mimeutility.java

java Email you can use it to send email to others

/*
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
 *
 * Copyright 1997-2007 Sun Microsystems, Inc. All rights reserved.
 *
 * The contents of this file are subject to the terms of either the GNU
 * General Public License Version 2 only ("GPL") or the Common Development
 * and Distribution License("CDDL") (collectively, the "License").  You
 * may not use this file except in compliance with the License. You can obtain
 * a copy of the License at https://glassfish.dev.java.net/public/CDDL+GPL.html
 * or glassfish/bootstrap/legal/LICENSE.txt.  See the License for the specific
 * language governing permissions and limitations under the License.
 *
 * When distributing the software, include this License Header Notice in each
 * file and include the License file at glassfish/bootstrap/legal/LICENSE.txt.
 * Sun designates this particular file as subject to the "Classpath" exception
 * as provided by Sun in the GPL Version 2 section of the License file that
 * accompanied this code.  If applicable, add the following below the License
 * Header, with the fields enclosed by brackets [] replaced by your own
 * identifying information: "Portions Copyrighted [year]
 * [name of copyright owner]"
 *
 * Contributor(s):
 *
 * If you wish your version of this file to be governed by only the CDDL or
 * only the GPL Version 2, indicate your decision by adding "[Contributor]
 * elects to include this software in this distribution under the [CDDL or GPL
 * Version 2] license."  If you don't indicate a single choice of license, a
 * recipient has the option to distribute your version of this file under
 * either the CDDL, the GPL Version 2 or to extend the choice of license to
 * its licensees as provided above.  However, if you add GPL Version 2 code
 * and therefore, elected the GPL Version 2 license, then the option applies
 * only if the new code is made subject to such option by the copyright
 * holder.
 */

/*
 * @(#)MimeUtility.java	1.60 07/05/15
 */

package javax.mail.internet;

import javax.mail.MessagingException;
import javax.activation.*;
import java.util.*;
import java.io.*;
import com.sun.mail.util.*;

/**
 * This is a utility class that provides various MIME related
 * functionality. <p>
 *
 * There are a set of methods to encode and decode MIME headers as 
 * per RFC 2047. A brief description on handling such headers is
 * given below: <p>
 *
 * RFC 822 mail headers <strong>must</strong> contain only US-ASCII
 * characters. Headers that contain non US-ASCII characters must be
 * encoded so that they contain only US-ASCII characters. Basically,
 * this process involves using either BASE64 or QP to encode certain
 * characters. RFC 2047 describes this in detail. <p>
 *
 * In Java, Strings contain (16 bit) Unicode characters. ASCII is a
 * subset of Unicode (and occupies the range 0 - 127). A String
 * that contains only ASCII characters is already mail-safe. If the
 * String contains non US-ASCII characters, it must be encoded. An
 * additional complexity in this step is that since Unicode is not
 * yet a widely used charset, one might want to first charset-encode
 * the String into another charset and then do the transfer-encoding.
 * <p>
 * Note that to get the actual bytes of a mail-safe String (say,
 * for sending over SMTP), one must do 
 * <p><blockquote><pre>
 *
 *	byte[] bytes = string.getBytes("iso-8859-1");	
 *
 * </pre></blockquote><p>
 * 
 * The <code>setHeader</code> and <code>addHeader</code> methods
 * on MimeMessage and MimeBodyPart assume that the given header values
 * are Unicode strings that contain only US-ASCII characters. Hence
 * the callers of those methods must insure that the values they pass
 * do not contain non US-ASCII characters. The methods in this class 
 * help do this. <p>
 *
 * The <code>getHeader</code> family of methods on MimeMessage and
 * MimeBodyPart return the raw header value. These might be encoded
 * as per RFC 2047, and if so, must be decoded into Unicode Strings.
 * The methods in this class help to do this. <p>
 *
 * Several System properties control strict conformance to the MIME
 * spec.  Note that these are not session properties but must be set
 * globally as System properties. <p>
 *
 * The <code>mail.mime.decodetext.strict</code> property controls
 * decoding of MIME encoded words.  The MIME spec requires that encoded
 * words start at the beginning of a whitespace separated word.  Some
 * mailers incorrectly include encoded words in the middle of a word.
 * If the <code>mail.mime.decodetext.strict</code> System property is
 * set to <code>"false"</code>, an attempt will be made to decode these
 * illegal encoded words. The default is true. <p>
 *
 * The <code>mail.mime.encodeeol.strict</code> property controls the
 * choice of Content-Transfer-Encoding for MIME parts that are not of
 * type "text".  Often such parts will contain textual data for which
 * an encoding that allows normal end of line conventions is appropriate.
 * In rare cases, such a part will appear to contain entirely textual
 * data, but will require an encoding that preserves CR and LF characters
 * without change.  If the <code>mail.mime.encodeeol.strict</code>
 * System property is set to <code>"true"</code>, such an encoding will
 * be used when necessary.  The default is false. <p>
 *
 * In addition, the <code>mail.mime.charset</code> System property can
 * be used to specify the default MIME charset to use for encoded words
 * and text parts that don't otherwise specify a charset.  Normally, the
 * default MIME charset is derived from the default Java charset, as
 * specified in the <code>file.encoding</code> System property.  Most
 * applications will have no need to explicitly set the default MIME
 * charset.  In cases where the default MIME charset to be used for
 * mail messages is different than the charset used for files stored on
 * the system, this property should be set.
 *
 * @version 1.60, 07/05/15
 * @author  John Mani
 * @author  Bill Shannon
 */

public class MimeUtility {

    // This class cannot be instantiated
    private MimeUtility() { }

    public static final int ALL = -1;

    private static boolean decodeStrict = true;
    private static boolean encodeEolStrict = false;
    private static boolean foldEncodedWords = false;
    private static boolean foldText = true;

    static {
	try {
	    String s = System.getProperty("mail.mime.decodetext.strict");
	    // default to true
	    decodeStrict = s == null || !s.equalsIgnoreCase("false");
	    s = System.getProperty("mail.mime.encodeeol.strict");
	    // default to false
	    encodeEolStrict = s != null && s.equalsIgnoreCase("true");
	    s = System.getProperty("mail.mime.foldencodedwords");
	    // default to false
	    foldEncodedWords = s != null && s.equalsIgnoreCase("true");
	    s = System.getProperty("mail.mime.foldtext");
	    // default to true
	    foldText = s == null || !s.equalsIgnoreCase("false");
	} catch (SecurityException sex) {
	    // ignore it
	}
    }
		

    /**
     * Get the content-transfer-encoding that should be applied
     * to the input stream of this datasource, to make it mailsafe. <p>
     *
     * The algorithm used here is: <br>
     * <ul>
     * <li>
     * If the primary type of this datasource is "text" and if all
     * the bytes in its input stream are US-ASCII, then the encoding
     * is "7bit". If more than half of the bytes are non-US-ASCII, then
     * the encoding is "base64". If less than half of the bytes are
     * non-US-ASCII, then the encoding is "quoted-printable".
     * <li>
     * If the primary type of this datasource is not "text", then if
     * all the bytes of its input stream are US-ASCII, the encoding
     * is "7bit". If there is even one non-US-ASCII character, the
     * encoding is "base64".
     * </ul>
     *
     * @param	ds	DataSource
     * @return		the encoding. This is either "7bit",
     *			"quoted-printable" or "base64"
     */ 
    public static String getEncoding(DataSource ds) {
	ContentType cType = null;
	InputStream is = null;
	String encoding = null;

	try {
	    cType = new ContentType(ds.getContentType());
	    is = ds.getInputStream();
	} catch (Exception ex) {
	    return "base64"; // what else ?!
	}

	boolean isText = cType.match("text/*");
	// if not text, stop processing when we see non-ASCII
	int i = checkAscii(is, ALL, !isText);
	switch (i) {
	case ALL_ASCII:
	    encoding = "7bit"; // all ascii
	    break;
	case MOSTLY_ASCII:
	    encoding = "quoted-printable"; // mostly ascii
	    break;
	default:
	    encoding = "base64"; // mostly binary
	    break;
	}

	// Close the input stream
	try {
	    is.close();
	} catch (IOException ioex) { }

	return encoding;
    }

    /**
     * Same as <code>getEncoding(DataSource)</code> except that instead
     * of reading the data from an <code>InputStream</code> it uses the
     * <code>writeTo</code> method to examine the data.  This is more
     * efficient in the common case of a <code>DataHandler</code>
     * created with an object and a MIME type (for example, a
     * "text/plain" String) because all the I/O is done in this
     * thread.  In the case requiring an <code>InputStream</code> the
     * <code>DataHandler</code> uses a thread, a pair of pipe streams,
     * and the <code>writeTo</code> method to produce the data. <p>
     *
     * @since	JavaMail 1.2
     */
    public static String getEncoding(DataHandler dh) {
	ContentType cType = null;
	String encoding = null;

	/*
	 * Try to pick the most efficient means of determining the
	 * encoding.  If this DataHandler was created using a DataSource,
	 * the getEncoding(DataSource) method is typically faster.  If
	 * the DataHandler was created with an object, this method is
	 * much faster.  To distinguish the two cases, we use a heuristic.
	 * A DataHandler created with an object will always have a null name.
	 * A DataHandler created with a DataSource will usually have a
	 * non-null name.
	 *
	 * XXX - This is actually quite a disgusting hack, but it makes
	 *	 a common case run over twice as fast.
	 */
	if (dh.getName() != null)
	    return getEncoding(dh.getDataSource());

	try {
	    cType = new ContentType(dh.getContentType());
	} catch (Exception ex) {
	    return "base64"; // what else ?!
	}

	if (cType.match("text/*")) {
	    // Check all of the available bytes
	    AsciiOutputStream aos = new AsciiOutputStream(false, false);
	    try {
		dh.writeTo(aos);
	    } catch (IOException ex) {
	    	// ignore it, can't happen
	    }
	    switch (aos.getAscii()) {
	    case ALL_ASCII:
		encoding = "7bit"; // all ascii
		break;
	    case MOSTLY_ASCII:
		encoding = "quoted-printable"; // mostly ascii
		break;
	    default:
		encoding = "base64"; // mostly binary
		break;
	    }
	} else { // not "text"
	    // Check all of available bytes, break out if we find
	    // at least one non-US-ASCII character
	    AsciiOutputStream aos =
			new AsciiOutputStream(true, encodeEolStrict);
	    try {
		dh.writeTo(aos);
	    } catch (IOException ex) { }	// ignore it
	    if (aos.getAscii() == ALL_ASCII) // all ascii
		encoding = "7bit";
	    else // found atleast one non-ascii character, use b64 
		encoding = "base64";
	}

	return encoding;
    }

    /**
     * Decode the given input stream. The Input stream returned is
     * the decoded input stream. All the encodings defined in RFC 2045
     * are supported here. They include "base64", "quoted-printable",
     * "7bit", "8bit", and "binary". In addition, "uuencode" is also
     * supported.
     *
     * @param	is		input stream
     * @param	encoding	the encoding of the stream.
     * @return			decoded input stream.
     */
    public static InputStream decode(InputStream is, String encoding)
		throws MessagingException {
	if (encoding.equalsIgnoreCase("base64"))
	    return new BASE64DecoderStream(is);
	else if (encoding.equalsIgnoreCase("quoted-printable"))
	    return new QPDecoderStream(is);
	else if (encoding.equalsIgnoreCase("uuencode") ||
		 encoding.equalsIgnoreCase("x-uuencode") ||
		 encoding.equalsIgnoreCase("x-uue"))
	    return new UUDecoderStream(is);
	else if (encoding.equalsIgnoreCase("binary") ||
		 encoding.equalsIgnoreCase("7bit") ||
		 encoding.equalsIgnoreCase("8bit"))
	    return is;
	else
	    throw new MessagingException("Unknown encoding: " + encoding);
    }

    /**
     * Wrap an encoder around the given output stream. 
     * All the encodings defined in RFC 2045 are supported here. 
     * They include "base64", "quoted-printable", "7bit", "8bit" and
     * "binary". In addition, "uuencode" is also supported.
     *
     * @param	os		output stream
     * @param	encoding	the encoding of the stream. 
     * @return			output stream that applies the
     *				specified encoding.
     */
    public static OutputStream encode(OutputStream os, String encoding)
		throws MessagingException {
        if (encoding == null)
	    return os;
	else if (encoding.equalsIgnoreCase("base64"))
	    return new BASE64EncoderStream(os);
	else if (encoding.equalsIgnoreCase("quoted-printable"))
	    return new QPEncoderStream(os);
	else if (encoding.equalsIgnoreCase("uuencode") ||
		 encoding.equalsIgnoreCase("x-uuencode") ||
		 encoding.equalsIgnoreCase("x-uue"))
	    return new UUEncoderStream(os);
	else if (encoding.equalsIgnoreCase("binary") ||
		 encoding.equalsIgnoreCase("7bit") ||
		 encoding.equalsIgnoreCase("8bit"))
	    return os;
	else
	    throw new MessagingException("Unknown encoding: " +encoding);
    }

    /**
     * Wrap an encoder around the given output stream.
     * All the encodings defined in RFC 2045 are supported here.
     * They include "base64", "quoted-printable", "7bit", "8bit" and
     * "binary". In addition, "uuencode" is also supported.
     * The <code>filename</code> parameter is used with the "uuencode"
     * encoding and is included in the encoded output.
     *
     * @param   os              output stream
     * @param   encoding        the encoding of the stream.
     * @param   filename        name for the file being encoded (only used
     *                          with uuencode)
     * @return                  output stream that applies the
     *                          specified encoding.
     * @since                   JavaMail 1.2
     */
    public static OutputStream encode(OutputStream os, String encoding,
                                      String filename)
                throws MessagingException {
        if (encoding == null)
            return os;
        else if (encoding.equalsIgnoreCase("base64"))
            return new BASE64EncoderStream(os);
        else if (encoding.equalsIgnoreCase("quoted-printable"))
            return new QPEncoderStream(os);
        else if (encoding.equalsIgnoreCase("uuencode") ||
                 encoding.equalsIgnoreCase("x-uuencode") ||
                 encoding.equalsIgnoreCase("x-uue"))
            return new UUEncoderStream(os, filename);
        else if (encoding.equalsIgnoreCase("binary") ||
                 encoding.equalsIgnoreCase("7bit") ||
                 encoding.equalsIgnoreCase("8bit"))
            return os;
        else
            throw new MessagingException("Unknown encoding: " +encoding);
    }

    /**
     * Encode a RFC 822 "text" token into mail-safe form as per
     * RFC 2047. <p>
     *
     * The given Unicode string is examined for non US-ASCII
     * characters. If the string contains only US-ASCII characters,