11.18 技术参数修改

This commit is contained in:
zy123 2024-11-18 16:12:11 +08:00
parent d77dde3f6e
commit a7abff0f8c
2 changed files with 101 additions and 74 deletions

View File

@ -7,6 +7,8 @@ from flask_app.general.format_change import pdf2docx, docx2pdf
from flask_app.general.通义千问long import upload_file from flask_app.general.通义千问long import upload_file
from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main
from flask_app.货物标.技术参数要求提取 import get_technical_requirements from flask_app.货物标.技术参数要求提取 import get_technical_requirements
from flask_app.货物标.技术参数要求提取后处理函数 import extract_matching_keys
def get_global_logger(unique_id): def get_global_logger(unique_id):
if unique_id is None: if unique_id is None:
@ -16,80 +18,6 @@ def get_global_logger(unique_id):
logger = None logger = None
def extract_matching_keys(data_dict, good_list):
"""
递归遍历data_dict查找good_list中存在的键完全匹配或以good_list中的键开头后跟-数字并将匹配的键及其值添加到结果字典中
对于重复的键名添加后缀 -a, -b, -c 等以确保唯一性
参数:
- data_dict (dict): 要遍历的嵌套字典
- good_list (list): 包含要查找的键的列表
返回:
- dict: 包含所有匹配键及其值的字典
"""
result = {}
key_count = {} # 用于统计每个匹配键的出现次数
# 预编译正则模式以提高效率
patterns = [re.compile(r'^' + re.escape(g) + r'(?:-\d+)?$') for g in good_list] #考虑同一系统下有同门设备,如交换机
def matches(key):
return any(pattern.match(key) for pattern in patterns)
# 第一次遍历:统计每个匹配键的出现次数
def first_pass(current_dict):
if isinstance(current_dict, dict):
for key, value in current_dict.items():
if matches(key):
key_count[key] = key_count.get(key, 0) + 1
first_pass(value)
elif isinstance(current_dict, list):
for item in current_dict:
first_pass(item)
first_pass(data_dict)
# 初始化用于跟踪每个重复键当前使用的后缀编号
suffix_map = {key: 0 for key, count in key_count.items() if count > 1}
def get_suffix(count):
"""
根据计数获取字母后缀例如 考虑不同系统下都有同门设备如交换机
1 -> '-a'
2 -> '-b'
...
26 -> '-z'
27 -> '-aa'
"""
letters = string.ascii_lowercase
suffix = ''
while count > 0:
count, remainder = divmod(count - 1, 26)
suffix = letters[remainder] + suffix
return '-' + suffix
# 第二次遍历:添加后缀并构建结果字典
def recurse(current_dict):
if isinstance(current_dict, dict):
for key, value in current_dict.items():
if matches(key):
if key_count.get(key, 0) > 1:
suffix_map[key] += 1
suffix = get_suffix(suffix_map[key])
new_key = f"{key}{suffix}"
else:
new_key = key
result[new_key] = value
recurse(value)
elif isinstance(current_dict, list):
for item in current_dict:
recurse(item)
# 如果current_dict不是dict或list则无需进一步处理
recurse(data_dict)
return result
def get_technical_requirements_main(file_path,file_type,unique_id,output_folder): def get_technical_requirements_main(file_path,file_type,unique_id,output_folder):
global logger global logger
logger = get_global_logger(unique_id) logger = get_global_logger(unique_id)

View File

@ -1,4 +1,103 @@
import json import json
import re
import string
from collections import OrderedDict
#传输技术参数需求的时候后处理
def extract_matching_keys(data_dict, good_list, special_keys=None):
"""
递归遍历data_dict查找good_list中存在的键完全匹配或以good_list中的键开头后跟-数字并将匹配的键及其值添加到结果字典中
对于重复的键名添加后缀 -a, -b, -c 等以确保唯一性
对于特殊键"系统功能"在键名前添加其父键名和''例如"交通信号的系统功能"
参数:
- data_dict (dict): 要遍历的嵌套字典
- good_list (list): 包含要查找的键的列表
- special_keys (list): 需要特殊处理的键的列表
返回:
- OrderedDict: 包含所有匹配键及其值的字典保持原始顺序
"""
if special_keys is None:
special_keys = []
result = OrderedDict()
key_count = {} # 用于统计每个匹配键的出现次数(不包括特殊键)
# 预编译正则模式以提高效率
patterns = [re.compile(r'^' + re.escape(g) + r'(?:-\d+)?$') for g in good_list]
def matches(key):
return any(pattern.match(key) for pattern in patterns)
# 第一次遍历:统计普通键的出现次数
def first_pass(current_dict):
if isinstance(current_dict, dict):
for key, value in current_dict.items():
if matches(key) and key not in special_keys:
key_count[key] = key_count.get(key, 0) + 1
# 递归遍历
if isinstance(value, dict):
first_pass(value)
elif isinstance(value, list):
first_pass(value)
elif isinstance(current_dict, list):
for item in current_dict:
first_pass(item)
first_pass(data_dict)
# 初始化用于跟踪每个重复键当前使用的后缀编号
suffix_map = {key: 0 for key, count in key_count.items() if count > 1}
def get_suffix(count):
"""
根据计数获取字母后缀例如
1 -> '-a'
2 -> '-b'
...
26 -> '-z'
27 -> '-aa'
"""
letters = string.ascii_lowercase
suffix = ''
while count > 0:
count, remainder = divmod(count - 1, 26)
suffix = letters[remainder] + suffix
return '-' + suffix
# 第二次遍历:添加后缀或前缀,并构建结果字典
def recurse(current_dict, parent_key=None):
if isinstance(current_dict, dict):
for key, value in current_dict.items():
if matches(key):
if key in special_keys:
# 对于特殊键,使用当前父键名加'的'前缀
new_key = f"{parent_key}{key}" if parent_key else key
result[new_key] = value
else:
if key_count.get(key, 0) > 1:
# 对于重复键,添加后缀以确保唯一性
suffix_map[key] += 1
suffix = get_suffix(suffix_map[key])
new_key = f"{key}{suffix}"
else:
new_key = key
result[new_key] = value
# 递归遍历
# 如果当前键是字典,新的父键是当前键
# 否则,保持原来的父键
if isinstance(value, dict):
recurse(value, parent_key=key)
elif isinstance(value, list):
recurse(value, parent_key=parent_key)
elif isinstance(current_dict, list):
for item in current_dict:
recurse(item, parent_key=parent_key)
recurse(data_dict)
return result
def postprocess(data): def postprocess(data):
"""递归地转换字典中的值为列表,如果所有键对应的值都是'/', '{}''未知'""" """递归地转换字典中的值为列表,如果所有键对应的值都是'/', '{}''未知'"""
def convert_dict(value): def convert_dict(value):