📄 base64.java
字号:
package org.jivesoftware.util;
/**
* <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>
* Change Log:
* </p>
* <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 2.2.1
*/
public class Base64
{
/* ******** P U B L I C F I E L D S ******** */
/** No options specified. Value is zero. */
public final static int NO_OPTIONS = 0;
/** Specify encoding. */
public final static int ENCODE = 1;
/** Specify decoding. */
public final static int DECODE = 0;
/** Specify that data should be gzip-compressed. */
public final static int GZIP = 2;
/** Don't break lines when encoding (violates strict Base64 specification) */
public final static int DONT_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 final static 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 final static int ORDERED = 32;
/* ******** P R I V A T E F I E L D S ******** */
/** Maximum line length (76) of Base64 output. */
private final static int MAX_LINE_LENGTH = 76;
/** The equals sign (=) as a byte. */
private final static byte EQUALS_SIGN = (byte)'=';
/** The new line character (\n) as a byte. */
private final static byte NEW_LINE = (byte)'\n';
/** Preferred encoding. */
private final static String PREFERRED_ENCODING = "UTF-8";
// I think I end up not using the BAD_ENCODING indicator.
//private final static byte BAD_ENCODING = -9; // Indicates error in encoding
private final static byte WHITE_SPACE_ENC = -5; // Indicates white space in encoding
private final static 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. */
//private final static byte[] ALPHABET;
/* Host platform me be something funny like EBCDIC, so we hardcode these values. */
private final static 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 final static 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 // Decimal 123 - 126
/*,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9, // Decimal 127 - 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 final static 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 final static 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 // Decimal 123 - 126
/*,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9, // Decimal 127 - 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 it is described here:
* <a href="http://www.faqs.org/qa/rfcc-1940.html">http://www.faqs.org/qa/rfcc-1940.html</a>.
*/
private final static 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 final static 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 // Decimal 123 - 126
/*,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9,-9, // Decimal 127 - 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 and URLSAFE
* in which case one of them will be picked, though there is
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -