unicode与中文互换

view source

print?

001	package com.loyin.util;

002

003	import java.lang.Character.UnicodeBlock;

004

005	public class UnicodeTool {

006

/**

007	* 中文转换成 unicode

008	* @author fanhui

009	* 2007-3-15

010	* @param inStr

011

* @return

012

*/

013	public static String encodeUnicode(String inStr) {

014	char[] myBuffer = inStr.toCharArray();

015

016	StringBuffer sb = new StringBuffer();

017	for (int i = 0; i < inStr.length(); i++) {

018	char ch=myBuffer[i];

019	if((int)ch<10){

020	sb.append("\\u000"+(int)ch);

021

continue;

022

}

023	UnicodeBlock ub = UnicodeBlock.of(ch);

024	if(ub == UnicodeBlock.BASIC_LATIN){

025

//英文及数字等

026	sb.append(myBuffer[i]);

027	}else if(ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS){

028

//全角半角字符

029	int j = (int) myBuffer[i] - 65248;

030	sb.append((char)j);

031

}else{

032

//汉字

033	short s = (short) myBuffer[i];

034	String hexS = Integer.toHexString(s);

035	String unicode = "\\u"+hexS;

036	sb.append(unicode.toLowerCase());

037

}

038

}

039	return sb.toString();

040

}

041

042

/**

043	* unicode 转换成 中文

044	* @author fanhui

045	* 2007-3-15

046	* @param theString

047

* @return

048

*/

049	public static String decodeUnicode(String theString) {

050	char aChar;

051	int len = theString.length();

052	StringBuffer outBuffer = new StringBuffer(len);

053	for (int x = 0; x < len;) {

054	aChar = theString.charAt(x++);

055	if (aChar == '\\') {

056	aChar = theString.charAt(x++);

057	if (aChar == 'u') {

058	// Read the xxxx

059	int value = 0;

060	for (int i = 0; i < 4; i++) {

061	aChar = theString.charAt(x++);

062	switch (aChar) {

063

case '0':

064

case '1':

065

case '2':

066

case '3':

067

case '4':

068

case '5':

069

case '6':

070

case '7':

071

case '8':

072

case '9':

073	value = (value << 4) + aChar - '0';

074

break;

075

case 'a':

076

case 'b':

077

case 'c':

078

case 'd':

079

case 'e':

080

case 'f':

081	value = (value << 4) + 10 + aChar - 'a';

082

break;

083

case 'A':

084

case 'B':

085

case 'C':

086

case 'D':

087

case 'E':

088

case 'F':

089	value = (value << 4) + 10 + aChar - 'A';

090

break;

091

default:

092	throw new IllegalArgumentException(

093	"Malformed   \\uxxxx   encoding.");

094

}

095

}

096	outBuffer.append((char) value);

097

} else {

098	if (aChar == 't')

099	aChar = '\t';

100	else if (aChar == 'r')

101	aChar = '\r';

102	else if (aChar == 'n')

103	aChar = '\n';

104	else if (aChar == 'f')

105	aChar = '\f';

106	outBuffer.append(aChar);

107

}

108

} else

109	outBuffer.append(aChar);

110

}

111	return outBuffer.toString();

112

}

113

114

}