中文转化为unicode
原文地址：http://www.cnitblog.com/neatstudio/archive/2006/07/28/14315.html
js
mode="zhuan";
function encode(obj,btn){ if(mode=="zhuan"){ obj.value=obj.value.replace(/[^\u0000-\u00FF]/g,function($0){return escape($0).replace(/(%u)(\w{4})/gi,"&#x$2;")}); btn.value="还原"; mode="huan"; }else{ obj.value=unescape(obj.value.replace(/&#x/g,'%u').replace(/;/g,'')); btn.value="转化"; mode="zhuan"; }}
JAVA：
//转为unicode
public static void writeUnicode(final DataOutputStream out, final String value){try {final String unicode = gbEncoding( value );final byte[] data = unicode.getBytes();final int dataLength = data.length;System.out.println( "Data Length is: " + dataLength );System.out.println( "Data is: " + value );out.writeInt( dataLength ); //先写出字符串的长度out.write( data, 0, dataLength ); //然后写出转化后的字符串} catch (IOException e) { }} public static String gbEncoding( final String gbString ) {char[] utfBytes = gbString.toCharArray();String unicodeBytes = "";for( int byteIndex = 0; byteIndex < utfBytes.length; byteIndex ++ ) {String hexB = Integer.toHexString( utfBytes[ byteIndex ] );if( hexB.length() <= 2 ) {hexB = "00" + hexB;}unicodeBytes = unicodeBytes + "\\\\u" + hexB;}System.out.println( "unicodeBytes is: " + unicodeBytes );return unicodeBytes;}/** *//****************************************************** 功能介绍:将unicode字符串转为汉字* 输入参数:源unicode字符串* 输出参数:转换后的字符串*****************************************************/ private String decodeUnicode( final String dataStr ) {int start = 0;int end = 0;final StringBuffer buffer = new StringBuffer();while( start > -1 ) {end = dataStr.indexOf( "\\\\u", start + 2 );String charStr = "";if( end == -1 ) {charStr = dataStr.substring( start + 2, dataStr.length() );} else {charStr = dataStr.substring( start + 2, end);}char letter = (char) Integer.parseInt( charStr, 16 ); // 16进制parse整形字符串。buffer.append( new Character( letter ).toString() );start = end;}return buffer.toString(); }
JSP：
/** *//** ToUnicode.java */ package com.edgewww.util; import java.io.*; /** *//** * 字符串转换成Unicode码的类 * @author 栾金奎 jsp@shanghai.com * @date 2001-03-05 */ public class ToUnicode { /** *//** * 把字符串转换成Unicode码 * @param strText 待转换的字符串 * @param code 转换前字符串的编码，如"GBK" * @return 转换后的Unicode码字符串 */ public String toUnicode(String strText,String code) throws UnsupportedEncodingException{ char c; String strRet = "" ; int intAsc; String strHex; strText = new String(strText.getBytes("8859_1"),code); for ( int i = 0; i < strText.length(); i++ ){ c = strText.charAt(i); intAsc = (int)c; if(intAsc>128){ strHex = Integer.toHexString(intAsc); strRet = strRet + "&#x" + strHex+";"; } else{ strRet = strRet + c; } } return strRet ; } } /** *//** 应用举例 */ /** *//** gbk2Unicode.jsp */ <meta http-equiv="Content-Type" content="text/html; charset=big5"> <jsp:useBean id="g2u" scope="session" class="com.edgewww.util.ToUnicode"/> <% String lang = "这是简体中文"; %> <br> <%=lang %> <br> <%=g2u.toUnicode(lang,"GBK") %>
页:
[1]