UTF-8 encoding problems?

Use this code to find the location of a wayward non-UTF-8 character:

import java.io.File;
import java.io.FileInputStream;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CodingErrorAction;

public class CheckEncoding {
 public static void main(String[] args) {
  FileInputStream fis;
  try {
   fis = new FileInputStream(new File(args[0]));
   CharsetDecoder decoder = Charset.forName("UTF-8").newDecoder();
   decoder.onMalformedInput(CodingErrorAction.REPORT);
   decoder.onUnmappableCharacter(CodingErrorAction.REPORT);
   byte[] buff = new byte[1];
   int i = 0;
   while ((i = fis.read(buff)) > 0) {
    System.out.print(decoder.decode(ByteBuffer.wrap(buff, 0, i))
      .array());
   }
  } catch (Exception e) {
   e.printStackTrace();
  }
 }
}

Use this class to automagically scrub out unwanted bad characters:

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
import java.nio.charset.CodingErrorAction;

public class UTF8Scrubber extends InputStream {

 CharsetDecoder decoder = null;
 CharsetEncoder encoder = null;
 private InputStream is;
 
 public UTF8Scrubber(InputStream is) {
  super();
  this.is = is;
  decoder = Charset.forName("UTF-8").newDecoder();
  decoder.onMalformedInput(CodingErrorAction.REPLACE);
  decoder.replaceWith(" ");
  decoder.onUnmappableCharacter(CodingErrorAction.REPLACE);
  encoder = Charset.forName("UTF-8").newEncoder();
 }



 @Override
 public int read() throws IOException {
  byte[] b = new byte[1];
  if(is.read(b) == 1)
   return encoder.encode(decoder.decode(ByteBuffer.wrap(b))).array()[0];
  return -1;
 }
 
 public static void main(String[] args) throws IOException {
  byte[] buff = new byte[1024];
  int i = 0;
  InputStream is = new UTF8Scrubber(new FileInputStream(new File(args[0])));
  while((i=is.read(buff))>0) {
   System.out.print(new String(buff,0,i));
  }
 }
 
}