简单的字符编解码

今天在使用搜索的时候，发现网站对中文编码不是常见的形式%AB%，而是%u4e92%，采用的是Unicode编码，决定对其解码。

package com.bc.codec;

import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.net.URLEncoder;

/**
 * <pre>
 * 简单的字符编解码
 * </pre>
 * 
 * @author badu
 * 
 */
public class DecodeTest {
	final String ENCODE_UTF8 = "UTF-8";
	final String ENCODE_GBK = "GBK";

	public static void main(String[] args) {
		DecodeTest test = new DecodeTest();

		// encoding
		String msg = "http://weibo.com/?=纳木措";
		System.out.println(test.encode(msg));
		System.out.println(test.decode(test.encode(msg)));

		// decoding
		// 汉字"互联网"的unicode编码
		String dsg = "\u4e92%\u8054%\u7f51";
		String regex = "%";
		String[] str = dsg.split(regex);
		for (String s : str) {
			System.out.println(test.unicodeToUtf8(s));
		}
	}

	public String decode(String str) {
		try {
			return URLDecoder.decode(str, ENCODE_UTF8);
		} catch (UnsupportedEncodingException e) {
			e.printStackTrace();
			return null;
		}
	}

	public String encode(String str) {
		try {
			return URLEncoder.encode(str, ENCODE_UTF8);
		} catch (UnsupportedEncodingException e) {
			e.printStackTrace();
			return null;
		}
	}

	public String unicodeToUtf8(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   <a><font color=#4563b9>\\uxxxx</font></a>   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();
	}
}

%AB%这种形式的编码比较常见，直接用URLEncode和URLDecode实现编码和解码。

%u4e92%这种格式则是多了步转化。

顺便比较了各个搜索引擎对中文的处理，其中baidu.com, soso.com, sougou.com, 采用的是%AB%式编码；

google.com.hk, youdou.com则直接是中文，采用UTF-8编码。

参照：http://zhaobohao.iteye.com/blog/591650