java utf 8 bom_Java读带有BOM的UTF-8文件乱码原因及解决方法

原因：

关于utf-8编码的txt文件，windows以记事本方式保存时会在第一行最开始处自动加入bom格式的相关信息，大概三个字节！

所以java在读取此类文件时第一行时会多出三个不相关的字节，这样对正常的程序产生了不良影响！

解决方法：

网上有如下解决方法确实可行

１.使用UltraEdit将上边的txt文件另存为UTF-8无BOM格式；

２.使用Notepad++打开上边的txt文件执行如下操作“格式-->以UTF-8无BOM格式编码”，修改后将txt文本进行保存

不足之处：

但是这样也有不足，这样对文件生产者提出了很高的要求，万一这样的文件是很多人生产的，那就势必会产生各种各样的问题，这归根到底是jdk的一个bug.

有没有什么办法能够一劳永逸呢，答案是有的，咱们程序里控制，来跟着我一起做！

终极解决方案：

(１)在工程中增加JDK提供的一个工具类：

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)读取时使用如下代码：　　//因为我这边是服务器上的远程文件，如果是本地文件使用File类

URL url = new URL("http://****/***/test.txt");

// File f  = new File("test.txt");

String enc = null; // or NULL to use systemdefault

UnicodeInputStream uin = new UnicodeInputStream(url.openStream(),enc);  //如果是本地将url.openStream -> new FileInputStream(f)

enc = uin.getEncoding(); // check and skip possible BOM bytes

InputStreamReader in;

if (enc == null){

in = new InputStreamReader(uin);

}else {

in = new InputStreamReader(uin, enc);

}

BufferedReader reader = new BufferedReader(in);

//BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream("D:/tags.txt"),"utf-8"));

String tmp =reader.readLine();

这样读取的结果就是正常的了，有什么问题还可以留言！