forked from ESAPI/esapi-java-legacy
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathBase64.java
More file actions
1815 lines (1555 loc) · 71.1 KB
/
Copy pathBase64.java
File metadata and controls
1815 lines (1555 loc) · 71.1 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
package org.owasp.esapi.codecs;
import org.owasp.esapi.ESAPI;
import org.owasp.esapi.Logger;
/**
* <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>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
* (though that breaks strict Base64 compatibility), and encoding using the URL-safe
* and Ordered dialects.</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.DONT_BREAK_LINES );</code>
*
* <p>to compress the data before encoding it and then making the output have no newline characters.</p>
*
*
* <p>
* Change Log:
* </p>
* <ul>
* <li>v2.2.2 - Fixed encodeFileToFile and decodeFileToFile to use the
* Base64.InputStream class to encode and decode on the fly which uses
* less memory than encoding/decoding an entire file into memory before writing.</li>
* <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 2.2.2
*/
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
private static final Logger logger = ESAPI.getLogger("Base64");
/* ******** 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
* no guarantee as to which one will be picked.
*/
private final static byte[] getAlphabet( 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 final static byte[] getDecodabet( 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(){}
/**
* Encodes or decodes two files from the command line;
* <strong>feel free to delete this method (in fact you probably should)
* if you're embedding this code into a larger program.</strong>
*/
public final static void main( String[] args )
{
if( args.length < 3 ){
usage("Not enough arguments.");
} // end if: args.length < 3
else {
String flag = args[0];
String infile = args[1];
String outfile = args[2];
if( flag.equals( "-e" ) ){
Base64.encodeFileToFile( infile, outfile );
} // end if: encode
else if( flag.equals( "-d" ) ) {
Base64.decodeFileToFile( infile, outfile );
} // end else if: decode
else {
usage( "Unknown flag: " + flag );
} // end else
} // end else
} // end main
/**
* Prints command line usage.
*
* @param msg A message to include with usage info.
*/
private final static void usage( String msg )
{
System.err.println( msg );
System.err.println( "Usage: java Base64 -e|-d inputfile outputfile" );
} // end usage
/* ******** 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( byte[] b4, byte[] threeBytes, int numSigBytes, 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
* @return the <var>destination</var> array
* @since 1.3
*/
private static byte[] encode3to4(
byte[] source, int srcOffset, int numSigBytes,
byte[] destination, int destOffset, int options )
{
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.
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 destination;
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 destination;
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 destination;
default:
return destination;
} // end switch
} // end encode3to4
/**
* Serializes an object and returns the Base64-encoded
* version of that serialized object. If the object
* cannot be serialized or there is another error,
* the method will return <tt>null</tt>.
* The object is not GZip-compressed before being encoded.
*
* @param serializableObject The object to encode
* @return The Base64-encoded object
* @since 1.4
*/
public static String encodeObject( java.io.Serializable serializableObject )
{
return encodeObject( serializableObject, NO_OPTIONS );
} // end encodeObject
/**
* Serializes an object and returns the Base64-encoded
* version of that serialized object. If the object
* cannot be serialized or there is another error,
* the method will return <tt>null</tt>.
* <p>
* Valid options:<pre>
* GZIP: gzip-compresses object before encoding it.
* DONT_BREAK_LINES: don't break lines at 76 characters
* <i>Note: Technically, this makes your encoding non-compliant.</i>
* </pre>
* <p>
* Example: <code>encodeObject( myObj, Base64.GZIP )</code> or
* <p>
* Example: <code>encodeObject( myObj, Base64.GZIP | Base64.DONT_BREAK_LINES )</code>
*
* @param serializableObject The object to encode
* @param options Specified options
* @return The Base64-encoded object
* @see Base64#GZIP
* @see Base64#DONT_BREAK_LINES
* @since 2.0
*/
public static String encodeObject( java.io.Serializable serializableObject, int options )
{
// Streams
java.io.ByteArrayOutputStream baos = null;
java.io.OutputStream b64os = null;
java.io.ObjectOutputStream oos = null;
java.util.zip.GZIPOutputStream gzos = null;
// Isolate options
int gzip = (options & GZIP);
int dontBreakLines = (options & DONT_BREAK_LINES);
try
{
// ObjectOutputStream -> (GZIP) -> Base64 -> ByteArrayOutputStream
baos = new java.io.ByteArrayOutputStream();
b64os = new Base64.OutputStream( baos, ENCODE | options );
// GZip?
if( gzip == GZIP )
{
gzos = new java.util.zip.GZIPOutputStream( b64os );
oos = new java.io.ObjectOutputStream( gzos );
} // end if: gzip
else
oos = new java.io.ObjectOutputStream( b64os );
oos.writeObject( serializableObject );
} // end try
catch( java.io.IOException e )
{
logger.error( Logger.SECURITY, "Problem writing object", e );
return null;
} // end catch
finally
{
try{ oos.close(); } catch( Exception e ){}
try{ gzos.close(); } catch( Exception e ){}
try{ b64os.close(); } catch( Exception e ){}
try{ baos.close(); } catch( Exception e ){}
} // end finally
// Return value according to relevant encoding.
try
{
return new String( baos.toByteArray(), PREFERRED_ENCODING );
} // end try
catch (java.io.UnsupportedEncodingException uue)
{
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
* @since 1.4
*/
public static String encodeBytes( byte[] source )
{
return encodeBytes( source, 0, source.length, NO_OPTIONS );
} // end encodeBytes
/**
* Encodes a byte array into Base64 notation.
* <p>
* Valid options:<pre>
* GZIP: gzip-compresses object before encoding it.
* DONT_BREAK_LINES: don't break lines at 76 characters
* <i>Note: Technically, this makes your encoding non-compliant.</i>
* </pre>
* <p>
* Example: <code>encodeBytes( myData, Base64.GZIP )</code> or
* <p>
* Example: <code>encodeBytes( myData, Base64.GZIP | Base64.DONT_BREAK_LINES )</code>
*
*
* @param source The data to convert
* @param options Specified options
* @see Base64#GZIP
* @see Base64#DONT_BREAK_LINES
* @since 2.0
*/
public static String encodeBytes( byte[] source, int options )
{
return encodeBytes( source, 0, source.length, options );
} // end encodeBytes
/**
* Encodes a byte array into Base64 notation.
* Does not GZip-compress data.
*
* @param source The data to convert
* @param off Offset in array where conversion should begin
* @param len Length of data to convert
* @since 1.4
*/
public static String encodeBytes( byte[] source, int off, int len )
{
return encodeBytes( source, off, len, NO_OPTIONS );
} // end encodeBytes
/**
* Encodes a byte array into Base64 notation.
* <p>
* Valid options:<pre>
* GZIP: gzip-compresses object before encoding it.
* DONT_BREAK_LINES: don't break lines at 76 characters
* <i>Note: Technically, this makes your encoding non-compliant.</i>
* </pre>
* <p>
* Example: <code>encodeBytes( myData, Base64.GZIP )</code> or
* <p>
* Example: <code>encodeBytes( myData, Base64.GZIP | Base64.DONT_BREAK_LINES )</code>
*
*
* @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
* @param options alphabet type is pulled from this (standard, url-safe, ordered)
* @see Base64#GZIP
* @see Base64#DONT_BREAK_LINES
* @since 2.0
*/
public static String encodeBytes( byte[] source, int off, int len, int options )
{
// Isolate options
int dontBreakLines = ( options & DONT_BREAK_LINES );
int gzip = ( options & GZIP );
// Compress?
if( gzip == GZIP )
{
java.io.ByteArrayOutputStream baos = null;
java.util.zip.GZIPOutputStream gzos = null;
Base64.OutputStream b64os = null;
try
{
// GZip -> Base64 -> ByteArray
baos = new java.io.ByteArrayOutputStream();
b64os = new Base64.OutputStream( baos, ENCODE | options );
gzos = new java.util.zip.GZIPOutputStream( b64os );
gzos.write( source, off, len );
gzos.close();
} // end try
catch( java.io.IOException e )
{
logger.error( Logger.SECURITY, "Problem writing gzip stream", e );
return null;
} // end catch
finally
{
try{ gzos.close(); } catch( Exception e ){}
try{ b64os.close(); } catch( Exception e ){}
try{ baos.close(); } catch( Exception e ){}
} // end finally
// Return value according to relevant encoding.
try
{
return new String( baos.toByteArray(), PREFERRED_ENCODING );
} // end try
catch (java.io.UnsupportedEncodingException uue)
{
return new String( baos.toByteArray() );
} // end catch
} // end if: compress
// Else, don't compress. Better not to use streams at all then.
else
{
// Convert option to boolean in way that code likes it.
boolean breakLines = dontBreakLines == 0;
int len43 = len * 4 / 3;
byte[] outBuff = new byte[ ( len43 ) // Main 4:3
+ ( (len % 3) > 0 ? 4 : 0 ) // Account for padding
+ (breakLines ? ( len43 / MAX_LINE_LENGTH ) : 0) ]; // New lines
int d = 0;
int e = 0;
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
} // en dfor: each piece of array
if( d < len )
{
encode3to4( source, d+off, len - d, outBuff, e, options );
e += 4;
} // end if: some padding needed
// Return value according to relevant encoding.
try
{
return new String( outBuff, 0, e, PREFERRED_ENCODING );
} // end try
catch (java.io.UnsupportedEncodingException uue)
{
return new String( outBuff, 0, e );
} // end catch
} // end else: don't compress
} // end encodeBytes
/* ******** 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
* @since 1.3
*/
private static int decode4to3( byte[] source, int srcOffset, byte[] destination, int destOffset, int options )
{
byte[] DECODABET = getDecodabet( options );
// Example: Dk==
if( source[ srcOffset + 2] == EQUALS_SIGN )
{
// Two ways to do the same thing. Don't know which way I like best.
//int outBuff = ( ( DECODABET[ source[ srcOffset ] ] << 24 ) >>> 6 )
// | ( ( DECODABET[ source[ srcOffset + 1] ] << 24 ) >>> 12 );
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 )
{
// Two ways to do the same thing. Don't know which way I like best.
//int outBuff = ( ( DECODABET[ source[ srcOffset ] ] << 24 ) >>> 6 )
// | ( ( DECODABET[ source[ srcOffset + 1 ] ] << 24 ) >>> 12 )
// | ( ( DECODABET[ source[ srcOffset + 2 ] ] << 24 ) >>> 18 );
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
{
try{
// Two ways to do the same thing. Don't know which way I like best.
//int outBuff = ( ( DECODABET[ source[ srcOffset ] ] << 24 ) >>> 6 )
// | ( ( DECODABET[ source[ srcOffset + 1 ] ] << 24 ) >>> 12 )
// | ( ( DECODABET[ source[ srcOffset + 2 ] ] << 24 ) >>> 18 )
// | ( ( DECODABET[ source[ srcOffset + 3 ] ] << 24 ) >>> 24 );
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;
}catch( Exception e){
logger.error( Logger.SECURITY, "Problem writing object", e );
logger.error( Logger.SECURITY, ""+source[srcOffset]+ ": " + ( DECODABET[ source[ srcOffset ] ] ) );
logger.error( Logger.SECURITY, ""+source[srcOffset+1]+ ": " + ( DECODABET[ source[ srcOffset + 1 ] ] ) );
logger.error( Logger.SECURITY, ""+source[srcOffset+2]+ ": " + ( DECODABET[ source[ srcOffset + 2 ] ] ) );
logger.error( Logger.SECURITY, ""+source[srcOffset+3]+ ": " + ( DECODABET[ source[ srcOffset + 3 ] ] ) );
return -1;
} // end catch
}
} // end decodeToBytes
/**
* Very low-level access to decoding ASCII characters in
* the form of a byte array. Does not support automatically
* gunzipping or any other "fancy" features.
*
* @param source The Base64 encoded data
* @param off The offset of where to begin decoding
* @param len The length of characters to decode
* @return decoded data
* @since 1.3
*/
public static byte[] decode( byte[] source, int off, int len, int options )
{
byte[] DECODABET = getDecodabet( options );
int len34 = len * 3 / 4;
byte[] outBuff = new byte[ len34 ]; // Upper limit on size of output
int outBuffPosn = 0;
byte[] b4 = new byte[4];
int b4Posn = 0;
int i = 0;
byte sbiCrop = 0;
byte sbiDecode = 0;
for( i = off; i < off+len; i++ )
{
sbiCrop = (byte)(source[i] & 0x7f); // Only the low seven bits
sbiDecode = DECODABET[ sbiCrop ];
if( sbiDecode >= WHITE_SPACE_ENC ) // White space, Equals sign or better
{
if( sbiDecode >= EQUALS_SIGN_ENC )
{
b4[ b4Posn++ ] = sbiCrop;
if( b4Posn > 3 )
{
outBuffPosn += decode4to3( b4, 0, outBuff, outBuffPosn, options );
b4Posn = 0;
// If that was the equals sign, break out of 'for' loop
if( sbiCrop == EQUALS_SIGN )
break;
} // end if: quartet built
} // end if: equals sign or better
} // end if: white space, equals sign or better
else
{
logger.error( Logger.SECURITY, "Bad Base64 input character at " + i + ": " + source[i] + "(decimal)" );
return null;
} // end else:
} // each input character
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
* @since 1.4
*/
public static byte[] decode( String s )
{
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
* @since 1.4
*/
public static byte[] decode( String s, int options )
{
byte[] bytes;
try
{
bytes = s.getBytes( PREFERRED_ENCODING );
} // end try
catch( java.io.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)
if( bytes != null && bytes.length >= 4 )