Java判断一个字符串中是否有中文字符有两种方法,但是原理都一样,就是通过Unicode编码来判断,因为中文在Unicode中的编码区间为:0x4e00--0x9fa5
第一种:
- String chineseStr = "中华人民公社abc";
- char[] charArray = chineseStr.toCharArray();
- for(int i=0;i<charArray.length;i++){
- if ((charArray[i] >= 0x4e00)&&(charArray[i] <= 0x9fa5)){
- System.out.println(charArray[i]);
- }
- }
String chineseStr = "中华人民公社abc";
char[] charArray = chineseStr.toCharArray();
for(int i=0;i<charArray.length;i++){
if ((charArray[i] >= 0x4e00)&&(charArray[i] <= 0x9fa5)){
System.out.println(charArray[i]);
}
}
第二种:
- String str = "中国chinese";
- for (int i = 0; i < str.length(); i++) {
- System.out.println(str.substring(i, i + 1).matches("[\\u4e00-\\u9fa5]+"));
- }
String str = "中国chinese";
for (int i = 0; i < str.length(); i++) {
System.out.println(str.substring(i, i + 1).matches("[\\u4e00-\\u9fa5]+"));
}
第三种:
- public class IsChineseOrEnglish {
- // GENERAL_PUNCTUATION 判断中文的“号
- // CJK_SYMBOLS_AND_PUNCTUATION 判断中文的。号
- // HALFWIDTH_AND_FULLWIDTH_FORMS 判断中文的,号
- public 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.GENERAL_PUNCTUATION
- || ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
- || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
- return true;
- }
- return false;
- }
- public static void isChinese(String strName) {
- char[] ch = strName.toCharArray();
- for (int i = 0; i < ch.length; i++) {
- char c = ch[i];
- if (isChinese(c) == true) {
- System.out.println(isChinese(c));
- return;
- } else {
- System.out.println(isChinese(c));
- return;
- }
- }
- }
- public static void main(String[] args) {
- // Random r = new Random();
- // for (int i = 0; i < 20; i++)
- // System.out.println(r.nextInt(10) + 1);
- isChinese("き");
- isChinese("中国");
- }
- }