/**
 * 將一個GBK編碼的txt文件轉化為UTF-8的XML檔案
 * @author SUNBIN
 *
 */
public class ConvertXML {
	public static void main(String[] args) {
		getXML("敏感詞庫大全.txt");
	}
	public static void getXML(String path){
		try {
			//獲取txt檔案
			File file = new File(path);
			//獲取xml檔案 
			File xmlFile = new File("src/sensitive.xml");
			if(!xmlFile.exists()){//不存在則建立檔案
				xmlFile.createNewFile();
			}
			//InputStreamReader讀取GBK檔案
			InputStreamReader isr = new InputStreamReader(new FileInputStream(file), "GBK");
 

			//OutputStreamWriter輸出UTF-8檔案
			OutputStreamWriter osw = new OutputStreamWriter(new FileOutputStream(xmlFile), "UTF-8");
			//包裝一下，以便一行一行讀寫檔案
			BufferedReader bufr = new BufferedReader(isr);
			BufferedWriter bufw = new BufferedWriter(osw);
			String line = null;
			bufw.write("<?xml version=\"1.0\" encoding=\"UTF-8\"?>"+"\n");//xml頭
			bufw.write("<sensitiveWords>"+"\n");//根標籤
			int id=1;
			while((line = bufr.readLine())!=null){//讀一行寫一行
				if(!"".equals(line.trim())){
					bufw.write("\t");
					bufw.write("<sensitiveWord id=\""+(id++)+"\">");
					bufw.write(line);
					bufw.write("</sensitiveWord>"+"\n");
				}
			}
			bufw.write("</sensitiveWords>");//根結束標籤
			bufw.flush();
			bufr.close();
			bufw.close();
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		
	}
}

Java使用UNICODE編碼,可以在讀檔案時使用GBK,此時記憶體中存在的是GBK轉化為UNICODE儲存的,寫出時採用UTF-8寫出(UNICODE轉化為UTF-8)。

同理:我們可以利用java的這一特性進行各種不同規範的編碼轉化.