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.Objects;
021
022import org.apache.commons.codec.CodecPolicy;
023
024/**
025 * Provides Base16 encoding and decoding.
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.
037 * </p>
038 *
039 * @see <a href="https://tools.ietf.org/html/rfc4648#section-8">RFC 4648 - 8. Base 16 Encoding</a>
040 * @since 1.15
041 */
042public class Base16 extends BaseNCodec {
043
044    /**
045     * BASE16 characters are 4 bits in length. They are formed by taking an 8-bit group, which is converted into two BASE16 characters.
046     */
047    private static final int BITS_PER_ENCODED_BYTE = 4;
048    private static final int BYTES_PER_ENCODED_BLOCK = 2;
049    private static final int BYTES_PER_UNENCODED_BLOCK = 1;
050
051    /**
052     * 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
053     * positive integer equivalents. Characters that are not in the Base16 alphabet but fall within the bounds of the array are translated to -1.
054     */
055    // @formatter:off
056    private static final byte[] UPPER_CASE_DECODE_TABLE = {
057            //  0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
058            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
059            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
060            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 20-2f
061             0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
062            -1, 10, 11, 12, 13, 14, 15                                      // 40-46 A-F
063    };
064    // @formatter:on
065
066    /**
067     * 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
068     * 4648.
069     */
070    private static final byte[] UPPER_CASE_ENCODE_TABLE = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
071
072    /**
073     * This array is a lookup table that translates Unicode characters drawn from the a lower-case "Base16 Alphabet" into their 4-bit positive integer
074     * equivalents. Characters that are not in the Base16 alphabet but fall within the bounds of the array are translated to -1.
075     */
076    // @formatter:off
077    private static final byte[] LOWER_CASE_DECODE_TABLE = {
078            //  0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
079            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
080            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
081            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 20-2f
082             0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
083            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 40-4f
084            -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 50-5f
085            -1, 10, 11, 12, 13, 14, 15                                      // 60-66 a-f
086    };
087    // @formatter:on
088
089    /**
090     * This array is a lookup table that translates 4-bit positive integer index values into their "Base16 Alphabet" lower-case equivalents.
091     */
092    private static final byte[] LOWER_CASE_ENCODE_TABLE = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f' };
093
094    /** Mask used to extract 4 bits, used when decoding character. */
095    private static final int MASK_4BITS = 0x0f;
096
097    /**
098     * Decode table to use.
099     */
100    private final byte[] decodeTable;
101
102    /**
103     * Encode table to use.
104     */
105    private final byte[] encodeTable;
106
107    /**
108     * Constructs a Base16 codec used for decoding and encoding.
109     */
110    public Base16() {
111        this(false);
112    }
113
114    /**
115     * Constructs a Base16 codec used for decoding and encoding.
116     *
117     * @param lowerCase if {@code true} then use a lower-case Base16 alphabet.
118     */
119    public Base16(final boolean lowerCase) {
120        this(lowerCase, DECODING_POLICY_DEFAULT);
121    }
122
123    /**
124     * Constructs a Base16 codec used for decoding and encoding.
125     *
126     * @param lowerCase      if {@code true} then use a lower-case Base16 alphabet.
127     * @param encodeTable    the encode table.
128     * @param decodingPolicy Decoding policy.
129     */
130    private Base16(final boolean lowerCase, final byte[] encodeTable, final CodecPolicy decodingPolicy) {
131        super(BYTES_PER_UNENCODED_BLOCK, BYTES_PER_ENCODED_BLOCK, 0, 0, PAD_DEFAULT, decodingPolicy);
132        Objects.requireNonNull(encodeTable, "encodeTable");
133        this.encodeTable = encodeTable;
134        this.decodeTable = encodeTable == LOWER_CASE_ENCODE_TABLE ? LOWER_CASE_DECODE_TABLE : UPPER_CASE_DECODE_TABLE;
135    }
136
137    /**
138     * Constructs a Base16 codec used for decoding and encoding.
139     *
140     * @param lowerCase      if {@code true} then use a lower-case Base16 alphabet.
141     * @param decodingPolicy Decoding policy.
142     */
143    public Base16(final boolean lowerCase, final CodecPolicy decodingPolicy) {
144        this(lowerCase, lowerCase ? LOWER_CASE_ENCODE_TABLE : UPPER_CASE_ENCODE_TABLE, decodingPolicy);
145    }
146
147    @Override
148    void decode(final byte[] data, int offset, final int length, final Context context) {
149        if (context.eof || length < 0) {
150            context.eof = true;
151            if (context.ibitWorkArea != 0) {
152                validateTrailingCharacter();
153            }
154            return;
155        }
156        final int dataLen = Math.min(data.length - offset, length);
157        final int availableChars = (context.ibitWorkArea != 0 ? 1 : 0) + dataLen;
158        // small optimization to short-cut the rest of this method when it is fed byte-by-byte
159        if (availableChars == 1 && availableChars == dataLen) {
160            // store 1/2 byte for next invocation of decode, we offset by +1 as empty-value is 0
161            context.ibitWorkArea = decodeOctet(data[offset]) + 1;
162            return;
163        }
164        // we must have an even number of chars to decode
165        final int charsToProcess = availableChars % BYTES_PER_ENCODED_BLOCK == 0 ? availableChars : availableChars - 1;
166        final int end = offset + dataLen;
167        final byte[] buffer = ensureBufferSize(charsToProcess / BYTES_PER_ENCODED_BLOCK, context);
168        int result;
169        if (dataLen < availableChars) {
170            // we have 1/2 byte from previous invocation to decode
171            result = context.ibitWorkArea - 1 << BITS_PER_ENCODED_BYTE;
172            result |= decodeOctet(data[offset++]);
173            buffer[context.pos++] = (byte) result;
174            // reset to empty-value for next invocation!
175            context.ibitWorkArea = 0;
176        }
177        final int loopEnd = end - 1;
178        while (offset < loopEnd) {
179            result = decodeOctet(data[offset++]) << BITS_PER_ENCODED_BYTE;
180            result |= decodeOctet(data[offset++]);
181            buffer[context.pos++] = (byte) result;
182        }
183        // we have one char of a hex-pair left over
184        if (offset < end) {
185            // store 1/2 byte for next invocation of decode, we offset by +1 as empty-value is 0
186            context.ibitWorkArea = decodeOctet(data[offset]) + 1;
187        }
188    }
189
190    private int decodeOctet(final byte octet) {
191        int decoded = -1;
192        if ((octet & 0xff) < decodeTable.length) {
193            decoded = decodeTable[octet];
194        }
195        if (decoded == -1) {
196            throw new IllegalArgumentException("Invalid octet in encoded value: " + (int) octet);
197        }
198        return decoded;
199    }
200
201    @Override
202    void encode(final byte[] data, final int offset, final int length, final Context context) {
203        if (context.eof) {
204            return;
205        }
206        if (length < 0) {
207            context.eof = true;
208            return;
209        }
210        final int size = length * BYTES_PER_ENCODED_BLOCK;
211        if (size < 0) {
212            throw new IllegalArgumentException("Input length exceeds maximum size for encoded data: " + length);
213        }
214        final byte[] buffer = ensureBufferSize(size, context);
215        final int end = offset + length;
216        for (int i = offset; i < end; i++) {
217            final int value = data[i];
218            final int high = value >> BITS_PER_ENCODED_BYTE & MASK_4BITS;
219            final int low = value & MASK_4BITS;
220            buffer[context.pos++] = encodeTable[high];
221            buffer[context.pos++] = encodeTable[low];
222        }
223    }
224
225    /**
226     * Returns whether or not the {@code octet} is in the Base16 alphabet.
227     *
228     * @param octet The value to test.
229     * @return {@code true} if the value is defined in the Base16 alphabet {@code false} otherwise.
230     */
231    @Override
232    public boolean isInAlphabet(final byte octet) {
233        return (octet & 0xff) < decodeTable.length && decodeTable[octet] != -1;
234    }
235
236    /**
237     * Validates whether decoding allows an entire final trailing character that cannot be used for a complete byte.
238     *
239     * @throws IllegalArgumentException if strict decoding is enabled
240     */
241    private void validateTrailingCharacter() {
242        if (isStrictDecoding()) {
243            throw new IllegalArgumentException("Strict decoding: Last encoded character is a valid base 16 alphabet character but not a possible encoding. " +
244                    "Decoding requires at least two characters to create one byte.");
245        }
246    }
247}