|
|
@@ -41,8 +41,8 @@ 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 = "code/bidding_document_extract/all_tables.json"
|
|
|
+ # file_path = "code/bidding_document_extract/all_tables_三峡左右岸.json"
|
|
|
all_tables = self.bm.json_read(file_path)
|
|
|
return all_tables
|
|
|
|
|
|
@@ -58,6 +58,7 @@ class DocumentPreReview():
|
|
|
'''
|
|
|
all_tables = self.bidding_tables
|
|
|
|
|
|
+ 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])
|
|
|
|
|
|
@@ -65,25 +66,25 @@ class DocumentPreReview():
|
|
|
scrutinize_dict = dict([(scrutinize,[]) for scrutinize in scrutinize_tuple])
|
|
|
scrutinize_page = 0
|
|
|
scrutinize_index = 0
|
|
|
+ scrutinize_Initial_position_marker = 0 # 详审位置标记
|
|
|
|
|
|
record_page = 0
|
|
|
bidder_know = {} # 投标人须知前附表
|
|
|
for partial_form in all_tables:
|
|
|
table_name = partial_form['table_name']
|
|
|
- confidence = partial_form['confidence']
|
|
|
page_number = partial_form['page_numbers']
|
|
|
title_len = partial_form['title_len']
|
|
|
tables = partial_form["table"]
|
|
|
|
|
|
- if '投标人须知前附表' == table_name: record_page = page_number[0]
|
|
|
+ if '投标人须知前附表' == table_name:
|
|
|
+ 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]})
|
|
|
-
|
|
|
- if ('评标方法' not in table_name) and (confidence != 1): continue
|
|
|
- table_name = table_name.strip().replace("\n","")
|
|
|
+
|
|
|
+ if '评标方法' in table_name:
|
|
|
+ table_name = table_name.strip().replace("\n","")
|
|
|
if table_name == "评标办法前附表":
|
|
|
table_page_num = page_number[0]
|
|
|
inital_data = tables[0]
|
|
|
@@ -91,10 +92,8 @@ class DocumentPreReview():
|
|
|
regulation_number_index = inital_data.index("条款号")
|
|
|
evaluation_factor_index = inital_data.index("评审因素")
|
|
|
evaluation_criteria_index = inital_data.index("评审标准")
|
|
|
- tag_sign = ''
|
|
|
+
|
|
|
for table in tables[1:]:
|
|
|
- # regulation_number = table[regulation_number_index]
|
|
|
- # if "条款号" == regulation_number: break
|
|
|
tag = table[regulation_number_index+1]
|
|
|
if tag: tag = tag.strip().replace("\n","")
|
|
|
if tag and (tag in tag_list):
|
|
|
@@ -103,23 +102,25 @@ class DocumentPreReview():
|
|
|
if tag_sign in tag_dict:
|
|
|
tag_dict[tag_sign].append({"评审因素":evaluation_factor.strip().replace("\n",""),
|
|
|
"评审标准":evaluation_criteria.strip().replace("\n","")})
|
|
|
+ if '评分因素' in table or '评分标准' in table:
|
|
|
+ scrutinize_page = table_page_num
|
|
|
+ scrutinize_Initial_position_marker = 1
|
|
|
+ if not scrutinize_page: scrutinize_page = table_page_num+1
|
|
|
|
|
|
+ ''' scrutinize '''
|
|
|
+ if page_number[0] == 35:
|
|
|
+ print()
|
|
|
+ if (scrutinize_page == page_number[0] and scrutinize_Initial_position_marker) or scrutinize_page == page_number[0]:
|
|
|
+ regulation_number_index,evaluation_factor_index,evaluation_criteria_index,weights_index = 0,0,0,0
|
|
|
+ for table in tables:
|
|
|
if '评分因素' in table and '评分标准' in table:
|
|
|
- scrutinize_page = table_page_num+1
|
|
|
+ regulation_number_index = table.index("条款号")
|
|
|
+ evaluation_factor_index = table.index("评分因素")
|
|
|
+ evaluation_criteria_index = table.index("评分标准")
|
|
|
+ weights_index = table.index("权重")
|
|
|
+ tag_sign = ''
|
|
|
scrutinize_index = tables.index(table)
|
|
|
- if not scrutinize_page:
|
|
|
- scrutinize_page = table_page_num+1
|
|
|
-
|
|
|
- ''' scrutinize '''
|
|
|
- if scrutinize_index:
|
|
|
- if scrutinize_page-1 == page_number[0]:
|
|
|
- table_ = tables[scrutinize_index]
|
|
|
- regulation_number_index = table_.index("条款号")
|
|
|
- evaluation_factor_index = table_.index("评分因素")
|
|
|
- evaluation_criteria_index = table_.index("评分标准")
|
|
|
- weights_index = table_.index("权重")
|
|
|
- tag_sign = ''
|
|
|
-
|
|
|
+ if scrutinize_index:
|
|
|
for table in tables[scrutinize_index+1:]:
|
|
|
if table[regulation_number_index+1]: tag = table[regulation_number_index+1]
|
|
|
else: tag = table[regulation_number_index+2]
|
|
|
@@ -134,111 +135,62 @@ class DocumentPreReview():
|
|
|
"评分标准":evaluation_criteria.strip().replace("\n",""),
|
|
|
"权重":weights.strip().replace("\n","")}
|
|
|
scrutinize_dict[tag_sign].append(value)
|
|
|
-
|
|
|
- elif scrutinize_page == page_number[0] and title_len == 5:
|
|
|
- evaluation_factor_index -= 1
|
|
|
- evaluation_criteria_index -= 1
|
|
|
- weights_index -= 1
|
|
|
- for table in tables:
|
|
|
- if not table[2]:
|
|
|
- scrutinize_dict[tag_sign][-1]['评分标准'] += table[3]
|
|
|
- continue
|
|
|
- tag = table[regulation_number_index+1]
|
|
|
- if tag:
|
|
|
- tag = tag.strip().replace("\n","")
|
|
|
- tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
|
|
|
- if tag and (tag in scrutinize_tuple):
|
|
|
- tag_sign = tag
|
|
|
- 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",""),
|
|
|
- "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 '评审标准' in tag_sign:
|
|
|
- scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
|
|
|
- break
|
|
|
- print(scrutinize_dict)
|
|
|
-
|
|
|
- elif scrutinize_page+1 == page_number[0] and title_len != 4:
|
|
|
- for table in tables:
|
|
|
- if not table[2]:
|
|
|
- scrutinize_dict[tag_sign][-1]['评分标准'] += table[3]
|
|
|
- continue
|
|
|
- tag = table[regulation_number_index+1]
|
|
|
- if tag:
|
|
|
- tag = tag.strip().replace("\n","")
|
|
|
- tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
|
|
|
- if tag and (tag in scrutinize_tuple):
|
|
|
- tag_sign = tag
|
|
|
- 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",""),
|
|
|
- "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 '评审标准' in tag_sign:
|
|
|
scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
|
|
|
break
|
|
|
-
|
|
|
- print(scrutinize_dict)
|
|
|
-
|
|
|
- else:
|
|
|
- if scrutinize_page == page_number[0]:
|
|
|
- for table in tables:
|
|
|
- if '评分因素' in table and '评分标准' in table:
|
|
|
- regulation_number_index = table.index("条款号")
|
|
|
- evaluation_factor_index = table.index("评分因素")
|
|
|
- evaluation_criteria_index = table.index("评分标准")
|
|
|
- weights_index = table.index("权重")
|
|
|
- tag_sign = ''
|
|
|
- scrutinize_index = tables.index(table)
|
|
|
- if not scrutinize_index: continue
|
|
|
- for table in tables[scrutinize_index+1:]:
|
|
|
- if table[regulation_number_index+1]: tag = table[regulation_number_index+1]
|
|
|
- else: tag = table[regulation_number_index+2]
|
|
|
- if tag:
|
|
|
- tag = tag.strip().replace("\n","")
|
|
|
- tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
|
|
|
- if tag and (tag in scrutinize_tuple):
|
|
|
- tag_sign = tag
|
|
|
- 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",""),
|
|
|
- "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 '评审标准' in tag_sign:
|
|
|
- scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
|
|
|
- break
|
|
|
- pprint(scrutinize_dict)
|
|
|
-
|
|
|
- elif scrutinize_page+1 == page_number[0] and title_len != 4:
|
|
|
- for table in tables:
|
|
|
- if not table[2]:
|
|
|
- scrutinize_dict[tag_sign][-1]['评分标准'] += table[3]
|
|
|
- continue
|
|
|
- tag = table[regulation_number_index+1]
|
|
|
- if tag:
|
|
|
- tag = tag.strip().replace("\n","")
|
|
|
- tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
|
|
|
- if tag and (tag in scrutinize_tuple):
|
|
|
- tag_sign = tag
|
|
|
- evaluation_factor,evaluation_criteria,weights = table[evaluation_factor_index],table[evaluation_criteria_index],table[weights_index]
|
|
|
+ elif scrutinize_page+1 == page_number[0] and title_len == 5 and '报价' not in tag_sign:
|
|
|
+ if scrutinize_Initial_position_marker:
|
|
|
+ evaluation_factor_index -= 1
|
|
|
+ evaluation_criteria_index -= 1
|
|
|
+ weights_index -= 1
|
|
|
+ for table in tables:
|
|
|
+ if not table[2]:
|
|
|
+ scrutinize_dict[tag_sign][-1]['评分标准'] += table[3]
|
|
|
+ continue
|
|
|
+ tag = table[regulation_number_index+1]
|
|
|
+ if tag:
|
|
|
+ tag = tag.strip().replace("\n","")
|
|
|
+ tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
|
|
|
+ if tag and (tag in scrutinize_tuple):
|
|
|
+ tag_sign = tag
|
|
|
+ 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",""),
|
|
|
+ "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 '评审标准' in tag_sign:
|
|
|
+ scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
|
|
|
+ scrutinize_Initial_position_marker = 0
|
|
|
+ break
|
|
|
+ elif scrutinize_page+2 == page_number[0] and title_len == 5 and '报价' not in tag_sign:
|
|
|
+ for table in tables:
|
|
|
+ if not table[2]:
|
|
|
+ scrutinize_dict[tag_sign][-1]['评分标准'] += table[3]
|
|
|
+ continue
|
|
|
+ tag = table[regulation_number_index+1]
|
|
|
+ if tag:
|
|
|
+ tag = tag.strip().replace("\n","")
|
|
|
+ tag = re.findall("[\u4e00-\u9fff]+", tag)[0]
|
|
|
+ if tag and (tag in scrutinize_tuple):
|
|
|
+ tag_sign = tag
|
|
|
+ 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","")}
|
|
|
- scrutinize_dict[tag_sign].append(value)
|
|
|
- if '报价' in tag_sign and '评审标准' in tag_sign:
|
|
|
- scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
|
|
|
- break
|
|
|
- pprint(scrutinize_dict)
|
|
|
+ "评分标准":evaluation_criteria.strip().replace("\n",""),
|
|
|
+ "权重":weights.strip().replace("\n","")}
|
|
|
+ except:
|
|
|
+ print()
|
|
|
+ scrutinize_dict[tag_sign].append(value)
|
|
|
+ if '报价' in tag_sign and '评审标准' in tag_sign:
|
|
|
+ scrutinize_dict = {key: value for key, value in scrutinize_dict.items() if value}
|
|
|
+ break
|
|
|
|
|
|
-
|
|
|
- pprint(tag_dict)
|
|
|
- pprint(bidder_know)
|
|
|
- return tag_dict,bidder_know
|
|
|
+ # pprint(tag_dict)
|
|
|
+ # pprint(scrutinize_dict)
|
|
|
+ # pprint(bidder_know)
|
|
|
+ return tag_dict,bidder_know,scrutinize_dict
|
|
|
|
|
|
def get_announcement(self)->str:
|
|
|
''' bidder announcement
|
lfygithub01