java 清除 bom

参考工具  http://akini.mbnet.fi/java/unicodereader/

Utf8BomRemover 清除bom的方法

package cn.com.do1.component.common.util;
import java.io.*;
import java.nio.charset.Charset;
public  class  Utf8BomRemover  {
    /**
     * 读取流中前面的字符，看是否有bom，如果有bom，将bom头先读掉丢弃
     *
     * @param in
     * @return
     * @throws java.io.IOException
     */
    public static InputStream getInputStream(InputStream in) throws IOException {
        PushbackInputStream testin = new PushbackInputStream(in);
        int ch = testin.read();
        if (ch != 0xEF) {
            testin.unread(ch);
        } else if ((ch = testin.read()) != 0xBB) {
            testin.unread(ch);
            testin.unread(0xef);
        } else if ((ch = testin.read()) != 0xBF) {
            throw new IOException("错误的UTF-8格式文件");
        } else {
// 不需要做，这里是bom头被读完了
// // System.out.println("still exist bom");
        }
        return testin;
    }
    /**
     * 根据一个文件名，读取完文件，干掉bom头。
     *
     * @param fileName
     * @throws java.io.IOException
     */
    public static   void trimBom(String fileName) throws IOException {
        FileInputStream fin = new FileInputStream(fileName);
// 开始写临时文件
        InputStream in = getInputStream(fin);
        ByteArrayOutputStream bos = new ByteArrayOutputStream();
        byte b[] = new byte[4096];
        int len = 0;
        while (in.available() > 0) {
            len = in.read(b, 0, 4096);
//            out.write(b, 0, len);
            bos.write(b, 0, len);
        }
        in.close();
        fin.close();
        bos.close();
// 临时文件写完，开始将临时文件写回本文件。
        System.out.println("[" + fileName + "]");
        FileOutputStream out = new FileOutputStream(fileName);
        out.write(bos.toByteArray());
        out.close();
        System.out.println("处理文件" + fileName);
    }
    public  static  void  main(String[] args)  throws  IOException {
        //刪除指定文件夾下（含子文件夾）所有java文件的BOM，若構造器中參數為null則刪除所有文件頭部BOM
        new  Utf8BomRemover( "java" ).start( "\"F:\\\\flwork\\\\gmmsDGYH\\\\src\\\\com");
    }
    /**
     * 根据一个文件名，读取完文件，干掉bom头2  这里使用了第三方类UnicodeReader
     *
     * @throws java.io.IOException
     */
    public  void saveFile(String file) throws IOException {
        InputStream in= new FileInputStream( file);
        BufferedReader bre = null;
        OutputStreamWriter pw = null;//定义一个流
        CharArrayWriter writer =   new CharArrayWriter();
        //这一句会读取BOM头
        //bre = new BufferedReader(new InputStreamReader(in, "UTF-8"));
        //这一句会干掉BOM头
        bre = new BufferedReader(new UnicodeReader(in, Charset.defaultCharset().name()));//
        String line = bre.readLine();
        while(line != null)
        {
            writer.write(line);
            /*
            加上这段代码可以查看更详细的16进制
            byte[] allbytes = line.getBytes("UTF-8");
            for (int i=0; i < allbytes.length; i++)
            {
                int tmp = allbytes[i];
                String hexString = Integer.toHexString(tmp);
                // 1个byte变成16进制的，只需要2位就可以表示了，取后面两位，去掉前面的符号填充
                hexString = hexString.substring(hexString.length() -2);
                System.out.print(hexString.toUpperCase());
                System.out.print(" ");
            }*/
            line = bre.readLine();
        }
        writer.flush();
        bre.close();
        FileWriter f2 = new FileWriter(file);
        writer.writeTo(f2);
        f2.close();
        writer.close();
    }
    private  String extension =  null ;
    public  Utf8BomRemover(String extension) {
        super ();
        this .extension = extension;
    }
    /** 啟動對某個文件夾的篩選 */
    @SuppressWarnings ( "unchecked" )
    public  void  start(String rootDir)  throws  IOException {
        traverseFolder2(rootDir);
    }
    public void traverseFolder2(String path) throws IOException {
        File file = new File(path);
        if (file.exists()) {
            File[] files = file.listFiles();
            if (files.length == 0) {
                System.out.println("文件夹是空的!");
                return;
            } else {
                for (File file2 : files) {
                    if (file2.isDirectory()) {
                        System.out.println("文件夹:" + file2.getAbsolutePath());
                        traverseFolder2(file2.getAbsolutePath());
                    } else {
                        remove(file2.getAbsolutePath());
                    }
                }
            }
        } else {
            System.out.println("文件不存在!");
        }
    }
    /** 移除UTF-8的BOM */
    private  void  remove(String path)  throws  IOException {
        saveFile(path);
        trimBom(path);
    }
}

第二种方法的UnicodeReader 类

package cn.com.do1.component.common.util;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.PushbackInputStream;
import java.io.Reader;
/**
version: 1.1 / 2007-01-25
- changed BOM recognition ordering (longer boms first)
网络地址：http://koti.mbnet.fi/akini/java/unicodereader/UnicodeReader.java.txt
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
***/
/**
* 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);
  }
}