Posted on 2009-12-11 23:55
啥都寫點(diǎn) 閱讀(1259)
評(píng)論(0) 編輯 收藏 所屬分類:
J2SE

當(dāng)前流行的字符編碼格式有US-ASCII、ISO-8859-1、UTF-8、UTF-16BE、UTF-16LE、UTF-16、GBK和GB2312等,其中GBK、GB2312是專門處理中文編碼的。

String的getBytes方法用于按指定編碼獲取字符串的字節(jié)組成,參數(shù)指定了解碼格式,如果沒指定解碼格式,用系統(tǒng)的默認(rèn)編碼格式,如中文Windows下的默認(rèn)編碼格式為GB2312

String 的 "String(byte[] bs,String charset)" 構(gòu)造方法用于把字節(jié)數(shù)組按照指定的編碼組合成一個(gè)字符串對(duì)象。

/** *//**------------------------------------ChangeCharset.java-----------------------------------------*/
package book.string;

import java.io.UnsupportedEncodingException;


/** *//**
* 轉(zhuǎn)換字符串的編碼
*/

public class ChangeCharset
{

/** *//** 7位ASCII字符,也叫作ISO646-US、Unicode字符集的基本拉丁塊 */
public static final String US_ASCII = "US-ASCII";

/** *//** ISO 拉丁字母表 No.1,也叫作 ISO-LATIN-1 */
public static final String ISO_8859_1 = "ISO-8859-1";

/** *//** 8 位 UCS 轉(zhuǎn)換格式 */
public static final String UTF_8 = "UTF-8";

/** *//** 16 位 UCS 轉(zhuǎn)換格式,Big Endian(最低地址存放高位字節(jié))字節(jié)順序 */
public static final String UTF_16BE = "UTF-16BE";

/** *//** 16 位 UCS 轉(zhuǎn)換格式,Little-endian(最高地址存放低位字節(jié))字節(jié)順序 */
public static final String UTF_16LE = "UTF-16LE";

/** *//** 16 位 UCS 轉(zhuǎn)換格式,字節(jié)順序由可選的字節(jié)順序標(biāo)記來(lái)標(biāo)識(shí) */
public static final String UTF_16 = "UTF-16";

/** *//** 中文超大字符集 */
public static final String GBK = "GBK";


/** *//**
* 將字符編碼轉(zhuǎn)換成US-ASCII碼
*/

public String toASCII(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, US_ASCII);
}

/** *//**
* 將字符編碼轉(zhuǎn)換成ISO-8859-1碼
*/

public String toISO_8859_1(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, ISO_8859_1);
}

/** *//**
* 將字符編碼轉(zhuǎn)換成UTF-8碼
*/

public String toUTF_8(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, UTF_8);
}

/** *//**
* 將字符編碼轉(zhuǎn)換成UTF-16BE碼
*/

public String toUTF_16BE(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, UTF_16BE);
}

/** *//**
* 將字符編碼轉(zhuǎn)換成UTF-16LE碼
*/

public String toUTF_16LE(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, UTF_16LE);
}

/** *//**
* 將字符編碼轉(zhuǎn)換成UTF-16碼
*/

public String toUTF_16(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, UTF_16);
}

/** *//**
* 將字符編碼轉(zhuǎn)換成GBK碼
*/

public String toGBK(String str) throws UnsupportedEncodingException
{
return this.changeCharset(str, GBK);
}

/** *//**
* 字符串編碼轉(zhuǎn)換的實(shí)現(xiàn)方法
* @param str 待轉(zhuǎn)換編碼的字符串
* @param newCharset 目標(biāo)編碼
* @return
* @throws UnsupportedEncodingException
*/
public String changeCharset(String str, String newCharset)

throws UnsupportedEncodingException
{

if (str != null)
{
//用默認(rèn)字符編碼解碼字符串。
byte[] bs = str.getBytes();
//用新的字符編碼生成字符串
return new String(bs, newCharset);
}
return null;
}

/** *//**
* 字符串編碼轉(zhuǎn)換的實(shí)現(xiàn)方法
* @param str 待轉(zhuǎn)換編碼的字符串
* @param oldCharset 原編碼
* @param newCharset 目標(biāo)編碼
* @return
* @throws UnsupportedEncodingException
*/
public String changeCharset(String str, String oldCharset, String newCharset)

throws UnsupportedEncodingException
{

if (str != null)
{
//用舊的字符編碼解碼字符串。解碼可能會(huì)出現(xiàn)異常。
byte[] bs = str.getBytes(oldCharset);
//用新的字符編碼生成字符串
return new String(bs, newCharset);
}
return null;
}


public static void main(String[] args) throws UnsupportedEncodingException
{
ChangeCharset test = new ChangeCharset();
String str = "This is a 中文的 String!";
System.out.println("str: " + str);
String gbk = test.toGBK(str);
System.out.println("轉(zhuǎn)換成GBK碼: " + gbk);
System.out.println();
String ascii = test.toASCII(str);
System.out.println("轉(zhuǎn)換成US-ASCII碼: " + ascii);
gbk = test.changeCharset(ascii,ChangeCharset.US_ASCII, ChangeCharset.GBK);
System.out.println("再把ASCII碼的字符串轉(zhuǎn)換成GBK碼: " + gbk);
System.out.println();
String iso88591 = test.toISO_8859_1(str);
System.out.println("轉(zhuǎn)換成ISO-8859-1碼: " + iso88591);
gbk = test.changeCharset(iso88591,ChangeCharset.ISO_8859_1, ChangeCharset.GBK);
System.out.println("再把ISO-8859-1碼的字符串轉(zhuǎn)換成GBK碼: " + gbk);
System.out.println();
String utf8 = test.toUTF_8(str);
System.out.println("轉(zhuǎn)換成UTF-8碼: " + utf8);
gbk = test.changeCharset(utf8,ChangeCharset.UTF_8, ChangeCharset.GBK);
System.out.println("再把UTF-8碼的字符串轉(zhuǎn)換成GBK碼: " + gbk);
System.out.println();
String utf16be = test.toUTF_16BE(str);
System.out.println("轉(zhuǎn)換成UTF-16BE碼:" + utf16be);
gbk = test.changeCharset(utf16be,ChangeCharset.UTF_16BE, ChangeCharset.GBK);
System.out.println("再把UTF-16BE碼的字符串轉(zhuǎn)換成GBK碼: " + gbk);
System.out.println();
String utf16le = test.toUTF_16LE(str);
System.out.println("轉(zhuǎn)換成UTF-16LE碼:" + utf16le);
gbk = test.changeCharset(utf16le,ChangeCharset.UTF_16LE, ChangeCharset.GBK);
System.out.println("再把UTF-16LE碼的字符串轉(zhuǎn)換成GBK碼: " + gbk);
System.out.println();
String utf16 = test.toUTF_16(str);
System.out.println("轉(zhuǎn)換成UTF-16碼:" + utf16);
gbk = test.changeCharset(utf16,ChangeCharset.UTF_16LE, ChangeCharset.GBK);
System.out.println("再把UTF-16碼的字符串轉(zhuǎn)換成GBK碼: " + gbk);
String s = new String("中文".getBytes("UTF-8"),"UTF-8");
System.out.println(s);
}
}

--
學(xué)海無(wú)涯