java中文字符转换_Java字符串中文检测转换

public class ChineseUtils {

public static void main(String[] args) {

String str= "中国 (1).jpg";

try {

String str2= new String(str.getBytes("iso-8859-1"),"iso-8859-1");

System.out.println(str2);

System.out.println(isMessyCode(str2));

System.out.println(toChinese(str2));

} catch (UnsupportedEncodingException e) {

e.printStackTrace();

}

}

private static boolean isChinese(charc) {

Character.UnicodeBlock ub=Character.UnicodeBlock.of(c);if (ub ==Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS|| ub ==Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS|| ub ==Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A|| ub ==Character.UnicodeBlock.GENERAL_PUNCTUATION|| ub ==Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION|| ub ==Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {

returntrue;

}

returnfalse;

}

public static boolean isMessyCode(String strName) {

Pattern p= Pattern.compile("\\s*|\t*|\r*|\n*");

Matcher m=p.matcher(strName);

String after= m.replaceAll("");

String temp= after.replaceAll("\\p{P}", "");char[] ch =temp.trim().toCharArray();float chLength = 0;float count = 0;for (int i = 0; i < ch.length; i++) {char c =ch[i];if (!Character.isLetterOrDigit(c)) {if (!isChinese(c)) {

count= count + 1;

}

chLength++;

}

}float result = count /chLength ;if (result > 0.4) {

returntrue;

}else{

returnfalse;

}

}

public static String toChinese(String msg){if(isMessyCode(msg)){

try {

return new String(msg.getBytes("ISO8859-1"), "UTF-8");

} catch (Exception e) {

}

}

return msg ;

}

}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值