Java获取匹配到的中文(正则表达式)
/**
* 获取所有匹配到的中文
* @param oriText
* @return
*/
public String getChineseWords(String oriText) {
if (oriText.isEmpty())
return "";
String reg = "[\u4E00-\u9FFF]+";
Pattern pattern = Pattern.compile(reg);
Matcher matcher = pattern.matcher(oriText);
StringBuilder builder = new StringBuilder();
while (matcher.find()) {
builder.append(matcher.group());
}
if(StringUtils.isEmpty(builder)){
return oriText;
} else {
return builder.toString();
}
}
/**
* 获取第一次匹配到的连续中文
* @param oriText
* @return
*/
public String getChineseWord(String oriText) {
String reg = "[\u4E00-\u9FFF]+";
Pattern pattern = Pattern.compile(reg);
Matcher matcher = pattern.matcher(oriText);
if (matcher.find()) {
return matcher.group();
}
return oriText;
}
public static void main(String[] args) throws IOException {
String ori = "n好呀3342111啥哈哈哈哈";
System.err.println(new GeneralUtil().getChineseWord(ori));
}