lib/compression/lzxpress.c

   1 /*
   2  * Copyright (C) Matthieu Suiche 2008
   3  *
   4  * All rights reserved.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  *
  10  * 1. Redistributions of source code must retain the above copyright
  11  *    notice, this list of conditions and the following disclaimer.
  12  *
  13  * 2. Redistributions in binary form must reproduce the above copyright
  14  *    notice, this list of conditions and the following disclaimer in the
  15  *    documentation and/or other materials provided with the distribution.
  16  *
  17  * 3. Neither the name of the author nor the names of its contributors
  18  *    may be used to endorse or promote products derived from this software
  19  *    without specific prior written permission.
  20  *
  21  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  22  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  23  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  24  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  25  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  26  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  27  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  28  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  29  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  30  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  31  * SUCH DAMAGE.
  32  *
  33  */
  34
  35 #include "replace.h"
  36 #include "lzxpress.h"
  37 #include "../lib/util/byteorder.h"
  38
  39
  40 #define __BUF_POS_CONST(buf,ofs)(((const uint8_t *)buf)+(ofs))
  41 #define __PULL_BYTE(buf,ofs) \
  42         ((uint8_t)((*__BUF_POS_CONST(buf,ofs)) & 0xFF))
  43
  44 #ifndef PULL_LE_UINT16
  45 #define PULL_LE_UINT16(buf,ofs) ((uint16_t)( \
  46         ((uint16_t)(((uint16_t)(__PULL_BYTE(buf,(ofs)+0))) << 0)) | \
  47         ((uint16_t)(((uint16_t)(__PULL_BYTE(buf,(ofs)+1))) << 8)) \
  48 ))
  49 #endif
  50
  51 #ifndef PULL_LE_UINT32
  52 #define PULL_LE_UINT32(buf,ofs) ((uint32_t)( \
  53         ((uint32_t)(((uint32_t)(__PULL_BYTE(buf,(ofs)+0))) <<  0)) | \
  54         ((uint32_t)(((uint32_t)(__PULL_BYTE(buf,(ofs)+1))) <<  8)) | \
  55         ((uint32_t)(((uint32_t)(__PULL_BYTE(buf,(ofs)+2))) << 16)) | \
  56         ((uint32_t)(((uint32_t)(__PULL_BYTE(buf,(ofs)+3))) << 24)) \
  57 ))
  58 #endif
  59
  60 ssize_t lzxpress_compress(const uint8_t *uncompressed,
  61                           uint32_t uncompressed_size,
  62                           uint8_t *compressed,
  63                           uint32_t max_compressed_size)
  64 {
  65         uint32_t uncompressed_pos, compressed_pos, byte_left;
  66         uint32_t max_offset, best_offset;
  67         int32_t offset;
  68         uint32_t max_len, len, best_len;
  69         const uint8_t *str1, *str2;
  70         uint32_t indic;
  71         uint8_t *indic_pos;
  72         uint32_t indic_bit, nibble_index;
  73
  74         uint32_t metadata_size;
  75         uint16_t metadata;
  76         uint16_t *dest;
  77
  78         if (!uncompressed_size) {
  79                 return 0;
  80         }
  81
  82         uncompressed_pos = 0;
  83         indic = 0;
  84         *(uint32_t *)compressed = 0;
  85         compressed_pos = sizeof(uint32_t);
  86         indic_pos = &compressed[0];
  87
  88         byte_left = uncompressed_size;
  89         indic_bit = 0;
  90         nibble_index = 0;
  91
  92         if (uncompressed_pos > XPRESS_BLOCK_SIZE)
  93                 return 0;
  94
  95         do {
  96                 bool found = false;
  97
  98                 max_offset = uncompressed_pos;
  99
 100                 str1 = &uncompressed[uncompressed_pos];
 101
 102                 best_len = 2;
 103                 best_offset = 0;
 104
 105                 max_offset = MIN(0x1FFF, max_offset);
 106
 107                 /* search for the longest match in the window for the lookahead buffer */
 108                 for (offset = 1; (uint32_t)offset <= max_offset; offset++) {
 109                         str2 = &str1[-offset];
 110
 111                         /* maximum len we can encode into metadata */
 112                         max_len = MIN((255 + 15 + 7 + 3), byte_left);
 113
 114                         for (len = 0; (len < max_len) && (str1[len] == str2[len]); len++);
 115
 116                         /*
 117                          * We check if len is better than the value found before, including the
 118                          * sequence of identical bytes
 119                          */
 120                         if (len > best_len) {
 121                                 found = true;
 122                                 best_len = len;
 123                                 best_offset = offset;
 124                         }
 125                 }
 126
 127                 if (found) {
 128                         metadata_size = 0;
 129                         dest = (uint16_t *)&compressed[compressed_pos];
 130
 131                         if (best_len < 10) {
 132                                 /* Classical meta-data */
 133                                 metadata = (uint16_t)(((best_offset - 1) << 3) | (best_len - 3));
 134                                 SSVAL(dest, metadata_size / sizeof(uint16_t), metadata);
 135                                 metadata_size += sizeof(uint16_t);
 136                         } else {
 137                                 metadata = (uint16_t)(((best_offset - 1) << 3) | 7);
 138                                 SSVAL(dest, metadata_size / sizeof(uint16_t), metadata);
 139                                 metadata_size = sizeof(uint16_t);
 140
 141                                 if (best_len < (15 + 7 + 3)) {
 142                                         /* Shared byte */
 143                                         if (!nibble_index) {
 144                                                 compressed[compressed_pos + metadata_size] = (best_len - (3 + 7)) & 0xF;
 145                                                 metadata_size += sizeof(uint8_t);
 146                                         } else {
 147                                                 compressed[nibble_index] &= 0xF;
 148                                                 compressed[nibble_index] |= (best_len - (3 + 7)) * 16;
 149                                         }
 150                                 } else if (best_len < (3 + 7 + 15 + 255)) {
 151                                         /* Shared byte */
 152                                         if (!nibble_index) {
 153                                                 compressed[compressed_pos + metadata_size] = 15;
 154                                                 metadata_size += sizeof(uint8_t);
 155                                         } else {
 156                                                 compressed[nibble_index] &= 0xF;
 157                                                 compressed[nibble_index] |= (15 * 16);
 158                                         }
 159
 160                                         /* Additional best_len */
 161                                         compressed[compressed_pos + metadata_size] = (best_len - (3 + 7 + 15)) & 0xFF;
 162                                         metadata_size += sizeof(uint8_t);
 163                                 } else {
 164                                         /* Shared byte */
 165                                         if (!nibble_index) {
 166                                                 compressed[compressed_pos + metadata_size] |= 15;
 167                                                 metadata_size += sizeof(uint8_t);
 168                                         } else {
 169                                                 compressed[nibble_index] |= 15 << 4;
 170                                         }
 171
 172                                         /* Additional best_len */
 173                                         compressed[compressed_pos + metadata_size] = 255;
 174
 175                                         metadata_size += sizeof(uint8_t);
 176
 177                                         compressed[compressed_pos + metadata_size] = (best_len - 3) & 0xFF;
 178                                         compressed[compressed_pos + metadata_size + 1] = ((best_len - 3) >> 8) & 0xFF;
 179                                         metadata_size += sizeof(uint16_t);
 180                                 }
 181                         }
 182
 183                         indic |= 1 << (32 - ((indic_bit % 32) + 1));
 184
 185                         if (best_len > 9) {
 186                                 if (nibble_index == 0) {
 187                                         nibble_index = compressed_pos + sizeof(uint16_t);
 188                                 } else {
 189                                         nibble_index = 0;
 190                                 }
 191                         }
 192
 193                         compressed_pos += metadata_size;
 194                         uncompressed_pos += best_len;
 195                         byte_left -= best_len;
 196                 } else {
 197                         compressed[compressed_pos++] = uncompressed[uncompressed_pos++];
 198                         byte_left--;
 199                 }
 200                 indic_bit++;
 201
 202                 if ((indic_bit - 1) % 32 > (indic_bit % 32)) {
 203                         SIVAL(indic_pos, 0, indic);
 204                         indic = 0;
 205                         indic_pos = &compressed[compressed_pos];
 206                         compressed_pos += sizeof(uint32_t);
 207                 }
 208         } while (byte_left > 3);
 209
 210         do {
 211                 compressed[compressed_pos] = uncompressed[uncompressed_pos];
 212                 indic_bit++;
 213
 214                 uncompressed_pos++;
 215                 compressed_pos++;
 216                 if (((indic_bit - 1) % 32) > (indic_bit % 32)){
 217                         SIVAL(indic_pos, 0, indic);
 218                         indic = 0;
 219                         indic_pos = &compressed[compressed_pos];
 220                         compressed_pos += sizeof(uint32_t);
 221                 }
 222         } while (uncompressed_pos < uncompressed_size);
 223
 224         if ((indic_bit % 32) > 0) {
 225                 for (; (indic_bit % 32) != 0; indic_bit++)
 226                         indic |= 0 << (32 - ((indic_bit % 32) + 1));
 227
 228                 *(uint32_t *)&compressed[compressed_pos] = 0;
 229                 SIVAL(indic_pos, 0, indic);
 230                 compressed_pos += sizeof(uint32_t);
 231         }
 232
 233         return compressed_pos;
 234 }
 235
 236 ssize_t lzxpress_decompress(const uint8_t *input,
 237                             uint32_t input_size,
 238                             uint8_t *output,
 239                             uint32_t max_output_size)
 240 {
 241         uint32_t output_index, input_index;
 242         uint32_t indicator, indicator_bit;
 243         uint32_t length;
 244         uint32_t offset;
 245         uint32_t nibble_index;
 246
 247         output_index = 0;
 248         input_index = 0;
 249         indicator = 0;
 250         indicator_bit = 0;
 251         length = 0;
 252         offset = 0;
 253         nibble_index = 0;
 254
 255         do {
 256                 if (indicator_bit == 0) {
 257                         indicator = PULL_LE_UINT32(input, input_index);
 258                         input_index += sizeof(uint32_t);
 259                         indicator_bit = 32;
 260                 }
 261                 indicator_bit--;
 262
 263                 /*
 264                  * check whether the bit specified by indicator_bit is set or not
 265                  * set in indicator. For example, if indicator_bit has value 4
 266                  * check whether the 4th bit of the value in indicator is set
 267                  */
 268                 if (((indicator >> indicator_bit) & 1) == 0) {
 269                         output[output_index] = input[input_index];
 270                         input_index += sizeof(uint8_t);
 271                         output_index += sizeof(uint8_t);
 272                 } else {
 273                         length = PULL_LE_UINT16(input, input_index);
 274                         input_index += sizeof(uint16_t);
 275                         offset = length / 8;
 276                         length = length % 8;
 277
 278                         if (length == 7) {
 279                                 if (nibble_index == 0) {
 280                                         nibble_index = input_index;
 281                                         length = input[input_index] % 16;
 282                                         input_index += sizeof(uint8_t);
 283                                 } else {
 284                                         length = input[nibble_index] / 16;
 285                                         nibble_index = 0;
 286                                 }
 287
 288                                 if (length == 15) {
 289                                         length = input[input_index];
 290                                         input_index += sizeof(uint8_t);
 291                                         if (length == 255) {
 292                                                 length = PULL_LE_UINT16(input, input_index);
 293                                                 input_index += sizeof(uint16_t);
 294                                                 length -= (15 + 7);
 295                                         }
 296                                         length += 15;
 297                                 }
 298                                 length += 7;
 299                         }
 300
 301                         length += 3;
 302
 303                         do {
 304                                 if ((output_index >= max_output_size) || ((offset + 1) > output_index)) break;
 305
 306                                 output[output_index] = output[output_index - offset - 1];
 307
 308                                 output_index += sizeof(uint8_t);
 309                                 length -= sizeof(uint8_t);
 310                         } while (length != 0);
 311                 }
 312         } while ((output_index < max_output_size) && (input_index < (input_size)));
 313
 314         return output_index;
 315 }