/* * Copyright (c) 1995 Matthias Pfaller. * * Most of this code is from the unzip512 distribution and was put * in the public domain by Mark Adler 1994. * * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by Matthias Pfaller. * 4. The name of the author may not be used to endorse or promote products * derived from this software without specific prior written permission * * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * $Id: inflate.c,v 1.1 1995/10/18 08:51:23 deraadt Exp $ */ #include #include #include #include "stand.h" #include "samachdep.h" #ifndef EOF #define EOF -1 #endif typedef unsigned char uch; /* code assumes unsigned bytes; these type- */ typedef unsigned short ush; /* defs replace byte/UWORD/ULONG (which are */ typedef unsigned long ulg; /* predefined on some systems) & match zip */ extern int qflag; extern uch slide[]; extern ulg crc_32_tab[]; #define NEXTBYTE nextbyte() #define FLUSH(n) flush(n) #define WSIZE 0x8000 #define memzero(dest, len) bzero(dest, len) /* Function prototypes */ #ifndef OF # ifdef __STDC__ # define OF(a) a # else /* !__STDC__ */ # define OF(a) () # endif /* ?__STDC__ */ #endif /* From: funzip.c -- put in the public domain by Mark Adler */ #define VERSION "3.83 of 28 August 1994" /* All funzip does is take a zip file from stdin and decompress the first entry to stdout. The entry has to be either deflated or stored. If the entry is encrypted, then the decryption password must be supplied on the command line as the first argument. funzip needs to be linked with inflate.o and crypt.o compiled from the unzip source. If decryption is desired, the full version of crypt.c (and crypt.h) from zcrypt21.zip or later must be used. */ /* compression methods */ #define STORED 0 #define DEFLATED 8 /* PKZIP header definitions */ #define ZIPMAG 0x4b50 /* two-byte zip lead-in */ #define LOCREM 0x0403 /* remaining two bytes in zip signature */ #define LOCSIG 0x04034b50L /* full signature */ #define LOCFLG 4 /* offset of bit flag */ #define CRPFLG 1 /* bit for encrypted entry */ #define EXTFLG 8 /* bit for extended local header */ #define LOCHOW 6 /* offset of compression method */ #define LOCTIM 8 /* file mod time (for decryption) */ #define LOCCRC 12 /* offset of crc */ #define LOCSIZ 16 /* offset of compressed size */ #define LOCLEN 20 /* offset of uncompressed length */ #define LOCFIL 24 /* offset of file name field length */ #define LOCEXT 26 /* offset of extra field length */ #define LOCHDR 28 /* size of local header, including LOCREM */ #define EXTHDR 16 /* size of extended local header, inc sig */ /* GZIP header definitions */ #define GZPMAG 0x8b1f /* two-byte gzip lead-in */ #define GZPHOW 0 /* offset of method number */ #define GZPFLG 1 /* offset of gzip flags */ #define GZPMUL 2 /* bit for multiple-part gzip file */ #define GZPISX 4 /* bit for extra field present */ #define GZPISF 8 /* bit for filename present */ #define GZPISC 16 /* bit for comment present */ #define GZPISE 32 /* bit for encryption */ #define GZPTIM 2 /* offset of Unix file modification time */ #define GZPEXF 6 /* offset of extra flags */ #define GZPCOS 7 /* offset of operating system compressed on */ #define GZPHDR 8 /* length of minimal gzip header */ /* Macros for getting two-byte and four-byte header values */ #define SH(p) ((ush)(uch)((p)[0]) | ((ush)(uch)((p)[1]) << 8)) #define LG(p) ((ulg)(SH(p)) | ((ulg)(SH((p)+2)) << 16)) /* Function prototypes */ ulg updcrc OF((uch *, ulg)); int inflate OF((void)); void err OF((int, char *)); /* Globals */ uch *outptr; /* points to next byte in output buffer */ ulg outcnt; /* bytes in output buffer */ ulg outsiz; /* total bytes written to out */ int encrypted; /* flag to turn on decryption */ int qflag = 1; /* turn off messages in inflate.c */ uch slide[WSIZE]; uch *addr, *load, *esym; extern uch *r3, *r6, *r7; int bsize; /* Masks for inflate.c */ ush mask_bits[] = { 0x0000, 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff }; extern uch input_data[]; uch *datap = input_data; struct exec x; int nextbyte() { extern int input_len; if (!(input_len & 0x1fff)) twiddle(); if (input_len-- > 0) return(*datap++); else return(EOF); } int nextblock(p, n) char *p; int n; { extern int input_len; twiddle(); if (input_len < n) return(0); memcpy(p, datap, n); input_len -= n; datap += n; return(n); } ulg updcrc(s, n) uch *s; /* pointer to bytes to pump through */ ulg n; /* number of bytes in s[] */ /* Run a set of bytes through the crc shift register. If s is a NULL pointer, then initialize the crc shift register contents instead. Return the current crc in either case. */ { register ulg c; /* temporary variable */ static ulg crc = 0xffffffffL; /* shift register contents */ if (s == (uch *)NULL) c = 0xffffffffL; else { c = crc; while (n--) c = crc_32_tab[((int)c ^ (*s++)) & 0xff] ^ (c >> 8); } crc = c; return c ^ 0xffffffffL; /* (instead of ~c for 64-bit machines) */ } void nextstate() { static int state = 0; switch (state) { case 0: if (N_BADMAG(x)) panic("Bad exec format\n"); load = addr = (uch *)(x.a_entry & 0x00ffff00); printf("Uncompressing @ 0x%x\n", addr); bsize = x.a_text; if (N_GETMAGIC(x) == ZMAGIC) { bcopy(&x, addr, sizeof(x)); addr += sizeof(x); bsize -= sizeof(x); } printf("%d", x.a_text); state = 1; break; case 1: if (N_GETMAGIC(x) == NMAGIC) while ((int)addr & CLOFSET) *addr++ = 0; bsize = x.a_data; printf("+%d", x.a_data); state = 2; break; case 2: printf("+%d", x.a_bss); bzero(addr, x.a_bss ); addr += x.a_bss; bcopy(&x.a_syms, addr, sizeof(x.a_syms)); addr += sizeof(x.a_syms); printf(" [%d+", x.a_syms); if (x.a_syms) { bsize = x.a_syms + sizeof(int); state = 3; break; } printf("0]"); case 4: printf(" total 0x%x", addr); x.a_entry &= 0xffffff; printf(" start 0x%x\n", x.a_entry); #define round_to_size(x,t) \ (((int)(x) + sizeof(t) - 1) & ~(sizeof(t) - 1)) esym = (char *)round_to_size(addr - load, int); #undef round_to_size state = -1; break; case 3: printf("%d]", ((int *)addr)[-1]); bsize = ((int *)addr)[-1] - sizeof(int); state = 4; break; case -1: printf("Already at EOF\n"); break; } } int flush(w) /* used by inflate.c (FLUSH macro) */ ulg w; /* number of bytes to flush */ { uch *p = slide; updcrc(slide, w); outsiz += w; while (bsize <= w) { bcopy(p, addr, bsize); p += bsize; addr += bsize; w -= bsize; nextstate(); } if (w) { bcopy(p, addr, w); addr += w; bsize -= w; } return(0); } main() { ush n; uch h[LOCHDR]; /* first local header (GZPHDR < LOCHDR) */ int g = 0; /* true if gzip format */ char *s = ""; cninit(); addr = (uch *)&x; bsize = sizeof(x); /* read local header, check validity, and skip name and extra fields */ n = nextbyte(); n |= nextbyte() << 8; if (n == ZIPMAG) { if (nextblock((char *)h, LOCHDR) != LOCHDR || SH(h) != LOCREM) panic("invalid zip file"); if (SH(h + LOCHOW) != STORED && SH(h + LOCHOW) != DEFLATED) panic("first entry not deflated or stored--can't funzip"); for (n = SH(h + LOCFIL); n--; ) g = nextbyte(); for (n = SH(h + LOCEXT); n--; ) g = nextbyte(); g = 0; encrypted = h[LOCFLG] & CRPFLG; } else if (n == GZPMAG) { if (nextblock((char *)h, GZPHDR) != GZPHDR) panic("invalid gzip file"); if (h[GZPHOW] != DEFLATED) panic("gzip file not deflated"); if (h[GZPFLG] & GZPMUL) panic("cannot handle multi-part gzip files"); if (h[GZPFLG] & GZPISX) { n = nextbyte(); n |= nextbyte() << 8; while (n--) g = nextbyte(); } if (h[GZPFLG] & GZPISF) while ((g = nextbyte()) != 0 && g != EOF) ; if (h[GZPFLG] & GZPISC) while ((g = nextbyte()) != 0 && g != EOF) ; g = 1; encrypted = h[GZPFLG] & GZPISE; } else panic("input not a zip or gzip file"); /* if entry encrypted, decrypt and validate encryption header */ if (encrypted) panic("cannot decrypt entry (need to recompile with full crypt.c)"); /* prepare output buffer and crc */ outptr = slide; outcnt = 0L; outsiz = 0L; updcrc(NULL, 0L); /* decompress */ if (g || h[LOCHOW]) { /* deflated entry */ int r; if ((r = inflate()) != 0) if (r == 3) panic("out of memory"); else panic("invalid compressed data--format violated"); inflate_free(); } else { /* stored entry */ register ulg n; n = LG(h + LOCLEN); if (n != LG(h + LOCSIZ)) { printf("len %ld, siz %ld\n", n, LG(h + LOCSIZ)); panic("invalid compressed data--length mismatch"); } while (n--) { ush c = nextbyte(); *outptr++ = (uch)c; if (++outcnt == WSIZE) /* do FlushOutput() */ { flush(outcnt); outptr = slide; outcnt = 0L; } } if (outcnt) /* flush one last time; no need to reset outptr/outcnt */ flush(outcnt); } /* if extended header, get it */ if (g) { if (nextblock((char *)h + LOCCRC, 8) != 8) panic("gzip file ended prematurely"); } else if ((h[LOCFLG] & EXTFLG) && nextblock((char *)h + LOCCRC - 4, EXTHDR) != EXTHDR) panic("zip file ended prematurely"); /* validate decompression */ if (LG(h + LOCCRC) != updcrc(slide, 0L)) panic("invalid compressed data--crc error"); if (LG(h + (g ? LOCSIZ : LOCLEN)) != outsiz) panic("invalid compressed data--length error"); /* check if there are more entries */ if (!g && nextblock((char *)h, 4) == 4 && LG(h) == LOCSIG) printf("funzip warning: zip file has more than one entry--rest ignored\n"); asm(" movd %0,r3" : : "g" (r3)); /* magic */ asm(" movd %0,r4" : : "g" (esym)); asm(" movd %0,r5" : : "g" (load)); asm(" movd %0,r6" : : "g" (r6)); /* devtype */ asm(" movd %0,r7" : : "g" (r7)); /* howto */ (*((int (*)()) x.a_entry))(); } /* Table of CRC-32's of all single-byte values (made by makecrc.c) */ ulg crc_32_tab[] = { 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L, 0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L, 0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, 0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL, 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L, 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L, 0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, 0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL, 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L, 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL, 0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, 0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L, 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L, 0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL, 0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, 0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L, 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL, 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L, 0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, 0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L, 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL, 0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L, 0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L, 0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL, 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L, 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L, 0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L, 0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L, 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L, 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL, 0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, 0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L, 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L, 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL, 0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, 0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L, 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL, 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L, 0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, 0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L, 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL, 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L, 0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, 0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL, 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L, 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L, 0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, 0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L, 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L, 0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L, 0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, 0x2d02ef8dL }; /* From: inflate.c -- put in the public domain by Mark Adler version c14o, 23 August 1994 */ /* Inflate deflated (PKZIP's method 8 compressed) data. The compression method searches for as much of the current string of bytes (up to a length of 258) in the previous 32K bytes. If it doesn't find any matches (of at least length 3), it codes the next byte. Otherwise, it codes the length of the matched string and its distance backwards from the current position. There is a single Huffman code that codes both single bytes (called "literals") and match lengths. A second Huffman code codes the distance information, which follows a length code. Each length or distance code actually represents a base value and a number of "extra" (sometimes zero) bits to get to add to the base value. At the end of each deflated block is a special end-of-block (EOB) literal/ length code. The decoding process is basically: get a literal/length code; if EOB then done; if a literal, emit the decoded byte; if a length then get the distance and emit the referred-to bytes from the sliding window of previously emitted data. There are (currently) three kinds of inflate blocks: stored, fixed, and dynamic. The compressor outputs a chunk of data at a time and decides which method to use on a chunk-by-chunk basis. A chunk might typically be 32K to 64K, uncompressed. If the chunk is uncompressible, then the "stored" method is used. In this case, the bytes are simply stored as is, eight bits per byte, with none of the above coding. The bytes are preceded by a count, since there is no longer an EOB code. If the data is compressible, then either the fixed or dynamic methods are used. In the dynamic method, the compressed data is preceded by an encoding of the literal/length and distance Huffman codes that are to be used to decode this block. The representation is itself Huffman coded, and so is preceded by a description of that code. These code descriptions take up a little space, and so for small blocks, there is a predefined set of codes, called the fixed codes. The fixed method is used if the block ends up smaller that way (usually for quite small chunks); otherwise the dynamic method is used. In the latter case, the codes are customized to the probabilities in the current block and so can code it much better than the pre-determined fixed codes can. The Huffman codes themselves are decoded using a mutli-level table lookup, in order to maximize the speed of decoding plus the speed of building the decoding tables. See the comments below that precede the lbits and dbits tuning parameters. */ /* Notes beyond the 1.93a appnote.txt: 1. Distance pointers never point before the beginning of the output stream. 2. Distance pointers can point back across blocks, up to 32k away. 3. There is an implied maximum of 7 bits for the bit length table and 15 bits for the actual data. 4. If only one code exists, then it is encoded using one bit. (Zero would be more efficient, but perhaps a little confusing.) If two codes exist, they are coded using one bit each (0 and 1). 5. There is no way of sending zero distance codes--a dummy must be sent if there are none. (History: a pre 2.0 version of PKZIP would store blocks with no distance codes, but this was discovered to be too harsh a criterion.) Valid only for 1.93a. 2.04c does allow zero distance codes, which is sent as one code of zero bits in length. 6. There are up to 286 literal/length codes. Code 256 represents the end-of-block. Note however that the static length tree defines 288 codes just to fill out the Huffman codes. Codes 286 and 287 cannot be used though, since there is no length base or extra bits defined for them. Similarily, there are up to 30 distance codes. However, static trees define 32 codes (all 5 bits) to fill out the Huffman codes, but the last two had better not show up in the data. 7. Unzip can check dynamic Huffman blocks for complete code sets. The exception is that a single code would not be complete (see #4). 8. The five bits following the block type is really the number of literal codes sent minus 257. 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits (1+6+6). Therefore, to output three times the length, you output three codes (1+1+1), whereas to output four times the same length, you only need two codes (1+3). Hmm. 10. In the tree reconstruction algorithm, Code = Code + Increment only if BitLength(i) is not zero. (Pretty obvious.) 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) 12. Note: length code 284 can represent 227-258, but length code 285 really is 258. The last length deserves its own, short code since it gets used a lot in very redundant files. The length 258 is special since 258 - 3 (the min match length) is 255. 13. The literal/length and distance code bit lengths are read as a single stream of lengths. It is possible (and advantageous) for a repeat code (16, 17, or 18) to go across the boundary between the two sets of lengths. */ #define PKZIP_BUG_WORKAROUND /* PKZIP 1.93a problem--live with it */ /* inflate.h must supply the uch slide[WSIZE] array and the NEXTBYTE, FLUSH() and memzero macros. If the window size is not 32K, it should also define WSIZE. If INFMOD is defined, it can include compiled functions to support the NEXTBYTE and/or FLUSH() macros. There are defaults for NEXTBYTE and FLUSH() below for use as examples of what those functions need to do. Normally, you would also want FLUSH() to compute a crc on the data. inflate.h also needs to provide these typedefs: typedef unsigned char uch; typedef unsigned short ush; typedef unsigned long ulg; This module uses the external functions malloc() and free() (and probably memset() or bzero() in the memzero() macro). Their prototypes are normally found in and . */ /* Warning: the fwrite above might not work on 16-bit compilers, since 0x8000 might be interpreted as -32,768 by the library function. */ /* Huffman code lookup table entry--this entry is four bytes for machines that have 16-bit pointers (e.g. PC's in the small or medium model). Valid extra bits are 0..13. e == 15 is EOB (end of block), e == 16 means that v is a literal, 16 < e < 32 means that v is a pointer to the next table, which codes e - 16 bits, and lastly e == 99 indicates an unused code. If a code with e == 99 is looked up, this implies an error in the data. */ struct huft { uch e; /* number of extra bits or operation */ uch b; /* number of bits in this code or subcode */ union { ush n; /* literal, length base, or distance base */ struct huft *t; /* pointer to next level of table */ } v; }; int huft_build OF((unsigned *, unsigned, unsigned, ush *, ush *, struct huft **, int *)); int huft_free OF((struct huft *)); int inflate_codes OF((struct huft *, struct huft *, int, int)); int inflate_stored OF((void)); int inflate_fixed OF((void)); int inflate_dynamic OF((void)); int inflate_block OF((int *)); int inflate OF((void)); int inflate_free OF((void)); /* The inflate algorithm uses a sliding 32K byte window on the uncompressed stream to find repeated byte strings. This is implemented here as a circular buffer. The index is updated simply by incrementing and then and'ing with 0x7fff (32K-1). */ /* It is left to other modules to supply the 32K area. It is assumed to be usable as if it were declared "uch slide[32768];" or as just "uch *slide;" and then malloc'ed in the latter case. The definition must be in unzip.h, included above. */ unsigned wp; /* current position in slide */ /* Tables for deflate from PKZIP's appnote.txt. */ static unsigned border[] = { /* Order of the bit length code lengths */ 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; static ush cplens[] = { /* Copy lengths for literal codes 257..285 */ 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}; /* note: see note #13 above about the 258 in this list. */ static ush cplext[] = { /* Extra bits for literal codes 257..285 */ 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */ static ush cpdist[] = { /* Copy offsets for distance codes 0..29 */ 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}; static ush cpdext[] = { /* Extra bits for distance codes */ 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13}; /* And'ing with mask[n] masks the lower n bits */ ush mask[] = { 0x0000, 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff }; /* Macros for inflate() bit peeking and grabbing. The usage is: NEEDBITS(j) x = b & mask[j]; DUMPBITS(j) where NEEDBITS makes sure that b has at least j bits in it, and DUMPBITS removes the bits from b. The macros use the variable k for the number of bits in b. Normally, b and k are register variables for speed, and are initialized at the begining of a routine that uses these macros from a global bit buffer and count. In order to not ask for more bits than there are in the compressed stream, the Huffman tables are constructed to only ask for just enough bits to make up the end-of-block code (value 256). Then no bytes need to be "returned" to the buffer at the end of the last block. See the huft_build() routine. */ ulg bb; /* bit buffer */ unsigned bk; /* bits in bit buffer */ #ifndef CHECK_EOF # define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE)<>=(n);k-=(n);} /* Huffman code decoding is performed using a multi-level table lookup. The fastest way to decode is to simply build a lookup table whose size is determined by the longest code. However, the time it takes to build this table can also be a factor if the data being decoded is not very long. The most common codes are necessarily the shortest codes, so those codes dominate the decoding time, and hence the speed. The idea is you can have a shorter table that decodes the shorter, more probable codes, and then point to subsidiary tables for the longer codes. The time it costs to decode the longer codes is then traded against the time it takes to make longer tables. This results of this trade are in the variables lbits and dbits below. lbits is the number of bits the first level table for literal/ length codes can decode in one step, and dbits is the same thing for the distance codes. Subsequent tables are also less than or equal to those sizes. These values may be adjusted either when all of the codes are shorter than that, in which case the longest code length in bits is used, or when the shortest code is *longer* than the requested table size, in which case the length of the shortest code in bits is used. There are two different values for the two tables, since they code a different number of possibilities each. The literal/length table codes 286 possible values, or in a flat code, a little over eight bits. The distance table codes 30 possible values, or a little less than five bits, flat. The optimum values for speed end up being about one bit more than those, so lbits is 8+1 and dbits is 5+1. The optimum values may differ though from machine to machine, and possibly even between compilers. Your mileage may vary. */ int lbits = 9; /* bits in base literal/length lookup table */ int dbits = 6; /* bits in base distance lookup table */ /* If BMAX needs to be larger than 16, then h and x[] should be ulg. */ #define BMAX 16 /* maximum bit length of any code (16 for explode) */ #define N_MAX 288 /* maximum number of codes in any set */ unsigned hufts; /* track memory usage */ void *malloc(n) int n; { void *p; p = alloc(n + sizeof(n)); if (!p) return(NULL); *((int *)p) = n; p += sizeof(n); return(p); } int huft_build(b, n, s, d, e, t, m) unsigned *b; /* code lengths in bits (all assumed <= BMAX) */ unsigned n; /* number of codes (assumed <= N_MAX) */ unsigned s; /* number of simple-valued codes (0..s-1) */ ush *d; /* list of base values for non-simple codes */ ush *e; /* list of extra bits for non-simple codes */ struct huft **t; /* result: starting table */ int *m; /* maximum lookup bits, returns actual */ /* Given a list of code lengths and a maximum table size, make a set of tables to decode that set of codes. Return zero on success, one if the given code set is incomplete (the tables are still built in this case), two if the input is invalid (all zero length codes or an oversubscribed set of lengths), and three if not enough memory. The code with value 256 is special, and the tables are constructed so that no bits beyond that code are fetched when that code is decoded. */ { unsigned a; /* counter for codes of length k */ unsigned c[BMAX+1]; /* bit length count table */ unsigned el; /* length of EOB code (value 256) */ unsigned f; /* i repeats in table every f entries */ int g; /* maximum code length */ int h; /* table level */ register unsigned i; /* counter, current code */ register unsigned j; /* counter */ register int k; /* number of bits in current code */ int lx[BMAX+1]; /* memory for l[-1..BMAX-1] */ int *l = lx+1; /* stack of bits per table */ register unsigned *p; /* pointer into c[], b[], or v[] */ register struct huft *q; /* points to current table */ struct huft r; /* table entry for structure assignment */ struct huft *u[BMAX]; /* table stack */ static unsigned v[N_MAX]; /* values in order of bit length */ register int w; /* bits before this table == (l * h) */ unsigned x[BMAX+1]; /* bit offsets, then code stack */ unsigned *xp; /* pointer into x */ int y; /* number of dummy codes added */ unsigned z; /* number of entries in current table */ /* Generate counts for each bit length */ el = n > 256 ? b[256] : BMAX; /* set length of EOB code, if any */ memzero((char *)c, sizeof(c)); p = b; i = n; do { c[*p]++; p++; /* assume all entries <= BMAX */ } while (--i); if (c[0] == n) /* null input--all zero length codes */ { *t = (struct huft *)NULL; *m = 0; return 0; } /* Find minimum and maximum length, bound *m by those */ for (j = 1; j <= BMAX; j++) if (c[j]) break; k = j; /* minimum code length */ if ((unsigned)*m < j) *m = j; for (i = BMAX; i; i--) if (c[i]) break; g = i; /* maximum code length */ if ((unsigned)*m > i) *m = i; /* Adjust last length count to fill out codes, if needed */ for (y = 1 << j; j < i; j++, y <<= 1) if ((y -= c[j]) < 0) return 2; /* bad input: more codes than bits */ if ((y -= c[i]) < 0) return 2; c[i] += y; /* Generate starting offsets into the value table for each length */ x[1] = j = 0; p = c + 1; xp = x + 2; while (--i) { /* note that i == g from above */ *xp++ = (j += *p++); } /* Make a table of values in order of bit lengths */ p = b; i = 0; do { if ((j = *p++) != 0) v[x[j]++] = i; } while (++i < n); /* Generate the Huffman codes and for each, make the table entries */ x[0] = i = 0; /* first Huffman code is zero */ p = v; /* grab values in bit order */ h = -1; /* no tables yet--level -1 */ w = l[-1] = 0; /* no bits decoded yet */ u[0] = (struct huft *)NULL; /* just to keep compilers happy */ q = (struct huft *)NULL; /* ditto */ z = 0; /* ditto */ /* go through the bit lengths (k already is bits in shortest code) */ for (; k <= g; k++) { a = c[k]; while (a--) { /* here i is the Huffman code of length k bits for value *p */ /* make tables up to required level */ while (k > w + l[h]) { w += l[h++]; /* add bits already decoded */ /* compute minimum size table less than or equal to *m bits */ z = (z = g - w) > (unsigned)*m ? *m : z; /* upper limit */ if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ { /* too few codes for k-w bit table */ f -= a + 1; /* deduct codes from patterns left */ xp = c + k; while (++j < z) /* try smaller tables up to z bits */ { if ((f <<= 1) <= *++xp) break; /* enough codes to use up j bits */ f -= *xp; /* else deduct codes from patterns */ } } if ((unsigned)w + j > el && (unsigned)w < el) j = el - w; /* make EOB code end at table */ z = 1 << j; /* table entries for j-bit table */ l[h] = j; /* set table size in stack */ /* allocate and link in new table */ if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) == (struct huft *)NULL) { if (h) huft_free(u[0]); return 3; /* not enough memory */ } hufts += z + 1; /* track memory usage */ *t = q + 1; /* link to list for huft_free() */ *(t = &(q->v.t)) = (struct huft *)NULL; u[h] = ++q; /* table starts after link */ /* connect to last table, if there is one */ if (h) { x[h] = i; /* save pattern for backing up */ r.b = (uch)l[h-1]; /* bits to dump before this table */ r.e = (uch)(16 + j); /* bits in this table */ r.v.t = q; /* pointer to this table */ j = (i & ((1 << w) - 1)) >> (w - l[h-1]); u[h-1][j] = r; /* connect to last table */ } } /* set up table entry in r */ r.b = (uch)(k - w); if (p >= v + n) r.e = 99; /* out of values--invalid code */ else if (*p < s) { r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */ r.v.n = *p++; /* simple code is just the value */ } else { r.e = (uch)e[*p - s]; /* non-simple--look up in lists */ r.v.n = d[*p++ - s]; } /* fill code-like entries with r */ f = 1 << (k - w); for (j = i >> w; j < z; j += f) q[j] = r; /* backwards increment the k-bit code i */ for (j = 1 << (k - 1); i & j; j >>= 1) i ^= j; i ^= j; /* backup over finished tables */ while ((i & ((1 << w) - 1)) != x[h]) w -= l[--h]; /* don't need to update q */ } } /* return actual size of base table */ *m = l[0]; /* Return true (1) if we were given an incomplete table */ return y != 0 && g != 1; } int huft_free(t) struct huft *t; /* table to free */ /* Free the malloc'ed tables built by huft_build(), which makes a linked list of the tables it made, with the links in a dummy first entry of each table. */ { register struct huft *p, *q; /* Go through linked list, freeing from the malloced (t[-1]) address. */ p = t; while (p != (struct huft *)NULL) { q = (--p)->v.t; free(((void *)p) - sizeof(int), ((int *)p)[-1]); p = q; } return 0; } #ifdef ASM_INFLATECODES # define inflate_codes(tl,td,bl,bd) flate_codes(tl,td,bl,bd,(uch *)slide) int flate_codes OF((struct huft *, struct huft *, int, int, uch *)); #else int inflate_codes(tl, td, bl, bd) struct huft *tl, *td; /* literal/length and distance decoder tables */ int bl, bd; /* number of bits decoded by tl[] and td[] */ /* inflate (decompress) the codes in a deflated (compressed) block. Return an error code or zero if it all goes ok. */ { register unsigned e; /* table entry flag/number of extra bits */ unsigned n, d; /* length and index for copy */ unsigned w; /* current window position */ struct huft *t; /* pointer to table entry */ unsigned ml, md; /* masks for bl and bd bits */ register ulg b; /* bit buffer */ register unsigned k; /* number of bits in bit buffer */ /* make local copies of globals */ b = bb; /* initialize bit buffer */ k = bk; w = wp; /* initialize window position */ /* inflate the coded data */ ml = mask[bl]; /* precompute masks for speed */ md = mask[bd]; while (1) /* do until end of block */ { NEEDBITS((unsigned)bl) if ((e = (t = tl + ((unsigned)b & ml))->e) > 16) do { if (e == 99) return 1; DUMPBITS(t->b) e -= 16; NEEDBITS(e) } while ((e = (t = t->v.t + ((unsigned)b & mask[e]))->e) > 16); DUMPBITS(t->b) if (e == 16) /* then it's a literal */ { slide[w++] = (uch)t->v.n; if (w == WSIZE) { FLUSH(w); w = 0; } } else /* it's an EOB or a length */ { /* exit if end of block */ if (e == 15) break; /* get length of block to copy */ NEEDBITS(e) n = t->v.n + ((unsigned)b & mask[e]); DUMPBITS(e); /* decode distance of block to copy */ NEEDBITS((unsigned)bd) if ((e = (t = td + ((unsigned)b & md))->e) > 16) do { if (e == 99) return 1; DUMPBITS(t->b) e -= 16; NEEDBITS(e) } while ((e = (t = t->v.t + ((unsigned)b & mask[e]))->e) > 16); DUMPBITS(t->b) NEEDBITS(e) d = w - t->v.n - ((unsigned)b & mask[e]); DUMPBITS(e) /* do the copy */ do { n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e); #ifndef NOMEMCPY if (w - d >= e) /* (this test assumes unsigned comparison) */ { memcpy(slide + w, slide + d, e); w += e; d += e; } else /* do it slow to avoid memcpy() overlap */ #endif /* !NOMEMCPY */ do { slide[w++] = slide[d++]; } while (--e); if (w == WSIZE) { FLUSH(w); w = 0; } } while (n); } } /* restore the globals from the locals */ wp = w; /* restore global window pointer */ bb = b; /* restore global bit buffer */ bk = k; /* done */ return 0; } #endif /* ASM_INFLATECODES */ int inflate_stored() /* "decompress" an inflated type 0 (stored) block. */ { unsigned n; /* number of bytes in block */ unsigned w; /* current window position */ register ulg b; /* bit buffer */ register unsigned k; /* number of bits in bit buffer */ /* make local copies of globals */ b = bb; /* initialize bit buffer */ k = bk; w = wp; /* initialize window position */ /* go to byte boundary */ n = k & 7; DUMPBITS(n); /* get the length and its complement */ NEEDBITS(16) n = ((unsigned)b & 0xffff); DUMPBITS(16) NEEDBITS(16) if (n != (unsigned)((~b) & 0xffff)) return 1; /* error in compressed data */ DUMPBITS(16) /* read and output the compressed data */ while (n--) { NEEDBITS(8) slide[w++] = (uch)b; if (w == WSIZE) { FLUSH(w); w = 0; } DUMPBITS(8) } /* restore the globals from the locals */ wp = w; /* restore global window pointer */ bb = b; /* restore global bit buffer */ bk = k; return 0; } /* Globals for literal tables (built once) */ struct huft *fixed_tl = (struct huft *)NULL; struct huft *fixed_td; int fixed_bl, fixed_bd; int inflate_fixed() /* decompress an inflated type 1 (fixed Huffman codes) block. We should either replace this with a custom decoder, or at least precompute the Huffman tables. */ { /* if first time, set up tables for fixed blocks */ if (fixed_tl == (struct huft *)NULL) { int i; /* temporary variable */ static unsigned l[288]; /* length list for huft_build */ /* literal table */ for (i = 0; i < 144; i++) l[i] = 8; for (; i < 256; i++) l[i] = 9; for (; i < 280; i++) l[i] = 7; for (; i < 288; i++) /* make a complete, but wrong code set */ l[i] = 8; fixed_bl = 7; if ((i = huft_build(l, 288, 257, cplens, cplext, &fixed_tl, &fixed_bl)) != 0) { fixed_tl = (struct huft *)NULL; return i; } /* distance table */ for (i = 0; i < 30; i++) /* make an incomplete code set */ l[i] = 5; fixed_bd = 5; if ((i = huft_build(l, 30, 0, cpdist, cpdext, &fixed_td, &fixed_bd)) > 1) { huft_free(fixed_tl); fixed_tl = (struct huft *)NULL; return i; } } /* decompress until an end-of-block code */ return inflate_codes(fixed_tl, fixed_td, fixed_bl, fixed_bd) != 0; } int inflate_dynamic() /* decompress an inflated type 2 (dynamic Huffman codes) block. */ { int i; /* temporary variables */ unsigned j; unsigned l; /* last length */ unsigned m; /* mask for bit lengths table */ unsigned n; /* number of lengths to get */ struct huft *tl; /* literal/length code table */ struct huft *td; /* distance code table */ int bl; /* lookup bits for tl */ int bd; /* lookup bits for td */ unsigned nb; /* number of bit length codes */ unsigned nl; /* number of literal/length codes */ unsigned nd; /* number of distance codes */ #ifdef PKZIP_BUG_WORKAROUND static unsigned ll[288+32]; /* literal/length and distance code lengths */ #else static unsigned ll[286+30]; /* literal/length and distance code lengths */ #endif register ulg b; /* bit buffer */ register unsigned k; /* number of bits in bit buffer */ /* make local bit buffer */ b = bb; k = bk; /* read in table lengths */ NEEDBITS(5) nl = 257 + ((unsigned)b & 0x1f); /* number of literal/length codes */ DUMPBITS(5) NEEDBITS(5) nd = 1 + ((unsigned)b & 0x1f); /* number of distance codes */ DUMPBITS(5) NEEDBITS(4) nb = 4 + ((unsigned)b & 0xf); /* number of bit length codes */ DUMPBITS(4) #ifdef PKZIP_BUG_WORKAROUND if (nl > 288 || nd > 32) #else if (nl > 286 || nd > 30) #endif return 1; /* bad lengths */ /* read in bit-length-code lengths */ for (j = 0; j < nb; j++) { NEEDBITS(3) ll[border[j]] = (unsigned)b & 7; DUMPBITS(3) } for (; j < 19; j++) ll[border[j]] = 0; /* build decoding table for trees--single level, 7 bit lookup */ bl = 7; if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0) { if (i == 1) huft_free(tl); return i; /* incomplete code set */ } /* read in literal and distance code lengths */ n = nl + nd; m = mask[bl]; i = l = 0; while ((unsigned)i < n) { NEEDBITS((unsigned)bl) j = (td = tl + ((unsigned)b & m))->b; DUMPBITS(j) j = td->v.n; if (j < 16) /* length of code in bits (0..15) */ ll[i++] = l = j; /* save last length in l */ else if (j == 16) /* repeat last length 3 to 6 times */ { NEEDBITS(2) j = 3 + ((unsigned)b & 3); DUMPBITS(2) if ((unsigned)i + j > n) return 1; while (j--) ll[i++] = l; } else if (j == 17) /* 3 to 10 zero length codes */ { NEEDBITS(3) j = 3 + ((unsigned)b & 7); DUMPBITS(3) if ((unsigned)i + j > n) return 1; while (j--) ll[i++] = 0; l = 0; } else /* j == 18: 11 to 138 zero length codes */ { NEEDBITS(7) j = 11 + ((unsigned)b & 0x7f); DUMPBITS(7) if ((unsigned)i + j > n) return 1; while (j--) ll[i++] = 0; l = 0; } } /* free decoding table for trees */ huft_free(tl); /* restore the global bit buffer */ bb = b; bk = k; /* build the decoding tables for literal/length and distance codes */ bl = lbits; if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0) { return i; /* incomplete code set */ } bd = dbits; if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0) { if (i == 1 && !qflag) { #ifdef PKZIP_BUG_WORKAROUND i = 0; } #else huft_free(td); } huft_free(tl); return i; /* incomplete code set */ #endif } /* decompress until an end-of-block code */ if (inflate_codes(tl, td, bl, bd)) return 1; /* free the decoding tables, return */ huft_free(tl); huft_free(td); return 0; } int inflate_block(e) int *e; /* last block flag */ /* decompress an inflated block */ { unsigned t; /* block type */ register ulg b; /* bit buffer */ register unsigned k; /* number of bits in bit buffer */ /* make local bit buffer */ b = bb; k = bk; /* read in last block bit */ NEEDBITS(1) *e = (int)b & 1; DUMPBITS(1) /* read in block type */ NEEDBITS(2) t = (unsigned)b & 3; DUMPBITS(2) /* restore the global bit buffer */ bb = b; bk = k; /* inflate that block type */ if (t == 2) return inflate_dynamic(); if (t == 0) return inflate_stored(); if (t == 1) return inflate_fixed(); /* bad block type */ return 2; } int inflate() /* decompress an inflated entry */ { int e; /* last block flag */ int r; /* result code */ unsigned h; /* maximum struct huft's malloc'ed */ /* initialize window, bit buffer */ wp = 0; bk = 0; bb = 0; /* decompress until the last block */ h = 0; do { hufts = 0; if ((r = inflate_block(&e)) != 0) return r; if (hufts > h) h = hufts; } while (!e); /* flush out slide */ FLUSH(wp); /* return success */ return 0; } int inflate_free() { if (fixed_tl != (struct huft *)NULL) { huft_free(fixed_td); huft_free(fixed_tl); fixed_td = fixed_tl = (struct huft *)NULL; } return 0; }