base/compression/lzss_compression.cc

   1 /*
   2  * Copyright (c) 2003-2004 The Regents of The University of Michigan
   3  * All rights reserved.
   4  *
   5  * Redistribution and use in source and binary forms, with or without
   6  * modification, are permitted provided that the following conditions are
   7  * met: redistributions of source code must retain the above copyright
   8  * notice, this list of conditions and the following disclaimer;
   9  * redistributions in binary form must reproduce the above copyright
  10  * notice, this list of conditions and the following disclaimer in the
  11  * documentation and/or other materials provided with the distribution;
  12  * neither the name of the copyright holders nor the names of its
  13  * contributors may be used to endorse or promote products derived from
  14  * this software without specific prior written permission.
  15  *
  16  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  17  * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  18  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  19  * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  20  * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  21  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  22  * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  23  * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  24  * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  25  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  26  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  27  */
  28
  29 /** @file
  30  * LZSSCompression definitions.
  31  */
  32
  33 #include <assert.h>
  34
  35 #include "base/compression/lzss_compression.hh"
  36
  37 #include "base/misc.hh" //for fatal
  38
  39 void
  40 LZSSCompression::findSubString(uint8_t *src, int back, int size, uint16_t &L,
  41                                uint16_t &P)
  42 {
  43     int front = 0;
  44     int max_length = size - back;
  45     L = 0;
  46     P = back - 1;
  47     while (front < back) {
  48         while (src[front] != src[back] && front < back) ++front;
  49         if (front >= back) {
  50             return;
  51         }
  52         int i = 1;
  53         while (src[front+i] == src[back+i] && i < max_length) ++i;
  54         if (i >= L) {
  55             L = i;
  56             P = front;
  57         }
  58         if (src[front+i] != src[back+i-1]) {
  59             // can't find a longer substring until past this point.
  60             front += i;
  61         } else {
  62             ++front;
  63         }
  64     }
  65 }
  66
  67 int
  68 LZSSCompression::emitByte(uint8_t *dest, uint8_t byte)
  69 {
  70     if ((byte >> 5 & 0x7) == 0 || (byte >> 5 & 0x7) == 7) {
  71         // If the top 3 bits are the same, emit 00<6bits>
  72         dest[0] = byte & 0x3f;
  73         return 1;
  74     } else {
  75         // emit 01XXXXXX <8 bits>
  76         dest[0] = 0x40;
  77         dest[1] = byte;
  78         return 2;
  79     }
  80 }
  81
  82 void
  83 LZSSCompression::emitString(uint8_t *dest, uint16_t P, uint16_t L)
  84 {
  85     // Emit 1<7P> <5P><3L> <8L>
  86     dest[0] = 1<<7 | (P >> 5 & 0x7f);
  87     dest[1] = ((P & 0x1f) << 3) | (L>>8 & 0x3);
  88     dest[2] = L & 0xFF;
  89 }
  90
  91 int
  92 LZSSCompression::compress(uint8_t *dest, uint8_t *src, int size)
  93 {
  94     if (size > 4096) {
  95         fatal("Compression can only handle block sizes of 4096 bytes or less");
  96     }
  97
  98     // Encode the first byte.
  99     int dest_index = emitByte(dest, src[0]);
 100     int i = 1;
 101     // A 11 bit field
 102     uint16_t L;
 103     // A 12 bit field
 104     uint16_t P = 0;
 105
 106     while (i < size && dest_index < size) {
 107         L = 0;
 108
 109         if (dest_index+3 >= size) {
 110             dest_index = size;
 111             continue;
 112         }
 113
 114         if (i == size - 1) {
 115             // Output the character
 116             dest_index += emitByte(&dest[dest_index], src[i]);
 117             ++i;
 118             continue;
 119         }
 120         findSubString(src, i, size, L, P);
 121         if (L > 1) {
 122             // Output the string reference
 123             emitString(&dest[dest_index], P, L);
 124             dest_index += 3;
 125             i = i+L;
 126         } else {
 127             // Output the character
 128             dest_index += emitByte(&dest[dest_index], src[i]);
 129             ++i;
 130         }
 131     }
 132
 133     if (dest_index >= size) {
 134         // Have expansion instead of compression, just copy.
 135         memcpy(dest,src,size);
 136         return size;
 137     }
 138     return dest_index;
 139 }
 140
 141 int
 142 LZSSCompression::uncompress(uint8_t *dest, uint8_t *src, int size)
 143 {
 144     int index = 0;
 145     int i = 0;
 146     while (i < size) {
 147         if (src[i] & 1<<7 ) {
 148             // We have a string
 149             // Extract P
 150             int start = (src[i] & 0x3f)<<5 | ((src[i+1] >> 3) & 0x1f);
 151             // Extract L
 152             int len = (src[i+1] & 0x07)<<8 | src[i+2];
 153             i += 3;
 154             for (int j = start; j < start+len; ++j) {
 155                 dest[index++] = dest[j];
 156             }
 157         } else {
 158             // We have a character
 159             if (src[i] & 1<<6) {
 160                 // Value is in the next byte
 161                 dest[index++] = src[i+1];
 162                 i += 2;
 163             } else {
 164                 // just extend the lower 6 bits
 165                 dest[index++] = (src[i] & 0x3f) | ((src[i] & 1<<5) ? 0xC0 : 0);
 166                 ++i;
 167             }
 168         }
 169     }
 170     return index;
 171 }