Index: stable/4/gnu/usr.bin/gzip/gzip.h =================================================================== --- stable/4/gnu/usr.bin/gzip/gzip.h (revision 162445) +++ stable/4/gnu/usr.bin/gzip/gzip.h (revision 162446) @@ -1,315 +1,319 @@ /* gzip.h -- common declarations for all gzip modules * Copyright (C) 1992-1993 Jean-loup Gailly. * This is free software; you can redistribute it and/or modify it under the * terms of the GNU General Public License, see the file COPYING. + * + * $FreeBSD$ */ #if defined(__STDC__) || defined(PROTO) # define OF(args) args #else # define OF(args) () #endif #ifdef __STDC__ typedef void *voidp; #else typedef char *voidp; #endif /* I don't like nested includes, but the string and io functions are used * too often */ #include #if !defined(NO_STRING_H) || defined(STDC_HEADERS) # include # if !defined(STDC_HEADERS) && !defined(NO_MEMORY_H) && !defined(__GNUC__) # include # endif # define memzero(s, n) memset ((voidp)(s), 0, (n)) #else # include # define strchr index # define strrchr rindex # define memcpy(d, s, n) bcopy((s), (d), (n)) # define memcmp(s1, s2, n) bcmp((s1), (s2), (n)) # define memzero(s, n) bzero((s), (n)) #endif #ifndef RETSIGTYPE # define RETSIGTYPE void #endif #define local static typedef unsigned char uch; typedef unsigned short ush; typedef unsigned long ulg; /* Return codes from gzip */ #define OK 0 #define ERROR 1 #define WARNING 2 /* Compression methods (see algorithm.doc) */ #define STORED 0 #define COMPRESSED 1 #define PACKED 2 #define LZHED 3 /* methods 4 to 7 reserved */ #define DEFLATED 8 #define MAX_METHODS 9 extern int method; /* compression method */ /* To save memory for 16 bit systems, some arrays are overlaid between * the various modules: * deflate: prev+head window d_buf l_buf outbuf * unlzw: tab_prefix tab_suffix stack inbuf outbuf * inflate: window inbuf * unpack: window inbuf prefix_len * unlzh: left+right window c_table inbuf c_len * For compression, input is done in window[]. For decompression, output * is done in window except for unlzw. */ #ifndef INBUFSIZ # ifdef SMALL_MEM # define INBUFSIZ 0x2000 /* input buffer size */ # else # define INBUFSIZ 0x8000 /* input buffer size */ # endif #endif #define INBUF_EXTRA 64 /* required by unlzw() */ #ifndef OUTBUFSIZ # ifdef SMALL_MEM # define OUTBUFSIZ 8192 /* output buffer size */ # else # define OUTBUFSIZ 16384 /* output buffer size */ # endif #endif #define OUTBUF_EXTRA 2048 /* required by unlzw() */ #ifndef DIST_BUFSIZE # ifdef SMALL_MEM # define DIST_BUFSIZE 0x2000 /* buffer for distances, see trees.c */ # else # define DIST_BUFSIZE 0x8000 /* buffer for distances, see trees.c */ # endif #endif #ifdef DYN_ALLOC # define EXTERN(type, array) extern type * near array # define DECLARE(type, array, size) type * near array # define ALLOC(type, array, size) { \ array = (type*)fcalloc((size_t)(((size)+1L)/2), 2*sizeof(type)); \ if (array == NULL) error("insufficient memory"); \ } # define FREE(array) {if (array != NULL) fcfree(array), array=NULL;} #else # define EXTERN(type, array) extern type array[] # define DECLARE(type, array, size) type array[size] # define ALLOC(type, array, size) # define FREE(array) #endif EXTERN(uch, inbuf); /* input buffer */ EXTERN(uch, outbuf); /* output buffer */ EXTERN(ush, d_buf); /* buffer for distances, see trees.c */ EXTERN(uch, window); /* Sliding window and suffix table (unlzw) */ #define tab_suffix window #ifndef MAXSEG_64K # define tab_prefix prev /* hash link (see deflate.c) */ # define head (prev+WSIZE) /* hash head (see deflate.c) */ EXTERN(ush, tab_prefix); /* prefix code (see unlzw.c) */ #else # define tab_prefix0 prev # define head tab_prefix1 EXTERN(ush, tab_prefix0); /* prefix for even codes */ EXTERN(ush, tab_prefix1); /* prefix for odd codes */ #endif extern unsigned insize; /* valid bytes in inbuf */ extern unsigned inptr; /* index of next byte to be processed in inbuf */ extern unsigned outcnt; /* bytes in output buffer */ extern long bytes_in; /* number of input bytes */ extern long bytes_out; /* number of output bytes */ extern long header_bytes;/* number of bytes in gzip header */ #define isize bytes_in /* for compatibility with old zip sources (to be cleaned) */ extern int ifd; /* input file descriptor */ extern int ofd; /* output file descriptor */ extern char ifname[]; /* input file name or "stdin" */ extern char ofname[]; /* output file name or "stdout" */ extern char *progname; /* program name */ extern long time_stamp; /* original time stamp (modification time) */ extern long ifile_size; /* input file size, -1 for devices (debug only) */ typedef int file_t; /* Do not use stdio */ #define NO_FILE (-1) /* in memory compression */ #define PACK_MAGIC "\037\036" /* Magic header for packed files */ #define GZIP_MAGIC "\037\213" /* Magic header for gzip files, 1F 8B */ #define OLD_GZIP_MAGIC "\037\236" /* Magic header for gzip 0.5 = freeze 1.x */ #define LZH_MAGIC "\037\240" /* Magic header for SCO LZH Compress files*/ #define PKZIP_MAGIC "\120\113\003\004" /* Magic header for pkzip files */ /* gzip flag byte */ #define ASCII_FLAG 0x01 /* bit 0 set: file probably ascii text */ #define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */ #define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ #define ORIG_NAME 0x08 /* bit 3 set: original file name present */ #define COMMENT 0x10 /* bit 4 set: file comment present */ #define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ #define RESERVED 0xC0 /* bit 6,7: reserved */ /* internal file attribute */ #define UNKNOWN 0xffff #define BINARY 0 #define ASCII 1 #ifndef WSIZE # define WSIZE 0x8000 /* window size--must be a power of two, and */ #endif /* at least 32K for zip's deflate method */ #define MIN_MATCH 3 #define MAX_MATCH 258 /* The minimum and maximum match lengths */ #define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) /* Minimum amount of lookahead, except at the end of the input file. * See deflate.c for comments about the MIN_MATCH+1. */ #define MAX_DIST (WSIZE-MIN_LOOKAHEAD) /* In order to simplify the code, particularly on 16 bit machines, match * distances are limited to MAX_DIST instead of WSIZE. */ extern int decrypt; /* flag to turn on decryption */ extern int exit_code; /* program exit code */ extern int verbose; /* be verbose (-v) */ extern int quiet; /* be quiet (-q) */ extern int level; /* compression level */ extern int test; /* check .z file integrity */ extern int to_stdout; /* output to stdout (-c) */ extern int save_orig_name; /* set if original name must be saved */ + +#define MIN(a,b) ((a) <= (b) ? (a) : (b)) #define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf(0)) #define try_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf(1)) /* put_byte is used for the compressed output, put_ubyte for the * uncompressed output. However unlzw() uses window for its * suffix table instead of its output buffer, so it does not use put_ubyte * (to be cleaned up). */ #define put_byte(c) {outbuf[outcnt++]=(uch)(c); if (outcnt==OUTBUFSIZ)\ flush_outbuf();} #define put_ubyte(c) {window[outcnt++]=(uch)(c); if (outcnt==WSIZE)\ flush_window();} /* Output a 16 bit value, lsb first */ #define put_short(w) \ { if (outcnt < OUTBUFSIZ-2) { \ outbuf[outcnt++] = (uch) ((w) & 0xff); \ outbuf[outcnt++] = (uch) ((ush)(w) >> 8); \ } else { \ put_byte((uch)((w) & 0xff)); \ put_byte((uch)((ush)(w) >> 8)); \ } \ } /* Output a 32 bit value to the bit stream, lsb first */ #define put_long(n) { \ put_short((n) & 0xffff); \ put_short(((ulg)(n)) >> 16); \ } #define seekable() 0 /* force sequential output */ #define translate_eol 0 /* no option -a yet */ #define tolow(c) (isupper(c) ? (c)-'A'+'a' : (c)) /* force to lower case */ /* 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)) /* Diagnostic functions */ #ifdef DEBUG # define Assert(cond,msg) {if(!(cond)) error(msg);} # define Trace(x) fprintf x # define Tracev(x) {if (verbose) fprintf x ;} # define Tracevv(x) {if (verbose>1) fprintf x ;} # define Tracec(c,x) {if (verbose && (c)) fprintf x ;} # define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;} #else # define Assert(cond,msg) # define Trace(x) # define Tracev(x) # define Tracevv(x) # define Tracec(c,x) # define Tracecv(c,x) #endif #define WARN(msg) {if (!quiet) fprintf msg ; \ if (exit_code == OK) exit_code = WARNING;} /* in zip.c: */ extern int zip OF((int in, int out)); extern int file_read OF((char *buf, unsigned size)); /* in unzip.c */ extern int unzip OF((int in, int out)); extern int check_zipfile OF((int in)); /* in unpack.c */ extern int unpack OF((int in, int out)); /* in unlzh.c */ extern int unlzh OF((int in, int out)); /* in gzip.c */ RETSIGTYPE abort_gzip OF((void)); /* in deflate.c */ void lm_init OF((int pack_level, ush *flags)); ulg deflate OF((void)); /* in trees.c */ void ct_init OF((ush *attr, int *method)); int ct_tally OF((int dist, int lc)); ulg flush_block OF((char *buf, ulg stored_len, int eof)); /* in bits.c */ void bi_init OF((file_t zipfile)); void send_bits OF((int value, int length)); unsigned bi_reverse OF((unsigned value, int length)); void bi_windup OF((void)); void copy_block OF((char *buf, unsigned len, int header)); extern int (*read_buf) OF((char *buf, unsigned size)); /* in util.c: */ extern int copy OF((int in, int out)); extern ulg updcrc OF((uch *s, unsigned n)); extern void clear_bufs OF((void)); extern int fill_inbuf OF((int eof_ok)); extern void flush_outbuf OF((void)); extern void flush_window OF((void)); extern void write_buf OF((int fd, voidp buf, unsigned cnt)); extern char *strlwr OF((char *s)); extern char *basename OF((char *fname)); extern void make_simple_name OF((char *name)); extern char *add_envopt OF((int *argcp, char ***argvp, char *env)); extern void error OF((char *m)); extern void warn OF((char *a, char *b)); extern void read_error OF((void)); extern void write_error OF((void)); extern void display_ratio OF((long num, long den, FILE *file)); extern voidp xmalloc OF((unsigned int size)); /* in inflate.c */ extern int inflate OF((void)); Index: stable/4/gnu/usr.bin/gzip/inflate.c =================================================================== --- stable/4/gnu/usr.bin/gzip/inflate.c (revision 162445) +++ stable/4/gnu/usr.bin/gzip/inflate.c (revision 162446) @@ -1,958 +1,958 @@ /* inflate.c -- Not copyrighted 1992 by Mark Adler version c10p1, 10 January 1993 */ /* You can do whatever you like with this source file, though I would prefer that if you modify it and redistribute it that you include comments to that effect with your name and the date. Thank you. [The history has been moved to the file ChangeLog.] */ /* 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 deals with some chunk of data at a time, and decides which method to use on a chunk-by-chunk basis. A chunk might typically be 32K or 64K. 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 codes 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. 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. Similarly, 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. */ #ifdef RCSID static char rcsid[] = "$FreeBSD$"; #endif #include #include "tailor.h" #if defined(STDC_HEADERS) || !defined(NO_STDLIB_H) # include #endif #include "gzip.h" #define slide window /* 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; }; /* Function prototypes */ 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)); /* 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 */ #define wp outcnt #define flush_output(w) (wp=(w),flush_window()) /* 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}; /* Macros for inflate() bit peeking and grabbing. The usage is: NEEDBITS(j) x = b & mask_bits[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 beginning of a routine that uses these macros from a global bit buffer and count. If we assume that EOB will be the longest code, then we will never ask for bits with NEEDBITS that are beyond the end of the stream. So, NEEDBITS should not read any more bytes than are needed to meet the request. Then no bytes need to be "returned" to the buffer at the end of the last block. However, this assumption is not true for fixed blocks--the EOB code is 7 bits, but the other literal/length codes can be 8 or 9 bits. (The EOB code is shorter than other codes because fixed blocks are generally short. So, while a block always has an EOB, many other literal/length codes have a significantly lower probability of showing up at all.) However, by making the first table have a lookup of seven bits, the EOB code will be found in that first lookup, and so will not require that too many bits be pulled from the stream. */ ulg bb; /* bit buffer */ unsigned bk; /* bits in bit buffer */ ush mask_bits[] = { 0x0000, 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff }; #ifdef CRYPT uch cc; # define NEXTBYTE() \ (decrypt ? (cc = get_byte(), zdecode(cc), cc) : get_byte()) #else # define NEXTBYTE() (uch)get_byte() #endif #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 */ 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. */ { unsigned a; /* counter for codes of length k */ unsigned c[BMAX+1]; /* bit length count table */ 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 l; /* bits per table (returned in m) */ 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 */ 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 */ memzero(c, sizeof(c)); p = b; i = n; do { Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"), n-i, *p)); c[*p]++; /* assume all entries <= BMAX */ p++; /* Can't combine with above line (Solaris bug) */ } while (--i); if (c[0] == n) /* null input--all zero length codes */ { *t = (struct huft *)NULL; *m = 0; - return 0; + return 2; } /* Find minimum and maximum length, bound *m by those */ l = *m; for (j = 1; j <= BMAX; j++) if (c[j]) break; k = j; /* minimum code length */ if ((unsigned)l < j) l = j; for (i = BMAX; i; i--) if (c[i]) break; g = i; /* maximum code length */ if ((unsigned)l > i) l = i; *m = l; /* 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); n = x[g]; /* set n to length of v */ /* 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; /* bits decoded == (l * h) */ 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; /* previous table always l bits */ /* compute minimum size table less than or equal to l bits */ z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */ 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; if (j < z) 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 */ } } z = 1 << j; /* table entries for j-bit table */ /* 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; /* 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 >> (w - l); /* (get around Turbo C bug) */ 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 = (ush)(*p); /* simple code is just the value */ p++; /* one compiler does not like *p++ */ } 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]) { h--; /* don't need to update q */ w -= l; } } } /* 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((char*)p); p = q; } return 0; } 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_bits[bl]; /* precompute masks for speed */ md = mask_bits[bd]; for (;;) /* 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_bits[e]))->e) > 16); DUMPBITS(t->b) if (e == 16) /* then it's a literal */ { slide[w++] = (uch)t->v.n; Tracevv((stderr, "%c", slide[w-1])); if (w == WSIZE) { flush_output(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_bits[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_bits[e]))->e) > 16); DUMPBITS(t->b) NEEDBITS(e) d = w - t->v.n - ((unsigned)b & mask_bits[e]); DUMPBITS(e) Tracevv((stderr,"\\[%d,%d]", w-d, n)); /* do the copy */ do { n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e); #if !defined(NOMEMCPY) && !defined(DEBUG) 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++]; Tracevv((stderr, "%c", slide[w-1])); } while (--e); if (w == WSIZE) { flush_output(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; } 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_output(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; } 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. */ { int i; /* temporary variable */ 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 l[288]; /* length list for huft_build */ /* set up 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; bl = 7; if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0) return i; /* set up distance table */ for (i = 0; i < 30; i++) /* make an incomplete code set */ l[i] = 5; bd = 5; if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1) { huft_free(tl); return i; } /* 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_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 unsigned ll[288+32]; /* literal/length and distance code lengths */ #else 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 */ } if (tl == NULL) /* Grrrhhh */ return 2; /* read in literal and distance code lengths */ n = nl + nd; m = mask_bits[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) { if (i == 1) { fprintf(stderr, " incomplete literal tree\n"); huft_free(tl); } return i; /* incomplete code set */ } bd = dbits; if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0) { if (i == 1) { fprintf(stderr, " incomplete distance tree\n"); #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); /* Undo too much lookahead. The next read will be byte aligned so we * can discard unused bits in the last meaningful byte. */ while (bk >= 8) { bk -= 8; inptr--; } /* flush out slide */ flush_output(wp); /* return success */ #ifdef DEBUG fprintf(stderr, "<%u> ", h); #endif /* DEBUG */ return 0; } Index: stable/4/gnu/usr.bin/gzip/unlzh.c =================================================================== --- stable/4/gnu/usr.bin/gzip/unlzh.c (revision 162445) +++ stable/4/gnu/usr.bin/gzip/unlzh.c (revision 162446) @@ -1,401 +1,405 @@ /* unlzh.c -- decompress files in SCO compress -H (LZH) format. * The code in this file is directly derived from the public domain 'ar002' * written by Haruhiko Okumura. */ #ifdef RCSID static char rcsid[] = "$FreeBSD$"; #endif #include #include "tailor.h" #include "gzip.h" #include "lzw.h" /* just for consistency checking */ /* decode.c */ local unsigned decode OF((unsigned count, uch buffer[])); local void decode_start OF((void)); /* huf.c */ local void huf_decode_start OF((void)); local unsigned decode_c OF((void)); local unsigned decode_p OF((void)); local void read_pt_len OF((int nn, int nbit, int i_special)); local void read_c_len OF((void)); /* io.c */ local void fillbuf OF((int n)); local unsigned getbits OF((int n)); local void init_getbits OF((void)); /* maketbl.c */ local void make_table OF((int nchar, uch bitlen[], int tablebits, ush table[])); #define DICBIT 13 /* 12(-lh4-) or 13(-lh5-) */ #define DICSIZ ((unsigned) 1 << DICBIT) #ifndef CHAR_BIT # define CHAR_BIT 8 #endif #ifndef UCHAR_MAX # define UCHAR_MAX 255 #endif #define BITBUFSIZ (CHAR_BIT * 2 * sizeof(char)) /* Do not use CHAR_BIT * sizeof(bitbuf), does not work on machines * for which short is not on 16 bits (Cray). */ /* encode.c and decode.c */ #define MAXMATCH 256 /* formerly F (not more than UCHAR_MAX + 1) */ #define THRESHOLD 3 /* choose optimal value */ /* huf.c */ #define NC (UCHAR_MAX + MAXMATCH + 2 - THRESHOLD) /* alphabet = {0, 1, 2, ..., NC - 1} */ #define CBIT 9 /* $\lfloor \log_2 NC \rfloor + 1$ */ #define CODE_BIT 16 /* codeword length */ #define NP (DICBIT + 1) #define NT (CODE_BIT + 3) #define PBIT 4 /* smallest integer such that (1U << PBIT) > NP */ #define TBIT 5 /* smallest integer such that (1U << TBIT) > NT */ #if NT > NP # define NPT NT #else # define NPT NP #endif /* local ush left[2 * NC - 1]; */ /* local ush right[2 * NC - 1]; */ #define left prev #define right head #if NC > (1<<(BITS-2)) error cannot overlay left+right and prev #endif /* local uch c_len[NC]; */ #define c_len outbuf #if NC > OUTBUFSIZ error cannot overlay c_len and outbuf #endif local uch pt_len[NPT]; local unsigned blocksize; local ush pt_table[256]; /* local ush c_table[4096]; */ #define c_table d_buf #if (DIST_BUFSIZE-1) < 4095 error cannot overlay c_table and d_buf #endif /*********************************************************** io.c -- input/output ***********************************************************/ local ush bitbuf; local unsigned subbitbuf; local int bitcount; local void fillbuf(n) /* Shift bitbuf n bits left, read n bits */ int n; { bitbuf <<= n; while (n > bitcount) { bitbuf |= subbitbuf << (n -= bitcount); subbitbuf = (unsigned)try_byte(); if ((int)subbitbuf == EOF) subbitbuf = 0; bitcount = CHAR_BIT; } bitbuf |= subbitbuf >> (bitcount -= n); } local unsigned getbits(n) int n; { unsigned x; x = bitbuf >> (BITBUFSIZ - n); fillbuf(n); return x; } local void init_getbits() { bitbuf = 0; subbitbuf = 0; bitcount = 0; fillbuf(BITBUFSIZ); } /*********************************************************** maketbl.c -- make table for decoding ***********************************************************/ local void make_table(nchar, bitlen, tablebits, table) int nchar; uch bitlen[]; int tablebits; ush table[]; { ush count[17], weight[17], start[18], *p; unsigned i, k, len, ch, jutbits, avail, nextcode, mask; for (i = 1; i <= 16; i++) count[i] = 0; - for (i = 0; i < (unsigned)nchar; i++) count[bitlen[i]]++; + for (i = 0; i < (unsigned)nchar; i++) { + if (bitlen[i] > 16) + error("Bad table (case a)\n"); + else count[bitlen[i]]++; + } start[1] = 0; for (i = 1; i <= 16; i++) start[i + 1] = start[i] + (count[i] << (16 - i)); - if ((start[17] & 0xffff) != 0) - error("Bad table\n"); + if ((start[17] & 0xffff) != 0 || tablebits > 16) /* 16 for weight below */ + error("Bad table (case b)\n"); jutbits = 16 - tablebits; for (i = 1; i <= (unsigned)tablebits; i++) { start[i] >>= jutbits; weight[i] = (unsigned) 1 << (tablebits - i); } while (i <= 16) { weight[i] = (unsigned) 1 << (16 - i); i++; } i = start[tablebits + 1] >> jutbits; if (i != 0) { - k = 1 << tablebits; - while (i != k) table[i++] = 0; + k = MIN(1 << tablebits, DIST_BUFSIZE); + while (i < k) table[i++] = 0; } avail = nchar; mask = (unsigned) 1 << (15 - tablebits); for (ch = 0; ch < (unsigned)nchar; ch++) { if ((len = bitlen[ch]) == 0) continue; - nextcode = start[len] + weight[len]; + nextcode = MIN(start[len] + weight[len], DIST_BUFSIZE); if (len <= (unsigned)tablebits) { for (i = start[len]; i < nextcode; i++) table[i] = ch; } else { k = start[len]; p = &table[k >> jutbits]; i = len - tablebits; while (i != 0) { if (*p == 0) { right[avail] = left[avail] = 0; *p = avail++; } if (k & mask) p = &right[*p]; else p = &left[*p]; k <<= 1; i--; } *p = ch; } start[len] = nextcode; } } /*********************************************************** huf.c -- static Huffman ***********************************************************/ local void read_pt_len(nn, nbit, i_special) int nn; int nbit; int i_special; { int i, c, n; unsigned mask; n = getbits(nbit); if (n == 0) { c = getbits(nbit); for (i = 0; i < nn; i++) pt_len[i] = 0; for (i = 0; i < 256; i++) pt_table[i] = c; } else { i = 0; - while (i < n) { + while (i < MIN(n,NPT)) { c = bitbuf >> (BITBUFSIZ - 3); if (c == 7) { mask = (unsigned) 1 << (BITBUFSIZ - 1 - 3); while (mask & bitbuf) { mask >>= 1; c++; } } fillbuf((c < 7) ? 3 : c - 3); pt_len[i++] = c; if (i == i_special) { c = getbits(2); - while (--c >= 0) pt_len[i++] = 0; + while (--c >= 0 && i < NPT) pt_len[i++] = 0; } } while (i < nn) pt_len[i++] = 0; make_table(nn, pt_len, 8, pt_table); } } local void read_c_len() { int i, c, n; unsigned mask; n = getbits(CBIT); if (n == 0) { c = getbits(CBIT); for (i = 0; i < NC; i++) c_len[i] = 0; for (i = 0; i < 4096; i++) c_table[i] = c; } else { i = 0; - while (i < n) { + while (i < MIN(n,NC)) { c = pt_table[bitbuf >> (BITBUFSIZ - 8)]; if (c >= NT) { mask = (unsigned) 1 << (BITBUFSIZ - 1 - 8); do { if (bitbuf & mask) c = right[c]; else c = left [c]; mask >>= 1; - } while (c >= NT); + } while (c >= NT && (mask || c != left[c])); } fillbuf((int) pt_len[c]); if (c <= 2) { if (c == 0) c = 1; else if (c == 1) c = getbits(4) + 3; else c = getbits(CBIT) + 20; - while (--c >= 0) c_len[i++] = 0; + while (--c >= 0 && i < NC) c_len[i++] = 0; } else c_len[i++] = c - 2; } while (i < NC) c_len[i++] = 0; make_table(NC, c_len, 12, c_table); } } local unsigned decode_c() { unsigned j, mask; if (blocksize == 0) { blocksize = getbits(16); if (blocksize == 0) { return NC; /* end of file */ } read_pt_len(NT, TBIT, 3); read_c_len(); read_pt_len(NP, PBIT, -1); } blocksize--; j = c_table[bitbuf >> (BITBUFSIZ - 12)]; if (j >= NC) { mask = (unsigned) 1 << (BITBUFSIZ - 1 - 12); do { if (bitbuf & mask) j = right[j]; else j = left [j]; mask >>= 1; - } while (j >= NC); + } while (j >= NC && (mask || j != left[j])); } fillbuf((int) c_len[j]); return j; } local unsigned decode_p() { unsigned j, mask; j = pt_table[bitbuf >> (BITBUFSIZ - 8)]; if (j >= NP) { mask = (unsigned) 1 << (BITBUFSIZ - 1 - 8); do { if (bitbuf & mask) j = right[j]; else j = left [j]; mask >>= 1; - } while (j >= NP); + } while (j >= NP && (mask || j != left[j])); } fillbuf((int) pt_len[j]); if (j != 0) j = ((unsigned) 1 << (j - 1)) + getbits((int) (j - 1)); return j; } local void huf_decode_start() { init_getbits(); blocksize = 0; } /*********************************************************** decode.c ***********************************************************/ local int j; /* remaining bytes to copy */ local int done; /* set at end of input */ local void decode_start() { huf_decode_start(); j = 0; done = 0; } /* Decode the input and return the number of decoded bytes put in buffer */ local unsigned decode(count, buffer) unsigned count; uch buffer[]; /* The calling function must keep the number of bytes to be processed. This function decodes either 'count' bytes or 'DICSIZ' bytes, whichever is smaller, into the array 'buffer[]' of size 'DICSIZ' or more. Call decode_start() once for each new file before calling this function. */ { local unsigned i; unsigned r, c; r = 0; while (--j >= 0) { buffer[r] = buffer[i]; i = (i + 1) & (DICSIZ - 1); - if (++r == count) return r; + if (++r >= count) return r; } for ( ; ; ) { c = decode_c(); if (c == NC) { done = 1; return r; } if (c <= UCHAR_MAX) { buffer[r] = c; - if (++r == count) return r; + if (++r >= count) return r; } else { j = c - (UCHAR_MAX + 1 - THRESHOLD); i = (r - decode_p() - 1) & (DICSIZ - 1); while (--j >= 0) { buffer[r] = buffer[i]; i = (i + 1) & (DICSIZ - 1); - if (++r == count) return r; + if (++r >= count) return r; } } } } /* =========================================================================== * Unlzh in to out. Return OK or ERROR. */ int unlzh(in, out) int in; int out; { unsigned n; ifd = in; ofd = out; decode_start(); while (!done) { n = decode((unsigned) DICSIZ, window); if (!test && n > 0) { write_buf(out, (char*)window, n); } } return OK; } Index: stable/4/gnu/usr.bin/gzip/unpack.c =================================================================== --- stable/4/gnu/usr.bin/gzip/unpack.c (revision 162445) +++ stable/4/gnu/usr.bin/gzip/unpack.c (revision 162446) @@ -1,239 +1,238 @@ /* unpack.c -- decompress files in pack format. * Copyright (C) 1992-1993 Jean-loup Gailly * This is free software; you can redistribute it and/or modify it under the * terms of the GNU General Public License, see the file COPYING. */ #ifdef RCSID static char rcsid[] = "$FreeBSD$"; #endif #include "tailor.h" #include "gzip.h" #include "crypt.h" -#define MIN(a,b) ((a) <= (b) ? (a) : (b)) /* The arguments must not have side effects. */ #define MAX_BITLEN 25 /* Maximum length of Huffman codes. (Minor modifications to the code * would be needed to support 32 bits codes, but pack never generates * more than 24 bits anyway.) */ #define LITERALS 256 /* Number of literals, excluding the End of Block (EOB) code */ #define MAX_PEEK 12 /* Maximum number of 'peek' bits used to optimize traversal of the * Huffman tree. */ local ulg orig_len; /* original uncompressed length */ local int max_len; /* maximum bit length of Huffman codes */ local uch literal[LITERALS]; /* The literal bytes present in the Huffman tree. The EOB code is not * represented. */ local int lit_base[MAX_BITLEN+1]; /* All literals of a given bit length are contiguous in literal[] and * have contiguous codes. literal[code+lit_base[len]] is the literal * for a code of len bits. */ local int leaves [MAX_BITLEN+1]; /* Number of leaves for each bit length */ local int parents[MAX_BITLEN+1]; /* Number of parents for each bit length */ local int peek_bits; /* Number of peek bits currently used */ /* local uch prefix_len[1 << MAX_PEEK]; */ #define prefix_len outbuf /* For each bit pattern b of peek_bits bits, prefix_len[b] is the length * of the Huffman code starting with a prefix of b (upper bits), or 0 * if all codes of prefix b have more than peek_bits bits. It is not * necessary to have a huge table (large MAX_PEEK) because most of the * codes encountered in the input stream are short codes (by construction). * So for most codes a single lookup will be necessary. */ #if (1< OUTBUFSIZ error cannot overlay prefix_len and outbuf #endif local ulg bitbuf; /* Bits are added on the low part of bitbuf and read from the high part. */ local int valid; /* number of valid bits in bitbuf */ /* all bits above the last valid bit are always zero */ /* Set code to the next 'bits' input bits without skipping them. code * must be the name of a simple variable and bits must not have side effects. * IN assertions: bits <= 25 (so that we still have room for an extra byte * when valid is only 24), and mask = (1<> (valid-(bits))) & (mask); \ } /* Skip the given number of bits (after having peeked at them): */ #define skip_bits(bits) (valid -= (bits)) #define clear_bitbuf() (valid = 0, bitbuf = 0) /* Local functions */ local void read_tree OF((void)); local void build_tree OF((void)); /* =========================================================================== * Read the Huffman tree. */ local void read_tree() { int len; /* bit length */ int base; /* base offset for a sequence of leaves */ int n; /* Read the original input size, MSB first */ orig_len = 0; for (n = 1; n <= 4; n++) orig_len = (orig_len << 8) | (ulg)get_byte(); max_len = (int)get_byte(); /* maximum bit length of Huffman codes */ if (max_len > MAX_BITLEN) { error("invalid compressed data -- Huffman code > 32 bits"); } /* Get the number of leaves at each bit length */ n = 0; for (len = 1; len <= max_len; len++) { leaves[len] = (int)get_byte(); n += leaves[len]; } if (n > LITERALS) { error("too many leaves in Huffman tree"); } Trace((stderr, "orig_len %ld, max_len %d, leaves %d\n", orig_len, max_len, n)); /* There are at least 2 and at most 256 leaves of length max_len. * (Pack arbitrarily rejects empty files and files consisting of * a single byte even repeated.) To fit the last leaf count in a * byte, it is offset by 2. However, the last literal is the EOB * code, and is not transmitted explicitly in the tree, so we must * adjust here by one only. */ leaves[max_len]++; /* Now read the leaves themselves */ base = 0; for (len = 1; len <= max_len; len++) { /* Remember where the literals of this length start in literal[] : */ lit_base[len] = base; /* And read the literals: */ - for (n = leaves[len]; n > 0; n--) { + for (n = leaves[len]; n > 0 && base < LITERALS; n--) { literal[base++] = (uch)get_byte(); } } leaves[max_len]++; /* Now include the EOB code in the Huffman tree */ } /* =========================================================================== * Build the Huffman tree and the prefix table. */ local void build_tree() { int nodes = 0; /* number of nodes (parents+leaves) at current bit length */ int len; /* current bit length */ uch *prefixp; /* pointer in prefix_len */ for (len = max_len; len >= 1; len--) { /* The number of parent nodes at this level is half the total * number of nodes at parent level: */ nodes >>= 1; parents[len] = nodes; /* Update lit_base by the appropriate bias to skip the parent nodes * (which are not represented in the literal array): */ lit_base[len] -= nodes; /* Restore nodes to be parents+leaves: */ nodes += leaves[len]; } /* Construct the prefix table, from shortest leaves to longest ones. * The shortest code is all ones, so we start at the end of the table. */ peek_bits = MIN(max_len, MAX_PEEK); prefixp = &prefix_len[1< prefix_len) *--prefixp = (uch)len; } /* The length of all other codes is unknown: */ while (prefixp > prefix_len) *--prefixp = 0; } /* =========================================================================== * Unpack in to out. This routine does not support the old pack format * with magic header \037\037. * * IN assertions: the buffer inbuf contains already the beginning of * the compressed data, from offsets inptr to insize-1 included. * The magic header has already been checked. The output buffer is cleared. */ int unpack(in, out) int in, out; /* input and output file descriptors */ { int len; /* Bit length of current code */ unsigned eob; /* End Of Block code */ register unsigned peek; /* lookahead bits */ unsigned peek_mask; /* Mask for peek_bits bits */ ifd = in; ofd = out; read_tree(); /* Read the Huffman tree */ build_tree(); /* Build the prefix table */ clear_bitbuf(); /* Initialize bit input */ peek_mask = (1< 0) { peek >>= peek_bits - len; /* discard the extra bits */ } else { /* Code of more than peek_bits bits, we must traverse the tree */ ulg mask = peek_mask; len = peek_bits; do { len++, mask = (mask<<1)+1; look_bits(peek, len, mask); } while (peek < (unsigned)parents[len]); /* loop as long as peek is a parent node */ } /* At this point, peek is the next complete code, of len bits */ if (peek == eob && len == max_len) break; /* end of file? */ put_ubyte(literal[peek+lit_base[len]]); Tracev((stderr,"%02d %04x %c\n", len, peek, literal[peek+lit_base[len]])); skip_bits(len); } /* for (;;) */ flush_window(); Trace((stderr, "bytes_out %ld\n", bytes_out)); if (orig_len != (ulg)bytes_out) { error("invalid compressed data--length error"); } return OK; }