优化医院名繁简转换

This commit is contained in:
2024-08-14 11:25:04 +08:00
parent 885e869659
commit 8e86337ff1
5 changed files with 13 additions and 3 deletions

View File

@@ -181,8 +181,8 @@ def parse_hospital(string):
if not string:
return result
string = util.traditional_to_simple_chinese(string)
string_without_brackets = string.replace(")", "").replace("", "").replace("(", " ").replace("", " ")
string_without_company = string_without_brackets.replace("有限公司", "")
simple_chinese_string = string_without_company.replace("", "")
result += simple_chinese_string.split(" ")
result += string_without_company.split(" ")
return result

View File

@@ -2,6 +2,8 @@ import logging
import os
from datetime import datetime
from opencc import OpenCC
from util import string_util
@@ -209,3 +211,9 @@ def chinese_money_to_number(chinese_money_amount):
amount += j / 10
amount += f / 100
return round(amount, 2)
# 将繁体字转换为简体字
def traditional_to_simple_chinese(traditional_chinese):
converter = OpenCC('t2s')
return converter.convert(traditional_chinese)