將字符串的編碼格式轉換為utf-8

方式一：

/**
 * 將字符串的編碼格式轉換為utf-8
 * 
 * @param str
 * @return Name = new
 * String(Name.getBytes("ISO-8859-1"), "utf-8");
 */
public static String toUTF8(String str) {
	if (isEmpty(str)) {
		return "";
	}
	try {
		if (str.equals(new String(str.getBytes("GB2312"), "GB2312"))) {
			str = new String(str.getBytes("GB2312"), "utf-8");
			return str;
		}
	} catch (Exception exception) {
	}
	try {
		if (str.equals(new String(str.getBytes("ISO-8859-1"), "ISO-8859-1"))) {
			str = new String(str.getBytes("ISO-8859-1"), "utf-8");
			return str;
		}
	} catch (Exception exception1) {
	}
	try {
		if (str.equals(new String(str.getBytes("GBK"), "GBK"))) {
			str = new String(str.getBytes("GBK"), "utf-8");
			return str;
		}
	} catch (Exception exception3) {
	}
	return str;
}
 

/**
 * 判斷是否為空
 * 
 * @param str
 * @return
 */
public static boolean isEmpty(String str) {
	// 如果字符串不為null，去除空格后值不與空字符串相等的話，證明字符串有實質性的內容
	if (str != null && !str.trim().isEmpty()) {
		return false;// 不為空
	}
	return true;// 為空
}

 

方式二：

import java.io.UnsupportedEncodingException; 
  
/** 
 * 轉換字符串的編碼 
 */
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 轉換格式 */
 public static final String UTF_8 = "UTF-8"; 
  
 /** 16 位 UCS 轉換格式，Big Endian（最低地址存放高位字節）字節順序 */
 public static final String UTF_16BE = "UTF-16BE"; 
  
 /** 16 位 UCS 轉換格式，Little-endian（最高地址存放低位字節）字節順序 */
 public static final String UTF_16LE = "UTF-16LE"; 
  
 /** 16 位 UCS 轉換格式，字節順序由可選的字節順序標記來標識 */
 public static final String UTF_16 = "UTF-16"; 
  
 /** 中文超大字符集 */
 public static final String GBK = "GBK"; 
  
 /** 
 * 將字符編碼轉換成US-ASCII碼 
 */
 public String toASCII(String str) throws UnsupportedEncodingException{ 
 return this.changeCharset(str, US_ASCII); 
 } 
 /** 
 * 將字符編碼轉換成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); 
 } 
 /** 
 * 將字符編碼轉換成GBK碼 
 */
 public String toGBK(String str) throws UnsupportedEncodingException{ 
 return this.changeCharset(str, GBK); 
 } 
   
 /** 
 * 字符串編碼轉換的實現方法 
 * @param str 待轉換編碼的字符串 
 * @param newCharset 目標編碼 
 * @return 
 * @throws UnsupportedEncodingException 
 */
 public String changeCharset(String str, String newCharset) 
  throws UnsupportedEncodingException { 
 if (str != null) { 
  //用默認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; 
 } 
 /** 
 * 字符串編碼轉換的實現方法 
 * @param str 待轉換編碼的字符串 
 * @param oldCharset 原編碼 
 * @param newCharset 目標編碼 
 * @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。解碼可能會出現異常。 
  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("轉換成GBK碼: " + gbk); 
 System.out.println(); 
 String ascii = test.toASCII(str); 
 System.out.println("轉換成US-ASCII碼: " + ascii); 
 gbk = test.changeCharset(ascii,ChangeCharset.US_ASCII, ChangeCharset.GBK); 
 System.out.println("再把ASCII碼的字符串轉換成GBK碼: " + gbk); 
 System.out.println(); 
 String iso88591 = test.toISO_8859_1(str); 
 System.out.println("轉換成ISO-8859-1碼: " + iso88591); 
 gbk = test.changeCharset(iso88591,ChangeCharset.ISO_8859_1, ChangeCharset.GBK); 
 System.out.println("再把ISO-8859-1碼的字符串轉換成GBK碼: " + gbk); 
 System.out.println(); 
 String utf8 = test.toUTF_8(str); 
 System.out.println("轉換成UTF-8碼: " + utf8); 
 gbk = test.changeCharset(utf8,ChangeCharset.UTF_8, ChangeCharset.GBK); 
 System.out.println("再把UTF-8碼的字符串轉換成GBK碼: " + gbk); 
 System.out.println(); 
 String utf16be = test.toUTF_16BE(str); 
 System.out.println("轉換成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,ChangeCharset.UTF_16LE, ChangeCharset.GBK); 
 System.out.println("再把UTF-16LE碼的字符串轉換成GBK碼: " + gbk); 
 System.out.println(); 
 String utf16 = test.toUTF_16(str); 
 System.out.println("轉換成UTF-16碼:" + utf16); 
 gbk = test.changeCharset(utf16,ChangeCharset.UTF_16LE, ChangeCharset.GBK); 
 System.out.println("再把UTF-16碼的字符串轉換成GBK碼: " + gbk); 
 String s = new String("中文".getBytes("UTF-8"),"UTF-8"); 
 System.out.println(s); 
 } 
}