Start line:  
End line:  

Snippet Preview

Snippet HTML Code

Stack Overflow Questions
Copyright (c) 2008-2014, Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.

version: 1.1 / 2007-01-25 - changed BOM recognition ordering (longer boms first) Original pseudocode : Thomas Weidenfeller Implementation tweaked: Aki Nieminen Implementation changed: Andrey Somov UTF-32 removed because it is not supported by YAML no default encoding BOMs: 00 00 FE FF = UTF-32, big-endian FF FE 00 00 = UTF-32, little-endian EF BB BF = UTF-8, FE FF = UTF-16, big-endian FF FE = UTF-16, little-endian Win2k Notepad: Unicode format = UTF-16LE
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 {
     private static final Charset UTF8 = Charset.forName("UTF-8");
     private static final Charset UTF16BE = Charset.forName("UTF-16BE");
     private static final Charset UTF16LE = Charset.forName("UTF-16LE");
     InputStreamReader internalIn2 = null;
     private static final int BOM_SIZE = 3;


in InputStream to be read
     public UnicodeReader(InputStream in) {
          = new PushbackInputStream(in);

Get stream encoding or NULL if stream is uninitialized. Call init() or read() method to initialize it.

encoding used
     public String getEncoding() {
         return .getEncoding();

Read-ahead four bytes and check for BOM marks. Extra bytes are unread back to the stream, only BOM bytes are skipped.

Throws: unable to read from stream or incomplete stream
     protected void init() throws IOException {
         if ( != null)
         Charset encoding;
         byte bom[] = new byte[];
         int nunread;
         n = .read(bom, 0, bom.length);
         if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB) && (bom[2] == (byte) 0xBF)) {
             encoding = ;
             unread = n - 3;
         } else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) {
            encoding = ;
            unread = n - 2;
        } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) {
            encoding = ;
            unread = n - 2;
        } else {
            // Unicode BOM mark not found, unread all bytes
            encoding = ;
            unread = n;
        if (unread > 0)
            .unread(bom, (n - unread), unread);
        // Use given encoding
        CharsetDecoder decoder = encoding.newDecoder().onUnmappableCharacter(
         = new InputStreamReader(decoder);
    public void close() throws IOException {
    public int read(char[] cbufint offint lenthrows IOException {
        return .read(cbufofflen);
New to GrepCode? Check out our FAQ X