001/* 002 * Licensed to the Apache Software Foundation (ASF) under one or more 003 * contributor license agreements. See the NOTICE file distributed with 004 * this work for additional information regarding copyright ownership. 005 * The ASF licenses this file to You under the Apache License, Version 2.0 006 * (the "License"); you may not use this file except in compliance with 007 * the License. You may obtain a copy of the License at 008 * 009 * http://www.apache.org/licenses/LICENSE-2.0 010 * 011 * Unless required by applicable law or agreed to in writing, software 012 * distributed under the License is distributed on an "AS IS" BASIS, 013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 014 * See the License for the specific language governing permissions and 015 * limitations under the License. 016 */ 017 018package org.apache.commons.net.util; 019 020import java.io.UnsupportedEncodingException; 021import java.math.BigInteger; 022 023 024 025/** 026 * Provides Base64 encoding and decoding as defined by RFC 2045. 027 * 028 * <p> 029 * This class implements section <cite>6.8. Base64 Content-Transfer-Encoding</cite> from RFC 2045 <cite>Multipurpose 030 * Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies</cite> by Freed and Borenstein. 031 * </p> 032 * <p> 033 * The class can be parameterized in the following manner with various constructors: 034 * <ul> 035 * <li>URL-safe mode: Default off.</li> 036 * <li>Line length: Default 76. Line length that aren't multiples of 4 will still essentially end up being multiples of 037 * 4 in the encoded data. 038 * <li>Line separator: Default is CRLF ("\r\n")</li> 039 * </ul> 040 * <p> 041 * Since this class operates directly on byte streams, and not character streams, it is hard-coded to only encode/decode 042 * character encodings which are compatible with the lower 127 ASCII chart (ISO-8859-1, Windows-1252, UTF-8, etc). 043 * </p> 044 * 045 * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045</a> 046 * @since 2.2 047 */ 048public class Base64 { 049 private static final int DEFAULT_BUFFER_RESIZE_FACTOR = 2; 050 051 private static final int DEFAULT_BUFFER_SIZE = 8192; 052 053 /** 054 * Chunk size per RFC 2045 section 6.8. 055 * 056 * <p> 057 * The {@value} character limit does not count the trailing CRLF, but counts all other characters, including any 058 * equal signs. 059 * </p> 060 * 061 * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 6.8</a> 062 */ 063 static final int CHUNK_SIZE = 76; 064 065 /** 066 * Chunk separator per RFC 2045 section 2.1. 067 * 068 * @see <a href="http://www.ietf.org/rfc/rfc2045.txt">RFC 2045 section 2.1</a> 069 */ 070 private static final byte[] CHUNK_SEPARATOR = {'\r', '\n'}; 071 072 private static final byte[] EMPTY_BYTE_ARRAY = new byte[0]; 073 074 /** 075 * This array is a lookup table that translates 6-bit positive integer index values into their "Base64 Alphabet" 076 * equivalents as specified in Table 1 of RFC 2045. 077 * 078 * Thanks to "commons" project in ws.apache.org for this code. 079 * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ 080 */ 081 private static final byte[] STANDARD_ENCODE_TABLE = { 082 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 083 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 084 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 085 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 086 '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '+', '/' 087 }; 088 089 /** 090 * This is a copy of the STANDARD_ENCODE_TABLE above, but with + and / 091 * changed to - and _ to make the encoded Base64 results more URL-SAFE. 092 * This table is only used when the Base64's mode is set to URL-SAFE. 093 */ 094 private static final byte[] URL_SAFE_ENCODE_TABLE = { 095 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 096 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 097 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 098 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 099 '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '-', '_' 100 }; 101 102 /** 103 * Byte used to pad output. 104 */ 105 private static final byte PAD = '='; 106 107 /** 108 * This array is a lookup table that translates Unicode characters drawn from the "Base64 Alphabet" (as specified in 109 * Table 1 of RFC 2045) into their 6-bit positive integer equivalents. Characters that are not in the Base64 110 * alphabet but fall within the bounds of the array are translated to -1. 111 * 112 * Note: '+' and '-' both decode to 62. '/' and '_' both decode to 63. This means decoder seamlessly handles both 113 * URL_SAFE and STANDARD base64. (The encoder, on the other hand, needs to know ahead of time what to emit). 114 * 115 * Thanks to "commons" project in ws.apache.org for this code. 116 * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ 117 */ 118 private static final byte[] DECODE_TABLE = { 119 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 120 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 121 -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, 62, -1, 63, 52, 53, 54, 122 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 123 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 124 24, 25, -1, -1, -1, -1, 63, -1, 26, 27, 28, 29, 30, 31, 32, 33, 34, 125 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51 126 }; 127 128 /** Mask used to extract 6 bits, used when encoding */ 129 private static final int MASK_6BITS = 0x3f; 130 131 /** Mask used to extract 8 bits, used in decoding base64 bytes */ 132 private static final int MASK_8BITS = 0xff; 133 134 // The static final fields above are used for the original static byte[] methods on Base64. 135 // The private member fields below are used with the new streaming approach, 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 above remains static because it is able 140 * to decode both STANDARD and URL_SAFE streams, but the encodeTable must be a member variable so we can switch 141 * between the two modes. 142 */ 143 private final byte[] encodeTable; 144 145 /** 146 * Line length for encoding. Not used when decoding. A value of zero or less implies no chunking of the base64 147 * encoded data. 148 */ 149 private final int lineLength; 150 151 /** 152 * Line separator for encoding. Not used when decoding. Only used if lineLength > 0. 153 */ 154 private final byte[] lineSeparator; 155 156 /** 157 * Convenience variable to help us determine when our buffer is going to run out of room and needs resizing. 158 * <code>decodeSize = 3 + lineSeparator.length;</code> 159 */ 160 private final int decodeSize; 161 162 /** 163 * Convenience variable to help us determine when our buffer is going to run out of room and needs resizing. 164 * <code>encodeSize = 4 + lineSeparator.length;</code> 165 */ 166 private final int encodeSize; 167 168 /** 169 * Buffer for streaming. 170 */ 171 private byte[] buffer; 172 173 /** 174 * Position where next character should be written in the buffer. 175 */ 176 private int pos; 177 178 /** 179 * Position where next character should be read from the buffer. 180 */ 181 private int readPos; 182 183 /** 184 * Variable tracks how many characters have been written to the current line. Only used when encoding. We use it to 185 * make sure each encoded line never goes beyond lineLength (if lineLength > 0). 186 */ 187 private int currentLinePos; 188 189 /** 190 * Writes to the buffer only occur after every 3 reads when encoding, an every 4 reads when decoding. This variable 191 * helps track that. 192 */ 193 private int modulus; 194 195 /** 196 * Boolean flag to indicate the EOF has been reached. Once EOF has been reached, this Base64 object becomes useless, 197 * and must be thrown away. 198 */ 199 private boolean eof; 200 201 /** 202 * Place holder for the 3 bytes we're dealing with for our base64 logic. Bitwise operations store and extract the 203 * base64 encoding or decoding from this variable. 204 */ 205 private int x; 206 207 /** 208 * Creates a Base64 codec used for decoding (all modes) and encoding in URL-unsafe mode. 209 * <p> 210 * When encoding the line length is 76, the line separator is CRLF, and the encoding table is STANDARD_ENCODE_TABLE. 211 * </p> 212 * 213 * <p> 214 * When decoding all variants are supported. 215 * </p> 216 */ 217 public Base64() { 218 this(false); 219 } 220 221 /** 222 * Creates a Base64 codec used for decoding (all modes) and encoding in the given URL-safe mode. 223 * <p> 224 * When encoding the line length is 76, the line separator is CRLF, and the encoding table is STANDARD_ENCODE_TABLE. 225 * </p> 226 * 227 * <p> 228 * When decoding all variants are supported. 229 * </p> 230 * 231 * @param urlSafe 232 * if <code>true</code>, URL-safe encoding is used. In most cases this should be set to 233 * <code>false</code>. 234 * @since 1.4 235 */ 236 public Base64(final boolean urlSafe) { 237 this(CHUNK_SIZE, CHUNK_SEPARATOR, urlSafe); 238 } 239 240 /** 241 * Creates a Base64 codec used for decoding (all modes) and encoding in URL-unsafe mode. 242 * <p> 243 * When encoding the line length is given in the constructor, the line separator is CRLF, and the encoding table is 244 * STANDARD_ENCODE_TABLE. 245 * </p> 246 * <p> 247 * Line lengths that aren't multiples of 4 will still essentially end up being multiples of 4 in the encoded data. 248 * </p> 249 * <p> 250 * When decoding all variants are supported. 251 * </p> 252 * 253 * @param lineLength 254 * Each line of encoded data will be at most of the given length (rounded down to nearest multiple of 4). 255 * If {@code lineLength <= 0}, then the output will not be divided into lines (chunks). Ignored when decoding. 256 * @since 1.4 257 */ 258 public Base64(final int lineLength) { 259 this(lineLength, CHUNK_SEPARATOR); 260 } 261 262 /** 263 * Creates a Base64 codec used for decoding (all modes) and encoding in URL-unsafe mode. 264 * <p> 265 * When encoding the line length and line separator are given in the constructor, and the encoding table is 266 * STANDARD_ENCODE_TABLE. 267 * </p> 268 * <p> 269 * Line lengths that aren't multiples of 4 will still essentially end up being multiples of 4 in the encoded data. 270 * </p> 271 * <p> 272 * When decoding all variants are supported. 273 * </p> 274 * 275 * @param lineLength 276 * Each line of encoded data will be at most of the given length (rounded down to nearest multiple of 4). 277 * If {@code lineLength <= 0}, then the output will not be divided into lines (chunks). Ignored when decoding. 278 * @param lineSeparator 279 * Each line of encoded data will end with this sequence of bytes. 280 * @throws IllegalArgumentException 281 * Thrown when the provided lineSeparator included some base64 characters. 282 * @since 1.4 283 */ 284 public Base64(final int lineLength, final byte[] lineSeparator) { 285 this(lineLength, lineSeparator, false); 286 } 287 288 /** 289 * Creates a Base64 codec used for decoding (all modes) and encoding in URL-unsafe mode. 290 * <p> 291 * When encoding the line length and line separator are given in the constructor, and the encoding table is 292 * STANDARD_ENCODE_TABLE. 293 * </p> 294 * <p> 295 * Line lengths that aren't multiples of 4 will still essentially end up being multiples of 4 in the encoded data. 296 * </p> 297 * <p> 298 * When decoding all variants are supported. 299 * </p> 300 * 301 * @param lineLength 302 * Each line of encoded data will be at most of the given length (rounded down to nearest multiple of 4). 303 * If {@code lineLength <= 0}, then the output will not be divided into lines (chunks). Ignored when decoding. 304 * @param lineSeparator 305 * Each line of encoded data will end with this sequence of bytes. 306 * @param urlSafe 307 * Instead of emitting '+' and '/' we emit '-' and '_' respectively. urlSafe is only applied to encode 308 * operations. Decoding seamlessly handles both modes. 309 * @throws IllegalArgumentException 310 * The provided lineSeparator included some base64 characters. That's not going to work! 311 * @since 1.4 312 */ 313 public Base64(int lineLength, byte[] lineSeparator, final boolean urlSafe) { 314 if (lineSeparator == null) { 315 lineLength = 0; // disable chunk-separating 316 lineSeparator = EMPTY_BYTE_ARRAY; // this just gets ignored 317 } 318 this.lineLength = lineLength > 0 ? (lineLength / 4) * 4 : 0; 319 this.lineSeparator = new byte[lineSeparator.length]; 320 System.arraycopy(lineSeparator, 0, this.lineSeparator, 0, lineSeparator.length); 321 if (lineLength > 0) { 322 this.encodeSize = 4 + lineSeparator.length; 323 } else { 324 this.encodeSize = 4; 325 } 326 this.decodeSize = this.encodeSize - 1; 327 if (containsBase64Byte(lineSeparator)) { 328 final String sep = newStringUtf8(lineSeparator); 329 throw new IllegalArgumentException("lineSeperator must not contain base64 characters: [" + sep + "]"); 330 } 331 this.encodeTable = urlSafe ? URL_SAFE_ENCODE_TABLE : STANDARD_ENCODE_TABLE; 332 } 333 334 /** 335 * Returns our current encode mode. True if we're URL-SAFE, false otherwise. 336 * 337 * @return true if we're in URL-SAFE mode, false otherwise. 338 * @since 1.4 339 */ 340 public boolean isUrlSafe() { 341 return this.encodeTable == URL_SAFE_ENCODE_TABLE; 342 } 343 344 /** 345 * Returns true if this Base64 object has buffered data for reading. 346 * 347 * @return true if there is Base64 object still available for reading. 348 */ 349 boolean hasData() { 350 return this.buffer != null; 351 } 352 353 /** 354 * Returns the amount of buffered data available for reading. 355 * 356 * @return The amount of buffered data available for reading. 357 */ 358 int avail() { 359 return buffer != null ? pos - readPos : 0; 360 } 361 362 /** Doubles our buffer. */ 363 private void resizeBuffer() { 364 if (buffer == null) { 365 buffer = new byte[DEFAULT_BUFFER_SIZE]; 366 pos = 0; 367 readPos = 0; 368 } else { 369 final byte[] b = new byte[buffer.length * DEFAULT_BUFFER_RESIZE_FACTOR]; 370 System.arraycopy(buffer, 0, b, 0, buffer.length); 371 buffer = b; 372 } 373 } 374 375 /** 376 * Extracts buffered data into the provided byte[] array, starting at position bPos, up to a maximum of bAvail 377 * bytes. Returns how many bytes were actually extracted. 378 * 379 * @param b 380 * byte[] array to extract the buffered data into. 381 * @param bPos 382 * position in byte[] array to start extraction at. 383 * @param bAvail 384 * amount of bytes we're allowed to extract. We may extract fewer (if fewer are available). 385 * @return The number of bytes successfully extracted into the provided byte[] array. 386 */ 387 int readResults(final byte[] b, final int bPos, final int bAvail) { 388 if (buffer != null) { 389 final int len = Math.min(avail(), bAvail); 390 if (buffer != b) { 391 System.arraycopy(buffer, readPos, b, bPos, len); 392 readPos += len; 393 if (readPos >= pos) { 394 buffer = null; 395 } 396 } else { 397 // Re-using the original consumer's output array is only 398 // allowed for one round. 399 buffer = null; 400 } 401 return len; 402 } 403 return eof ? -1 : 0; 404 } 405 406 /** 407 * Sets the streaming buffer. This is a small optimization where we try to buffer directly to the consumer's output 408 * array for one round (if the consumer calls this method first) instead of starting our own buffer. 409 * 410 * @param out 411 * byte[] array to buffer directly to. 412 * @param outPos 413 * Position to start buffering into. 414 * @param outAvail 415 * Amount of bytes available for direct buffering. 416 */ 417 void setInitialBuffer(final byte[] out, final int outPos, final int outAvail) { 418 // We can re-use consumer's original output array under 419 // special circumstances, saving on some System.arraycopy(). 420 if (out != null && out.length == outAvail) { 421 buffer = out; 422 pos = outPos; 423 readPos = outPos; 424 } 425 } 426 427 /** 428 * <p> 429 * Encodes all of the provided data, starting at inPos, for inAvail bytes. Must be called at least twice: once with 430 * the data to encode, and once with inAvail set to "-1" to alert encoder that EOF has been reached, so flush last 431 * remaining bytes (if not multiple of 3). 432 * </p> 433 * <p> 434 * Thanks to "commons" project in ws.apache.org for the bitwise operations, and general approach. 435 * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ 436 * </p> 437 * 438 * @param in 439 * byte[] array of binary data to base64 encode. 440 * @param inPos 441 * Position to start reading data from. 442 * @param inAvail 443 * Amount of bytes available from input for encoding. 444 */ 445 void encode(final byte[] in, int inPos, final int inAvail) { 446 if (eof) { 447 return; 448 } 449 // inAvail < 0 is how we're informed of EOF in the underlying data we're 450 // encoding. 451 if (inAvail < 0) { 452 eof = true; 453 if (buffer == null || buffer.length - pos < encodeSize) { 454 resizeBuffer(); 455 } 456 switch (modulus) { 457 case 1 : 458 buffer[pos++] = encodeTable[(x >> 2) & MASK_6BITS]; 459 buffer[pos++] = encodeTable[(x << 4) & MASK_6BITS]; 460 // URL-SAFE skips the padding to further reduce size. 461 if (encodeTable == STANDARD_ENCODE_TABLE) { 462 buffer[pos++] = PAD; 463 buffer[pos++] = PAD; 464 } 465 break; 466 467 case 2 : 468 buffer[pos++] = encodeTable[(x >> 10) & MASK_6BITS]; 469 buffer[pos++] = encodeTable[(x >> 4) & MASK_6BITS]; 470 buffer[pos++] = encodeTable[(x << 2) & MASK_6BITS]; 471 // URL-SAFE skips the padding to further reduce size. 472 if (encodeTable == STANDARD_ENCODE_TABLE) { 473 buffer[pos++] = PAD; 474 } 475 break; 476 default: 477 break; // other values ignored 478 } 479 if (lineLength > 0 && pos > 0) { 480 System.arraycopy(lineSeparator, 0, buffer, pos, lineSeparator.length); 481 pos += lineSeparator.length; 482 } 483 } else { 484 for (int i = 0; i < inAvail; i++) { 485 if (buffer == null || buffer.length - pos < encodeSize) { 486 resizeBuffer(); 487 } 488 modulus = (++modulus) % 3; 489 int b = in[inPos++]; 490 if (b < 0) { 491 b += 256; 492 } 493 x = (x << 8) + b; 494 if (0 == modulus) { 495 buffer[pos++] = encodeTable[(x >> 18) & MASK_6BITS]; 496 buffer[pos++] = encodeTable[(x >> 12) & MASK_6BITS]; 497 buffer[pos++] = encodeTable[(x >> 6) & MASK_6BITS]; 498 buffer[pos++] = encodeTable[x & MASK_6BITS]; 499 currentLinePos += 4; 500 if (lineLength > 0 && lineLength <= currentLinePos) { 501 System.arraycopy(lineSeparator, 0, buffer, pos, lineSeparator.length); 502 pos += lineSeparator.length; 503 currentLinePos = 0; 504 } 505 } 506 } 507 } 508 } 509 510 /** 511 * <p> 512 * Decodes all of the provided data, starting at inPos, for inAvail bytes. Should be called at least twice: once 513 * with the data to decode, and once with inAvail set to "-1" to alert decoder that EOF has been reached. The "-1" 514 * call is not necessary when decoding, but it doesn't hurt, either. 515 * </p> 516 * <p> 517 * Ignores all non-base64 characters. This is how chunked (e.g. 76 character) data is handled, since CR and LF are 518 * silently ignored, but has implications for other bytes, too. This method subscribes to the garbage-in, 519 * garbage-out philosophy: it will not check the provided data for validity. 520 * </p> 521 * <p> 522 * Thanks to "commons" project in ws.apache.org for the bitwise operations, and general approach. 523 * http://svn.apache.org/repos/asf/webservices/commons/trunk/modules/util/ 524 * </p> 525 * 526 * @param in 527 * byte[] array of ascii data to base64 decode. 528 * @param inPos 529 * Position to start reading data from. 530 * @param inAvail 531 * Amount of bytes available from input for encoding. 532 */ 533 void decode(final byte[] in, int inPos, final int inAvail) { 534 if (eof) { 535 return; 536 } 537 if (inAvail < 0) { 538 eof = true; 539 } 540 for (int i = 0; i < inAvail; i++) { 541 if (buffer == null || buffer.length - pos < decodeSize) { 542 resizeBuffer(); 543 } 544 final byte b = in[inPos++]; 545 if (b == PAD) { 546 // We're done. 547 eof = true; 548 break; 549 } 550 if (b >= 0 && b < DECODE_TABLE.length) { 551 final int result = DECODE_TABLE[b]; 552 if (result >= 0) { 553 modulus = (++modulus) % 4; 554 x = (x << 6) + result; 555 if (modulus == 0) { 556 buffer[pos++] = (byte) ((x >> 16) & MASK_8BITS); 557 buffer[pos++] = (byte) ((x >> 8) & MASK_8BITS); 558 buffer[pos++] = (byte) (x & MASK_8BITS); 559 } 560 } 561 } 562 } 563 564 // Two forms of EOF as far as base64 decoder is concerned: actual 565 // EOF (-1) and first time '=' character is encountered in stream. 566 // This approach makes the '=' padding characters completely optional. 567 if (eof && modulus != 0) { 568 x = x << 6; 569 switch (modulus) { 570 case 2 : 571 x = x << 6; 572 buffer[pos++] = (byte) ((x >> 16) & MASK_8BITS); 573 break; 574 case 3 : 575 buffer[pos++] = (byte) ((x >> 16) & MASK_8BITS); 576 buffer[pos++] = (byte) ((x >> 8) & MASK_8BITS); 577 break; 578 default: 579 break; // other values ignored 580 } 581 } 582 } 583 584 /** 585 * Returns whether or not the <code>octet</code> is in the base 64 alphabet. 586 * 587 * @param octet 588 * The value to test 589 * @return <code>true</code> if the value is defined in the the base 64 alphabet, <code>false</code> otherwise. 590 * @since 1.4 591 */ 592 public static boolean isBase64(final byte octet) { 593 return octet == PAD || (octet >= 0 && octet < DECODE_TABLE.length && DECODE_TABLE[octet] != -1); 594 } 595 596 /** 597 * Tests a given byte array to see if it contains only valid characters within the Base64 alphabet. Currently the 598 * method treats whitespace as valid. 599 * 600 * @param arrayOctet 601 * byte array to test 602 * @return <code>true</code> if all bytes are valid characters in the Base64 alphabet or if the byte array is empty; 603 * false, otherwise 604 */ 605 public static boolean isArrayByteBase64(final byte[] arrayOctet) { 606 for (final byte element : arrayOctet) { 607 if (!isBase64(element) && !isWhiteSpace(element)) { 608 return false; 609 } 610 } 611 return true; 612 } 613 614 /** 615 * Tests a given byte array to see if it contains only valid characters within the Base64 alphabet. 616 * 617 * @param arrayOctet 618 * byte array to test 619 * @return <code>true</code> if any byte is a valid character in the Base64 alphabet; false herwise 620 */ 621 private static boolean containsBase64Byte(final byte[] arrayOctet) { 622 for (final byte element : arrayOctet) 623 { 624 if (isBase64(element)) { 625 return true; 626 } 627 } 628 return false; 629 } 630 631 /** 632 * Encodes binary data using the base64 algorithm but does not chunk the output. 633 * 634 * @param binaryData 635 * binary data to encode 636 * @return byte[] containing Base64 characters in their UTF-8 representation. 637 */ 638 public static byte[] encodeBase64(final byte[] binaryData) { 639 return encodeBase64(binaryData, false); 640 } 641 642 /** 643 * Encodes binary data using the base64 algorithm into 76 character blocks separated by CRLF. 644 * <p> 645 * For a non-chunking version, see {@link #encodeBase64StringUnChunked(byte[])}. 646 * 647 * @param binaryData 648 * binary data to encode 649 * @return String containing Base64 characters. 650 * @since 1.4 651 */ 652 public static String encodeBase64String(final byte[] binaryData) { 653 return newStringUtf8(encodeBase64(binaryData, true)); 654 } 655 656 /** 657 * Encodes binary data using the base64 algorithm, without using chunking. 658 * <p> 659 * For a chunking version, see {@link #encodeBase64String(byte[])}. 660 * 661 * @param binaryData 662 * binary data to encode 663 * @return String containing Base64 characters. 664 * @since 3.2 665 */ 666 public static String encodeBase64StringUnChunked(final byte[] binaryData) { 667 return newStringUtf8(encodeBase64(binaryData, false)); 668 } 669 670 /** 671 * Encodes binary data using the base64 algorithm. 672 * 673 * @param binaryData 674 * binary data to encode 675 * @param useChunking whether to split the output into chunks 676 * @return String containing Base64 characters. 677 * @since 3.2 678 */ 679 public static String encodeBase64String(final byte[] binaryData, final boolean useChunking) { 680 return newStringUtf8(encodeBase64(binaryData, useChunking)); 681 } 682 683 /** 684 * Encodes binary data using a URL-safe variation of the base64 algorithm but does not chunk the output. The 685 * url-safe variation emits - and _ instead of + and / characters. 686 * 687 * @param binaryData 688 * binary data to encode 689 * @return byte[] containing Base64 characters in their UTF-8 representation. 690 * @since 1.4 691 */ 692 public static byte[] encodeBase64URLSafe(final byte[] binaryData) { 693 return encodeBase64(binaryData, false, true); 694 } 695 696 /** 697 * Encodes binary data using a URL-safe variation of the base64 algorithm but does not chunk the output. The 698 * url-safe variation emits - and _ instead of + and / characters. 699 * 700 * @param binaryData 701 * binary data to encode 702 * @return String containing Base64 characters 703 * @since 1.4 704 */ 705 public static String encodeBase64URLSafeString(final byte[] binaryData) { 706 return newStringUtf8(encodeBase64(binaryData, false, true)); 707 } 708 709 /** 710 * Encodes binary data using the base64 algorithm and chunks the encoded output into 76 character blocks 711 * 712 * @param binaryData 713 * binary data to encode 714 * @return Base64 characters chunked in 76 character blocks 715 */ 716 public static byte[] encodeBase64Chunked(final byte[] binaryData) { 717 return encodeBase64(binaryData, true); 718 } 719 720 /** 721 * Decodes a String containing containing characters in the Base64 alphabet. 722 * 723 * @param pArray 724 * A String containing Base64 character data 725 * @return a byte array containing binary data 726 * @since 1.4 727 */ 728 public byte[] decode(final String pArray) { 729 return decode(getBytesUtf8(pArray)); 730 } 731 732 private byte[] getBytesUtf8(final String pArray) { 733 try { 734 return pArray.getBytes("UTF8"); 735 } catch (final UnsupportedEncodingException e) { 736 throw new RuntimeException(e); 737 } 738 } 739 740 /** 741 * Decodes a byte[] containing containing characters in the Base64 alphabet. 742 * 743 * @param pArray 744 * A byte array containing Base64 character data 745 * @return a byte array containing binary data 746 */ 747 public byte[] decode(final byte[] pArray) { 748 reset(); 749 if (pArray == null || pArray.length == 0) { 750 return pArray; 751 } 752 final long len = (pArray.length * 3) / 4; 753 final byte[] buf = new byte[(int) len]; 754 setInitialBuffer(buf, 0, buf.length); 755 decode(pArray, 0, pArray.length); 756 decode(pArray, 0, -1); // Notify decoder of EOF. 757 758 // Would be nice to just return buf (like we sometimes do in the encode 759 // logic), but we have no idea what the line-length was (could even be 760 // variable). So we cannot determine ahead of time exactly how big an 761 // array is necessary. Hence the need to construct a 2nd byte array to 762 // hold the final result: 763 764 final byte[] result = new byte[pos]; 765 readResults(result, 0, result.length); 766 return result; 767 } 768 769 /** 770 * Encodes binary data using the base64 algorithm, optionally chunking the output into 76 character blocks. 771 * 772 * @param binaryData 773 * Array containing binary data to encode. 774 * @param isChunked 775 * if <code>true</code> this encoder will chunk the base64 output into 76 character blocks 776 * @return Base64-encoded data. 777 * @throws IllegalArgumentException 778 * Thrown when the input array needs an output array bigger than {@link Integer#MAX_VALUE} 779 */ 780 public static byte[] encodeBase64(final byte[] binaryData, final boolean isChunked) { 781 return encodeBase64(binaryData, isChunked, false); 782 } 783 784 /** 785 * Encodes binary data using the base64 algorithm, optionally chunking the output into 76 character blocks. 786 * 787 * @param binaryData 788 * Array containing binary data to encode. 789 * @param isChunked 790 * if <code>true</code> this encoder will chunk the base64 output into 76 character blocks 791 * @param urlSafe 792 * if <code>true</code> this encoder will emit - and _ instead of the usual + and / characters. 793 * @return Base64-encoded data. 794 * @throws IllegalArgumentException 795 * Thrown when the input array needs an output array bigger than {@link Integer#MAX_VALUE} 796 * @since 1.4 797 */ 798 public static byte[] encodeBase64(final byte[] binaryData, final boolean isChunked, final boolean urlSafe) { 799 return encodeBase64(binaryData, isChunked, urlSafe, Integer.MAX_VALUE); 800 } 801 802 /** 803 * Encodes binary data using the base64 algorithm, optionally chunking the output into 76 character blocks. 804 * 805 * @param binaryData 806 * Array containing binary data to encode. 807 * @param isChunked 808 * if <code>true</code> this encoder will chunk the base64 output into 76 character blocks 809 * @param urlSafe 810 * if <code>true</code> this encoder will emit - and _ instead of the usual + and / characters. 811 * @param maxResultSize 812 * The maximum result size to accept. 813 * @return Base64-encoded data. 814 * @throws IllegalArgumentException 815 * Thrown when the input array needs an output array bigger than maxResultSize 816 * @since 1.4 817 */ 818 public static byte[] encodeBase64(final byte[] binaryData, final boolean isChunked, final boolean urlSafe, 819 final int maxResultSize) { 820 if (binaryData == null || binaryData.length == 0) { 821 return binaryData; 822 } 823 824 final long len = getEncodeLength(binaryData, isChunked ? CHUNK_SIZE : 0, 825 isChunked ? CHUNK_SEPARATOR : EMPTY_BYTE_ARRAY); 826 if (len > maxResultSize) { 827 throw new IllegalArgumentException("Input array too big, the output array would be bigger (" + len 828 + ") than the specified maxium size of " + maxResultSize); 829 } 830 831 final Base64 b64 = isChunked ? new Base64(urlSafe) : new Base64(0, CHUNK_SEPARATOR, urlSafe); 832 return b64.encode(binaryData); 833 } 834 835 /** 836 * Decodes a Base64 String into octets 837 * 838 * @param base64String 839 * String containing Base64 data 840 * @return Array containing decoded data. 841 * @since 1.4 842 */ 843 public static byte[] decodeBase64(final String base64String) { 844 return new Base64().decode(base64String); 845 } 846 847 /** 848 * Decodes Base64 data into octets 849 * 850 * @param base64Data 851 * Byte array containing Base64 data 852 * @return Array containing decoded data. 853 */ 854 public static byte[] decodeBase64(final byte[] base64Data) { 855 return new Base64().decode(base64Data); 856 } 857 858 859 860 /** 861 * Checks if a byte value is whitespace or not. 862 * 863 * @param byteToCheck 864 * the byte to check 865 * @return true if byte is whitespace, false otherwise 866 */ 867 private static boolean isWhiteSpace(final byte byteToCheck) { 868 switch (byteToCheck) { 869 case ' ' : 870 case '\n' : 871 case '\r' : 872 case '\t' : 873 return true; 874 default : 875 return false; 876 } 877 } 878 879 /** 880 * Encodes a byte[] containing binary data, into a String containing characters in the Base64 alphabet. 881 * 882 * @param pArray 883 * a byte array containing binary data 884 * @return A String containing only Base64 character data 885 * @since 1.4 886 */ 887 public String encodeToString(final byte[] pArray) { 888 return newStringUtf8(encode(pArray)); 889 } 890 891 private static String newStringUtf8(final byte[] encode) { 892 String str = null; 893 try { 894 str = new String(encode, "UTF8"); 895 } catch (final UnsupportedEncodingException ue) { 896 throw new RuntimeException(ue); 897 } 898 return str; 899 } 900 901 /** 902 * Encodes a byte[] containing binary data, into a byte[] containing characters in the Base64 alphabet. 903 * 904 * @param pArray 905 * a byte array containing binary data 906 * @return A byte array containing only Base64 character data 907 */ 908 public byte[] encode(final byte[] pArray) { 909 reset(); 910 if (pArray == null || pArray.length == 0) { 911 return pArray; 912 } 913 final long len = getEncodeLength(pArray, lineLength, lineSeparator); 914 byte[] buf = new byte[(int) len]; 915 setInitialBuffer(buf, 0, buf.length); 916 encode(pArray, 0, pArray.length); 917 encode(pArray, 0, -1); // Notify encoder of EOF. 918 // Encoder might have resized, even though it was unnecessary. 919 if (buffer != buf) { 920 readResults(buf, 0, buf.length); 921 } 922 // In URL-SAFE mode we skip the padding characters, so sometimes our 923 // final length is a bit smaller. 924 if (isUrlSafe() && pos < buf.length) { 925 final byte[] smallerBuf = new byte[pos]; 926 System.arraycopy(buf, 0, smallerBuf, 0, pos); 927 buf = smallerBuf; 928 } 929 return buf; 930 } 931 932 /** 933 * Pre-calculates the amount of space needed to base64-encode the supplied array. 934 * 935 * @param pArray byte[] array which will later be encoded 936 * @param chunkSize line-length of the output (<= 0 means no chunking) between each 937 * chunkSeparator (e.g. CRLF). 938 * @param chunkSeparator the sequence of bytes used to separate chunks of output (e.g. CRLF). 939 * 940 * @return amount of space needed to encoded the supplied array. Returns 941 * a long since a max-len array will require Integer.MAX_VALUE + 33%. 942 */ 943 private static long getEncodeLength(final byte[] pArray, int chunkSize, final byte[] chunkSeparator) { 944 // base64 always encodes to multiples of 4. 945 chunkSize = (chunkSize / 4) * 4; 946 947 long len = (pArray.length * 4) / 3; 948 final long mod = len % 4; 949 if (mod != 0) { 950 len += 4 - mod; 951 } 952 if (chunkSize > 0) { 953 final boolean lenChunksPerfectly = len % chunkSize == 0; 954 len += (len / chunkSize) * chunkSeparator.length; 955 if (!lenChunksPerfectly) { 956 len += chunkSeparator.length; 957 } 958 } 959 return len; 960 } 961 962 // Implementation of integer encoding used for crypto 963 /** 964 * Decodes a byte64-encoded integer according to crypto standards such as W3C's XML-Signature 965 * 966 * @param pArray 967 * a byte array containing base64 character data 968 * @return A BigInteger 969 * @since 1.4 970 */ 971 public static BigInteger decodeInteger(final byte[] pArray) { 972 return new BigInteger(1, decodeBase64(pArray)); 973 } 974 975 /** 976 * Encodes to a byte64-encoded integer according to crypto standards such as W3C's XML-Signature 977 * 978 * @param bigInt 979 * a BigInteger 980 * @return A byte array containing base64 character data 981 * @throws NullPointerException 982 * if null is passed in 983 * @since 1.4 984 */ 985 public static byte[] encodeInteger(final BigInteger bigInt) { 986 if (bigInt == null) { 987 throw new NullPointerException("encodeInteger called with null parameter"); 988 } 989 return encodeBase64(toIntegerBytes(bigInt), false); 990 } 991 992 /** 993 * Returns a byte-array representation of a <code>BigInteger</code> without sign bit. 994 * 995 * @param bigInt 996 * <code>BigInteger</code> to be converted 997 * @return a byte array representation of the BigInteger parameter 998 */ 999 static byte[] toIntegerBytes(final BigInteger bigInt) { 1000 int bitlen = bigInt.bitLength(); 1001 // round bitlen 1002 bitlen = ((bitlen + 7) >> 3) << 3; 1003 final byte[] bigBytes = bigInt.toByteArray(); 1004 1005 if (((bigInt.bitLength() % 8) != 0) && (((bigInt.bitLength() / 8) + 1) == (bitlen / 8))) { 1006 return bigBytes; 1007 } 1008 // set up params for copying everything but sign bit 1009 int startSrc = 0; 1010 int len = bigBytes.length; 1011 1012 // if bigInt is exactly byte-aligned, just skip signbit in copy 1013 if ((bigInt.bitLength() % 8) == 0) { 1014 startSrc = 1; 1015 len--; 1016 } 1017 final int startDst = bitlen / 8 - len; // to pad w/ nulls as per spec 1018 final byte[] resizedBytes = new byte[bitlen / 8]; 1019 System.arraycopy(bigBytes, startSrc, resizedBytes, startDst, len); 1020 return resizedBytes; 1021 } 1022 1023 /** 1024 * Resets this Base64 object to its initial newly constructed state. 1025 */ 1026 private void reset() { 1027 buffer = null; 1028 pos = 0; 1029 readPos = 0; 1030 currentLinePos = 0; 1031 modulus = 0; 1032 eof = false; 1033 } 1034 1035 // Getters for use in testing 1036 1037 int getLineLength() { 1038 return lineLength; 1039 } 1040 1041 byte[] getLineSeparator() { 1042 return lineSeparator.clone(); 1043 } 1044}