Java处理文件的BOM问题

---

Java处理文件的BOM问题

0. 问题描述

在公司遇到了一个看起来很奇怪，很坑的问题，从形式上看，两个字符串一模一样，然，调用equals方法就是匹配不成功。其中一个字符串s1是从csv文件读出来的，另一个字符串s2是手写的。两个字符串打印到控制台也是一模一样，但复制到编译器里就看出来差别了，原来是win系统的原因，给文件增加了BOM头。

1. 解决方案

前辈的肩膀

• UnicodeReader

/**
 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.
    */
  public 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);
   }

}

• UnicodeInputStream

/**
 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 in byte length ordering:
   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.*;

/**
 * This inputstream will recognize unicode BOM marks
 * and will skip bytes if getEncoding() method is called
 * before any of the read(...) methods.
 *
 * Usage pattern:
     String enc = "ISO-8859-1"; // or NULL to use systemdefault
     FileInputStream fis = new FileInputStream(file);
     UnicodeInputStream uin = new UnicodeInputStream(fis, enc);
     enc = uin.getEncoding(); // check and skip possible BOM bytes
     InputStreamReader in;
     if (enc == null) in = new InputStreamReader(uin);
     else in = new InputStreamReader(uin, enc);
 */
public class UnicodeInputStream extends InputStream {
   PushbackInputStream internalIn;
   boolean             isInited = false;
	String              defaultEnc;
	String              encoding;

	private static final int BOM_SIZE = 4;

public	UnicodeInputStream(InputStream in, String defaultEnc) {
		internalIn = new PushbackInputStream(in, BOM_SIZE);
		this.defaultEnc = defaultEnc;
	}

	public String getDefaultEncoding() {
      return defaultEnc;
   }

   public String getEncoding() {
      if (!isInited) {
         try {
            init();
         } catch (IOException ex) {
            IllegalStateException ise = new IllegalStateException("Init method failed.");
            ise.initCause(ise);
            throw ise;
         }
      }
      return encoding;
   }

   /**
    * 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 (isInited) return;

      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);

      isInited = true;
   }

   public void close() throws IOException {
      //init();
      isInited = true;
      internalIn.close();
   }

   public int read() throws IOException {
      //init();
      isInited = true;
      return internalIn.read();
   }
}

2. 使用案例

• 使用Reader

try {
        BufferedReader reader = new BufferedReader(new UnicodeReader(new FileInputStream("filePath"), "utf-8"));

     } catch (Exception e) {
         e.printStackTrace();
     }

读取CSV时:按逗号拆分参考

try (CSVReader csvReader = new CSVReaderBuilder(new BufferedReader(new InputStreamReader(new FileInputStream(srcPath), charset))).build()) {

}catch (Exception e) {
         e.printStackTrace();
     }

• 使用InputStream

try {
   BufferedInputStream bufferedInputStream = new BufferedInputStream(new UnicodeInputStream(new FileInputStream("filePath"), "utf-8"));

} catch (Exception e) {
     e.printStackTrace();
 }