java读取UTF-8的txt文件，第一行有?

参考jackpk的博客，网址：https://blog.csdn.net/jackpk/article/details/5702964/

test.txt文件采用写字板保存为UTF-8格式

保存并关闭后使用写字板再次打开该UTF-8文档，中文、字母正常显示

1. import java.io.BufferedReader;  
2. import java.io.File;  
3. import java.io.FileInputStream;  
4. import java.io.InputStreamReader;  
5.   
6. public class ReadTxtFile {  
7.   
8.     public static void main(String[] args) {  
9.         try {  
10.             String charsetName = "UTF-8";   
11.             String path = "D:/to_delete/test.txt";  
12.   
13.             File file = new File(path);  
14.             if (file.isFile() && file.exists())   
15.             {  
16.                 InputStreamReader insReader = new InputStreamReader(  
17.                         new FileInputStream(file), charsetName);  
18.   
19.                 BufferedReader bufReader = new BufferedReader(insReader);  
20.   
21.                 String line = new String();  
22.                 while ((line = bufReader.readLine()) != null) {  
23.                     System.out.println(line);  
24.                 }  
25.                 bufReader.close();  
26.                 insReader.close();  
27.             }  
28.   
29.         } catch (Exception e) {  
30.             System.out.println("读取文件内容操作出错");  
31.             e.printStackTrace();  
32.         }  
33.     }  
34.   
35. } 
    

第一行? ，

Java读取BOM（Byte Order　Mark）的问题，在使用UTF-8时，可以在文件的开始使用3个字节的"EF BB BF"来标识文件使用了UTF-8的编码，当然也可以不用这个3个字节。

上面的问题应该就是因为对开头3个字节的读取导致的。

/**
 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);
    }

}

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.charset.Charset;


public class UTF8Test {
    public static void main(String[] args) throws IOException {
        File f  = new File("./utf.txt");
        FileInputStream in = new FileInputStream(f);
        // 指定读取文件时以UTF-8的格式读取
//        BufferedReader br = new BufferedReader(new InputStreamReader(in, "UTF-8"));
        BufferedReader br = new BufferedReader(new UnicodeReader(in, Charset.defaultCharset().name()));
        
        String line = br.readLine();
        while(line != null)
        {
            System.out.println(line);
            line = br.readLine();
        }
    }
}