164 lines
7.2 KiB
Python
164 lines
7.2 KiB
Python
import json
|
||
import re
|
||
|
||
|
||
def extract_content_after_special_chars(content):
|
||
"""
|
||
提取特定符号后的内容，直到遇到结束符号。
|
||
"""
|
||
pattern = r'[\x01\x02☑√团]([^□]+)'
|
||
match = re.search(pattern, content)
|
||
if match:
|
||
return match.group(1).strip() # 提取匹配的内容，并去除多余空格
|
||
return content # 如果没有找到匹配，返回原内容
|
||
|
||
def load_json(file_path):
|
||
"""
|
||
加载JSON文件，并统一其中的括号为全角括号。
|
||
"""
|
||
with open(file_path, 'r', encoding='utf-8') as f:
|
||
data = json.load(f)
|
||
return standardize_brackets_in_json(data)
|
||
|
||
def standardize_brackets_in_json(data):
|
||
"""
|
||
递归地处理JSON数据，将所有文本中的半角括号转换为全角括号。
|
||
"""
|
||
if isinstance(data, dict):
|
||
return {k: standardize_brackets_in_json(v) for k, v in data.items()}
|
||
elif isinstance(data, list):
|
||
return [standardize_brackets_in_json(element) for element in data]
|
||
elif isinstance(data, str):
|
||
return standardize_brackets(data)
|
||
else:
|
||
return data
|
||
|
||
def convert_dict_to_str(d):
|
||
if isinstance(d, dict):
|
||
return "\n".join(f"{k}: {v}" for k, v in d.items())
|
||
return str(d)
|
||
|
||
def extarct_normal(json_data, value, combined_value):
|
||
found_subentries = check_and_collect_subentries(json_data, value, combined_value)
|
||
if not found_subentries: #若无子条目，直接查找
|
||
content = json_data.get(value, "") #从一个字典 json_data 中获取与键名 value 相关联的值，默认值为""
|
||
if content:
|
||
combined_value.append(get_values_only(content))
|
||
return True
|
||
return found_subentries
|
||
|
||
#用于查找和处理由主条目派生的子条目 eg：如果 value 是 "1.1"，它将查找所有像 "1.1.1", "1.1.2" 等以 "1.1." 开头的键,不会匹配仅为 "1.1" 的键。
|
||
def check_and_collect_subentries(json_data, value, combined_value):
|
||
found_subentries = False
|
||
subentry_index = 1
|
||
for subkey in json_data:
|
||
if subkey.startswith(value + "."):
|
||
content = json_data[subkey]
|
||
combined_value.append(f"{subentry_index}. {get_values_only(content)}")
|
||
subentry_index += 1
|
||
found_subentries = True
|
||
return found_subentries
|
||
|
||
#针对于有子序号（）的情况
|
||
def extract_specific_subentry(content, subentry_key):
|
||
"""
|
||
提取指定的子条目文本，考虑全角和半角括号。
|
||
"""
|
||
subentry_index = subentry_key.replace("（", "").replace("）", "")
|
||
try:
|
||
idx = int(subentry_index)
|
||
bracket_pattern = f"（{idx}）"
|
||
parts = content.split(bracket_pattern)
|
||
if len(parts) > 1:
|
||
next_bracket_pattern = f"（{idx+1}）"
|
||
next_part = parts[1].split(next_bracket_pattern, 1)[0]
|
||
return next_part.strip()
|
||
except ValueError:
|
||
return ""
|
||
return ""
|
||
|
||
def extract_content_after_special_chars(content):
|
||
if not content:
|
||
return content
|
||
"""
|
||
提取特定符号后的内容，直到遇到结束符号或内容末尾。
|
||
"""
|
||
# 定义搜索特殊字符的正则表达式
|
||
pattern = r'[\x01\x02☑√团]([^□]*)'
|
||
match = re.search(pattern, content)
|
||
if match:
|
||
# 如果找到匹配，返回从特殊字符之后到下一个□或到内容末尾的部分
|
||
return match.group(1).strip() # 去除多余空白字符
|
||
# 如果没有找到特殊字符，返回原始内容
|
||
return content
|
||
|
||
def get_values_only(content):
|
||
if isinstance(content, dict):
|
||
# 如果内容是字典，首先将字典的值转换为字符串
|
||
content = " / ".join(content.values())
|
||
# 检查并处理特殊字符
|
||
return extract_content_after_special_chars(content)
|
||
def standardize_brackets(value):
|
||
"""
|
||
将输入中的所有半角括号转换为全角括号。
|
||
"""
|
||
return value.replace('(', '（').replace(')', '）')
|
||
|
||
def process_json_with_subentries(json_data, value, combined_value):
|
||
"""
|
||
处理JSON数据，寻找指定的条目，考虑全角和半角括号。
|
||
"""
|
||
value = standardize_brackets(value) #将1.11(1)->1.11（1）
|
||
if "（" in value and "）" in value: #存在（）的情况
|
||
first_content=get_values_only(json_data.get(value))
|
||
if first_content:
|
||
combined_value.append(first_content)
|
||
return True
|
||
base_key, subentry_key = value.split("（") #base_key:1.11 subentry_key:（1）
|
||
subentry_key = "（" + subentry_key
|
||
content = json_data.get(base_key.strip())
|
||
if content:
|
||
if isinstance(content, str):
|
||
extracted_content = extract_specific_subentry(content, subentry_key)
|
||
if extracted_content:
|
||
combined_value.append(extracted_content)
|
||
return True
|
||
else:
|
||
return False
|
||
else:
|
||
return extarct_normal(json_data, value, combined_value)
|
||
|
||
def find_entries_in_jsons(entries, json_primary, json_secondary):
|
||
results = {}
|
||
for entry in entries:
|
||
key, value = next(iter(entry.items()))
|
||
combined_value = []
|
||
# 先尝试在json_primary中寻找，如果找不到再在json_secondary中查找
|
||
found_in_primary = process_json_with_subentries(json_primary, value, combined_value)
|
||
if not found_in_primary:
|
||
process_json_with_subentries(json_secondary, value, combined_value)
|
||
if combined_value:
|
||
results[key] = "\n".join(combined_value)
|
||
return results
|
||
def process_and_merge_entries(entries_with_numbers, primary_json_path, secondary_json_path):
|
||
primary_json_data = load_json(primary_json_path)
|
||
secondary_json_data = load_json(secondary_json_path)
|
||
combined_results = find_entries_in_jsons(entries_with_numbers, primary_json_data, secondary_json_data)
|
||
return combined_results
|
||
|
||
if __name__ == "__main__":
|
||
# Hypothetical entries and file paths for testing
|
||
# entries_with_numbers = [{'形式评审标准.投标文件签字盖章': '3.7.3(3)'}, {'形式评审标准.多标段投标': '10.1'}, {'形式评审标准.“技术暗标”': '3.7.4(5)'}, {'响应性评审标准.投标内容': '1.3.1'}, {'响应性评审标准.工期': '1.3.2'}, {'响应性评审标准.工程质量': '1.3.3'}, {'响应性评审标准.投标有效期': '3.3.1'}, {'响应性评审标准.投标保证金': '3.4.1'}, {'响应性评审标准.分包计划': '1.11'}]
|
||
entries_with_numbers=[{'xxx': '3.6.3(5)'}]
|
||
primary_json_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\truncate_output.json'
|
||
secondary_json_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\clause.json'
|
||
|
||
# Since this is just a test block, make sure these paths point to actual JSON files with the appropriate structure
|
||
try:
|
||
combined_results = process_and_merge_entries(entries_with_numbers, primary_json_path, secondary_json_path)
|
||
print("Combined Results:", json.dumps(combined_results, indent=4, ensure_ascii=False))
|
||
except FileNotFoundError:
|
||
print("One or more JSON files were not found. Please check the file paths.")
|
||
except json.JSONDecodeError:
|
||
print("One or more files could not be decoded. Please check the file content.")
|