document_.py更新

document_.py

@@ -1,7 +1,5 @@
 '''
 招投标文件预审查
-
-1. 解析bidding_document_extract中all_tables.json结果
 '''
 from tools import BaseMethods
 from pprint import pprint
@@ -32,7 +30,7 @@ class DocumentPreReview():
         self.bidding_context = self.get_bidding_context()
         self.chinese_num_map = chinese_num_map
 
-    def get_contexts(self, file_path:str = 'code/bidding_document_extract/contexts.json'):
+    def get_contexts(self, file_path:str = 'data/预审查数据/contexts.json'):
         ''' get contexts by page
         '''
         contexts = self.bm.json_read(file_path)
@@ -41,27 +39,39 @@ class DocumentPreReview():
     def get_bidding_table(self):
         ''' get table data
         '''
-        file_path = "code/bidding_document_extract/all_tables.json"
-        # file_path = "code/bidding_document_extract/all_tables_三峡左右岸.json"
+        file_path = "data/预审查数据/Bidding_tables_2022-2025年度三峡电站9台机组检修密封加工制作重新招标招标文件印刷版.json"
         all_tables = self.bm.json_read(file_path)
         return all_tables
     
     def get_bidding_context(self):
         ''' read json to get context
         '''
-        file_path = "code/bidding_document_extract/基于物联网技术的三峡坝区智慧仓储研究与建设招标文件-发出.json"
+        file_path = "data/预审查数据/基于物联网技术的三峡坝区智慧仓储研究与建设招标文件-发出.json"
         bidding_context = self.bm.json_read(file_path)
         return bidding_context
+    
+    def _scrutinize_judge(self, tag:str):
+        ''' 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")
+        hit_num = 0
+        for scru in scrutinize_tuple:
+            if scru in tag: hit_num+= 1
+        if hit_num>=3: return True
+        else: return False
 
     def get_table(self):
-        ''' get table to json
+        ''' parse the tables.json file to get the table data from it.
         '''
         all_tables = self.bidding_tables
 
+        # 招标文件内容中预审查
         tag_sign = ''
         tag_list = ("形式评审标准", "资格评审标准", "响应性评审标准")
         tag_dict = dict([(tag,[]) for tag in tag_list])
         
+        # 招标文件内容中清标表格数据
         scrutinize_tuple = ("商务部分评分标准","技术部分评审标准","投标报价评审标准","报价部分评审标准","报价评分标准")
         scrutinize_dict = dict([(scrutinize,[]) for scrutinize in scrutinize_tuple])
         scrutinize_page = 0
@@ -80,8 +90,11 @@ class DocumentPreReview():
                 record_page = page_number[0]
             if page_number[0] < record_page + 3: 
                 for table in tables[1:]:
-                    if table[0] and table[0] not in bidder_know: bidder_know[table[0]] = []
-                    if table[0]: bidder_know[table[0]].append({"条款名称":table[1],"编列内容":table[2]})
+                    try:
+                        if table[0] and table[0] not in bidder_know: bidder_know[table[0]] = []
+                        if table[0]: bidder_know[table[0]].append({"条款名称":table[1],"编列内容":table[2]})
+                    except:
+                        print()
                 
             if '评标方法' in table_name:
                 table_name = table_name.strip().replace("\n","")
@@ -96,7 +109,7 @@ class DocumentPreReview():
                 for table in tables[1:]:
                     tag = table[regulation_number_index+1]
                     if tag: tag = tag.strip().replace("\n","")
-                    if tag and (tag in tag_list):
+                    if tag and self._scrutinize_judge(tag):
                         tag_sign = tag
                     evaluation_factor,evaluation_criteria = table[evaluation_factor_index],table[evaluation_criteria_index]
                     if tag_sign in tag_dict: 
@@ -125,8 +138,9 @@ class DocumentPreReview():
                         if tag: 
                             tag = tag.strip().replace("\n","")
                             tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
-                        if tag and (tag in scrutinize_tuple):
+                        if tag and self._scrutinize_judge(tag):
                             tag_sign = tag
+                            if tag_sign not in scrutinize_dict: scrutinize_dict[tag_sign] = []
                         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",""),
@@ -149,8 +163,9 @@ class DocumentPreReview():
                     if tag: 
                         tag = tag.strip().replace("\n","")
                         tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
-                    if tag and (tag in scrutinize_tuple):
+                    if tag and self._scrutinize_judge(tag):
                         tag_sign = tag
+                        if tag_sign not in scrutinize_dict: scrutinize_dict[tag_sign] = []
                     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",""),
@@ -170,23 +185,21 @@ class DocumentPreReview():
                     if tag: 
                         tag = tag.strip().replace("\n","")
                         tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
-                    if tag and (tag in scrutinize_tuple):
+                    if tag and self._scrutinize_judge(tag):
                         tag_sign = tag
+                        if tag_sign not in scrutinize_dict: scrutinize_dict[tag_sign] = []
                     evaluation_factor,evaluation_criteria,weights = table[evaluation_factor_index],table[evaluation_criteria_index],table[weights_index]
-                    try:
-                        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",""),
-                                    "评分标准":evaluation_criteria.strip().replace("\n",""),
-                                    "权重":weights.strip().replace("\n","")}
-                    except:
-                        print()
+                    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",""),
+                                "评分标准":evaluation_criteria.strip().replace("\n",""),
+                                "权重":weights.strip().replace("\n","")}
                     scrutinize_dict[tag_sign].append(value)
                     if '报价' in tag_sign and '标准' in tag_sign:
                         scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
                         break
 
         # pprint(tag_dict)
-        # pprint(scrutinize_dict)
+        pprint(scrutinize_dict)
         # pprint(bidder_know)
         return tag_dict,bidder_know,scrutinize_dict
     
@@ -260,10 +273,7 @@ class DocumentPreReview():
                     if text == title and format_index == -1:
                         format_index = self.bidding_context.index(context)
                         break
-                    '''
-                    不对比目录，只对比内容，只要存在即认定符合要求
-                    '''
-
+                    
                 title_index = title_list.index(title)
                 if title_index != len(title_list)-1:
                     title_next = title_list[title_index+1]
@@ -273,8 +283,8 @@ class DocumentPreReview():
                     text = context['text'].strip().replace(" ","")
                     if title_next and title_next == text:
                         break
-                    file_format[title].append(context)
-                file_format   # 需要优化提取的内容
+                    file_format[title].append(text)
+                pprint(file_format)   # 需要优化提取的内容
                 '''
                 招标文件 file_format 与投标文件内容对比，投标文件中只要存在file_format内容即可
                 '''