Unicode转UTF-8

Unicode解码方法

最新推荐文章于 2025-01-08 01:24:56 发布

最新推荐文章于 2025-01-08 01:24:56 发布 · 66 阅读

本文介绍了一个用于解码Unicode转义序列的Java方法。该方法能够处理包括特殊字符和Unicode四字节转义序列在内的各种输入，并将其转换为正确的字符输出。

private static String decodeUnicode(String theString) {
	char aChar;
	int len = theString.length();
	StringBuffer outBuffer = new StringBuffer(len);
	for (int x = 0; x < len;) {
		aChar = theString.charAt(x++);
		if (aChar == '\\') {
			aChar = theString.charAt(x++);
			if (aChar == 'u') {
				// Read the xxxx
				int value = 0;
				for (int i = 0; i < 4; i++) {
					aChar = theString.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:
						throw new IllegalArgumentException(
								"Malformed   \\uxxxx   encoding.");
					}

				}
				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();
}