-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathApacheCodec.java
More file actions
2157 lines (1999 loc) · 77.3 KB
/
ApacheCodec.java
File metadata and controls
2157 lines (1999 loc) · 77.3 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
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.stellar.sdkandroidspi;
import java.io.FilterOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import java.util.Objects;
/**
* Copy from commons-codec:commons-codec:1.16.0
*
* <p>This is a compromise, because the Android platform built-in with commons-codec:commons-codec:
* 1.3.0 version in API < 28, which does not include the Base32 module. See <a
* href="https://github.com/stellar/java-stellar-sdk/issues/542">the issue</a>
*/
class ApacheCodec {
enum CodecPolicy {
/** The strict policy. Data that causes a codec to fail should throw an exception. */
STRICT,
/** The lenient policy. Data that causes a codec to fail should not throw an exception. */
LENIENT
}
static class Base32 extends BaseNCodec {
/**
* BASE32 characters are 5 bits in length. They are formed by taking a block of five octets to
* form a 40-bit string, which is converted into eight BASE32 characters.
*/
private static final int BITS_PER_ENCODED_BYTE = 5;
private static final int BYTES_PER_ENCODED_BLOCK = 8;
private static final int BYTES_PER_UNENCODED_BLOCK = 5;
/**
* This array is a lookup table that translates Unicode characters drawn from the "Base32
* Alphabet" (as specified in Table 3 of RFC 4648) into their 5-bit positive integer
* equivalents. Characters that are not in the Base32 alphabet but fall within the bounds of the
* array are translated to -1.
*/
private static final byte[] DECODE_TABLE = {
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 00-0f
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 10-1f
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 20-2f
-1,
-1,
26,
27,
28,
29,
30,
31,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 30-3f 2-7
-1,
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14, // 40-4f A-O
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25, // 50-5a P-Z
-1,
-1,
-1,
-1,
-1, // 5b-5f
-1,
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14, // 60-6f a-o
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25, // 70-7a p-z
};
/**
* This array is a lookup table that translates 5-bit positive integer index values into their
* "Base32 Alphabet" equivalents as specified in Table 3 of RFC 4648.
*/
private static final byte[] ENCODE_TABLE = {
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
'2', '3', '4', '5', '6', '7',
};
/**
* This array is a lookup table that translates Unicode characters drawn from the "Base32 Hex
* Alphabet" (as specified in Table 4 of RFC 4648) into their 5-bit positive integer
* equivalents. Characters that are not in the Base32 Hex alphabet but fall within the bounds of
* the array are translated to -1.
*/
private static final byte[] HEX_DECODE_TABLE = {
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 00-0f
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 10-1f
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 20-2f
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
-1,
-1,
-1,
-1,
-1,
-1, // 30-3f 0-9
-1,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24, // 40-4f A-O
25,
26,
27,
28,
29,
30,
31, // 50-56 P-V
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1, // 57-5f
-1,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24, // 60-6f a-o
25,
26,
27,
28,
29,
30,
31 // 70-76 p-v
};
/**
* This array is a lookup table that translates 5-bit positive integer index values into their
* "Base32 Hex Alphabet" equivalents as specified in Table 4 of RFC 4648.
*/
private static final byte[] HEX_ENCODE_TABLE = {
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I',
'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V',
};
/** Mask used to extract 5 bits, used when encoding Base32 bytes */
private static final int MASK_5BITS = 0x1f;
/** Mask used to extract 4 bits, used when decoding final trailing character. */
private static final long MASK_4BITS = 0x0fL;
/** Mask used to extract 3 bits, used when decoding final trailing character. */
private static final long MASK_3BITS = 0x07L;
/** Mask used to extract 2 bits, used when decoding final trailing character. */
private static final long MASK_2BITS = 0x03L;
/** Mask used to extract 1 bits, used when decoding final trailing character. */
private static final long MASK_1BITS = 0x01L;
// The static final fields above are used for the original static byte[] methods on Base32.
// The private member fields below are used with the new streaming approach, which requires
// some state be preserved between calls of encode() and decode().
/**
* Convenience variable to help us determine when our buffer is going to run out of room and
* needs resizing. {@code decodeSize = {@link #BYTES_PER_ENCODED_BLOCK} - 1 +
* lineSeparator.length;}
*/
private final int decodeSize;
/** Decode table to use. */
private final byte[] decodeTable;
/**
* Convenience variable to help us determine when our buffer is going to run out of room and
* needs resizing. {@code encodeSize = {@link #BYTES_PER_ENCODED_BLOCK} + lineSeparator.length;}
*/
private final int encodeSize;
/** Encode table to use. */
private final byte[] encodeTable;
/** Line separator for encoding. Not used when decoding. Only used if lineLength > 0. */
private final byte[] lineSeparator;
/**
* Creates a Base32 codec used for decoding and encoding.
*
* <p>When encoding the line length is 0 (no chunking).
*/
public Base32() {
this(false);
}
/**
* Creates a Base32 codec used for decoding and encoding.
*
* <p>When encoding the line length is 0 (no chunking).
*
* @param useHex if {@code true} then use Base32 Hex alphabet
*/
public Base32(final boolean useHex) {
this(0, null, useHex, PAD_DEFAULT);
}
/**
* Creates a Base32 codec used for decoding and encoding.
*
* <p>When encoding the line length is 0 (no chunking).
*
* @param useHex if {@code true} then use Base32 Hex alphabet
* @param padding byte used as padding byte.
*/
public Base32(final boolean useHex, final byte padding) {
this(0, null, useHex, padding);
}
/**
* Creates a Base32 codec used for decoding and encoding.
*
* <p>When encoding the line length is 0 (no chunking).
*
* @param pad byte used as padding byte.
*/
public Base32(final byte pad) {
this(false, pad);
}
/**
* Creates a Base32 codec used for decoding and encoding.
*
* <p>When encoding the line length is given in the constructor, the line separator is CRLF.
*
* @param lineLength Each line of encoded data will be at most of the given length (rounded down
* to the nearest multiple of 8). If lineLength <= 0, then the output will not be divided
* into lines (chunks). Ignored when decoding.
*/
public Base32(final int lineLength) {
this(lineLength, CHUNK_SEPARATOR);
}
/**
* Creates a Base32 codec used for decoding and encoding.
*
* <p>When encoding the line length and line separator are given in the constructor.
*
* <p>Line lengths that aren't multiples of 8 will still essentially end up being multiples of 8
* in the encoded data.
*
* @param lineLength Each line of encoded data will be at most of the given length (rounded down
* to the nearest multiple of 8). If lineLength <= 0, then the output will not be divided
* into lines (chunks). Ignored when decoding.
* @param lineSeparator Each line of encoded data will end with this sequence of bytes.
* @throws IllegalArgumentException Thrown when the {@code lineSeparator} contains Base32
* characters.
*/
public Base32(final int lineLength, final byte[] lineSeparator) {
this(lineLength, lineSeparator, false, PAD_DEFAULT);
}
/**
* Creates a Base32 / Base32 Hex codec used for decoding and encoding.
*
* <p>When encoding the line length and line separator are given in the constructor.
*
* <p>Line lengths that aren't multiples of 8 will still essentially end up being multiples of 8
* in the encoded data.
*
* @param lineLength Each line of encoded data will be at most of the given length (rounded down
* to the nearest multiple of 8). If lineLength <= 0, then the output will not be divided
* into lines (chunks). Ignored when decoding.
* @param lineSeparator Each line of encoded data will end with this sequence of bytes.
* @param useHex if {@code true}, then use Base32 Hex alphabet, otherwise use Base32 alphabet
* @throws IllegalArgumentException Thrown when the {@code lineSeparator} contains Base32
* characters. Or the lineLength > 0 and lineSeparator is null.
*/
public Base32(final int lineLength, final byte[] lineSeparator, final boolean useHex) {
this(lineLength, lineSeparator, useHex, PAD_DEFAULT);
}
/**
* Creates a Base32 / Base32 Hex codec used for decoding and encoding.
*
* <p>When encoding the line length and line separator are given in the constructor.
*
* <p>Line lengths that aren't multiples of 8 will still essentially end up being multiples of 8
* in the encoded data.
*
* @param lineLength Each line of encoded data will be at most of the given length (rounded down
* to the nearest multiple of 8). If lineLength <= 0, then the output will not be divided
* into lines (chunks). Ignored when decoding.
* @param lineSeparator Each line of encoded data will end with this sequence of bytes.
* @param useHex if {@code true}, then use Base32 Hex alphabet, otherwise use Base32 alphabet
* @param padding byte used as padding byte.
* @throws IllegalArgumentException Thrown when the {@code lineSeparator} contains Base32
* characters. Or the lineLength > 0 and lineSeparator is null.
*/
public Base32(
final int lineLength,
final byte[] lineSeparator,
final boolean useHex,
final byte padding) {
this(lineLength, lineSeparator, useHex, padding, DECODING_POLICY_DEFAULT);
}
/**
* Creates a Base32 / Base32 Hex codec used for decoding and encoding.
*
* <p>When encoding the line length and line separator are given in the constructor.
*
* <p>Line lengths that aren't multiples of 8 will still essentially end up being multiples of 8
* in the encoded data.
*
* @param lineLength Each line of encoded data will be at most of the given length (rounded down
* to the nearest multiple of 8). If lineLength <= 0, then the output will not be divided
* into lines (chunks). Ignored when decoding.
* @param lineSeparator Each line of encoded data will end with this sequence of bytes.
* @param useHex if {@code true}, then use Base32 Hex alphabet, otherwise use Base32 alphabet
* @param padding byte used as padding byte.
* @param decodingPolicy The decoding policy.
* @throws IllegalArgumentException Thrown when the {@code lineSeparator} contains Base32
* characters. Or the lineLength > 0 and lineSeparator is null.
* @since 1.15
*/
public Base32(
final int lineLength,
final byte[] lineSeparator,
final boolean useHex,
final byte padding,
final CodecPolicy decodingPolicy) {
super(
BYTES_PER_UNENCODED_BLOCK,
BYTES_PER_ENCODED_BLOCK,
lineLength,
lineSeparator == null ? 0 : lineSeparator.length,
padding,
decodingPolicy);
if (useHex) {
this.encodeTable = HEX_ENCODE_TABLE;
this.decodeTable = HEX_DECODE_TABLE;
} else {
this.encodeTable = ENCODE_TABLE;
this.decodeTable = DECODE_TABLE;
}
if (lineLength > 0) {
if (lineSeparator == null) {
throw new IllegalArgumentException(
"lineLength " + lineLength + " > 0, but lineSeparator is null");
}
// Must be done after initializing the tables
if (containsAlphabetOrPad(lineSeparator)) {
final String sep = StringUtils.newStringUtf8(lineSeparator);
throw new IllegalArgumentException(
"lineSeparator must not contain Base32 characters: [" + sep + "]");
}
this.encodeSize = BYTES_PER_ENCODED_BLOCK + lineSeparator.length;
this.lineSeparator = lineSeparator.clone();
} else {
this.encodeSize = BYTES_PER_ENCODED_BLOCK;
this.lineSeparator = null;
}
this.decodeSize = this.encodeSize - 1;
if (isInAlphabet(padding) || Character.isWhitespace(padding)) {
throw new IllegalArgumentException("pad must not be in alphabet or whitespace");
}
}
/**
* Decodes all of the provided data, starting at inPos, for inAvail bytes. Should be called at
* least twice: once with the data to decode, and once with inAvail set to "-1" to alert decoder
* that EOF has been reached. The "-1" call is not necessary when decoding, but it doesn't hurt,
* either.
*
* <p>Ignores all non-Base32 characters. This is how chunked (e.g. 76 character) data is
* handled, since CR and LF are silently ignored, but has implications for other bytes, too.
* This method subscribes to the garbage-in, garbage-out philosophy: it will not check the
* provided data for validity.
*
* @param input byte[] array of ASCII data to Base32 decode.
* @param inPos Position to start reading data from.
* @param inAvail Amount of bytes available from input for decoding.
* @param context the context to be used
*/
@Override
void decode(final byte[] input, int inPos, final int inAvail, final Context context) {
// package protected for access from I/O streams
if (context.eof) {
return;
}
if (inAvail < 0) {
context.eof = true;
}
for (int i = 0; i < inAvail; i++) {
final byte b = input[inPos++];
if (b == pad) {
// We're done.
context.eof = true;
break;
}
final byte[] buffer = ensureBufferSize(decodeSize, context);
if (b >= 0 && b < this.decodeTable.length) {
final int result = this.decodeTable[b];
if (result >= 0) {
context.modulus = (context.modulus + 1) % BYTES_PER_ENCODED_BLOCK;
// collect decoded bytes
context.lbitWorkArea = (context.lbitWorkArea << BITS_PER_ENCODED_BYTE) + result;
if (context.modulus == 0) { // we can output the 5 bytes
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 32) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 24) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 16) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) (context.lbitWorkArea & MASK_8BITS);
}
}
}
}
// Two forms of EOF as far as Base32 decoder is concerned: actual
// EOF (-1) and first time '=' character is encountered in stream.
// This approach makes the '=' padding characters completely optional.
if (context.eof && context.modulus > 0) { // if modulus == 0, nothing to do
final byte[] buffer = ensureBufferSize(decodeSize, context);
// We ignore partial bytes, i.e. only multiples of 8 count.
// Any combination not part of a valid encoding is either partially decoded
// or will raise an exception. Possible trailing characters are 2, 4, 5, 7.
// It is not possible to encode with 1, 3, 6 trailing characters.
// For backwards compatibility 3 & 6 chars are decoded anyway rather than discarded.
// See the encode(byte[]) method EOF section.
switch (context.modulus) {
// case 0 : // impossible, as excluded above
case 1: // 5 bits - either ignore entirely, or raise an exception
validateTrailingCharacters();
case 2: // 10 bits, drop 2 and output one byte
validateCharacter(MASK_2BITS, context);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 2) & MASK_8BITS);
break;
case 3: // 15 bits, drop 7 and output 1 byte, or raise an exception
validateTrailingCharacters();
// Not possible from a valid encoding but decode anyway
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 7) & MASK_8BITS);
break;
case 4: // 20 bits = 2*8 + 4
validateCharacter(MASK_4BITS, context);
context.lbitWorkArea = context.lbitWorkArea >> 4; // drop 4 bits
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea) & MASK_8BITS);
break;
case 5: // 25 bits = 3*8 + 1
validateCharacter(MASK_1BITS, context);
context.lbitWorkArea = context.lbitWorkArea >> 1;
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 16) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea) & MASK_8BITS);
break;
case 6: // 30 bits = 3*8 + 6, or raise an exception
validateTrailingCharacters();
// Not possible from a valid encoding but decode anyway
context.lbitWorkArea = context.lbitWorkArea >> 6;
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 16) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea) & MASK_8BITS);
break;
case 7: // 35 bits = 4*8 +3
validateCharacter(MASK_3BITS, context);
context.lbitWorkArea = context.lbitWorkArea >> 3;
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 24) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 16) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea >> 8) & MASK_8BITS);
buffer[context.pos++] = (byte) ((context.lbitWorkArea) & MASK_8BITS);
break;
default:
// modulus can be 0-7, and we excluded 0,1 already
throw new IllegalStateException("Impossible modulus " + context.modulus);
}
}
}
/**
* Encodes all of the provided data, starting at inPos, for inAvail bytes. Must be called at
* least twice: once with the data to encode, and once with inAvail set to "-1" to alert encoder
* that EOF has been reached, so flush last remaining bytes (if not multiple of 5).
*
* @param input byte[] array of binary data to Base32 encode.
* @param inPos Position to start reading data from.
* @param inAvail Amount of bytes available from input for encoding.
* @param context the context to be used
*/
@Override
void encode(final byte[] input, int inPos, final int inAvail, final Context context) {
// package protected for access from I/O streams
if (context.eof) {
return;
}
// inAvail < 0 is how we're informed of EOF in the underlying data we're
// encoding.
if (inAvail < 0) {
context.eof = true;
if (0 == context.modulus && lineLength == 0) {
return; // no leftovers to process and not using chunking
}
final byte[] buffer = ensureBufferSize(encodeSize, context);
final int savedPos = context.pos;
switch (context.modulus) { // % 5
case 0:
break;
case 1: // Only 1 octet; take top 5 bits then remainder
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 3) & MASK_5BITS]; // 8-1*5 = 3
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea << 2) & MASK_5BITS]; // 5-3=2
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
break;
case 2: // 2 octets = 16 bits to use
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 11) & MASK_5BITS]; // 16-1*5 = 11
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 6) & MASK_5BITS]; // 16-2*5 = 6
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 1) & MASK_5BITS]; // 16-3*5 = 1
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea << 4) & MASK_5BITS]; // 5-1 = 4
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
break;
case 3: // 3 octets = 24 bits to use
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 19) & MASK_5BITS]; // 24-1*5 = 19
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 14) & MASK_5BITS]; // 24-2*5 = 14
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 9) & MASK_5BITS]; // 24-3*5 = 9
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 4) & MASK_5BITS]; // 24-4*5 = 4
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea << 1) & MASK_5BITS]; // 5-4 = 1
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
buffer[context.pos++] = pad;
break;
case 4: // 4 octets = 32 bits to use
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 27) & MASK_5BITS]; // 32-1*5 = 27
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 22) & MASK_5BITS]; // 32-2*5 = 22
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 17) & MASK_5BITS]; // 32-3*5 = 17
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 12) & MASK_5BITS]; // 32-4*5 = 12
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 7) & MASK_5BITS]; // 32-5*5 = 7
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea >> 2) & MASK_5BITS]; // 32-6*5 = 2
buffer[context.pos++] =
encodeTable[(int) (context.lbitWorkArea << 3) & MASK_5BITS]; // 5-2 = 3
buffer[context.pos++] = pad;
break;
default:
throw new IllegalStateException("Impossible modulus " + context.modulus);
}
context.currentLinePos += context.pos - savedPos; // keep track of current line position
// if currentPos == 0 we are at the start of a line, so don't add CRLF
if (lineLength > 0 && context.currentLinePos > 0) { // add chunk separator if required
System.arraycopy(lineSeparator, 0, buffer, context.pos, lineSeparator.length);
context.pos += lineSeparator.length;
}
} else {
for (int i = 0; i < inAvail; i++) {
final byte[] buffer = ensureBufferSize(encodeSize, context);
context.modulus = (context.modulus + 1) % BYTES_PER_UNENCODED_BLOCK;
int b = input[inPos++];
if (b < 0) {
b += 256;
}
context.lbitWorkArea = (context.lbitWorkArea << 8) + b; // BITS_PER_BYTE
if (0 == context.modulus) { // we have enough bytes to create our output
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 35) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 30) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 25) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 20) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 15) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 10) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) (context.lbitWorkArea >> 5) & MASK_5BITS];
buffer[context.pos++] = encodeTable[(int) context.lbitWorkArea & MASK_5BITS];
context.currentLinePos += BYTES_PER_ENCODED_BLOCK;
if (lineLength > 0 && lineLength <= context.currentLinePos) {
System.arraycopy(lineSeparator, 0, buffer, context.pos, lineSeparator.length);
context.pos += lineSeparator.length;
context.currentLinePos = 0;
}
}
}
}
}
/**
* Returns whether or not the {@code octet} is in the Base32 alphabet.
*
* @param octet The value to test
* @return {@code true} if the value is defined in the Base32 alphabet {@code false} otherwise.
*/
@Override
public boolean isInAlphabet(final byte octet) {
return octet >= 0 && octet < decodeTable.length && decodeTable[octet] != -1;
}
/**
* Validates whether decoding the final trailing character is possible in the context of the set
* of possible base 32 values.
*
* <p>The character is valid if the lower bits within the provided mask are zero. This is used
* to test the final trailing base-32 digit is zero in the bits that will be discarded.
*
* @param emptyBitsMask The mask of the lower bits that should be empty
* @param context the context to be used
* @throws IllegalArgumentException if the bits being checked contain any non-zero value
*/
private void validateCharacter(final long emptyBitsMask, final Context context) {
// Use the long bit work area
if (isStrictDecoding() && (context.lbitWorkArea & emptyBitsMask) != 0) {
throw new IllegalArgumentException(
"Strict decoding: Last encoded character (before the paddings if any) is a valid "
+ "base 32 alphabet but not a possible encoding. "
+ "Expected the discarded bits from the character to be zero.");
}
}
/**
* Validates whether decoding allows final trailing characters that cannot be created during
* encoding.
*
* @throws IllegalArgumentException if strict decoding is enabled
*/
private void validateTrailingCharacters() {
if (isStrictDecoding()) {
throw new IllegalArgumentException(
"Strict decoding: Last encoded character(s) (before the paddings if any) are valid "
+ "base 32 alphabet but not a possible encoding. "
+ "Decoding requires either 2, 4, 5, or 7 trailing 5-bit characters to create bytes.");
}
}
}
static class BinaryCodec {
/*
* tried to avoid using ArrayUtils to minimize dependencies while using these empty arrays - dep is just not worth
* it.
*/
/** Empty char array. */
private static final char[] EMPTY_CHAR_ARRAY = {};
/** Empty byte array. */
private static final byte[] EMPTY_BYTE_ARRAY = {};
/** Mask for bit 0 of a byte. */
private static final int BIT_0 = 1;
/** Mask for bit 1 of a byte. */
private static final int BIT_1 = 0x02;
/** Mask for bit 2 of a byte. */
private static final int BIT_2 = 0x04;
/** Mask for bit 3 of a byte. */
private static final int BIT_3 = 0x08;
/** Mask for bit 4 of a byte. */
private static final int BIT_4 = 0x10;
/** Mask for bit 5 of a byte. */
private static final int BIT_5 = 0x20;
/** Mask for bit 6 of a byte. */
private static final int BIT_6 = 0x40;
/** Mask for bit 7 of a byte. */
private static final int BIT_7 = 0x80;
private static final int[] BITS = {BIT_0, BIT_1, BIT_2, BIT_3, BIT_4, BIT_5, BIT_6, BIT_7};
/**
* Decodes a byte array where each byte represents an ASCII '0' or '1'.
*
* @param ascii each byte represents an ASCII '0' or '1'
* @return the raw encoded binary where each bit corresponds to a byte in the byte array
* argument
*/
public static byte[] fromAscii(final byte[] ascii) {
if (isEmpty(ascii)) {
return EMPTY_BYTE_ARRAY;
}
final int asciiLength = ascii.length;
// get length/8 times bytes with 3 bit shifts to the right of the length
final byte[] raw = new byte[asciiLength >> 3];
/*
* We decr index jj by 8 as we go along to not recompute indices using multiplication every time inside the
* loop.
*/
for (int ii = 0, jj = asciiLength - 1; ii < raw.length; ii++, jj -= 8) {
for (int bits = 0; bits < BITS.length; ++bits) {
if (ascii[jj - bits] == '1') {
raw[ii] |= BITS[bits];
}
}
}
return raw;
}
// ------------------------------------------------------------------------
//
// static codec operations
//
// ------------------------------------------------------------------------
/**
* Decodes a char array where each char represents an ASCII '0' or '1'.
*
* @param ascii each char represents an ASCII '0' or '1'
* @return the raw encoded binary where each bit corresponds to a char in the char array
* argument
*/
public static byte[] fromAscii(final char[] ascii) {
if (ascii == null || ascii.length == 0) {
return EMPTY_BYTE_ARRAY;
}
final int asciiLength = ascii.length;
// get length/8 times bytes with 3 bit shifts to the right of the length
final byte[] raw = new byte[asciiLength >> 3];
/*
* We decr index jj by 8 as we go along to not recompute indices using multiplication every time inside the
* loop.
*/
for (int ii = 0, jj = asciiLength - 1; ii < raw.length; ii++, jj -= 8) {
for (int bits = 0; bits < BITS.length; ++bits) {
if (ascii[jj - bits] == '1') {
raw[ii] |= BITS[bits];
}
}
}
return raw;
}
/**
* Returns {@code true} if the given array is {@code null} or empty (size 0.)
*
* @param array the source array
* @return {@code true} if the given array is {@code null} or empty (size 0.)
*/
static boolean isEmpty(final byte[] array) {
return array == null || array.length == 0;
}
/**
* Converts an array of raw binary data into an array of ASCII 0 and 1 character bytes - each
* byte is a truncated char.
*
* @param raw the raw binary data to convert
* @return an array of 0 and 1 character bytes for each bit of the argument
*/
public static byte[] toAsciiBytes(final byte[] raw) {
if (isEmpty(raw)) {
return EMPTY_BYTE_ARRAY;
}
final int rawLength = raw.length;
// get 8 times the bytes with 3 bit shifts to the left of the length
final byte[] l_ascii = new byte[rawLength << 3];
/*
* We decr index jj by 8 as we go along to not recompute indices using multiplication every time inside the
* loop.
*/
for (int ii = 0, jj = l_ascii.length - 1; ii < rawLength; ii++, jj -= 8) {
for (int bits = 0; bits < BITS.length; ++bits) {
if ((raw[ii] & BITS[bits]) == 0) {
l_ascii[jj - bits] = '0';
} else {
l_ascii[jj - bits] = '1';
}
}
}
return l_ascii;
}
/**
* Converts an array of raw binary data into an array of ASCII 0 and 1 characters.
*
* @param raw the raw binary data to convert
* @return an array of 0 and 1 characters for each bit of the argument
*/
public static char[] toAsciiChars(final byte[] raw) {
if (isEmpty(raw)) {
return EMPTY_CHAR_ARRAY;
}
final int rawLength = raw.length;
// get 8 times the bytes with 3 bit shifts to the left of the length
final char[] l_ascii = new char[rawLength << 3];
/*
* We decr index jj by 8 as we go along to not recompute indices using multiplication every time inside the
* loop.
*/