Java read UTF8 txt file, first character empty or question mark question

Ref: 79529756
41485403

1. Create a new class, called "Unicodereader", copy and paste the following content;

/** version:1.1/2007-01-25-changed BOM recognition ordering (longer BOMs first) Original Pseudocode:thomas Weiden Feller implementation Tweaked:aki Nieminen http://www.unicode.org/unicode/faq/utf_bom.html boms:00 FE FF = UTF-3 2, Big-endian ff FE xx = UTF-32, Little-endian EF BB BF = UTF-8, FE FF = UTF-16, Big-endian F  F FE = UTF-16, little-endian win2k notepad:unicode format = Utf-16le***/import java.io.*;/** * Generic Unicode TextReader, which would 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 being read * @param defaultenc default encoding if stream does not * 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 is * Unread back to the stream, only BOM bytes is 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) &&amp ; (Bom[3] = = (byte) 0xFF)) {Encoding = "utf-32be";      unread = n-4; } else if ((bom[0] = = (byte) 0xFF) && (bom[1] = = (byte) 0xFE) && (bom[2] = = (byte) 0x00) &A         mp;& (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); }}

When writing to a file:

         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("["+"\r\n");            out.write(s+","+"\r\n");        } catch (IOException ex)         {            ex.printStackTrace();        }        finally {            out.flush();    out.close();    System.out.println("关闭fwriter");        }            }

Java read UTF8 txt file, first character empty or question mark question