page = 0
         scrutinize_index = -1
-        scrutinize_Initial_title_len = 0  # 详审位置标记
+        scrutinize_Initial_title_len = 0  # 详审表长度
+        scrutinize_second_title_len = 0
         scrutinize_sign = False
 
         regulation_number_index_,evaluation_factor_index,evaluation_criteria_index,weights_index = 0,0,0,0
@@ -219,6 +220,7 @@ class DocumentPreReview():
                                 scrutinize_Initial_title_len = 0
                                 break
             elif scrutinize_page+1 in page_number and scrutinize_sign:
+                scrutinize_second_title_len = title_len
                 difference_value = scrutinize_Initial_title_len - title_len
                 if difference_value:
                     table_length = len(table)
@@ -230,9 +232,11 @@ class DocumentPreReview():
                         evaluation_criteria_index = table_length-2
                         weights_index = table_length-1
                 for table in tables:
-                    if not table[2]:
-                        scrutinize_dict[tag_sign_][-1]['评分标准'] += table[3]
+                    if not table[evaluation_criteria_index]:
+                        scrutinize_dict[tag_sign_][-1]['评分标准'] += table[-1] if table[-1] else table[-2]
                         continue
+                    if '条款内容' in table and '编列内容' in table:
+                        break
                     if table[regulation_number_index_+1]: tag = table[regulation_number_index_+1]
                     elif self._scrutinize_judge(table[regulation_number_index_+2]): tag = table[regulation_number_index_+2]
                     else: tag = table[regulation_number_index_]
@@ -254,15 +258,17 @@ class DocumentPreReview():
                                 scrutinize_Initial_title_len = 0
                                 break
             elif scrutinize_page+2 in page_number and scrutinize_sign:
-                difference_value = scrutinize_Initial_title_len - title_len
+                difference_value = scrutinize_second_title_len - title_len
                 if difference_value:
                     evaluation_factor_index -= difference_value
                     evaluation_criteria_index -= difference_value
                     weights_index -= difference_value
                 for table in tables:
-                    if not table[2]:
-                        scrutinize_dict[tag_sign_][-1]['评分标准'] += table[3]
+                    if not table[evaluation_criteria_index]:
+                        scrutinize_dict[tag_sign_][-1]['评分标准'] += table[-1] if table[-1] else table[-2]
                         continue
+                    if '条款内容' in table and '编列内容' in table:
+                        break
                     if table[regulation_number_index_+1]: tag = table[regulation_number_index_+1]
                     elif self._scrutinize_judge(table[regulation_number_index_+2]): tag = table[regulation_number_index_+2]
                     else: tag = table[regulation_number_index_]
@@ -299,7 +305,7 @@ if __name__ == '__main__':
     #         scrutinize_dict = dpr.get_table()  # TODO scrutinize_dict是需要的结果
     #         break
 
-    path_ = "data/清标详审数据/(未签章)白鹤滩电站辅助值班及接待机器人研究采购程序文件-table.json"
+    path_ = "data/清标详审数据/2023-2024年度乌东德电站图像监控系统及广播系统扩建-table(1).json"
     dpr = DocumentPreReview(path_)
     scrutinize_dict = dpr.get_table()