View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *      https://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  
18  package org.apache.commons.codec.binary;
19  
20  import java.util.Arrays;
21  
22  import org.apache.commons.codec.CodecPolicy;
23  
24  /**
25   * 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>.
26   *
27   * <p>
28   * This class is thread-safe.
29   * </p>
30   * <p>
31   * This implementation strictly follows RFC 4648, and as such unlike the {@link Base32} and {@link Base64} implementations, it does not ignore invalid alphabet
32   * characters or whitespace, neither does it offer chunking or padding characters.
33   * </p>
34   * <p>
35   * 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
36   * alphabet.
37   * </p>
38   *
39   * @see Base16InputStream
40   * @see Base16OutputStream
41   * @see <a href="https://tools.ietf.org/html/rfc4648#section-8">RFC 4648 - 8. Base 16 Encoding</a>
42   * @since 1.15
43   */
44  public class Base16 extends BaseNCodec {
45  
46      /**
47       * Builds {@link Base16} instances.
48       *
49       * <p>
50       * To configure a new instance, use a {@link Builder}. For example:
51       * </p>
52       *
53       * <pre>
54       * Base16 Base16 = Base16.builder()
55       *   .setDecodingPolicy(DecodingPolicy.LENIENT) // default is lenient
56       *   .get()
57       * </pre>
58       *
59       * @since 1.20.0
60       */
61      public static class Builder extends AbstractBuilder<Base16, Builder> {
62  
63          /**
64           * Constructs a new instance.
65           */
66          public Builder() {
67              super(null);
68              setDecodeTable(UPPER_CASE_DECODE_TABLE);
69              setEncodeTable(UPPER_CASE_ENCODE_TABLE);
70              setEncodedBlockSize(BYTES_PER_ENCODED_BLOCK);
71              setUnencodedBlockSize(BYTES_PER_UNENCODED_BLOCK);
72              setLineLength(0);
73              setLineSeparator(EMPTY_BYTE_ARRAY);
74          }
75  
76          @Override
77          public Base16 get() {
78              return new Base16(this);
79          }
80  
81          @Override
82          public Builder setEncodeTable(final byte... encodeTable) {
83              super.setDecodeTableRaw(Arrays.equals(encodeTable, LOWER_CASE_ENCODE_TABLE) ? LOWER_CASE_DECODE_TABLE : UPPER_CASE_DECODE_TABLE);
84              return super.setEncodeTable(encodeTable);
85          }
86  
87          /**
88           * Sets whether to use the the lower-case Base16 alphabet.
89           *
90           * @param lowerCase {@code true} to use the lower-case Base16 alphabet.
91           * @return {@code this} instance.
92           */
93          public Builder setLowerCase(final boolean lowerCase) {
94              setEncodeTableRaw(lowerCase ? LOWER_CASE_ENCODE_TABLE : UPPER_CASE_ENCODE_TABLE);
95              return asThis();
96          }
97  
98      }
99  
100     /**
101      * BASE16 characters are 4 bits in length. They are formed by taking an 8-bit group, which is converted into two BASE16 characters.
102      */
103     private static final int BITS_PER_ENCODED_BYTE = 4;
104 
105     private static final int BYTES_PER_ENCODED_BLOCK = 2;
106 
107     private static final int BYTES_PER_UNENCODED_BLOCK = 1;
108     /**
109      * 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
110      * positive integer equivalents. Characters that are not in the Base16 alphabet but fall within the bounds of the array are translated to -1.
111      */
112     // @formatter:off
113     private static final byte[] UPPER_CASE_DECODE_TABLE = {
114             //  0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
115             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
116             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
117             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 20-2f
118              0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
119             -1, 10, 11, 12, 13, 14, 15                                      // 40-46 A-F
120     };
121     // @formatter:on
122     /**
123      * 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
124      * 4648.
125      */
126     private static final byte[] UPPER_CASE_ENCODE_TABLE = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
127 
128     /**
129      * This array is a lookup table that translates Unicode characters drawn from the a lower-case "Base16 Alphabet" into their 4-bit positive integer
130      * equivalents. Characters that are not in the Base16 alphabet but fall within the bounds of the array are translated to -1.
131      */
132     // @formatter:off
133     private static final byte[] LOWER_CASE_DECODE_TABLE = {
134             //  0   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
135             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 00-0f
136             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 10-1f
137             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 20-2f
138              0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, // 30-3f 0-9
139             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 40-4f
140             -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 50-5f
141             -1, 10, 11, 12, 13, 14, 15                                      // 60-66 a-f
142     };
143     // @formatter:on
144     /**
145      * This array is a lookup table that translates 4-bit positive integer index values into their "Base16 Alphabet" lower-case equivalents.
146      */
147     private static final byte[] LOWER_CASE_ENCODE_TABLE = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f' };
148 
149     /** Mask used to extract 4 bits, used when decoding character. */
150     private static final int MASK_4_BITS = 0x0f;
151 
152     /**
153      * Constructs a new builder.
154      *
155      * @return a new builder.
156      * @since 1.20.0
157      */
158     public static Builder builder() {
159         return new Builder();
160     }
161 
162     /**
163      * Constructs a Base16 codec used for decoding and encoding.
164      */
165     public Base16() {
166         this(false);
167     }
168 
169     /**
170      * Constructs a Base16 codec used for decoding and encoding.
171      *
172      * @param lowerCase {@code true} to use the lower-case Base16 alphabet.
173      * @deprecated Use {@link #builder()} and {@link Builder}.
174      */
175     @Deprecated
176     public Base16(final boolean lowerCase) {
177         this(lowerCase, DECODING_POLICY_DEFAULT);
178     }
179 
180     /**
181      * Constructs a Base16 codec used for decoding and encoding.
182      *
183      * @param lowerCase      {@code true} to use the lower-case Base16 alphabet.
184      * @param decodingPolicy Decoding policy.
185      * @deprecated Use {@link #builder()} and {@link Builder}.
186      */
187     @Deprecated
188     public Base16(final boolean lowerCase, final CodecPolicy decodingPolicy) {
189         this(builder().setEncodeTable(lowerCase ? LOWER_CASE_ENCODE_TABLE : UPPER_CASE_ENCODE_TABLE).setDecodingPolicy(decodingPolicy));
190     }
191 
192     private Base16(final Builder builder) {
193         super(builder);
194     }
195 
196     @Override
197     void decode(final byte[] data, int offset, final int length, final Context context) {
198         if (context.eof || length < 0) {
199             context.eof = true;
200             if (context.ibitWorkArea != 0) {
201                 validateTrailingCharacter();
202             }
203             return;
204         }
205         final int dataLen = Math.min(data.length - offset, length);
206         final int availableChars = (context.ibitWorkArea != 0 ? 1 : 0) + dataLen;
207         // small optimization to short-cut the rest of this method when it is fed byte-by-byte
208         if (availableChars == 1 && availableChars == dataLen) {
209             // store 1/2 byte for next invocation of decode, we offset by +1 as empty-value is 0
210             context.ibitWorkArea = decodeOctet(data[offset]) + 1;
211             return;
212         }
213         // we must have an even number of chars to decode
214         final int charsToProcess = availableChars % BYTES_PER_ENCODED_BLOCK == 0 ? availableChars : availableChars - 1;
215         final int end = offset + dataLen;
216         final byte[] buffer = ensureBufferSize(charsToProcess / BYTES_PER_ENCODED_BLOCK, context);
217         int result;
218         if (dataLen < availableChars) {
219             // we have 1/2 byte from previous invocation to decode
220             result = context.ibitWorkArea - 1 << BITS_PER_ENCODED_BYTE;
221             result |= decodeOctet(data[offset++]);
222             buffer[context.pos++] = (byte) result;
223             // reset to empty-value for next invocation!
224             context.ibitWorkArea = 0;
225         }
226         final int loopEnd = end - 1;
227         while (offset < loopEnd) {
228             result = decodeOctet(data[offset++]) << BITS_PER_ENCODED_BYTE;
229             result |= decodeOctet(data[offset++]);
230             buffer[context.pos++] = (byte) result;
231         }
232         // we have one char of a hex-pair left over
233         if (offset < end) {
234             // store 1/2 byte for next invocation of decode, we offset by +1 as empty-value is 0
235             context.ibitWorkArea = decodeOctet(data[offset]) + 1;
236         }
237     }
238 
239     private int decodeOctet(final byte octet) {
240         int decoded = -1;
241         if ((octet & 0xff) < decodeTable.length) {
242             decoded = decodeTable[octet];
243         }
244         if (decoded == -1) {
245             throw new IllegalArgumentException("Invalid octet in encoded value: " + (int) octet);
246         }
247         return decoded;
248     }
249 
250     @Override
251     void encode(final byte[] data, final int offset, final int length, final Context context) {
252         if (context.eof) {
253             return;
254         }
255         if (length < 0) {
256             context.eof = true;
257             return;
258         }
259         final int size = length * BYTES_PER_ENCODED_BLOCK;
260         if (size < 0) {
261             throw new IllegalArgumentException("Input length exceeds maximum size for encoded data: " + length);
262         }
263         final byte[] buffer = ensureBufferSize(size, context);
264         final int end = offset + length;
265         for (int i = offset; i < end; i++) {
266             final int value = data[i];
267             final int high = value >> BITS_PER_ENCODED_BYTE & MASK_4_BITS;
268             final int low = value & MASK_4_BITS;
269             buffer[context.pos++] = encodeTable[high];
270             buffer[context.pos++] = encodeTable[low];
271         }
272     }
273 
274     /**
275      * Returns whether or not the {@code octet} is in the Base16 alphabet.
276      *
277      * @param octet The value to test.
278      * @return {@code true} if the value is defined in the Base16 alphabet {@code false} otherwise.
279      */
280     @Override
281     public boolean isInAlphabet(final byte octet) {
282         return (octet & 0xff) < decodeTable.length && decodeTable[octet] != -1;
283     }
284 
285     /**
286      * Validates whether decoding allows an entire final trailing character that cannot be used for a complete byte.
287      *
288      * @throws IllegalArgumentException if strict decoding is enabled
289      */
290     private void validateTrailingCharacter() {
291         if (isStrictDecoding()) {
292             throw new IllegalArgumentException("Strict decoding: Last encoded character is a valid Base 16 alphabet character but not a possible encoding. " +
293                     "Decoding requires at least two characters to create one byte.");
294         }
295     }
296 }