001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      https://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018package org.apache.commons.codec.binary;
019
020import java.util.Arrays;
021
022import org.apache.commons.codec.CodecPolicy;
023
024/**
025 * Provides Base16 encoding and decoding as defined by <a href="https://tools.ietf.org/html/rfc4648#section-8">RFC 4648 - 8. Base 16 Encoding</a>.
026 *
027 * <p>
028 * This class is thread-safe.
029 * </p>
030 * <p>
031 * This implementation strictly follows RFC 4648, and as such unlike the {@link Base32} and {@link Base64} implementations, it does not ignore invalid alphabet
032 * characters or whitespace, neither does it offer chunking or padding characters.
033 * </p>
034 * <p>
035 * The only additional feature above those specified in RFC 4648 is support for working with a lower-case alphabet in addition to the default upper-case
036 * alphabet, and configuring a custom 16-byte alphabet with {@link Builder#setEncodeTable(byte...)}.
037 * </p>
038 *
039 * @see Base16InputStream
040 * @see Base16OutputStream
041 * @see <a href="https://tools.ietf.org/html/rfc4648#section-8">RFC 4648 - 8. Base 16 Encoding</a>
042 * @since 1.15
043 */
044public class Base16 extends BaseNCodec {
045
046    /**
047     * Builds {@link Base16} instances.
048     *
049     * <p>
050     * To configure a new instance, use a {@link Builder}. For example:
051     * </p>
052     *
053     * <pre>
054     * Base16 Base16 = Base16.builder()
055     *   .setDecodingPolicy(DecodingPolicy.LENIENT) // default is lenient
056     *   .get()
057     * </pre>
058     *
059     * @since 1.20.0
060     */
061    public static class Builder extends AbstractBuilder<Base16, Builder> {
062
063        /**
064         * Constructs a new instance.
065         */
066        public Builder() {
067            super(null);
068            setDecodeTable(UPPER_CASE_DECODE_TABLE);
069            setEncodeTable(UPPER_CASE_ENCODE_TABLE);
070            setEncodedBlockSize(BYTES_PER_ENCODED_BLOCK);
071            setUnencodedBlockSize(BYTES_PER_UNENCODED_BLOCK);
072            setLineLength(0);
073            setLineSeparator(EMPTY_BYTE_ARRAY);
074        }
075
076        @Override
077        public Base16 get() {
078            return new Base16(this);
079        }
080
081        /**
082         * Sets the Base16 encode table and derives the matching decode table.
083         *
084         * @param encodeTable 16 unique bytes, null resets to the default upper-case table.
085         * @return {@code this} instance.
086         * @throws IllegalArgumentException if {@code encodeTable} does not contain 16 unique bytes.
087         */
088        @Override
089        public Builder setEncodeTable(final byte... encodeTable) {
090            final byte[] table = encodeTable != null ? encodeTable : UPPER_CASE_ENCODE_TABLE;
091            super.setDecodeTableRaw(toDecodeTable(table));
092            return super.setEncodeTable(table);
093        }
094
095        /**
096         * Sets whether to use the lower-case Base16 alphabet.
097         *
098         * @param lowerCase {@code true} to use the lower-case Base16 alphabet.
099         * @return {@code this} instance.
100         */
101        public Builder setLowerCase(final boolean lowerCase) {
102            return setEncodeTable(lowerCase ? LOWER_CASE_ENCODE_TABLE : UPPER_CASE_ENCODE_TABLE);
103        }
104
105    }
106
107    /**
108     * BASE16 characters are 4 bits in length. They are formed by taking an 8-bit group, which is converted into two BASE16 characters.
109     */
110    private static final int BITS_PER_ENCODED_BYTE = 4;
111
112    private static final int BYTES_PER_ENCODED_BLOCK = 2;
113
114    private static final int BYTES_PER_UNENCODED_BLOCK = 1;
115
116    /**
117     * This array is a lookup table that translates Unicode characters drawn from the "Base16 Alphabet" (as specified in Table 5 of RFC 4648) into their 4-bit
118     * positive integer equivalents. Characters that are not in the Base16 alphabet but fall within the bounds of the array are translated to -1.
119     */
120    // @formatter:off
121    private static final byte[] UPPER_CASE_DECODE_TABLE = {
122            //  0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
123            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
124            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
125            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 20-2f
126             0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
127            -1, 10, 11, 12, 13, 14, 15                                      // 40-46 A-F
128    };
129    // @formatter:on
130
131    /**
132     * This array is a lookup table that translates 4-bit positive integer index values into their "Base16 Alphabet" equivalents as specified in Table 5 of RFC
133     * 4648.
134     */
135    private static final byte[] UPPER_CASE_ENCODE_TABLE = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
136
137    /**
138     * This array is a lookup table that translates Unicode characters drawn from the a lower-case "Base16 Alphabet" into their 4-bit positive integer
139     * equivalents. Characters that are not in the Base16 alphabet but fall within the bounds of the array are translated to -1.
140     */
141    // @formatter:off
142    private static final byte[] LOWER_CASE_DECODE_TABLE = {
143            //  0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
144            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
145            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
146            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 20-2f
147             0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
148            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 40-4f
149            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 50-5f
150            -1, 10, 11, 12, 13, 14, 15                                      // 60-66 a-f
151    };
152    // @formatter:on
153
154    /**
155     * This array is a lookup table that translates 4-bit positive integer index values into their "Base16 Alphabet" lower-case equivalents.
156     */
157    private static final byte[] LOWER_CASE_ENCODE_TABLE = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f' };
158
159    /** Mask used to extract 4 bits, used when decoding character. */
160    private static final int MASK_4_BITS = 0x0f;
161
162    /**
163     * Constructs a new builder.
164     *
165     * @return A new builder.
166     * @since 1.20.0
167     */
168    public static Builder builder() {
169        return new Builder();
170    }
171
172    private static byte[] toDecodeTable(final byte[] encodeTable) {
173        if (Arrays.equals(encodeTable, UPPER_CASE_ENCODE_TABLE)) {
174            return UPPER_CASE_DECODE_TABLE;
175        }
176        if (Arrays.equals(encodeTable, LOWER_CASE_ENCODE_TABLE)) {
177            return LOWER_CASE_DECODE_TABLE;
178        }
179        if (encodeTable.length != 1 << BITS_PER_ENCODED_BYTE) {
180            throw new IllegalArgumentException("Base16 encode table must contain 16 entries.");
181        }
182        int max = -1;
183        for (final byte b : encodeTable) {
184            max = Math.max(max, b & 0xff);
185        }
186        final byte[] decodeTable = new byte[max + 1];
187        Arrays.fill(decodeTable, (byte) -1);
188        for (int i = 0; i < encodeTable.length; i++) {
189            final int b = encodeTable[i] & 0xff;
190            if (decodeTable[b] != -1) {
191                throw new IllegalArgumentException("Duplicate value in Base16 encode table: " + b);
192            }
193            decodeTable[b] = (byte) i;
194        }
195        return decodeTable;
196    }
197
198    /**
199     * Constructs a Base16 codec used for decoding and encoding.
200     */
201    public Base16() {
202        this(false);
203    }
204
205    /**
206     * Constructs a Base16 codec used for decoding and encoding.
207     *
208     * @param lowerCase {@code true} to use the lower-case Base16 alphabet.
209     * @deprecated Use {@link #builder()} and {@link Builder}.
210     */
211    @Deprecated
212    public Base16(final boolean lowerCase) {
213        this(lowerCase, DECODING_POLICY_DEFAULT);
214    }
215
216    /**
217     * Constructs a Base16 codec used for decoding and encoding.
218     *
219     * @param lowerCase      {@code true} to use the lower-case Base16 alphabet.
220     * @param decodingPolicy Decoding policy.
221     * @deprecated Use {@link #builder()} and {@link Builder}.
222     */
223    @Deprecated
224    public Base16(final boolean lowerCase, final CodecPolicy decodingPolicy) {
225        this(builder().setEncodeTable(lowerCase ? LOWER_CASE_ENCODE_TABLE : UPPER_CASE_ENCODE_TABLE).setDecodingPolicy(decodingPolicy));
226    }
227
228    private Base16(final Builder builder) {
229        super(builder);
230    }
231
232    @Override
233    void decode(final byte[] data, int offset, final int length, final Context context) {
234        if (context.eof || length < 0) {
235            context.eof = true;
236            if (context.ibitWorkArea != 0) {
237                validateTrailingCharacter();
238            }
239            return;
240        }
241        final int dataLen = Math.min(data.length - offset, length);
242        final int availableChars = (context.ibitWorkArea != 0 ? 1 : 0) + dataLen;
243        // small optimization to short-cut the rest of this method when it is fed byte-by-byte
244        if (availableChars == 1 && availableChars == dataLen) {
245            // store 1/2 byte for next invocation of decode, we offset by +1 as empty-value is 0
246            context.ibitWorkArea = decodeOctet(data[offset]) + 1;
247            return;
248        }
249        // we must have an even number of chars to decode
250        final int charsToProcess = availableChars % BYTES_PER_ENCODED_BLOCK == 0 ? availableChars : availableChars - 1;
251        final int end = offset + dataLen;
252        final byte[] buffer = ensureBufferSize(charsToProcess / BYTES_PER_ENCODED_BLOCK, context);
253        int result;
254        if (dataLen < availableChars) {
255            // we have 1/2 byte from previous invocation to decode
256            result = context.ibitWorkArea - 1 << BITS_PER_ENCODED_BYTE;
257            result |= decodeOctet(data[offset++]);
258            buffer[context.pos++] = (byte) result;
259            // reset to empty-value for next invocation!
260            context.ibitWorkArea = 0;
261        }
262        final int loopEnd = end - 1;
263        while (offset < loopEnd) {
264            result = decodeOctet(data[offset++]) << BITS_PER_ENCODED_BYTE;
265            result |= decodeOctet(data[offset++]);
266            buffer[context.pos++] = (byte) result;
267        }
268        // we have one char of a hex-pair left over
269        if (offset < end) {
270            // store 1/2 byte for next invocation of decode, we offset by +1 as empty-value is 0
271            context.ibitWorkArea = decodeOctet(data[offset]) + 1;
272        }
273    }
274
275    private int decodeOctet(final byte octet) {
276        int decoded = -1;
277        final int b = octet & 0xff;
278        if (b < decodeTable.length) {
279            decoded = decodeTable[b];
280        }
281        if (decoded == -1) {
282            throw new IllegalArgumentException("Invalid octet in encoded value: " + (int) octet);
283        }
284        return decoded;
285    }
286
287    @Override
288    void encode(final byte[] data, final int offset, final int length, final Context context) {
289        if (context.eof) {
290            return;
291        }
292        if (length < 0) {
293            context.eof = true;
294            return;
295        }
296        final int size = length * BYTES_PER_ENCODED_BLOCK;
297        if (size < 0) {
298            throw new IllegalArgumentException("Input length exceeds maximum size for encoded data: " + length);
299        }
300        final byte[] buffer = ensureBufferSize(size, context);
301        final int end = offset + length;
302        for (int i = offset; i < end; i++) {
303            final int value = data[i];
304            final int high = value >> BITS_PER_ENCODED_BYTE & MASK_4_BITS;
305            final int low = value & MASK_4_BITS;
306            buffer[context.pos++] = encodeTable[high];
307            buffer[context.pos++] = encodeTable[low];
308        }
309    }
310
311    /**
312     * Returns whether or not the {@code octet} is in the Base16 alphabet.
313     *
314     * @param octet The value to test.
315     * @return {@code true} if the value is defined in the Base16 alphabet {@code false} otherwise.
316     */
317    @Override
318    public boolean isInAlphabet(final byte octet) {
319        final int b = octet & 0xff;
320        return b < decodeTable.length && decodeTable[b] != -1;
321    }
322
323    /**
324     * Validates whether decoding allows an entire final trailing character that cannot be used for a complete byte.
325     *
326     * @throws IllegalArgumentException if strict decoding is enabled.
327     */
328    private void validateTrailingCharacter() {
329        if (isStrictDecoding()) {
330            throw new IllegalArgumentException("Strict decoding: Last encoded character is a valid Base 16 alphabet character but not a possible encoding. " +
331                    "Decoding requires at least two characters to create one byte.");
332        }
333    }
334}