dom4j中使用SAXReader读取xml文件出现Premature end of file异常问题

一般性写法:

SAXReader reader = new SAXReader();

Document dom = null;

try{

dom = reader.read(new File(path));

}catch(Exception e){e.printStackTrace();}

此种写法有时会出现org.dom4j.DocumentException: Error on line -1 of document : Premature end of file. Nested exception: Premature end of file.异常，

而文件却是没什么问题。

官网上有解释说：

使用dom4j解析来自InputStream中的XML内容，发生异常：Premature end of file原因是：

这个InputStream已经读过了，在读入dom4j时，不是从开头读的，因此报错。

另外加点自己的想法：上面一种写法未指定读取文件的编码，导致dom4j在处理解析时出现错误！

因此有了另外一种写法（先获取文件内容存入缓存中）：

Document dom = null;

try{

StringBuffer content = new StringBuffer();

BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(path),"UTF-8"));

String line = null;

while((line = br.readLine()) != null ){

content.append(line+"\n");

}

br.close();

dom = DocumentHelper.parseText(content.toString());

}catch(Exception e){

}

若该种写法仍有问题，请先确认该文件的编码方式，若是UTF-8编码的且进行过BOM mark的则需要对文件内容进行特殊处理（即去掉文件开头的BOM mark标记）。

具体可参见该处理工具类：

</pre><p> </p><pre class="java" name="code">package org.shefron.fc.utfwithbom;

import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PushbackInputStream;

public class UTFFileHandler {

/**
*
* @param file the filePath
* @return the FileInputStream
* @throws Exception
*/
public static InputStream getInputStream(String file) throws Exception{
FileInputStream fis = null;
try{
fis = new FileInputStream(file);
}catch(Exception e){
System.out.println(e.getMessage());
throw new Exception("IO Stream Error!");
}
return fis;

}

/**
*
* @param file the filePath
* @param enc  the default encoding
* @return the UTFFileHandler.UnicodeInputStream
* @throws Exception
*/
public static InputStream getInputStreamWithoutBom(String file,String enc) throws Exception{

UnicodeInputStream stream = null;
try{
FileInputStream fis = new FileInputStream(file);
stream = new UnicodeInputStream(fis,null);
System.out.println("encoding:"+stream.getEncoding() );
}catch(Exception e){
System.out.println(e.getMessage());
throw new Exception("IO Stream Error!");
}
return stream;

}

/**
* 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);
*/
public static 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();
}
}

}