La marca de orden de bytes arruina la lectura de archivos en Java
Estoy intentando leer archivos CSV usando Java. Algunos de los archivos pueden tener una marca de orden de bytes al principio, pero no todos. Cuando está presente, el orden de los bytes se lee junto con el resto de la primera línea, lo que provoca problemas con las comparaciones de cadenas.
¿Existe una manera fácil de omitir la marca de orden de bytes cuando está presente?
Aceptado
EDITAR : Hice una versión adecuada en GitHub: https://github.com/gpakosz/UnicodeBOMInputStream
Aquí hay una clase que codifiqué hace un tiempo, simplemente edité el nombre del paquete antes de pegarlo. Nada especial, es bastante similar a las soluciones publicadas en la base de datos de errores de SUN. Incorpórelo en su código y estará bien.
/* ____________________________________________________________________________
*
* File: UnicodeBOMInputStream.java
* Author: Gregory Pakosz.
* Date: 02 - November - 2005
* ____________________________________________________________________________
*/
package com.stackoverflow.answer;
import java.io.IOException;
import java.io.InputStream;
import java.io.PushbackInputStream;
/**
* The <code>UnicodeBOMInputStream</code> class wraps any
* <code>InputStream</code> and detects the presence of any Unicode BOM
* (Byte Order Mark) at its beginning, as defined by
* <a href="http://www.faqs.org/rfcs/rfc3629.html">RFC 3629 - UTF-8, a transformation format of ISO 10646</a>
*
* <p>The
* <a href="http://www.unicode.org/unicode/faq/utf_bom.html">Unicode FAQ</a>
* defines 5 types of BOMs:<ul>
* <li><pre>00 00 FE FF = UTF-32, big-endian</pre></li>
* <li><pre>FF FE 00 00 = UTF-32, little-endian</pre></li>
* <li><pre>FE FF = UTF-16, big-endian</pre></li>
* <li><pre>FF FE = UTF-16, little-endian</pre></li>
* <li><pre>EF BB BF = UTF-8</pre></li>
* </ul></p>
*
* <p>Use the {@link #getBOM()} method to know whether a BOM has been detected
* or not.
* </p>
* <p>Use the {@link #skipBOM()} method to remove the detected BOM from the
* wrapped <code>InputStream</code> object.</p>
*/
public class UnicodeBOMInputStream extends InputStream
{
/**
* Type safe enumeration class that describes the different types of Unicode
* BOMs.
*/
public static final class BOM
{
/**
* NONE.
*/
public static final BOM NONE = new BOM(new byte[]{},"NONE");
/**
* UTF-8 BOM (EF BB BF).
*/
public static final BOM UTF_8 = new BOM(new byte[]{(byte)0xEF,
(byte)0xBB,
(byte)0xBF},
"UTF-8");
/**
* UTF-16, little-endian (FF FE).
*/
public static final BOM UTF_16_LE = new BOM(new byte[]{ (byte)0xFF,
(byte)0xFE},
"UTF-16 little-endian");
/**
* UTF-16, big-endian (FE FF).
*/
public static final BOM UTF_16_BE = new BOM(new byte[]{ (byte)0xFE,
(byte)0xFF},
"UTF-16 big-endian");
/**
* UTF-32, little-endian (FF FE 00 00).
*/
public static final BOM UTF_32_LE = new BOM(new byte[]{ (byte)0xFF,
(byte)0xFE,
(byte)0x00,
(byte)0x00},
"UTF-32 little-endian");
/**
* UTF-32, big-endian (00 00 FE FF).
*/
public static final BOM UTF_32_BE = new BOM(new byte[]{ (byte)0x00,
(byte)0x00,
(byte)0xFE,
(byte)0xFF},
"UTF-32 big-endian");
/**
* Returns a <code>String</code> representation of this <code>BOM</code>
* value.
*/
public final String toString()
{
return description;
}
/**
* Returns the bytes corresponding to this <code>BOM</code> value.
*/
public final byte[] getBytes()
{
final int length = bytes.length;
final byte[] result = new byte[length];
// Make a defensive copy
System.arraycopy(bytes,0,result,0,length);
return result;
}
private BOM(final byte bom[], final String description)
{
assert(bom != null) : "invalid BOM: null is not allowed";
assert(description != null) : "invalid description: null is not allowed";
assert(description.length() != 0) : "invalid description: empty string is not allowed";
this.bytes = bom;
this.description = description;
}
final byte bytes[];
private final String description;
} // BOM
/**
* Constructs a new <code>UnicodeBOMInputStream</code> that wraps the
* specified <code>InputStream</code>.
*
* @param inputStream an <code>InputStream</code>.
*
* @throws NullPointerException when <code>inputStream</code> is
* <code>null</code>.
* @throws IOException on reading from the specified <code>InputStream</code>
* when trying to detect the Unicode BOM.
*/
public UnicodeBOMInputStream(final InputStream inputStream) throws NullPointerException,
IOException
{
if (inputStream == null)
throw new NullPointerException("invalid input stream: null is not allowed");
in = new PushbackInputStream(inputStream,4);
final byte bom[] = new byte[4];
final int read = in.read(bom);
switch(read)
{
case 4:
if ((bom[0] == (byte)0xFF) &&
(bom[1] == (byte)0xFE) &&
(bom[2] == (byte)0x00) &&
(bom[3] == (byte)0x00))
{
this.bom = BOM.UTF_32_LE;
break;
}
else
if ((bom[0] == (byte)0x00) &&
(bom[1] == (byte)0x00) &&
(bom[2] == (byte)0xFE) &&
(bom[3] == (byte)0xFF))
{
this.bom = BOM.UTF_32_BE;
break;
}
case 3:
if ((bom[0] == (byte)0xEF) &&
(bom[1] == (byte)0xBB) &&
(bom[2] == (byte)0xBF))
{
this.bom = BOM.UTF_8;
break;
}
case 2:
if ((bom[0] == (byte)0xFF) &&
(bom[1] == (byte)0xFE))
{
this.bom = BOM.UTF_16_LE;
break;
}
else
if ((bom[0] == (byte)0xFE) &&
(bom[1] == (byte)0xFF))
{
this.bom = BOM.UTF_16_BE;
break;
}
default:
this.bom = BOM.NONE;
break;
}
if (read > 0)
in.unread(bom,0,read);
}
/**
* Returns the <code>BOM</code> that was detected in the wrapped
* <code>InputStream</code> object.
*
* @return a <code>BOM</code> value.
*/
public final BOM getBOM()
{
// BOM type is immutable.
return bom;
}
/**
* Skips the <code>BOM</code> that was found in the wrapped
* <code>InputStream</code> object.
*
* @return this <code>UnicodeBOMInputStream</code>.
*
* @throws IOException when trying to skip the BOM from the wrapped
* <code>InputStream</code> object.
*/
public final synchronized UnicodeBOMInputStream skipBOM() throws IOException
{
if (!skipped)
{
in.skip(bom.bytes.length);
skipped = true;
}
return this;
}
/**
* {@inheritDoc}
*/
public int read() throws IOException
{
return in.read();
}
/**
* {@inheritDoc}
*/
public int read(final byte b[]) throws IOException,
NullPointerException
{
return in.read(b,0,b.length);
}
/**
* {@inheritDoc}
*/
public int read(final byte b[],
final int off,
final int len) throws IOException,
NullPointerException
{
return in.read(b,off,len);
}
/**
* {@inheritDoc}
*/
public long skip(final long n) throws IOException
{
return in.skip(n);
}
/**
* {@inheritDoc}
*/
public int available() throws IOException
{
return in.available();
}
/**
* {@inheritDoc}
*/
public void close() throws IOException
{
in.close();
}
/**
* {@inheritDoc}
*/
public synchronized void mark(final int readlimit)
{
in.mark(readlimit);
}
/**
* {@inheritDoc}
*/
public synchronized void reset() throws IOException
{
in.reset();
}
/**
* {@inheritDoc}
*/
public boolean markSupported()
{
return in.markSupported();
}
private final PushbackInputStream in;
private final BOM bom;
private boolean skipped = false;
} // UnicodeBOMInputStream
Y lo estás usando de esta manera:
import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.InputStreamReader;
public final class UnicodeBOMInputStreamUsage
{
public static void main(final String[] args) throws Exception
{
FileInputStream fis = new FileInputStream("test/offending_bom.txt");
UnicodeBOMInputStream ubis = new UnicodeBOMInputStream(fis);
System.out.println("detected BOM: " + ubis.getBOM());
System.out.print("Reading the content of the file without skipping the BOM: ");
InputStreamReader isr = new InputStreamReader(ubis);
BufferedReader br = new BufferedReader(isr);
System.out.println(br.readLine());
br.close();
isr.close();
ubis.close();
fis.close();
fis = new FileInputStream("test/offending_bom.txt");
ubis = new UnicodeBOMInputStream(fis);
isr = new InputStreamReader(ubis);
br = new BufferedReader(isr);
ubis.skipBOM();
System.out.print("Reading the content of the file after skipping the BOM: ");
System.out.println(br.readLine());
br.close();
isr.close();
ubis.close();
fis.close();
}
} // UnicodeBOMInputStreamUsage
La biblioteca Apache Commons IOInputStream tiene una que puede detectar y descartar listas de materiales: BOMInputStream(javadoc) :
BOMInputStream bomIn = new BOMInputStream(in);
int firstNonBOMByte = bomIn.read(); // Skips BOM
if (bomIn.hasBOM()) {
// has a UTF-8 BOM
}
Si también necesita detectar diferentes codificaciones, también puede distinguir entre varias marcas de orden de bytes diferentes, por ejemplo, UTF-8 frente a UTF-16 big + little endian; detalles en el enlace del documento anterior. Luego puede usar el detectado ByteOrderMarkpara elegir un Charsetpara decodificar la transmisión. (Probablemente haya una forma más sencilla de hacer esto si necesita toda esta funcionalidad; ¿tal vez el UnicodeReader en la respuesta de BalusC?). Tenga en cuenta que, en general, no existe una muy buena manera de detectar en qué codificación se encuentran algunos bytes, pero si la secuencia comienza con una lista de materiales, aparentemente esto puede ser útil.
Editar : si necesita detectar la lista de materiales en UTF-16, UTF-32, etc., entonces el constructor debe ser:
new BOMInputStream(is, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE,
ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE)
Vota a favor del comentario de @martin-charlesworth :)
