java unicode转UTF-8

最新推荐文章于 2024-10-30 00:58:34 发布

xiejunna

最新推荐文章于 2024-10-30 00:58:34 发布

阅读量1.8w

点赞数 1

分类专栏： java 文章标签： java 算法

本文链接：https://blog.youkuaiyun.com/xiejunna/article/details/119967649

版权

java 专栏收录该内容

94 篇文章

订阅专栏

本文介绍了如何使用Java实现Unicode字符串到UTF-8的转换，通过decodeUnicode方法逐字符解析并处理转义字符。主要关注了处理`u`编码的Unicode字符和特殊字符转换。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package data.test;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

public class UnicodeToUtf8 {
	
	private static final Logger logger = LoggerFactory.getLogger(UnicodeToUtf8.class);
	
	public static String decodeUnicode(String unicodeStr) {
		char aChar;
		int len = unicodeStr.length();
		StringBuffer outBuffer = new StringBuffer(len);
		for (int x = 0; x < len;) {
			aChar = unicodeStr.charAt(x++);
			if (aChar == '\\') {
				aChar = unicodeStr.charAt(x++);
				if (aChar == 'u') {
					// Read the xxxx
					int value = 0;
					for (int i = 0; i < 4; i++) {
						aChar = unicodeStr.charAt(x++);
						switch (aChar) {
						case '0':
						case '1':
						case '2':
						case '3':
						case '4':
						case '5':
						case '6':
						case '7':
						case '8':
						case '9':
							value = (value << 4) + aChar - '0';
							break;
						case 'a':
						case 'b':
						case 'c':
						case 'd':
						case 'e':
						case 'f':
							value = (value << 4) + 10 + aChar - 'a';
							break;
						case 'A':
						case 'B':
						case 'C':
						case 'D':
						case 'E':
						case 'F':
							value = (value << 4) + 10 + aChar - 'A';
							break;
						default:
							logger.warn("{}","UnicodeToUtf8 exception!");
							return "";
						}

					}
					outBuffer.append((char) value);
				} else {
					if (aChar == 't')
						aChar = '\t';
					else if (aChar == 'r')
						aChar = '\r';
					else if (aChar == 'n')
						aChar = '\n';
					else if (aChar == 'f')
						aChar = '\f';
					outBuffer.append(aChar);
				}
			} else
				outBuffer.append(aChar);
		}
		return outBuffer.toString();
	}
	
	public static void main(String[] args) {
		String str = "\u7acb\u767d_\u5168\u81ea\u52a8\u6d53\u7f29_\u6d17\u8863\u7c89_900g";
		str = decodeUnicode(str);
		System.out.println(str);
		
	}
	
}