10.18小解析
This commit is contained in:
parent
d06d6a145f
commit
861a54a378
@ -48,6 +48,15 @@ def pdf2docx(local_path_in):
|
||||
print(f"format_change p2d:have downloaded file to: {downloaded_filepath}")
|
||||
return downloaded_filepath
|
||||
|
||||
def doc2docx(local_path_in):
|
||||
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/d2d'
|
||||
receive_download_url = upload_file(local_path_in, remote_url)
|
||||
print(receive_download_url)
|
||||
filename, folder = get_filename_and_folder(local_path_in) # 输入输出在同一个文件夹
|
||||
local_filename = os.path.join(folder, filename) # 输出文件名
|
||||
downloaded_filepath, file_type = download_file(receive_download_url, local_filename)
|
||||
print(f"format_change d2d:have downloaded file to: {downloaded_filepath}")
|
||||
return downloaded_filepath
|
||||
def docx2pdf(local_path_in):
|
||||
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/d2p'
|
||||
receive_download_url = upload_file(local_path_in, remote_url)
|
||||
@ -60,8 +69,8 @@ def docx2pdf(local_path_in):
|
||||
if __name__ == '__main__':
|
||||
# 替换为你的文件路径和API URL
|
||||
local_path_in="C:\\Users\\Administrator\\Desktop\\货物标\\zbfilesdocx\\磋商文件(1).doc"
|
||||
# pdf2docx(local_path_in)
|
||||
downloaded_file=docx2pdf(local_path_in)
|
||||
downloaded_file=doc2docx(local_path_in)
|
||||
# downloaded_file=docx2pdf(local_path_in)
|
||||
print(downloaded_file)
|
||||
|
||||
|
||||
|
||||
@ -1,22 +1,51 @@
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
def extract_content_from_json(string):
|
||||
"""输入字符串，提取 { 和 } 之间的内容，并将其解析为字典"""
|
||||
"""
|
||||
输入字符串，提取 { 和 } 之间的内容，并将其解析为字典。
|
||||
如果使用 insert_missing_commas 修复后仍然失败，则尝试返回原始的解析结果（如果可能）。
|
||||
"""
|
||||
if not string.strip():
|
||||
return {}
|
||||
|
||||
# 提取第一个匹配的 JSON 对象
|
||||
match = re.search(r'\{[\s\S]*\}', string)
|
||||
if match:
|
||||
json_data = match.group(0)
|
||||
try:
|
||||
json_data = match.group(0)
|
||||
return json.loads(json_data) #返回字典
|
||||
except json.JSONDecodeError as e:
|
||||
print(f"json_utils: extract_content_from_json: JSON decode error: {e}")
|
||||
return {}
|
||||
# 尝试直接解析原始 JSON 数据
|
||||
return json.loads(json_data)
|
||||
except json.JSONDecodeError as original_error:
|
||||
print(f"原始 JSON 解析失败: {original_error}")
|
||||
try:
|
||||
# 尝试修复缺失的逗号
|
||||
fixed_json = insert_missing_commas(json_data)
|
||||
return json.loads(fixed_json)
|
||||
except json.JSONDecodeError as fixed_error:
|
||||
print(f"修复后的 JSON 解析失败: {fixed_error}")
|
||||
# 可选：返回空字典或其他默认值
|
||||
return {}
|
||||
else:
|
||||
print("json_utils: extract_content_from_json: No valid JSON content found.")
|
||||
print("json_utils: extract_content_from_json: 未找到有效的 JSON 内容。")
|
||||
return {}
|
||||
|
||||
def insert_missing_commas(json_str):
|
||||
"""
|
||||
使用正则表达式在缺失逗号的位置插入逗号。
|
||||
具体来说，寻找一个值的结束引号后紧跟着下一个键的开始引号，并在中间插入逗号。
|
||||
"""
|
||||
# 这个正则匹配一个字符串结尾的引号，可能有空白字符，然后是另一个键的引号
|
||||
pattern = r'(":\s*"[^"]*)"\s*(")'
|
||||
replacement = r'\1", \2'
|
||||
|
||||
previous_str = None
|
||||
while previous_str != json_str:
|
||||
previous_str = json_str
|
||||
json_str = re.sub(pattern, replacement, json_str)
|
||||
|
||||
return json_str
|
||||
def clean_json_string(json_string):
|
||||
"""清理JSON字符串，移除多余的反引号并解析为字典"""
|
||||
return extract_content_from_json(json_string)
|
||||
|
||||
@ -43,20 +43,30 @@ def aggregate_basic_info_engineering(baseinfo_list):
|
||||
|
||||
# 合并所有基础信息并收集相关键
|
||||
for baseinfo in baseinfo_list:
|
||||
# json_data = clean_json_string(baseinfo)
|
||||
combined_data.update(baseinfo)
|
||||
relevant_keys_detected.update(baseinfo.keys())
|
||||
|
||||
# 动态调整键组
|
||||
dynamic_key_handling(key_groups, relevant_keys_detected)
|
||||
|
||||
# 创建一个副本以存储未分类的项目
|
||||
unclassified_items = {k: v for k, v in combined_data.items() if k not in [item for sublist in key_groups.values() for item in sublist]}
|
||||
|
||||
# 按键组分类并嵌套
|
||||
for group_name, keys in key_groups.items():
|
||||
group_data = {key: combined_data.get(key, "未提供") for key in keys}
|
||||
combined_data[group_name] = group_data
|
||||
# Optionally remove original keys to avoid duplication
|
||||
# 从 unclassified_items 中移除已分类的键
|
||||
for key in keys:
|
||||
combined_data.pop(key, None)
|
||||
unclassified_items.pop(key, None)
|
||||
|
||||
# 将剩余未分类的键值对添加到 "其他信息" 组
|
||||
combined_data["其他信息"].update(unclassified_items)
|
||||
|
||||
# 移除顶层的未分类键值对
|
||||
for key in list(combined_data.keys()):
|
||||
if key not in key_groups:
|
||||
del combined_data[key]
|
||||
|
||||
return combined_data
|
||||
|
||||
|
||||
@ -43,20 +43,30 @@ def aggregate_basic_info_engineering(baseinfo_list):
|
||||
|
||||
# 合并所有基础信息并收集相关键
|
||||
for baseinfo in baseinfo_list:
|
||||
# json_data = clean_json_string(baseinfo)
|
||||
combined_data.update(baseinfo)
|
||||
relevant_keys_detected.update(baseinfo.keys())
|
||||
|
||||
# 动态调整键组
|
||||
dynamic_key_handling(key_groups, relevant_keys_detected)
|
||||
|
||||
# 创建一个副本以存储未分类的项目
|
||||
unclassified_items = {k: v for k, v in combined_data.items() if k not in [item for sublist in key_groups.values() for item in sublist]}
|
||||
|
||||
# 按键组分类并嵌套
|
||||
for group_name, keys in key_groups.items():
|
||||
group_data = {key: combined_data.get(key, "未提供") for key in keys}
|
||||
combined_data[group_name] = group_data
|
||||
# Optionally remove original keys to avoid duplication
|
||||
# 从 unclassified_items 中移除已分类的键
|
||||
for key in keys:
|
||||
combined_data.pop(key, None)
|
||||
unclassified_items.pop(key, None)
|
||||
|
||||
# 将剩余未分类的键值对添加到 "其他信息" 组
|
||||
combined_data["其他信息"].update(unclassified_items)
|
||||
|
||||
# 移除顶层的未分类键值对
|
||||
for key in list(combined_data.keys()):
|
||||
if key not in key_groups:
|
||||
del combined_data[key]
|
||||
|
||||
return combined_data
|
||||
|
||||
@ -113,27 +123,22 @@ def combine_basic_info(merged_baseinfo_path,truncate0, output_folder, clause_pat
|
||||
返回：
|
||||
- dict: 综合后的基础信息。
|
||||
"""
|
||||
baseinfo_list = []
|
||||
baseinfo_file_path = 'flask_app/static/提示词/基本信息工程标.txt'
|
||||
# baseinfo_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\基本信息工程标.txt'
|
||||
questions = read_questions_from_file(baseinfo_file_path)
|
||||
res1 = multi_threading(questions, knowledge_name)
|
||||
|
||||
for index, response in res1:
|
||||
try:
|
||||
if response and len(response) > 1:
|
||||
baseinfo_list.append(clean_json_string(response[1]))
|
||||
else:
|
||||
print(f"基础信息整合： Warning: Missing or incomplete response data for query index {index}.")
|
||||
except Exception as e:
|
||||
print(f"基础信息整合： Error processing response for query index {index}: {e}")
|
||||
# baseinfo_prompt_file_path='flask_app/static/提示词/基本信息工程标qianwen-long.txt'
|
||||
baseinfo_prompt_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\基本信息工程标qianwen-long.txt'
|
||||
questions = read_questions_from_file(baseinfo_prompt_file_path)
|
||||
file_id = upload_file(merged_baseinfo_path)
|
||||
baseinfo_results = multi_threading(questions, "", file_id, 2)
|
||||
# 清理 JSON 字符串
|
||||
baseinfo_list = [clean_json_string(res) for _, res in baseinfo_results] if baseinfo_results else []
|
||||
for i in baseinfo_list:
|
||||
print(json.dumps(i,ensure_ascii=False,indent=4))
|
||||
|
||||
# 判断是否分包、是否需要递交投标保证金等
|
||||
chosen_numbers, merged = judge_whether_main(truncate0, output_folder)
|
||||
baseinfo_list.append(merged)
|
||||
|
||||
judge_file_path = 'flask_app/static/提示词/是否相关问题.txt'
|
||||
# judge_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\是否相关问题.txt'
|
||||
# judge_file_path = 'flask_app/static/提示词/是否相关问题.txt'
|
||||
judge_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\是否相关问题.txt'
|
||||
judge_questions = read_questions_from_judge(judge_file_path, chosen_numbers)
|
||||
judge_consortium = judge_consortium_bidding(baseinfo_list) # 通过招标公告判断是否接受联合体投标
|
||||
|
||||
@ -159,11 +164,12 @@ def combine_basic_info(merged_baseinfo_path,truncate0, output_folder, clause_pat
|
||||
aggregated_baseinfo = aggregate_basic_info_engineering(baseinfo_list) # 现在是一个字典
|
||||
return {"基础信息": aggregated_baseinfo}
|
||||
|
||||
#TODO:先不带投标人须知正文，如果是未知，再直接问正文，
|
||||
if __name__ == "__main__":
|
||||
merged_baseinfo_path="C:\\Users\\Administrator\\Desktop\\招标文件\\special_output\\zbtest2_merged_baseinfo.pdf"
|
||||
output_folder="C:\\Users\Administrator\Desktop\\fsdownload\\3424b7cb-1f85-44b4-a432-44539b870405"
|
||||
truncate0="C:\\Users\Administrator\Desktop\\fsdownload\\3424b7cb-1f85-44b4-a432-44539b870405\\ztbfile_tobidders_notice_table.pdf"
|
||||
clause_path="C:\\Users\Administrator\Desktop\\fsdownload\\3424b7cb-1f85-44b4-a432-44539b870405\\clause1.json"
|
||||
output_folder="C:\\Users\\Administrator\\Desktop\\招标文件\\special_output"
|
||||
truncate0="C:\\Users\\Administrator\\Desktop\\招标文件\\special_output\\zbtest2_tobidders_notice_table.pdf"
|
||||
clause_path="C:\\Users\\Administrator\\Desktop\\招标文件\\special_output\\clause1.json"
|
||||
res=combine_basic_info(merged_baseinfo_path,truncate0,output_folder,clause_path)
|
||||
print(json.dumps(res,ensure_ascii=False,indent=4))
|
||||
|
||||
|
||||
@ -230,14 +230,14 @@ def convert_clause_to_json(input_path,output_folder,type=1):
|
||||
# json.dump(processed_data, file, ensure_ascii=False, indent=4)
|
||||
|
||||
if __name__ == "__main__":
|
||||
file_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\招标01'
|
||||
file_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\special_output\\zbtest2_tobidders_notice.pdf'
|
||||
# file_path='C:\\Users\\Administrator\\Desktop\\货物标\\output4\\招招招标文件（一中多媒体报告厅教学设备）_tobidders_notice_part1.pdf'
|
||||
# start_word = "投标人须知正文"
|
||||
# end_phrases = [
|
||||
# r'^第[一二三四五六七八九十]+章\s+评标办法', r'^评标办法前附表', r'^附录：', r'^附录一：', r'^附件：', r'^附件一：',
|
||||
# r'^附表：', r'^附表一：', r'^附录:', r'^附录一:', r'^附件:', r'^附件一:', r'^附表:', r'^附表一:',
|
||||
# ]
|
||||
output_folder = 'C:\\Users\\Administrator\\Desktop\\招标文件\\test3\\tmp'
|
||||
output_folder = 'C:\\Users\\Administrator\\Desktop\\招标文件\\special_output'
|
||||
try:
|
||||
output_path = convert_clause_to_json(file_path,output_folder)
|
||||
print(f"Final JSON result saved to: {output_path}")
|
||||
|
||||
@ -42,8 +42,8 @@ def preprocess_files(output_folder, downloaded_file_path, file_type, unique_id):
|
||||
logger.error("Unsupported file type provided. Preprocessing halted.")
|
||||
return None
|
||||
|
||||
# 异步上传知识库
|
||||
future_knowledge = executor.submit(addfileToKnowledge, docx_path, "招标解析" + unique_id)
|
||||
# # 异步上传知识库
|
||||
# future_knowledge = executor.submit(addfileToKnowledge, docx_path, "招标解析" + unique_id)
|
||||
|
||||
# 调用截取PDF多次
|
||||
truncate_files = truncate_pdf_multiple(pdf_path, output_folder)
|
||||
@ -55,6 +55,7 @@ def preprocess_files(output_folder, downloaded_file_path, file_type, unique_id):
|
||||
truncate0 = truncate_files[0]
|
||||
truncate1 = truncate_files[1]
|
||||
truncate3 = truncate_files[3]
|
||||
merged_baseinfo_path=truncate_files[-1]
|
||||
clause_path = convert_clause_to_json(truncate_files[2], output_folder) # 投标人须知正文条款pdf->json
|
||||
|
||||
logger.info("文件预处理done")
|
||||
@ -66,8 +67,9 @@ def preprocess_files(output_folder, downloaded_file_path, file_type, unique_id):
|
||||
'truncate0': truncate0,
|
||||
'truncate1': truncate1,
|
||||
'truncate3': truncate3,
|
||||
'knowledge_future': future_knowledge, # 返回 Future 对象
|
||||
# 'knowledge_future': future_knowledge, # 返回 Future 对象
|
||||
'truncate0_jsonpath': truncate_jsonpath,
|
||||
'merged_baseinfo_path':merged_baseinfo_path,
|
||||
'clause_path': clause_path,
|
||||
'invalid_docpath': invalid_docpath
|
||||
}
|
||||
|
||||
@ -2,7 +2,7 @@
|
||||
|
||||
2.该招标文件的工程概况（或项目概况）是？招标范围是？请按json格式给我提供信息，键名分别为'项目概况','招标范围'，若存在嵌套信息，嵌套内容键名以文件中对应字段命名，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
3.该招标文件的招标控制价（可指代投标限价、投资概算金额、工程概算金额、合同估算价，但非监理费用）是？请按json格式给我提供信息，键名为'招标控制价'，若存在未知信息，在对应的键值中填'未知'。
|
||||
3.该招标文件的招标控制价（或投标限价或预算金额或合同估算价，但非监理费用）是？请按json格式给我提供信息，键名为'招标控制价'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
4.投标文件递交截止日期是？递交方式是？请按json格式给我提供信息，键名分别是'投标文件递交截止日期','投标文件递交方式',若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
|
||||
25
flask_app/static/提示词/基本信息工程标qianwen-long.txt
Normal file
25
flask_app/static/提示词/基本信息工程标qianwen-long.txt
Normal file
@ -0,0 +1,25 @@
|
||||
1.该招标文件的项目名称（或工程名称）是？招标编号（或项目编号）是？招标人是？招标代理机构是？请按json格式给我提供信息，键名分别是'项目名称','招标编号','招标人','招标代理机构'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
2.该招标文件的项目概况（或工程概况）是？招标范围是？请按json格式给我提供信息，键名分别为'项目概况','招标范围'，若存在嵌套信息，嵌套内容键名以文件中对应字段命名，而嵌套键值必须与原文保持一致，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
3.该招标文件的招标控制价（或投标限价或预算金额或合同估算价，但非监理费用）是？请按json格式给我提供信息，键名为'招标控制价'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
4.投标文件递交截止日期是？递交方式是？请按json格式给我提供信息，键名分别是'投标文件递交截止日期','投标文件递交方式',若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
5.招标人和招标代理机构的联系方式是？请按json格式给我提供信息，键名分别是'招标人联系方式'，'招标代理机构联系方式',若存在嵌套信息，嵌套内容键名以文件中对应字段命名，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
6.该招标文件的评标结果（或相关信息）公示媒介在哪？请按json格式给我提供信息，键名是'评标结果公示媒介'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
7.该招标文件的投标竞争下浮率是多少？请按json格式给我提供信息，键名是'投标竞争下浮率'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
8.该项目的投标有效期是多久（或自投标截止之日起多久之内有效）？请按json格式给我提供信息，键名是'投标有效期'，键值为文中相关表述，不得擅自总结、删减，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
9.该招标文件中对投标人准备和参加投标活动发生的费用是如何规定的？请以json的格式给我提供信息，键名是'投标费用承担'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
10.投标人要求澄清招标文件的截止时间是？请以json的格式给我提供信息，键名是'投标人要求澄清招标文件的截止时间'，若存在未知信息，在对应的键值中填'未知'。
|
||||
|
||||
11.该文档要求扣留的质量保证金百分比是多少，请以json格式给我提供信息，键名为'质量保证金'，如果没有则以'未知'填充。
|
||||
|
||||
12.该项目是否接受联合体投标？请按json格式给我提供信息，键名为'是否接受联合体投标'，'是否接受联合体投标'的键值仅限于'是'、'否'、'未知'。
|
||||
|
||||
13.该项目的开标时间（或开启时间）和开标地点是？请按json格式给我提供信息，键名为'开标时间'和'开标地点'，对于"开标时间"，若文中没有明确时间，将其键值设为文中相关表述，若存在未知信息，在对应的键值中填'未知'。
|
||||
@ -52,13 +52,25 @@ def aggregate_basic_info_goods(baseinfo_list):
|
||||
# 动态调整键组
|
||||
dynamic_key_handling(key_groups, relevant_keys_detected)
|
||||
|
||||
# 创建一个副本以存储未分类的项目
|
||||
unclassified_items = {k: v for k, v in combined_data.items() if
|
||||
k not in [item for sublist in key_groups.values() for item in sublist]}
|
||||
|
||||
# 按键组分类并嵌套
|
||||
for group_name, keys in key_groups.items():
|
||||
group_data = {key: combined_data.get(key, "未提供") for key in keys}
|
||||
combined_data[group_name] = group_data
|
||||
# Optionally remove original keys to avoid duplication
|
||||
# 从 unclassified_items 中移除已分类的键
|
||||
for key in keys:
|
||||
combined_data.pop(key, None)
|
||||
unclassified_items.pop(key, None)
|
||||
|
||||
# 将剩余未分类的键值对添加到 "其他信息" 组中
|
||||
combined_data["其他信息"].update(unclassified_items)
|
||||
|
||||
# 移除顶层的未分类键值对
|
||||
for key in list(combined_data.keys()):
|
||||
if key not in key_groups:
|
||||
del combined_data[key]
|
||||
|
||||
return combined_data
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user