Base64.java
/*
* This file is part of Waarp Project (named also Waarp or GG).
*
* Copyright (c) 2019, Waarp SAS, and individual contributors by the @author
* tags. See the COPYRIGHT.txt in the distribution for a full listing of
* individual contributors.
*
* All Waarp Project is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or (at your
* option) any later version.
*
* Waarp is distributed in the hope that it will be useful, but WITHOUT ANY
* WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
* A PARTICULAR PURPOSE. See the GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along with
* Waarp . If not, see <http://www.gnu.org/licenses/>.
*/
package org.waarp.common.utility;
import org.waarp.common.file.FileUtils;
import org.waarp.common.logging.SysErrLogger;
import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.FilterInputStream;
import java.io.FilterOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
import java.io.ObjectStreamClass;
import java.io.OutputStream;
import java.io.Serializable;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.util.zip.GZIPInputStream;
import java.util.zip.GZIPOutputStream;
/**
* <p>
* Encodes and decodes to and from Base64 notation.
* </p>
* <p>
* Homepage: <a href="http://iharder.net/base64">http://iharder.net/base64</a>.
* </p>
*
* <p>
* Example:
* </p>
*
* {@code String encoded = Base64.encode( myByteArray );} <br />
* {@code byte[] myByteArray = Base64.decode( encoded );}
*
* <p>
* The <tt>options</tt> parameter, which appears in a few places, is used to
* pass several pieces of
* information to the encoder. In the "higher level" methods such as
* encodeBytes( bytes, options ) the options
* parameter can be used to indicate such things as first gzipping the bytes
* before encoding them, not
* inserting linefeeds, and encoding using the URL-safe and Ordered dialects.
* </p>
*
* <p>
* Note, according to <a href="http://www.faqs.org/rfcs/rfc3548.html">RFC3548</a>,
* Section 2.1,
* implementations should not add line feeds unless explicitly told to do so.
* I've got Base64 set to this
* behavior now, although earlier versions broke lines by default.
* </p>
*
* <p>
* The constants defined in Base64 can be OR-ed together to combine options, so
* you might make a call like
* this:
* </p>
*
* {@code String encoded = Base64.encodeBytes( mybytes, Base64.GZIP |
* Base64.DO_BREAK_LINES );}
* <p>
* to compress the data before encoding it and then making the output have
* newline characters.
* </p>
* <p>
* Also...
* </p>
* {@code String encoded = Base64.encodeBytes( crazyString.getBytes() );}
*
*
*
* <p>
* Change Log:
* </p>
* <ul>
* <li>v2.3.7 - Fixed subtle bug when base 64 input stream contained the value
* 01111111, which is an invalid
* base 64 character but should not throw an ArrayIndexOutOfBoundsException
* either. Led to discovery of
* mishandling (or potential for better handling) of other bad input
* characters.
* You should now get an
* IOException if you try decoding something that has bad characters in
* it.</li>
* <li>v2.3.6 - Fixed bug when breaking lines and the final byte of the encoded
* string ended in the last
* column; the buffer was not properly shrunk and contained an extra (null)
* byte
* that made it into the
* string.</li>
* <li>v2.3.5 - Fixed bug in {@link #encodeFromFile} where estimated buffer
* size
* was wrong for files of size
* 31, 34, and 37 bytes.</li>
* <li>v2.3.4 - Fixed bug when working with gzipped streams whereby flushing
* the
* Base64.OutputStream closed
* the Base64 encoding (by padding with equals signs) too soon. Also added an
* option to suppress the automatic
* decoding of gzipped streams. Also added experimental support for specifying
* a
* class loader when using the
* {@link #decodeToObject(String, int, ClassLoader)}
* method.</li>
* <li>v2.3.3 - Changed default char encoding to US-ASCII which reduces the
* internal Java footprint with its
* CharEncoders and so forth. Fixed some javadocs that were inconsistent.
* Removed imports and specified things
* like java.io.IOException explicitly inline.</li>
* <li>v2.3.2 - Reduced memory footprint! Finally refined the "guessing" of how
* big the final encoded data
* will be so that the code doesn't have to create two output arrays: an
* oversized initial one and then a
* final, exact-sized one. Big win when using the {@link
* #encodeBytesToBytes(byte[])} family of methods (and
* not using the gzip options which uses a different mechanism with streams and
* stuff).</li>
* <li>v2.3.1 - Added {@link #encodeBytesToBytes(byte[], int, int, int)} and
* some similar helper methods to be
* more efficient with memory by not returning a String but just a byte
* array.</li>
* <li>v2.3 - <strong>This is not a drop-in replacement!</strong> This is two
* years of comments and bug fixes
* queued up and finally executed. Thanks to everyone who sent me stuff, and
* I'm
* sorry I wasn't able to
* distribute your fixes to everyone else. Much bad coding was cleaned up
* including throwing exceptions where
* necessary instead of returning null values or something similar. Here are
* some changes that may affect you:
* <ul>
* <li><em>Does not break lines, by default.</em> This is to keep in compliance
* with
* <a href="http://www.faqs.org/rfcs/rfc3548.html">RFC3548</a>.</li>
* <li><em>Throws exceptions instead of returning null values.</em> Because
* some
* operations (especially those
* that may permit the GZIP option) use IO streams, there is a possiblity of an
* java.io.IOException being
* thrown. After some discussion and thought, I've changed the behavior of the
* methods to throw
* java.io.IOExceptions rather than return null if ever there's an error. I
* think this is more appropriate,
* though it will require some changes to your code. Sorry, it should have been
* done this way to begin
* with.</li>
* <li><em>Removed all references to System.out, System.err, and the like.</em>
* Shame on me. All I can say is
* sorry they were ever there.</li>
* <li><em>Throws NullPointerExceptions and IllegalArgumentExceptions</em> as
* needed such as when passed
* arrays are null or offsets are invalid.</li>
* <li>Cleaned up as much javadoc as I could to avoid any javadoc warnings.
* This
* was especially annoying
* before for people who were thorough in their own projects and then had gobs
* of javadoc warnings on this
* file.</li>
* </ul>
* <li>v2.2.1 - Fixed bug using URL_SAFE and ORDERED encodings. Fixed bug when
* using very small files (~<
* 40 bytes).</li>
* <li>v2.2 - Added some helper methods for encoding/decoding directly from one
* file to the next. Also added a
* main() method to support command line encoding/decoding from one file to the
* next. Also added these Base64
* dialects:
* <ol>
* <li>The default is RFC3548 format.</li>
* <li>Calling Base64.setFormat(Base64.BASE64_FORMAT.URLSAFE_FORMAT) generates
* URL and file name friendly
* format as described in Section 4 of RFC3548. http://www.faqs.org/rfcs/rfc3548.html</li>
* <li>Calling Base64.setFormat(Base64.BASE64_FORMAT.ORDERED_FORMAT) generates
* URL and file name friendly
* format that preserves lexical ordering as described in
* http://www.faqs.org/qa/rfcc-1940.html</li>
* </ol>
* Special thanks to Jim Kellerman at <a href="http://www.powerset.com/">http://www.powerset.com/</a>
* for
* contributing the new Base64 dialects.</li>
*
* <li>v2.1 - Cleaned up javadoc comments and unused variables and methods.
* Added some convenience methods for
* reading and writing to and from files.</li>
* <li>v2.0.2 - Now specifies UTF-8 encoding in places where the code fails on
* systems with other encodings
* (like EBCDIC).</li>
* <li>v2.0.1 - Fixed an error when decoding a single byte, that is, when the
* encoded data was a single
* byte.</li>
* <li>v2.0 - I got rid of methods that used booleans to set options. Now
* everything is more consolidated and
* cleaner. The code now detects when data that's being decoded is
* gzip-compressed and will decompress it
* automatically. Generally things are cleaner. You'll probably have to change
* some method calls that you were
* making to support the new options format (<tt>int</tt>s that you "OR"
* together).</li>
* <li>v1.5.1 - Fixed bug when decompressing and decoding to a byte[] using
* <tt>decode( String s, boolean gzipCompressed )</tt>. Added the ability to
* "suspend" encoding in the Output
* Stream so you can turn on and off the encoding if you need to embed base64
* data in an otherwise "normal"
* stream (like an XML file).</li>
* <li>v1.5 - Output stream pases on flush() command but doesn't do anything
* itself. This helps when using
* GZIP streams. Added the ability to GZip-compress objects before encoding
* them.</li>
* <li>v1.4 - Added helper methods to read/write files.</li>
* <li>v1.3.6 - Fixed OutputStream.flush() so that 'position' is reset.</li>
* <li>v1.3.5 - Added flag to turn on and off line breaks. Fixed bug in input
* stream where last buffer being
* read, if not completely full, was not returned.</li>
* <li>v1.3.4 - Fixed when "improperly padded stream" error was thrown at the
* wrong time.</li>
* <li>v1.3.3 - Fixed I/O streams which were totally messed up.</li>
* </ul>
*
* <p>
* I am placing this code in the Public Domain. Do with it as you will. This
* software comes with no guarantees
* or warranties but with plenty of well-wishing instead! Please visit
* <a href="http://iharder.net/base64">http://iharder.net/base64</a>
* periodically to check for updates or to
* contribute improvements.
* </p>
*
* @author Robert Harder
* @author rob@iharder.net
* @version 2.3.7
*/
public final class Base64 {
/* ******** P U B L I C F I E L D S ******** */
/**
* No options specified. Value is zero.
*/
public static final int NO_OPTIONS = 0;
/**
* Specify encoding in first bit. Value is one.
*/
public static final int ENCODE = 1;
/**
* Specify decoding in first bit. Value is zero.
*/
public static final int DECODE = 0;
/**
* Specify that data should be gzip-compressed in second bit. Value is two.
*/
public static final int GZIP = 2;
/**
* Specify that gzipped data should <em>not</em> be automatically gunzipped.
*/
public static final int DONT_GUNZIP = 4;
/**
* Do break lines when encoding. Value is 8.
*/
public static final int DO_BREAK_LINES = 8;
/**
* Encode using Base64-like encoding that is URL- and Filename-safe as
* described in Section 4 of RFC3548:
* <a href="http://www.faqs.org/rfcs/rfc3548.html">http://www.faqs.org/rfcs/rfc3548.html</a>.
* It is important
* to note that data encoded this way is <em>not</em> officially valid
* Base64, or at the very least should not
* be called Base64 without also specifying that is was encoded using the
* URL- and Filename-safe dialect.
*/
public static final int URL_SAFE = 16;
/**
* Encode using the special "ordered" dialect of Base64 described here:
* <a href="http://www.faqs.org/qa/rfcc-1940.html">http://www.faqs.org/qa/rfcc-1940.html</a>.
*/
public static final int ORDERED = 32;
/* ******** P R I V A T E F I E L D S ******** */
/**
* Maximum line length (76) of Base64 output.
*/
private static final int MAX_LINE_LENGTH = 76;
/**
* The equals sign (=) as a byte.
*/
private static final byte EQUALS_SIGN = (byte) '=';
/**
* The new line character (\n) as a byte.
*/
private static final byte NEW_LINE = (byte) '\n';
/**
* Preferred encoding.
*/
private static final String PREFERRED_ENCODING = "US-ASCII";
private static final byte WHITE_SPACE_ENC = -5;
// Indicates white space in encoding
private static final byte EQUALS_SIGN_ENC = -1;
// Indicates equals sign in encoding
/* ******** S T A N D A R D B A S E 6 4 A L P H A B E T ******** */
/**
* The 64 valid Base64 values.
*/
/* Host platform me be something funny like EBCDIC, so we hardcode these values. */
private static final byte[] _STANDARD_ALPHABET = {
(byte) 'A', (byte) 'B', (byte) 'C', (byte) 'D', (byte) 'E', (byte) 'F',
(byte) 'G', (byte) 'H', (byte) 'I', (byte) 'J', (byte) 'K', (byte) 'L',
(byte) 'M', (byte) 'N', (byte) 'O', (byte) 'P', (byte) 'Q', (byte) 'R',
(byte) 'S', (byte) 'T', (byte) 'U', (byte) 'V', (byte) 'W', (byte) 'X',
(byte) 'Y', (byte) 'Z', (byte) 'a', (byte) 'b', (byte) 'c', (byte) 'd',
(byte) 'e', (byte) 'f', (byte) 'g', (byte) 'h', (byte) 'i', (byte) 'j',
(byte) 'k', (byte) 'l', (byte) 'm', (byte) 'n', (byte) 'o', (byte) 'p',
(byte) 'q', (byte) 'r', (byte) 's', (byte) 't', (byte) 'u', (byte) 'v',
(byte) 'w', (byte) 'x', (byte) 'y', (byte) 'z', (byte) '0', (byte) '1',
(byte) '2', (byte) '3', (byte) '4', (byte) '5', (byte) '6', (byte) '7',
(byte) '8', (byte) '9', (byte) '+', (byte) '/'
};
/**
* Translates a Base64 value to either its 6-bit reconstruction value or a
* negative number indicating some
* other meaning.
**/
private static final byte[] _STANDARD_DECODABET = {
-9, -9, -9, -9, -9, -9, -9, -9, -9, // Decimal 0 - 8
-5, -5, // Whitespace: Tab and Linefeed
-9, -9, // Decimal 11 - 12
-5, // Whitespace: Carriage Return
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 14 - 26
-9, -9, -9, -9, -9, // Decimal 27 - 31
-5, // Whitespace: Space
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, // Decimal 33 - 42
62, // Plus sign at decimal 43
-9, -9, -9, // Decimal 44 - 46
63, // Slash at decimal 47
52, 53, 54, 55, 56, 57, 58, 59, 60, 61, // Numbers zero through nine
-9, -9, -9, // Decimal 58 - 60
-1, // Equals sign at decimal 61
-9, -9, -9, // Decimal 62 - 64
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
// Letters 'A' through 'N'
14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
// Letters 'O' through 'Z'
-9, -9, -9, -9, -9, -9, // Decimal 91 - 96
26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
// Letters 'a' through 'm'
39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51,
// Letters 'n' through 'z'
-9, -9, -9, -9, -9 // Decimal 123 - 127
, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 128 - 139
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 140 - 152
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 153 - 165
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 166 - 178
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 179 - 191
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 192 - 204
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 205 - 217
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 218 - 230
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 231 - 243
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9 // Decimal 244 - 255
};
/* ******** U R L S A F E B A S E 6 4 A L P H A B E T ******** */
/**
* Used in the URL- and Filename-safe dialect described in Section 4 of
* RFC3548:
* <a href="http://www.faqs.org/rfcs/rfc3548.html">http://www.faqs.org/rfcs/rfc3548.html</a>.
* Notice that the
* last two bytes become "hyphen" and "underscore" instead of "plus" and
* "slash."
*/
private static final byte[] _URL_SAFE_ALPHABET = {
(byte) 'A', (byte) 'B', (byte) 'C', (byte) 'D', (byte) 'E', (byte) 'F',
(byte) 'G', (byte) 'H', (byte) 'I', (byte) 'J', (byte) 'K', (byte) 'L',
(byte) 'M', (byte) 'N', (byte) 'O', (byte) 'P', (byte) 'Q', (byte) 'R',
(byte) 'S', (byte) 'T', (byte) 'U', (byte) 'V', (byte) 'W', (byte) 'X',
(byte) 'Y', (byte) 'Z', (byte) 'a', (byte) 'b', (byte) 'c', (byte) 'd',
(byte) 'e', (byte) 'f', (byte) 'g', (byte) 'h', (byte) 'i', (byte) 'j',
(byte) 'k', (byte) 'l', (byte) 'm', (byte) 'n', (byte) 'o', (byte) 'p',
(byte) 'q', (byte) 'r', (byte) 's', (byte) 't', (byte) 'u', (byte) 'v',
(byte) 'w', (byte) 'x', (byte) 'y', (byte) 'z', (byte) '0', (byte) '1',
(byte) '2', (byte) '3', (byte) '4', (byte) '5', (byte) '6', (byte) '7',
(byte) '8', (byte) '9', (byte) '-', (byte) '_'
};
/**
* Used in decoding URL- and Filename-safe dialects of Base64.
*/
private static final byte[] _URL_SAFE_DECODABET = {
-9, -9, -9, -9, -9, -9, -9, -9, -9, // Decimal 0 - 8
-5, -5, // Whitespace: Tab and Linefeed
-9, -9, // Decimal 11 - 12
-5, // Whitespace: Carriage Return
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 14 - 26
-9, -9, -9, -9, -9, // Decimal 27 - 31
-5, // Whitespace: Space
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, // Decimal 33 - 42
-9, // Plus sign at decimal 43
-9, // Decimal 44
62, // Minus sign at decimal 45
-9, // Decimal 46
-9, // Slash at decimal 47
52, 53, 54, 55, 56, 57, 58, 59, 60, 61, // Numbers zero through nine
-9, -9, -9, // Decimal 58 - 60
-1, // Equals sign at decimal 61
-9, -9, -9, // Decimal 62 - 64
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
// Letters 'A' through 'N'
14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
// Letters 'O' through 'Z'
-9, -9, -9, -9, // Decimal 91 - 94
63, // Underscore at decimal 95
-9, // Decimal 96
26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
// Letters 'a' through 'm'
39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51,
// Letters 'n' through 'z'
-9, -9, -9, -9, -9 // Decimal 123 - 127
, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 128 - 139
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 140 - 152
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 153 - 165
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 166 - 178
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 179 - 191
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 192 - 204
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 205 - 217
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 218 - 230
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 231 - 243
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9 // Decimal 244 - 255
};
/* ******** O R D E R E D B A S E 6 4 A L P H A B E T ******** */
/**
* I don't get the point of this technique, but someone requested it, and
* it
* is described here:
* <a href="http://www.faqs.org/qa/rfcc-1940.html">http://www.faqs.org/qa/rfcc-1940.html</a>.
*/
private static final byte[] _ORDERED_ALPHABET = {
(byte) '-', (byte) '0', (byte) '1', (byte) '2', (byte) '3', (byte) '4',
(byte) '5', (byte) '6', (byte) '7', (byte) '8', (byte) '9', (byte) 'A',
(byte) 'B', (byte) 'C', (byte) 'D', (byte) 'E', (byte) 'F', (byte) 'G',
(byte) 'H', (byte) 'I', (byte) 'J', (byte) 'K', (byte) 'L', (byte) 'M',
(byte) 'N', (byte) 'O', (byte) 'P', (byte) 'Q', (byte) 'R', (byte) 'S',
(byte) 'T', (byte) 'U', (byte) 'V', (byte) 'W', (byte) 'X', (byte) 'Y',
(byte) 'Z', (byte) '_', (byte) 'a', (byte) 'b', (byte) 'c', (byte) 'd',
(byte) 'e', (byte) 'f', (byte) 'g', (byte) 'h', (byte) 'i', (byte) 'j',
(byte) 'k', (byte) 'l', (byte) 'm', (byte) 'n', (byte) 'o', (byte) 'p',
(byte) 'q', (byte) 'r', (byte) 's', (byte) 't', (byte) 'u', (byte) 'v',
(byte) 'w', (byte) 'x', (byte) 'y', (byte) 'z'
};
/**
* Used in decoding the "ordered" dialect of Base64.
*/
private static final byte[] _ORDERED_DECODABET = {
-9, -9, -9, -9, -9, -9, -9, -9, -9, // Decimal 0 - 8
-5, -5, // Whitespace: Tab and Linefeed
-9, -9, // Decimal 11 - 12
-5, // Whitespace: Carriage Return
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 14 - 26
-9, -9, -9, -9, -9, // Decimal 27 - 31
-5, // Whitespace: Space
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, // Decimal 33 - 42
-9, // Plus sign at decimal 43
-9, // Decimal 44
0, // Minus sign at decimal 45
-9, // Decimal 46
-9, // Slash at decimal 47
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, // Numbers zero through nine
-9, -9, -9, // Decimal 58 - 60
-1, // Equals sign at decimal 61
-9, -9, -9, // Decimal 62 - 64
11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23,
// Letters 'A' through 'M'
24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36,
// Letters 'N' through 'Z'
-9, -9, -9, -9, // Decimal 91 - 94
37, // Underscore at decimal 95
-9, // Decimal 96
38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
// Letters 'a' through 'm'
51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
// Letters 'n' through 'z'
-9, -9, -9, -9, -9 // Decimal 123 - 127
, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 128 - 139
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 140 - 152
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 153 - 165
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 166 - 178
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 179 - 191
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 192 - 204
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 205 - 217
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 218 - 230
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
// Decimal 231 - 243
-9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9, -9 // Decimal 244 - 255
};
/* ******** D E T E R M I N E W H I C H A L H A B E T ******** */
/**
* Returns one of the _SOMETHING_ALPHABET byte arrays depending on the
* options specified. It's possible,
* though silly, to specify ORDERED <b>and</b> URLSAFE in which case one of
* them will be picked, though there
* is no guarantee as to which one will be picked.
*/
private static byte[] getAlphabet(final int options) {
if ((options & URL_SAFE) == URL_SAFE) {
return _URL_SAFE_ALPHABET;
} else if ((options & ORDERED) == ORDERED) {
return _ORDERED_ALPHABET;
} else {
return _STANDARD_ALPHABET;
}
} // end getAlphabet
/**
* Returns one of the _SOMETHING_DECODABET byte arrays depending on the
* options specified. It's possible,
* though silly, to specify ORDERED and URL_SAFE in which case one of them
* will be picked, though there is no
* guarantee as to which one will be picked.
*/
private static byte[] getDecodabet(final int options) {
if ((options & URL_SAFE) == URL_SAFE) {
return _URL_SAFE_DECODABET;
} else if ((options & ORDERED) == ORDERED) {
return _ORDERED_DECODABET;
} else {
return _STANDARD_DECODABET;
}
} // end getAlphabet
/**
* Defeats instantiation.
*/
private Base64() {
}
/* ******** E N C O D I N G M E T H O D S ******** */
/**
* Encodes up to the first three bytes of array <var>threeBytes</var> and
* returns a four-byte array in Base64
* notation. The actual number of significant bytes in your array is given
* by <var>numSigBytes</var>. The
* array <var>threeBytes</var> needs only be as big as
* <var>numSigBytes</var>. Code can reuse a byte array by
* passing a four-byte array as <var>b4</var>.
*
* @param b4 A reusable byte array to reduce array instantiation
* @param threeBytes the array to convert
* @param numSigBytes the number of significant bytes in your array
*
* @return four byte array in Base64 notation.
*
* @since 1.5.1
*/
private static byte[] encode3to4(final byte[] b4, final byte[] threeBytes,
final int numSigBytes, final int options) {
encode3to4(threeBytes, 0, numSigBytes, b4, 0, options);
return b4;
} // end encode3to4
/**
* <p>
* Encodes up to three bytes of the array <var>source</var> and writes the
* resulting four Base64 bytes to
* <var>destination</var>. The source and destination arrays can be
* manipulated anywhere along their length by
* specifying <var>srcOffset</var> and <var>destOffset</var>. This method
* does not check to make sure your
* arrays are large enough to accomodate <var>srcOffset</var> + 3 for the
* <var>source</var> array or
* <var>destOffset</var> + 4 for the <var>destination</var> array. The
* actual number of significant bytes in
* your array is given by <var>numSigBytes</var>.
* </p>
* <p>
* This is the lowest level of the encoding methods with all possible
* parameters.
* </p>
*
* @param source the array to convert
* @param srcOffset the index where conversion begins
* @param numSigBytes the number of significant bytes in your array
* @param destination the array to hold the conversion
* @param destOffset the index where output will be put
*
* @since 1.3
*/
private static void encode3to4(final byte[] source, final int srcOffset,
final int numSigBytes,
final byte[] destination, final int destOffset,
final int options) {
final byte[] alphabet = getAlphabet(options);
// 1 2 3
// 01234567890123456789012345678901 Bit position
// --------000000001111111122222222 Array position from threeBytes
// --------| || || || | Six bit groups to index alphabet
// >>18 >>12 >> 6 >> 0 Right shift necessary
// 0x3f 0x3f 0x3f Additional AND
// Create buffer with zero-padding if there are only one or two
// significant bytes passed in the array.
// We have to shift left 24 in order to flush out the 1's that appear
// when Java treats a value as negative that is cast from a byte to an int.
final int inBuff = (numSigBytes > 0? source[srcOffset] << 24 >>> 8 : 0) |
(numSigBytes > 1? source[srcOffset + 1] << 24 >>> 16 :
0) |
(numSigBytes > 2? source[srcOffset + 2] << 24 >>> 24 :
0);
switch (numSigBytes) {
case 3:
destination[destOffset] = alphabet[inBuff >>> 18];
destination[destOffset + 1] = alphabet[inBuff >>> 12 & 0x3f];
destination[destOffset + 2] = alphabet[inBuff >>> 6 & 0x3f];
destination[destOffset + 3] = alphabet[inBuff & 0x3f];
return;
case 2:
destination[destOffset] = alphabet[inBuff >>> 18];
destination[destOffset + 1] = alphabet[inBuff >>> 12 & 0x3f];
destination[destOffset + 2] = alphabet[inBuff >>> 6 & 0x3f];
destination[destOffset + 3] = EQUALS_SIGN;
return;
case 1:
destination[destOffset] = alphabet[inBuff >>> 18];
destination[destOffset + 1] = alphabet[inBuff >>> 12 & 0x3f];
destination[destOffset + 2] = EQUALS_SIGN;
destination[destOffset + 3] = EQUALS_SIGN;
return;
default:
} // end switch
} // end encode3to4
/**
* Performs Base64 encoding on the {@code raw} ByteBuffer, writing it
* to the {@code encoded}
* ByteBuffer. This is an experimental feature. Currently it does not pass
* along any options (such as
* {@link #DO_BREAK_LINES} or {@link #GZIP}.
*
* @param raw input buffer
* @param encoded output buffer
*
* @since 2.3
*/
public static void encode(final ByteBuffer raw, final ByteBuffer encoded) {
final byte[] raw3 = { 0, 0, 0 };
final byte[] enc4 = { 0, 0, 0, 0 };
while (raw.hasRemaining()) {
final int rem = Math.min(3, raw.remaining());
raw.get(raw3, 0, rem);
encode3to4(enc4, raw3, rem, NO_OPTIONS);
encoded.put(enc4);
} // end input remaining
}
/**
* Performs Base64 encoding on the {@code raw} ByteBuffer, writing it
* to the {@code encoded}
* CharBuffer. This is an experimental feature. Currently it does not pass
* along any options (such as
* {@link #DO_BREAK_LINES} or {@link #GZIP}.
*
* @param raw input buffer
* @param encoded output buffer
*
* @since 2.3
*/
public static void encode(final ByteBuffer raw, final CharBuffer encoded) {
final byte[] raw3 = { 0, 0, 0 };
final byte[] enc4 = { 0, 0, 0, 0 };
while (raw.hasRemaining()) {
final int rem = Math.min(3, raw.remaining());
raw.get(raw3, 0, rem);
encode3to4(enc4, raw3, rem, NO_OPTIONS);
for (int i = 0; i < 4; i++) {
encoded.put((char) (enc4[i] & 0xFF));
}
} // end input remaining
}
/**
* Serializes an object and returns the Base64-encoded version of that
* serialized object.
*
* <p>
* As of v 2.3, if the object cannot be serialized or there is another
* error, the method will throw an
* java.io.IOException. <b>This is new to v2.3!</b> In earlier versions, it
* just returned a null value, but in
* retrospect that's a pretty poor way to handle it.
* </p>
* <p>
* The object is not GZip-compressed before being encoded.
*
* @param serializableObject The object to encode
*
* @return The Base64-encoded object
*
* @throws IOException if there is an error
* @throws NullPointerException if serializedObject is null
* @since 1.4
*/
public static String encodeObject(final Serializable serializableObject)
throws IOException {
return encodeObject(serializableObject, NO_OPTIONS);
} // end encodeObject
/**
* Serializes an object and returns the Base64-encoded version of that
* serialized object.
*
* <p>
* As of v 2.3, if the object cannot be serialized or there is another
* error, the method will throw an
* java.io.IOException. <b>This is new to v2.3!</b> In earlier versions, it
* just returned a null value, but in
* retrospect that's a pretty poor way to handle it.
* </p>
* <p>
* The object is not GZip-compressed before being encoded.
* <p>
* Example options:
*
* <pre>
* GZIP: gzip-compresses object before encoding it.
* DO_BREAK_LINES: break lines at 76 characters
* </pre>
* <p>
* Example: {@code encodeObject( myObj, Base64.GZIP )} or
* <p>
* Example: {@code encodeObject( myObj, Base64.GZIP | Base64.DO_BREAK_LINES
* )}
*
* @param serializableObject The object to encode
* @param options Specified options
*
* @return The Base64-encoded object
*
* @throws IOException if there is an error
* @see Base64#GZIP
* @see Base64#DO_BREAK_LINES
* @since 2.0
*/
public static String encodeObject(final Serializable serializableObject,
final int options) throws IOException {
if (serializableObject == null) {
throw new IllegalArgumentException("Cannot serialize a null object.");
} // end if: null
// Streams
ByteArrayOutputStream baos = null;
OutputStream b64os = null;
GZIPOutputStream gzos = null;
ObjectOutputStream oos = null;
try {
// ObjectOutputStream -> (GZIP) -> Base64 -> ByteArrayOutputStream
baos = new ByteArrayOutputStream();
b64os = new InnerOutputStream(baos, ENCODE | options);
if ((options & GZIP) != 0) {
// Gzip
gzos = new GZIPOutputStream(b64os);
oos = new ObjectOutputStream(gzos);
} else {
// Not gzipped
oos = new ObjectOutputStream(b64os);
}
oos.writeObject(serializableObject);
} // end try
// end catch
finally {
FileUtils.close(oos);
FileUtils.close(gzos);
FileUtils.close(b64os);
FileUtils.close(baos);
} // end finally
// Return value according to relevant encoding.
try {
return new String(baos.toByteArray(), PREFERRED_ENCODING);
} // end try
catch (final UnsupportedEncodingException uue) {
// Fall back to some Java default
return new String(baos.toByteArray());
} // end catch
} // end encode
/**
* Encodes a byte array into Base64 notation. Does not GZip-compress data.
*
* @param source The data to convert
*
* @return The data in Base64-encoded form
*
* @throws NullPointerException if source array is null
* @since 1.4
*/
public static String encodeBytes(final byte[] source) {
// Since we're not going to have the GZIP encoding turned on,
// we're not going to have an java.io.IOException thrown, so
// we should not force the user to have to catch it.
String encoded = null;
try {
encoded = encodeBytes(source, 0, source.length, NO_OPTIONS);
} catch (final IOException ex) {
assert false : ex.getMessage();
} // end catch
assert encoded != null;
return encoded;
} // end encodeBytes
/**
* Encodes a byte array into Base64 notation.
* <p>
* Example options:
*
* <pre>
* GZIP: gzip-compresses object before encoding it.
* DO_BREAK_LINES: break lines at 76 characters
* <i>Note: Technically, this makes your encoding non-compliant.</i>
* </pre>
* <p>
* Example: {@code encodeBytes( myData, Base64.GZIP )} or
* <p>
* Example: {@code encodeBytes( myData, Base64.GZIP | Base64.DO_BREAK_LINES
* )}
*
*
* <p>
* As of v 2.3, if there is an error with the GZIP stream, the method will
* throw an java.io.IOException.
* <b>This is new to v2.3!</b> In earlier versions, it just returned a null
* value, but in retrospect that's a
* pretty poor way to handle it.
* </p>
*
* @param source The data to convert
* @param options Specified options
*
* @return The Base64-encoded data as a String
*
* @throws IOException if there is an error
* @throws NullPointerException if source array is null
* @see Base64#GZIP
* @see Base64#DO_BREAK_LINES
* @since 2.0
*/
public static String encodeBytes(final byte[] source, final int options)
throws IOException {
return encodeBytes(source, 0, source.length, options);
} // end encodeBytes
/**
* Encodes a byte array into Base64 notation. Does not GZip-compress data.
*
* <p>
* As of v 2.3, if there is an error, the method will throw an
* java.io.IOException. <b>This is new to
* v2.3!</b> In earlier versions, it just returned a null value, but in
* retrospect that's a pretty poor way to
* handle it.
* </p>
*
* @param source The data to convert
* @param off Offset in array where conversion should begin
* @param len Length of data to convert
*
* @return The Base64-encoded data as a String
*
* @throws NullPointerException if source array is null
* @throws IllegalArgumentException if source array, offset, or
* length are invalid
* @since 1.4
*/
public static String encodeBytes(final byte[] source, final int off,
final int len) {
// Since we're not going to have the GZIP encoding turned on,
// we're not going to have an java.io.IOException thrown, so
// we should not force the user to have to catch it.
String encoded = null;
try {
encoded = encodeBytes(source, off, len, NO_OPTIONS);
} catch (final IOException ex) {
assert false : ex.getMessage();
} // end catch
assert encoded != null;
return encoded;
} // end encodeBytes
/**
* Encodes a byte array into Base64 notation.
* <p>
* Example options:
*
* <pre>
* GZIP: gzip-compresses object before encoding it.
* DO_BREAK_LINES: break lines at 76 characters
* <i>Note: Technically, this makes your encoding non-compliant.</i>
* </pre>
* <p>
* Example: {@code encodeBytes( myData, Base64.GZIP )} or
* <p>
* Example: {@code encodeBytes( myData, Base64.GZIP | Base64.DO_BREAK_LINES
* )}
*
*
* <p>
* As of v 2.3, if there is an error with the GZIP stream, the method will
* throw an java.io.IOException.
* <b>This is new to v2.3!</b> In earlier versions, it just returned a null
* value, but in retrospect that's a
* pretty poor way to handle it.
* </p>
*
* @param source The data to convert
* @param off Offset in array where conversion should begin
* @param len Length of data to convert
* @param options Specified options
*
* @return The Base64-encoded data as a String
*
* @throws IOException if there is an error
* @throws NullPointerException if source array is null
* @throws IllegalArgumentException if source array, offset, or
* length are invalid
* @see Base64#GZIP
* @see Base64#DO_BREAK_LINES
* @since 2.0
*/
public static String encodeBytes(final byte[] source, final int off,
final int len, final int options)
throws IOException {
final byte[] encoded = encodeBytesToBytes(source, off, len, options);
// Return value according to relevant encoding.
try {
return new String(encoded, PREFERRED_ENCODING);
} // end try
catch (final UnsupportedEncodingException uue) {
return new String(encoded);
} // end catch
} // end encodeBytes
/**
* Similar to {@link #encodeBytes(byte[])} but returns a byte array instead
* of instantiating a String. This is
* more efficient if you're working with I/O streams and have large data
* sets to encode.
*
* @param source The data to convert
*
* @return The Base64-encoded data as a byte[] (of ASCII characters)
*
* @throws NullPointerException if source array is null
* @since 2.3.1
*/
public static byte[] encodeBytesToBytes(final byte[] source) {
byte[] encoded = null;
try {
encoded = encodeBytesToBytes(source, 0, source.length, NO_OPTIONS);
} catch (final IOException ex) {
assert false :
"IOExceptions only come from GZipping, which is turned off: " +
ex.getMessage();
}
return encoded;
}
/**
* Similar to {@link #encodeBytes(byte[], int, int, int)} but returns a byte
* array instead of instantiating a
* String. This is more efficient if you're working with I/O streams and
* have large data sets to encode.
*
* @param source The data to convert
* @param off Offset in array where conversion should begin
* @param len Length of data to convert
* @param options Specified options
*
* @return The Base64-encoded data as a String
*
* @throws IOException if there is an error
* @throws NullPointerException if source array is null
* @throws IllegalArgumentException if source array, offset, or
* length are invalid
* @see Base64#GZIP
* @see Base64#DO_BREAK_LINES
* @since 2.3.1
*/
public static byte[] encodeBytesToBytes(final byte[] source, final int off,
final int len, final int options)
throws IOException {
if (source == null) {
throw new IllegalArgumentException("Cannot serialize a null array.");
} // end if: null
if (off < 0) {
throw new IllegalArgumentException("Cannot have negative offset: " + off);
} // end if: off < 0
if (len < 0) {
throw new IllegalArgumentException("Cannot have length offset: " + len);
} // end if: len < 0
if (off + len > source.length) {
throw new IllegalArgumentException(String.format(
"Cannot have offset of %d and length of %d with array of length %d",
off, len, source.length));
} // end if: off < 0
// Compress?
if ((options & GZIP) != 0) {
ByteArrayOutputStream baos = null;
GZIPOutputStream gzos = null;
InnerOutputStream b64os = null;
try {
// GZip -> Base64 -> ByteArray
baos = new ByteArrayOutputStream();
b64os = new InnerOutputStream(baos, ENCODE | options);
gzos = new GZIPOutputStream(b64os);
gzos.write(source, off, len);
} // end try
// end catch
finally {
FileUtils.close(gzos);
FileUtils.close(b64os);
FileUtils.close(baos);
} // end finally
return baos.toByteArray();
} // end if: compress
// Else, don't compress. Better not to use streams at all then.
else {
final boolean breakLines = (options & DO_BREAK_LINES) != 0;
// New lines
// Try to determine more precisely how big the array needs to be.
// If we get it right, we don't have to do an array copy, and
// we save a bunch of memory.
int encLen = (len / 3) * 4 +
(len % 3 > 0? 4 : 0); // Bytes needed for actual encoding
if (breakLines) {
encLen += encLen / MAX_LINE_LENGTH; // Plus extra newline characters
}
final byte[] outBuff = new byte[encLen];
int d = 0;
int e = 0;
final int len2 = len - 2;
int lineLength = 0;
for (; d < len2; d += 3, e += 4) {
encode3to4(source, d + off, 3, outBuff, e, options);
lineLength += 4;
if (breakLines && lineLength >= MAX_LINE_LENGTH) {
outBuff[e + 4] = NEW_LINE;
e++;
lineLength = 0;
} // end if: end of line
} // end for: each piece of array
if (d < len) {
encode3to4(source, d + off, len - d, outBuff, e, options);
e += 4;
} // end if: some padding needed
// Only resize array if we didn't guess it right.
if (e <= outBuff.length - 1) {
// If breaking lines and the last byte falls right at
// the line length (76 bytes per line), there will be
// one extra byte, and the array will need to be resized.
// Not too bad of an estimate on array size, I'd say.
final byte[] finalOut = new byte[e];
System.arraycopy(outBuff, 0, finalOut, 0, e);
return finalOut;
} else {
return outBuff;
}
} // end else: don't compress
} // end encodeBytesToBytes
/* ******** D E C O D I N G M E T H O D S ******** */
/**
* Decodes four bytes from array <var>source</var> and writes the resulting
* bytes (up to three of them) to
* <var>destination</var>. The source and destination arrays can be
* manipulated anywhere along their length by
* specifying <var>srcOffset</var> and <var>destOffset</var>. This method
* does not check to make sure your
* arrays are large enough to accomodate <var>srcOffset</var> + 4 for the
* <var>source</var> array or
* <var>destOffset</var> + 3 for the <var>destination</var> array. This
* method returns the actual number of
* bytes that were converted from the Base64 encoding.
* <p>
* This is the lowest level of the decoding methods with all possible
* parameters.
* </p>
*
* @param source the array to convert
* @param srcOffset the index where conversion begins
* @param destination the array to hold the conversion
* @param destOffset the index where output will be put
* @param options alphabet type is pulled from this (standard,
* url-safe, ordered)
*
* @return the number of decoded bytes converted
*
* @throws NullPointerException if source or destination arrays are
* null
* @throws IllegalArgumentException if srcOffset or destOffset are
* invalid or there is not enough room in the
* array.
* @since 1.3
*/
private static int decode4to3(final byte[] source, final int srcOffset,
final byte[] destination, final int destOffset,
final int options) {
// Lots of error checking and exception throwing
if (source == null) {
throw new IllegalArgumentException("Source array was null.");
} // end if
if (destination == null) {
throw new IllegalArgumentException("Destination array was null.");
} // end if
if (srcOffset < 0 || srcOffset + 3 >= source.length) {
throw new IllegalArgumentException(String.format(
"Source array with length %d cannot have offset of %d and still process four bytes.",
source.length, srcOffset));
} // end if
if (destOffset < 0 || destOffset + 2 >= destination.length) {
throw new IllegalArgumentException(String.format(
"Destination array with length %d cannot have offset of %d and still store three bytes.",
destination.length, destOffset));
} // end if
final byte[] decodabet = getDecodabet(options);
// Example: Dk==
if (source[srcOffset + 2] == EQUALS_SIGN) {
final int outBuff = (decodabet[source[srcOffset]] & 0xFF) << 18 |
(decodabet[source[srcOffset + 1]] & 0xFF) << 12;
destination[destOffset] = (byte) (outBuff >>> 16);
return 1;
}
// Example: DkL=
else if (source[srcOffset + 3] == EQUALS_SIGN) {
final int outBuff = (decodabet[source[srcOffset]] & 0xFF) << 18 |
(decodabet[source[srcOffset + 1]] & 0xFF) << 12 |
(decodabet[source[srcOffset + 2]] & 0xFF) << 6;
destination[destOffset] = (byte) (outBuff >>> 16);
destination[destOffset + 1] = (byte) (outBuff >>> 8);
return 2;
}
// Example: DkLE
else {
final int outBuff = (decodabet[source[srcOffset]] & 0xFF) << 18 |
(decodabet[source[srcOffset + 1]] & 0xFF) << 12 |
(decodabet[source[srcOffset + 2]] & 0xFF) << 6 |
decodabet[source[srcOffset + 3]] & 0xFF;
destination[destOffset] = (byte) (outBuff >> 16);
destination[destOffset + 1] = (byte) (outBuff >> 8);
destination[destOffset + 2] = (byte) outBuff;
return 3;
}
} // end decodeToBytes
/**
* Low-level access to decoding ASCII characters in the form of a byte
* array. <strong>Ignores GUNZIP option,
* if it's set.</strong> This is not generally a recommended method,
* although it is used internally as part of
* the decoding process. Special case: if len = 0, an empty array is
* returned. Still, if you need more speed
* and reduced memory footprint (and aren't gzipping), consider this
* method.
*
* @param source The Base64 encoded data
*
* @return decoded data
*
* @since 2.3.1
*/
public static byte[] decode(final byte[] source) throws IOException {
final byte[] decoded;
decoded = decode(source, 0, source.length, NO_OPTIONS);
return decoded;
}
/**
* Low-level access to decoding ASCII characters in the form of a byte
* array. <strong>Ignores GUNZIP option,
* if it's set.</strong> This is not generally a recommended method,
* although it is used internally as part of
* the decoding process. Special case: if len = 0, an empty array is
* returned. Still, if you need more speed
* and reduced memory footprint (and aren't gzipping), consider this
* method.
*
* @param source The Base64 encoded data
* @param off The offset of where to begin decoding
* @param len The length of characters to decode
* @param options Can specify options such as alphabet type to use
*
* @return decoded data
*
* @throws IOException If bogus characters exist in source
* data
* @since 1.3
*/
public static byte[] decode(final byte[] source, final int off, final int len,
final int options) throws IOException {
// Lots of error checking and exception throwing
if (source == null) {
throw new IllegalArgumentException("Cannot decode null source array.");
} // end if
if (off < 0 || off + len > source.length) {
throw new IllegalArgumentException(String.format(
"Source array with length %d cannot have offset of %d and process %d bytes.",
source.length, off, len));
} // end if
if (len == 0) {
return SingletonUtils.getSingletonByteArray();
} else if (len < 4) {
throw new IllegalArgumentException(
"Base64-encoded string must have at least four characters, but length specified was " +
len);
} // end if
final byte[] decodabet = getDecodabet(options);
final int len34 = len * 3 / 4; // Estimate on array size
final byte[] outBuff = new byte[len34]; // Upper limit on size of output
int outBuffPosn = 0; // Keep track of where we're writing
final byte[] b4 =
{ 0, 0, 0, 0 }; // Four byte buffer from source, eliminating white space
int b4Posn = 0; // Keep track of four byte input buffer
int i; // Source array counter
byte sbiDecode; // Special value from decodabet
for (i = off; i < off + len; i++) { // Loop through source
sbiDecode = decodabet[source[i] & 0xFF];
// White space, Equals sign, or legit Base64 character
// Note the values such as -5 and -9 in the
// DECODABETs at the top of the file.
if (sbiDecode >= WHITE_SPACE_ENC) {
if (sbiDecode >= EQUALS_SIGN_ENC) {
b4[b4Posn++] = source[i]; // Save non-whitespace
if (b4Posn > 3) { // Time to decode?
outBuffPosn += decode4to3(b4, 0, outBuff, outBuffPosn, options);
b4Posn = 0;
// If that was the equals sign, break out of 'for' loop
if (source[i] == EQUALS_SIGN) {
break;
} // end if: equals sign
} // end if: quartet built
} // end if: equals sign or better
} // end if: white space, equals sign or better
else {
// There's a bad input character in the Base64 stream.
throw new IOException(String.format(
"Bad Base64 input character decimal %d in array position %d",
source[i] & 0xFF, i));
} // end else:
} // each input character
final byte[] out = new byte[outBuffPosn];
System.arraycopy(outBuff, 0, out, 0, outBuffPosn);
return out;
} // end decode
/**
* Decodes data from Base64 notation, automatically detecting
* gzip-compressed data and decompressing it.
*
* @param s the string to decode
*
* @return the decoded data
*
* @throws IOException If there is a problem
* @since 1.4
*/
public static byte[] decode(final String s) throws IOException {
return decode(s, NO_OPTIONS);
}
/**
* Decodes data from Base64 notation, automatically detecting
* gzip-compressed data and decompressing it.
*
* @param s the string to decode
* @param options encode options such as URL_SAFE
*
* @return the decoded data
*
* @throws IOException if there is an error
* @throws NullPointerException if <tt>s</tt> is null
* @since 1.4
*/
public static byte[] decode(final String s, final int options)
throws IOException {
if (s == null) {
throw new IllegalArgumentException("Input string was null.");
} // end if
byte[] bytes;
try {
bytes = s.getBytes(PREFERRED_ENCODING);
} // end try
catch (final UnsupportedEncodingException uee) {
bytes = s.getBytes();
} // end catch
// </change>
// Decode
bytes = decode(bytes, 0, bytes.length, options);
// Check to see if it's gzip-compressed
// GZIP Magic Two-Byte Number: 0x8b1f (35615)
final boolean dontGunzip = (options & DONT_GUNZIP) != 0;
if (bytes != null && bytes.length >= 4 && !dontGunzip) {
final int head = bytes[0] & 0xff | bytes[1] << 8 & 0xff00;
if (GZIPInputStream.GZIP_MAGIC == head) {
ByteArrayInputStream bais = null;
GZIPInputStream gzis = null;
ByteArrayOutputStream baos = null;
final byte[] buffer = new byte[2048];
int length;
try {
baos = new ByteArrayOutputStream();
bais = new ByteArrayInputStream(bytes);
gzis = new GZIPInputStream(bais);
while ((length = gzis.read(buffer)) >= 0) {
baos.write(buffer, 0, length);
} // end while: reading input
// No error? Get new bytes.
bytes = baos.toByteArray();
} // end try
catch (final IOException e) {
SysErrLogger.FAKE_LOGGER.ignoreLog(e);
// Just return originally-decoded bytes
} // end catch
finally {
FileUtils.close(baos);
FileUtils.close(gzis);
FileUtils.close(bais);
} // end finally
} // end if: gzipped
} // end if: bytes.length >= 2
return bytes;
} // end decode
/**
* Attempts to decode Base64 data and deserialize a Java Object within.
* Returns <tt>null</tt> if there was an
* error.
*
* @param encodedObject The Base64 data to decode
*
* @return The decoded and deserialized object
*
* @throws NullPointerException if encodedObject is null
* @throws IOException if there is a general error
* @throws ClassNotFoundException if the decoded object is of a
* class that cannot be found by the JVM
* @since 1.5
*/
public static Object decodeToObject(final String encodedObject)
throws IOException, ClassNotFoundException {
return decodeToObject(encodedObject, NO_OPTIONS, null);
}
/**
* Attempts to decode Base64 data and deserialize a Java Object within.
* Returns <tt>null</tt> if there was an
* error. If <tt>loader</tt> is not null, it will be the class loader used
* when deserializing.
*
* @param encodedObject The Base64 data to decode
* @param options Various parameters related to decoding
* @param loader Optional class loader to use in deserializing
* classes.
*
* @return The decoded and deserialized object
*
* @throws NullPointerException if encodedObject is null
* @throws IOException if there is a general error
* @throws ClassNotFoundException if the decoded object is of a
* class that cannot be found by the JVM
* @since 2.3.4
*/
public static Object decodeToObject(final String encodedObject,
final int options,
final ClassLoader loader)
throws IOException, ClassNotFoundException {
// Decode and gunzip if necessary
final byte[] objBytes = decode(encodedObject, options);
ByteArrayInputStream bais = null;
ObjectInputStream ois = null;
Object obj;
try {
bais = new ByteArrayInputStream(objBytes);
// If no custom class loader is provided, use Java's builtin OIS.
if (loader == null) {
ois = new ObjectInputStream(bais);
} // end if: no loader provided
// Else make a customized object input stream that uses
// the provided class loader.
else {
ois = new ObjectInputStream(bais) {
@Override
public final Class<?> resolveClass(
final ObjectStreamClass streamClass)
throws IOException, ClassNotFoundException {
final Class<?> c =
Class.forName(streamClass.getName(), false, loader);//NOSONAR
if (c == null) {
return super.resolveClass(streamClass);
} else {
return c; // Class loader knows of this class.
} // end else: not null
} // end resolveClass
}; // end ois
} // end else: no custom class loader
obj = ois.readObject();
} // end try
// end catch
// end catch
finally {
FileUtils.close(bais);
FileUtils.close(ois);
} // end finally
return obj;
} // end decodeObject
/**
* Convenience method for encoding data to a file.
*
* <p>
* As of v 2.3, if there is a error, the method will throw an
* java.io.IOException. <b>This is new to v2.3!</b>
* In earlier versions, it just returned false, but in retrospect that's a
* pretty poor way to handle it.
* </p>
*
* @param dataToEncode byte array of data to encode in base64 form
* @param filename Filename for saving encoded data
*
* @throws IOException if there is an error
* @throws NullPointerException if dataToEncode is null
* @since 2.1
*/
public static void encodeToFile(final byte[] dataToEncode,
final String filename) throws IOException {
if (dataToEncode == null) {
throw new IllegalArgumentException("Data to encode was null.");
} // end iff
InnerOutputStream bos = null;
try {
bos = new InnerOutputStream(new FileOutputStream(filename), ENCODE);
bos.write(dataToEncode);
} // end try
// end catch: java.io.IOException
finally {
FileUtils.close(bos);
} // end finally
} // end encodeToFile
/**
* Convenience method for decoding data to a file.
*
* <p>
* As of v 2.3, if there is a error, the method will throw an
* java.io.IOException. <b>This is new to v2.3!</b>
* In earlier versions, it just returned false, but in retrospect that's a
* pretty poor way to handle it.
* </p>
*
* @param dataToDecode Base64-encoded data as a string
* @param filename Filename for saving decoded data
*
* @throws IOException if there is an error
* @since 2.1
*/
public static void decodeToFile(final String dataToDecode,
final String filename) throws IOException {
InnerOutputStream bos = null;
try {
bos = new InnerOutputStream(new FileOutputStream(filename), DECODE);
bos.write(dataToDecode.getBytes(PREFERRED_ENCODING));
} // end try
// end catch: java.io.IOException
finally {
FileUtils.close(bos);
} // end finally
} // end decodeToFile
/**
* Convenience method for reading a base64-encoded file and decoding it.
*
* <p>
* As of v 2.3, if there is a error, the method will throw an
* java.io.IOException. <b>This is new to v2.3!</b>
* In earlier versions, it just returned false, but in retrospect that's a
* pretty poor way to handle it.
* </p>
*
* @param filename Filename for reading encoded data
*
* @return decoded byte array
*
* @throws IOException if there is an error
* @since 2.1
*/
public static byte[] decodeFromFile(final String filename)
throws IOException {
byte[] decodedData;
InnerInputStream bis = null;
try {
// Set up some useful variables
final File file = new File(filename);
final byte[] buffer;
int length = 0;
int numBytes;
// Check for size of file
if (file.length() > Integer.MAX_VALUE) {
throw new IOException(
"File is too big for this convenience method (" + file.length() +
" bytes).");
} // end if: file too big for int index
buffer = new byte[(int) file.length()];
// Open a stream
bis = new InnerInputStream(
new BufferedInputStream(new FileInputStream(file)), DECODE);
// Read until done
while ((numBytes = bis.read(buffer, length, 4096)) >= 0) {
length += numBytes;
} // end while
// Save in a variable to return
decodedData = new byte[length];
System.arraycopy(buffer, 0, decodedData, 0, length);
} // end try
// end catch: java.io.IOException
finally {
FileUtils.close(bis);
} // end finally
return decodedData;
} // end decodeFromFile
/**
* Convenience method for reading a binary file and base64-encoding it.
*
* <p>
* As of v 2.3, if there is a error, the method will throw an
* java.io.IOException. <b>This is new to v2.3!</b>
* In earlier versions, it just returned false, but in retrospect that's a
* pretty poor way to handle it.
* </p>
*
* @param filename Filename for reading binary data
*
* @return base64-encoded string
*
* @throws IOException if there is an error
* @since 2.1
*/
public static String encodeFromFile(final String filename)
throws IOException {
String encodedData;
InnerInputStream bis = null;
try {
// Set up some useful variables
final File file = new File(filename);
// Check for size of file
if (file.length() > Integer.MAX_VALUE) {
throw new IOException(
"File is too big for this convenience method (" + file.length() +
" bytes).");
} // end if: file too big for int index
final byte[] buffer = new byte[Math.max((int) (file.length() * 1.4 + 1),
40)]; // Need max() for math on small
// files (v2.2.1); Need +1 for a
// few corner cases (v2.3.5)
int length = 0;
int numBytes;
// Open a stream
bis = new InnerInputStream(
new BufferedInputStream(new FileInputStream(file)), ENCODE);
// Read until done
while ((numBytes = bis.read(buffer, length, 4096)) >= 0) {
length += numBytes;
} // end while
// Save in a variable to return
encodedData = new String(buffer, 0, length, PREFERRED_ENCODING);
} // end try
// end catch: java.io.IOException
finally {
FileUtils.close(bis);
} // end finally
return encodedData;
} // end encodeFromFile
/**
* Reads <tt>infile</tt> and encodes it to <tt>outfile</tt>.
*
* @param infile Input file
* @param outfile Output file
*
* @throws IOException if there is an error
* @since 2.2
*/
public static void encodeFileToFile(final String infile, final String outfile)
throws IOException {
final String encoded = encodeFromFile(infile);
OutputStream out = null;
try {
out = new BufferedOutputStream(new FileOutputStream(outfile));
out.write(encoded.getBytes(PREFERRED_ENCODING)); // Strict, 7-bit output.
} // end try
// end catch
finally {
FileUtils.close(out);
} // end finally
} // end encodeFileToFile
/**
* Reads <tt>infile</tt> and decodes it to <tt>outfile</tt>.
*
* @param infile Input file
* @param outfile Output file
*
* @throws IOException if there is an error
* @since 2.2
*/
public static void decodeFileToFile(final String infile, final String outfile)
throws IOException {
final byte[] decoded = decodeFromFile(infile);
OutputStream out = null;
try {
out = new BufferedOutputStream(new FileOutputStream(outfile));
out.write(decoded);
} // end try
// end catch
finally {
FileUtils.close(out);
} // end finally
} // end decodeFileToFile
/* ******** I N N E R C L A S S I N P U T S T R E A M ******** */
/**
* A {@link InnerInputStream} will read data from another
* <tt>java.io.InputStream</tt>, given in the
* constructor, and encode/decode to/from Base64 notation on the fly.
*
* @see Base64
* @since 1.3
*/
private static class InnerInputStream extends FilterInputStream {
private final boolean encode; // Encoding or decoding
private int position; // Current position in the buffer
private final byte[] buffer; // Small buffer holding converted data
private final int bufferLength; // Length of buffer (3 or 4)
private int numSigBytes; // Number of meaningful bytes in the buffer
private int lineLength;
private final boolean breakLines;
// Break lines at less than 80 characters
private final int options; // Record options used to create the stream.
private final byte[] decodabet;
// Local copies to avoid extra method calls
/**
* Constructs a {@link InnerInputStream} in DECODE mode.
*
* @param in the <tt>java.io.InputStream</tt> from which to read
* data.
*
* @since 1.3
*/
public InnerInputStream(final InputStream in) {
this(in, DECODE);
} // end constructor
/**
* Constructs a {@link InnerInputStream} in either ENCODE or DECODE
* mode.
* <p>
* Valid options:
*
* <pre>
* ENCODE or DECODE: Encode or Decode as data is read.
* DO_BREAK_LINES: break lines at 76 characters
* (only meaningful when encoding)</i>
* </pre>
* <p>
* Example: {@code new Base64.InputStream( in, Base64.DECODE )}
*
* @param in the <tt>java.io.InputStream</tt> from which to read
* data.
* @param options Specified options
*
* @see Base64#ENCODE
* @see Base64#DECODE
* @see Base64#DO_BREAK_LINES
* @since 2.0
*/
private InnerInputStream(final InputStream in, final int options) {
super(in);
this.options = options; // Record for later
breakLines = (options & DO_BREAK_LINES) > 0;
encode = (options & ENCODE) > 0;
bufferLength = encode? 4 : 3;
final byte[] bsize3 = { 0, 0, 0 };
final byte[] bsize4 = { 0, 0, 0, 0 };
buffer = encode? bsize4 : bsize3;
position = -1;
lineLength = 0;
decodabet = getDecodabet(options);
} // end constructor
/**
* Reads enough of the input stream to convert to/from Base64 and
* returns the next byte.
*
* @return next byte
*
* @since 1.3
*/
@Override
public final int read() throws IOException {
// Do we need to get data?
if (position < 0) {
if (encode) {
final byte[] b3 = { 0, 0, 0 };
int numBinaryBytes = 0;
for (int i = 0; i < 3; i++) {
final int b = in.read();
// If end of stream, b is -1.
if (b >= 0) {
b3[i] = (byte) b;
numBinaryBytes++;
} else {
break; // out of for loop
} // end else: end of stream
} // end for: each needed input byte
if (numBinaryBytes > 0) {
encode3to4(b3, 0, numBinaryBytes, buffer, 0, options);
position = 0;
numSigBytes = 4;
} // end if: got data
else {
return -1; // Must be end of stream
} // end else
} // end if: encoding
// Else decoding
else {
final byte[] b4 = { 0, 0, 0, 0 };
int i;
for (i = 0; i < 4; i++) {
// Read four "meaningful" bytes:
int b;
do {
b = in.read();
} while (b >= 0 && decodabet[b & 0x7f] <= WHITE_SPACE_ENC);
if (b < 0) {
break; // Reads a -1 if end of stream
} // end if: end of stream
b4[i] = (byte) b;
} // end for: each needed input byte
if (i == 4) {
numSigBytes = decode4to3(b4, 0, buffer, 0, options);
position = 0;
} // end if: got four characters
else if (i == 0) {
return -1;
} // end else if: also padded correctly
else {
// Must have broken out from above.
throw new IOException("Improperly padded Base64 input.");
} // end
} // end else: decode
} // end else: get data
// Got data?
if (position >= 0) {
// End of relevant data?
if ( /* !encode && */position >= numSigBytes) {
return -1;
} // end if: got data
if (encode && breakLines && lineLength >= MAX_LINE_LENGTH) {
lineLength = 0;
return '\n';
} // end if
else {
lineLength++; // This isn't important when decoding
// but throwing an extra "if" seems
// just as wasteful.
final int b = buffer[position++];
if (position >= bufferLength) {
position = -1;
} // end if: end
return b & 0xFF; // This is how you "cast" a byte that's
// intended to be unsigned.
} // end else
} // end if: position >= 0
// Else error
else {
throw new IOException("Error in Base64 code reading stream.");
} // end else
} // end read
/**
* Calls {@link #read()} repeatedly until the end of stream is reached
* or <var>len</var> bytes are read.
* Returns number of bytes read into array or -1 if end of stream is
* encountered.
*
* @param dest array to hold values
* @param off offset for array
* @param len max number of bytes to read into array
*
* @return bytes read into array or -1 if end of stream is encountered.
*
* @since 1.3
*/
@Override
public final int read(final byte[] dest, final int off, final int len)
throws IOException {
int i;
int b;
for (i = 0; i < len; i++) {
b = read();
if (b >= 0) {
dest[off + i] = (byte) b;
} else if (i == 0) {
return -1;
} else {
break; // Out of 'for' loop
} // Out of 'for' loop
} // end for: each byte read
return i;
} // end read
} // end inner class InputStream
/* ******** I N N E R C L A S S O U T P U T S T R E A M ******** */
/**
* A {@link InnerOutputStream} will write data to another
* <tt>java.io.OutputStream</tt>, given in the
* constructor, and encode/decode to/from Base64 notation on the fly.
*
* @see Base64
* @since 1.3
*/
private static class InnerOutputStream extends FilterOutputStream {
private final boolean encode;
private int position;
private byte[] buffer;
private final int bufferLength;
private int lineLength;
private final boolean breakLines;
private final byte[] b4 = { 0, 0, 0, 0 }; // Scratch used in a few places
private boolean suspendEncoding;
private final int options; // Record for later
private final byte[] decodabet;
// Local copies to avoid extra method calls
/**
* Constructs a {@link InnerOutputStream} in ENCODE mode.
*
* @param out the <tt>java.io.OutputStream</tt> to which data
* will be written.
*
* @since 1.3
*/
public InnerOutputStream(final OutputStream out) {
this(out, ENCODE);
} // end constructor
/**
* Constructs a {@link InnerOutputStream} in either ENCODE or DECODE
* mode.
* <p>
* Valid options:
*
* <pre>
* ENCODE or DECODE: Encode or Decode as data is read.
* DO_BREAK_LINES: don't break lines at 76 characters
* (only meaningful when encoding)</i>
* </pre>
* <p>
* Example: {@code new Base64.OutputStream( out, Base64.ENCODE )}
*
* @param out the <tt>java.io.OutputStream</tt> to which data
* will be written.
* @param options Specified options.
*
* @see Base64#ENCODE
* @see Base64#DECODE
* @see Base64#DO_BREAK_LINES
* @since 1.3
*/
private InnerOutputStream(final OutputStream out, final int options) {
super(out);
breakLines = (options & DO_BREAK_LINES) != 0;
encode = (options & ENCODE) != 0;
bufferLength = encode? 3 : 4;
final byte[] bsize3 = { 0, 0, 0 };
final byte[] bsize4 = { 0, 0, 0, 0 };
buffer = encode? bsize3 : bsize4;
position = 0;
lineLength = 0;
suspendEncoding = false;
this.options = options;
decodabet = getDecodabet(options);
} // end constructor
/**
* Writes the byte to the output stream after converting to/from Base64
* notation. When encoding, bytes are
* buffered three at a time before the output stream actually gets a
* write() call. When decoding, bytes are
* buffered four at a time.
*
* @param theByte the byte to write
*
* @since 1.3
*/
@Override
public final void write(final int theByte) throws IOException {
// Encoding suspended?
if (suspendEncoding) {
out.write(theByte);
return;
} // end if: supsended
// Encode?
if (encode) {
buffer[position++] = (byte) theByte;
if (position >= bufferLength) { // Enough to encode.
out.write(encode3to4(b4, buffer, bufferLength, options));
lineLength += 4;
if (breakLines && lineLength >= MAX_LINE_LENGTH) {
out.write(NEW_LINE);
lineLength = 0;
} // end if: end of line
position = 0;
} // end if: enough to output
} // end if: encoding
// Else, Decoding
else {
// Meaningful Base64 character?
if (decodabet[theByte & 0x7f] > WHITE_SPACE_ENC) {
buffer[position++] = (byte) theByte;
if (position >= bufferLength) { // Enough to output.
final int len = decode4to3(buffer, 0, b4, 0, options);
out.write(b4, 0, len);
position = 0;
} // end if: enough to output
} // end if: meaningful base64 character
else if (decodabet[theByte & 0x7f] != WHITE_SPACE_ENC) {
throw new IOException("Invalid character in Base64 data.");
} // end else: not white space either
} // end else: decoding
} // end write
/**
* Calls {@link #write(int)} repeatedly until <var>len</var> bytes are
* written.
*
* @param theBytes array from which to read bytes
* @param off offset for array
* @param len max number of bytes to read into array
*
* @since 1.3
*/
@Override
public final void write(final byte[] theBytes, final int off, final int len)
throws IOException {
// Encoding suspended?
if (suspendEncoding) {
out.write(theBytes, off, len);
return;
} // end if: supsended
for (int i = 0; i < len; i++) {
write(theBytes[off + i]);
} // end for: each byte written
} // end write
/**
* Method added by PHIL. [Thanks, PHIL. -Rob] This pads the buffer
* without closing the stream.
*
* @throws IOException if there's an error.
*/
public final void flushBase64() throws IOException {
if (position > 0) {
if (encode) {
out.write(encode3to4(b4, buffer, position, options));
position = 0;
} // end if: encoding
else {
throw new IOException("Base64 input not properly padded.");
} // end else: decoding
} // end if: buffer partially full
} // end flush
/**
* Flushes and closes (I think, in the superclass) the stream.
*
* @since 1.3
*/
@Override
public final void close() throws IOException {
// 1. Ensure that pending characters are written
flushBase64();
// 2. Actually close the stream
// Base class both flushes and closes.
super.close();
buffer = null;
out = null;
} // end close
/**
* Suspends encoding of the stream. May be helpful if you need to embed
* a piece of base64-encoded data in a
* stream.
*
* @throws IOException if there's an error flushing
* @since 1.5.1
*/
public final void suspendEncoding() throws IOException {
flushBase64();
suspendEncoding = true;
} // end suspendEncoding
/**
* Resumes encoding of the stream. May be helpful if you need to embed a
* piece of base64-encoded data in a
* stream.
*
* @since 1.5.1
*/
public final void resumeEncoding() {
suspendEncoding = false;
} // end resumeEncoding
} // end inner class OutputStream
} // end class Base64