Java 判断字符串是否是汉字

在Java中，判断一个字符串是否完全由汉字组成，或者判断字符串中是否包含汉字,可以通过以下几种方法实现：

使用正则表达式

public class ChineseCharacterChecker {
    public static boolean isAllChinese(String str) {
        if (str == null || str.isEmpty()) {
            return false;
        }
        return str.matches("^[\\u4e00-\\u9fa5]+$");
    }
    public static boolean containsChinese(String str) {
        if (str == null || str.isEmpty()) {
            return false;
        }
        return str.matches(".*[\\u4e00-\\u9fa5].*");
    }
    public static void main(String[] args) {
        String test1 = "汉字测试";
        String test2 = "Hello汉字";
        String test3 = "Hello123";
        System.out.println(isAllChinese(test1)); // true
        System.out.println(isAllChinese(test2)); // false
        System.out.println(isAllChinese(test3)); // false
        System.out.println(containsChinese(test1)); // true
        System.out.println(containsChinese(test2)); // true
        System.out.println(containsChinese(test3)); // false
    }
}

使用Character类

public class ChineseCharacterChecker {
    public static boolean isAllChinese(String str) {
        if (str == null || str.isEmpty()) {
            return false;
        }
        for (char c : str.toCharArray()) {
            if (!isChinese(c)) {
                return false;
            }
        }
        return true;
    }
    public static boolean containsChinese(String str) {
        if (str == null || str.isEmpty()) {
            return false;
        }
        for (char c : str.toCharArray()) {
            if (isChinese(c)) {
                return true;
            }
        }
        return false;
    }
    private static boolean isChinese(char c) {
        Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
        return 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;
    }
    public static void main(String[] args) {
        String test1 = "汉字测试";
        String test2 = "Hello汉字";
        String test3 = "Hello123";
        System.out.println(isAllChinese(test1)); // true
        System.out.println(isAllChinese(test2)); // false
        System.out.println(isAllChinese(test3)); // false
        System.out.println(containsChinese(test1)); // true
        System.out.println(containsChinese(test2)); // true
        System.out.println(containsChinese(test3)); // false
    }
}

使用Apache Commons Lang库

如果你使用Apache Commons Lang库，可以使用StringUtils类：

import org.apache.commons.lang3.StringUtils;
import org.apache.commons.lang3.CharUtils;
public class ChineseCharacterChecker {
    public static boolean isAllChinese(String str) {
        if (str == null || str.isEmpty()) {
            return false;
        }
        for (char c : str.toCharArray()) {
            if (!CharUtils.isAscii(c) && !isChinese(c)) {
                return false;
            }
        }
        return true;
    }
    private static boolean isChinese(char c) {
        Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
        return 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;
    }
    public static void main(String[] args) {
        String test1 = "汉字测试";
        String test2 = "Hello汉字";
        String test3 = "Hello123";
        System.out.println(isAllChinese(test1)); // true
        System.out.println(isAllChinese(test2)); // false
        System.out.println(isAllChinese(test3)); // false
    }
}

注意事项

1. 汉字的Unicode范围大致在\u4e00到\u9fa5之间，但这个范围并不完全覆盖所有汉字
2. 上述方法中的isChinese方法考虑了更多的Unicode块，可以识别更广泛的汉字字符
3. 如果你需要更精确的汉字判断，可以考虑使用专门的汉字识别库或数据库
4. 对于性能敏感的场景，正则表达式方法可能比循环遍历字符更高效

选择哪种方法取决于你的具体需求和项目环境，正则表达式方法通常是最简洁的,而Character类方法则提供了更细粒度的控制。