156 lines
6.9 KiB
Python
156 lines
6.9 KiB
Python
import json
|
||
import re
|
||
|
||
|
||
# 对于每个target_value元素，如果有完美匹配json_data中的键，那就加入这个完美匹配的键名，否则，把全部模糊匹配到的键名都加入
|
||
def find_keys_by_value(target_value, json_data):
|
||
matched_keys = [k for k, v in json_data.items() if v == target_value] #首先检查 JSON 中的每个键值对，如果值完全等于目标值，则将这些键收集起来。
|
||
if not matched_keys:
|
||
matched_keys = [k for k, v in json_data.items() if isinstance(v, str) and v.startswith(target_value)] #如果没有找到完全匹配的键，它会检查字符串类型的值是否以目标值开头，并收集这些键。
|
||
return matched_keys # eg:[3.1,3.1.1,3.1.2,3.2...]
|
||
|
||
|
||
# 定义查找以特定前缀开始的键的函数，eg:若match_keys中有3.1，那么以3.1为前缀的键都会被找出来，如3.1.1 3.1.2...
|
||
def find_keys_with_prefix(key_prefix, json_data):
|
||
subheadings = [k for k in json_data if k.startswith(key_prefix)]
|
||
return subheadings
|
||
|
||
|
||
# 从文件中读取JSON数据，并提取特定内容
|
||
def extract_json(data, target_values):
|
||
results = {}
|
||
for target_value in target_values:
|
||
matched_keys = find_keys_by_value(target_value, data)
|
||
for key in matched_keys:
|
||
key_and_subheadings = find_keys_with_prefix(key, data)
|
||
for subkey in key_and_subheadings:
|
||
if "." in subkey:
|
||
parent_key = subkey.rsplit('.', 1)[0]
|
||
top_level_key = parent_key.split('.')[0] + '.'
|
||
# 特别处理定标相关的顶级键，确保不会重复添加其他键
|
||
if top_level_key not in results:
|
||
results[top_level_key] = target_value
|
||
# 添加或更新父级键
|
||
if parent_key not in results:
|
||
if parent_key in data:
|
||
results[parent_key] = data[parent_key]
|
||
# 添加当前键
|
||
results[subkey] = data[subkey]
|
||
return results
|
||
|
||
def sort_clean_data_keys(data):
|
||
# 预处理：删除键名中的空格
|
||
def preprocess_key(key):
|
||
return re.sub(r'\s+', '', key)
|
||
|
||
# 将键转换成由整数构成的元组，作为排序依据
|
||
def key_func(key):
|
||
return tuple(int(part) for part in re.split(r'\D+', key) if part)
|
||
|
||
# 创建一个新的字典，键名经过预处理
|
||
preprocessed_data = {preprocess_key(key): value for key, value in data.items()}
|
||
|
||
# 对预处理后的字典键进行排序
|
||
sorted_keys = sorted(preprocessed_data.keys(), key=key_func)
|
||
|
||
# 创建一个新的字典，按照排序后的键添加键值对
|
||
sorted_data = {key: preprocessed_data[key] for key in sorted_keys}
|
||
|
||
return sorted_data
|
||
|
||
# 转换结构化的JSON数据
|
||
def transform_json(data):
|
||
result = {}
|
||
temp = {0: result} # 初始化根字典
|
||
|
||
# 首先，创建一个临时字典用于检查是否存在三级标题
|
||
has_subkey = {}
|
||
for key in data.keys():
|
||
parts = key.split('.')
|
||
if len(parts) > 2 and parts[1]:
|
||
parent_key = parts[0] + '.' + parts[1]
|
||
has_subkey[parent_key] = True
|
||
|
||
for key, value in data.items():
|
||
match = re.match(r'(\d+)(?:\.(\d+))?(?:\.(\d+))?', key)
|
||
if match:
|
||
levels = [int(l) for l in match.groups() if l is not None]
|
||
if (len(levels) - 1) in temp:
|
||
parent = temp[len(levels) - 1]
|
||
else:
|
||
print(f"No parent found at level {len(levels) - 1} for key '{key}'. Check the data structure.")
|
||
continue
|
||
|
||
if len(levels) == len(match.groups()):
|
||
if isinstance(parent, list):
|
||
parent.append(value)
|
||
else:
|
||
# 对于根级别，使用完整的值作为键
|
||
if len(levels) == 1:
|
||
parent[value] = {}
|
||
temp[len(levels)] = parent[value]
|
||
else:
|
||
parent[value.split()[0]] = value
|
||
else:
|
||
new_key = value
|
||
if '\n' in value and len(levels) == 2 and f"{levels[0]}.{levels[1]}" not in has_subkey:
|
||
new_key, new_value = value.split('\n', 1)
|
||
new_key = new_key.strip()
|
||
new_value = new_value.strip()
|
||
if isinstance(parent, list):
|
||
if len(parent) == 0 or not isinstance(parent[-1], dict):
|
||
parent.append({})
|
||
parent[-1][new_key] = new_value
|
||
else:
|
||
parent[new_key] = new_value
|
||
else:
|
||
if isinstance(parent, list):
|
||
if len(parent) == 0 or not isinstance(parent[-1], dict):
|
||
parent.append({})
|
||
parent = parent[-1]
|
||
if new_key not in parent:
|
||
parent[new_key] = []
|
||
temp[len(levels)] = parent[new_key]
|
||
|
||
def remove_single_item_lists(node):
|
||
if isinstance(node, dict):
|
||
for key in list(node.keys()):
|
||
node[key] = remove_single_item_lists(node[key])
|
||
if isinstance(node[key], list) and not node[key]:
|
||
node[key] = ""
|
||
elif isinstance(node, list) and len(node) == 1:
|
||
return remove_single_item_lists(node[0])
|
||
return node
|
||
|
||
return remove_single_item_lists(result)
|
||
|
||
|
||
# 读取JSON数据，提取内容，转换结构，并打印结果
|
||
def extract_from_notice(clause_path, type):
|
||
if type == 1:
|
||
target_values = ["投标","投标文件"]
|
||
elif type == 2:
|
||
target_values = ["开标", "评标", "定标"]
|
||
elif type == 3:
|
||
target_values = ["重新招标、不再招标和终止招标", "重新招标", "不再招标", "终止招标"]
|
||
else:
|
||
raise ValueError("Invalid type specified. Use 1 for '投标文件, 投标' or 2 for '开标, 评标, 定标'or 3 for '重新招标'")
|
||
with open(clause_path, 'r', encoding='utf-8') as file:
|
||
data = json.load(file)
|
||
extracted_data = extract_json(data, target_values) # 读取json
|
||
sorted_data=sort_clean_data_keys(extracted_data) #对键进行排序
|
||
transformed_data = transform_json(sorted_data)
|
||
return transformed_data
|
||
|
||
|
||
#TODO:考虑5.1这种二级标题后面换行符，但是仍然存在5.1.1情况时该怎么办 再审视一下zbtest20的处理是否合理
|
||
if __name__ == "__main__":
|
||
file_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\tmp\\clause1.json'
|
||
# file_path='C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\clause1.json'
|
||
try:
|
||
res = extract_from_notice(file_path, 2) # 可以改变此处的 type 参数测试不同的场景
|
||
res2=json.dumps(res,ensure_ascii=False,indent=4)
|
||
print(res2)
|
||
except ValueError as e:
|
||
print(e)
|