document_.py update

document_.py

@@ -52,7 +52,7 @@ class DocumentPreReview():
         ''' Clause number content judgment 
             商务 技术 报价 评审 评分 标准
         '''
-        scrutinize_tuple = ("商务","技术","报价","评审","评分","标准")
+        scrutinize_tuple = ("商务","技术","报价","评审","评分","标准","部分")
         hit_num = 0
         for scru in scrutinize_tuple:
             if scru in tag: hit_num+= 1
@@ -155,6 +155,8 @@ class DocumentPreReview():
         scrutinize_second_title_len = 0
         scrutinize_sign = False
 
+        weight_comp = re.compile("(\d+%)")
+
         regulation_number_index_,evaluation_factor_index,evaluation_criteria_index,weights_index = 0,0,0,0
 
         for partial_form in all_tables:
@@ -208,6 +210,10 @@ class DocumentPreReview():
                         if tag and self._scrutinize_judge(tag):
                             tag_sign_ = tag
                             if tag_sign_ not in scrutinize_dict: scrutinize_dict[tag_sign_] = []
+                        if len(table) >= weights_index:
+                            weighr_finder = weight_comp.findall(table[-1])
+                            if weighr_finder: table.append(weighr_finder[0])
+                            else: table.append('3%')
                         evaluation_factor,evaluation_criteria,weights = table[evaluation_factor_index],table[evaluation_criteria_index],table[weights_index]
                         if not weights: value = {"评分因素":evaluation_factor.strip().replace("\n",""),"评分标准":evaluation_criteria.strip().replace("\n","")}
                         else: value = {"评分因素":evaluation_factor.strip().replace("\n",""),
@@ -246,6 +252,10 @@ class DocumentPreReview():
                     if tag and self._scrutinize_judge(tag):
                         tag_sign_ = tag
                         if tag_sign_ not in scrutinize_dict: scrutinize_dict[tag_sign_] = []
+                    if len(table) >= weights_index:
+                        weighr_finder = weight_comp.findall(table[-1])
+                        if weighr_finder: table[weights_index] = weighr_finder[0]
+                        else: table[weights_index] = '3%'
                     evaluation_factor,evaluation_criteria,weights = table[evaluation_factor_index],table[evaluation_criteria_index],table[weights_index]
                     if not weights: value = {"评分因素":evaluation_factor.strip().replace("\n",""), "评分标准":evaluation_criteria.strip().replace("\n","")}
                     else: value = {"评分因素":evaluation_factor.strip().replace("\n",""),
@@ -278,6 +288,10 @@ class DocumentPreReview():
                     if tag and self._scrutinize_judge(tag):
                         tag_sign_ = tag
                         if tag_sign_ not in scrutinize_dict: scrutinize_dict[tag_sign_] = []
+                    if len(table) >= weights_index:
+                        weighr_finder = weight_comp.findall(table[-1])
+                        if weighr_finder: table[weights_index] = weighr_finder[0]
+                        else: table[weights_index] = '3%'
                     evaluation_factor,evaluation_criteria,weights = table[evaluation_factor_index],table[evaluation_criteria_index],table[weights_index]
                     if not weights: value = {"评分因素":evaluation_factor.strip().replace("\n",""), "评分标准":evaluation_criteria.strip().replace("\n","")}
                     else: value = {"评分因素":evaluation_factor.strip().replace("\n",""),
@@ -305,7 +319,7 @@ 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/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"
+    path_ = "data/清标详审数据/溪洛渡水电站3台东电机组推导轴承密封更换-table.json"
     dpr = DocumentPreReview(path_)
     scrutinize_dict = dpr.get_table()