stata 正则 保留中文

use 0807a\xcv,clear
gen text_strings = B
. *仅保留中文字符
. replace text_strings=ustrregexra(text_strings,"[^\u4e00-\u9fa5]+"," ") 
. *去除中文数字
. replace text_strings=ustrregexra(text_strings,"[一二三四五六七八九十]+"," ")