/* inftrees.c -- generate Huffman trees for efficient decoding * Copyright (C) 1995-2022 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ #include "zutil.h" #include "inftrees.h" #define MAXBITS 15 const char inflate_copyright[] = " inflate 1.2.13 Copyright 1995-2022 Mark Adler "; /* If you use the zlib library in a product, an acknowledgment is welcome in the documentation of your product. If for some reason you cannot include such an acknowledgment, I would appreciate that you keep this copyright string in the executable of your product. */ /* Build a set of tables to decode the provided canonical Huffman code. The code lengths are lens[0..codes-1]. The result starts at *table, whose indices are 0..2^bits-1. work is a writable array of at least lens shorts, which is used as a work area. type is the type of code to be generated, CODES, LENS, or DISTS. On return, zero is success, -1 is an invalid code, and +1 means that ENOUGH isn't enough. table on return points to the next available entry's address. bits is the requested root table index bits, and on return it is the actual root table index bits. It will differ if the request is greater than the longest code or if it is less than the shortest code. */ int ZLIB_INTERNAL inflate_table(type, lens, codes, table, bits, work) codetype type; unsigned short FAR *lens; unsigned codes; code FAR * FAR *table; unsigned FAR *bits; unsigned short FAR *work; { unsigned len; /* a code's length in bits */ unsigned sym; /* index of code symbols */ unsigned min, max; /* minimum and maximum code lengths */ unsigned root; /* number of index bits for root table */ unsigned curr; /* number of index bits for current table */ unsigned drop; /* code bits to drop for sub-table */ int left; /* number of prefix codes available */ unsigned used; /* code entries in table used */ unsigned huff; /* Huffman code */ unsigned incr; /* for incrementing code, index */ unsigned fill; /* index for replicating entries */ unsigned low; /* low bits for current root entry */ unsigned mask; /* mask for low root bits */ code here; /* table entry for duplication */ code FAR *next; /* next available space in table */ const unsigned short FAR *base; /* base value table to use */ const unsigned short FAR *extra; /* extra bits table to use */ unsigned match; /* use base and extra for symbol >= match */ unsigned short count[MAXBITS+1]; /* number of codes of each length */ unsigned short offs[MAXBITS+1]; /* offsets in table for each length */ static const unsigned short lbase[31] = { /* Length codes 257..285 base */ 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; static const unsigned short lext[31] = { /* Length codes 257..285 extra */ 16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18, 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 194, 65}; static const unsigned short dbase[32] = { /* Distance codes 0..29 base */ 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, 8193, 12289, 16385, 24577, 0, 0}; static const unsigned short dext[32] = { /* Distance codes 0..29 extra */ 16, 16, 16, 16, 17, 17, 18, 18, 19, 19, 20, 20, 21, 21, 22, 22, 23, 23, 24, 24, 25, 25, 26, 26, 27, 27, 28, 28, 29, 29, 64, 64}; /* Process a set of code lengths to create a canonical Huffman code. The code lengths are lens[0..codes-1]. Each length corresponds to the symbols 0..codes-1. The Huffman code is generated by first sorting the symbols by length from short to long, and retaining the symbol order for codes with equal lengths. Then the code starts with all zero bits for the first code of the shortest length, and the codes are integer increments for the same length, and zeros are appended as the length increases. For the deflate format, these bits are stored backwards from their more natural integer increment ordering, and so when the decoding tables are built in the large loop below, the integer codes are incremented backwards. This routine assumes, but does not check, that all of the entries in lens[] are in the range 0..MAXBITS. The caller must assure this. 1..MAXBITS is interpreted as that code length. zero means that that symbol does not occur in this code. The codes are sorted by computing a count of codes for each length, creating from that a table of starting indices for each length in the sorted table, and then entering the symbols in order in the sorted table. The sorted table is work[], with that space being provided by the caller. The length counts are used for other purposes as well, i.e. finding the minimum and maximum length codes, determining if there are any codes at all, checking for a valid set of lengths, and looking ahead at length counts to determine sub-table sizes when building the decoding tables. */ /* accumulate lengths for codes (assumes lens[] all in 0..MAXBITS) */ for (len = 0; len <= MAXBITS; len++) count[len] = 0; for (sym = 0; sym < codes; sym++) count[lens[sym]]++; /* bound code lengths, force root to be within code lengths */ root = *bits; for (max = MAXBITS; max >= 1; max--) if (count[max] != 0) break; if (root > max) root = max; if (max == 0) { /* no symbols to code at all */ here.op = (unsigned char)64; /* invalid code marker */ here.bits = (unsigned char)1; here.val = (unsigned short)0; *(*table)++ = here; /* make a table to force an error */ *(*table)++ = here; *bits = 1; return 0; /* no symbols, but wait for decoding to report error */ } for (min = 1; min < max; min++) if (count[min] != 0) break; if (root < min) root = min; /* check for an over-subscribed or incomplete set of lengths */ left = 1; for (len = 1; len <= MAXBITS; len++) { left <<= 1; left -= count[len]; if (left < 0) return -1; /* over-subscribed */ } if (left > 0 && (type == CODES || max != 1)) return -1; /* incomplete set */ /* generate offsets into symbol table for each length for sorting */ offs[1] = 0; for (len = 1; len < MAXBITS; len++) offs[len + 1] = offs[len] + count[len]; /* sort symbols by length, by symbol order within each length */ for (sym = 0; sym < codes; sym++) if (lens[sym] != 0) work[offs[lens[sym]]++] = (unsigned short)sym; /* Create and fill in decoding tables. In this loop, the table being filled is at next and has curr index bits. The code being used is huff with length len. That code is converted to an index by dropping drop bits off of the bottom. For codes where len is less than drop + curr, those top drop + curr - len bits are incremented through all values to fill the table with replicated entries. root is the number of index bits for the root table. When len exceeds root, sub-tables are created pointed to by the root entry with an index of the low root bits of huff. This is saved in low to check for when a new sub-table should be started. drop is zero when the root table is being filled, and drop is root when sub-tables are being filled. When a new sub-table is needed, it is necessary to look ahead in the code lengths to determine what size sub-table is needed. The length counts are used for this, and so count[] is decremented as codes are entered in the tables. used keeps track of how many table entries have been allocated from the provided *table space. It is checked for LENS and DIST tables against the constants ENOUGH_LENS and ENOUGH_DISTS to guard against changes in the initial root table size constants. See the comments in inftrees.h for more information. sym increments through all symbols, and the loop terminates when all codes of length max, i.e. all codes, have been processed. This routine permits incomplete codes, so another loop after this one fills in the rest of the decoding tables with invalid code markers. */ /* set up for code type */ switch (type) { case CODES: base = extra = work; /* dummy value--not used */ match = 20; break; case LENS: base = lbase; extra = lext; match = 257; break; default: /* DISTS */ base = dbase; extra = dext; match = 0; } /* initialize state for loop */ huff = 0; /* starting code */ sym = 0; /* starting code symbol */ len = min; /* starting code length */ next = *table; /* current table to fill in */ curr = root; /* current table index bits */ drop = 0; /* current bits to drop from code for index */ low = (unsigned)(-1); /* trigger new sub-table when len > root */ used = 1U << root; /* use root table entries */ mask = used - 1; /* mask for comparing low */ /* check available table space */ if ((type == LENS && used > ENOUGH_LENS) || (type == DISTS && used > ENOUGH_DISTS)) return 1; /* process all codes and make table entries */ for (;;) { /* create table entry */ here.bits = (unsigned char)(len - drop); if (work[sym] + 1U < match) { here.op = (unsigned char)0; here.val = work[sym]; } else if (work[sym] >= match) { here.op = (unsigned char)(extra[work[sym] - match]); here.val = base[work[sym] - match]; } else { here.op = (unsigned char)(32 + 64); /* end of block */ here.val = 0; } /* replicate for those indices with low len bits equal to huff */ incr = 1U << (len - drop); fill = 1U << curr; min = fill; /* save offset to next table */ do { fill -= incr; next[(huff >> drop) + fill] = here; } while (fill != 0); /* backwards increment the len-bit code huff */ incr = 1U << (len - 1); while (huff & incr) incr >>= 1; if (incr != 0) { huff &= incr - 1; huff += incr; } else huff = 0; /* go to next symbol, update count, len */ sym++; if (--(count[len]) == 0) { if (len == max) break; len = lens[work[sym]]; } /* create new sub-table if needed */ if (len > root && (huff & mask) != low) { /* if first time, transition to sub-tables */ if (drop == 0) drop = root; /* increment past last table */ next += min; /* here min is 1 << curr */ /* determine length of next table */ curr = len - drop; left = (int)(1 << curr); while (curr + drop < max) { left -= count[curr + drop]; if (left <= 0) break; curr++; left <<= 1; } /* check for enough space */ used += 1U << curr; if ((type == LENS && used > ENOUGH_LENS) || (type == DISTS && used > ENOUGH_DISTS)) return 1; /* point entry in root table to sub-table */ low = huff & mask; (*table)[low].op = (unsigned char)curr; (*table)[low].bits = (unsigned char)root; (*table)[low].val = (unsigned short)(next - *table); } } /* fill in remaining table entry if code is incomplete (guaranteed to have at most one remaining entry, since if the code is incomplete, the maximum code length that was allowed to get this far is one bit) */ if (huff != 0) { here.op = (unsigned char)64; /* invalid code marker */ here.bits = (unsigned char)(len - drop); here.val = (unsigned short)0; next[huff] = here; } /* set return parameters */ *table += used; *bits = root; return 0; } href='#n293'>293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359