java读取UTF-8文本文件第一个字符多出一个问号解决方法

最新推荐文章于 2022-03-08 22:12:17 发布

原创最新推荐文章于 2022-03-08 22:12:17 发布 · 置顶 · 9.9k 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#编码 #出现问号 #UTF-8

本文介绍了一个Java工具类，用于自动检测文件的编码格式（如UTF-8、UTF-16等），并提供了使用示例。通过该工具类可以简化文件读取过程中的编码适配工作。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1.创建工具类

import java.io.*;

public class UnicodeReader extends Reader {
  PushbackInputStream internalIn;
  InputStreamReader   internalIn2 = null;
  String              defaultEnc;

  private static final int BOM_SIZE = 4;

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

  public String getDefaultEncoding() {
     return defaultEnc;
  }

  
  public String getEncoding() {
     if (internalIn2 == null) return null;
     return internalIn2.getEncoding();
  }

  
  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);
  }

}

2.使用工具类读取文件

BufferedReader br = new BufferedReader(
     new UnicodeReader(
     new FileInputStream(sqlFile), 
     Charset.defaultCharset().name()));

3.出现有问号的编写

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"));
String line = br.readLine();
while(line != null)
{
System.out.println(line);
line = br.readLine();
}