141 lines
6.8 KiB
Python
141 lines
6.8 KiB
Python
import json
|
||
import re
|
||
from flask_app.general.投标人须知正文提取指定内容 import process_nested_data, transform_json, get_requirements_with_gpt,extract_sections
|
||
|
||
|
||
# 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
|
||
|
||
|
||
# 从完整的json文件中读取所需数据，eg:投标、评标
|
||
# def extract_json(data, target_values):
|
||
# results = {}
|
||
#
|
||
# # 遍历所有目标值
|
||
# for target_value in target_values:
|
||
# # 找到所有与目标值匹配的键
|
||
# matched_keys = find_keys_by_value(target_value, data)
|
||
#
|
||
# for key in matched_keys:
|
||
# # 查找所有以该键为前缀的子键，限制只提取直接子项
|
||
# key_and_subheadings = find_keys_with_prefix(key, data)
|
||
#
|
||
# for subkey in key_and_subheadings:
|
||
# # 如果子键有多级结构（比如 '7.2.1'），并且是直接子项
|
||
# if "." in subkey:
|
||
# parent_key = subkey.rsplit('.', 1)[0]
|
||
# top_level_key = parent_key.split('.')[0] + '.'
|
||
#
|
||
# # 确保顶级键不会重复添加
|
||
# if top_level_key not in results:
|
||
# results[top_level_key] = data[top_level_key]
|
||
#
|
||
# # 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]
|
||
#
|
||
# # 添加当前子键和它的值
|
||
# if subkey in data:
|
||
# results[subkey] = data[subkey]
|
||
#
|
||
# return results
|
||
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
|
||
|
||
"""
|
||
递归处理嵌套的数据结构（字典和列表）。
|
||
对最内层的字符串值应用 post_process 函数。
|
||
post_process 函数尝试将长字符串按特定模式分割成块，每块至少包含50个中英文字符。
|
||
如果字典中所有值都是 ""、"/" 或空列表，则返回'键'的列表。
|
||
"""
|
||
|
||
# 读取JSON数据，提取内容，转换结构，并打印结果
|
||
def extract_from_notice(merged_baseinfo_path,clause_path, type):
|
||
if type == 1:
|
||
target_values = ["投标","投标文件","响应文件"]
|
||
elif type == 2:
|
||
target_values = ["开标", "评标", "定标","磋商程序","中标"]
|
||
elif type == 3:
|
||
target_values = ["重新招标、不再招标和终止招标","重新招标","重新采购", "不再招标", "不再采购","终止招标","终止采购"]
|
||
elif type == 4:
|
||
target_values = ["评标"] # 测试
|
||
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
|
||
if not extracted_data:
|
||
final_result = get_requirements_with_gpt(merged_baseinfo_path, type) # 万一没用正则匹配到，那就调用大模型
|
||
return final_result
|
||
# print(json.dumps(extracted_data,ensure_ascii=False,indent=4))
|
||
final_result=extract_sections(extracted_data,target_values)
|
||
return final_result
|
||
# print(json.dumps(res, ensure_ascii=False, indent=4))
|
||
# sorted_data = sort_clean_data_keys(extracted_data) # 对输入的字典 data 的键进行预处理和排序
|
||
# transformed_data = transform_json(sorted_data)
|
||
# print(json.dumps(transformed_data,ensure_ascii=False,indent=4))
|
||
# final_result = process_nested_data(transformed_data)
|
||
# return final_result
|
||
|
||
if __name__ == "__main__":
|
||
# file_path = 'C:\\Users\\Administrator\\Desktop\\fsdownload\\3bffaa84-2434-4bd0-a8ee-5c234ccd7fa0\\clause1.json'
|
||
merged_baseinfo_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\4e5bc6c2-c2b8-4c0b-8e57-81a498b982f6\\ztbfile_tobidders_notice.pdf"
|
||
clause_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\4e5bc6c2-c2b8-4c0b-8e57-81a498b982f6\\clause1.json"
|
||
try:
|
||
res = extract_from_notice(merged_baseinfo_path,clause_path, 1) # 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)
|