字节顺序标记搞砸了 Java 中的文件读取

编辑：我在 GitHub 上发布了适当的版本：https://github.com/gpakosz/UnicodeBOMInputStream

这是我前段时间编写的一个类，我只是在粘贴之前编辑了包名。没什么特别的，它与 SUN 的 bug 数据库中发布的解决方案非常相似。将它合并到您的代码中就可以了。

/* ____________________________________________________________________________
 * 
 * File:    UnicodeBOMInputStream.java
 * Author:  Gregory Pakosz.
 * Date:    02 - November - 2005    
 * ____________________________________________________________________________
 */
package com.stackoverflow.answer;

import java.io.IOException;
import java.io.InputStream;
import java.io.PushbackInputStream;

/**
 * The <code>UnicodeBOMInputStream</code> class wraps any
 * <code>InputStream</code> and detects the presence of any Unicode BOM
 * (Byte Order Mark) at its beginning, as defined by
 * <a href="http://www.faqs.org/rfcs/rfc3629.html">RFC 3629 - UTF-8, a transformation format of ISO 10646</a>
 * 
 * <p>The
 * <a href="http://www.unicode.org/unicode/faq/utf_bom.html">Unicode FAQ</a>
 * defines 5 types of BOMs:<ul>
 * <li><pre>00 00 FE FF  = UTF-32, big-endian</pre></li>
 * <li><pre>FF FE 00 00  = UTF-32, little-endian</pre></li>
 * <li><pre>FE FF        = UTF-16, big-endian</pre></li>
 * <li><pre>FF FE        = UTF-16, little-endian</pre></li>
 * <li><pre>EF BB BF     = UTF-8</pre></li>
 * </ul></p>
 * 
 * <p>Use the {@link #getBOM()} method to know whether a BOM has been detected
 * or not.
 * </p>
 * <p>Use the {@link #skipBOM()} method to remove the detected BOM from the
 * wrapped <code>InputStream</code> object.</p>
 */
public class UnicodeBOMInputStream extends InputStream
{
  /**
   * Type safe enumeration class that describes the different types of Unicode
   * BOMs.
   */
  public static final class BOM
  {
    /**
     * NONE.
     */
    public static final BOM NONE = new BOM(new byte[]{},"NONE");

    /**
     * UTF-8 BOM (EF BB BF).
     */
    public static final BOM UTF_8 = new BOM(new byte[]{(byte)0xEF,
                                                       (byte)0xBB,
                                                       (byte)0xBF},
                                            "UTF-8");

    /**
     * UTF-16, little-endian (FF FE).
     */
    public static final BOM UTF_16_LE = new BOM(new byte[]{ (byte)0xFF,
                                                            (byte)0xFE},
                                                "UTF-16 little-endian");

    /**
     * UTF-16, big-endian (FE FF).
     */
    public static final BOM UTF_16_BE = new BOM(new byte[]{ (byte)0xFE,
                                                            (byte)0xFF},
                                                "UTF-16 big-endian");

    /**
     * UTF-32, little-endian (FF FE 00 00).
     */
    public static final BOM UTF_32_LE = new BOM(new byte[]{ (byte)0xFF,
                                                            (byte)0xFE,
                                                            (byte)0x00,
                                                            (byte)0x00},
                                                "UTF-32 little-endian");

    /**
     * UTF-32, big-endian (00 00 FE FF).
     */
    public static final BOM UTF_32_BE = new BOM(new byte[]{ (byte)0x00,
                                                            (byte)0x00,
                                                            (byte)0xFE,
                                                            (byte)0xFF},
                                                "UTF-32 big-endian");

    /**
     * Returns a <code>String</code> representation of this <code>BOM</code>
     * value.
     */
    public final String toString()
    {
      return description;
    }

    /**
     * Returns the bytes corresponding to this <code>BOM</code> value.
     */
    public final byte[] getBytes()
    {
      final int     length = bytes.length;
      final byte[]  result = new byte[length];

      // Make a defensive copy
      System.arraycopy(bytes,0,result,0,length);

      return result;
    }

    private BOM(final byte bom[], final String description)
    {
      assert(bom != null)               : "invalid BOM: null is not allowed";
      assert(description != null)       : "invalid description: null is not allowed";
      assert(description.length() != 0) : "invalid description: empty string is not allowed";

      this.bytes          = bom;
      this.description  = description;
    }

            final byte    bytes[];
    private final String  description;

  } // BOM

  /**
   * Constructs a new <code>UnicodeBOMInputStream</code> that wraps the
   * specified <code>InputStream</code>.
   * 
   * @param inputStream an <code>InputStream</code>.
   * 
   * @throws NullPointerException when <code>inputStream</code> is
   * <code>null</code>.
   * @throws IOException on reading from the specified <code>InputStream</code>
   * when trying to detect the Unicode BOM.
   */
  public UnicodeBOMInputStream(final InputStream inputStream) throws  NullPointerException,
                                                                      IOException

  {
    if (inputStream == null)
      throw new NullPointerException("invalid input stream: null is not allowed");

    in = new PushbackInputStream(inputStream,4);

    final byte  bom[] = new byte[4];
    final int   read  = in.read(bom);

    switch(read)
    {
      case 4:
        if ((bom[0] == (byte)0xFF) &&
            (bom[1] == (byte)0xFE) &&
            (bom[2] == (byte)0x00) &&
            (bom[3] == (byte)0x00))
        {
          this.bom = BOM.UTF_32_LE;
          break;
        }
        else
        if ((bom[0] == (byte)0x00) &&
            (bom[1] == (byte)0x00) &&
            (bom[2] == (byte)0xFE) &&
            (bom[3] == (byte)0xFF))
        {
          this.bom = BOM.UTF_32_BE;
          break;
        }

      case 3:
        if ((bom[0] == (byte)0xEF) &&
            (bom[1] == (byte)0xBB) &&
            (bom[2] == (byte)0xBF))
        {
          this.bom = BOM.UTF_8;
          break;
        }

      case 2:
        if ((bom[0] == (byte)0xFF) &&
            (bom[1] == (byte)0xFE))
        {
          this.bom = BOM.UTF_16_LE;
          break;
        }
        else
        if ((bom[0] == (byte)0xFE) &&
            (bom[1] == (byte)0xFF))
        {
          this.bom = BOM.UTF_16_BE;
          break;
        }

      default:
        this.bom = BOM.NONE;
        break;
    }

    if (read > 0)
      in.unread(bom,0,read);
  }

  /**
   * Returns the <code>BOM</code> that was detected in the wrapped
   * <code>InputStream</code> object.
   * 
   * @return a <code>BOM</code> value.
   */
  public final BOM getBOM()
  {
    // BOM type is immutable.
    return bom;
  }

  /**
   * Skips the <code>BOM</code> that was found in the wrapped
   * <code>InputStream</code> object.
   * 
   * @return this <code>UnicodeBOMInputStream</code>.
   * 
   * @throws IOException when trying to skip the BOM from the wrapped
   * <code>InputStream</code> object.
   */
  public final synchronized UnicodeBOMInputStream skipBOM() throws IOException
  {
    if (!skipped)
    {
      in.skip(bom.bytes.length);
      skipped = true;
    }
    return this;
  }

  /**
   * {@inheritDoc}
   */
  public int read() throws IOException
  {
    return in.read();
  }

  /**
   * {@inheritDoc}
   */
  public int read(final byte b[]) throws  IOException,
                                          NullPointerException
  {
    return in.read(b,0,b.length);
  }

  /**
   * {@inheritDoc}
   */
  public int read(final byte b[],
                  final int off,
                  final int len) throws IOException,
                                        NullPointerException
  {
    return in.read(b,off,len);
  }

  /**
   * {@inheritDoc}
   */
  public long skip(final long n) throws IOException
  {
    return in.skip(n);
  }

  /**
   * {@inheritDoc}
   */
  public int available() throws IOException
  {
    return in.available();
  }

  /**
   * {@inheritDoc}
   */
  public void close() throws IOException
  {
    in.close();
  }

  /**
   * {@inheritDoc}
   */
  public synchronized void mark(final int readlimit)
  {
    in.mark(readlimit);
  }

  /**
   * {@inheritDoc}
   */
  public synchronized void reset() throws IOException
  {
    in.reset();
  }

  /**
   * {@inheritDoc}
   */
  public boolean markSupported() 
  {
    return in.markSupported();
  }

  private final PushbackInputStream in;
  private final BOM                 bom;
  private       boolean             skipped = false;

} // UnicodeBOMInputStream

你正在以这种方式使用它：

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.InputStreamReader;

public final class UnicodeBOMInputStreamUsage
{
  public static void main(final String[] args) throws Exception
  {
    FileInputStream fis = new FileInputStream("test/offending_bom.txt");
    UnicodeBOMInputStream ubis = new UnicodeBOMInputStream(fis);

    System.out.println("detected BOM: " + ubis.getBOM());

    System.out.print("Reading the content of the file without skipping the BOM: ");
    InputStreamReader isr = new InputStreamReader(ubis);
    BufferedReader br = new BufferedReader(isr);

    System.out.println(br.readLine());

    br.close();
    isr.close();
    ubis.close();
    fis.close();

    fis = new FileInputStream("test/offending_bom.txt");
    ubis = new UnicodeBOMInputStream(fis);
    isr = new InputStreamReader(ubis);
    br = new BufferedReader(isr);

    ubis.skipBOM();

    System.out.print("Reading the content of the file after skipping the BOM: ");
    System.out.println(br.readLine());

    br.close();
    isr.close();
    ubis.close();
    fis.close();
  }

} // UnicodeBOMInputStreamUsage

Apache Commons IO 库有一个可以检测和丢弃 BOM 的 InputStream：BOMInputStream (javadoc)：

BOMInputStream bomIn = new BOMInputStream(in);
int firstNonBOMByte = bomIn.read(); // Skips BOM
if (bomIn.hasBOM()) {
    // has a UTF-8 BOM
}

如果您还需要检测不同的编码，它还可以区分各种不同的字节顺序标记，例如 UTF-8 与 UTF-16 大端 + 小端 - 详细信息请参见上面的文档链接。然后，您可以使用检测到的 ByteOrderMark 选择一个 Charset 来解码流。 （如果您需要所有这些功能，可能有一种更简化的方法来执行此操作 - 也许是 BalusC 答案中的 UnicodeReader？）。请注意，一般来说，检测某些字节的编码方式不是很好，但如果流以 BOM 开头，显然这会有所帮助。

编辑：如果您需要检测 UTF-16、UTF-32 等格式的 BOM，则构造函数应为：

new BOMInputStream(is, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE,
        ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE)

支持@martin-charlesworth 的评论 :)

更简单的解决方案：

public class BOMSkipper
{
    public static void skip(Reader reader) throws IOException
    {
        reader.mark(1);
        char[] possibleBOM = new char[1];
        reader.read(possibleBOM);

        if (possibleBOM[0] != '\ufeff')
        {
            reader.reset();
        }
    }
}

使用示例：

BufferedReader input = new BufferedReader(new InputStreamReader(new FileInputStream(file), fileExpectedCharset));
BOMSkipper.skip(input);
//Now UTF prefix not present:
input.readLine();
...

它适用于所有 5 种 UTF 编码！

Google Data API 有一个 UnicodeReader，它会自动检测编码。

您可以使用它来代替 InputStreamReader。这是其源代码的 - 略微压缩的 - 摘录，非常简单：

public class UnicodeReader extends Reader {
    private static final int BOM_SIZE = 4;
    private final InputStreamReader reader;

    /**
     * Construct UnicodeReader
     * @param in Input stream.
     * @param defaultEncoding Default encoding to be used if BOM is not found,
     * or <code>null</code> to use system default encoding.
     * @throws IOException If an I/O error occurs.
     */
    public UnicodeReader(InputStream in, String defaultEncoding) throws IOException {
        byte bom[] = new byte[BOM_SIZE];
        String encoding;
        int unread;
        PushbackInputStream pushbackStream = new PushbackInputStream(in, BOM_SIZE);
        int n = pushbackStream.read(bom, 0, bom.length);

        // Read ahead four bytes and check for BOM marks.
        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 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 {
            encoding = defaultEncoding;
            unread = n;
        }

        // Unread bytes if necessary and skip BOM marks.
        if (unread > 0) {
            pushbackStream.unread(bom, (n - unread), unread);
        } else if (unread < -1) {
            pushbackStream.unread(bom, 0, 0);
        }

        // Use given encoding.
        if (encoding == null) {
            reader = new InputStreamReader(pushbackStream);
        } else {
            reader = new InputStreamReader(pushbackStream, encoding);
        }
    }

    public String getEncoding() {
        return reader.getEncoding();
    }

    public int read(char[] cbuf, int off, int len) throws IOException {
        return reader.read(cbuf, off, len);
    }

    public void close() throws IOException {
        reader.close();
    }
}

@rescdsk 已经提到了 Apache Commons IO 库的 BOMInputStream，但我没有看到它提到如何获得一个InputStream 没有 BOM。

以下是我在 Scala 中的做法。

 import java.io._
 val file = new File(path_to_xml_file_with_BOM)
 val fileInpStream = new FileInputStream(file)   
 val bomIn = new BOMInputStream(fileInpStream, 
         false); // false means don't include BOM

要简单地从您的文件中删除 BOM 字符，我建议使用 Apache Common IO

public BOMInputStream(InputStream delegate,
              boolean include)
Constructs a new BOM InputStream that detects a a ByteOrderMark.UTF_8 and optionally includes it.
Parameters:
delegate - the InputStream to delegate to
include - true to include the UTF-8 BOM or false to exclude it

将 include 设置为 false，您的 BOM 字符将被排除。

很遗憾没有。您必须识别并跳过自己。 This page 详细说明了您需要注意的事项。另请参阅 this SO question 了解更多详细信息。

这是我在大多数字符集中读取 csv 文件的代码。它应该涵盖 99% 的情况。

        try(InputStream inputStream = new FileInputStream(csvFile);){
            BOMInputStream bomInputStream = new BOMInputStream(inputStream ,ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE);
            Charset charset;
            if(!bomInputStream.hasBOM()) charset = StandardCharsets.UTF_8;
            else if(bomInputStream.hasBOM(ByteOrderMark.UTF_8)) charset = StandardCharsets.UTF_8;
            else if(bomInputStream.hasBOM(ByteOrderMark.UTF_16LE)) charset = StandardCharsets.UTF_16LE;
            else if(bomInputStream.hasBOM(ByteOrderMark.UTF_16BE)) charset = StandardCharsets.UTF_16BE;
            else { throw new Exception("The charset of the file " + csvFile + " is not supported.");}
            
            try(Reader streamReader = new InputStreamReader(bomInputStream, charset);
                BufferedReader bufferedReader = new BufferedReader(streamReader);) {
                for(String line; (line = bufferedReader.readLine()) != null; ) {
                    String[] columns = line.split(",");
             //read csv columns
            }
        }

IMO 给出的答案都不是真正令人满意的。只是跳过 BOM，然后以当前平台的默认编码读取流的其余部分，这绝对是错误的。请记住：Unix/Linux 和 windows 上的平台默认值不同：前者是 UTF-8，后者是 ANSI。这种解决方案仅在流的其余部分（在 BOM 之后）仅包含 7 位 ASCII 字符时才有效（我承认，在大多数程序员附近的文件中，例如配置是正确的）。但是一旦出现非 ASCII 字符，这种方法就会失败。

这就是为什么所有可以将字节数组/流转换为字符串（反之亦然）的 java 类/方法都有第二个参数来指示要使用的编码（Reader、Writer、Scanner、String.getBytes() 等）。

世界上有很多字符编码，不仅仅是 UTF-xx。而且 - 在今年 2021 年 - 最终用户应用程序之间仍然存在很多编码问题，特别是如果它们在不同平台（iOS、Windows、Unix）上运行。所有这些问题的存在只是因为程序员懒得学习字符编码是如何工作的。

因此，绝对必须首先评估要使用的编码，然后使用找到的编码执行字符串/流转换。第一步是查阅相应的规范。只有当您无法确定在读取流时遇到哪种编码时，您必须自己评估它。但请注意：这样的评估始终只是“最佳猜测”，没有算法可以涵盖所有可能性。

从这个意义上说，Lee 从 2021 年 2 月 6 日起的答案（和编码示例）是 IMO 最好的答案，但如果没有 BOM，他会回退到 UTF-8。

我遇到了同样的问题，因为我没有阅读一堆文件，所以我做了一个更简单的解决方案。我认为我的编码是 UTF-8，因为当我在此页面的帮助下打印出违规字符时：Get unicode value of a character 我发现它是 \ufeff。我使用代码 System.out.println( "\\u" + Integer.toHexString(str.charAt(0) | 0x10000).substring(1) ); 打印出有问题的 unicode 值。

一旦我得到了有问题的 unicode 值，我在继续阅读之前将其替换在文件的第一行。该部分的业务逻辑：

String str = reader.readLine().trim();
str = str.replace("\ufeff", "");

这解决了我的问题。然后我就可以毫无问题地继续处理文件了。我在 trim() 上添加了前导或尾随空格，您可以根据您的具体需求执行或不执行此操作。

NotePad++ 是一个很好的将 UTF-8 编码转换为 UTF-8(BOM) 编码的工具。

https://notepad-plus-plus.org/downloads/

UTF8BOMTester.java

public class UTF8BOMTester {

public static void main(String[] args) throws FileNotFoundException, IOException {
    // TODO Auto-generated method stub
    File file = new File("test.txt");
    boolean same = UTF8BOMInputStream.isSameEncodingType(file);
    System.out.println(same);
    if (same) {
        UTF8BOMInputStream is = new UTF8BOMInputStream(file);
        BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"));
        System.out.println(br.readLine());
    }

}

static void bytesPrint(byte[] b) {
    for (byte a : b)
        System.out.printf("%x ", a);
}}

UTF8BOMInputStream.java

public class UTF8BOMInputStream extends InputStream {

byte[] SYMBLE_BOM = { (byte) 0xEF, (byte) 0xBB, (byte) 0xBF };
FileInputStream fis;
final boolean isSameEncodingType;
public UTF8BOMInputStream(File file) throws IOException {
    FileInputStream fis=new FileInputStream(file);
    byte[] symble=new byte[3];
    fis.read(symble);
    bytesPrint(symble);
    isSameEncodingType=isSameEncodingType(symble);
    if(isSameEncodingType)
        this.fis=fis;
    else
        this.fis=null;
    
}

@Override
public int read() throws IOException {
    return fis.read();
}

void bytesPrint(byte[] b) {
    for (byte a : b)
        System.out.printf("%x ", a);
}

boolean bytesCompare(byte[] a, byte[] b) {
    if (a.length != b.length)
        return false;

    for (int i = 0; i < a.length; i++) {
        if (a[i] != b[i])
            return false;
    }
    return true;
}
boolean isSameEncodingType(byte[] symble) {
    return bytesCompare(symble,SYMBLE_BOM);
}
public static boolean isSameEncodingType(File file) throws IOException {
    return (new UTF8BOMInputStream(file)).isSameEncodingType;
}