java字串應用之字串編碼轉換
阿新 • • 發佈：2019-01-25
{
/** 7位ASCII字元，也叫作ISO646-US、Unicode字符集的基本拉丁塊 */
publicstaticfinal String US_ASCII ="US-ASCII";
/** ISO拉丁字母表 No.1，也叫做ISO-LATIN-1 */
publicstaticfinal String ISO_8859_1 ="ISO-8859-1";
/** 8 位 UCS 轉換格式 */
publicstaticfinal String UTF_8 ="UTF-8";
/** 16 位 UCS 轉換格式，Big Endian(最低地址存放高位位元組）位元組順序
publicstaticfinal String UTF_16BE ="UTF-16BE";
/** 16 位 UCS 轉換格式，Litter Endian（最高地址存放地位位元組）位元組順序 */
publicstaticfinal String UTF_16LE ="UTF-16LE";
/** 16 位 UCS 轉換格式，位元組順序由可選的位元組順序標記來標識 */
publicstaticfinal String UTF_16 ="UTF-16";
/** 中文超大字符集 **/
publicstatic
publicstaticfinal String GB2312 ="GB2312";
/** 將字元編碼轉換成US-ASCII碼 */
public String toASCII(String str) throws UnsupportedEncodingException {
returnthis.changeCharset(str, US_ASCII);
}
/** 將字元編碼轉換成ISO-8859-1 */
public String toISO_8859_1(String str)
returnthis.changeCharset(str, ISO_8859_1);
}
/** 將字元編碼轉換成UTF-8 */
public String toUTF_8(String str) throws UnsupportedEncodingException {
returnthis.changeCharset(str, UTF_8);
}
/** 將字元編碼轉換成UTF-16BE */
public String toUTF_16BE(String str) throws UnsupportedEncodingException{
returnthis.changeCharset(str, UTF_16BE);
}
/** 將字元編碼轉換成UTF-16LE */
public String toUTF_16LE(String str) throws UnsupportedEncodingException {
returnthis.changeCharset(str, UTF_16LE);
}
/** 將字元編碼轉換成UTF-16 */
public String toUTF_16(String str) throws UnsupportedEncodingException {
returnthis.changeCharset(str, UTF_16);
}
/** 將字元編碼轉換成GBK */
public String toGBK(String str) throws UnsupportedEncodingException {
returnthis.changeCharset(str, GBK);
}
/** 將字元編碼轉換成GB2312 */
public String toGB2312(String str) throws UnsupportedEncodingException {
returnthis.changeCharset(str,GB2312);
}
/**
* 字串編碼轉換的實現方法
* @param str 待轉換的字串
* @param newCharset 目標編碼
*/
public String changeCharset(String str, String newCharset) throws UnsupportedEncodingException {
if(str !=null) {
//用預設字元編碼解碼字串。與系統相關，中文windows預設為GB2312
byte[] bs = str.getBytes();
returnnew String(bs, newCharset); //用新的字元編碼生成字串
}
returnnull;
}
/**
* 字串編碼轉換的實現方法
* @param str 待轉換的字串
* @param oldCharset 源字符集
* @param newCharset 目標字符集
*/
public String changeCharset(String str, String oldCharset, String newCharset) throws UnsupportedEncodingException {
if(str !=null) {
//用源字元編碼解碼字串
byte[] bs = str.getBytes(oldCharset);
returnnew String(bs, newCharset);
}
returnnull;
}
publicstaticvoid 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("轉換成GBK碼："+ gbk);
System.out.println();
String ascii = test.toASCII(str);
System.out.println("轉換成US-ASCII："+ ascii);
System.out.println();
String iso88591 = test.toISO_8859_1(str);
System.out.println("轉換成ISO-8859-1碼："+ iso88591);
System.out.println();
gbk = test.changeCharset(iso88591, ISO_8859_1, GBK);
System.out.println("再把ISO-8859-1碼的字串轉換成GBK碼："+ gbk);
System.out.println();
String utf8 = test.toUTF_8(str);
System.out.println();
System.out.println("轉換成UTF-8碼："+ utf8);
String utf16be = test.toUTF_16BE(str);
System.out.println("轉換成UTF-16BE碼："+ utf16be);
gbk = test.changeCharset(utf16be, UTF_16BE, GBK);
System.out.println("再把UTF-16BE編碼的字元轉換成GBK碼："+ gbk);
System.out.println();
String utf16le = test.toUTF_16LE(str);
System.out.println("轉換成UTF-16LE碼："+ utf16le);
gbk = test.changeCharset(utf16le, UTF_16LE, GBK);
System.out.println("再把UTF-16LE編碼的字串轉換成GBK碼："+ gbk);
System.out.println();
String utf16 = test.toUTF_16(str);
System.out.println("轉換成UTF-16碼："+ utf16);
String gb2312 = test.changeCharset(utf16, UTF_16, GB2312);
System.out.println("再把UTF-16編碼的字串轉換成GB2312碼："+ gb2312);
}
}
/** 7位ASCII字元，也叫作ISO646-US、Unicode字符集的基本拉丁塊 */
publicstaticfinal String US_ASCII ="US-ASCII"; /** ISO拉丁字母表 No.1，也叫做ISO-LATIN-1 */ publicstaticfinal String ISO_8859_1 ="ISO-8859-1"; /** 8 位 UCS 轉換格式 */ publicstaticfinal String UTF_8 ="UTF-8"; /** 16 位 UCS 轉換格式，Big Endian(最低地址存放高位位元組）位元組順序 publicstaticfinal String UTF_16BE ="UTF-16BE"; /** 16 位 UCS 轉換格式，Litter Endian（最高地址存放地位位元組）位元組順序 */ publicstaticfinal String UTF_16LE ="UTF-16LE"; /** 16 位 UCS 轉換格式，位元組順序由可選的位元組順序標記來標識 */ publicstaticfinal String UTF_16 ="UTF-16"; /** 中文超大字符集 **/ publicstatic publicstaticfinal String GB2312 ="GB2312"; /** 將字元編碼轉換成US-ASCII碼 */ public String toASCII(String str) throws UnsupportedEncodingException { returnthis.changeCharset(str, US_ASCII); } /** 將字元編碼轉換成ISO-8859-1 */ public String toISO_8859_1(String str) returnthis.changeCharset(str, ISO_8859_1); } /** 將字元編碼轉換成UTF-8 */ public String toUTF_8(String str) throws UnsupportedEncodingException { returnthis.changeCharset(str, UTF_8); } /** 將字元編碼轉換成UTF-16BE */ public String toUTF_16BE(String str) throws UnsupportedEncodingException{ returnthis.changeCharset(str, UTF_16BE); } /** 將字元編碼轉換成UTF-16LE */ public String toUTF_16LE(String str) throws UnsupportedEncodingException { returnthis.changeCharset(str, UTF_16LE); } /** 將字元編碼轉換成UTF-16 */ public String toUTF_16(String str) throws UnsupportedEncodingException { returnthis.changeCharset(str, UTF_16); } /** 將字元編碼轉換成GBK */ public String toGBK(String str) throws UnsupportedEncodingException { returnthis.changeCharset(str, GBK); } /** 將字元編碼轉換成GB2312 */ public String toGB2312(String str) throws UnsupportedEncodingException { returnthis.changeCharset(str,GB2312); } /** * 字串編碼轉換的實現方法 * @param str 待轉換的字串 * @param newCharset 目標編碼 */ public String changeCharset(String str, String newCharset) throws UnsupportedEncodingException { if(str !=null) { //用預設字元編碼解碼字串。與系統相關，中文windows預設為GB2312byte[] bs = str.getBytes(); returnnew String(bs, newCharset); //用新的字元編碼生成字串 } returnnull; } /** * 字串編碼轉換的實現方法 * @param str 待轉換的字串 * @param oldCharset 源字符集 * @param newCharset 目標字符集 */ public String changeCharset(String str, String oldCharset, String newCharset) throws UnsupportedEncodingException { if(str !=null) { //用源字元編碼解碼字串byte[] bs = str.getBytes(oldCharset); returnnew String(bs, newCharset); } returnnull; } publicstaticvoid 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("轉換成GBK碼："+ gbk); System.out.println(); String ascii = test.toASCII(str); System.out.println("轉換成US-ASCII："+ ascii); System.out.println(); String iso88591 = test.toISO_8859_1(str); System.out.println("轉換成ISO-8859-1碼："+ iso88591); System.out.println(); gbk = test.changeCharset(iso88591, ISO_8859_1, GBK); System.out.println("再把ISO-8859-1碼的字串轉換成GBK碼："+ gbk); System.out.println(); String utf8 = test.toUTF_8(str); System.out.println(); System.out.println("轉換成UTF-8碼："+ utf8); String utf16be = test.toUTF_16BE(str); System.out.println("轉換成UTF-16BE碼："+ utf16be); gbk = test.changeCharset(utf16be, UTF_16BE, GBK); System.out.println("再把UTF-16BE編碼的字元轉換成GBK碼："+ gbk); System.out.println(); String utf16le = test.toUTF_16LE(str); System.out.println("轉換成UTF-16LE碼："+ utf16le); gbk = test.changeCharset(utf16le, UTF_16LE, GBK); System.out.println("再把UTF-16LE編碼的字串轉換成GBK碼："+ gbk); System.out.println(); String utf16 = test.toUTF_16(str); System.out.println("轉換成UTF-16碼："+ utf16); String gb2312 = test.changeCharset(utf16, UTF_16, GB2312); System.out.println("再把UTF-16編碼的字串轉換成GB2312碼："+ gb2312); }}