bzip2.js 13 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365
  1. /*
  2. bzip2.js - a small bzip2 decompression implementation
  3. Copyright 2011 by antimatter15 (antimatter15@gmail.com)
  4. Based on micro-bunzip by Rob Landley (rob@landley.net).
  5. Copyright (c) 2011 by antimatter15 (antimatter15@gmail.com).
  6. Permission is hereby granted, free of charge, to any person obtaining a
  7. copy of this software and associated documentation files (the "Software"),
  8. to deal in the Software without restriction, including without limitation
  9. the rights to use, copy, modify, merge, publish, distribute, sublicense,
  10. and/or sell copies of the Software, and to permit persons to whom the
  11. Software is furnished to do so, subject to the following conditions:
  12. The above copyright notice and this permission notice shall be included
  13. in all copies or substantial portions of the Software.
  14. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
  15. EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  16. MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
  17. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
  18. DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
  19. TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH
  20. THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  21. */
  22. function Bzip2Error(message) {
  23. this.name = 'Bzip2Error';
  24. this.message = message;
  25. this.stack = (new Error()).stack;
  26. }
  27. Bzip2Error.prototype = new Error;
  28. var message = {
  29. Error: function(message) {throw new Bzip2Error(message);}
  30. };
  31. var bzip2 = {};
  32. bzip2.Bzip2Error = Bzip2Error;
  33. bzip2.crcTable =
  34. [
  35. 0x00000000, 0x04c11db7, 0x09823b6e, 0x0d4326d9,
  36. 0x130476dc, 0x17c56b6b, 0x1a864db2, 0x1e475005,
  37. 0x2608edb8, 0x22c9f00f, 0x2f8ad6d6, 0x2b4bcb61,
  38. 0x350c9b64, 0x31cd86d3, 0x3c8ea00a, 0x384fbdbd,
  39. 0x4c11db70, 0x48d0c6c7, 0x4593e01e, 0x4152fda9,
  40. 0x5f15adac, 0x5bd4b01b, 0x569796c2, 0x52568b75,
  41. 0x6a1936c8, 0x6ed82b7f, 0x639b0da6, 0x675a1011,
  42. 0x791d4014, 0x7ddc5da3, 0x709f7b7a, 0x745e66cd,
  43. 0x9823b6e0, 0x9ce2ab57, 0x91a18d8e, 0x95609039,
  44. 0x8b27c03c, 0x8fe6dd8b, 0x82a5fb52, 0x8664e6e5,
  45. 0xbe2b5b58, 0xbaea46ef, 0xb7a96036, 0xb3687d81,
  46. 0xad2f2d84, 0xa9ee3033, 0xa4ad16ea, 0xa06c0b5d,
  47. 0xd4326d90, 0xd0f37027, 0xddb056fe, 0xd9714b49,
  48. 0xc7361b4c, 0xc3f706fb, 0xceb42022, 0xca753d95,
  49. 0xf23a8028, 0xf6fb9d9f, 0xfbb8bb46, 0xff79a6f1,
  50. 0xe13ef6f4, 0xe5ffeb43, 0xe8bccd9a, 0xec7dd02d,
  51. 0x34867077, 0x30476dc0, 0x3d044b19, 0x39c556ae,
  52. 0x278206ab, 0x23431b1c, 0x2e003dc5, 0x2ac12072,
  53. 0x128e9dcf, 0x164f8078, 0x1b0ca6a1, 0x1fcdbb16,
  54. 0x018aeb13, 0x054bf6a4, 0x0808d07d, 0x0cc9cdca,
  55. 0x7897ab07, 0x7c56b6b0, 0x71159069, 0x75d48dde,
  56. 0x6b93dddb, 0x6f52c06c, 0x6211e6b5, 0x66d0fb02,
  57. 0x5e9f46bf, 0x5a5e5b08, 0x571d7dd1, 0x53dc6066,
  58. 0x4d9b3063, 0x495a2dd4, 0x44190b0d, 0x40d816ba,
  59. 0xaca5c697, 0xa864db20, 0xa527fdf9, 0xa1e6e04e,
  60. 0xbfa1b04b, 0xbb60adfc, 0xb6238b25, 0xb2e29692,
  61. 0x8aad2b2f, 0x8e6c3698, 0x832f1041, 0x87ee0df6,
  62. 0x99a95df3, 0x9d684044, 0x902b669d, 0x94ea7b2a,
  63. 0xe0b41de7, 0xe4750050, 0xe9362689, 0xedf73b3e,
  64. 0xf3b06b3b, 0xf771768c, 0xfa325055, 0xfef34de2,
  65. 0xc6bcf05f, 0xc27dede8, 0xcf3ecb31, 0xcbffd686,
  66. 0xd5b88683, 0xd1799b34, 0xdc3abded, 0xd8fba05a,
  67. 0x690ce0ee, 0x6dcdfd59, 0x608edb80, 0x644fc637,
  68. 0x7a089632, 0x7ec98b85, 0x738aad5c, 0x774bb0eb,
  69. 0x4f040d56, 0x4bc510e1, 0x46863638, 0x42472b8f,
  70. 0x5c007b8a, 0x58c1663d, 0x558240e4, 0x51435d53,
  71. 0x251d3b9e, 0x21dc2629, 0x2c9f00f0, 0x285e1d47,
  72. 0x36194d42, 0x32d850f5, 0x3f9b762c, 0x3b5a6b9b,
  73. 0x0315d626, 0x07d4cb91, 0x0a97ed48, 0x0e56f0ff,
  74. 0x1011a0fa, 0x14d0bd4d, 0x19939b94, 0x1d528623,
  75. 0xf12f560e, 0xf5ee4bb9, 0xf8ad6d60, 0xfc6c70d7,
  76. 0xe22b20d2, 0xe6ea3d65, 0xeba91bbc, 0xef68060b,
  77. 0xd727bbb6, 0xd3e6a601, 0xdea580d8, 0xda649d6f,
  78. 0xc423cd6a, 0xc0e2d0dd, 0xcda1f604, 0xc960ebb3,
  79. 0xbd3e8d7e, 0xb9ff90c9, 0xb4bcb610, 0xb07daba7,
  80. 0xae3afba2, 0xaafbe615, 0xa7b8c0cc, 0xa379dd7b,
  81. 0x9b3660c6, 0x9ff77d71, 0x92b45ba8, 0x9675461f,
  82. 0x8832161a, 0x8cf30bad, 0x81b02d74, 0x857130c3,
  83. 0x5d8a9099, 0x594b8d2e, 0x5408abf7, 0x50c9b640,
  84. 0x4e8ee645, 0x4a4ffbf2, 0x470cdd2b, 0x43cdc09c,
  85. 0x7b827d21, 0x7f436096, 0x7200464f, 0x76c15bf8,
  86. 0x68860bfd, 0x6c47164a, 0x61043093, 0x65c52d24,
  87. 0x119b4be9, 0x155a565e, 0x18197087, 0x1cd86d30,
  88. 0x029f3d35, 0x065e2082, 0x0b1d065b, 0x0fdc1bec,
  89. 0x3793a651, 0x3352bbe6, 0x3e119d3f, 0x3ad08088,
  90. 0x2497d08d, 0x2056cd3a, 0x2d15ebe3, 0x29d4f654,
  91. 0xc5a92679, 0xc1683bce, 0xcc2b1d17, 0xc8ea00a0,
  92. 0xd6ad50a5, 0xd26c4d12, 0xdf2f6bcb, 0xdbee767c,
  93. 0xe3a1cbc1, 0xe760d676, 0xea23f0af, 0xeee2ed18,
  94. 0xf0a5bd1d, 0xf464a0aa, 0xf9278673, 0xfde69bc4,
  95. 0x89b8fd09, 0x8d79e0be, 0x803ac667, 0x84fbdbd0,
  96. 0x9abc8bd5, 0x9e7d9662, 0x933eb0bb, 0x97ffad0c,
  97. 0xafb010b1, 0xab710d06, 0xa6322bdf, 0xa2f33668,
  98. 0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4
  99. ];
  100. bzip2.array = function(bytes) {
  101. var bit = 0, byte = 0;
  102. var BITMASK = [0, 0x01, 0x03, 0x07, 0x0F, 0x1F, 0x3F, 0x7F, 0xFF ];
  103. return function(n) {
  104. var result = 0;
  105. while(n > 0) {
  106. var left = 8 - bit;
  107. if (n >= left) {
  108. result <<= left;
  109. result |= (BITMASK[left] & bytes[byte++]);
  110. bit = 0;
  111. n -= left;
  112. } else {
  113. result <<= n;
  114. result |= ((bytes[byte] & (BITMASK[n] << (8 - n - bit))) >> (8 - n - bit));
  115. bit += n;
  116. n = 0;
  117. }
  118. }
  119. return result;
  120. }
  121. }
  122. bzip2.simple = function(srcbuffer, stream) {
  123. var bits = bzip2.array(srcbuffer);
  124. var size = bzip2.header(bits);
  125. var ret = false;
  126. var bufsize = 100000 * size;
  127. var buf = new Int32Array(bufsize);
  128. do {
  129. ret = bzip2.decompress(bits, stream, buf, bufsize);
  130. } while(!ret);
  131. }
  132. bzip2.header = function(bits) {
  133. this.byteCount = new Int32Array(256);
  134. this.symToByte = new Uint8Array(256);
  135. this.mtfSymbol = new Int32Array(256);
  136. this.selectors = new Uint8Array(0x8000);
  137. if (bits(8*3) != 4348520) message.Error("No magic number found");
  138. var i = bits(8) - 48;
  139. if (i < 1 || i > 9) message.Error("Not a BZIP archive");
  140. return i;
  141. };
  142. //takes a function for reading the block data (starting with 0x314159265359)
  143. //a block size (0-9) (optional, defaults to 9)
  144. //a length at which to stop decompressing and return the output
  145. bzip2.decompress = function(bits, stream, buf, bufsize, streamCRC) {
  146. var MAX_HUFCODE_BITS = 20;
  147. var MAX_SYMBOLS = 258;
  148. var SYMBOL_RUNA = 0;
  149. var SYMBOL_RUNB = 1;
  150. var GROUP_SIZE = 50;
  151. var crc = 0 ^ (-1);
  152. for(var h = '', i = 0; i < 6; i++) h += bits(8).toString(16);
  153. if (h == "177245385090") {
  154. var finalCRC = bits(32)|0;
  155. if (finalCRC !== streamCRC) message.Error("Error in bzip2: crc32 do not match");
  156. // align stream to byte
  157. bits(null);
  158. return null; // reset streamCRC for next call
  159. }
  160. if (h != "314159265359") message.Error("eek not valid bzip data");
  161. var crcblock = bits(32)|0; // CRC code
  162. if (bits(1)) message.Error("unsupported obsolete version");
  163. var origPtr = bits(24);
  164. if (origPtr > bufsize) message.Error("Initial position larger than buffer size");
  165. var t = bits(16);
  166. var symTotal = 0;
  167. for (i = 0; i < 16; i++) {
  168. if (t & (1 << (15 - i))) {
  169. var k = bits(16);
  170. for(j = 0; j < 16; j++) {
  171. if (k & (1 << (15 - j))) {
  172. this.symToByte[symTotal++] = (16 * i) + j;
  173. }
  174. }
  175. }
  176. }
  177. var groupCount = bits(3);
  178. if (groupCount < 2 || groupCount > 6) message.Error("another error");
  179. var nSelectors = bits(15);
  180. if (nSelectors == 0) message.Error("meh");
  181. for(var i = 0; i < groupCount; i++) this.mtfSymbol[i] = i;
  182. for(var i = 0; i < nSelectors; i++) {
  183. for(var j = 0; bits(1); j++) if (j >= groupCount) message.Error("whoops another error");
  184. var uc = this.mtfSymbol[j];
  185. for(var k = j-1; k>=0; k--) {
  186. this.mtfSymbol[k+1] = this.mtfSymbol[k];
  187. }
  188. this.mtfSymbol[0] = uc;
  189. this.selectors[i] = uc;
  190. }
  191. var symCount = symTotal + 2;
  192. var groups = [];
  193. var length = new Uint8Array(MAX_SYMBOLS),
  194. temp = new Uint16Array(MAX_HUFCODE_BITS+1);
  195. var hufGroup;
  196. for(var j = 0; j < groupCount; j++) {
  197. t = bits(5); //lengths
  198. for(var i = 0; i < symCount; i++) {
  199. while(true){
  200. if (t < 1 || t > MAX_HUFCODE_BITS) message.Error("I gave up a while ago on writing error messages");
  201. if (!bits(1)) break;
  202. if (!bits(1)) t++;
  203. else t--;
  204. }
  205. length[i] = t;
  206. }
  207. var minLen, maxLen;
  208. minLen = maxLen = length[0];
  209. for(var i = 1; i < symCount; i++) {
  210. if (length[i] > maxLen) maxLen = length[i];
  211. else if (length[i] < minLen) minLen = length[i];
  212. }
  213. hufGroup = groups[j] = {};
  214. hufGroup.permute = new Int32Array(MAX_SYMBOLS);
  215. hufGroup.limit = new Int32Array(MAX_HUFCODE_BITS + 1);
  216. hufGroup.base = new Int32Array(MAX_HUFCODE_BITS + 1);
  217. hufGroup.minLen = minLen;
  218. hufGroup.maxLen = maxLen;
  219. var base = hufGroup.base;
  220. var limit = hufGroup.limit;
  221. var pp = 0;
  222. for(var i = minLen; i <= maxLen; i++)
  223. for(var t = 0; t < symCount; t++)
  224. if (length[t] == i) hufGroup.permute[pp++] = t;
  225. for(i = minLen; i <= maxLen; i++) temp[i] = limit[i] = 0;
  226. for(i = 0; i < symCount; i++) temp[length[i]]++;
  227. pp = t = 0;
  228. for(i = minLen; i < maxLen; i++) {
  229. pp += temp[i];
  230. limit[i] = pp - 1;
  231. pp <<= 1;
  232. base[i+1] = pp - (t += temp[i]);
  233. }
  234. limit[maxLen] = pp + temp[maxLen] - 1;
  235. base[minLen] = 0;
  236. }
  237. for(var i = 0; i < 256; i++) {
  238. this.mtfSymbol[i] = i;
  239. this.byteCount[i] = 0;
  240. }
  241. var runPos, count, symCount, selector;
  242. runPos = count = symCount = selector = 0;
  243. while(true) {
  244. if (!(symCount--)) {
  245. symCount = GROUP_SIZE - 1;
  246. if (selector >= nSelectors) message.Error("meow i'm a kitty, that's an error");
  247. hufGroup = groups[this.selectors[selector++]];
  248. base = hufGroup.base;
  249. limit = hufGroup.limit;
  250. }
  251. i = hufGroup.minLen;
  252. j = bits(i);
  253. while(true) {
  254. if (i > hufGroup.maxLen) message.Error("rawr i'm a dinosaur");
  255. if (j <= limit[i]) break;
  256. i++;
  257. j = (j << 1) | bits(1);
  258. }
  259. j -= base[i];
  260. if (j < 0 || j >= MAX_SYMBOLS) message.Error("moo i'm a cow");
  261. var nextSym = hufGroup.permute[j];
  262. if (nextSym == SYMBOL_RUNA || nextSym == SYMBOL_RUNB) {
  263. if (!runPos){
  264. runPos = 1;
  265. t = 0;
  266. }
  267. if (nextSym == SYMBOL_RUNA) t += runPos;
  268. else t += 2 * runPos;
  269. runPos <<= 1;
  270. continue;
  271. }
  272. if (runPos) {
  273. runPos = 0;
  274. if (count + t > bufsize) message.Error("Boom.");
  275. uc = this.symToByte[this.mtfSymbol[0]];
  276. this.byteCount[uc] += t;
  277. while(t--) buf[count++] = uc;
  278. }
  279. if (nextSym > symTotal) break;
  280. if (count >= bufsize) message.Error("I can't think of anything. Error");
  281. i = nextSym - 1;
  282. uc = this.mtfSymbol[i];
  283. for(var k = i-1; k>=0; k--) {
  284. this.mtfSymbol[k+1] = this.mtfSymbol[k];
  285. }
  286. this.mtfSymbol[0] = uc
  287. uc = this.symToByte[uc];
  288. this.byteCount[uc]++;
  289. buf[count++] = uc;
  290. }
  291. if (origPtr < 0 || origPtr >= count) message.Error("I'm a monkey and I'm throwing something at someone, namely you");
  292. var j = 0;
  293. for(var i = 0; i < 256; i++) {
  294. k = j + this.byteCount[i];
  295. this.byteCount[i] = j;
  296. j = k;
  297. }
  298. for(var i = 0; i < count; i++) {
  299. uc = buf[i] & 0xff;
  300. buf[this.byteCount[uc]] |= (i << 8);
  301. this.byteCount[uc]++;
  302. }
  303. var pos = 0, current = 0, run = 0;
  304. if (count) {
  305. pos = buf[origPtr];
  306. current = (pos & 0xff);
  307. pos >>= 8;
  308. run = -1;
  309. }
  310. count = count;
  311. var copies, previous, outbyte;
  312. while(count) {
  313. count--;
  314. previous = current;
  315. pos = buf[pos];
  316. current = pos & 0xff;
  317. pos >>= 8;
  318. if (run++ == 3) {
  319. copies = current;
  320. outbyte = previous;
  321. current = -1;
  322. } else {
  323. copies = 1;
  324. outbyte = current;
  325. }
  326. while(copies--) {
  327. crc = ((crc << 8) ^ this.crcTable[((crc>>24) ^ outbyte) & 0xFF])&0xFFFFFFFF; // crc32
  328. stream(outbyte);
  329. }
  330. if (current != previous) run = 0;
  331. }
  332. crc = (crc ^ (-1)) >>> 0;
  333. if ((crc|0) != (crcblock|0)) message.Error("Error in bzip2: crc32 do not match");
  334. streamCRC = (crc ^ ((streamCRC << 1) | (streamCRC >>> 31))) & 0xFFFFFFFF;
  335. return streamCRC;
  336. }
  337. module.exports = bzip2;