Example usage for com.itextpdf.text.xml XMLUtil getEncodingName

Introduction

In this page you can find the example usage for com.itextpdf.text.xml XMLUtil getEncodingName.

Prototype

public static String getEncodingName(final byte[] b4) 

Source Link

Document

Returns the IANA encoding name that is auto-detected from the bytes specified, with the endian-ness of that encoding where appropriate.

Usage

From source file:pdfreader.XMLParser.java

License:Open Source License

/**
 * Detects encoding from a stream./*from ww w. j  a  va 2s .  co  m*/
 *
 * @param in the stream
 * @return a Reader with the deduced encoding.
 * @throws IOException                  if IO went wrong
 * @throws UnsupportedEncodingException if unsupported encoding was detected
 */
public InputStreamReader detectEncoding(final InputStream in) throws IOException, UnsupportedEncodingException {
    // we expect a '>' in the first 100 characters
   in.mark(1028);
   byte b4[] = new byte[4];
    int count = in.read(b4);
    if (count != 4)
        throw new IOException("Insufficient length");
    String encoding = XMLUtil.getEncodingName(b4);
    String decl = null;
    if (encoding.equals("UTF-8")) {
        StringBuffer sb = new StringBuffer();
        int c;
        while ((c = in.read()) != -1) {
            if (c == '>')
                break;
            sb.append((char) c);
        }
        decl = sb.toString();
    } else if (encoding.equals("CP037")) {
        ByteArrayOutputStream bi = new ByteArrayOutputStream();
        int c;
        while ((c = in.read()) != -1) {
            if (c == 0x6e) // that's '>' in ebcdic
                break;
            bi.write(c);
        }
        decl = new String(bi.toByteArray(), "CP037");
    }
    if (decl != null) {
        decl = EncodingUtil.getDeclaredEncoding(decl);
        if (decl != null)
            encoding = decl;
    }
    in.reset();
    return new InputStreamReader(in, IanaEncodings.getJavaEncoding(encoding));
}

---