Java 完美判断字符串中中文字符【中文符号】

时间:2022-12-17 13:45:22
package com.cmc.util;

import java.util.regex.Pattern;

public class CharUtil {

    public static void main(String[] args) {
String[] strArr = new String[] { "www.micmiu.com", "!@#$%^&*()_+{}[]|\"'?/:;<>,.", "!¥……()——:;“”‘’《》,。?、", "不要啊", "やめて", "韩佳人", "???" };
for (String str : strArr) {
System.out.println("===========> 测试字符串:" + str);
System.out.println("正则判断结果:" + isChineseByREG(str) + " -- " + isChineseByName(str));
System.out.println("Unicode判断结果 :" + isChinese(str));
System.out.println("详细判断列表:");
char[] ch = str.toCharArray();
for (int i = ; i < ch.length; i++) {
char c = ch[i];
System.out.println(c + " --> " + (isChinese(c) ? "是" : "否"));
}
}
} //根据Unicode编码完美的判断中文汉字和符号
private static boolean isChinese(char c){
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.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B
|| ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS
|| ub == Character.UnicodeBlock.GENERAL_PUNCTUATION){
return true;
}
return false;
} //完整的判断中文汉字和符号
public static boolean isChinese(String strName){
char[] ch=strName.toCharArray();
for (int i = ; i < ch.length; i++) {
char c=ch[i];
if(isChinese(c)){
return true;
}
}
return false;
} //只能判断部分CJK字符(CJK统一汉字)
public static boolean isChineseByREG(String str){
if(str==null){
return false;
}
Pattern patter=Pattern.compile("[\\u4E00-\\u9FBF]+");
return patter.matcher(str.trim()).find();
} //只能判断部分CJK字符(CJK统一汉字)
public static boolean isChineseByName(String str){
if(str==null){
return false;
}
// 大小写不同:\\p 表示包含,\\P 表示不包含
// \\p{Cn} 的意思为 Unicode 中未被定义字符的编码,\\P{Cn} 就表示 Unicode中已经被定义字符的编码
String reg = "\\p{InCJK Unified Ideographs}&&\\P{Cn}";
Pattern pattern = Pattern.compile(reg);
return pattern.matcher(str.trim()).find();
}
}