zoukankan      html  css  js  c++  java
  • java读utf8 的txt文件,第一个字符为空或问号问题

    参考:https://blog.csdn.net/yangzhichao888/article/details/79529756
    https://blog.csdn.net/wangzhi291/article/details/41485403

    1.新建一个类,叫“UnicodeReader”,复制粘贴如下内容;

    
    /**
     version: 1.1 / 2007-01-25
     - changed BOM recognition ordering (longer boms first)
    
     Original pseudocode   : Thomas Weidenfeller
     Implementation tweaked: Aki Nieminen
    
     http://www.unicode.org/unicode/faq/utf_bom.html
     BOMs:
       00 00 FE FF    = UTF-32, big-endian
       FF FE 00 00    = UTF-32, little-endian
       EF BB BF       = UTF-8,
       FE FF          = UTF-16, big-endian
       FF FE          = UTF-16, little-endian
    
     Win2k Notepad:
       Unicode format = UTF-16LE
    ***/
    
    import java.io.*;
    
    /**
     * Generic unicode textreader, which will use BOM mark
     * to identify the encoding to be used. If BOM is not found
     * then use a given default or system encoding.
     */
    public class UnicodeReader extends Reader {
       PushbackInputStream internalIn;
       InputStreamReader   internalIn2 = null;
       String              defaultEnc;
    
       private static final int BOM_SIZE = 4;
    
       /**
        *
        * @param in  inputstream to be read
        * @param defaultEnc default encoding if stream does not have 
        *                   BOM marker. Give NULL to use system-level default.
        */
       UnicodeReader(InputStream in, String defaultEnc) {
          internalIn = new PushbackInputStream(in, BOM_SIZE);
          this.defaultEnc = defaultEnc;
       }
    
       public String getDefaultEncoding() {
          return defaultEnc;
       }
    
       /**
        * Get stream encoding or NULL if stream is uninitialized.
        * Call init() or read() method to initialize it.
        */
       public String getEncoding() {
          if (internalIn2 == null) return null;
          return internalIn2.getEncoding();
       }
    
       /**
        * Read-ahead four bytes and check for BOM marks. Extra bytes are
        * unread back to the stream, only BOM bytes are skipped.
        */
       protected void init() throws IOException {
          if (internalIn2 != null) return;
    
          String encoding;
          byte bom[] = new byte[BOM_SIZE];
          int n, unread;
          n = internalIn.read(bom, 0, bom.length);
    
          if ( (bom[0] == (byte)0x00) && (bom[1] == (byte)0x00) &&
                      (bom[2] == (byte)0xFE) && (bom[3] == (byte)0xFF) ) {
             encoding = "UTF-32BE";
             unread = n - 4;
          } else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) &&
                      (bom[2] == (byte)0x00) && (bom[3] == (byte)0x00) ) {
             encoding = "UTF-32LE";
             unread = n - 4;
          } else if (  (bom[0] == (byte)0xEF) && (bom[1] == (byte)0xBB) &&
                (bom[2] == (byte)0xBF) ) {
             encoding = "UTF-8";
             unread = n - 3;
          } else if ( (bom[0] == (byte)0xFE) && (bom[1] == (byte)0xFF) ) {
             encoding = "UTF-16BE";
             unread = n - 2;
          } else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) ) {
             encoding = "UTF-16LE";
             unread = n - 2;
          } else {
             // Unicode BOM mark not found, unread all bytes
             encoding = defaultEnc;
             unread = n;
          }    
          //System.out.println("read=" + n + ", unread=" + unread);
    
          if (unread > 0) internalIn.unread(bom, (n - unread), unread);
    
          // Use given encoding
          if (encoding == null) {
             internalIn2 = new InputStreamReader(internalIn);
          } else {
             internalIn2 = new InputStreamReader(internalIn, encoding);
          }
       }
    
       public void close() throws IOException {
          init();
          internalIn2.close();
       }
    
       public int read(char[] cbuf, int off, int len) throws IOException {
          init();
          return internalIn2.read(cbuf, off, len);
       }
    
    }
    
    

    写入文件时:

        	 PrintWriter out=null;
            try {
    
            	File filename = new File(savefile);
                filename.createNewFile();
                out = new PrintWriter(new BufferedWriter(new OutputStreamWriter(new FileOutputStream(filename),"UTF-8")));
                System.out.println("打开fwriter");
                String []ss = content.split(",");
                out.write("["+"
    ");
                out.write(s+","+"
    ");
    
            } catch (IOException ex) 
            {
                ex.printStackTrace();
            }
            finally {
                out.flush();
    	out.close();
    	System.out.println("关闭fwriter");
            }
            
        }
    
    
    
  • 相关阅读:
    我罗斯方块最终篇
    我罗斯汇报作业一
    11组-Alpha冲刺-2/6
    11组-Alpha冲刺-1/6
    结对编程作业
    11组 团队展示
    第一次个人编程作业
    第一次博客作业
    寒假作业3
    寒假作业2
  • 原文地址:https://www.cnblogs.com/YuQiao0303/p/9277612.html
Copyright © 2011-2022 走看看