Java 完美判断中文字符

package com.micmiu.utils;

import java.util.regex.Pattern;

/**
 * 字符通用工具类
 * 
 * @author <a href="http://www.micmiu.com">Michael Sun</a>
 */
public class CharUtil {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		String[] strArr = new String[] { "www.micmiu.com",
				"!@#$%^&*()_+{}[]|\"'?/:;<>,.", "!¥……()——:;“”‘’《》,。?、", "不要啊",
				"やめて", "韩佳人", "한가인" };
		for (String str : strArr) {
			System.out.println("===========> 测试字符串:" + str);
			System.out.println("正则判断:" + 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 = 0; 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 = 0; 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 pattern = Pattern.compile("[\\u4E00-\\u9FBF]+");
		return pattern.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();
	}
}

 http://www.micmiu.com/lang/java/java-check-chinese/

猜你喜欢

转载自m635674608.iteye.com/blog/2267524