Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
Base64 |
|
| 2.712121212121212;2.712 | ||||
Base64$CharEncoding |
|
| 2.712121212121212;2.712 | ||||
Base64$Charsets |
|
| 2.712121212121212;2.712 | ||||
Base64$Context |
|
| 2.712121212121212;2.712 | ||||
Base64$StringUtils |
|
| 2.712121212121212;2.712 |
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 | * http://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 ca.uhn.hl7v2.hoh.util.repackage; | |
19 | ||
20 | import java.io.UnsupportedEncodingException; | |
21 | import java.math.BigInteger; | |
22 | import java.nio.charset.Charset; | |
23 | import java.nio.charset.UnsupportedCharsetException; | |
24 | ||
25 | /** | |
26 | * Provides Base64 encoding and decoding as defined by <a | |
27 | * href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a>. | |
28 | * | |
29 | * <p> | |
30 | * This class implements section <cite>6.8. Base64 | |
31 | * Content-Transfer-Encoding</cite> from RFC 2045 <cite>Multipurpose Internet | |
32 | * Mail Extensions (MIME) Part One: Format of Internet Message Bodies</cite> by | |
33 | * Freed and Borenstein. | |
34 | * </p> | |
35 | * <p> | |
36 | * The class can be parameterized in the following manner with various | |
37 | * constructors: | |
38 | * <ul> | |
39 | * <li>URL-safe mode: Default off.</li> | |
40 | * <li>Line length: Default 76. Line length that aren't multiples of 4 will | |
41 | * still essentially end up being multiples of 4 in the encoded data. | |
42 | * <li>Line separator: Default is CRLF ("\r\n")</li> | |
43 | * </ul> | |
44 | * </p> | |
45 | * <p> | |
46 | * Since this class operates directly on byte streams, and not character | |
47 | * streams, it is hard-coded to only encode/decode character encodings which are | |
48 | * compatible with the lower 127 ASCII chart (ISO-8859-1, Windows-1252, UTF-8, | |
49 | * etc). | |
50 | * </p> | |
51 | * <p> | |
52 | * This class is thread-safe. | |
53 | * </p> | |
54 | * | |
55 | * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a> | |
56 | * @author Note that this class has been repackaged from Apache Commons-Codec | |
57 | * and is distributed under the terms of the Apache Software License, | |
58 | * version 2.0 | |
59 | */ | |
60 | public class Base64 { | |
61 | ||
62 | public static void main(String[] args) { | |
63 | ||
64 | 0 | System.out.println("basic " + encodeBase64String("cgta:d@3r$@TTg2446yhhh2h4".getBytes())); |
65 | ||
66 | 0 | } |
67 | ||
68 | /** | |
69 | * BASE32 characters are 6 bits in length. They are formed by taking a block | |
70 | * of 3 octets to form a 24-bit string, which is converted into 4 BASE64 | |
71 | * characters. | |
72 | */ | |
73 | private static final int BITS_PER_ENCODED_BYTE = 6; | |
74 | private static final int BYTES_PER_UNENCODED_BLOCK = 3; | |
75 | private static final int BYTES_PER_ENCODED_BLOCK = 4; | |
76 | ||
77 | /** | |
78 | * Chunk separator per RFC 2045 section 2.1. | |
79 | * | |
80 | * <p> | |
81 | * N.B. The next major release may break compatibility and make this field | |
82 | * private. | |
83 | * </p> | |
84 | * | |
85 | * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section | |
86 | * 2.1</a> | |
87 | */ | |
88 | 5 | static final byte[] CHUNK_SEPARATOR = { '\r', '\n' }; |
89 | ||
90 | /** | |
91 | * This array is a lookup table that translates 6-bit positive integer index | |
92 | * values into their "Base64 Alphabet" equivalents as specified in Table 1 | |
93 | * of RFC 2045. | |
94 | * | |
95 | * Thanks to "commons" project in ws.apache.org for this code. | |
96 | * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ | |
97 | */ | |
98 | 5 | private static final byte[] STANDARD_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', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', |
99 | 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '+', '/' }; | |
100 | ||
101 | /** | |
102 | * This is a copy of the STANDARD_ENCODE_TABLE above, but with + and / | |
103 | * changed to - and _ to make the encoded Base64 results more URL-SAFE. This | |
104 | * table is only used when the Base64's mode is set to URL-SAFE. | |
105 | */ | |
106 | 5 | private static final byte[] URL_SAFE_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', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', |
107 | 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '-', '_' }; | |
108 | ||
109 | /** | |
110 | * This array is a lookup table that translates Unicode characters drawn | |
111 | * from the "Base64 Alphabet" (as specified in Table 1 of RFC 2045) into | |
112 | * their 6-bit positive integer equivalents. Characters that are not in the | |
113 | * Base64 alphabet but fall within the bounds of the array are translated to | |
114 | * -1. | |
115 | * | |
116 | * Note: '+' and '-' both decode to 62. '/' and '_' both decode to 63. This | |
117 | * means decoder seamlessly handles both URL_SAFE and STANDARD base64. (The | |
118 | * encoder, on the other hand, needs to know ahead of time what to emit). | |
119 | * | |
120 | * Thanks to "commons" project in ws.apache.org for this code. | |
121 | * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ | |
122 | */ | |
123 | 5 | private static final byte[] DECODE_TABLE = { -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, 62, -1, 63, 52, 53, 54, 55, 56, 57, 58, 59, 60, |
124 | 61, -1, -1, -1, -1, -1, -1, -1, 0, 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, -1, -1, -1, -1, 63, -1, 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 }; | |
125 | ||
126 | /** | |
127 | * Base64 uses 6-bit fields. | |
128 | */ | |
129 | /** Mask used to extract 6 bits, used when encoding */ | |
130 | private static final int MASK_6BITS = 0x3f; | |
131 | ||
132 | // The static final fields above are used for the original static byte[] | |
133 | // methods on Base64. | |
134 | // The private member fields below are used with the new streaming approach, | |
135 | // which requires | |
136 | // some state be preserved between calls of encode() and decode(). | |
137 | ||
138 | /** | |
139 | * Encode table to use: either STANDARD or URL_SAFE. Note: the DECODE_TABLE | |
140 | * above remains static because it is able to decode both STANDARD and | |
141 | * URL_SAFE streams, but the encodeTable must be a member variable so we can | |
142 | * switch between the two modes. | |
143 | */ | |
144 | private byte[] encodeTable; | |
145 | ||
146 | // Only one decode table currently; keep for consistency with Base32 code | |
147 | 495 | private final byte[] decodeTable = DECODE_TABLE; |
148 | ||
149 | /** | |
150 | * Line separator for encoding. Not used when decoding. Only used if | |
151 | * lineLength > 0. | |
152 | */ | |
153 | private byte[] lineSeparator; | |
154 | ||
155 | /** | |
156 | * Convenience variable to help us determine when our buffer is going to run | |
157 | * out of room and needs resizing. | |
158 | * <code>decodeSize = 3 + lineSeparator.length;</code> | |
159 | */ | |
160 | private int decodeSize; | |
161 | ||
162 | /** | |
163 | * Convenience variable to help us determine when our buffer is going to run | |
164 | * out of room and needs resizing. | |
165 | * <code>encodeSize = 4 + lineSeparator.length;</code> | |
166 | */ | |
167 | private int encodeSize; | |
168 | ||
169 | /** | |
170 | * Creates a Base64 codec used for decoding (all modes) and encoding in | |
171 | * URL-unsafe mode. | |
172 | * <p> | |
173 | * When encoding the line length is 0 (no chunking), and the encoding table | |
174 | * is STANDARD_ENCODE_TABLE. | |
175 | * </p> | |
176 | * | |
177 | * <p> | |
178 | * When decoding all variants are supported. | |
179 | * </p> | |
180 | */ | |
181 | public Base64() { | |
182 | 265 | this(0); |
183 | 265 | } |
184 | ||
185 | /** | |
186 | * Creates a Base64 codec used for decoding (all modes) and encoding in the | |
187 | * given URL-safe mode. | |
188 | * <p> | |
189 | * When encoding the line length is 76, the line separator is CRLF, and the | |
190 | * encoding table is STANDARD_ENCODE_TABLE. | |
191 | * </p> | |
192 | * | |
193 | * <p> | |
194 | * When decoding all variants are supported. | |
195 | * </p> | |
196 | * | |
197 | * @param urlSafe | |
198 | * if {@code true}, URL-safe encoding is used. In most cases this | |
199 | * should be set to {@code false}. | |
200 | * @since 1.4 | |
201 | */ | |
202 | public Base64(boolean urlSafe) { | |
203 | 0 | this(MIME_CHUNK_SIZE, CHUNK_SEPARATOR, urlSafe); |
204 | 0 | } |
205 | ||
206 | /** | |
207 | * Creates a Base64 codec used for decoding (all modes) and encoding in | |
208 | * URL-unsafe mode. | |
209 | * <p> | |
210 | * When encoding the line length is given in the constructor, the line | |
211 | * separator is CRLF, and the encoding table is STANDARD_ENCODE_TABLE. | |
212 | * </p> | |
213 | * <p> | |
214 | * Line lengths that aren't multiples of 4 will still essentially end up | |
215 | * being multiples of 4 in the encoded data. | |
216 | * </p> | |
217 | * <p> | |
218 | * When decoding all variants are supported. | |
219 | * </p> | |
220 | * | |
221 | * @param lineLength | |
222 | * Each line of encoded data will be at most of the given length | |
223 | * (rounded down to nearest multiple of 4). If lineLength <= 0, | |
224 | * then the output will not be divided into lines (chunks). | |
225 | * Ignored when decoding. | |
226 | * @since 1.4 | |
227 | */ | |
228 | public Base64(int lineLength) { | |
229 | 265 | this(lineLength, CHUNK_SEPARATOR); |
230 | 265 | } |
231 | ||
232 | /** | |
233 | * Creates a Base64 codec used for decoding (all modes) and encoding in | |
234 | * URL-unsafe mode. | |
235 | * <p> | |
236 | * When encoding the line length and line separator are given in the | |
237 | * constructor, and the encoding table is STANDARD_ENCODE_TABLE. | |
238 | * </p> | |
239 | * <p> | |
240 | * Line lengths that aren't multiples of 4 will still essentially end up | |
241 | * being multiples of 4 in the encoded data. | |
242 | * </p> | |
243 | * <p> | |
244 | * When decoding all variants are supported. | |
245 | * </p> | |
246 | * | |
247 | * @param lineLength | |
248 | * Each line of encoded data will be at most of the given length | |
249 | * (rounded down to nearest multiple of 4). If lineLength <= 0, | |
250 | * then the output will not be divided into lines (chunks). | |
251 | * Ignored when decoding. | |
252 | * @param lineSeparator | |
253 | * Each line of encoded data will end with this sequence of | |
254 | * bytes. | |
255 | * @throws IllegalArgumentException | |
256 | * Thrown when the provided lineSeparator included some base64 | |
257 | * characters. | |
258 | * @since 1.4 | |
259 | */ | |
260 | public Base64(int lineLength, byte[] lineSeparator) { | |
261 | 265 | this(lineLength, lineSeparator, false); |
262 | 265 | } |
263 | ||
264 | /** | |
265 | * Creates a Base64 codec used for decoding (all modes) and encoding in | |
266 | * URL-unsafe mode. | |
267 | * <p> | |
268 | * When encoding the line length and line separator are given in the | |
269 | * constructor, and the encoding table is STANDARD_ENCODE_TABLE. | |
270 | * </p> | |
271 | * <p> | |
272 | * Line lengths that aren't multiples of 4 will still essentially end up | |
273 | * being multiples of 4 in the encoded data. | |
274 | * </p> | |
275 | * <p> | |
276 | * When decoding all variants are supported. | |
277 | * </p> | |
278 | * | |
279 | * @param lineLength | |
280 | * Each line of encoded data will be at most of the given length | |
281 | * (rounded down to nearest multiple of 4). If lineLength <= 0, | |
282 | * then the output will not be divided into lines (chunks). | |
283 | * Ignored when decoding. | |
284 | * @param lineSeparator | |
285 | * Each line of encoded data will end with this sequence of | |
286 | * bytes. | |
287 | * @param urlSafe | |
288 | * Instead of emitting '+' and '/' we emit '-' and '_' | |
289 | * respectively. urlSafe is only applied to encode operations. | |
290 | * Decoding seamlessly handles both modes. | |
291 | * @throws IllegalArgumentException | |
292 | * The provided lineSeparator included some base64 characters. | |
293 | * That's not going to work! | |
294 | * @since 1.4 | |
295 | */ | |
296 | public Base64(int lineLength, byte[] lineSeparator, boolean urlSafe) { | |
297 | 495 | this(BYTES_PER_UNENCODED_BLOCK, BYTES_PER_ENCODED_BLOCK, lineLength, lineSeparator == null ? 0 : lineSeparator.length); |
298 | // TODO could be simplified if there is no requirement to reject invalid | |
299 | // line sep when length <=0 | |
300 | // @see test case Base64Test.testConstructors() | |
301 | 495 | if (lineSeparator != null) { |
302 | 495 | if (containsAlphabetOrPad(lineSeparator)) { |
303 | 0 | String sep = StringUtils.newStringUtf8(lineSeparator); |
304 | 0 | throw new IllegalArgumentException("lineSeparator must not contain base64 characters: [" + sep + "]"); |
305 | } | |
306 | 495 | if (lineLength > 0) { // null line-sep forces no chunking rather |
307 | // than throwing IAE | |
308 | 0 | this.encodeSize = BYTES_PER_ENCODED_BLOCK + lineSeparator.length; |
309 | 0 | this.lineSeparator = new byte[lineSeparator.length]; |
310 | 0 | System.arraycopy(lineSeparator, 0, this.lineSeparator, 0, lineSeparator.length); |
311 | } else { | |
312 | 495 | this.encodeSize = BYTES_PER_ENCODED_BLOCK; |
313 | 495 | this.lineSeparator = null; |
314 | } | |
315 | } else { | |
316 | 0 | this.encodeSize = BYTES_PER_ENCODED_BLOCK; |
317 | 0 | this.lineSeparator = null; |
318 | } | |
319 | 495 | this.decodeSize = this.encodeSize - 1; |
320 | 495 | this.encodeTable = urlSafe ? URL_SAFE_ENCODE_TABLE : STANDARD_ENCODE_TABLE; |
321 | 495 | } |
322 | ||
323 | /** | |
324 | * Returns our current encode mode. True if we're URL-SAFE, false otherwise. | |
325 | * | |
326 | * @return true if we're in URL-SAFE mode, false otherwise. | |
327 | * @since 1.4 | |
328 | */ | |
329 | public boolean isUrlSafe() { | |
330 | 0 | return this.encodeTable == URL_SAFE_ENCODE_TABLE; |
331 | } | |
332 | ||
333 | /** | |
334 | * <p> | |
335 | * Encodes all of the provided data, starting at inPos, for inAvail bytes. | |
336 | * Must be called at least twice: once with the data to encode, and once | |
337 | * with inAvail set to "-1" to alert encoder that EOF has been reached, so | |
338 | * flush last remaining bytes (if not multiple of 3). | |
339 | * </p> | |
340 | * <p> | |
341 | * Thanks to "commons" project in ws.apache.org for the bitwise operations, | |
342 | * and general approach. | |
343 | * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ | |
344 | * </p> | |
345 | * | |
346 | * @param in | |
347 | * byte[] array of binary data to base64 encode. | |
348 | * @param inPos | |
349 | * Position to start reading data from. | |
350 | * @param inAvail | |
351 | * Amount of bytes available from input for encoding. | |
352 | * @param context | |
353 | * the context to be used | |
354 | */ | |
355 | void encode(byte[] in, int inPos, int inAvail, Context context) { | |
356 | 460 | if (context.eof) { |
357 | 0 | return; |
358 | } | |
359 | // inAvail < 0 is how we're informed of EOF in the underlying data we're | |
360 | // encoding. | |
361 | 460 | if (inAvail < 0) { |
362 | 230 | context.eof = true; |
363 | 230 | if (0 == context.modulus && lineLength == 0) { |
364 | 155 | return; // no leftovers to process and not using chunking |
365 | } | |
366 | 75 | ensureBufferSize(encodeSize, context); |
367 | 75 | int savedPos = context.pos; |
368 | 75 | switch (context.modulus) { // 0-2 |
369 | case 1: // 8 bits = 6 + 2 | |
370 | 0 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 2) & MASK_6BITS]; // top |
371 | // 6 | |
372 | // bits | |
373 | 0 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea << 4) & MASK_6BITS]; // remaining |
374 | // 2 | |
375 | // URL-SAFE skips the padding to further reduce size. | |
376 | 0 | if (encodeTable == STANDARD_ENCODE_TABLE) { |
377 | 0 | context.buffer[context.pos++] = PAD; |
378 | 0 | context.buffer[context.pos++] = PAD; |
379 | } | |
380 | break; | |
381 | ||
382 | case 2: // 16 bits = 6 + 6 + 4 | |
383 | 75 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 10) & MASK_6BITS]; |
384 | 75 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 4) & MASK_6BITS]; |
385 | 75 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea << 2) & MASK_6BITS]; |
386 | // URL-SAFE skips the padding to further reduce size. | |
387 | 75 | if (encodeTable == STANDARD_ENCODE_TABLE) { |
388 | 75 | context.buffer[context.pos++] = PAD; |
389 | } | |
390 | break; | |
391 | } | |
392 | 75 | context.currentLinePos += context.pos - savedPos; // keep track of |
393 | // current line | |
394 | // position | |
395 | // if currentPos == 0 we are at the start of a line, so don't add | |
396 | // CRLF | |
397 | 75 | if (lineLength > 0 && context.currentLinePos > 0) { |
398 | 0 | System.arraycopy(lineSeparator, 0, context.buffer, context.pos, lineSeparator.length); |
399 | 0 | context.pos += lineSeparator.length; |
400 | } | |
401 | 75 | } else { |
402 | 39830 | for (int i = 0; i < inAvail; i++) { |
403 | 39600 | ensureBufferSize(encodeSize, context); |
404 | 39600 | context.modulus = (context.modulus + 1) % BYTES_PER_UNENCODED_BLOCK; |
405 | 39600 | int b = in[inPos++]; |
406 | 39600 | if (b < 0) { |
407 | 12068 | b += 256; |
408 | } | |
409 | 39600 | context.ibitWorkArea = (context.ibitWorkArea << 8) + b; // BITS_PER_BYTE |
410 | 39600 | if (0 == context.modulus) { // 3 bytes = 24 bits = 4 * 6 bits to |
411 | // extract | |
412 | 13150 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 18) & MASK_6BITS]; |
413 | 13150 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 12) & MASK_6BITS]; |
414 | 13150 | context.buffer[context.pos++] = encodeTable[(context.ibitWorkArea >> 6) & MASK_6BITS]; |
415 | 13150 | context.buffer[context.pos++] = encodeTable[context.ibitWorkArea & MASK_6BITS]; |
416 | 13150 | context.currentLinePos += BYTES_PER_ENCODED_BLOCK; |
417 | 13150 | if (lineLength > 0 && lineLength <= context.currentLinePos) { |
418 | 0 | System.arraycopy(lineSeparator, 0, context.buffer, context.pos, lineSeparator.length); |
419 | 0 | context.pos += lineSeparator.length; |
420 | 0 | context.currentLinePos = 0; |
421 | } | |
422 | } | |
423 | } | |
424 | } | |
425 | 305 | } |
426 | ||
427 | /** | |
428 | * <p> | |
429 | * Decodes all of the provided data, starting at inPos, for inAvail bytes. | |
430 | * Should be called at least twice: once with the data to decode, and once | |
431 | * with inAvail set to "-1" to alert decoder that EOF has been reached. The | |
432 | * "-1" call is not necessary when decoding, but it doesn't hurt, either. | |
433 | * </p> | |
434 | * <p> | |
435 | * Ignores all non-base64 characters. This is how chunked (e.g. 76 | |
436 | * character) data is handled, since CR and LF are silently ignored, but has | |
437 | * implications for other bytes, too. This method subscribes to the | |
438 | * garbage-in, garbage-out philosophy: it will not check the provided data | |
439 | * for validity. | |
440 | * </p> | |
441 | * <p> | |
442 | * Thanks to "commons" project in ws.apache.org for the bitwise operations, | |
443 | * and general approach. | |
444 | * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ | |
445 | * </p> | |
446 | * | |
447 | * @param in | |
448 | * byte[] array of ascii data to base64 decode. | |
449 | * @param inPos | |
450 | * Position to start reading data from. | |
451 | * @param inAvail | |
452 | * Amount of bytes available from input for encoding. | |
453 | * @param context | |
454 | * the context to be used | |
455 | */ | |
456 | void decode(byte[] in, int inPos, int inAvail, Context context) { | |
457 | 530 | if (context.eof) { |
458 | 125 | return; |
459 | } | |
460 | 405 | if (inAvail < 0) { |
461 | 140 | context.eof = true; |
462 | } | |
463 | 34240 | for (int i = 0; i < inAvail; i++) { |
464 | 33960 | ensureBufferSize(decodeSize, context); |
465 | 33960 | byte b = in[inPos++]; |
466 | 33960 | if (b == PAD) { |
467 | // We're done. | |
468 | 125 | context.eof = true; |
469 | 125 | break; |
470 | } else { | |
471 | 33835 | if (b >= 0 && b < DECODE_TABLE.length) { |
472 | 33835 | int result = DECODE_TABLE[b]; |
473 | 33835 | if (result >= 0) { |
474 | 33835 | context.modulus = (context.modulus + 1) % BYTES_PER_ENCODED_BLOCK; |
475 | 33835 | context.ibitWorkArea = (context.ibitWorkArea << BITS_PER_ENCODED_BYTE) + result; |
476 | 33835 | if (context.modulus == 0) { |
477 | 8365 | context.buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 16) & MASK_8BITS); |
478 | 8365 | context.buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 8) & MASK_8BITS); |
479 | 8365 | context.buffer[context.pos++] = (byte) (context.ibitWorkArea & MASK_8BITS); |
480 | } | |
481 | } | |
482 | } | |
483 | } | |
484 | } | |
485 | ||
486 | // Two forms of EOF as far as base64 decoder is concerned: actual | |
487 | // EOF (-1) and first time '=' character is encountered in stream. | |
488 | // This approach makes the '=' padding characters completely optional. | |
489 | 405 | if (context.eof && context.modulus != 0) { |
490 | 125 | ensureBufferSize(decodeSize, context); |
491 | ||
492 | // We have some spare bits remaining | |
493 | // Output all whole multiples of 8 bits and ignore the rest | |
494 | 125 | switch (context.modulus) { |
495 | // case 1: // 6 bits - ignore entirely | |
496 | // break; | |
497 | case 2: // 12 bits = 8 + 4 | |
498 | 0 | context.ibitWorkArea = context.ibitWorkArea >> 4; // dump the |
499 | // extra 4 | |
500 | // bits | |
501 | 0 | context.buffer[context.pos++] = (byte) ((context.ibitWorkArea) & MASK_8BITS); |
502 | 0 | break; |
503 | case 3: // 18 bits = 8 + 8 + 2 | |
504 | 125 | context.ibitWorkArea = context.ibitWorkArea >> 2; // dump 2 bits |
505 | 125 | context.buffer[context.pos++] = (byte) ((context.ibitWorkArea >> 8) & MASK_8BITS); |
506 | 125 | context.buffer[context.pos++] = (byte) ((context.ibitWorkArea) & MASK_8BITS); |
507 | break; | |
508 | } | |
509 | } | |
510 | 405 | } |
511 | ||
512 | /** | |
513 | * Tests a given byte array to see if it contains only valid characters | |
514 | * within the Base64 alphabet. Currently the method treats whitespace as | |
515 | * valid. | |
516 | * | |
517 | * @param arrayOctet | |
518 | * byte array to test | |
519 | * @return {@code true} if all bytes are valid characters in the Base64 | |
520 | * alphabet or if the byte array is empty; {@code false}, otherwise | |
521 | * @deprecated 1.5 Use {@link #isBase64(byte[])}, will be removed in 2.0. | |
522 | */ | |
523 | @Deprecated | |
524 | public static boolean isArrayByteBase64(byte[] arrayOctet) { | |
525 | 0 | return isBase64(arrayOctet); |
526 | } | |
527 | ||
528 | /** | |
529 | * Returns whether or not the <code>octet</code> is in the base 64 alphabet. | |
530 | * | |
531 | * @param octet | |
532 | * The value to test | |
533 | * @return {@code true} if the value is defined in the the base 64 alphabet, | |
534 | * {@code false} otherwise. | |
535 | * @since 1.4 | |
536 | */ | |
537 | public static boolean isBase64(byte octet) { | |
538 | 0 | return octet == PAD_DEFAULT || (octet >= 0 && octet < DECODE_TABLE.length && DECODE_TABLE[octet] != -1); |
539 | } | |
540 | ||
541 | /** | |
542 | * Tests a given String to see if it contains only valid characters within | |
543 | * the Base64 alphabet. Currently the method treats whitespace as valid. | |
544 | * | |
545 | * @param base64 | |
546 | * String to test | |
547 | * @return {@code true} if all characters in the String are valid characters | |
548 | * in the Base64 alphabet or if the String is empty; {@code false}, | |
549 | * otherwise | |
550 | * @since 1.5 | |
551 | */ | |
552 | public static boolean isBase64(String base64) { | |
553 | 0 | return isBase64(StringUtils.getBytesUtf8(base64)); |
554 | } | |
555 | ||
556 | /** | |
557 | * Tests a given byte array to see if it contains only valid characters | |
558 | * within the Base64 alphabet. Currently the method treats whitespace as | |
559 | * valid. | |
560 | * | |
561 | * @param arrayOctet | |
562 | * byte array to test | |
563 | * @return {@code true} if all bytes are valid characters in the Base64 | |
564 | * alphabet or if the byte array is empty; {@code false}, otherwise | |
565 | * @since 1.5 | |
566 | */ | |
567 | public static boolean isBase64(byte[] arrayOctet) { | |
568 | 0 | for (int i = 0; i < arrayOctet.length; i++) { |
569 | 0 | if (!isBase64(arrayOctet[i]) && !isWhiteSpace(arrayOctet[i])) { |
570 | 0 | return false; |
571 | } | |
572 | } | |
573 | 0 | return true; |
574 | } | |
575 | ||
576 | /** | |
577 | * Encodes binary data using the base64 algorithm but does not chunk the | |
578 | * output. | |
579 | * | |
580 | * @param binaryData | |
581 | * binary data to encode | |
582 | * @return byte[] containing Base64 characters in their UTF-8 | |
583 | * representation. | |
584 | */ | |
585 | public static byte[] encodeBase64(byte[] binaryData) { | |
586 | 0 | return encodeBase64(binaryData, false); |
587 | } | |
588 | ||
589 | /** | |
590 | * Encodes binary data using the base64 algorithm but does not chunk the | |
591 | * output. | |
592 | * | |
593 | * NOTE: We changed the behaviour of this method from multi-line chunking | |
594 | * (commons-codec-1.4) to single-line non-chunking (commons-codec-1.5). | |
595 | * | |
596 | * @param binaryData | |
597 | * binary data to encode | |
598 | * @return String containing Base64 characters. | |
599 | * @since 1.4 (NOTE: 1.4 chunked the output, whereas 1.5 does not). | |
600 | */ | |
601 | public static String encodeBase64String(byte[] binaryData) { | |
602 | 230 | return StringUtils.newStringUtf8(encodeBase64(binaryData, false)); |
603 | } | |
604 | ||
605 | /** | |
606 | * Encodes binary data using a URL-safe variation of the base64 algorithm | |
607 | * but does not chunk the output. The url-safe variation emits - and _ | |
608 | * instead of + and / characters. | |
609 | * | |
610 | * @param binaryData | |
611 | * binary data to encode | |
612 | * @return byte[] containing Base64 characters in their UTF-8 | |
613 | * representation. | |
614 | * @since 1.4 | |
615 | */ | |
616 | public static byte[] encodeBase64URLSafe(byte[] binaryData) { | |
617 | 0 | return encodeBase64(binaryData, false, true); |
618 | } | |
619 | ||
620 | /** | |
621 | * Encodes binary data using a URL-safe variation of the base64 algorithm | |
622 | * but does not chunk the output. The url-safe variation emits - and _ | |
623 | * instead of + and / characters. | |
624 | * | |
625 | * @param binaryData | |
626 | * binary data to encode | |
627 | * @return String containing Base64 characters | |
628 | * @since 1.4 | |
629 | */ | |
630 | public static String encodeBase64URLSafeString(byte[] binaryData) { | |
631 | 0 | return StringUtils.newStringUtf8(encodeBase64(binaryData, false, true)); |
632 | } | |
633 | ||
634 | /** | |
635 | * Encodes binary data using the base64 algorithm and chunks the encoded | |
636 | * output into 76 character blocks | |
637 | * | |
638 | * @param binaryData | |
639 | * binary data to encode | |
640 | * @return Base64 characters chunked in 76 character blocks | |
641 | */ | |
642 | public static byte[] encodeBase64Chunked(byte[] binaryData) { | |
643 | 0 | return encodeBase64(binaryData, true); |
644 | } | |
645 | ||
646 | /** | |
647 | * Encodes binary data using the base64 algorithm, optionally chunking the | |
648 | * output into 76 character blocks. | |
649 | * | |
650 | * @param binaryData | |
651 | * Array containing binary data to encode. | |
652 | * @param isChunked | |
653 | * if {@code true} this encoder will chunk the base64 output into | |
654 | * 76 character blocks | |
655 | * @return Base64-encoded data. | |
656 | * @throws IllegalArgumentException | |
657 | * Thrown when the input array needs an output array bigger than | |
658 | * {@link Integer#MAX_VALUE} | |
659 | */ | |
660 | public static byte[] encodeBase64(byte[] binaryData, boolean isChunked) { | |
661 | 230 | return encodeBase64(binaryData, isChunked, false); |
662 | } | |
663 | ||
664 | /** | |
665 | * Encodes binary data using the base64 algorithm, optionally chunking the | |
666 | * output into 76 character blocks. | |
667 | * | |
668 | * @param binaryData | |
669 | * Array containing binary data to encode. | |
670 | * @param isChunked | |
671 | * if {@code true} this encoder will chunk the base64 output into | |
672 | * 76 character blocks | |
673 | * @param urlSafe | |
674 | * if {@code true} this encoder will emit - and _ instead of the | |
675 | * usual + and / characters. | |
676 | * @return Base64-encoded data. | |
677 | * @throws IllegalArgumentException | |
678 | * Thrown when the input array needs an output array bigger than | |
679 | * {@link Integer#MAX_VALUE} | |
680 | * @since 1.4 | |
681 | */ | |
682 | public static byte[] encodeBase64(byte[] binaryData, boolean isChunked, boolean urlSafe) { | |
683 | 230 | return encodeBase64(binaryData, isChunked, urlSafe, Integer.MAX_VALUE); |
684 | } | |
685 | ||
686 | /** | |
687 | * Encodes binary data using the base64 algorithm, optionally chunking the | |
688 | * output into 76 character blocks. | |
689 | * | |
690 | * @param binaryData | |
691 | * Array containing binary data to encode. | |
692 | * @param isChunked | |
693 | * if {@code true} this encoder will chunk the base64 output into | |
694 | * 76 character blocks | |
695 | * @param urlSafe | |
696 | * if {@code true} this encoder will emit - and _ instead of the | |
697 | * usual + and / characters. | |
698 | * @param maxResultSize | |
699 | * The maximum result size to accept. | |
700 | * @return Base64-encoded data. | |
701 | * @throws IllegalArgumentException | |
702 | * Thrown when the input array needs an output array bigger than | |
703 | * maxResultSize | |
704 | * @since 1.4 | |
705 | */ | |
706 | public static byte[] encodeBase64(byte[] binaryData, boolean isChunked, boolean urlSafe, int maxResultSize) { | |
707 | 230 | if (binaryData == null || binaryData.length == 0) { |
708 | 0 | return binaryData; |
709 | } | |
710 | ||
711 | // Create this so can use the super-class method | |
712 | // Also ensures that the same roundings are performed by the ctor and | |
713 | // the code | |
714 | 230 | Base64 b64 = isChunked ? new Base64(urlSafe) : new Base64(0, CHUNK_SEPARATOR, urlSafe); |
715 | 230 | long len = b64.getEncodedLength(binaryData); |
716 | 230 | if (len > maxResultSize) { |
717 | 0 | throw new IllegalArgumentException("Input array too big, the output array would be bigger (" + len + ") than the specified maximum size of " + maxResultSize); |
718 | } | |
719 | ||
720 | 230 | return b64.encode(binaryData); |
721 | } | |
722 | ||
723 | /** | |
724 | * Decodes a Base64 String into octets | |
725 | * | |
726 | * @param base64String | |
727 | * String containing Base64 data | |
728 | * @return Array containing decoded data. | |
729 | * @since 1.4 | |
730 | */ | |
731 | public static byte[] decodeBase64(String base64String) { | |
732 | 265 | return new Base64().decode(base64String); |
733 | } | |
734 | ||
735 | /** | |
736 | * Decodes Base64 data into octets | |
737 | * | |
738 | * @param base64Data | |
739 | * Byte array containing Base64 data | |
740 | * @return Array containing decoded data. | |
741 | */ | |
742 | public static byte[] decodeBase64(byte[] base64Data) { | |
743 | 0 | return new Base64().decode(base64Data); |
744 | } | |
745 | ||
746 | // Implementation of the Encoder Interface | |
747 | ||
748 | // Implementation of integer encoding used for crypto | |
749 | /** | |
750 | * Decodes a byte64-encoded integer according to crypto standards such as | |
751 | * W3C's XML-Signature | |
752 | * | |
753 | * @param pArray | |
754 | * a byte array containing base64 character data | |
755 | * @return A BigInteger | |
756 | * @since 1.4 | |
757 | */ | |
758 | public static BigInteger decodeInteger(byte[] pArray) { | |
759 | 0 | return new BigInteger(1, decodeBase64(pArray)); |
760 | } | |
761 | ||
762 | /** | |
763 | * Encodes to a byte64-encoded integer according to crypto standards such as | |
764 | * W3C's XML-Signature | |
765 | * | |
766 | * @param bigInt | |
767 | * a BigInteger | |
768 | * @return A byte array containing base64 character data | |
769 | * @throws NullPointerException | |
770 | * if null is passed in | |
771 | * @since 1.4 | |
772 | */ | |
773 | public static byte[] encodeInteger(BigInteger bigInt) { | |
774 | 0 | if (bigInt == null) { |
775 | 0 | throw new NullPointerException("encodeInteger called with null parameter"); |
776 | } | |
777 | 0 | return encodeBase64(toIntegerBytes(bigInt), false); |
778 | } | |
779 | ||
780 | /** | |
781 | * Returns a byte-array representation of a <code>BigInteger</code> without | |
782 | * sign bit. | |
783 | * | |
784 | * @param bigInt | |
785 | * <code>BigInteger</code> to be converted | |
786 | * @return a byte array representation of the BigInteger parameter | |
787 | */ | |
788 | static byte[] toIntegerBytes(BigInteger bigInt) { | |
789 | 0 | int bitlen = bigInt.bitLength(); |
790 | // round bitlen | |
791 | 0 | bitlen = ((bitlen + 7) >> 3) << 3; |
792 | 0 | byte[] bigBytes = bigInt.toByteArray(); |
793 | ||
794 | 0 | if (((bigInt.bitLength() % 8) != 0) && (((bigInt.bitLength() / 8) + 1) == (bitlen / 8))) { |
795 | 0 | return bigBytes; |
796 | } | |
797 | // set up params for copying everything but sign bit | |
798 | 0 | int startSrc = 0; |
799 | 0 | int len = bigBytes.length; |
800 | ||
801 | // if bigInt is exactly byte-aligned, just skip signbit in copy | |
802 | 0 | if ((bigInt.bitLength() % 8) == 0) { |
803 | 0 | startSrc = 1; |
804 | 0 | len--; |
805 | } | |
806 | 0 | int startDst = bitlen / 8 - len; // to pad w/ nulls as per spec |
807 | 0 | byte[] resizedBytes = new byte[bitlen / 8]; |
808 | 0 | System.arraycopy(bigBytes, startSrc, resizedBytes, startDst, len); |
809 | 0 | return resizedBytes; |
810 | } | |
811 | ||
812 | /** | |
813 | * Returns whether or not the <code>octet</code> is in the Base32 alphabet. | |
814 | * | |
815 | * @param octet | |
816 | * The value to test | |
817 | * @return {@code true} if the value is defined in the the Base32 alphabet | |
818 | * {@code false} otherwise. | |
819 | */ | |
820 | protected boolean isInAlphabet(byte octet) { | |
821 | 990 | return octet >= 0 && octet < decodeTable.length && decodeTable[octet] != -1; |
822 | } | |
823 | ||
824 | /** | |
825 | * Holds thread context so classes can be thread-safe. | |
826 | * | |
827 | * This class is not itself thread-safe; each thread must allocate its own | |
828 | * copy. | |
829 | * | |
830 | * @since 1.7 | |
831 | */ | |
832 | static class Context { | |
833 | ||
834 | /** | |
835 | * Place holder for the bytes we're dealing with for our based logic. | |
836 | * Bitwise operations store and extract the encoding or decoding from | |
837 | * this variable. | |
838 | */ | |
839 | int ibitWorkArea; | |
840 | ||
841 | /** | |
842 | * Place holder for the bytes we're dealing with for our based logic. | |
843 | * Bitwise operations store and extract the encoding or decoding from | |
844 | * this variable. | |
845 | */ | |
846 | long lbitWorkArea; | |
847 | ||
848 | /** | |
849 | * Buffer for streaming. | |
850 | */ | |
851 | byte[] buffer; | |
852 | ||
853 | /** | |
854 | * Position where next character should be written in the buffer. | |
855 | */ | |
856 | int pos; | |
857 | ||
858 | /** | |
859 | * Position where next character should be read from the buffer. | |
860 | */ | |
861 | int readPos; | |
862 | ||
863 | /** | |
864 | * Boolean flag to indicate the EOF has been reached. Once EOF has been | |
865 | * reached, this object becomes useless, and must be thrown away. | |
866 | */ | |
867 | boolean eof; | |
868 | ||
869 | /** | |
870 | * Variable tracks how many characters have been written to the current | |
871 | * line. Only used when encoding. We use it to make sure each encoded | |
872 | * line never goes beyond lineLength (if lineLength > 0). | |
873 | */ | |
874 | int currentLinePos; | |
875 | ||
876 | /** | |
877 | * Writes to the buffer only occur after every 3/5 reads when encoding, | |
878 | * and every 4/8 reads when decoding. This variable helps track that. | |
879 | */ | |
880 | int modulus; | |
881 | ||
882 | 495 | Context() { |
883 | 495 | } |
884 | } | |
885 | ||
886 | /** | |
887 | * EOF | |
888 | * | |
889 | * @since 1.7 | |
890 | */ | |
891 | static final int EOF = -1; | |
892 | ||
893 | /** | |
894 | * MIME chunk size per RFC 2045 section 6.8. | |
895 | * | |
896 | * <p> | |
897 | * The {@value} character limit does not count the trailing CRLF, but counts | |
898 | * all other characters, including any equal signs. | |
899 | * </p> | |
900 | * | |
901 | * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section | |
902 | * 6.8</a> | |
903 | */ | |
904 | public static final int MIME_CHUNK_SIZE = 76; | |
905 | ||
906 | /** | |
907 | * PEM chunk size per RFC 1421 section 4.3.2.4. | |
908 | * | |
909 | * <p> | |
910 | * The {@value} character limit does not count the trailing CRLF, but counts | |
911 | * all other characters, including any equal signs. | |
912 | * </p> | |
913 | * | |
914 | * @see <a href="http://tools.ietf.org/html/rfc1421">RFC 1421 section | |
915 | * 4.3.2.4</a> | |
916 | */ | |
917 | public static final int PEM_CHUNK_SIZE = 64; | |
918 | ||
919 | private static final int DEFAULT_BUFFER_RESIZE_FACTOR = 2; | |
920 | ||
921 | /** | |
922 | * Defines the default buffer size - currently {@value} - must be large | |
923 | * enough for at least one encoded block+separator | |
924 | */ | |
925 | private static final int DEFAULT_BUFFER_SIZE = 8192; | |
926 | ||
927 | /** Mask used to extract 8 bits, used in decoding bytes */ | |
928 | protected static final int MASK_8BITS = 0xff; | |
929 | ||
930 | /** | |
931 | * Byte used to pad output. | |
932 | */ | |
933 | protected static final byte PAD_DEFAULT = '='; // Allow static access to | |
934 | // default | |
935 | ||
936 | 495 | protected final byte PAD = PAD_DEFAULT; // instance variable just in case it |
937 | // needs to vary later | |
938 | ||
939 | /** | |
940 | * Number of bytes in each full block of unencoded data, e.g. 4 for Base64 | |
941 | * and 5 for Base32 | |
942 | */ | |
943 | private final int unencodedBlockSize; | |
944 | ||
945 | /** | |
946 | * Number of bytes in each full block of encoded data, e.g. 3 for Base64 and | |
947 | * 8 for Base32 | |
948 | */ | |
949 | private final int encodedBlockSize; | |
950 | ||
951 | /** | |
952 | * Chunksize for encoding. Not used when decoding. A value of zero or less | |
953 | * implies no chunking of the encoded data. Rounded down to nearest multiple | |
954 | * of encodedBlockSize. | |
955 | */ | |
956 | protected int lineLength; | |
957 | ||
958 | /** | |
959 | * Size of chunk separator. Not used unless {@link #lineLength} > 0. | |
960 | */ | |
961 | private int chunkSeparatorLength; | |
962 | ||
963 | /** | |
964 | * Note <code>lineLength</code> is rounded down to the nearest multiple of | |
965 | * {@link #encodedBlockSize} If <code>chunkSeparatorLength</code> is zero, | |
966 | * then chunking is disabled. | |
967 | * | |
968 | * @param unencodedBlockSize | |
969 | * the size of an unencoded block (e.g. Base64 = 3) | |
970 | * @param encodedBlockSize | |
971 | * the size of an encoded block (e.g. Base64 = 4) | |
972 | * @param lineLength | |
973 | * if > 0, use chunking with a length <code>lineLength</code> | |
974 | * @param chunkSeparatorLength | |
975 | * the chunk separator length, if relevant | |
976 | */ | |
977 | 495 | protected Base64(int unencodedBlockSize, int encodedBlockSize, int lineLength, int chunkSeparatorLength) { |
978 | 495 | this.unencodedBlockSize = unencodedBlockSize; |
979 | 495 | this.encodedBlockSize = encodedBlockSize; |
980 | 495 | this.lineLength = (lineLength > 0 && chunkSeparatorLength > 0) ? (lineLength / encodedBlockSize) * encodedBlockSize : 0; |
981 | 495 | this.chunkSeparatorLength = chunkSeparatorLength; |
982 | 495 | } |
983 | ||
984 | /** | |
985 | * Returns true if this object has buffered data for reading. | |
986 | * | |
987 | * @param context | |
988 | * the context to be used | |
989 | * @return true if there is data still available for reading. | |
990 | */ | |
991 | boolean hasData(Context context) { // package protected for access from I/O | |
992 | // streams | |
993 | 0 | return context.buffer != null; |
994 | } | |
995 | ||
996 | /** | |
997 | * Returns the amount of buffered data available for reading. | |
998 | * | |
999 | * @param context | |
1000 | * the context to be used | |
1001 | * @return The amount of buffered data available for reading. | |
1002 | */ | |
1003 | int available(Context context) { // package protected for access from I/O | |
1004 | // streams | |
1005 | 495 | return context.buffer != null ? context.pos - context.readPos : 0; |
1006 | } | |
1007 | ||
1008 | /** | |
1009 | * Get the default buffer size. Can be overridden. | |
1010 | * | |
1011 | * @return {@link #DEFAULT_BUFFER_SIZE} | |
1012 | */ | |
1013 | protected int getDefaultBufferSize() { | |
1014 | 495 | return DEFAULT_BUFFER_SIZE; |
1015 | } | |
1016 | ||
1017 | /** | |
1018 | * Increases our buffer by the {@link #DEFAULT_BUFFER_RESIZE_FACTOR}. | |
1019 | * | |
1020 | * @param context | |
1021 | * the context to be used | |
1022 | */ | |
1023 | private void resizeBuffer(Context context) { | |
1024 | 495 | if (context.buffer == null) { |
1025 | 495 | context.buffer = new byte[getDefaultBufferSize()]; |
1026 | 495 | context.pos = 0; |
1027 | 495 | context.readPos = 0; |
1028 | } else { | |
1029 | 0 | byte[] b = new byte[context.buffer.length * DEFAULT_BUFFER_RESIZE_FACTOR]; |
1030 | 0 | System.arraycopy(context.buffer, 0, b, 0, context.buffer.length); |
1031 | 0 | context.buffer = b; |
1032 | } | |
1033 | 495 | } |
1034 | ||
1035 | /** | |
1036 | * Ensure that the buffer has room for <code>size</code> bytes | |
1037 | * | |
1038 | * @param size | |
1039 | * minimum spare space required | |
1040 | * @param context | |
1041 | * the context to be used | |
1042 | */ | |
1043 | protected void ensureBufferSize(int size, Context context) { | |
1044 | 73760 | if ((context.buffer == null) || (context.buffer.length < context.pos + size)) { |
1045 | 495 | resizeBuffer(context); |
1046 | } | |
1047 | 73760 | } |
1048 | ||
1049 | /** | |
1050 | * Extracts buffered data into the provided byte[] array, starting at | |
1051 | * position bPos, up to a maximum of bAvail bytes. Returns how many bytes | |
1052 | * were actually extracted. | |
1053 | * | |
1054 | * @param b | |
1055 | * byte[] array to extract the buffered data into. | |
1056 | * @param bPos | |
1057 | * position in byte[] array to start extraction at. | |
1058 | * @param bAvail | |
1059 | * amount of bytes we're allowed to extract. We may extract fewer | |
1060 | * (if fewer are available). | |
1061 | * @param context | |
1062 | * the context to be used | |
1063 | * @return The number of bytes successfully extracted into the provided | |
1064 | * byte[] array. | |
1065 | */ | |
1066 | int readResults(byte[] b, int bPos, int bAvail, Context context) { // package | |
1067 | // protected | |
1068 | // for | |
1069 | // access | |
1070 | // from | |
1071 | // I/O | |
1072 | // streams | |
1073 | 495 | if (context.buffer != null) { |
1074 | 495 | int len = Math.min(available(context), bAvail); |
1075 | 495 | System.arraycopy(context.buffer, context.readPos, b, bPos, len); |
1076 | 495 | context.readPos += len; |
1077 | 495 | if (context.readPos >= context.pos) { |
1078 | 495 | context.buffer = null; // so hasData() will return false, and |
1079 | // this method can return -1 | |
1080 | } | |
1081 | 495 | return len; |
1082 | } | |
1083 | 0 | return context.eof ? EOF : 0; |
1084 | } | |
1085 | ||
1086 | /** | |
1087 | * Checks if a byte value is whitespace or not. Whitespace is taken to mean: | |
1088 | * space, tab, CR, LF | |
1089 | * | |
1090 | * @param byteToCheck | |
1091 | * the byte to check | |
1092 | * @return true if byte is whitespace, false otherwise | |
1093 | */ | |
1094 | protected static boolean isWhiteSpace(byte byteToCheck) { | |
1095 | 0 | switch (byteToCheck) { |
1096 | case ' ': | |
1097 | case '\n': | |
1098 | case '\r': | |
1099 | case '\t': | |
1100 | 0 | return true; |
1101 | default: | |
1102 | 0 | return false; |
1103 | } | |
1104 | } | |
1105 | ||
1106 | /** | |
1107 | * Encodes an Object using the Base-N algorithm. This method is provided in | |
1108 | * order to satisfy the requirements of the Encoder interface, and will | |
1109 | * throw an EncoderException if the supplied object is not of type byte[]. | |
1110 | * | |
1111 | * @param obj | |
1112 | * Object to encode | |
1113 | * @return An object (of type byte[]) containing the Base-N encoded data | |
1114 | * which corresponds to the byte[] supplied. | |
1115 | * @throws EncoderException | |
1116 | * if the parameter supplied is not of type byte[] | |
1117 | */ | |
1118 | public Object encode(Object obj) throws Exception { | |
1119 | 0 | if (!(obj instanceof byte[])) { |
1120 | 0 | throw new Exception("Parameter supplied to Base-N encode is not a byte[]"); |
1121 | } | |
1122 | 0 | return encode((byte[]) obj); |
1123 | } | |
1124 | ||
1125 | /** | |
1126 | * Encodes a byte[] containing binary data, into a String containing | |
1127 | * characters in the Base-N alphabet. Uses UTF8 encoding. | |
1128 | * | |
1129 | * @param pArray | |
1130 | * a byte array containing binary data | |
1131 | * @return A String containing only Base-N character data | |
1132 | */ | |
1133 | public String encodeToString(byte[] pArray) { | |
1134 | 0 | return StringUtils.newStringUtf8(encode(pArray)); |
1135 | } | |
1136 | ||
1137 | /** | |
1138 | * Encodes a byte[] containing binary data, into a String containing | |
1139 | * characters in the appropriate alphabet. Uses UTF8 encoding. | |
1140 | * | |
1141 | * @param pArray | |
1142 | * a byte array containing binary data | |
1143 | * @return String containing only character data in the appropriate | |
1144 | * alphabet. | |
1145 | */ | |
1146 | public String encodeAsString(byte[] pArray) { | |
1147 | 0 | return StringUtils.newStringUtf8(encode(pArray)); |
1148 | } | |
1149 | ||
1150 | /** | |
1151 | * Decodes an Object using the Base-N algorithm. This method is provided in | |
1152 | * order to satisfy the requirements of the Decoder interface, and will | |
1153 | * throw a DecoderException if the supplied object is not of type byte[] or | |
1154 | * String. | |
1155 | * | |
1156 | * @param obj | |
1157 | * Object to decode | |
1158 | * @return An object (of type byte[]) containing the binary data which | |
1159 | * corresponds to the byte[] or String supplied. | |
1160 | * @throws DecoderException | |
1161 | * if the parameter supplied is not of type byte[] | |
1162 | */ | |
1163 | public Object decode(Object obj) throws Exception { | |
1164 | 0 | if (obj instanceof byte[]) { |
1165 | 0 | return decode((byte[]) obj); |
1166 | 0 | } else if (obj instanceof String) { |
1167 | 0 | return decode((String) obj); |
1168 | } else { | |
1169 | 0 | throw new Exception("Parameter supplied to Base-N decode is not a byte[] or a String"); |
1170 | } | |
1171 | } | |
1172 | ||
1173 | /** | |
1174 | * Decodes a String containing characters in the Base-N alphabet. | |
1175 | * | |
1176 | * @param pArray | |
1177 | * A String containing Base-N character data | |
1178 | * @return a byte array containing binary data | |
1179 | */ | |
1180 | public byte[] decode(String pArray) { | |
1181 | 265 | return decode(StringUtils.getBytesUtf8(pArray)); |
1182 | } | |
1183 | ||
1184 | /** | |
1185 | * Decodes a byte[] containing characters in the Base-N alphabet. | |
1186 | * | |
1187 | * @param pArray | |
1188 | * A byte array containing Base-N character data | |
1189 | * @return a byte array containing binary data | |
1190 | */ | |
1191 | public byte[] decode(byte[] pArray) { | |
1192 | 265 | Context context = new Context(); |
1193 | 265 | if (pArray == null || pArray.length == 0) { |
1194 | 0 | return pArray; |
1195 | } | |
1196 | 265 | decode(pArray, 0, pArray.length, context); |
1197 | 265 | decode(pArray, 0, EOF, context); // Notify decoder of EOF. |
1198 | 265 | byte[] result = new byte[context.pos]; |
1199 | 265 | readResults(result, 0, result.length, context); |
1200 | 265 | return result; |
1201 | } | |
1202 | ||
1203 | /** | |
1204 | * Encodes a byte[] containing binary data, into a byte[] containing | |
1205 | * characters in the alphabet. | |
1206 | * | |
1207 | * @param pArray | |
1208 | * a byte array containing binary data | |
1209 | * @return A byte array containing only the basen alphabetic character data | |
1210 | */ | |
1211 | public byte[] encode(byte[] pArray) { | |
1212 | 230 | Context context = new Context(); |
1213 | 230 | if (pArray == null || pArray.length == 0) { |
1214 | 0 | return pArray; |
1215 | } | |
1216 | 230 | encode(pArray, 0, pArray.length, context); |
1217 | 230 | encode(pArray, 0, EOF, context); // Notify encoder of EOF. |
1218 | 230 | byte[] buf = new byte[context.pos - context.readPos]; |
1219 | 230 | readResults(buf, 0, buf.length, context); |
1220 | 230 | return buf; |
1221 | } | |
1222 | ||
1223 | /** | |
1224 | * Tests a given byte array to see if it contains only valid characters | |
1225 | * within the alphabet. The method optionally treats whitespace and pad as | |
1226 | * valid. | |
1227 | * | |
1228 | * @param arrayOctet | |
1229 | * byte array to test | |
1230 | * @param allowWSPad | |
1231 | * if {@code true}, then whitespace and PAD are also allowed | |
1232 | * | |
1233 | * @return {@code true} if all bytes are valid characters in the alphabet or | |
1234 | * if the byte array is empty; {@code false}, otherwise | |
1235 | */ | |
1236 | public boolean isInAlphabet(byte[] arrayOctet, boolean allowWSPad) { | |
1237 | 0 | for (int i = 0; i < arrayOctet.length; i++) { |
1238 | 0 | if (!isInAlphabet(arrayOctet[i]) && (!allowWSPad || (arrayOctet[i] != PAD) && !isWhiteSpace(arrayOctet[i]))) { |
1239 | 0 | return false; |
1240 | } | |
1241 | } | |
1242 | 0 | return true; |
1243 | } | |
1244 | ||
1245 | /** | |
1246 | * Tests a given String to see if it contains only valid characters within | |
1247 | * the alphabet. The method treats whitespace and PAD as valid. | |
1248 | * | |
1249 | * @param basen | |
1250 | * String to test | |
1251 | * @return {@code true} if all characters in the String are valid characters | |
1252 | * in the alphabet or if the String is empty; {@code false}, | |
1253 | * otherwise | |
1254 | * @see #isInAlphabet(byte[], boolean) | |
1255 | */ | |
1256 | public boolean isInAlphabet(String basen) { | |
1257 | 0 | return isInAlphabet(StringUtils.getBytesUtf8(basen), true); |
1258 | } | |
1259 | ||
1260 | /** | |
1261 | * Tests a given byte array to see if it contains any characters within the | |
1262 | * alphabet or PAD. | |
1263 | * | |
1264 | * Intended for use in checking line-ending arrays | |
1265 | * | |
1266 | * @param arrayOctet | |
1267 | * byte array to test | |
1268 | * @return {@code true} if any byte is a valid character in the alphabet or | |
1269 | * PAD; {@code false} otherwise | |
1270 | */ | |
1271 | protected boolean containsAlphabetOrPad(byte[] arrayOctet) { | |
1272 | 495 | if (arrayOctet == null) { |
1273 | 0 | return false; |
1274 | } | |
1275 | 1485 | for (byte element : arrayOctet) { |
1276 | 990 | if (PAD == element || isInAlphabet(element)) { |
1277 | 0 | return true; |
1278 | } | |
1279 | } | |
1280 | 495 | return false; |
1281 | } | |
1282 | ||
1283 | /** | |
1284 | * Calculates the amount of space needed to encode the supplied array. | |
1285 | * | |
1286 | * @param pArray | |
1287 | * byte[] array which will later be encoded | |
1288 | * | |
1289 | * @return amount of space needed to encoded the supplied array. Returns a | |
1290 | * long since a max-len array will require > Integer.MAX_VALUE | |
1291 | */ | |
1292 | public long getEncodedLength(byte[] pArray) { | |
1293 | // Calculate non-chunked size - rounded up to allow for padding | |
1294 | // cast to long is needed to avoid possibility of overflow | |
1295 | 230 | long len = ((pArray.length + unencodedBlockSize - 1) / unencodedBlockSize) * (long) encodedBlockSize; |
1296 | 230 | if (lineLength > 0) { // We're using chunking |
1297 | // Round up to nearest multiple | |
1298 | 0 | len += ((len + lineLength - 1) / lineLength) * chunkSeparatorLength; |
1299 | } | |
1300 | 230 | return len; |
1301 | } | |
1302 | ||
1303 | /** | |
1304 | * Character encoding names required of every implementation of the Java | |
1305 | * platform. | |
1306 | * | |
1307 | * From the Java documentation <a href= | |
1308 | * "http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html" | |
1309 | * >Standard charsets</a>: | |
1310 | * <p> | |
1311 | * <cite>Every implementation of the Java platform is required to support | |
1312 | * the following character encodings. Consult the release documentation for | |
1313 | * your implementation to see if any other encodings are supported. Consult | |
1314 | * the release documentation for your implementation to see if any other | |
1315 | * encodings are supported. </cite> | |
1316 | * </p> | |
1317 | * | |
1318 | * <ul> | |
1319 | * <li><code>US-ASCII</code><br/> | |
1320 | * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the | |
1321 | * Unicode character set.</li> | |
1322 | * <li><code>ISO-8859-1</code><br/> | |
1323 | * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li> | |
1324 | * <li><code>UTF-8</code><br/> | |
1325 | * Eight-bit Unicode Transformation Format.</li> | |
1326 | * <li><code>UTF-16BE</code><br/> | |
1327 | * Sixteen-bit Unicode Transformation Format, big-endian byte order.</li> | |
1328 | * <li><code>UTF-16LE</code><br/> | |
1329 | * Sixteen-bit Unicode Transformation Format, little-endian byte order.</li> | |
1330 | * <li><code>UTF-16</code><br/> | |
1331 | * Sixteen-bit Unicode Transformation Format, byte order specified by a | |
1332 | * mandatory initial byte-order mark (either order accepted on input, | |
1333 | * big-endian used on output.)</li> | |
1334 | * </ul> | |
1335 | * | |
1336 | * This perhaps would best belong in the [lang] project. Even if a similar | |
1337 | * interface is defined in [lang], it is not foreseen that [codec] would be | |
1338 | * made to depend on [lang]. | |
1339 | * | |
1340 | * <p> | |
1341 | * This class is immutable and thread-safe. | |
1342 | * </p> | |
1343 | * | |
1344 | * @see <a | |
1345 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1346 | * charsets</a> | |
1347 | * @since 1.4 | |
1348 | * @version $Id$ | |
1349 | */ | |
1350 | 0 | public class CharEncoding { |
1351 | /** | |
1352 | * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1. </p> | |
1353 | * <p> | |
1354 | * Every implementation of the Java platform is required to support this | |
1355 | * character encoding. | |
1356 | * </p> | |
1357 | * | |
1358 | * @see <a | |
1359 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1360 | * charsets</a> | |
1361 | */ | |
1362 | public static final String ISO_8859_1 = "ISO-8859-1"; | |
1363 | ||
1364 | /** | |
1365 | * <p> | |
1366 | * Seven-bit ASCII, also known as ISO646-US, also known as the Basic | |
1367 | * Latin block of the Unicode character set. | |
1368 | * </p> | |
1369 | * <p> | |
1370 | * Every implementation of the Java platform is required to support this | |
1371 | * character encoding. | |
1372 | * </p> | |
1373 | * | |
1374 | * @see <a | |
1375 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1376 | * charsets</a> | |
1377 | */ | |
1378 | public static final String US_ASCII = "US-ASCII"; | |
1379 | ||
1380 | /** | |
1381 | * <p> | |
1382 | * Sixteen-bit Unicode Transformation Format, The byte order specified | |
1383 | * by a mandatory initial byte-order mark (either order accepted on | |
1384 | * input, big-endian used on output) | |
1385 | * </p> | |
1386 | * <p> | |
1387 | * Every implementation of the Java platform is required to support this | |
1388 | * character encoding. | |
1389 | * </p> | |
1390 | * | |
1391 | * @see <a | |
1392 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1393 | * charsets</a> | |
1394 | */ | |
1395 | public static final String UTF_16 = "UTF-16"; | |
1396 | ||
1397 | /** | |
1398 | * <p> | |
1399 | * Sixteen-bit Unicode Transformation Format, big-endian byte order. | |
1400 | * </p> | |
1401 | * <p> | |
1402 | * Every implementation of the Java platform is required to support this | |
1403 | * character encoding. | |
1404 | * </p> | |
1405 | * | |
1406 | * @see <a | |
1407 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1408 | * charsets</a> | |
1409 | */ | |
1410 | public static final String UTF_16BE = "UTF-16BE"; | |
1411 | ||
1412 | /** | |
1413 | * <p> | |
1414 | * Sixteen-bit Unicode Transformation Format, little-endian byte order. | |
1415 | * </p> | |
1416 | * <p> | |
1417 | * Every implementation of the Java platform is required to support this | |
1418 | * character encoding. | |
1419 | * </p> | |
1420 | * | |
1421 | * @see <a | |
1422 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1423 | * charsets</a> | |
1424 | */ | |
1425 | public static final String UTF_16LE = "UTF-16LE"; | |
1426 | ||
1427 | /** | |
1428 | * <p> | |
1429 | * Eight-bit Unicode Transformation Format. | |
1430 | * </p> | |
1431 | * <p> | |
1432 | * Every implementation of the Java platform is required to support this | |
1433 | * character encoding. | |
1434 | * </p> | |
1435 | * | |
1436 | * @see <a | |
1437 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1438 | * charsets</a> | |
1439 | */ | |
1440 | public static final String UTF_8 = "UTF-8"; | |
1441 | } | |
1442 | ||
1443 | /** | |
1444 | * Charsets required of every implementation of the Java platform. | |
1445 | * | |
1446 | * From the Java documentation <a href= | |
1447 | * "http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html" | |
1448 | * >Standard charsets</a>: | |
1449 | * <p> | |
1450 | * <cite>Every implementation of the Java platform is required to support | |
1451 | * the following character encodings. Consult the release documentation for | |
1452 | * your implementation to see if any other encodings are supported. Consult | |
1453 | * the release documentation for your implementation to see if any other | |
1454 | * encodings are supported. </cite> | |
1455 | * </p> | |
1456 | * | |
1457 | * <ul> | |
1458 | * <li><code>US-ASCII</code><br/> | |
1459 | * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the | |
1460 | * Unicode character set.</li> | |
1461 | * <li><code>ISO-8859-1</code><br/> | |
1462 | * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li> | |
1463 | * <li><code>UTF-8</code><br/> | |
1464 | * Eight-bit Unicode Transformation Format.</li> | |
1465 | * <li><code>UTF-16BE</code><br/> | |
1466 | * Sixteen-bit Unicode Transformation Format, big-endian byte order.</li> | |
1467 | * <li><code>UTF-16LE</code><br/> | |
1468 | * Sixteen-bit Unicode Transformation Format, little-endian byte order.</li> | |
1469 | * <li><code>UTF-16</code><br/> | |
1470 | * Sixteen-bit Unicode Transformation Format, byte order specified by a | |
1471 | * mandatory initial byte-order mark (either order accepted on input, | |
1472 | * big-endian used on output.)</li> | |
1473 | * </ul> | |
1474 | * | |
1475 | * This perhaps would best belong in the Commons Lang project. Even if a | |
1476 | * similar class is defined in Commons Lang, it is not foreseen that Commons | |
1477 | * Codec would be made to depend on Commons Lang. | |
1478 | * | |
1479 | * <p> | |
1480 | * This class is immutable and thread-safe. | |
1481 | * </p> | |
1482 | * | |
1483 | * @see <a | |
1484 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1485 | * charsets</a> | |
1486 | * @since 1.7 | |
1487 | * @version $Id: CharEncoding.java 1173287 2011-09-20 18:16:19Z ggregory $ | |
1488 | */ | |
1489 | 0 | public static class Charsets { |
1490 | ||
1491 | // | |
1492 | // This class should only contain Charset instances for required | |
1493 | // encodings. This guarantees that it will load correctly and | |
1494 | // without delay on all Java platforms. | |
1495 | // | |
1496 | ||
1497 | /** | |
1498 | * Returns the given Charset or the default Charset if the given Charset | |
1499 | * is null. | |
1500 | * | |
1501 | * @param charset | |
1502 | * A charset or null. | |
1503 | * @return the given Charset or the default Charset if the given Charset | |
1504 | * is null | |
1505 | */ | |
1506 | public static Charset toCharset(Charset charset) { | |
1507 | 0 | return charset == null ? Charset.defaultCharset() : charset; |
1508 | } | |
1509 | ||
1510 | /** | |
1511 | * Returns a Charset for the named charset. If the name is null, return | |
1512 | * the default Charset. | |
1513 | * | |
1514 | * @param charset | |
1515 | * The name of the requested charset, may be null. | |
1516 | * @return a Charset for the named charset | |
1517 | * @throws UnsupportedCharsetException | |
1518 | * If the named charset is unavailable | |
1519 | */ | |
1520 | public static Charset toCharset(String charset) { | |
1521 | 0 | return charset == null ? Charset.defaultCharset() : Charset.forName(charset); |
1522 | } | |
1523 | ||
1524 | /** | |
1525 | * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1. </p> | |
1526 | * <p> | |
1527 | * Every implementation of the Java platform is required to support this | |
1528 | * character encoding. | |
1529 | * </p> | |
1530 | * | |
1531 | * @see <a | |
1532 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1533 | * charsets</a> | |
1534 | */ | |
1535 | 5 | public static final Charset ISO_8859_1 = Charset.forName(CharEncoding.ISO_8859_1); |
1536 | ||
1537 | /** | |
1538 | * <p> | |
1539 | * Seven-bit ASCII, also known as ISO646-US, also known as the Basic | |
1540 | * Latin block of the Unicode character set. | |
1541 | * </p> | |
1542 | * <p> | |
1543 | * Every implementation of the Java platform is required to support this | |
1544 | * character encoding. | |
1545 | * </p> | |
1546 | * | |
1547 | * @see <a | |
1548 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1549 | * charsets</a> | |
1550 | */ | |
1551 | 5 | public static final Charset US_ASCII = Charset.forName(CharEncoding.US_ASCII); |
1552 | ||
1553 | /** | |
1554 | * <p> | |
1555 | * Sixteen-bit Unicode Transformation Format, The byte order specified | |
1556 | * by a mandatory initial byte-order mark (either order accepted on | |
1557 | * input, big-endian used on output) | |
1558 | * </p> | |
1559 | * <p> | |
1560 | * Every implementation of the Java platform is required to support this | |
1561 | * character encoding. | |
1562 | * </p> | |
1563 | * | |
1564 | * @see <a | |
1565 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1566 | * charsets</a> | |
1567 | */ | |
1568 | 5 | public static final Charset UTF_16 = Charset.forName(CharEncoding.UTF_16); |
1569 | ||
1570 | /** | |
1571 | * <p> | |
1572 | * Sixteen-bit Unicode Transformation Format, big-endian byte order. | |
1573 | * </p> | |
1574 | * <p> | |
1575 | * Every implementation of the Java platform is required to support this | |
1576 | * character encoding. | |
1577 | * </p> | |
1578 | * | |
1579 | * @see <a | |
1580 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1581 | * charsets</a> | |
1582 | */ | |
1583 | 5 | public static final Charset UTF_16BE = Charset.forName(CharEncoding.UTF_16BE); |
1584 | ||
1585 | /** | |
1586 | * <p> | |
1587 | * Sixteen-bit Unicode Transformation Format, little-endian byte order. | |
1588 | * </p> | |
1589 | * <p> | |
1590 | * Every implementation of the Java platform is required to support this | |
1591 | * character encoding. | |
1592 | * </p> | |
1593 | * | |
1594 | * @see <a | |
1595 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1596 | * charsets</a> | |
1597 | */ | |
1598 | 5 | public static final Charset UTF_16LE = Charset.forName(CharEncoding.UTF_16LE); |
1599 | ||
1600 | /** | |
1601 | * <p> | |
1602 | * Eight-bit Unicode Transformation Format. | |
1603 | * </p> | |
1604 | * <p> | |
1605 | * Every implementation of the Java platform is required to support this | |
1606 | * character encoding. | |
1607 | * </p> | |
1608 | * | |
1609 | * @see <a | |
1610 | * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1611 | * charsets</a> | |
1612 | */ | |
1613 | 5 | public static final Charset UTF_8 = Charset.forName(CharEncoding.UTF_8); |
1614 | } | |
1615 | ||
1616 | /** | |
1617 | * Converts String to and from bytes using the encodings required by the | |
1618 | * Java specification. These encodings are specified in <a href= | |
1619 | * "http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html" | |
1620 | * >Standard charsets</a> | |
1621 | * | |
1622 | * <p> | |
1623 | * This class is immutable and thread-safe. | |
1624 | * </p> | |
1625 | * | |
1626 | * @see CharEncoding | |
1627 | * @see <a | |
1628 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1629 | * charsets</a> | |
1630 | * @version $Id$ | |
1631 | * @since 1.4 | |
1632 | */ | |
1633 | 0 | public static class StringUtils { |
1634 | ||
1635 | /** | |
1636 | * Calls {@link String#getBytes(Charset)} | |
1637 | * | |
1638 | * @param string | |
1639 | * The string to encode (if null, return null). | |
1640 | * @param charset | |
1641 | * The {@link Charset} to encode the {@code String} | |
1642 | * @return the encoded bytes | |
1643 | */ | |
1644 | private static byte[] getBytes(String string, Charset charset) { | |
1645 | 265 | if (string == null) { |
1646 | 0 | return null; |
1647 | } | |
1648 | 265 | return string.getBytes(charset); |
1649 | } | |
1650 | ||
1651 | /** | |
1652 | * Encodes the given string into a sequence of bytes using the | |
1653 | * ISO-8859-1 charset, storing the result into a new byte array. | |
1654 | * | |
1655 | * @param string | |
1656 | * the String to encode, may be {@code null} | |
1657 | * @return encoded bytes, or {@code null} if the input string was | |
1658 | * {@code null} | |
1659 | * @throws NullPointerException | |
1660 | * Thrown if {@link Charsets#ISO_8859_1} is not initialized, | |
1661 | * which should never happen since it is required by the | |
1662 | * Java platform specification. | |
1663 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1664 | * UnsupportedEncodingException | |
1665 | * @see <a | |
1666 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1667 | * charsets</a> | |
1668 | * @see #getBytesUnchecked(String, String) | |
1669 | */ | |
1670 | public static byte[] getBytesIso8859_1(String string) { | |
1671 | 0 | return getBytes(string, Charsets.ISO_8859_1); |
1672 | } | |
1673 | ||
1674 | /** | |
1675 | * Encodes the given string into a sequence of bytes using the named | |
1676 | * charset, storing the result into a new byte array. | |
1677 | * <p> | |
1678 | * This method catches {@link UnsupportedEncodingException} and rethrows | |
1679 | * it as {@link IllegalStateException}, which should never happen for a | |
1680 | * required charset name. Use this method when the encoding is required | |
1681 | * to be in the JRE. | |
1682 | * </p> | |
1683 | * | |
1684 | * @param string | |
1685 | * the String to encode, may be {@code null} | |
1686 | * @param charsetName | |
1687 | * The name of a required {@link java.nio.charset.Charset} | |
1688 | * @return encoded bytes, or {@code null} if the input string was | |
1689 | * {@code null} | |
1690 | * @throws IllegalStateException | |
1691 | * Thrown when a {@link UnsupportedEncodingException} is | |
1692 | * caught, which should never happen for a required charset | |
1693 | * name. | |
1694 | * @see CharEncoding | |
1695 | * @see String#getBytes(String) | |
1696 | */ | |
1697 | public static byte[] getBytesUnchecked(String string, String charsetName) { | |
1698 | 0 | if (string == null) { |
1699 | 0 | return null; |
1700 | } | |
1701 | try { | |
1702 | 0 | return string.getBytes(charsetName); |
1703 | 0 | } catch (UnsupportedEncodingException e) { |
1704 | 0 | throw StringUtils.newIllegalStateException(charsetName, e); |
1705 | } | |
1706 | } | |
1707 | ||
1708 | /** | |
1709 | * Encodes the given string into a sequence of bytes using the US-ASCII | |
1710 | * charset, storing the result into a new byte array. | |
1711 | * | |
1712 | * @param string | |
1713 | * the String to encode, may be {@code null} | |
1714 | * @return encoded bytes, or {@code null} if the input string was | |
1715 | * {@code null} | |
1716 | * @throws NullPointerException | |
1717 | * Thrown if {@link Charsets#US_ASCII} is not initialized, | |
1718 | * which should never happen since it is required by the | |
1719 | * Java platform specification. | |
1720 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1721 | * UnsupportedEncodingException | |
1722 | * @see <a | |
1723 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1724 | * charsets</a> | |
1725 | * @see #getBytesUnchecked(String, String) | |
1726 | */ | |
1727 | public static byte[] getBytesUsAscii(String string) { | |
1728 | 0 | return getBytes(string, Charsets.US_ASCII); |
1729 | } | |
1730 | ||
1731 | /** | |
1732 | * Encodes the given string into a sequence of bytes using the UTF-16 | |
1733 | * charset, storing the result into a new byte array. | |
1734 | * | |
1735 | * @param string | |
1736 | * the String to encode, may be {@code null} | |
1737 | * @return encoded bytes, or {@code null} if the input string was | |
1738 | * {@code null} | |
1739 | * @throws NullPointerException | |
1740 | * Thrown if {@link Charsets#UTF_16} is not initialized, | |
1741 | * which should never happen since it is required by the | |
1742 | * Java platform specification. | |
1743 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1744 | * UnsupportedEncodingException | |
1745 | * @see <a | |
1746 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1747 | * charsets</a> | |
1748 | * @see #getBytesUnchecked(String, String) | |
1749 | */ | |
1750 | public static byte[] getBytesUtf16(String string) { | |
1751 | 0 | return getBytes(string, Charsets.UTF_16); |
1752 | } | |
1753 | ||
1754 | /** | |
1755 | * Encodes the given string into a sequence of bytes using the UTF-16BE | |
1756 | * charset, storing the result into a new byte array. | |
1757 | * | |
1758 | * @param string | |
1759 | * the String to encode, may be {@code null} | |
1760 | * @return encoded bytes, or {@code null} if the input string was | |
1761 | * {@code null} | |
1762 | * @throws NullPointerException | |
1763 | * Thrown if {@link Charsets#UTF_16BE} is not initialized, | |
1764 | * which should never happen since it is required by the | |
1765 | * Java platform specification. | |
1766 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1767 | * UnsupportedEncodingException | |
1768 | * @see <a | |
1769 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1770 | * charsets</a> | |
1771 | * @see #getBytesUnchecked(String, String) | |
1772 | */ | |
1773 | public static byte[] getBytesUtf16Be(String string) { | |
1774 | 0 | return getBytes(string, Charsets.UTF_16BE); |
1775 | } | |
1776 | ||
1777 | /** | |
1778 | * Encodes the given string into a sequence of bytes using the UTF-16LE | |
1779 | * charset, storing the result into a new byte array. | |
1780 | * | |
1781 | * @param string | |
1782 | * the String to encode, may be {@code null} | |
1783 | * @return encoded bytes, or {@code null} if the input string was | |
1784 | * {@code null} | |
1785 | * @throws NullPointerException | |
1786 | * Thrown if {@link Charsets#UTF_16LE} is not initialized, | |
1787 | * which should never happen since it is required by the | |
1788 | * Java platform specification. | |
1789 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1790 | * UnsupportedEncodingException | |
1791 | * @see <a | |
1792 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1793 | * charsets</a> | |
1794 | * @see #getBytesUnchecked(String, String) | |
1795 | */ | |
1796 | public static byte[] getBytesUtf16Le(String string) { | |
1797 | 0 | return getBytes(string, Charsets.UTF_16LE); |
1798 | } | |
1799 | ||
1800 | /** | |
1801 | * Encodes the given string into a sequence of bytes using the UTF-8 | |
1802 | * charset, storing the result into a new byte array. | |
1803 | * | |
1804 | * @param string | |
1805 | * the String to encode, may be {@code null} | |
1806 | * @return encoded bytes, or {@code null} if the input string was | |
1807 | * {@code null} | |
1808 | * @throws NullPointerException | |
1809 | * Thrown if {@link Charsets#UTF_8} is not initialized, | |
1810 | * which should never happen since it is required by the | |
1811 | * Java platform specification. | |
1812 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1813 | * UnsupportedEncodingException | |
1814 | * @see <a | |
1815 | * href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard | |
1816 | * charsets</a> | |
1817 | * @see #getBytesUnchecked(String, String) | |
1818 | */ | |
1819 | public static byte[] getBytesUtf8(String string) { | |
1820 | 265 | return getBytes(string, Charsets.UTF_8); |
1821 | } | |
1822 | ||
1823 | private static IllegalStateException newIllegalStateException(String charsetName, UnsupportedEncodingException e) { | |
1824 | 0 | return new IllegalStateException(charsetName + ": " + e); |
1825 | } | |
1826 | ||
1827 | /** | |
1828 | * Constructs a new <code>String</code> by decoding the specified array | |
1829 | * of bytes using the given charset. | |
1830 | * | |
1831 | * @param bytes | |
1832 | * The bytes to be decoded into characters | |
1833 | * @param charset | |
1834 | * The {@link Charset} to encode the {@code String} | |
1835 | * @return A new <code>String</code> decoded from the specified array of | |
1836 | * bytes using the given charset, or {@code null} if the input | |
1837 | * byte array was {@code null}. | |
1838 | * @throws NullPointerException | |
1839 | * Thrown if {@link Charsets#UTF_8} is not initialized, | |
1840 | * which should never happen since it is required by the | |
1841 | * Java platform specification. | |
1842 | */ | |
1843 | private static String newString(byte[] bytes, Charset charset) { | |
1844 | 230 | return bytes == null ? null : new String(bytes, charset); |
1845 | } | |
1846 | ||
1847 | /** | |
1848 | * Constructs a new <code>String</code> by decoding the specified array | |
1849 | * of bytes using the given charset. | |
1850 | * <p> | |
1851 | * This method catches {@link UnsupportedEncodingException} and | |
1852 | * re-throws it as {@link IllegalStateException}, which should never | |
1853 | * happen for a required charset name. Use this method when the encoding | |
1854 | * is required to be in the JRE. | |
1855 | * </p> | |
1856 | * | |
1857 | * @param bytes | |
1858 | * The bytes to be decoded into characters, may be | |
1859 | * {@code null} | |
1860 | * @param charsetName | |
1861 | * The name of a required {@link java.nio.charset.Charset} | |
1862 | * @return A new <code>String</code> decoded from the specified array of | |
1863 | * bytes using the given charset, or {@code null} if the input | |
1864 | * byte array was {@code null}. | |
1865 | * @throws IllegalStateException | |
1866 | * Thrown when a {@link UnsupportedEncodingException} is | |
1867 | * caught, which should never happen for a required charset | |
1868 | * name. | |
1869 | * @see CharEncoding | |
1870 | * @see String#String(byte[], String) | |
1871 | */ | |
1872 | public static String newString(byte[] bytes, String charsetName) { | |
1873 | 0 | if (bytes == null) { |
1874 | 0 | return null; |
1875 | } | |
1876 | try { | |
1877 | 0 | return new String(bytes, charsetName); |
1878 | 0 | } catch (UnsupportedEncodingException e) { |
1879 | 0 | throw StringUtils.newIllegalStateException(charsetName, e); |
1880 | } | |
1881 | } | |
1882 | ||
1883 | /** | |
1884 | * Constructs a new <code>String</code> by decoding the specified array | |
1885 | * of bytes using the ISO-8859-1 charset. | |
1886 | * | |
1887 | * @param bytes | |
1888 | * The bytes to be decoded into characters, may be | |
1889 | * {@code null} | |
1890 | * @return A new <code>String</code> decoded from the specified array of | |
1891 | * bytes using the ISO-8859-1 charset, or {@code null} if the | |
1892 | * input byte array was {@code null}. | |
1893 | * @throws NullPointerException | |
1894 | * Thrown if {@link Charsets#ISO_8859_1} is not initialized, | |
1895 | * which should never happen since it is required by the | |
1896 | * Java platform specification. | |
1897 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1898 | * UnsupportedEncodingException | |
1899 | */ | |
1900 | public static String newStringIso8859_1(byte[] bytes) { | |
1901 | 0 | return new String(bytes, Charsets.ISO_8859_1); |
1902 | } | |
1903 | ||
1904 | /** | |
1905 | * Constructs a new <code>String</code> by decoding the specified array | |
1906 | * of bytes using the US-ASCII charset. | |
1907 | * | |
1908 | * @param bytes | |
1909 | * The bytes to be decoded into characters | |
1910 | * @return A new <code>String</code> decoded from the specified array of | |
1911 | * bytes using the US-ASCII charset, or {@code null} if the | |
1912 | * input byte array was {@code null}. | |
1913 | * @throws NullPointerException | |
1914 | * Thrown if {@link Charsets#US_ASCII} is not initialized, | |
1915 | * which should never happen since it is required by the | |
1916 | * Java platform specification. | |
1917 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1918 | * UnsupportedEncodingException | |
1919 | */ | |
1920 | public static String newStringUsAscii(byte[] bytes) { | |
1921 | 0 | return new String(bytes, Charsets.US_ASCII); |
1922 | } | |
1923 | ||
1924 | /** | |
1925 | * Constructs a new <code>String</code> by decoding the specified array | |
1926 | * of bytes using the UTF-16 charset. | |
1927 | * | |
1928 | * @param bytes | |
1929 | * The bytes to be decoded into characters | |
1930 | * @return A new <code>String</code> decoded from the specified array of | |
1931 | * bytes using the UTF-16 charset or {@code null} if the input | |
1932 | * byte array was {@code null}. | |
1933 | * @throws NullPointerException | |
1934 | * Thrown if {@link Charsets#UTF_16} is not initialized, | |
1935 | * which should never happen since it is required by the | |
1936 | * Java platform specification. | |
1937 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1938 | * UnsupportedEncodingException | |
1939 | */ | |
1940 | public static String newStringUtf16(byte[] bytes) { | |
1941 | 0 | return new String(bytes, Charsets.UTF_16); |
1942 | } | |
1943 | ||
1944 | /** | |
1945 | * Constructs a new <code>String</code> by decoding the specified array | |
1946 | * of bytes using the UTF-16BE charset. | |
1947 | * | |
1948 | * @param bytes | |
1949 | * The bytes to be decoded into characters | |
1950 | * @return A new <code>String</code> decoded from the specified array of | |
1951 | * bytes using the UTF-16BE charset, or {@code null} if the | |
1952 | * input byte array was {@code null}. | |
1953 | * @throws NullPointerException | |
1954 | * Thrown if {@link Charsets#UTF_16BE} is not initialized, | |
1955 | * which should never happen since it is required by the | |
1956 | * Java platform specification. | |
1957 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1958 | * UnsupportedEncodingException | |
1959 | */ | |
1960 | public static String newStringUtf16Be(byte[] bytes) { | |
1961 | 0 | return new String(bytes, Charsets.UTF_16BE); |
1962 | } | |
1963 | ||
1964 | /** | |
1965 | * Constructs a new <code>String</code> by decoding the specified array | |
1966 | * of bytes using the UTF-16LE charset. | |
1967 | * | |
1968 | * @param bytes | |
1969 | * The bytes to be decoded into characters | |
1970 | * @return A new <code>String</code> decoded from the specified array of | |
1971 | * bytes using the UTF-16LE charset, or {@code null} if the | |
1972 | * input byte array was {@code null}. | |
1973 | * @throws NullPointerException | |
1974 | * Thrown if {@link Charsets#UTF_16LE} is not initialized, | |
1975 | * which should never happen since it is required by the | |
1976 | * Java platform specification. | |
1977 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1978 | * UnsupportedEncodingException | |
1979 | */ | |
1980 | public static String newStringUtf16Le(byte[] bytes) { | |
1981 | 0 | return new String(bytes, Charsets.UTF_16LE); |
1982 | } | |
1983 | ||
1984 | /** | |
1985 | * Constructs a new <code>String</code> by decoding the specified array | |
1986 | * of bytes using the UTF-8 charset. | |
1987 | * | |
1988 | * @param bytes | |
1989 | * The bytes to be decoded into characters | |
1990 | * @return A new <code>String</code> decoded from the specified array of | |
1991 | * bytes using the UTF-8 charset, or {@code null} if the input | |
1992 | * byte array was {@code null}. | |
1993 | * @throws NullPointerException | |
1994 | * Thrown if {@link Charsets#UTF_8} is not initialized, | |
1995 | * which should never happen since it is required by the | |
1996 | * Java platform specification. | |
1997 | * @since As of 1.7, throws {@link NullPointerException} instead of | |
1998 | * UnsupportedEncodingException | |
1999 | */ | |
2000 | public static String newStringUtf8(byte[] bytes) { | |
2001 | 230 | return newString(bytes, Charsets.UTF_8); |
2002 | } | |
2003 | ||
2004 | } | |
2005 | ||
2006 | } |