近日在项目中遇到一件诡异的事情,有一个txt文件,用记事本保存和notepad++ 保存,再用Java读取的时候,读出来的结果不一致。
如上面这个txt 文件,读取“自杀”2个字,虽然打印在控制台都是一样的,但是进行长度比对发现notepad++长度是2,但是记事本保存后读出来的长度竟然是3。
后面在网上查询了一下,txt文件编码格式有UTF-8和UTF-8无(BOM) 2中格式,下面来看看 这2种格式有什么不同地方。
由此可以看出,带有BOM编码格式的TXT文件多三个字节出来。而记事本保存的恰好是带有BOM编码格式的文件,而notepad++保存的编码格式确实UTF-8无(BOM)格式。
既然知道了原理,下面贴出解决方案。
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Reader;
public class UTF8Test {
private final static String FILE_PATH = "D:\\Workspaces\\changhong\\myUtil\\src\\main\\resources\\Sen.txt";
/**
*
* @Title readByUtf8WithBom
* @Description 普通方式读取 txt文件,如果用记事本保存会存在bom格式
* @param @return 参数
* @return String 返回类型
* @throws
*/
public static String readByUtf8WithBom() {
File file = new File(FILE_PATH);
FileInputStream in = null;
Reader read = null;
String word = null;
try {
if (file.exists() && file.isFile()) {
in = new FileInputStream(file);
read = new InputStreamReader(in);
BufferedReader bf = new BufferedReader(read);
String txt = null;
while ((txt = bf.readLine()) != null) { // 读取文件
/* 判断文本文件里面的内容是否合法 平台系统中定义 每个敏感词后加上结束标志“|1” */
txt = txt.trim();// 去掉收尾的空格
String flag = txt.substring(txt.lastIndexOf("|") + 1);
if (flag.equals("1")) {
word = txt.substring(0, txt.lastIndexOf("|"));
}
}
}
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return word;
}
/**
*
* @Title readByUtf8WithOutBom
* @Description 读取 txt文件,如果存在bom格式 则去掉
* @param @return 参数
* @return String 返回类型
* @throws
*/
public static String readByUtf8WithOutBom() {
File file = new File(FILE_PATH);
FileInputStream in = null;
String word = null;
try {
if (file.exists() && file.isFile()) {
in = new FileInputStream(file);
BufferedReader bf = new BufferedReader(new UnicodeReader(in,"utf-8"));
String txt = null;
while ((txt = bf.readLine()) != null) { // 读取文件
/* 判断文本文件里面的内容是否合法 平台系统中定义 每个敏感词后加上结束标志“|1” */
txt = txt.trim();// 去掉收尾的空格
String flag = txt.substring(txt.lastIndexOf("|") + 1);
if (flag.equals("1")) {
word = txt.substring(0, txt.lastIndexOf("|"));
}
}
}
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return word;
}
public static void main(String[] args) {
String word =UTF8Test.readByUtf8WithBom();
String wordWithOutBom =UTF8Test.readByUtf8WithOutBom();
System.out.println("含有bom格式的字符串:"+word+",其长度为:"+word.length());
System.out.println("含有bom格式的字符串:"+wordWithOutBom+",其长度为:"+wordWithOutBom.length());
}}
其中UnicodeReader类 是国外某个大神写的,里面具体实现感兴趣的朋友可以去研究一下。
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);
}
}
源代码demo下载