本文主要是介绍utf-8、gbk、unicode相互转码的几种方式，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
utf-8、gbk、unicode相互转码的几种方式
以下代码是java对于常见编码方式进行相互转换的，主要是gbk和utf-8互转，gbk与uncode互转,utf-8与unicode互转。
package com.encoding.util;import java.io.UnsupportedEncodingException;
import java.lang.Character.UnicodeBlock;public class UtfAndGbk {/*** 第一种方法* utf-8转gbk* @param utf8* @return* @throws UnsupportedEncodingException*/public static String utf8ToGbk(String utf8) throws UnsupportedEncodingException {return new String(new String(utf8.getBytes("UTF-8"), "GBK"));}/*** 第一种方法* gbk转utf-8* @param utf8* @return* @throws UnsupportedEncodingException*/public static String gbkToUtf8(String utf8) throws UnsupportedEncodingException {return new String(new String(utf8.getBytes("GBK"), "UTF-8"));}/*** 第二种方法* gbk转utf-8 通过先转unicode,再转utf-8* @param utf8* @return* @throws UnsupportedEncodingException*/public static String gbk2utf8(String gbk) { String l_temp = GBK2Unicode(gbk); l_temp = unicodeToUtf8(l_temp); return l_temp; } /*** 第二种方法* utf-8转gbk 通过先转unicode再转gbk* @param utf8* @return* @throws UnsupportedEncodingException*/public static String utf82gbk(String utf) { String l_temp = utf8ToUnicode(utf); l_temp = Unicode2GBK(l_temp); return l_temp; } /** * gbk转unicode* @param str * @return String */ public static String GBK2Unicode(String str) { StringBuffer result = new StringBuffer(); for (int i = 0; i < str.length(); i++) { char chr1 = (char) str.charAt(i); if (!isNeedConvert(chr1)) { result.append(chr1); continue; } result.append("\\u" + Integer.toHexString((int) chr1)); } return result.toString(); } /** * unicode转gbk* @param dataStr * @return String */ public static String Unicode2GBK(String dataStr) { int index = 0; StringBuffer buffer = new StringBuffer(); int li_len = dataStr.length(); while (index < li_len) { if (index >= li_len - 1 || !"\\u".equals(dataStr.substring(index, index + 2))) { buffer.append(dataStr.charAt(index)); index++; continue; } String charStr = ""; charStr = dataStr.substring(index + 2, index + 6); char letter = (char) Integer.parseInt(charStr, 16); buffer.append(letter); index += 6; } return buffer.toString(); } public static boolean isNeedConvert(char para) { return ((para & (0x00FF)) != para); } /** * utf-8 转unicode * * @param inStr * @return String */ public static String utf8ToUnicode(String inStr) { char[] myBuffer = inStr.toCharArray(); StringBuffer sb = new StringBuffer(); for (int i = 0; i < inStr.length(); i++) { UnicodeBlock ub = UnicodeBlock.of(myBuffer[i]); if (ub == UnicodeBlock.BASIC_LATIN) { sb.append(myBuffer[i]); } else if (ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) { int j = (int) myBuffer[i] - 65248; sb.append((char) j); } else { short s = (short) myBuffer[i]; String hexS = Integer.toHexString(s); String unicode = "\\u" + hexS; sb.append(unicode.toLowerCase()); } } return sb.toString(); } /** * unicode转utf-8* @param theString * @return String */ public static 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 \\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(); }
}
这篇关于utf-8、gbk、unicode相互转码的几种方式的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
