File: BaseNCodec.java

package info (click to toggle)
tomcat9 9.0.70-2
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 43,208 kB
  • sloc: java: 358,255; xml: 63,839; jsp: 4,528; sh: 1,204; perl: 315; makefile: 18
file content (579 lines) | stat: -rw-r--r-- 21,735 bytes parent folder | download
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
/*
 * 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.apache.tomcat.util.codec.binary;

import org.apache.tomcat.util.buf.HexUtils;
import org.apache.tomcat.util.res.StringManager;

/**
 * Abstract superclass for Base-N encoders and decoders.
 *
 * <p>
 * This class is thread-safe.
 * </p>
 */
public abstract class BaseNCodec {

    protected static final StringManager sm = StringManager.getManager(BaseNCodec.class);

    /**
     * Holds thread context so classes can be thread-safe.
     *
     * This class is not itself thread-safe; each thread must allocate its own copy.
     *
     * @since 1.7
     */
    static class Context {

        /**
         * Placeholder for the bytes we're dealing with for our based logic.
         * Bitwise operations store and extract the encoding or decoding from this variable.
         */
        int ibitWorkArea;

        /**
         * Buffer for streaming.
         */
        byte[] buffer;

        /**
         * Position where next character should be written in the buffer.
         */
        int pos;

        /**
         * Position where next character should be read from the buffer.
         */
        int readPos;

        /**
         * Boolean flag to indicate the EOF has been reached. Once EOF has been reached, this object becomes useless,
         * and must be thrown away.
         */
        boolean eof;

        /**
         * Variable tracks how many characters have been written to the current line. Only used when encoding. We use
         * it to make sure each encoded line never goes beyond lineLength (if lineLength &gt; 0).
         */
        int currentLinePos;

        /**
         * Writes to the buffer only occur after every 3/5 reads when encoding, and every 4/8 reads when decoding. This
         * variable helps track that.
         */
        int modulus;

        /**
         * Returns a String useful for debugging (especially within a debugger.)
         *
         * @return a String useful for debugging.
         */
        @SuppressWarnings("boxing") // OK to ignore boxing here
        @Override
        public String toString() {
            return String.format("%s[buffer=%s, currentLinePos=%s, eof=%s, ibitWorkArea=%s, " +
                    "modulus=%s, pos=%s, readPos=%s]", this.getClass().getSimpleName(), HexUtils.toHexString(buffer),
                    currentLinePos, eof, ibitWorkArea, modulus, pos, readPos);
        }
    }

    /**
     * EOF
     *
     * @since 1.7
     */
    static final int EOF = -1;

    /**
     *  MIME chunk size per RFC 2045 section 6.8.
     *
     * <p>
     * The {@value} character limit does not count the trailing CRLF, but counts all other characters, including any
     * equal signs.
     * </p>
     *
     * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 6.8</a>
     */
    public static final int MIME_CHUNK_SIZE = 76;

    /**
     * PEM chunk size per RFC 1421 section 4.3.2.4.
     *
     * <p>
     * The {@value} character limit does not count the trailing CRLF, but counts all other characters, including any
     * equal signs.
     * </p>
     *
     * @see <a href="http://tools.ietf.org/html/rfc1421">RFC 1421 section 4.3.2.4</a>
     */
    public static final int PEM_CHUNK_SIZE = 64;

    private static final int DEFAULT_BUFFER_RESIZE_FACTOR = 2;

    /**
     * Defines the default buffer size - currently {@value}
     * - must be large enough for at least one encoded block+separator
     */
    private static final int DEFAULT_BUFFER_SIZE = 128;

    /**
     * The maximum size buffer to allocate.
     *
     * <p>This is set to the same size used in the JDK {@code java.util.ArrayList}:</p>
     * <blockquote>
     * Some VMs reserve some header words in an array.
     * Attempts to allocate larger arrays may result in
     * OutOfMemoryError: Requested array size exceeds VM limit.
     * </blockquote>
     */
    private static final int MAX_BUFFER_SIZE = Integer.MAX_VALUE - 8;

    /** Mask used to extract 8 bits, used in decoding bytes */
    protected static final int MASK_8BITS = 0xff;

    /**
     * Byte used to pad output.
     */
    protected static final byte PAD_DEFAULT = '='; // Allow static access to default

    /**
     * Chunk separator per RFC 2045 section 2.1.
     *
     * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 2.1</a>
     */
    static final byte[] CHUNK_SEPARATOR = {'\r', '\n'};

    /**
     * Compares two {@code int} values numerically treating the values
     * as unsigned. Taken from JDK 1.8.
     *
     * <p>TODO: Replace with JDK 1.8 Integer::compareUnsigned(int, int).</p>
     *
     * @param  x the first {@code int} to compare
     * @param  y the second {@code int} to compare
     * @return the value {@code 0} if {@code x == y}; a value less
     *         than {@code 0} if {@code x < y} as unsigned values; and
     *         a value greater than {@code 0} if {@code x > y} as
     *         unsigned values
     */
    private static int compareUnsigned(final int x, final int y) {
        return Integer.compare(x + Integer.MIN_VALUE, y + Integer.MIN_VALUE);
    }

    /**
     * Create a positive capacity at least as large the minimum required capacity.
     * If the minimum capacity is negative then this throws an OutOfMemoryError as no array
     * can be allocated.
     *
     * @param minCapacity the minimum capacity
     * @return the capacity
     * @throws OutOfMemoryError if the {@code minCapacity} is negative
     */
    private static int createPositiveCapacity(final int minCapacity) {
        if (minCapacity < 0) {
            // overflow
            throw new OutOfMemoryError("Unable to allocate array size: " + (minCapacity & 0xffffffffL));
        }
        // This is called when we require buffer expansion to a very big array.
        // Use the conservative maximum buffer size if possible, otherwise the biggest required.
        //
        // Note: In this situation JDK 1.8 java.util.ArrayList returns Integer.MAX_VALUE.
        // This excludes some VMs that can exceed MAX_BUFFER_SIZE but not allocate a full
        // Integer.MAX_VALUE length array.
        // The result is that we may have to allocate an array of this size more than once if
        // the capacity must be expanded again.
        return Math.max(minCapacity, MAX_BUFFER_SIZE);
    }

    /**
     * Gets a copy of the chunk separator per RFC 2045 section 2.1.
     *
     * @return the chunk separator
     * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 2.1</a>
     * @since 1.15
     */
    public static byte[] getChunkSeparator() {
        return CHUNK_SEPARATOR.clone();
    }

    /**
     * Checks if a byte value is whitespace or not.
     * Whitespace is taken to mean: space, tab, CR, LF
     * @param byteToCheck
     *            the byte to check
     * @return true if byte is whitespace, false otherwise
     */
    protected static boolean isWhiteSpace(final byte byteToCheck) {
        switch (byteToCheck) {
            case ' ' :
            case '\n' :
            case '\r' :
            case '\t' :
                return true;
            default :
                return false;
        }
    }

    /**
     * Increases our buffer by the {@link #DEFAULT_BUFFER_RESIZE_FACTOR}.
     * @param context the context to be used
     * @param minCapacity the minimum required capacity
     * @return the resized byte[] buffer
     * @throws OutOfMemoryError if the {@code minCapacity} is negative
     */
    private static byte[] resizeBuffer(final Context context, final int minCapacity) {
        // Overflow-conscious code treats the min and new capacity as unsigned.
        final int oldCapacity = context.buffer.length;
        int newCapacity = oldCapacity * DEFAULT_BUFFER_RESIZE_FACTOR;
        if (compareUnsigned(newCapacity, minCapacity) < 0) {
            newCapacity = minCapacity;
        }
        if (compareUnsigned(newCapacity, MAX_BUFFER_SIZE) > 0) {
            newCapacity = createPositiveCapacity(minCapacity);
        }

        final byte[] b = new byte[newCapacity];
        System.arraycopy(context.buffer, 0, b, 0, context.buffer.length);
        context.buffer = b;
        return b;
    }

    /** Pad byte. Instance variable just in case it needs to vary later. */
    protected final byte pad;

    /** Number of bytes in each full block of unencoded data, e.g. 4 for Base64 and 5 for Base32 */
    private final int unencodedBlockSize;

    /** Number of bytes in each full block of encoded data, e.g. 3 for Base64 and 8 for Base32 */
    private final int encodedBlockSize;

    /**
     * Chunksize for encoding. Not used when decoding.
     * A value of zero or less implies no chunking of the encoded data.
     * Rounded down to the nearest multiple of encodedBlockSize.
     */
    protected final int lineLength;

    /**
     * Size of chunk separator. Not used unless {@link #lineLength} &gt; 0.
     */
    private final int chunkSeparatorLength;

    /**
     * Note {@code lineLength} is rounded down to the nearest multiple of the encoded block size.
     * If {@code chunkSeparatorLength} is zero, then chunking is disabled.
     * @param unencodedBlockSize the size of an unencoded block (e.g. Base64 = 3)
     * @param encodedBlockSize the size of an encoded block (e.g. Base64 = 4)
     * @param lineLength if &gt; 0, use chunking with a length {@code lineLength}
     * @param chunkSeparatorLength the chunk separator length, if relevant
     */
    protected BaseNCodec(final int unencodedBlockSize, final int encodedBlockSize,
                         final int lineLength, final int chunkSeparatorLength) {
        this(unencodedBlockSize, encodedBlockSize, lineLength, chunkSeparatorLength, PAD_DEFAULT);
    }

    /**
     * Note {@code lineLength} is rounded down to the nearest multiple of the encoded block size.
     * If {@code chunkSeparatorLength} is zero, then chunking is disabled.
     * @param unencodedBlockSize the size of an unencoded block (e.g. Base64 = 3)
     * @param encodedBlockSize the size of an encoded block (e.g. Base64 = 4)
     * @param lineLength if &gt; 0, use chunking with a length {@code lineLength}
     * @param chunkSeparatorLength the chunk separator length, if relevant
     * @param pad byte used as padding byte.
     */
    protected BaseNCodec(final int unencodedBlockSize, final int encodedBlockSize,
                         final int lineLength, final int chunkSeparatorLength, final byte pad) {
        this.unencodedBlockSize = unencodedBlockSize;
        this.encodedBlockSize = encodedBlockSize;
        final boolean useChunking = lineLength > 0 && chunkSeparatorLength > 0;
        this.lineLength = useChunking ? (lineLength / encodedBlockSize) * encodedBlockSize : 0;
        this.chunkSeparatorLength = chunkSeparatorLength;
        this.pad = pad;
    }

    /**
     * Returns the amount of buffered data available for reading.
     *
     * @param context the context to be used
     * @return The amount of buffered data available for reading.
     */
    int available(final Context context) {  // package protected for access from I/O streams
        return hasData(context) ? context.pos - context.readPos : 0;
    }

    /**
     * Tests a given byte array to see if it contains any characters within the alphabet or PAD.
     *
     * Intended for use in checking line-ending arrays
     *
     * @param arrayOctet
     *            byte array to test
     * @return {@code true} if any byte is a valid character in the alphabet or PAD; {@code false} otherwise
     */
    protected boolean containsAlphabetOrPad(final byte[] arrayOctet) {
        if (arrayOctet == null) {
            return false;
        }
        for (final byte element : arrayOctet) {
            if (pad == element || isInAlphabet(element)) {
                return true;
            }
        }
        return false;
    }

    /**
     * Decodes a byte[] containing characters in the Base-N alphabet.
     *
     * @param pArray
     *            A byte array containing Base-N character data
     * @return a byte array containing binary data
     */
    public byte[] decode(final byte[] pArray) {
        return decode(pArray, 0, pArray.length);
    }

    public byte[] decode(final byte[] pArray, final int off, final int len) {
        if (pArray == null || len == 0) {
            return new byte[0];
        }
        final Context context = new Context();
        decode(pArray, off, len, context);
        decode(pArray, off, EOF, context); // Notify decoder of EOF.
        final byte[] result = new byte[context.pos];
        readResults(result, 0, result.length, context);
        return result;
    }

    // package protected for access from I/O streams
    abstract void decode(byte[] pArray, int i, int length, Context context);

    /**
     * Decodes a String containing characters in the Base-N alphabet.
     *
     * @param pArray
     *            A String containing Base-N character data
     * @return a byte array containing binary data
     */
    public byte[] decode(final String pArray) {
        return decode(StringUtils.getBytesUtf8(pArray));
    }

    /**
     * Encodes a byte[] containing binary data, into a byte[] containing characters in the alphabet.
     *
     * @param pArray
     *            a byte array containing binary data
     * @return A byte array containing only the base N alphabetic character data
     */
    public byte[] encode(final byte[] pArray) {
        if (pArray == null || pArray.length == 0) {
            return pArray;
        }
        return encode(pArray, 0, pArray.length);
    }

    /**
     * Encodes a byte[] containing binary data, into a byte[] containing
     * characters in the alphabet.
     *
     * @param pArray
     *            a byte array containing binary data
     * @param offset
     *            initial offset of the subarray.
     * @param length
     *            length of the subarray.
     * @return A byte array containing only the base N alphabetic character data
     * @since 1.11
     */
    public byte[] encode(final byte[] pArray, final int offset, final int length) {
        if (pArray == null || pArray.length == 0) {
            return pArray;
        }
        final Context context = new Context();
        encode(pArray, offset, length, context);
        encode(pArray, offset, EOF, context); // Notify encoder of EOF.
        final byte[] buf = new byte[context.pos - context.readPos];
        readResults(buf, 0, buf.length, context);
        return buf;
    }

    // package protected for access from I/O streams
    abstract void encode(byte[] pArray, int i, int length, Context context);

    /**
     * Encodes a byte[] containing binary data, into a String containing characters in the appropriate alphabet.
     * Uses UTF8 encoding.
     *
     * @param pArray a byte array containing binary data
     * @return String containing only character data in the appropriate alphabet.
     * @since 1.5
     * This is a duplicate of {@link #encodeToString(byte[])}; it was merged during refactoring.
    */
    public String encodeAsString(final byte[] pArray){
        return StringUtils.newStringUtf8(encode(pArray));
    }

    /**
     * Encodes a byte[] containing binary data, into a String containing characters in the Base-N alphabet.
     * Uses UTF8 encoding.
     *
     * @param pArray
     *            a byte array containing binary data
     * @return A String containing only Base-N character data
     */
    public String encodeToString(final byte[] pArray) {
        return StringUtils.newStringUtf8(encode(pArray));
    }

    /**
     * Ensure that the buffer has room for {@code size} bytes
     *
     * @param size minimum spare space required
     * @param context the context to be used
     * @return the buffer
     */
    protected byte[] ensureBufferSize(final int size, final Context context){
        if (context.buffer == null) {
            context.buffer = new byte[Math.max(size, getDefaultBufferSize())];
            context.pos = 0;
            context.readPos = 0;

            // Overflow-conscious:
            // x + y > z  ==  x + y - z > 0
        } else if (context.pos + size - context.buffer.length > 0) {
            return resizeBuffer(context, context.pos + size);
        }
        return context.buffer;
    }

    /**
     * Get the default buffer size. Can be overridden.
     *
     * @return the default buffer size.
     */
    protected int getDefaultBufferSize() {
        return DEFAULT_BUFFER_SIZE;
    }

    /**
     * Calculates the amount of space needed to encode the supplied array.
     *
     * @param pArray byte[] array which will later be encoded
     *
     * @return amount of space needed to encode the supplied array.
     * Returns a long since a max-len array will require &gt; Integer.MAX_VALUE
     */
    public long getEncodedLength(final byte[] pArray) {
        // Calculate non-chunked size - rounded up to allow for padding
        // cast to long is needed to avoid possibility of overflow
        long len = ((pArray.length + unencodedBlockSize-1)  / unencodedBlockSize) * (long) encodedBlockSize;
        if (lineLength > 0) { // We're using chunking
            // Round up to nearest multiple
            len += ((len + lineLength-1) / lineLength) * chunkSeparatorLength;
        }
        return len;
    }

    /**
     * Returns true if this object has buffered data for reading.
     *
     * @param context the context to be used
     * @return true if there is data still available for reading.
     */
    boolean hasData(final Context context) {  // package protected for access from I/O streams
        return context.pos > context.readPos;
    }

    /**
     * Returns whether or not the {@code octet} is in the current alphabet.
     * Does not allow whitespace or pad.
     *
     * @param value The value to test
     *
     * @return {@code true} if the value is defined in the current alphabet, {@code false} otherwise.
     */
    protected abstract boolean isInAlphabet(byte value);

    /**
     * Tests a given byte array to see if it contains only valid characters within the alphabet.
     * The method optionally treats whitespace and pad as valid.
     *
     * @param arrayOctet byte array to test
     * @param allowWSPad if {@code true}, then whitespace and PAD are also allowed
     *
     * @return {@code true} if all bytes are valid characters in the alphabet or if the byte array is empty;
     *         {@code false}, otherwise
     */
    public boolean isInAlphabet(final byte[] arrayOctet, final boolean allowWSPad) {
        for (final byte octet : arrayOctet) {
            if (!isInAlphabet(octet) &&
                    (!allowWSPad || (octet != pad) && !isWhiteSpace(octet))) {
                return false;
            }
        }
        return true;
    }

    /**
     * Tests a given String to see if it contains only valid characters within the alphabet.
     * The method treats whitespace and PAD as valid.
     *
     * @param basen String to test
     * @return {@code true} if all characters in the String are valid characters in the alphabet or if
     *         the String is empty; {@code false}, otherwise
     * @see #isInAlphabet(byte[], boolean)
     */
    public boolean isInAlphabet(final String basen) {
        return isInAlphabet(StringUtils.getBytesUtf8(basen), true);
    }

    /**
     * Extracts buffered data into the provided byte[] array, starting at position bPos, up to a maximum of bAvail
     * bytes. Returns how many bytes were actually extracted.
     * <p>
     * Package protected for access from I/O streams.
     *
     * @param b
     *            byte[] array to extract the buffered data into.
     * @param bPos
     *            position in byte[] array to start extraction at.
     * @param bAvail
     *            amount of bytes we're allowed to extract. We may extract fewer (if fewer are available).
     * @param context
     *            the context to be used
     * @return The number of bytes successfully extracted into the provided byte[] array.
     */
    int readResults(final byte[] b, final int bPos, final int bAvail, final Context context) {
        if (hasData(context)) {
            final int len = Math.min(available(context), bAvail);
            System.arraycopy(context.buffer, context.readPos, b, bPos, len);
            context.readPos += len;
            if (!hasData(context)) {
                // All data read.
                // Reset position markers but do not set buffer to null to allow its reuse.
                // hasData(context) will still return false, and this method will return 0 until
                // more data is available, or -1 if EOF.
                context.pos = context.readPos = 0;
            }
            return len;
        }
        return context.eof ? EOF : 0;
    }
}