java的unicode对于无头Utf-8格式的编码的判断是缺失
工具类实现java对文件编码的判断
编码格式判断工具类方法
public static String getTxtEncode(InputStream in) throws IOException {
String dc = Charset.defaultCharset().name();
UnicodeInputStream uin = new UnicodeInputStream(in, dc);
if ("UTF-8".equals(uin.getEncoding())) {
uin.close();
return "UTF-8";
}
uin.close();
byte[] head = new byte[3];
in.read(head);
in.reset();
String code = "GBK";
if (head[0] == -1 && head[1] == -2)
code = "UTF-16";
if (head[0] == -2 && head[1] == -1)
code = "Unicode";
// 带BOM
if (head[0] == -17 && head[1] == -69 && head[2] == -65)
code = "UTF-8";
if ("Unicode".equals(code)) {
code = "UTF-16";
}
return code;
}
此处代码实现对无头uff-8编码判断
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);
*
* 添加对无Bom Utf-8文件编码的识别
*/
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();
}
}
参考此文: http://jybzjf.iteye.com/blog/2262392