LZW压缩算法（lzw压缩编码）

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 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 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 using System; using System.IO; namespace Gif.Components { public class LZWEncoder { private static readonly int EOF = -1; private int imgW, imgH; private byte[] pixAry; private int initCodeSize; private int remaining; private int curPixel; // GIFCOMPR.C - GIF Image compression routines // // Lempel-Ziv compression based on 'compress'. GIF modifications by // David Rowley (mgardi@watdcsu.waterloo.edu) // General DEFINEs static readonly int BITS = 12; static readonly int HSIZE = 5003; // 80% occupancy // GIF Image compression - modified 'compress' // // Based on: compress.c - File compression ala IEEE Computer, June 1984. // // By Authors: Spencer W. Thomas (decvax!harpo!utah-cs!utah-gr!thomas) // Jim McKie (decvax!mcvax!jim) // Steve Davies (decvax!vax135!petsd!peora!srd) // Ken Turkowski (decvax!decwrl!turtlevax!ken) // James A. Woods (decvax!ihnp4!ames!jaw) // Joe Orost (decvax!vax135!petsd!joe) int n_bits; // number of bits/code int maxbits = BITS; // user settable max # bits/code int maxcode; // maximum code, given n_bits int maxmaxcode = 1 << BITS; // should NEVER generate this code int[] htab = new int[HSIZE];//这个是放hash的筒子,在这里面可以很快的找到1个key int[] codetab = new int[HSIZE]; int hsize = HSIZE; // for dynamic table sizing int free_ent = 0; // first unused entry // block compression parameters -- after all codes are used up, // and compression rate changes, start over. bool clear_flg = false; // Algorithm: use open addressing double hashing (no chaining) on the // prefix code / next character combination. We do a variant of Knuth's // algorithm D (vol. 3, sec. 6.4) along with G. Knott's relatively-prime // secondary probe. Here, the modular division first probe is gives way // to a faster exclusive-or manipulation. Also do block compression with // an adaptive reset, whereby the code table is cleared when the compression // ratio decreases, but after the table fills. The variable-length output // codes are re-sized at this point, and a special CLEAR code is generated // for the decompressor. Late addition: construct the table according to // file size for noticeable speed improvement on small files. Please direct // questions about this implementation to ames!jaw. int g_init_bits; int ClearCode; int EOFCode; // output // // Output the given code. // Inputs: // code: A n_bits-bit integer. If == -1, then EOF. This assumes // that n_bits =< wordsize - 1. // Outputs: // Outputs code to the file. // Assumptions: // Chars are 8 bits long. // Algorithm: // Maintain a BITS character long buffer (so that 8 codes will // fit in it exactly). Use the VAX insv instruction to insert each // code in turn. When the buffer fills up empty it and start over. int cur_accum = 0; int cur_bits = 0; int [] masks = { 0x0000, 0x0001, 0x0003, 0x0007, 0x000F, 0x001F, 0x003F, 0x007F, 0x00FF, 0x01FF, 0x03FF, 0x07FF, 0x0FFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF }; // Number of characters so far in this 'packet' int a_count; // Define the storage for the packet accumulator byte[] accum = new byte[256]; //---------------------------------------------------------------------------- public LZWEncoder(int width, int height, byte[] pixels, int color_depth) { imgW = width; imgH = height; pixAry = pixels; initCodeSize = Math.Max(2, color_depth); } // Add a character to the end of the current packet, and if it is 254 // characters, flush the packet to disk. void Add(byte c, Stream outs) { accum[a_count++] = c; if (a_count >= 254) Flush(outs); } // Clear out the hash table // table clear for block compress void ClearTable(Stream outs) { ResetCodeTable(hsize); free_ent = ClearCode + 2; clear_flg = true; Output(ClearCode, outs); } // reset code table // 全部初始化为-1 void ResetCodeTable(int hsize) { for (int i = 0; i < hsize; ++i) htab[i] = -1; } void Compress(int init_bits, Stream outs) { int fcode; int i /* = 0 */; int c; int ent; int disp; int hsize_reg; int hshift; // Set up the globals: g_init_bits - initial number of bits //原始数据的字长,在gif文件中，原始数据的字长可以为1(单色图),4(16色)，和8(256色) //开始的时候先加上1 //但是当原始数据长度为1的时候，开始为3 //因此原始长度1->3,4->5,8->9 //?为何原始数据字长为1的时候，开始长度为3呢？? //如果+1=2，只能表示四种状态，加上clearcode和endcode就用完了。所以必须扩展到3 g_init_bits = init_bits; // Set up the necessary values //是否需要加清除标志 //GIF为了提高压缩率，采用的是变长的字长(VCL)。比如说原始数据是8位，那么开始先加上1位(8+1=9) //当标号到2^9=512的时候，超过了当前长度9所能表现的最大值，此时后面的标号就必须用10位来表示 //以此类推，当标号到2^12的时候，因为最大为12,不能继续扩展了，需要在2^12=4096的位置上插入一个ClearCode,表示从这往后，从9位重新再来了 clear_flg = false; n_bits = g_init_bits; //获得n位数能表述的最大值(gif图像中开始一般为3,5,9，故maxcode一般为7,31,511) maxcode = MaxCode(n_bits); //表示从这里我重新开始构造字典字典了，以前的所有标记作废， //开始使用新的标记。这个标号集的大小多少比较合适呢？据说理论上是越大压缩率越高（我个人感觉太大了也不见得就好）， //不过处理的开销也呈指数增长 //gif规定，clearcode的值为原始数据最大字长所能表达的数值+1;比如原始数据长度为8,则clearcode=1<<(9-1)=256 ClearCode = 1 << (init_bits - 1); //结束标志为clearcode+1 EOFCode = ClearCode + 1; //这个是解除结束的 free_ent = ClearCode + 2; //清楚数量 a_count = 0; // clear packet //从图像中获得下一个像素 ent = NextPixel(); hshift = 0; for (fcode = hsize; fcode < 65536; fcode *= 2) ++hshift; //设置hash码范围 hshift = 8 - hshift; // set hash code range bound hsize_reg = hsize; //清除固定大小的hash表，用于存储标记，这个相当于字典 ResetCodeTable(hsize_reg); // clear hash table Output(ClearCode, outs); outer_loop : while ((c = NextPixel()) != EOF) { fcode = (c << maxbits) + ent; i = (c << hshift) ^ ent; // xor hashing //嘿嘿,小样,又来了,我认识你 if (htab[i] == fcode) { ent = codetab[i]; continue; } //这小子,新来的 else if (htab[i] >= 0) // non-empty slot { disp = hsize_reg - i; // secondary hash (after G. Knott) if (i == 0) disp = 1; do { if ((i -= disp) < 0) i += hsize_reg; if (htab[i] == fcode) { ent = codetab[i]; goto outer_loop; } } while (htab[i] >= 0); } Output(ent, outs); //从这里可以看出,ent就是前缀（prefix）,而当前正在处理的字符标志就是后缀（suffix） ent = c; //判断终止结束符是否超过当前位数所能表述的范围 if (free_ent < maxmaxcode) { //如果没有超 codetab[i] = free_ent++; // code -> hashtable //hash表里面建立相应索引 htab[i] = fcode; } else //说明超过了当前所能表述的范围,清空字典,重新再来 ClearTable(outs); } // Put out the final code. Output(ent, outs); Output(EOFCode, outs); } //---------------------------------------------------------------------------- public void Encode( Stream os) { os.WriteByte( Convert.ToByte( initCodeSize) ); // write "initial code size" byte //这个图像包含多少个像素 remaining = imgW * imgH; // reset navigation variables //当前处理的像素索引 curPixel = 0; Compress(initCodeSize + 1, os); // compress and write the pixel data os.WriteByte(0); // write block terminator } // Flush the packet to disk, and reset the accumulator void Flush(Stream outs) { if (a_count > 0) { outs.WriteByte( Convert.ToByte( a_count )); outs.Write(accum, 0, a_count); a_count = 0; } } /// <summary> /// 获得n位数所能表达的最大数值 /// </summary> /// <param name="n_bits">位数，一般情况下n_bits = 9</param> /// <returns>最大值,例如n_bits=8,则返回值就为2^8-1=255</returns> int MaxCode(int n_bits) { return (1 << n_bits) - 1; } //---------------------------------------------------------------------------- // Return the next pixel from the image //---------------------------------------------------------------------------- /// <summary> /// 从图像中获得下一个像素 /// </summary> /// <returns></returns> private int NextPixel() { //还剩多少个像素没有处理 //如果没有了,返回结束标志 if (remaining == 0) return EOF; //否则处理下一个,并将未处理像素数目-1 --remaining; //当前处理的像素 int temp = curPixel + 1; //如果当前处理像素在像素范围之内 if ( temp < pixAry.GetUpperBound( 0 )) { //下一个像素 byte pix = pixAry[curPixel++]; return pix & 0xff; } return 0xff; } /// <summary> /// 输出字到输出流 /// </summary> /// <param name="code">要输出的字</param> /// <param name="outs">输出流</param> void Output(int code, Stream outs) { //得到当前标志位所能表示的最大标志值 cur_accum &= masks[cur_bits]; if (cur_bits > 0) cur_accum |= (code << cur_bits); else //如果标志位为0,就将当前标号为输入流 cur_accum = code; //当前能标志的最大字长度(9-10-11-12-9-10。。。。。。。) cur_bits += n_bits; //如果当前最大长度大于8 while (cur_bits >= 8) { //向流中输出一个字节 Add((byte) (cur_accum & 0xff), outs); //将当前标号右移8位 cur_accum >>= 8; cur_bits -= 8; } // If the next entry is going to be too big for the code size, // then increase it, if possible. if (free_ent > maxcode || clear_flg) { if (clear_flg) { maxcode = MaxCode(n_bits = g_init_bits); clear_flg = false; } else { ++n_bits; if (n_bits == maxbits) maxcode = maxmaxcode; else maxcode = MaxCode(n_bits); } } if (code == EOFCode) { // At EOF, write the rest of the buffer. while (cur_bits > 0) { Add((byte) (cur_accum & 0xff), outs); cur_accum >>= 8; cur_bits -= 8; } Flush(outs); } } } }