[llvm-commits] [dragonegg] r152715 - in /dragonegg/trunk/test/compilator/local: bzip2.c gzip.c
Duncan Sands
baldrick at free.fr
Wed Mar 14 06:11:26 PDT 2012
Author: baldrick
Date: Wed Mar 14 08:11:25 2012
New Revision: 152715
URL: http://llvm.org/viewvc/llvm-project?rev=152715&view=rev
Log:
Better to download these large files rather than keeping them locally.
Removed:
dragonegg/trunk/test/compilator/local/bzip2.c
dragonegg/trunk/test/compilator/local/gzip.c
Removed: dragonegg/trunk/test/compilator/local/bzip2.c
URL: http://llvm.org/viewvc/llvm-project/dragonegg/trunk/test/compilator/local/bzip2.c?rev=152714&view=auto
==============================================================================
--- dragonegg/trunk/test/compilator/local/bzip2.c (original)
+++ dragonegg/trunk/test/compilator/local/bzip2.c (removed)
@@ -1,6998 +0,0 @@
-/*-------------------------------------------------------------*/
-/*--- Public header file for the library. ---*/
-/*--- bzlib.h ---*/
-/*-------------------------------------------------------------*/
-
-/*--
- This file is a part of bzip2 and/or libbzip2, a program and
- library for lossless, block-sorting data compression.
-
- Copyright (C) 1996-2002 Julian R Seward. 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. The origin of this software must not be misrepresented; you must
- not claim that you wrote the original software. If you use this
- software in a product, an acknowledgment in the product
- documentation would be appreciated but is not required.
-
- 3. Altered source versions must be plainly marked as such, and must
- not be misrepresented as being the original software.
-
- 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.
-
- Julian Seward, Cambridge, UK.
- jseward at acm.org
- bzip2/libbzip2 version 1.0 of 21 March 2000
-
- This program is based on (at least) the work of:
- Mike Burrows
- David Wheeler
- Peter Fenwick
- Alistair Moffat
- Radford Neal
- Ian H. Witten
- Robert Sedgewick
- Jon L. Bentley
-
- For more information on these sources, see the manual.
---*/
-
-
-#ifndef _BZLIB_H
-#define _BZLIB_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#define BZ_RUN 0
-#define BZ_FLUSH 1
-#define BZ_FINISH 2
-
-#define BZ_OK 0
-#define BZ_RUN_OK 1
-#define BZ_FLUSH_OK 2
-#define BZ_FINISH_OK 3
-#define BZ_STREAM_END 4
-#define BZ_SEQUENCE_ERROR (-1)
-#define BZ_PARAM_ERROR (-2)
-#define BZ_MEM_ERROR (-3)
-#define BZ_DATA_ERROR (-4)
-#define BZ_DATA_ERROR_MAGIC (-5)
-#define BZ_IO_ERROR (-6)
-#define BZ_UNEXPECTED_EOF (-7)
-#define BZ_OUTBUFF_FULL (-8)
-#define BZ_CONFIG_ERROR (-9)
-
-typedef
- struct {
- char *next_in;
- unsigned int avail_in;
- unsigned int total_in_lo32;
- unsigned int total_in_hi32;
-
- char *next_out;
- unsigned int avail_out;
- unsigned int total_out_lo32;
- unsigned int total_out_hi32;
-
- void *state;
-
- void *(*bzalloc)(void *,int,int);
- void (*bzfree)(void *,void *);
- void *opaque;
- }
- bz_stream;
-
-
-#ifndef BZ_IMPORT
-#define BZ_EXPORT
-#endif
-
-/* Need a definitition for FILE */
-#include <stdio.h>
-
-#ifdef _WIN32
-# include <windows.h>
-# ifdef small
- /* windows.h define small to char */
-# undef small
-# endif
-# ifdef BZ_EXPORT
-# define BZ_API(func) WINAPI func
-# define BZ_EXTERN extern
-# else
- /* import windows dll dynamically */
-# define BZ_API(func) (WINAPI * func)
-# define BZ_EXTERN
-# endif
-#else
-# define BZ_API(func) func
-# define BZ_EXTERN extern
-#endif
-
-
-/*-- Core (low-level) library functions --*/
-
-BZ_EXTERN int BZ_API(BZ2_bzCompressInit) (
- bz_stream* strm,
- int blockSize100k,
- int verbosity,
- int workFactor
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzCompress) (
- bz_stream* strm,
- int action
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzCompressEnd) (
- bz_stream* strm
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzDecompressInit) (
- bz_stream *strm,
- int verbosity,
- int small
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzDecompress) (
- bz_stream* strm
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzDecompressEnd) (
- bz_stream *strm
- );
-
-
-
-/*-- High(er) level library functions --*/
-
-#ifndef BZ_NO_STDIO
-#define BZ_MAX_UNUSED 5000
-
-typedef void BZFILE;
-
-BZ_EXTERN BZFILE* BZ_API(BZ2_bzReadOpen) (
- int* bzerror,
- FILE* f,
- int verbosity,
- int small,
- void* unused,
- int nUnused
- );
-
-BZ_EXTERN void BZ_API(BZ2_bzReadClose) (
- int* bzerror,
- BZFILE* b
- );
-
-BZ_EXTERN void BZ_API(BZ2_bzReadGetUnused) (
- int* bzerror,
- BZFILE* b,
- void** unused,
- int* nUnused
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzRead) (
- int* bzerror,
- BZFILE* b,
- void* buf,
- int len
- );
-
-BZ_EXTERN BZFILE* BZ_API(BZ2_bzWriteOpen) (
- int* bzerror,
- FILE* f,
- int blockSize100k,
- int verbosity,
- int workFactor
- );
-
-BZ_EXTERN void BZ_API(BZ2_bzWrite) (
- int* bzerror,
- BZFILE* b,
- void* buf,
- int len
- );
-
-BZ_EXTERN void BZ_API(BZ2_bzWriteClose) (
- int* bzerror,
- BZFILE* b,
- int abandon,
- unsigned int* nbytes_in,
- unsigned int* nbytes_out
- );
-
-BZ_EXTERN void BZ_API(BZ2_bzWriteClose64) (
- int* bzerror,
- BZFILE* b,
- int abandon,
- unsigned int* nbytes_in_lo32,
- unsigned int* nbytes_in_hi32,
- unsigned int* nbytes_out_lo32,
- unsigned int* nbytes_out_hi32
- );
-#endif
-
-
-/*-- Utility functions --*/
-
-BZ_EXTERN int BZ_API(BZ2_bzBuffToBuffCompress) (
- char* dest,
- unsigned int* destLen,
- char* source,
- unsigned int sourceLen,
- int blockSize100k,
- int verbosity,
- int workFactor
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzBuffToBuffDecompress) (
- char* dest,
- unsigned int* destLen,
- char* source,
- unsigned int sourceLen,
- int small,
- int verbosity
- );
-
-
-/*--
- Code contributed by Yoshioka Tsuneo
- (QWF00133 at niftyserve.or.jp/tsuneo-y at is.aist-nara.ac.jp),
- to support better zlib compatibility.
- This code is not _officially_ part of libbzip2 (yet);
- I haven't tested it, documented it, or considered the
- threading-safeness of it.
- If this code breaks, please contact both Yoshioka and me.
---*/
-
-BZ_EXTERN const char * BZ_API(BZ2_bzlibVersion) (
- void
- );
-
-#ifndef BZ_NO_STDIO
-BZ_EXTERN BZFILE * BZ_API(BZ2_bzopen) (
- const char *path,
- const char *mode
- );
-
-BZ_EXTERN BZFILE * BZ_API(BZ2_bzdopen) (
- int fd,
- const char *mode
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzread) (
- BZFILE* b,
- void* buf,
- int len
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzwrite) (
- BZFILE* b,
- void* buf,
- int len
- );
-
-BZ_EXTERN int BZ_API(BZ2_bzflush) (
- BZFILE* b
- );
-
-BZ_EXTERN void BZ_API(BZ2_bzclose) (
- BZFILE* b
- );
-
-BZ_EXTERN const char * BZ_API(BZ2_bzerror) (
- BZFILE *b,
- int *errnum
- );
-#endif
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif
-
-/*-------------------------------------------------------------*/
-/*--- end bzlib.h ---*/
-/*-------------------------------------------------------------*/
-/*-------------------------------------------------------------*/
-/*--- Private header file for the library. ---*/
-/*--- bzlib_private.h ---*/
-/*-------------------------------------------------------------*/
-
-#ifndef _BZLIB_PRIVATE_H
-#define _BZLIB_PRIVATE_H
-
-#include <stdlib.h>
-
-#ifndef BZ_NO_STDIO
-#include <stdio.h>
-#include <ctype.h>
-#include <string.h>
-#endif
-
-
-/*-- General stuff. --*/
-
-#define BZ_VERSION "1.0.2, 30-Dec-2001"
-
-typedef char Char;
-typedef unsigned char Bool;
-typedef unsigned char UChar;
-typedef int Int32;
-typedef unsigned int UInt32;
-typedef short Int16;
-typedef unsigned short UInt16;
-
-#define True ((Bool)1)
-#define False ((Bool)0)
-
-#ifndef __GNUC__
-#define __inline__ /* */
-#endif
-
-#ifndef BZ_NO_STDIO
-extern void BZ2_bz__AssertH__fail ( int errcode );
-#define AssertH(cond,errcode) \
- { if (!(cond)) BZ2_bz__AssertH__fail ( errcode ); }
-#if BZ_DEBUG
-#define AssertD(cond,msg) \
- { if (!(cond)) { \
- fprintf ( stderr, \
- "\n\nlibbzip2(debug build): internal error\n\t%s\n", msg );\
- exit(1); \
- }}
-#else
-#define AssertD(cond,msg) /* */
-#endif
-#define VPrintf0(zf) \
- fprintf(stderr,zf)
-#define VPrintf1(zf,za1) \
- fprintf(stderr,zf,za1)
-#define VPrintf2(zf,za1,za2) \
- fprintf(stderr,zf,za1,za2)
-#define VPrintf3(zf,za1,za2,za3) \
- fprintf(stderr,zf,za1,za2,za3)
-#define VPrintf4(zf,za1,za2,za3,za4) \
- fprintf(stderr,zf,za1,za2,za3,za4)
-#define VPrintf5(zf,za1,za2,za3,za4,za5) \
- fprintf(stderr,zf,za1,za2,za3,za4,za5)
-#else
-extern void bz_internal_error ( int errcode );
-#define AssertH(cond,errcode) \
- { if (!(cond)) bz_internal_error ( errcode ); }
-#define AssertD(cond,msg) /* */
-#define VPrintf0(zf) /* */
-#define VPrintf1(zf,za1) /* */
-#define VPrintf2(zf,za1,za2) /* */
-#define VPrintf3(zf,za1,za2,za3) /* */
-#define VPrintf4(zf,za1,za2,za3,za4) /* */
-#define VPrintf5(zf,za1,za2,za3,za4,za5) /* */
-#endif
-
-
-#define BZALLOC(nnn) (strm->bzalloc)(strm->opaque,(nnn),1)
-#define BZFREE(ppp) (strm->bzfree)(strm->opaque,(ppp))
-
-
-/*-- Header bytes. --*/
-
-#define BZ_HDR_B 0x42 /* 'B' */
-#define BZ_HDR_Z 0x5a /* 'Z' */
-#define BZ_HDR_h 0x68 /* 'h' */
-#define BZ_HDR_0 0x30 /* '0' */
-
-/*-- Constants for the back end. --*/
-
-#define BZ_MAX_ALPHA_SIZE 258
-#define BZ_MAX_CODE_LEN 23
-
-#define BZ_RUNA 0
-#define BZ_RUNB 1
-
-#define BZ_N_GROUPS 6
-#define BZ_G_SIZE 50
-#define BZ_N_ITERS 4
-
-#define BZ_MAX_SELECTORS (2 + (900000 / BZ_G_SIZE))
-
-
-
-/*-- Stuff for randomising repetitive blocks. --*/
-
-extern Int32 BZ2_rNums[512];
-
-#define BZ_RAND_DECLS \
- Int32 rNToGo; \
- Int32 rTPos \
-
-#define BZ_RAND_INIT_MASK \
- s->rNToGo = 0; \
- s->rTPos = 0 \
-
-#define BZ_RAND_MASK ((s->rNToGo == 1) ? 1 : 0)
-
-#define BZ_RAND_UPD_MASK \
- if (s->rNToGo == 0) { \
- s->rNToGo = BZ2_rNums[s->rTPos]; \
- s->rTPos++; \
- if (s->rTPos == 512) s->rTPos = 0; \
- } \
- s->rNToGo--;
-
-
-
-/*-- Stuff for doing CRCs. --*/
-
-extern UInt32 BZ2_crc32Table[256];
-
-#define BZ_INITIALISE_CRC(crcVar) \
-{ \
- crcVar = 0xffffffffL; \
-}
-
-#define BZ_FINALISE_CRC(crcVar) \
-{ \
- crcVar = ~(crcVar); \
-}
-
-#define BZ_UPDATE_CRC(crcVar,cha) \
-{ \
- crcVar = (crcVar << 8) ^ \
- BZ2_crc32Table[(crcVar >> 24) ^ \
- ((UChar)cha)]; \
-}
-
-
-
-/*-- States and modes for compression. --*/
-
-#define BZ_M_IDLE 1
-#define BZ_M_RUNNING 2
-#define BZ_M_FLUSHING 3
-#define BZ_M_FINISHING 4
-
-#define BZ_S_OUTPUT 1
-#define BZ_S_INPUT 2
-
-#define BZ_N_RADIX 2
-#define BZ_N_QSORT 12
-#define BZ_N_SHELL 18
-#define BZ_N_OVERSHOOT (BZ_N_RADIX + BZ_N_QSORT + BZ_N_SHELL + 2)
-
-
-
-
-/*-- Structure holding all the compression-side stuff. --*/
-
-typedef
- struct {
- /* pointer back to the struct bz_stream */
- bz_stream* strm;
-
- /* mode this stream is in, and whether inputting */
- /* or outputting data */
- Int32 mode;
- Int32 state;
-
- /* remembers avail_in when flush/finish requested */
- UInt32 avail_in_expect;
-
- /* for doing the block sorting */
- UInt32* arr1;
- UInt32* arr2;
- UInt32* ftab;
- Int32 origPtr;
-
- /* aliases for arr1 and arr2 */
- UInt32* ptr;
- UChar* block;
- UInt16* mtfv;
- UChar* zbits;
-
- /* for deciding when to use the fallback sorting algorithm */
- Int32 workFactor;
-
- /* run-length-encoding of the input */
- UInt32 state_in_ch;
- Int32 state_in_len;
- BZ_RAND_DECLS;
-
- /* input and output limits and current posns */
- Int32 nblock;
- Int32 nblockMAX;
- Int32 numZ;
- Int32 state_out_pos;
-
- /* map of bytes used in block */
- Int32 nInUse;
- Bool inUse[256];
- UChar unseqToSeq[256];
-
- /* the buffer for bit stream creation */
- UInt32 bsBuff;
- Int32 bsLive;
-
- /* block and combined CRCs */
- UInt32 blockCRC;
- UInt32 combinedCRC;
-
- /* misc administratium */
- Int32 verbosity;
- Int32 blockNo;
- Int32 blockSize100k;
-
- /* stuff for coding the MTF values */
- Int32 nMTF;
- Int32 mtfFreq [BZ_MAX_ALPHA_SIZE];
- UChar selector [BZ_MAX_SELECTORS];
- UChar selectorMtf[BZ_MAX_SELECTORS];
-
- UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- Int32 code [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- Int32 rfreq [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- /* second dimension: only 3 needed; 4 makes index calculations faster */
- UInt32 len_pack[BZ_MAX_ALPHA_SIZE][4];
-
- }
- EState;
-
-
-
-/*-- externs for compression. --*/
-
-extern void
-BZ2_blockSort ( EState* );
-
-extern void
-BZ2_compressBlock ( EState*, Bool );
-
-extern void
-BZ2_bsInitWrite ( EState* );
-
-extern void
-BZ2_hbAssignCodes ( Int32*, UChar*, Int32, Int32, Int32 );
-
-extern void
-BZ2_hbMakeCodeLengths ( UChar*, Int32*, Int32, Int32 );
-
-
-
-/*-- states for decompression. --*/
-
-#define BZ_X_IDLE 1
-#define BZ_X_OUTPUT 2
-
-#define BZ_X_MAGIC_1 10
-#define BZ_X_MAGIC_2 11
-#define BZ_X_MAGIC_3 12
-#define BZ_X_MAGIC_4 13
-#define BZ_X_BLKHDR_1 14
-#define BZ_X_BLKHDR_2 15
-#define BZ_X_BLKHDR_3 16
-#define BZ_X_BLKHDR_4 17
-#define BZ_X_BLKHDR_5 18
-#define BZ_X_BLKHDR_6 19
-#define BZ_X_BCRC_1 20
-#define BZ_X_BCRC_2 21
-#define BZ_X_BCRC_3 22
-#define BZ_X_BCRC_4 23
-#define BZ_X_RANDBIT 24
-#define BZ_X_ORIGPTR_1 25
-#define BZ_X_ORIGPTR_2 26
-#define BZ_X_ORIGPTR_3 27
-#define BZ_X_MAPPING_1 28
-#define BZ_X_MAPPING_2 29
-#define BZ_X_SELECTOR_1 30
-#define BZ_X_SELECTOR_2 31
-#define BZ_X_SELECTOR_3 32
-#define BZ_X_CODING_1 33
-#define BZ_X_CODING_2 34
-#define BZ_X_CODING_3 35
-#define BZ_X_MTF_1 36
-#define BZ_X_MTF_2 37
-#define BZ_X_MTF_3 38
-#define BZ_X_MTF_4 39
-#define BZ_X_MTF_5 40
-#define BZ_X_MTF_6 41
-#define BZ_X_ENDHDR_2 42
-#define BZ_X_ENDHDR_3 43
-#define BZ_X_ENDHDR_4 44
-#define BZ_X_ENDHDR_5 45
-#define BZ_X_ENDHDR_6 46
-#define BZ_X_CCRC_1 47
-#define BZ_X_CCRC_2 48
-#define BZ_X_CCRC_3 49
-#define BZ_X_CCRC_4 50
-
-
-
-/*-- Constants for the fast MTF decoder. --*/
-
-#define MTFA_SIZE 4096
-#define MTFL_SIZE 16
-
-
-
-/*-- Structure holding all the decompression-side stuff. --*/
-
-typedef
- struct {
- /* pointer back to the struct bz_stream */
- bz_stream* strm;
-
- /* state indicator for this stream */
- Int32 state;
-
- /* for doing the final run-length decoding */
- UChar state_out_ch;
- Int32 state_out_len;
- Bool blockRandomised;
- BZ_RAND_DECLS;
-
- /* the buffer for bit stream reading */
- UInt32 bsBuff;
- Int32 bsLive;
-
- /* misc administratium */
- Int32 blockSize100k;
- Bool smallDecompress;
- Int32 currBlockNo;
- Int32 verbosity;
-
- /* for undoing the Burrows-Wheeler transform */
- Int32 origPtr;
- UInt32 tPos;
- Int32 k0;
- Int32 unzftab[256];
- Int32 nblock_used;
- Int32 cftab[257];
- Int32 cftabCopy[257];
-
- /* for undoing the Burrows-Wheeler transform (FAST) */
- UInt32 *tt;
-
- /* for undoing the Burrows-Wheeler transform (SMALL) */
- UInt16 *ll16;
- UChar *ll4;
-
- /* stored and calculated CRCs */
- UInt32 storedBlockCRC;
- UInt32 storedCombinedCRC;
- UInt32 calculatedBlockCRC;
- UInt32 calculatedCombinedCRC;
-
- /* map of bytes used in block */
- Int32 nInUse;
- Bool inUse[256];
- Bool inUse16[16];
- UChar seqToUnseq[256];
-
- /* for decoding the MTF values */
- UChar mtfa [MTFA_SIZE];
- Int32 mtfbase[256 / MTFL_SIZE];
- UChar selector [BZ_MAX_SELECTORS];
- UChar selectorMtf[BZ_MAX_SELECTORS];
- UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
-
- Int32 limit [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- Int32 base [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- Int32 perm [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- Int32 minLens[BZ_N_GROUPS];
-
- /* save area for scalars in the main decompress code */
- Int32 save_i;
- Int32 save_j;
- Int32 save_t;
- Int32 save_alphaSize;
- Int32 save_nGroups;
- Int32 save_nSelectors;
- Int32 save_EOB;
- Int32 save_groupNo;
- Int32 save_groupPos;
- Int32 save_nextSym;
- Int32 save_nblockMAX;
- Int32 save_nblock;
- Int32 save_es;
- Int32 save_N;
- Int32 save_curr;
- Int32 save_zt;
- Int32 save_zn;
- Int32 save_zvec;
- Int32 save_zj;
- Int32 save_gSel;
- Int32 save_gMinlen;
- Int32* save_gLimit;
- Int32* save_gBase;
- Int32* save_gPerm;
-
- }
- DState;
-
-
-
-/*-- Macros for decompression. --*/
-
-#define BZ_GET_FAST(cccc) \
- s->tPos = s->tt[s->tPos]; \
- cccc = (UChar)(s->tPos & 0xff); \
- s->tPos >>= 8;
-
-#define BZ_GET_FAST_C(cccc) \
- c_tPos = c_tt[c_tPos]; \
- cccc = (UChar)(c_tPos & 0xff); \
- c_tPos >>= 8;
-
-#define SET_LL4(i,n) \
- { if (((i) & 0x1) == 0) \
- s->ll4[(i) >> 1] = (s->ll4[(i) >> 1] & 0xf0) | (n); else \
- s->ll4[(i) >> 1] = (s->ll4[(i) >> 1] & 0x0f) | ((n) << 4); \
- }
-
-#define GET_LL4(i) \
- ((((UInt32)(s->ll4[(i) >> 1])) >> (((i) << 2) & 0x4)) & 0xF)
-
-#define SET_LL(i,n) \
- { s->ll16[i] = (UInt16)(n & 0x0000ffff); \
- SET_LL4(i, n >> 16); \
- }
-
-#define GET_LL(i) \
- (((UInt32)s->ll16[i]) | (GET_LL4(i) << 16))
-
-#define BZ_GET_SMALL(cccc) \
- cccc = BZ2_indexIntoF ( s->tPos, s->cftab ); \
- s->tPos = GET_LL(s->tPos);
-
-
-/*-- externs for decompression. --*/
-
-extern Int32
-BZ2_indexIntoF ( Int32, Int32* );
-
-extern Int32
-BZ2_decompress ( DState* );
-
-extern void
-BZ2_hbCreateDecodeTables ( Int32*, Int32*, Int32*, UChar*,
- Int32, Int32, Int32 );
-
-
-#endif
-
-
-/*-- BZ_NO_STDIO seems to make NULL disappear on some platforms. --*/
-
-#ifdef BZ_NO_STDIO
-#ifndef NULL
-#define NULL 0
-#endif
-#endif
-
-
-/*-------------------------------------------------------------*/
-/*--- end bzlib_private.h ---*/
-/*-------------------------------------------------------------*/
-
-
-
-/*-------------------------------------------------------------*/
-/*--- Block sorting machinery ---*/
-/*--- blocksort.c ---*/
-/*-------------------------------------------------------------*/
-
-/*---------------------------------------------*/
-/*--- Fallback O(N log(N)^2) sorting ---*/
-/*--- algorithm, for repetitive blocks ---*/
-/*---------------------------------------------*/
-
-/*---------------------------------------------*/
-static
-__inline__
-void fallbackSimpleSort ( UInt32* fmap,
- UInt32* eclass,
- Int32 lo,
- Int32 hi )
-{
- Int32 i, j, tmp;
- UInt32 ec_tmp;
-
- if (lo == hi) return;
-
- if (hi - lo > 3) {
- for ( i = hi-4; i >= lo; i-- ) {
- tmp = fmap[i];
- ec_tmp = eclass[tmp];
- for ( j = i+4; j <= hi && ec_tmp > eclass[fmap[j]]; j += 4 )
- fmap[j-4] = fmap[j];
- fmap[j-4] = tmp;
- }
- }
-
- for ( i = hi-1; i >= lo; i-- ) {
- tmp = fmap[i];
- ec_tmp = eclass[tmp];
- for ( j = i+1; j <= hi && ec_tmp > eclass[fmap[j]]; j++ )
- fmap[j-1] = fmap[j];
- fmap[j-1] = tmp;
- }
-}
-
-
-/*---------------------------------------------*/
-#define fswap(zz1, zz2) \
- { Int32 zztmp = zz1; zz1 = zz2; zz2 = zztmp; }
-
-#define fvswap(zzp1, zzp2, zzn) \
-{ \
- Int32 yyp1 = (zzp1); \
- Int32 yyp2 = (zzp2); \
- Int32 yyn = (zzn); \
- while (yyn > 0) { \
- fswap(fmap[yyp1], fmap[yyp2]); \
- yyp1++; yyp2++; yyn--; \
- } \
-}
-
-
-#define fmin(a,b) ((a) < (b)) ? (a) : (b)
-
-#define fpush(lz,hz) { stackLo[sp] = lz; \
- stackHi[sp] = hz; \
- sp++; }
-
-#define fpop(lz,hz) { sp--; \
- lz = stackLo[sp]; \
- hz = stackHi[sp]; }
-
-#define FALLBACK_QSORT_SMALL_THRESH 10
-#define FALLBACK_QSORT_STACK_SIZE 100
-
-
-static
-void fallbackQSort3 ( UInt32* fmap,
- UInt32* eclass,
- Int32 loSt,
- Int32 hiSt )
-{
- Int32 unLo, unHi, ltLo, gtHi, n, m;
- Int32 sp, lo, hi;
- UInt32 med, r, r3;
- Int32 stackLo[FALLBACK_QSORT_STACK_SIZE];
- Int32 stackHi[FALLBACK_QSORT_STACK_SIZE];
-
- r = 0;
-
- sp = 0;
- fpush ( loSt, hiSt );
-
- while (sp > 0) {
-
- AssertH ( sp < FALLBACK_QSORT_STACK_SIZE, 1004 );
-
- fpop ( lo, hi );
- if (hi - lo < FALLBACK_QSORT_SMALL_THRESH) {
- fallbackSimpleSort ( fmap, eclass, lo, hi );
- continue;
- }
-
- /* Random partitioning. Median of 3 sometimes fails to
- avoid bad cases. Median of 9 seems to help but
- looks rather expensive. This too seems to work but
- is cheaper. Guidance for the magic constants
- 7621 and 32768 is taken from Sedgewick's algorithms
- book, chapter 35.
- */
- r = ((r * 7621) + 1) % 32768;
- r3 = r % 3;
- if (r3 == 0) med = eclass[fmap[lo]]; else
- if (r3 == 1) med = eclass[fmap[(lo+hi)>>1]]; else
- med = eclass[fmap[hi]];
-
- unLo = ltLo = lo;
- unHi = gtHi = hi;
-
- while (1) {
- while (1) {
- if (unLo > unHi) break;
- n = (Int32)eclass[fmap[unLo]] - (Int32)med;
- if (n == 0) {
- fswap(fmap[unLo], fmap[ltLo]);
- ltLo++; unLo++;
- continue;
- };
- if (n > 0) break;
- unLo++;
- }
- while (1) {
- if (unLo > unHi) break;
- n = (Int32)eclass[fmap[unHi]] - (Int32)med;
- if (n == 0) {
- fswap(fmap[unHi], fmap[gtHi]);
- gtHi--; unHi--;
- continue;
- };
- if (n < 0) break;
- unHi--;
- }
- if (unLo > unHi) break;
- fswap(fmap[unLo], fmap[unHi]); unLo++; unHi--;
- }
-
- AssertD ( unHi == unLo-1, "fallbackQSort3(2)" );
-
- if (gtHi < ltLo) continue;
-
- n = fmin(ltLo-lo, unLo-ltLo); fvswap(lo, unLo-n, n);
- m = fmin(hi-gtHi, gtHi-unHi); fvswap(unLo, hi-m+1, m);
-
- n = lo + unLo - ltLo - 1;
- m = hi - (gtHi - unHi) + 1;
-
- if (n - lo > hi - m) {
- fpush ( lo, n );
- fpush ( m, hi );
- } else {
- fpush ( m, hi );
- fpush ( lo, n );
- }
- }
-}
-
-#undef fmin
-#undef fpush
-#undef fpop
-#undef fswap
-#undef fvswap
-#undef FALLBACK_QSORT_SMALL_THRESH
-#undef FALLBACK_QSORT_STACK_SIZE
-
-
-/*---------------------------------------------*/
-/* Pre:
- nblock > 0
- eclass exists for [0 .. nblock-1]
- ((UChar*)eclass) [0 .. nblock-1] holds block
- ptr exists for [0 .. nblock-1]
-
- Post:
- ((UChar*)eclass) [0 .. nblock-1] holds block
- All other areas of eclass destroyed
- fmap [0 .. nblock-1] holds sorted order
- bhtab [ 0 .. 2+(nblock/32) ] destroyed
-*/
-
-#define SET_BH(zz) bhtab[(zz) >> 5] |= (1 << ((zz) & 31))
-#define CLEAR_BH(zz) bhtab[(zz) >> 5] &= ~(1 << ((zz) & 31))
-#define ISSET_BH(zz) (bhtab[(zz) >> 5] & (1 << ((zz) & 31)))
-#define WORD_BH(zz) bhtab[(zz) >> 5]
-#define UNALIGNED_BH(zz) ((zz) & 0x01f)
-
-static
-void fallbackSort ( UInt32* fmap,
- UInt32* eclass,
- UInt32* bhtab,
- Int32 nblock,
- Int32 verb )
-{
- Int32 ftab[257];
- Int32 ftabCopy[256];
- Int32 H, i, j, k, l, r, cc, cc1;
- Int32 nNotDone;
- Int32 nBhtab;
- UChar* eclass8 = (UChar*)eclass;
-
- /*--
- Initial 1-char radix sort to generate
- initial fmap and initial BH bits.
- --*/
- if (verb >= 4)
- VPrintf0 ( " bucket sorting ...\n" );
- for (i = 0; i < 257; i++) ftab[i] = 0;
- for (i = 0; i < nblock; i++) ftab[eclass8[i]]++;
- for (i = 0; i < 256; i++) ftabCopy[i] = ftab[i];
- for (i = 1; i < 257; i++) ftab[i] += ftab[i-1];
-
- for (i = 0; i < nblock; i++) {
- j = eclass8[i];
- k = ftab[j] - 1;
- ftab[j] = k;
- fmap[k] = i;
- }
-
- nBhtab = 2 + (nblock / 32);
- for (i = 0; i < nBhtab; i++) bhtab[i] = 0;
- for (i = 0; i < 256; i++) SET_BH(ftab[i]);
-
- /*--
- Inductively refine the buckets. Kind-of an
- "exponential radix sort" (!), inspired by the
- Manber-Myers suffix array construction algorithm.
- --*/
-
- /*-- set sentinel bits for block-end detection --*/
- for (i = 0; i < 32; i++) {
- SET_BH(nblock + 2*i);
- CLEAR_BH(nblock + 2*i + 1);
- }
-
- /*-- the log(N) loop --*/
- H = 1;
- while (1) {
-
- if (verb >= 4)
- VPrintf1 ( " depth %6d has ", H );
-
- j = 0;
- for (i = 0; i < nblock; i++) {
- if (ISSET_BH(i)) j = i;
- k = fmap[i] - H; if (k < 0) k += nblock;
- eclass[k] = j;
- }
-
- nNotDone = 0;
- r = -1;
- while (1) {
-
- /*-- find the next non-singleton bucket --*/
- k = r + 1;
- while (ISSET_BH(k) && UNALIGNED_BH(k)) k++;
- if (ISSET_BH(k)) {
- while (WORD_BH(k) == 0xffffffff) k += 32;
- while (ISSET_BH(k)) k++;
- }
- l = k - 1;
- if (l >= nblock) break;
- while (!ISSET_BH(k) && UNALIGNED_BH(k)) k++;
- if (!ISSET_BH(k)) {
- while (WORD_BH(k) == 0x00000000) k += 32;
- while (!ISSET_BH(k)) k++;
- }
- r = k - 1;
- if (r >= nblock) break;
-
- /*-- now [l, r] bracket current bucket --*/
- if (r > l) {
- nNotDone += (r - l + 1);
- fallbackQSort3 ( fmap, eclass, l, r );
-
- /*-- scan bucket and generate header bits-- */
- cc = -1;
- for (i = l; i <= r; i++) {
- cc1 = eclass[fmap[i]];
- if (cc != cc1) { SET_BH(i); cc = cc1; };
- }
- }
- }
-
- if (verb >= 4)
- VPrintf1 ( "%6d unresolved strings\n", nNotDone );
-
- H *= 2;
- if (H > nblock || nNotDone == 0) break;
- }
-
- /*--
- Reconstruct the original block in
- eclass8 [0 .. nblock-1], since the
- previous phase destroyed it.
- --*/
- if (verb >= 4)
- VPrintf0 ( " reconstructing block ...\n" );
- j = 0;
- for (i = 0; i < nblock; i++) {
- while (ftabCopy[j] == 0) j++;
- ftabCopy[j]--;
- eclass8[fmap[i]] = (UChar)j;
- }
- AssertH ( j < 256, 1005 );
-}
-
-#undef SET_BH
-#undef CLEAR_BH
-#undef ISSET_BH
-#undef WORD_BH
-#undef UNALIGNED_BH
-
-
-/*---------------------------------------------*/
-/*--- The main, O(N^2 log(N)) sorting ---*/
-/*--- algorithm. Faster for "normal" ---*/
-/*--- non-repetitive blocks. ---*/
-/*---------------------------------------------*/
-
-/*---------------------------------------------*/
-static
-__inline__
-Bool mainGtU ( UInt32 i1,
- UInt32 i2,
- UChar* block,
- UInt16* quadrant,
- UInt32 nblock,
- Int32* budget )
-{
- Int32 k;
- UChar c1, c2;
- UInt16 s1, s2;
-
- AssertD ( i1 != i2, "mainGtU" );
- /* 1 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 2 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 3 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 4 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 5 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 6 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 7 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 8 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 9 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 10 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 11 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
- /* 12 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- i1++; i2++;
-
- k = nblock + 8;
-
- do {
- /* 1 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 2 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 3 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 4 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 5 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 6 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 7 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
- /* 8 */
- c1 = block[i1]; c2 = block[i2];
- if (c1 != c2) return (c1 > c2);
- s1 = quadrant[i1]; s2 = quadrant[i2];
- if (s1 != s2) return (s1 > s2);
- i1++; i2++;
-
- if (i1 >= nblock) i1 -= nblock;
- if (i2 >= nblock) i2 -= nblock;
-
- k -= 8;
- (*budget)--;
- }
- while (k >= 0);
-
- return False;
-}
-
-
-/*---------------------------------------------*/
-/*--
- Knuth's increments seem to work better
- than Incerpi-Sedgewick here. Possibly
- because the number of elems to sort is
- usually small, typically <= 20.
---*/
-static
-Int32 incs[14] = { 1, 4, 13, 40, 121, 364, 1093, 3280,
- 9841, 29524, 88573, 265720,
- 797161, 2391484 };
-
-static
-void mainSimpleSort ( UInt32* ptr,
- UChar* block,
- UInt16* quadrant,
- Int32 nblock,
- Int32 lo,
- Int32 hi,
- Int32 d,
- Int32* budget )
-{
- Int32 i, j, h, bigN, hp;
- UInt32 v;
-
- bigN = hi - lo + 1;
- if (bigN < 2) return;
-
- hp = 0;
- while (incs[hp] < bigN) hp++;
- hp--;
-
- for (; hp >= 0; hp--) {
- h = incs[hp];
-
- i = lo + h;
- while (True) {
-
- /*-- copy 1 --*/
- if (i > hi) break;
- v = ptr[i];
- j = i;
- while ( mainGtU (
- ptr[j-h]+d, v+d, block, quadrant, nblock, budget
- ) ) {
- ptr[j] = ptr[j-h];
- j = j - h;
- if (j <= (lo + h - 1)) break;
- }
- ptr[j] = v;
- i++;
-
- /*-- copy 2 --*/
- if (i > hi) break;
- v = ptr[i];
- j = i;
- while ( mainGtU (
- ptr[j-h]+d, v+d, block, quadrant, nblock, budget
- ) ) {
- ptr[j] = ptr[j-h];
- j = j - h;
- if (j <= (lo + h - 1)) break;
- }
- ptr[j] = v;
- i++;
-
- /*-- copy 3 --*/
- if (i > hi) break;
- v = ptr[i];
- j = i;
- while ( mainGtU (
- ptr[j-h]+d, v+d, block, quadrant, nblock, budget
- ) ) {
- ptr[j] = ptr[j-h];
- j = j - h;
- if (j <= (lo + h - 1)) break;
- }
- ptr[j] = v;
- i++;
-
- if (*budget < 0) return;
- }
- }
-}
-
-
-/*---------------------------------------------*/
-/*--
- The following is an implementation of
- an elegant 3-way quicksort for strings,
- described in a paper "Fast Algorithms for
- Sorting and Searching Strings", by Robert
- Sedgewick and Jon L. Bentley.
---*/
-
-#define mswap(zz1, zz2) \
- { Int32 zztmp = zz1; zz1 = zz2; zz2 = zztmp; }
-
-#define mvswap(zzp1, zzp2, zzn) \
-{ \
- Int32 yyp1 = (zzp1); \
- Int32 yyp2 = (zzp2); \
- Int32 yyn = (zzn); \
- while (yyn > 0) { \
- mswap(ptr[yyp1], ptr[yyp2]); \
- yyp1++; yyp2++; yyn--; \
- } \
-}
-
-static
-__inline__
-UChar mmed3 ( UChar a, UChar b, UChar c )
-{
- UChar t;
- if (a > b) { t = a; a = b; b = t; };
- if (b > c) {
- b = c;
- if (a > b) b = a;
- }
- return b;
-}
-
-#define mmin(a,b) ((a) < (b)) ? (a) : (b)
-
-#define mpush(lz,hz,dz) { stackLo[sp] = lz; \
- stackHi[sp] = hz; \
- stackD [sp] = dz; \
- sp++; }
-
-#define mpop(lz,hz,dz) { sp--; \
- lz = stackLo[sp]; \
- hz = stackHi[sp]; \
- dz = stackD [sp]; }
-
-
-#define mnextsize(az) (nextHi[az]-nextLo[az])
-
-#define mnextswap(az,bz) \
- { Int32 tz; \
- tz = nextLo[az]; nextLo[az] = nextLo[bz]; nextLo[bz] = tz; \
- tz = nextHi[az]; nextHi[az] = nextHi[bz]; nextHi[bz] = tz; \
- tz = nextD [az]; nextD [az] = nextD [bz]; nextD [bz] = tz; }
-
-
-#define MAIN_QSORT_SMALL_THRESH 20
-#define MAIN_QSORT_DEPTH_THRESH (BZ_N_RADIX + BZ_N_QSORT)
-#define MAIN_QSORT_STACK_SIZE 100
-
-static
-void mainQSort3 ( UInt32* ptr,
- UChar* block,
- UInt16* quadrant,
- Int32 nblock,
- Int32 loSt,
- Int32 hiSt,
- Int32 dSt,
- Int32* budget )
-{
- Int32 unLo, unHi, ltLo, gtHi, n, m, med;
- Int32 sp, lo, hi, d;
-
- Int32 stackLo[MAIN_QSORT_STACK_SIZE];
- Int32 stackHi[MAIN_QSORT_STACK_SIZE];
- Int32 stackD [MAIN_QSORT_STACK_SIZE];
-
- Int32 nextLo[3];
- Int32 nextHi[3];
- Int32 nextD [3];
-
- sp = 0;
- mpush ( loSt, hiSt, dSt );
-
- while (sp > 0) {
-
- AssertH ( sp < MAIN_QSORT_STACK_SIZE, 1001 );
-
- mpop ( lo, hi, d );
- if (hi - lo < MAIN_QSORT_SMALL_THRESH ||
- d > MAIN_QSORT_DEPTH_THRESH) {
- mainSimpleSort ( ptr, block, quadrant, nblock, lo, hi, d, budget );
- if (*budget < 0) return;
- continue;
- }
-
- med = (Int32)
- mmed3 ( block[ptr[ lo ]+d],
- block[ptr[ hi ]+d],
- block[ptr[ (lo+hi)>>1 ]+d] );
-
- unLo = ltLo = lo;
- unHi = gtHi = hi;
-
- while (True) {
- while (True) {
- if (unLo > unHi) break;
- n = ((Int32)block[ptr[unLo]+d]) - med;
- if (n == 0) {
- mswap(ptr[unLo], ptr[ltLo]);
- ltLo++; unLo++; continue;
- };
- if (n > 0) break;
- unLo++;
- }
- while (True) {
- if (unLo > unHi) break;
- n = ((Int32)block[ptr[unHi]+d]) - med;
- if (n == 0) {
- mswap(ptr[unHi], ptr[gtHi]);
- gtHi--; unHi--; continue;
- };
- if (n < 0) break;
- unHi--;
- }
- if (unLo > unHi) break;
- mswap(ptr[unLo], ptr[unHi]); unLo++; unHi--;
- }
-
- AssertD ( unHi == unLo-1, "mainQSort3(2)" );
-
- if (gtHi < ltLo) {
- mpush(lo, hi, d+1 );
- continue;
- }
-
- n = mmin(ltLo-lo, unLo-ltLo); mvswap(lo, unLo-n, n);
- m = mmin(hi-gtHi, gtHi-unHi); mvswap(unLo, hi-m+1, m);
-
- n = lo + unLo - ltLo - 1;
- m = hi - (gtHi - unHi) + 1;
-
- nextLo[0] = lo; nextHi[0] = n; nextD[0] = d;
- nextLo[1] = m; nextHi[1] = hi; nextD[1] = d;
- nextLo[2] = n+1; nextHi[2] = m-1; nextD[2] = d+1;
-
- if (mnextsize(0) < mnextsize(1)) mnextswap(0,1);
- if (mnextsize(1) < mnextsize(2)) mnextswap(1,2);
- if (mnextsize(0) < mnextsize(1)) mnextswap(0,1);
-
- AssertD (mnextsize(0) >= mnextsize(1), "mainQSort3(8)" );
- AssertD (mnextsize(1) >= mnextsize(2), "mainQSort3(9)" );
-
- mpush (nextLo[0], nextHi[0], nextD[0]);
- mpush (nextLo[1], nextHi[1], nextD[1]);
- mpush (nextLo[2], nextHi[2], nextD[2]);
- }
-}
-
-#undef mswap
-#undef mvswap
-#undef mpush
-#undef mpop
-#undef mmin
-#undef mnextsize
-#undef mnextswap
-#undef MAIN_QSORT_SMALL_THRESH
-#undef MAIN_QSORT_DEPTH_THRESH
-#undef MAIN_QSORT_STACK_SIZE
-
-
-/*---------------------------------------------*/
-/* Pre:
- nblock > N_OVERSHOOT
- block32 exists for [0 .. nblock-1 +N_OVERSHOOT]
- ((UChar*)block32) [0 .. nblock-1] holds block
- ptr exists for [0 .. nblock-1]
-
- Post:
- ((UChar*)block32) [0 .. nblock-1] holds block
- All other areas of block32 destroyed
- ftab [0 .. 65536 ] destroyed
- ptr [0 .. nblock-1] holds sorted order
- if (*budget < 0), sorting was abandoned
-*/
-
-#define BIGFREQ(b) (ftab[((b)+1) << 8] - ftab[(b) << 8])
-#define SETMASK (1 << 21)
-#define CLEARMASK (~(SETMASK))
-
-static
-void mainSort ( UInt32* ptr,
- UChar* block,
- UInt16* quadrant,
- UInt32* ftab,
- Int32 nblock,
- Int32 verb,
- Int32* budget )
-{
- Int32 i, j, k, ss, sb;
- Int32 runningOrder[256];
- Bool bigDone[256];
- Int32 copyStart[256];
- Int32 copyEnd [256];
- UChar c1;
- Int32 numQSorted;
- UInt16 s;
- if (verb >= 4) VPrintf0 ( " main sort initialise ...\n" );
-
- /*-- set up the 2-byte frequency table --*/
- for (i = 65536; i >= 0; i--) ftab[i] = 0;
-
- j = block[0] << 8;
- i = nblock-1;
- for (; i >= 3; i -= 4) {
- quadrant[i] = 0;
- j = (j >> 8) | ( ((UInt16)block[i]) << 8);
- ftab[j]++;
- quadrant[i-1] = 0;
- j = (j >> 8) | ( ((UInt16)block[i-1]) << 8);
- ftab[j]++;
- quadrant[i-2] = 0;
- j = (j >> 8) | ( ((UInt16)block[i-2]) << 8);
- ftab[j]++;
- quadrant[i-3] = 0;
- j = (j >> 8) | ( ((UInt16)block[i-3]) << 8);
- ftab[j]++;
- }
- for (; i >= 0; i--) {
- quadrant[i] = 0;
- j = (j >> 8) | ( ((UInt16)block[i]) << 8);
- ftab[j]++;
- }
-
- /*-- (emphasises close relationship of block & quadrant) --*/
- for (i = 0; i < BZ_N_OVERSHOOT; i++) {
- block [nblock+i] = block[i];
- quadrant[nblock+i] = 0;
- }
-
- if (verb >= 4) VPrintf0 ( " bucket sorting ...\n" );
-
- /*-- Complete the initial radix sort --*/
- for (i = 1; i <= 65536; i++) ftab[i] += ftab[i-1];
-
- s = block[0] << 8;
- i = nblock-1;
- for (; i >= 3; i -= 4) {
- s = (s >> 8) | (block[i] << 8);
- j = ftab[s] -1;
- ftab[s] = j;
- ptr[j] = i;
- s = (s >> 8) | (block[i-1] << 8);
- j = ftab[s] -1;
- ftab[s] = j;
- ptr[j] = i-1;
- s = (s >> 8) | (block[i-2] << 8);
- j = ftab[s] -1;
- ftab[s] = j;
- ptr[j] = i-2;
- s = (s >> 8) | (block[i-3] << 8);
- j = ftab[s] -1;
- ftab[s] = j;
- ptr[j] = i-3;
- }
- for (; i >= 0; i--) {
- s = (s >> 8) | (block[i] << 8);
- j = ftab[s] -1;
- ftab[s] = j;
- ptr[j] = i;
- }
-
- /*--
- Now ftab contains the first loc of every small bucket.
- Calculate the running order, from smallest to largest
- big bucket.
- --*/
- for (i = 0; i <= 255; i++) {
- bigDone [i] = False;
- runningOrder[i] = i;
- }
-
- {
- Int32 vv;
- Int32 h = 1;
- do h = 3 * h + 1; while (h <= 256);
- do {
- h = h / 3;
- for (i = h; i <= 255; i++) {
- vv = runningOrder[i];
- j = i;
- while ( BIGFREQ(runningOrder[j-h]) > BIGFREQ(vv) ) {
- runningOrder[j] = runningOrder[j-h];
- j = j - h;
- if (j <= (h - 1)) goto zero;
- }
- zero:
- runningOrder[j] = vv;
- }
- } while (h != 1);
- }
-
- /*--
- The main sorting loop.
- --*/
-
- numQSorted = 0;
-
- for (i = 0; i <= 255; i++) {
-
- /*--
- Process big buckets, starting with the least full.
- Basically this is a 3-step process in which we call
- mainQSort3 to sort the small buckets [ss, j], but
- also make a big effort to avoid the calls if we can.
- --*/
- ss = runningOrder[i];
-
- /*--
- Step 1:
- Complete the big bucket [ss] by quicksorting
- any unsorted small buckets [ss, j], for j != ss.
- Hopefully previous pointer-scanning phases have already
- completed many of the small buckets [ss, j], so
- we don't have to sort them at all.
- --*/
- for (j = 0; j <= 255; j++) {
- if (j != ss) {
- sb = (ss << 8) + j;
- if ( ! (ftab[sb] & SETMASK) ) {
- Int32 lo = ftab[sb] & CLEARMASK;
- Int32 hi = (ftab[sb+1] & CLEARMASK) - 1;
- if (hi > lo) {
- if (verb >= 4)
- VPrintf4 ( " qsort [0x%x, 0x%x] "
- "done %d this %d\n",
- ss, j, numQSorted, hi - lo + 1 );
- mainQSort3 (
- ptr, block, quadrant, nblock,
- lo, hi, BZ_N_RADIX, budget
- );
- numQSorted += (hi - lo + 1);
- if (*budget < 0) return;
- }
- }
- ftab[sb] |= SETMASK;
- }
- }
-
- AssertH ( !bigDone[ss], 1006 );
-
- /*--
- Step 2:
- Now scan this big bucket [ss] so as to synthesise the
- sorted order for small buckets [t, ss] for all t,
- including, magically, the bucket [ss,ss] too.
- This will avoid doing Real Work in subsequent Step 1's.
- --*/
- {
- for (j = 0; j <= 255; j++) {
- copyStart[j] = ftab[(j << 8) + ss] & CLEARMASK;
- copyEnd [j] = (ftab[(j << 8) + ss + 1] & CLEARMASK) - 1;
- }
- for (j = ftab[ss << 8] & CLEARMASK; j < copyStart[ss]; j++) {
- k = ptr[j]-1; if (k < 0) k += nblock;
- c1 = block[k];
- if (!bigDone[c1])
- ptr[ copyStart[c1]++ ] = k;
- }
- for (j = (ftab[(ss+1) << 8] & CLEARMASK) - 1; j > copyEnd[ss]; j--) {
- k = ptr[j]-1; if (k < 0) k += nblock;
- c1 = block[k];
- if (!bigDone[c1])
- ptr[ copyEnd[c1]-- ] = k;
- }
- }
-
- AssertH ( (copyStart[ss]-1 == copyEnd[ss])
- ||
- /* Extremely rare case missing in bzip2-1.0.0 and 1.0.1.
- Necessity for this case is demonstrated by compressing
- a sequence of approximately 48.5 million of character
- 251; 1.0.0/1.0.1 will then die here. */
- (copyStart[ss] == 0 && copyEnd[ss] == nblock-1),
- 1007 )
-
- for (j = 0; j <= 255; j++) ftab[(j << 8) + ss] |= SETMASK;
-
- /*--
- Step 3:
- The [ss] big bucket is now done. Record this fact,
- and update the quadrant descriptors. Remember to
- update quadrants in the overshoot area too, if
- necessary. The "if (i < 255)" test merely skips
- this updating for the last bucket processed, since
- updating for the last bucket is pointless.
-
- The quadrant array provides a way to incrementally
- cache sort orderings, as they appear, so as to
- make subsequent comparisons in fullGtU() complete
- faster. For repetitive blocks this makes a big
- difference (but not big enough to be able to avoid
- the fallback sorting mechanism, exponential radix sort).
-
- The precise meaning is: at all times:
-
- for 0 <= i < nblock and 0 <= j <= nblock
-
- if block[i] != block[j],
-
- then the relative values of quadrant[i] and
- quadrant[j] are meaningless.
-
- else {
- if quadrant[i] < quadrant[j]
- then the string starting at i lexicographically
- precedes the string starting at j
-
- else if quadrant[i] > quadrant[j]
- then the string starting at j lexicographically
- precedes the string starting at i
-
- else
- the relative ordering of the strings starting
- at i and j has not yet been determined.
- }
- --*/
- bigDone[ss] = True;
-
- if (i < 255) {
- Int32 bbStart = ftab[ss << 8] & CLEARMASK;
- Int32 bbSize = (ftab[(ss+1) << 8] & CLEARMASK) - bbStart;
- Int32 shifts = 0;
-
- while ((bbSize >> shifts) > 65534) shifts++;
-
- for (j = bbSize-1; j >= 0; j--) {
- Int32 a2update = ptr[bbStart + j];
- UInt16 qVal = (UInt16)(j >> shifts);
- quadrant[a2update] = qVal;
- if (a2update < BZ_N_OVERSHOOT)
- quadrant[a2update + nblock] = qVal;
- }
- AssertH ( ((bbSize-1) >> shifts) <= 65535, 1002 );
- }
-
- }
-
- if (verb >= 4)
- VPrintf3 ( " %d pointers, %d sorted, %d scanned\n",
- nblock, numQSorted, nblock - numQSorted );
-}
-
-#undef BIGFREQ
-#undef SETMASK
-#undef CLEARMASK
-
-
-/*---------------------------------------------*/
-/* Pre:
- nblock > 0
- arr2 exists for [0 .. nblock-1 +N_OVERSHOOT]
- ((UChar*)arr2) [0 .. nblock-1] holds block
- arr1 exists for [0 .. nblock-1]
-
- Post:
- ((UChar*)arr2) [0 .. nblock-1] holds block
- All other areas of block destroyed
- ftab [ 0 .. 65536 ] destroyed
- arr1 [0 .. nblock-1] holds sorted order
-*/
-void BZ2_blockSort ( EState* s )
-{
- UInt32* ptr = s->ptr;
- UChar* block = s->block;
- UInt32* ftab = s->ftab;
- Int32 nblock = s->nblock;
- Int32 verb = s->verbosity;
- Int32 wfact = s->workFactor;
- UInt16* quadrant;
- Int32 budget;
- Int32 budgetInit;
- Int32 i;
-
- if (nblock < 10000) {
- fallbackSort ( s->arr1, s->arr2, ftab, nblock, verb );
- } else {
- /* Calculate the location for quadrant, remembering to get
- the alignment right. Assumes that &(block[0]) is at least
- 2-byte aligned -- this should be ok since block is really
- the first section of arr2.
- */
- i = nblock+BZ_N_OVERSHOOT;
- if (i & 1) i++;
- quadrant = (UInt16*)(&(block[i]));
-
- /* (wfact-1) / 3 puts the default-factor-30
- transition point at very roughly the same place as
- with v0.1 and v0.9.0.
- Not that it particularly matters any more, since the
- resulting compressed stream is now the same regardless
- of whether or not we use the main sort or fallback sort.
- */
- if (wfact < 1 ) wfact = 1;
- if (wfact > 100) wfact = 100;
- budgetInit = nblock * ((wfact-1) / 3);
- budget = budgetInit;
-
- mainSort ( ptr, block, quadrant, ftab, nblock, verb, &budget );
- if (verb >= 3)
- VPrintf3 ( " %d work, %d block, ratio %5.2f\n",
- budgetInit - budget,
- nblock,
- (float)(budgetInit - budget) /
- (float)(nblock==0 ? 1 : nblock) );
- if (budget < 0) {
- if (verb >= 2)
- VPrintf0 ( " too repetitive; using fallback"
- " sorting algorithm\n" );
- fallbackSort ( s->arr1, s->arr2, ftab, nblock, verb );
- }
- }
-
- s->origPtr = -1;
- for (i = 0; i < s->nblock; i++)
- if (ptr[i] == 0)
- { s->origPtr = i; break; };
-
- AssertH( s->origPtr != -1, 1003 );
-}
-
-
-/*-------------------------------------------------------------*/
-/*--- end blocksort.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-------------------------------------------------------------*/
-/*--- Huffman coding low-level stuff ---*/
-/*--- huffman.c ---*/
-/*-------------------------------------------------------------*/
-
-
-/*---------------------------------------------------*/
-#define WEIGHTOF(zz0) ((zz0) & 0xffffff00)
-#define DEPTHOF(zz1) ((zz1) & 0x000000ff)
-#define MYMAX(zz2,zz3) ((zz2) > (zz3) ? (zz2) : (zz3))
-
-#define ADDWEIGHTS(zw1,zw2) \
- (WEIGHTOF(zw1)+WEIGHTOF(zw2)) | \
- (1 + MYMAX(DEPTHOF(zw1),DEPTHOF(zw2)))
-
-#define UPHEAP(z) \
-{ \
- Int32 zz, tmp; \
- zz = z; tmp = heap[zz]; \
- while (weight[tmp] < weight[heap[zz >> 1]]) { \
- heap[zz] = heap[zz >> 1]; \
- zz >>= 1; \
- } \
- heap[zz] = tmp; \
-}
-
-#define DOWNHEAP(z) \
-{ \
- Int32 zz, yy, tmp; \
- zz = z; tmp = heap[zz]; \
- while (True) { \
- yy = zz << 1; \
- if (yy > nHeap) break; \
- if (yy < nHeap && \
- weight[heap[yy+1]] < weight[heap[yy]]) \
- yy++; \
- if (weight[tmp] < weight[heap[yy]]) break; \
- heap[zz] = heap[yy]; \
- zz = yy; \
- } \
- heap[zz] = tmp; \
-}
-
-
-/*---------------------------------------------------*/
-void BZ2_hbMakeCodeLengths ( UChar *len,
- Int32 *freq,
- Int32 alphaSize,
- Int32 maxLen )
-{
- /*--
- Nodes and heap entries run from 1. Entry 0
- for both the heap and nodes is a sentinel.
- --*/
- Int32 nNodes, nHeap, n1, n2, i, j, k;
- Bool tooLong;
-
- Int32 heap [ BZ_MAX_ALPHA_SIZE + 2 ];
- Int32 weight [ BZ_MAX_ALPHA_SIZE * 2 ];
- Int32 parent [ BZ_MAX_ALPHA_SIZE * 2 ];
-
- for (i = 0; i < alphaSize; i++)
- weight[i+1] = (freq[i] == 0 ? 1 : freq[i]) << 8;
-
- while (True) {
-
- nNodes = alphaSize;
- nHeap = 0;
-
- heap[0] = 0;
- weight[0] = 0;
- parent[0] = -2;
-
- for (i = 1; i <= alphaSize; i++) {
- parent[i] = -1;
- nHeap++;
- heap[nHeap] = i;
- UPHEAP(nHeap);
- }
-
- AssertH( nHeap < (BZ_MAX_ALPHA_SIZE+2), 2001 );
-
- while (nHeap > 1) {
- n1 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1);
- n2 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1);
- nNodes++;
- parent[n1] = parent[n2] = nNodes;
- weight[nNodes] = ADDWEIGHTS(weight[n1], weight[n2]);
- parent[nNodes] = -1;
- nHeap++;
- heap[nHeap] = nNodes;
- UPHEAP(nHeap);
- }
-
- AssertH( nNodes < (BZ_MAX_ALPHA_SIZE * 2), 2002 );
-
- tooLong = False;
- for (i = 1; i <= alphaSize; i++) {
- j = 0;
- k = i;
- while (parent[k] >= 0) { k = parent[k]; j++; }
- len[i-1] = j;
- if (j > maxLen) tooLong = True;
- }
-
- if (! tooLong) break;
-
- for (i = 1; i < alphaSize; i++) {
- j = weight[i] >> 8;
- j = 1 + (j / 2);
- weight[i] = j << 8;
- }
- }
-}
-
-
-/*---------------------------------------------------*/
-void BZ2_hbAssignCodes ( Int32 *code,
- UChar *length,
- Int32 minLen,
- Int32 maxLen,
- Int32 alphaSize )
-{
- Int32 n, vec, i;
-
- vec = 0;
- for (n = minLen; n <= maxLen; n++) {
- for (i = 0; i < alphaSize; i++)
- if (length[i] == n) { code[i] = vec; vec++; };
- vec <<= 1;
- }
-}
-
-
-/*---------------------------------------------------*/
-void BZ2_hbCreateDecodeTables ( Int32 *limit,
- Int32 *base,
- Int32 *perm,
- UChar *length,
- Int32 minLen,
- Int32 maxLen,
- Int32 alphaSize )
-{
- Int32 pp, i, j, vec;
-
- pp = 0;
- for (i = minLen; i <= maxLen; i++)
- for (j = 0; j < alphaSize; j++)
- if (length[j] == i) { perm[pp] = j; pp++; };
-
- for (i = 0; i < BZ_MAX_CODE_LEN; i++) base[i] = 0;
- for (i = 0; i < alphaSize; i++) base[length[i]+1]++;
-
- for (i = 1; i < BZ_MAX_CODE_LEN; i++) base[i] += base[i-1];
-
- for (i = 0; i < BZ_MAX_CODE_LEN; i++) limit[i] = 0;
- vec = 0;
-
- for (i = minLen; i <= maxLen; i++) {
- vec += (base[i+1] - base[i]);
- limit[i] = vec-1;
- vec <<= 1;
- }
- for (i = minLen + 1; i <= maxLen; i++)
- base[i] = ((limit[i-1] + 1) << 1) - base[i];
-}
-
-
-/*-------------------------------------------------------------*/
-/*--- end huffman.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-------------------------------------------------------------*/
-/*--- Table for doing CRCs ---*/
-/*--- crctable.c ---*/
-/*-------------------------------------------------------------*/
-
-
-/*--
- I think this is an implementation of the AUTODIN-II,
- Ethernet & FDDI 32-bit CRC standard. Vaguely derived
- from code by Rob Warnock, in Section 51 of the
- comp.compression FAQ.
---*/
-
-UInt32 BZ2_crc32Table[256] = {
-
- /*-- Ugly, innit? --*/
-
- 0x00000000L, 0x04c11db7L, 0x09823b6eL, 0x0d4326d9L,
- 0x130476dcL, 0x17c56b6bL, 0x1a864db2L, 0x1e475005L,
- 0x2608edb8L, 0x22c9f00fL, 0x2f8ad6d6L, 0x2b4bcb61L,
- 0x350c9b64L, 0x31cd86d3L, 0x3c8ea00aL, 0x384fbdbdL,
- 0x4c11db70L, 0x48d0c6c7L, 0x4593e01eL, 0x4152fda9L,
- 0x5f15adacL, 0x5bd4b01bL, 0x569796c2L, 0x52568b75L,
- 0x6a1936c8L, 0x6ed82b7fL, 0x639b0da6L, 0x675a1011L,
- 0x791d4014L, 0x7ddc5da3L, 0x709f7b7aL, 0x745e66cdL,
- 0x9823b6e0L, 0x9ce2ab57L, 0x91a18d8eL, 0x95609039L,
- 0x8b27c03cL, 0x8fe6dd8bL, 0x82a5fb52L, 0x8664e6e5L,
- 0xbe2b5b58L, 0xbaea46efL, 0xb7a96036L, 0xb3687d81L,
- 0xad2f2d84L, 0xa9ee3033L, 0xa4ad16eaL, 0xa06c0b5dL,
- 0xd4326d90L, 0xd0f37027L, 0xddb056feL, 0xd9714b49L,
- 0xc7361b4cL, 0xc3f706fbL, 0xceb42022L, 0xca753d95L,
- 0xf23a8028L, 0xf6fb9d9fL, 0xfbb8bb46L, 0xff79a6f1L,
- 0xe13ef6f4L, 0xe5ffeb43L, 0xe8bccd9aL, 0xec7dd02dL,
- 0x34867077L, 0x30476dc0L, 0x3d044b19L, 0x39c556aeL,
- 0x278206abL, 0x23431b1cL, 0x2e003dc5L, 0x2ac12072L,
- 0x128e9dcfL, 0x164f8078L, 0x1b0ca6a1L, 0x1fcdbb16L,
- 0x018aeb13L, 0x054bf6a4L, 0x0808d07dL, 0x0cc9cdcaL,
- 0x7897ab07L, 0x7c56b6b0L, 0x71159069L, 0x75d48ddeL,
- 0x6b93dddbL, 0x6f52c06cL, 0x6211e6b5L, 0x66d0fb02L,
- 0x5e9f46bfL, 0x5a5e5b08L, 0x571d7dd1L, 0x53dc6066L,
- 0x4d9b3063L, 0x495a2dd4L, 0x44190b0dL, 0x40d816baL,
- 0xaca5c697L, 0xa864db20L, 0xa527fdf9L, 0xa1e6e04eL,
- 0xbfa1b04bL, 0xbb60adfcL, 0xb6238b25L, 0xb2e29692L,
- 0x8aad2b2fL, 0x8e6c3698L, 0x832f1041L, 0x87ee0df6L,
- 0x99a95df3L, 0x9d684044L, 0x902b669dL, 0x94ea7b2aL,
- 0xe0b41de7L, 0xe4750050L, 0xe9362689L, 0xedf73b3eL,
- 0xf3b06b3bL, 0xf771768cL, 0xfa325055L, 0xfef34de2L,
- 0xc6bcf05fL, 0xc27dede8L, 0xcf3ecb31L, 0xcbffd686L,
- 0xd5b88683L, 0xd1799b34L, 0xdc3abdedL, 0xd8fba05aL,
- 0x690ce0eeL, 0x6dcdfd59L, 0x608edb80L, 0x644fc637L,
- 0x7a089632L, 0x7ec98b85L, 0x738aad5cL, 0x774bb0ebL,
- 0x4f040d56L, 0x4bc510e1L, 0x46863638L, 0x42472b8fL,
- 0x5c007b8aL, 0x58c1663dL, 0x558240e4L, 0x51435d53L,
- 0x251d3b9eL, 0x21dc2629L, 0x2c9f00f0L, 0x285e1d47L,
- 0x36194d42L, 0x32d850f5L, 0x3f9b762cL, 0x3b5a6b9bL,
- 0x0315d626L, 0x07d4cb91L, 0x0a97ed48L, 0x0e56f0ffL,
- 0x1011a0faL, 0x14d0bd4dL, 0x19939b94L, 0x1d528623L,
- 0xf12f560eL, 0xf5ee4bb9L, 0xf8ad6d60L, 0xfc6c70d7L,
- 0xe22b20d2L, 0xe6ea3d65L, 0xeba91bbcL, 0xef68060bL,
- 0xd727bbb6L, 0xd3e6a601L, 0xdea580d8L, 0xda649d6fL,
- 0xc423cd6aL, 0xc0e2d0ddL, 0xcda1f604L, 0xc960ebb3L,
- 0xbd3e8d7eL, 0xb9ff90c9L, 0xb4bcb610L, 0xb07daba7L,
- 0xae3afba2L, 0xaafbe615L, 0xa7b8c0ccL, 0xa379dd7bL,
- 0x9b3660c6L, 0x9ff77d71L, 0x92b45ba8L, 0x9675461fL,
- 0x8832161aL, 0x8cf30badL, 0x81b02d74L, 0x857130c3L,
- 0x5d8a9099L, 0x594b8d2eL, 0x5408abf7L, 0x50c9b640L,
- 0x4e8ee645L, 0x4a4ffbf2L, 0x470cdd2bL, 0x43cdc09cL,
- 0x7b827d21L, 0x7f436096L, 0x7200464fL, 0x76c15bf8L,
- 0x68860bfdL, 0x6c47164aL, 0x61043093L, 0x65c52d24L,
- 0x119b4be9L, 0x155a565eL, 0x18197087L, 0x1cd86d30L,
- 0x029f3d35L, 0x065e2082L, 0x0b1d065bL, 0x0fdc1becL,
- 0x3793a651L, 0x3352bbe6L, 0x3e119d3fL, 0x3ad08088L,
- 0x2497d08dL, 0x2056cd3aL, 0x2d15ebe3L, 0x29d4f654L,
- 0xc5a92679L, 0xc1683bceL, 0xcc2b1d17L, 0xc8ea00a0L,
- 0xd6ad50a5L, 0xd26c4d12L, 0xdf2f6bcbL, 0xdbee767cL,
- 0xe3a1cbc1L, 0xe760d676L, 0xea23f0afL, 0xeee2ed18L,
- 0xf0a5bd1dL, 0xf464a0aaL, 0xf9278673L, 0xfde69bc4L,
- 0x89b8fd09L, 0x8d79e0beL, 0x803ac667L, 0x84fbdbd0L,
- 0x9abc8bd5L, 0x9e7d9662L, 0x933eb0bbL, 0x97ffad0cL,
- 0xafb010b1L, 0xab710d06L, 0xa6322bdfL, 0xa2f33668L,
- 0xbcb4666dL, 0xb8757bdaL, 0xb5365d03L, 0xb1f740b4L
-};
-
-
-/*-------------------------------------------------------------*/
-/*--- end crctable.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-------------------------------------------------------------*/
-/*--- Table for randomising repetitive blocks ---*/
-/*--- randtable.c ---*/
-/*-------------------------------------------------------------*/
-
-
-/*---------------------------------------------*/
-Int32 BZ2_rNums[512] = {
- 619, 720, 127, 481, 931, 816, 813, 233, 566, 247,
- 985, 724, 205, 454, 863, 491, 741, 242, 949, 214,
- 733, 859, 335, 708, 621, 574, 73, 654, 730, 472,
- 419, 436, 278, 496, 867, 210, 399, 680, 480, 51,
- 878, 465, 811, 169, 869, 675, 611, 697, 867, 561,
- 862, 687, 507, 283, 482, 129, 807, 591, 733, 623,
- 150, 238, 59, 379, 684, 877, 625, 169, 643, 105,
- 170, 607, 520, 932, 727, 476, 693, 425, 174, 647,
- 73, 122, 335, 530, 442, 853, 695, 249, 445, 515,
- 909, 545, 703, 919, 874, 474, 882, 500, 594, 612,
- 641, 801, 220, 162, 819, 984, 589, 513, 495, 799,
- 161, 604, 958, 533, 221, 400, 386, 867, 600, 782,
- 382, 596, 414, 171, 516, 375, 682, 485, 911, 276,
- 98, 553, 163, 354, 666, 933, 424, 341, 533, 870,
- 227, 730, 475, 186, 263, 647, 537, 686, 600, 224,
- 469, 68, 770, 919, 190, 373, 294, 822, 808, 206,
- 184, 943, 795, 384, 383, 461, 404, 758, 839, 887,
- 715, 67, 618, 276, 204, 918, 873, 777, 604, 560,
- 951, 160, 578, 722, 79, 804, 96, 409, 713, 940,
- 652, 934, 970, 447, 318, 353, 859, 672, 112, 785,
- 645, 863, 803, 350, 139, 93, 354, 99, 820, 908,
- 609, 772, 154, 274, 580, 184, 79, 626, 630, 742,
- 653, 282, 762, 623, 680, 81, 927, 626, 789, 125,
- 411, 521, 938, 300, 821, 78, 343, 175, 128, 250,
- 170, 774, 972, 275, 999, 639, 495, 78, 352, 126,
- 857, 956, 358, 619, 580, 124, 737, 594, 701, 612,
- 669, 112, 134, 694, 363, 992, 809, 743, 168, 974,
- 944, 375, 748, 52, 600, 747, 642, 182, 862, 81,
- 344, 805, 988, 739, 511, 655, 814, 334, 249, 515,
- 897, 955, 664, 981, 649, 113, 974, 459, 893, 228,
- 433, 837, 553, 268, 926, 240, 102, 654, 459, 51,
- 686, 754, 806, 760, 493, 403, 415, 394, 687, 700,
- 946, 670, 656, 610, 738, 392, 760, 799, 887, 653,
- 978, 321, 576, 617, 626, 502, 894, 679, 243, 440,
- 680, 879, 194, 572, 640, 724, 926, 56, 204, 700,
- 707, 151, 457, 449, 797, 195, 791, 558, 945, 679,
- 297, 59, 87, 824, 713, 663, 412, 693, 342, 606,
- 134, 108, 571, 364, 631, 212, 174, 643, 304, 329,
- 343, 97, 430, 751, 497, 314, 983, 374, 822, 928,
- 140, 206, 73, 263, 980, 736, 876, 478, 430, 305,
- 170, 514, 364, 692, 829, 82, 855, 953, 676, 246,
- 369, 970, 294, 750, 807, 827, 150, 790, 288, 923,
- 804, 378, 215, 828, 592, 281, 565, 555, 710, 82,
- 896, 831, 547, 261, 524, 462, 293, 465, 502, 56,
- 661, 821, 976, 991, 658, 869, 905, 758, 745, 193,
- 768, 550, 608, 933, 378, 286, 215, 979, 792, 961,
- 61, 688, 793, 644, 986, 403, 106, 366, 905, 644,
- 372, 567, 466, 434, 645, 210, 389, 550, 919, 135,
- 780, 773, 635, 389, 707, 100, 626, 958, 165, 504,
- 920, 176, 193, 713, 857, 265, 203, 50, 668, 108,
- 645, 990, 626, 197, 510, 357, 358, 850, 858, 364,
- 936, 638
-};
-
-
-/*-------------------------------------------------------------*/
-/*--- end randtable.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-------------------------------------------------------------*/
-/*--- Compression machinery (not incl block sorting) ---*/
-/*--- compress.c ---*/
-/*-------------------------------------------------------------*/
-
-
-/*---------------------------------------------------*/
-/*--- Bit stream I/O ---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------------*/
-void BZ2_bsInitWrite ( EState* s )
-{
- s->bsLive = 0;
- s->bsBuff = 0;
-}
-
-
-/*---------------------------------------------------*/
-static
-void bsFinishWrite ( EState* s )
-{
- while (s->bsLive > 0) {
- s->zbits[s->numZ] = (UChar)(s->bsBuff >> 24);
- s->numZ++;
- s->bsBuff <<= 8;
- s->bsLive -= 8;
- }
-}
-
-
-/*---------------------------------------------------*/
-#define bsNEEDW(nz) \
-{ \
- while (s->bsLive >= 8) { \
- s->zbits[s->numZ] \
- = (UChar)(s->bsBuff >> 24); \
- s->numZ++; \
- s->bsBuff <<= 8; \
- s->bsLive -= 8; \
- } \
-}
-
-
-/*---------------------------------------------------*/
-static
-__inline__
-void bsW ( EState* s, Int32 n, UInt32 v )
-{
- bsNEEDW ( n );
- s->bsBuff |= (v << (32 - s->bsLive - n));
- s->bsLive += n;
-}
-
-
-/*---------------------------------------------------*/
-static
-void bsPutUInt32 ( EState* s, UInt32 u )
-{
- bsW ( s, 8, (u >> 24) & 0xffL );
- bsW ( s, 8, (u >> 16) & 0xffL );
- bsW ( s, 8, (u >> 8) & 0xffL );
- bsW ( s, 8, u & 0xffL );
-}
-
-
-/*---------------------------------------------------*/
-static
-void bsPutUChar ( EState* s, UChar c )
-{
- bsW( s, 8, (UInt32)c );
-}
-
-
-/*---------------------------------------------------*/
-/*--- The back end proper ---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------------*/
-static
-void makeMaps_e ( EState* s )
-{
- Int32 i;
- s->nInUse = 0;
- for (i = 0; i < 256; i++)
- if (s->inUse[i]) {
- s->unseqToSeq[i] = s->nInUse;
- s->nInUse++;
- }
-}
-
-
-/*---------------------------------------------------*/
-static
-void generateMTFValues ( EState* s )
-{
- UChar yy[256];
- Int32 i, j;
- Int32 zPend;
- Int32 wr;
- Int32 EOB;
-
- /*
- After sorting (eg, here),
- s->arr1 [ 0 .. s->nblock-1 ] holds sorted order,
- and
- ((UChar*)s->arr2) [ 0 .. s->nblock-1 ]
- holds the original block data.
-
- The first thing to do is generate the MTF values,
- and put them in
- ((UInt16*)s->arr1) [ 0 .. s->nblock-1 ].
- Because there are strictly fewer or equal MTF values
- than block values, ptr values in this area are overwritten
- with MTF values only when they are no longer needed.
-
- The final compressed bitstream is generated into the
- area starting at
- (UChar*) (&((UChar*)s->arr2)[s->nblock])
-
- These storage aliases are set up in bzCompressInit(),
- except for the last one, which is arranged in
- compressBlock().
- */
- UInt32* ptr = s->ptr;
- UChar* block = s->block;
- UInt16* mtfv = s->mtfv;
-
- makeMaps_e ( s );
- EOB = s->nInUse+1;
-
- for (i = 0; i <= EOB; i++) s->mtfFreq[i] = 0;
-
- wr = 0;
- zPend = 0;
- for (i = 0; i < s->nInUse; i++) yy[i] = (UChar) i;
-
- for (i = 0; i < s->nblock; i++) {
- UChar ll_i;
- AssertD ( wr <= i, "generateMTFValues(1)" );
- j = ptr[i]-1; if (j < 0) j += s->nblock;
- ll_i = s->unseqToSeq[block[j]];
- AssertD ( ll_i < s->nInUse, "generateMTFValues(2a)" );
-
- if (yy[0] == ll_i) {
- zPend++;
- } else {
-
- if (zPend > 0) {
- zPend--;
- while (True) {
- if (zPend & 1) {
- mtfv[wr] = BZ_RUNB; wr++;
- s->mtfFreq[BZ_RUNB]++;
- } else {
- mtfv[wr] = BZ_RUNA; wr++;
- s->mtfFreq[BZ_RUNA]++;
- }
- if (zPend < 2) break;
- zPend = (zPend - 2) / 2;
- };
- zPend = 0;
- }
- {
- register UChar rtmp;
- register UChar* ryy_j;
- register UChar rll_i;
- rtmp = yy[1];
- yy[1] = yy[0];
- ryy_j = &(yy[1]);
- rll_i = ll_i;
- while ( rll_i != rtmp ) {
- register UChar rtmp2;
- ryy_j++;
- rtmp2 = rtmp;
- rtmp = *ryy_j;
- *ryy_j = rtmp2;
- };
- yy[0] = rtmp;
- j = ryy_j - &(yy[0]);
- mtfv[wr] = j+1; wr++; s->mtfFreq[j+1]++;
- }
-
- }
- }
-
- if (zPend > 0) {
- zPend--;
- while (True) {
- if (zPend & 1) {
- mtfv[wr] = BZ_RUNB; wr++;
- s->mtfFreq[BZ_RUNB]++;
- } else {
- mtfv[wr] = BZ_RUNA; wr++;
- s->mtfFreq[BZ_RUNA]++;
- }
- if (zPend < 2) break;
- zPend = (zPend - 2) / 2;
- };
- zPend = 0;
- }
-
- mtfv[wr] = EOB; wr++; s->mtfFreq[EOB]++;
-
- s->nMTF = wr;
-}
-
-
-/*---------------------------------------------------*/
-#define BZ_LESSER_ICOST 0
-#define BZ_GREATER_ICOST 15
-
-static
-void sendMTFValues ( EState* s )
-{
- Int32 v, t, i, j, gs, ge, totc, bt, bc, iter;
- Int32 nSelectors, alphaSize, minLen, maxLen, selCtr;
- Int32 nGroups, nBytes;
-
- /*--
- UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- is a global since the decoder also needs it.
-
- Int32 code[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- Int32 rfreq[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
- are also globals only used in this proc.
- Made global to keep stack frame size small.
- --*/
-
-
- UInt16 cost[BZ_N_GROUPS];
- Int32 fave[BZ_N_GROUPS];
-
- UInt16* mtfv = s->mtfv;
-
- if (s->verbosity >= 3)
- VPrintf3( " %d in block, %d after MTF & 1-2 coding, "
- "%d+2 syms in use\n",
- s->nblock, s->nMTF, s->nInUse );
-
- alphaSize = s->nInUse+2;
- for (t = 0; t < BZ_N_GROUPS; t++)
- for (v = 0; v < alphaSize; v++)
- s->len[t][v] = BZ_GREATER_ICOST;
-
- /*--- Decide how many coding tables to use ---*/
- AssertH ( s->nMTF > 0, 3001 );
- if (s->nMTF < 200) nGroups = 2; else
- if (s->nMTF < 600) nGroups = 3; else
- if (s->nMTF < 1200) nGroups = 4; else
- if (s->nMTF < 2400) nGroups = 5; else
- nGroups = 6;
-
- /*--- Generate an initial set of coding tables ---*/
- {
- Int32 nPart, remF, tFreq, aFreq;
-
- nPart = nGroups;
- remF = s->nMTF;
- gs = 0;
- while (nPart > 0) {
- tFreq = remF / nPart;
- ge = gs-1;
- aFreq = 0;
- while (aFreq < tFreq && ge < alphaSize-1) {
- ge++;
- aFreq += s->mtfFreq[ge];
- }
-
- if (ge > gs
- && nPart != nGroups && nPart != 1
- && ((nGroups-nPart) % 2 == 1)) {
- aFreq -= s->mtfFreq[ge];
- ge--;
- }
-
- if (s->verbosity >= 3)
- VPrintf5( " initial group %d, [%d .. %d], "
- "has %d syms (%4.1f%%)\n",
- nPart, gs, ge, aFreq,
- (100.0 * (float)aFreq) / (float)(s->nMTF) );
-
- for (v = 0; v < alphaSize; v++)
- if (v >= gs && v <= ge)
- s->len[nPart-1][v] = BZ_LESSER_ICOST; else
- s->len[nPart-1][v] = BZ_GREATER_ICOST;
-
- nPart--;
- gs = ge+1;
- remF -= aFreq;
- }
- }
-
- /*---
- Iterate up to BZ_N_ITERS times to improve the tables.
- ---*/
- for (iter = 0; iter < BZ_N_ITERS; iter++) {
-
- for (t = 0; t < nGroups; t++) fave[t] = 0;
-
- for (t = 0; t < nGroups; t++)
- for (v = 0; v < alphaSize; v++)
- s->rfreq[t][v] = 0;
-
- /*---
- Set up an auxiliary length table which is used to fast-track
- the common case (nGroups == 6).
- ---*/
- if (nGroups == 6) {
- for (v = 0; v < alphaSize; v++) {
- s->len_pack[v][0] = (s->len[1][v] << 16) | s->len[0][v];
- s->len_pack[v][1] = (s->len[3][v] << 16) | s->len[2][v];
- s->len_pack[v][2] = (s->len[5][v] << 16) | s->len[4][v];
- }
- }
-
- nSelectors = 0;
- totc = 0;
- gs = 0;
- while (True) {
-
- /*--- Set group start & end marks. --*/
- if (gs >= s->nMTF) break;
- ge = gs + BZ_G_SIZE - 1;
- if (ge >= s->nMTF) ge = s->nMTF-1;
-
- /*--
- Calculate the cost of this group as coded
- by each of the coding tables.
- --*/
- for (t = 0; t < nGroups; t++) cost[t] = 0;
-
- if (nGroups == 6 && 50 == ge-gs+1) {
- /*--- fast track the common case ---*/
- register UInt32 cost01, cost23, cost45;
- register UInt16 icv;
- cost01 = cost23 = cost45 = 0;
-
-# define BZ_ITER(nn) \
- icv = mtfv[gs+(nn)]; \
- cost01 += s->len_pack[icv][0]; \
- cost23 += s->len_pack[icv][1]; \
- cost45 += s->len_pack[icv][2]; \
-
- BZ_ITER(0); BZ_ITER(1); BZ_ITER(2); BZ_ITER(3); BZ_ITER(4);
- BZ_ITER(5); BZ_ITER(6); BZ_ITER(7); BZ_ITER(8); BZ_ITER(9);
- BZ_ITER(10); BZ_ITER(11); BZ_ITER(12); BZ_ITER(13); BZ_ITER(14);
- BZ_ITER(15); BZ_ITER(16); BZ_ITER(17); BZ_ITER(18); BZ_ITER(19);
- BZ_ITER(20); BZ_ITER(21); BZ_ITER(22); BZ_ITER(23); BZ_ITER(24);
- BZ_ITER(25); BZ_ITER(26); BZ_ITER(27); BZ_ITER(28); BZ_ITER(29);
- BZ_ITER(30); BZ_ITER(31); BZ_ITER(32); BZ_ITER(33); BZ_ITER(34);
- BZ_ITER(35); BZ_ITER(36); BZ_ITER(37); BZ_ITER(38); BZ_ITER(39);
- BZ_ITER(40); BZ_ITER(41); BZ_ITER(42); BZ_ITER(43); BZ_ITER(44);
- BZ_ITER(45); BZ_ITER(46); BZ_ITER(47); BZ_ITER(48); BZ_ITER(49);
-
-# undef BZ_ITER
-
- cost[0] = cost01 & 0xffff; cost[1] = cost01 >> 16;
- cost[2] = cost23 & 0xffff; cost[3] = cost23 >> 16;
- cost[4] = cost45 & 0xffff; cost[5] = cost45 >> 16;
-
- } else {
- /*--- slow version which correctly handles all situations ---*/
- for (i = gs; i <= ge; i++) {
- UInt16 icv = mtfv[i];
- for (t = 0; t < nGroups; t++) cost[t] += s->len[t][icv];
- }
- }
-
- /*--
- Find the coding table which is best for this group,
- and record its identity in the selector table.
- --*/
- bc = 999999999; bt = -1;
- for (t = 0; t < nGroups; t++)
- if (cost[t] < bc) { bc = cost[t]; bt = t; };
- totc += bc;
- fave[bt]++;
- s->selector[nSelectors] = bt;
- nSelectors++;
-
- /*--
- Increment the symbol frequencies for the selected table.
- --*/
- if (nGroups == 6 && 50 == ge-gs+1) {
- /*--- fast track the common case ---*/
-
-# define BZ_ITUR(nn) s->rfreq[bt][ mtfv[gs+(nn)] ]++
-
- BZ_ITUR(0); BZ_ITUR(1); BZ_ITUR(2); BZ_ITUR(3); BZ_ITUR(4);
- BZ_ITUR(5); BZ_ITUR(6); BZ_ITUR(7); BZ_ITUR(8); BZ_ITUR(9);
- BZ_ITUR(10); BZ_ITUR(11); BZ_ITUR(12); BZ_ITUR(13); BZ_ITUR(14);
- BZ_ITUR(15); BZ_ITUR(16); BZ_ITUR(17); BZ_ITUR(18); BZ_ITUR(19);
- BZ_ITUR(20); BZ_ITUR(21); BZ_ITUR(22); BZ_ITUR(23); BZ_ITUR(24);
- BZ_ITUR(25); BZ_ITUR(26); BZ_ITUR(27); BZ_ITUR(28); BZ_ITUR(29);
- BZ_ITUR(30); BZ_ITUR(31); BZ_ITUR(32); BZ_ITUR(33); BZ_ITUR(34);
- BZ_ITUR(35); BZ_ITUR(36); BZ_ITUR(37); BZ_ITUR(38); BZ_ITUR(39);
- BZ_ITUR(40); BZ_ITUR(41); BZ_ITUR(42); BZ_ITUR(43); BZ_ITUR(44);
- BZ_ITUR(45); BZ_ITUR(46); BZ_ITUR(47); BZ_ITUR(48); BZ_ITUR(49);
-
-# undef BZ_ITUR
-
- } else {
- /*--- slow version which correctly handles all situations ---*/
- for (i = gs; i <= ge; i++)
- s->rfreq[bt][ mtfv[i] ]++;
- }
-
- gs = ge+1;
- }
- if (s->verbosity >= 3) {
- VPrintf2 ( " pass %d: size is %d, grp uses are ",
- iter+1, totc/8 );
- for (t = 0; t < nGroups; t++)
- VPrintf1 ( "%d ", fave[t] );
- VPrintf0 ( "\n" );
- }
-
- /*--
- Recompute the tables based on the accumulated frequencies.
- --*/
- for (t = 0; t < nGroups; t++)
- BZ2_hbMakeCodeLengths ( &(s->len[t][0]), &(s->rfreq[t][0]),
- alphaSize, 20 );
- }
-
-
- AssertH( nGroups < 8, 3002 );
- AssertH( nSelectors < 32768 &&
- nSelectors <= (2 + (900000 / BZ_G_SIZE)),
- 3003 );
-
-
- /*--- Compute MTF values for the selectors. ---*/
- {
- UChar pos[BZ_N_GROUPS], ll_i, tmp2, tmp;
- for (i = 0; i < nGroups; i++) pos[i] = i;
- for (i = 0; i < nSelectors; i++) {
- ll_i = s->selector[i];
- j = 0;
- tmp = pos[j];
- while ( ll_i != tmp ) {
- j++;
- tmp2 = tmp;
- tmp = pos[j];
- pos[j] = tmp2;
- };
- pos[0] = tmp;
- s->selectorMtf[i] = j;
- }
- };
-
- /*--- Assign actual codes for the tables. --*/
- for (t = 0; t < nGroups; t++) {
- minLen = 32;
- maxLen = 0;
- for (i = 0; i < alphaSize; i++) {
- if (s->len[t][i] > maxLen) maxLen = s->len[t][i];
- if (s->len[t][i] < minLen) minLen = s->len[t][i];
- }
- AssertH ( !(maxLen > 20), 3004 );
- AssertH ( !(minLen < 1), 3005 );
- BZ2_hbAssignCodes ( &(s->code[t][0]), &(s->len[t][0]),
- minLen, maxLen, alphaSize );
- }
-
- /*--- Transmit the mapping table. ---*/
- {
- Bool inUse16[16];
- for (i = 0; i < 16; i++) {
- inUse16[i] = False;
- for (j = 0; j < 16; j++)
- if (s->inUse[i * 16 + j]) inUse16[i] = True;
- }
-
- nBytes = s->numZ;
- for (i = 0; i < 16; i++)
- if (inUse16[i]) bsW(s,1,1); else bsW(s,1,0);
-
- for (i = 0; i < 16; i++)
- if (inUse16[i])
- for (j = 0; j < 16; j++) {
- if (s->inUse[i * 16 + j]) bsW(s,1,1); else bsW(s,1,0);
- }
-
- if (s->verbosity >= 3)
- VPrintf1( " bytes: mapping %d, ", s->numZ-nBytes );
- }
-
- /*--- Now the selectors. ---*/
- nBytes = s->numZ;
- bsW ( s, 3, nGroups );
- bsW ( s, 15, nSelectors );
- for (i = 0; i < nSelectors; i++) {
- for (j = 0; j < s->selectorMtf[i]; j++) bsW(s,1,1);
- bsW(s,1,0);
- }
- if (s->verbosity >= 3)
- VPrintf1( "selectors %d, ", s->numZ-nBytes );
-
- /*--- Now the coding tables. ---*/
- nBytes = s->numZ;
-
- for (t = 0; t < nGroups; t++) {
- Int32 curr = s->len[t][0];
- bsW ( s, 5, curr );
- for (i = 0; i < alphaSize; i++) {
- while (curr < s->len[t][i]) { bsW(s,2,2); curr++; /* 10 */ };
- while (curr > s->len[t][i]) { bsW(s,2,3); curr--; /* 11 */ };
- bsW ( s, 1, 0 );
- }
- }
-
- if (s->verbosity >= 3)
- VPrintf1 ( "code lengths %d, ", s->numZ-nBytes );
-
- /*--- And finally, the block data proper ---*/
- nBytes = s->numZ;
- selCtr = 0;
- gs = 0;
- while (True) {
- if (gs >= s->nMTF) break;
- ge = gs + BZ_G_SIZE - 1;
- if (ge >= s->nMTF) ge = s->nMTF-1;
- AssertH ( s->selector[selCtr] < nGroups, 3006 );
-
- if (nGroups == 6 && 50 == ge-gs+1) {
- /*--- fast track the common case ---*/
- UInt16 mtfv_i;
- UChar* s_len_sel_selCtr
- = &(s->len[s->selector[selCtr]][0]);
- Int32* s_code_sel_selCtr
- = &(s->code[s->selector[selCtr]][0]);
-
-# define BZ_ITAH(nn) \
- mtfv_i = mtfv[gs+(nn)]; \
- bsW ( s, \
- s_len_sel_selCtr[mtfv_i], \
- s_code_sel_selCtr[mtfv_i] )
-
- BZ_ITAH(0); BZ_ITAH(1); BZ_ITAH(2); BZ_ITAH(3); BZ_ITAH(4);
- BZ_ITAH(5); BZ_ITAH(6); BZ_ITAH(7); BZ_ITAH(8); BZ_ITAH(9);
- BZ_ITAH(10); BZ_ITAH(11); BZ_ITAH(12); BZ_ITAH(13); BZ_ITAH(14);
- BZ_ITAH(15); BZ_ITAH(16); BZ_ITAH(17); BZ_ITAH(18); BZ_ITAH(19);
- BZ_ITAH(20); BZ_ITAH(21); BZ_ITAH(22); BZ_ITAH(23); BZ_ITAH(24);
- BZ_ITAH(25); BZ_ITAH(26); BZ_ITAH(27); BZ_ITAH(28); BZ_ITAH(29);
- BZ_ITAH(30); BZ_ITAH(31); BZ_ITAH(32); BZ_ITAH(33); BZ_ITAH(34);
- BZ_ITAH(35); BZ_ITAH(36); BZ_ITAH(37); BZ_ITAH(38); BZ_ITAH(39);
- BZ_ITAH(40); BZ_ITAH(41); BZ_ITAH(42); BZ_ITAH(43); BZ_ITAH(44);
- BZ_ITAH(45); BZ_ITAH(46); BZ_ITAH(47); BZ_ITAH(48); BZ_ITAH(49);
-
-# undef BZ_ITAH
-
- } else {
- /*--- slow version which correctly handles all situations ---*/
- for (i = gs; i <= ge; i++) {
- bsW ( s,
- s->len [s->selector[selCtr]] [mtfv[i]],
- s->code [s->selector[selCtr]] [mtfv[i]] );
- }
- }
-
-
- gs = ge+1;
- selCtr++;
- }
- AssertH( selCtr == nSelectors, 3007 );
-
- if (s->verbosity >= 3)
- VPrintf1( "codes %d\n", s->numZ-nBytes );
-}
-
-
-/*---------------------------------------------------*/
-void BZ2_compressBlock ( EState* s, Bool is_last_block )
-{
- if (s->nblock > 0) {
-
- BZ_FINALISE_CRC ( s->blockCRC );
- s->combinedCRC = (s->combinedCRC << 1) | (s->combinedCRC >> 31);
- s->combinedCRC ^= s->blockCRC;
- if (s->blockNo > 1) s->numZ = 0;
-
- if (s->verbosity >= 2)
- VPrintf4( " block %d: crc = 0x%8x, "
- "combined CRC = 0x%8x, size = %d\n",
- s->blockNo, s->blockCRC, s->combinedCRC, s->nblock );
-
- BZ2_blockSort ( s );
- }
-
- s->zbits = (UChar*) (&((UChar*)s->arr2)[s->nblock]);
-
- /*-- If this is the first block, create the stream header. --*/
- if (s->blockNo == 1) {
- BZ2_bsInitWrite ( s );
- bsPutUChar ( s, BZ_HDR_B );
- bsPutUChar ( s, BZ_HDR_Z );
- bsPutUChar ( s, BZ_HDR_h );
- bsPutUChar ( s, (UChar)(BZ_HDR_0 + s->blockSize100k) );
- }
-
- if (s->nblock > 0) {
-
- bsPutUChar ( s, 0x31 ); bsPutUChar ( s, 0x41 );
- bsPutUChar ( s, 0x59 ); bsPutUChar ( s, 0x26 );
- bsPutUChar ( s, 0x53 ); bsPutUChar ( s, 0x59 );
-
- /*-- Now the block's CRC, so it is in a known place. --*/
- bsPutUInt32 ( s, s->blockCRC );
-
- /*--
- Now a single bit indicating (non-)randomisation.
- As of version 0.9.5, we use a better sorting algorithm
- which makes randomisation unnecessary. So always set
- the randomised bit to 'no'. Of course, the decoder
- still needs to be able to handle randomised blocks
- so as to maintain backwards compatibility with
- older versions of bzip2.
- --*/
- bsW(s,1,0);
-
- bsW ( s, 24, s->origPtr );
- generateMTFValues ( s );
- sendMTFValues ( s );
- }
-
-
- /*-- If this is the last block, add the stream trailer. --*/
- if (is_last_block) {
-
- bsPutUChar ( s, 0x17 ); bsPutUChar ( s, 0x72 );
- bsPutUChar ( s, 0x45 ); bsPutUChar ( s, 0x38 );
- bsPutUChar ( s, 0x50 ); bsPutUChar ( s, 0x90 );
- bsPutUInt32 ( s, s->combinedCRC );
- if (s->verbosity >= 2)
- VPrintf1( " final combined CRC = 0x%x\n ", s->combinedCRC );
- bsFinishWrite ( s );
- }
-}
-
-
-/*-------------------------------------------------------------*/
-/*--- end compress.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-------------------------------------------------------------*/
-/*--- Decompression machinery ---*/
-/*--- decompress.c ---*/
-/*-------------------------------------------------------------*/
-
-
-/*---------------------------------------------------*/
-static
-void makeMaps_d ( DState* s )
-{
- Int32 i;
- s->nInUse = 0;
- for (i = 0; i < 256; i++)
- if (s->inUse[i]) {
- s->seqToUnseq[s->nInUse] = i;
- s->nInUse++;
- }
-}
-
-
-/*---------------------------------------------------*/
-#define RETURN(rrr) \
- { retVal = rrr; goto save_state_and_return; };
-
-#define GET_BITS(lll,vvv,nnn) \
- case lll: s->state = lll; \
- while (True) { \
- if (s->bsLive >= nnn) { \
- UInt32 v; \
- v = (s->bsBuff >> \
- (s->bsLive-nnn)) & ((1 << nnn)-1); \
- s->bsLive -= nnn; \
- vvv = v; \
- break; \
- } \
- if (s->strm->avail_in == 0) RETURN(BZ_OK); \
- s->bsBuff \
- = (s->bsBuff << 8) | \
- ((UInt32) \
- (*((UChar*)(s->strm->next_in)))); \
- s->bsLive += 8; \
- s->strm->next_in++; \
- s->strm->avail_in--; \
- s->strm->total_in_lo32++; \
- if (s->strm->total_in_lo32 == 0) \
- s->strm->total_in_hi32++; \
- }
-
-#define GET_UCHAR(lll,uuu) \
- GET_BITS(lll,uuu,8)
-
-#define GET_BIT(lll,uuu) \
- GET_BITS(lll,uuu,1)
-
-/*---------------------------------------------------*/
-#define GET_MTF_VAL(label1,label2,lval) \
-{ \
- if (groupPos == 0) { \
- groupNo++; \
- if (groupNo >= nSelectors) \
- RETURN(BZ_DATA_ERROR); \
- groupPos = BZ_G_SIZE; \
- gSel = s->selector[groupNo]; \
- gMinlen = s->minLens[gSel]; \
- gLimit = &(s->limit[gSel][0]); \
- gPerm = &(s->perm[gSel][0]); \
- gBase = &(s->base[gSel][0]); \
- } \
- groupPos--; \
- zn = gMinlen; \
- GET_BITS(label1, zvec, zn); \
- while (1) { \
- if (zn > 20 /* the longest code */) \
- RETURN(BZ_DATA_ERROR); \
- if (zvec <= gLimit[zn]) break; \
- zn++; \
- GET_BIT(label2, zj); \
- zvec = (zvec << 1) | zj; \
- }; \
- if (zvec - gBase[zn] < 0 \
- || zvec - gBase[zn] >= BZ_MAX_ALPHA_SIZE) \
- RETURN(BZ_DATA_ERROR); \
- lval = gPerm[zvec - gBase[zn]]; \
-}
-
-
-/*---------------------------------------------------*/
-Int32 BZ2_decompress ( DState* s )
-{
- UChar uc;
- Int32 retVal;
- Int32 minLen, maxLen;
- bz_stream* strm = s->strm;
-
- /* stuff that needs to be saved/restored */
- Int32 i;
- Int32 j;
- Int32 t;
- Int32 alphaSize;
- Int32 nGroups;
- Int32 nSelectors;
- Int32 EOB;
- Int32 groupNo;
- Int32 groupPos;
- Int32 nextSym;
- Int32 nblockMAX;
- Int32 nblock;
- Int32 es;
- Int32 N;
- Int32 curr;
- Int32 zt;
- Int32 zn;
- Int32 zvec;
- Int32 zj;
- Int32 gSel;
- Int32 gMinlen;
- Int32* gLimit;
- Int32* gBase;
- Int32* gPerm;
-
- if (s->state == BZ_X_MAGIC_1) {
- /*initialise the save area*/
- s->save_i = 0;
- s->save_j = 0;
- s->save_t = 0;
- s->save_alphaSize = 0;
- s->save_nGroups = 0;
- s->save_nSelectors = 0;
- s->save_EOB = 0;
- s->save_groupNo = 0;
- s->save_groupPos = 0;
- s->save_nextSym = 0;
- s->save_nblockMAX = 0;
- s->save_nblock = 0;
- s->save_es = 0;
- s->save_N = 0;
- s->save_curr = 0;
- s->save_zt = 0;
- s->save_zn = 0;
- s->save_zvec = 0;
- s->save_zj = 0;
- s->save_gSel = 0;
- s->save_gMinlen = 0;
- s->save_gLimit = NULL;
- s->save_gBase = NULL;
- s->save_gPerm = NULL;
- }
-
- /*restore from the save area*/
- i = s->save_i;
- j = s->save_j;
- t = s->save_t;
- alphaSize = s->save_alphaSize;
- nGroups = s->save_nGroups;
- nSelectors = s->save_nSelectors;
- EOB = s->save_EOB;
- groupNo = s->save_groupNo;
- groupPos = s->save_groupPos;
- nextSym = s->save_nextSym;
- nblockMAX = s->save_nblockMAX;
- nblock = s->save_nblock;
- es = s->save_es;
- N = s->save_N;
- curr = s->save_curr;
- zt = s->save_zt;
- zn = s->save_zn;
- zvec = s->save_zvec;
- zj = s->save_zj;
- gSel = s->save_gSel;
- gMinlen = s->save_gMinlen;
- gLimit = s->save_gLimit;
- gBase = s->save_gBase;
- gPerm = s->save_gPerm;
-
- retVal = BZ_OK;
-
- switch (s->state) {
-
- GET_UCHAR(BZ_X_MAGIC_1, uc);
- if (uc != BZ_HDR_B) RETURN(BZ_DATA_ERROR_MAGIC);
-
- GET_UCHAR(BZ_X_MAGIC_2, uc);
- if (uc != BZ_HDR_Z) RETURN(BZ_DATA_ERROR_MAGIC);
-
- GET_UCHAR(BZ_X_MAGIC_3, uc)
- if (uc != BZ_HDR_h) RETURN(BZ_DATA_ERROR_MAGIC);
-
- GET_BITS(BZ_X_MAGIC_4, s->blockSize100k, 8)
- if (s->blockSize100k < (BZ_HDR_0 + 1) ||
- s->blockSize100k > (BZ_HDR_0 + 9)) RETURN(BZ_DATA_ERROR_MAGIC);
- s->blockSize100k -= BZ_HDR_0;
-
- if (s->smallDecompress) {
- s->ll16 = BZALLOC( s->blockSize100k * 100000 * sizeof(UInt16) );
- s->ll4 = BZALLOC(
- ((1 + s->blockSize100k * 100000) >> 1) * sizeof(UChar)
- );
- if (s->ll16 == NULL || s->ll4 == NULL) RETURN(BZ_MEM_ERROR);
- } else {
- s->tt = BZALLOC( s->blockSize100k * 100000 * sizeof(Int32) );
- if (s->tt == NULL) RETURN(BZ_MEM_ERROR);
- }
-
- GET_UCHAR(BZ_X_BLKHDR_1, uc);
-
- if (uc == 0x17) goto endhdr_2;
- if (uc != 0x31) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_BLKHDR_2, uc);
- if (uc != 0x41) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_BLKHDR_3, uc);
- if (uc != 0x59) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_BLKHDR_4, uc);
- if (uc != 0x26) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_BLKHDR_5, uc);
- if (uc != 0x53) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_BLKHDR_6, uc);
- if (uc != 0x59) RETURN(BZ_DATA_ERROR);
-
- s->currBlockNo++;
- if (s->verbosity >= 2)
- VPrintf1 ( "\n [%d: huff+mtf ", s->currBlockNo );
-
- s->storedBlockCRC = 0;
- GET_UCHAR(BZ_X_BCRC_1, uc);
- s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
- GET_UCHAR(BZ_X_BCRC_2, uc);
- s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
- GET_UCHAR(BZ_X_BCRC_3, uc);
- s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
- GET_UCHAR(BZ_X_BCRC_4, uc);
- s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
-
- GET_BITS(BZ_X_RANDBIT, s->blockRandomised, 1);
-
- s->origPtr = 0;
- GET_UCHAR(BZ_X_ORIGPTR_1, uc);
- s->origPtr = (s->origPtr << 8) | ((Int32)uc);
- GET_UCHAR(BZ_X_ORIGPTR_2, uc);
- s->origPtr = (s->origPtr << 8) | ((Int32)uc);
- GET_UCHAR(BZ_X_ORIGPTR_3, uc);
- s->origPtr = (s->origPtr << 8) | ((Int32)uc);
-
- if (s->origPtr < 0)
- RETURN(BZ_DATA_ERROR);
- if (s->origPtr > 10 + 100000*s->blockSize100k)
- RETURN(BZ_DATA_ERROR);
-
- /*--- Receive the mapping table ---*/
- for (i = 0; i < 16; i++) {
- GET_BIT(BZ_X_MAPPING_1, uc);
- if (uc == 1)
- s->inUse16[i] = True; else
- s->inUse16[i] = False;
- }
-
- for (i = 0; i < 256; i++) s->inUse[i] = False;
-
- for (i = 0; i < 16; i++)
- if (s->inUse16[i])
- for (j = 0; j < 16; j++) {
- GET_BIT(BZ_X_MAPPING_2, uc);
- if (uc == 1) s->inUse[i * 16 + j] = True;
- }
- makeMaps_d ( s );
- if (s->nInUse == 0) RETURN(BZ_DATA_ERROR);
- alphaSize = s->nInUse+2;
-
- /*--- Now the selectors ---*/
- GET_BITS(BZ_X_SELECTOR_1, nGroups, 3);
- if (nGroups < 2 || nGroups > 6) RETURN(BZ_DATA_ERROR);
- GET_BITS(BZ_X_SELECTOR_2, nSelectors, 15);
- if (nSelectors < 1) RETURN(BZ_DATA_ERROR);
- for (i = 0; i < nSelectors; i++) {
- j = 0;
- while (True) {
- GET_BIT(BZ_X_SELECTOR_3, uc);
- if (uc == 0) break;
- j++;
- if (j >= nGroups) RETURN(BZ_DATA_ERROR);
- }
- s->selectorMtf[i] = j;
- }
-
- /*--- Undo the MTF values for the selectors. ---*/
- {
- UChar pos[BZ_N_GROUPS], tmp, v;
- for (v = 0; v < nGroups; v++) pos[v] = v;
-
- for (i = 0; i < nSelectors; i++) {
- v = s->selectorMtf[i];
- tmp = pos[v];
- while (v > 0) { pos[v] = pos[v-1]; v--; }
- pos[0] = tmp;
- s->selector[i] = tmp;
- }
- }
-
- /*--- Now the coding tables ---*/
- for (t = 0; t < nGroups; t++) {
- GET_BITS(BZ_X_CODING_1, curr, 5);
- for (i = 0; i < alphaSize; i++) {
- while (True) {
- if (curr < 1 || curr > 20) RETURN(BZ_DATA_ERROR);
- GET_BIT(BZ_X_CODING_2, uc);
- if (uc == 0) break;
- GET_BIT(BZ_X_CODING_3, uc);
- if (uc == 0) curr++; else curr--;
- }
- s->len[t][i] = curr;
- }
- }
-
- /*--- Create the Huffman decoding tables ---*/
- for (t = 0; t < nGroups; t++) {
- minLen = 32;
- maxLen = 0;
- for (i = 0; i < alphaSize; i++) {
- if (s->len[t][i] > maxLen) maxLen = s->len[t][i];
- if (s->len[t][i] < minLen) minLen = s->len[t][i];
- }
- BZ2_hbCreateDecodeTables (
- &(s->limit[t][0]),
- &(s->base[t][0]),
- &(s->perm[t][0]),
- &(s->len[t][0]),
- minLen, maxLen, alphaSize
- );
- s->minLens[t] = minLen;
- }
-
- /*--- Now the MTF values ---*/
-
- EOB = s->nInUse+1;
- nblockMAX = 100000 * s->blockSize100k;
- groupNo = -1;
- groupPos = 0;
-
- for (i = 0; i <= 255; i++) s->unzftab[i] = 0;
-
- /*-- MTF init --*/
- {
- Int32 ii, jj, kk;
- kk = MTFA_SIZE-1;
- for (ii = 256 / MTFL_SIZE - 1; ii >= 0; ii--) {
- for (jj = MTFL_SIZE-1; jj >= 0; jj--) {
- s->mtfa[kk] = (UChar)(ii * MTFL_SIZE + jj);
- kk--;
- }
- s->mtfbase[ii] = kk + 1;
- }
- }
- /*-- end MTF init --*/
-
- nblock = 0;
- GET_MTF_VAL(BZ_X_MTF_1, BZ_X_MTF_2, nextSym);
-
- while (True) {
-
- if (nextSym == EOB) break;
-
- if (nextSym == BZ_RUNA || nextSym == BZ_RUNB) {
-
- es = -1;
- N = 1;
- do {
- if (nextSym == BZ_RUNA) es = es + (0+1) * N; else
- if (nextSym == BZ_RUNB) es = es + (1+1) * N;
- N = N * 2;
- GET_MTF_VAL(BZ_X_MTF_3, BZ_X_MTF_4, nextSym);
- }
- while (nextSym == BZ_RUNA || nextSym == BZ_RUNB);
-
- es++;
- uc = s->seqToUnseq[ s->mtfa[s->mtfbase[0]] ];
- s->unzftab[uc] += es;
-
- if (s->smallDecompress)
- while (es > 0) {
- if (nblock >= nblockMAX) RETURN(BZ_DATA_ERROR);
- s->ll16[nblock] = (UInt16)uc;
- nblock++;
- es--;
- }
- else
- while (es > 0) {
- if (nblock >= nblockMAX) RETURN(BZ_DATA_ERROR);
- s->tt[nblock] = (UInt32)uc;
- nblock++;
- es--;
- };
-
- continue;
-
- } else {
-
- if (nblock >= nblockMAX) RETURN(BZ_DATA_ERROR);
-
- /*-- uc = MTF ( nextSym-1 ) --*/
- {
- Int32 ii, jj, kk, pp, lno, off;
- UInt32 nn;
- nn = (UInt32)(nextSym - 1);
-
- if (nn < MTFL_SIZE) {
- /* avoid general-case expense */
- pp = s->mtfbase[0];
- uc = s->mtfa[pp+nn];
- while (nn > 3) {
- Int32 z = pp+nn;
- s->mtfa[(z) ] = s->mtfa[(z)-1];
- s->mtfa[(z)-1] = s->mtfa[(z)-2];
- s->mtfa[(z)-2] = s->mtfa[(z)-3];
- s->mtfa[(z)-3] = s->mtfa[(z)-4];
- nn -= 4;
- }
- while (nn > 0) {
- s->mtfa[(pp+nn)] = s->mtfa[(pp+nn)-1]; nn--;
- };
- s->mtfa[pp] = uc;
- } else {
- /* general case */
- lno = nn / MTFL_SIZE;
- off = nn % MTFL_SIZE;
- pp = s->mtfbase[lno] + off;
- uc = s->mtfa[pp];
- while (pp > s->mtfbase[lno]) {
- s->mtfa[pp] = s->mtfa[pp-1]; pp--;
- };
- s->mtfbase[lno]++;
- while (lno > 0) {
- s->mtfbase[lno]--;
- s->mtfa[s->mtfbase[lno]]
- = s->mtfa[s->mtfbase[lno-1] + MTFL_SIZE - 1];
- lno--;
- }
- s->mtfbase[0]--;
- s->mtfa[s->mtfbase[0]] = uc;
- if (s->mtfbase[0] == 0) {
- kk = MTFA_SIZE-1;
- for (ii = 256 / MTFL_SIZE-1; ii >= 0; ii--) {
- for (jj = MTFL_SIZE-1; jj >= 0; jj--) {
- s->mtfa[kk] = s->mtfa[s->mtfbase[ii] + jj];
- kk--;
- }
- s->mtfbase[ii] = kk + 1;
- }
- }
- }
- }
- /*-- end uc = MTF ( nextSym-1 ) --*/
-
- s->unzftab[s->seqToUnseq[uc]]++;
- if (s->smallDecompress)
- s->ll16[nblock] = (UInt16)(s->seqToUnseq[uc]); else
- s->tt[nblock] = (UInt32)(s->seqToUnseq[uc]);
- nblock++;
-
- GET_MTF_VAL(BZ_X_MTF_5, BZ_X_MTF_6, nextSym);
- continue;
- }
- }
-
- /* Now we know what nblock is, we can do a better sanity
- check on s->origPtr.
- */
- if (s->origPtr < 0 || s->origPtr >= nblock)
- RETURN(BZ_DATA_ERROR);
-
- s->state_out_len = 0;
- s->state_out_ch = 0;
- BZ_INITIALISE_CRC ( s->calculatedBlockCRC );
- s->state = BZ_X_OUTPUT;
- if (s->verbosity >= 2) VPrintf0 ( "rt+rld" );
-
- /*-- Set up cftab to facilitate generation of T^(-1) --*/
- s->cftab[0] = 0;
- for (i = 1; i <= 256; i++) s->cftab[i] = s->unzftab[i-1];
- for (i = 1; i <= 256; i++) s->cftab[i] += s->cftab[i-1];
-
- if (s->smallDecompress) {
-
- /*-- Make a copy of cftab, used in generation of T --*/
- for (i = 0; i <= 256; i++) s->cftabCopy[i] = s->cftab[i];
-
- /*-- compute the T vector --*/
- for (i = 0; i < nblock; i++) {
- uc = (UChar)(s->ll16[i]);
- SET_LL(i, s->cftabCopy[uc]);
- s->cftabCopy[uc]++;
- }
-
- /*-- Compute T^(-1) by pointer reversal on T --*/
- i = s->origPtr;
- j = GET_LL(i);
- do {
- Int32 tmp = GET_LL(j);
- SET_LL(j, i);
- i = j;
- j = tmp;
- }
- while (i != s->origPtr);
-
- s->tPos = s->origPtr;
- s->nblock_used = 0;
- if (s->blockRandomised) {
- BZ_RAND_INIT_MASK;
- BZ_GET_SMALL(s->k0); s->nblock_used++;
- BZ_RAND_UPD_MASK; s->k0 ^= BZ_RAND_MASK;
- } else {
- BZ_GET_SMALL(s->k0); s->nblock_used++;
- }
-
- } else {
-
- /*-- compute the T^(-1) vector --*/
- for (i = 0; i < nblock; i++) {
- uc = (UChar)(s->tt[i] & 0xff);
- s->tt[s->cftab[uc]] |= (i << 8);
- s->cftab[uc]++;
- }
-
- s->tPos = s->tt[s->origPtr] >> 8;
- s->nblock_used = 0;
- if (s->blockRandomised) {
- BZ_RAND_INIT_MASK;
- BZ_GET_FAST(s->k0); s->nblock_used++;
- BZ_RAND_UPD_MASK; s->k0 ^= BZ_RAND_MASK;
- } else {
- BZ_GET_FAST(s->k0); s->nblock_used++;
- }
-
- }
-
- RETURN(BZ_OK);
-
-
-
- endhdr_2:
-
- GET_UCHAR(BZ_X_ENDHDR_2, uc);
- if (uc != 0x72) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_ENDHDR_3, uc);
- if (uc != 0x45) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_ENDHDR_4, uc);
- if (uc != 0x38) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_ENDHDR_5, uc);
- if (uc != 0x50) RETURN(BZ_DATA_ERROR);
- GET_UCHAR(BZ_X_ENDHDR_6, uc);
- if (uc != 0x90) RETURN(BZ_DATA_ERROR);
-
- s->storedCombinedCRC = 0;
- GET_UCHAR(BZ_X_CCRC_1, uc);
- s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
- GET_UCHAR(BZ_X_CCRC_2, uc);
- s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
- GET_UCHAR(BZ_X_CCRC_3, uc);
- s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
- GET_UCHAR(BZ_X_CCRC_4, uc);
- s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
-
- s->state = BZ_X_IDLE;
- RETURN(BZ_STREAM_END);
-
- default: AssertH ( False, 4001 );
- }
-
- AssertH ( False, 4002 );
-
- save_state_and_return:
-
- s->save_i = i;
- s->save_j = j;
- s->save_t = t;
- s->save_alphaSize = alphaSize;
- s->save_nGroups = nGroups;
- s->save_nSelectors = nSelectors;
- s->save_EOB = EOB;
- s->save_groupNo = groupNo;
- s->save_groupPos = groupPos;
- s->save_nextSym = nextSym;
- s->save_nblockMAX = nblockMAX;
- s->save_nblock = nblock;
- s->save_es = es;
- s->save_N = N;
- s->save_curr = curr;
- s->save_zt = zt;
- s->save_zn = zn;
- s->save_zvec = zvec;
- s->save_zj = zj;
- s->save_gSel = gSel;
- s->save_gMinlen = gMinlen;
- s->save_gLimit = gLimit;
- s->save_gBase = gBase;
- s->save_gPerm = gPerm;
-
- return retVal;
-}
-
-
-/*-------------------------------------------------------------*/
-/*--- end decompress.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-------------------------------------------------------------*/
-/*--- Library top-level functions. ---*/
-/*--- bzlib.c ---*/
-/*-------------------------------------------------------------*/
-
-/*---------------------------------------------------*/
-/*--- Compression stuff ---*/
-/*---------------------------------------------------*/
-
-
-/*---------------------------------------------------*/
-#ifndef BZ_NO_STDIO
-void BZ2_bz__AssertH__fail ( int errcode )
-{
- fprintf(stderr,
- "\n\nbzip2/libbzip2: internal error number %d.\n"
- "This is a bug in bzip2/libbzip2, %s.\n"
- "Please report it to me at: jseward at acm.org. If this happened\n"
- "when you were using some program which uses libbzip2 as a\n"
- "component, you should also report this bug to the author(s)\n"
- "of that program. Please make an effort to report this bug;\n"
- "timely and accurate bug reports eventually lead to higher\n"
- "quality software. Thanks. Julian Seward, 30 December 2001.\n\n",
- errcode,
- BZ2_bzlibVersion()
- );
-
- if (errcode == 1007) {
- fprintf(stderr,
- "\n*** A special note about internal error number 1007 ***\n"
- "\n"
- "Experience suggests that a common cause of i.e. 1007\n"
- "is unreliable memory or other hardware. The 1007 assertion\n"
- "just happens to cross-check the results of huge numbers of\n"
- "memory reads/writes, and so acts (unintendedly) as a stress\n"
- "test of your memory system.\n"
- "\n"
- "I suggest the following: try compressing the file again,\n"
- "possibly monitoring progress in detail with the -vv flag.\n"
- "\n"
- "* If the error cannot be reproduced, and/or happens at different\n"
- " points in compression, you may have a flaky memory system.\n"
- " Try a memory-test program. I have used Memtest86\n"
- " (www.memtest86.com). At the time of writing it is free (GPLd).\n"
- " Memtest86 tests memory much more thorougly than your BIOSs\n"
- " power-on test, and may find failures that the BIOS doesn't.\n"
- "\n"
- "* If the error can be repeatably reproduced, this is a bug in\n"
- " bzip2, and I would very much like to hear about it. Please\n"
- " let me know, and, ideally, save a copy of the file causing the\n"
- " problem -- without which I will be unable to investigate it.\n"
- "\n"
- );
- }
-
- exit(3);
-}
-#endif
-
-
-/*---------------------------------------------------*/
-static
-int bz_config_ok ( void )
-{
- if (sizeof(int) != 4) return 0;
- if (sizeof(short) != 2) return 0;
- if (sizeof(char) != 1) return 0;
- return 1;
-}
-
-
-/*---------------------------------------------------*/
-static
-void* default_bzalloc ( void* opaque, Int32 items, Int32 size )
-{
- void* v = malloc ( items * size );
- return v;
-}
-
-static
-void default_bzfree ( void* opaque, void* addr )
-{
- if (addr != NULL) free ( addr );
-}
-
-
-/*---------------------------------------------------*/
-static
-void prepare_new_block ( EState* s )
-{
- Int32 i;
- s->nblock = 0;
- s->numZ = 0;
- s->state_out_pos = 0;
- BZ_INITIALISE_CRC ( s->blockCRC );
- for (i = 0; i < 256; i++) s->inUse[i] = False;
- s->blockNo++;
-}
-
-
-/*---------------------------------------------------*/
-static
-void init_RL ( EState* s )
-{
- s->state_in_ch = 256;
- s->state_in_len = 0;
-}
-
-
-static
-Bool isempty_RL ( EState* s )
-{
- if (s->state_in_ch < 256 && s->state_in_len > 0)
- return False; else
- return True;
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzCompressInit)
- ( bz_stream* strm,
- int blockSize100k,
- int verbosity,
- int workFactor )
-{
- Int32 n;
- EState* s;
-
- if (!bz_config_ok()) return BZ_CONFIG_ERROR;
-
- if (strm == NULL ||
- blockSize100k < 1 || blockSize100k > 9 ||
- workFactor < 0 || workFactor > 250)
- return BZ_PARAM_ERROR;
-
- if (workFactor == 0) workFactor = 30;
- if (strm->bzalloc == NULL) strm->bzalloc = default_bzalloc;
- if (strm->bzfree == NULL) strm->bzfree = default_bzfree;
-
- s = BZALLOC( sizeof(EState) );
- if (s == NULL) return BZ_MEM_ERROR;
- s->strm = strm;
-
- s->arr1 = NULL;
- s->arr2 = NULL;
- s->ftab = NULL;
-
- n = 100000 * blockSize100k;
- s->arr1 = BZALLOC( n * sizeof(UInt32) );
- s->arr2 = BZALLOC( (n+BZ_N_OVERSHOOT) * sizeof(UInt32) );
- s->ftab = BZALLOC( 65537 * sizeof(UInt32) );
-
- if (s->arr1 == NULL || s->arr2 == NULL || s->ftab == NULL) {
- if (s->arr1 != NULL) BZFREE(s->arr1);
- if (s->arr2 != NULL) BZFREE(s->arr2);
- if (s->ftab != NULL) BZFREE(s->ftab);
- if (s != NULL) BZFREE(s);
- return BZ_MEM_ERROR;
- }
-
- s->blockNo = 0;
- s->state = BZ_S_INPUT;
- s->mode = BZ_M_RUNNING;
- s->combinedCRC = 0;
- s->blockSize100k = blockSize100k;
- s->nblockMAX = 100000 * blockSize100k - 19;
- s->verbosity = verbosity;
- s->workFactor = workFactor;
-
- s->block = (UChar*)s->arr2;
- s->mtfv = (UInt16*)s->arr1;
- s->zbits = NULL;
- s->ptr = (UInt32*)s->arr1;
-
- strm->state = s;
- strm->total_in_lo32 = 0;
- strm->total_in_hi32 = 0;
- strm->total_out_lo32 = 0;
- strm->total_out_hi32 = 0;
- init_RL ( s );
- prepare_new_block ( s );
- return BZ_OK;
-}
-
-
-/*---------------------------------------------------*/
-static
-void add_pair_to_block ( EState* s )
-{
- Int32 i;
- UChar ch = (UChar)(s->state_in_ch);
- for (i = 0; i < s->state_in_len; i++) {
- BZ_UPDATE_CRC( s->blockCRC, ch );
- }
- s->inUse[s->state_in_ch] = True;
- switch (s->state_in_len) {
- case 1:
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- break;
- case 2:
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- break;
- case 3:
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- break;
- default:
- s->inUse[s->state_in_len-4] = True;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = (UChar)ch; s->nblock++;
- s->block[s->nblock] = ((UChar)(s->state_in_len-4));
- s->nblock++;
- break;
- }
-}
-
-
-/*---------------------------------------------------*/
-static
-void flush_RL ( EState* s )
-{
- if (s->state_in_ch < 256) add_pair_to_block ( s );
- init_RL ( s );
-}
-
-
-/*---------------------------------------------------*/
-#define ADD_CHAR_TO_BLOCK(zs,zchh0) \
-{ \
- UInt32 zchh = (UInt32)(zchh0); \
- /*-- fast track the common case --*/ \
- if (zchh != zs->state_in_ch && \
- zs->state_in_len == 1) { \
- UChar ch = (UChar)(zs->state_in_ch); \
- BZ_UPDATE_CRC( zs->blockCRC, ch ); \
- zs->inUse[zs->state_in_ch] = True; \
- zs->block[zs->nblock] = (UChar)ch; \
- zs->nblock++; \
- zs->state_in_ch = zchh; \
- } \
- else \
- /*-- general, uncommon cases --*/ \
- if (zchh != zs->state_in_ch || \
- zs->state_in_len == 255) { \
- if (zs->state_in_ch < 256) \
- add_pair_to_block ( zs ); \
- zs->state_in_ch = zchh; \
- zs->state_in_len = 1; \
- } else { \
- zs->state_in_len++; \
- } \
-}
-
-
-/*---------------------------------------------------*/
-static
-Bool copy_input_until_stop ( EState* s )
-{
- Bool progress_in = False;
-
- if (s->mode == BZ_M_RUNNING) {
-
- /*-- fast track the common case --*/
- while (True) {
- /*-- block full? --*/
- if (s->nblock >= s->nblockMAX) break;
- /*-- no input? --*/
- if (s->strm->avail_in == 0) break;
- progress_in = True;
- ADD_CHAR_TO_BLOCK ( s, (UInt32)(*((UChar*)(s->strm->next_in))) );
- s->strm->next_in++;
- s->strm->avail_in--;
- s->strm->total_in_lo32++;
- if (s->strm->total_in_lo32 == 0) s->strm->total_in_hi32++;
- }
-
- } else {
-
- /*-- general, uncommon case --*/
- while (True) {
- /*-- block full? --*/
- if (s->nblock >= s->nblockMAX) break;
- /*-- no input? --*/
- if (s->strm->avail_in == 0) break;
- /*-- flush/finish end? --*/
- if (s->avail_in_expect == 0) break;
- progress_in = True;
- ADD_CHAR_TO_BLOCK ( s, (UInt32)(*((UChar*)(s->strm->next_in))) );
- s->strm->next_in++;
- s->strm->avail_in--;
- s->strm->total_in_lo32++;
- if (s->strm->total_in_lo32 == 0) s->strm->total_in_hi32++;
- s->avail_in_expect--;
- }
- }
- return progress_in;
-}
-
-
-/*---------------------------------------------------*/
-static
-Bool copy_output_until_stop ( EState* s )
-{
- Bool progress_out = False;
-
- while (True) {
-
- /*-- no output space? --*/
- if (s->strm->avail_out == 0) break;
-
- /*-- block done? --*/
- if (s->state_out_pos >= s->numZ) break;
-
- progress_out = True;
- *(s->strm->next_out) = s->zbits[s->state_out_pos];
- s->state_out_pos++;
- s->strm->avail_out--;
- s->strm->next_out++;
- s->strm->total_out_lo32++;
- if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++;
- }
-
- return progress_out;
-}
-
-
-/*---------------------------------------------------*/
-static
-Bool handle_compress ( bz_stream* strm )
-{
- Bool progress_in = False;
- Bool progress_out = False;
- EState* s = strm->state;
-
- while (True) {
-
- if (s->state == BZ_S_OUTPUT) {
- progress_out |= copy_output_until_stop ( s );
- if (s->state_out_pos < s->numZ) break;
- if (s->mode == BZ_M_FINISHING &&
- s->avail_in_expect == 0 &&
- isempty_RL(s)) break;
- prepare_new_block ( s );
- s->state = BZ_S_INPUT;
- if (s->mode == BZ_M_FLUSHING &&
- s->avail_in_expect == 0 &&
- isempty_RL(s)) break;
- }
-
- if (s->state == BZ_S_INPUT) {
- progress_in |= copy_input_until_stop ( s );
- if (s->mode != BZ_M_RUNNING && s->avail_in_expect == 0) {
- flush_RL ( s );
- BZ2_compressBlock ( s, (Bool)(s->mode == BZ_M_FINISHING) );
- s->state = BZ_S_OUTPUT;
- }
- else
- if (s->nblock >= s->nblockMAX) {
- BZ2_compressBlock ( s, False );
- s->state = BZ_S_OUTPUT;
- }
- else
- if (s->strm->avail_in == 0) {
- break;
- }
- }
-
- }
-
- return progress_in || progress_out;
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzCompress) ( bz_stream *strm, int action )
-{
- Bool progress;
- EState* s;
- if (strm == NULL) return BZ_PARAM_ERROR;
- s = strm->state;
- if (s == NULL) return BZ_PARAM_ERROR;
- if (s->strm != strm) return BZ_PARAM_ERROR;
-
- preswitch:
- switch (s->mode) {
-
- case BZ_M_IDLE:
- return BZ_SEQUENCE_ERROR;
-
- case BZ_M_RUNNING:
- if (action == BZ_RUN) {
- progress = handle_compress ( strm );
- return progress ? BZ_RUN_OK : BZ_PARAM_ERROR;
- }
- else
- if (action == BZ_FLUSH) {
- s->avail_in_expect = strm->avail_in;
- s->mode = BZ_M_FLUSHING;
- goto preswitch;
- }
- else
- if (action == BZ_FINISH) {
- s->avail_in_expect = strm->avail_in;
- s->mode = BZ_M_FINISHING;
- goto preswitch;
- }
- else
- return BZ_PARAM_ERROR;
-
- case BZ_M_FLUSHING:
- if (action != BZ_FLUSH) return BZ_SEQUENCE_ERROR;
- if (s->avail_in_expect != s->strm->avail_in)
- return BZ_SEQUENCE_ERROR;
- progress = handle_compress ( strm );
- if (s->avail_in_expect > 0 || !isempty_RL(s) ||
- s->state_out_pos < s->numZ) return BZ_FLUSH_OK;
- s->mode = BZ_M_RUNNING;
- return BZ_RUN_OK;
-
- case BZ_M_FINISHING:
- if (action != BZ_FINISH) return BZ_SEQUENCE_ERROR;
- if (s->avail_in_expect != s->strm->avail_in)
- return BZ_SEQUENCE_ERROR;
- progress = handle_compress ( strm );
- if (!progress) return BZ_SEQUENCE_ERROR;
- if (s->avail_in_expect > 0 || !isempty_RL(s) ||
- s->state_out_pos < s->numZ) return BZ_FINISH_OK;
- s->mode = BZ_M_IDLE;
- return BZ_STREAM_END;
- }
- return BZ_OK; /*--not reached--*/
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzCompressEnd) ( bz_stream *strm )
-{
- EState* s;
- if (strm == NULL) return BZ_PARAM_ERROR;
- s = strm->state;
- if (s == NULL) return BZ_PARAM_ERROR;
- if (s->strm != strm) return BZ_PARAM_ERROR;
-
- if (s->arr1 != NULL) BZFREE(s->arr1);
- if (s->arr2 != NULL) BZFREE(s->arr2);
- if (s->ftab != NULL) BZFREE(s->ftab);
- BZFREE(strm->state);
-
- strm->state = NULL;
-
- return BZ_OK;
-}
-
-
-/*---------------------------------------------------*/
-/*--- Decompression stuff ---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzDecompressInit)
- ( bz_stream* strm,
- int verbosity,
- int small )
-{
- DState* s;
-
- if (!bz_config_ok()) return BZ_CONFIG_ERROR;
-
- if (strm == NULL) return BZ_PARAM_ERROR;
- if (small != 0 && small != 1) return BZ_PARAM_ERROR;
- if (verbosity < 0 || verbosity > 4) return BZ_PARAM_ERROR;
-
- if (strm->bzalloc == NULL) strm->bzalloc = default_bzalloc;
- if (strm->bzfree == NULL) strm->bzfree = default_bzfree;
-
- s = BZALLOC( sizeof(DState) );
- if (s == NULL) return BZ_MEM_ERROR;
- s->strm = strm;
- strm->state = s;
- s->state = BZ_X_MAGIC_1;
- s->bsLive = 0;
- s->bsBuff = 0;
- s->calculatedCombinedCRC = 0;
- strm->total_in_lo32 = 0;
- strm->total_in_hi32 = 0;
- strm->total_out_lo32 = 0;
- strm->total_out_hi32 = 0;
- s->smallDecompress = (Bool)small;
- s->ll4 = NULL;
- s->ll16 = NULL;
- s->tt = NULL;
- s->currBlockNo = 0;
- s->verbosity = verbosity;
-
- return BZ_OK;
-}
-
-
-/*---------------------------------------------------*/
-static
-void unRLE_obuf_to_output_FAST ( DState* s )
-{
- UChar k1;
-
- if (s->blockRandomised) {
-
- while (True) {
- /* try to finish existing run */
- while (True) {
- if (s->strm->avail_out == 0) return;
- if (s->state_out_len == 0) break;
- *( (UChar*)(s->strm->next_out) ) = s->state_out_ch;
- BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch );
- s->state_out_len--;
- s->strm->next_out++;
- s->strm->avail_out--;
- s->strm->total_out_lo32++;
- if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++;
- }
-
- /* can a new run be started? */
- if (s->nblock_used == s->save_nblock+1) return;
-
-
- s->state_out_len = 1;
- s->state_out_ch = s->k0;
- BZ_GET_FAST(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- s->state_out_len = 2;
- BZ_GET_FAST(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- s->state_out_len = 3;
- BZ_GET_FAST(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- BZ_GET_FAST(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- s->state_out_len = ((Int32)k1) + 4;
- BZ_GET_FAST(s->k0); BZ_RAND_UPD_MASK;
- s->k0 ^= BZ_RAND_MASK; s->nblock_used++;
- }
-
- } else {
-
- /* restore */
- UInt32 c_calculatedBlockCRC = s->calculatedBlockCRC;
- UChar c_state_out_ch = s->state_out_ch;
- Int32 c_state_out_len = s->state_out_len;
- Int32 c_nblock_used = s->nblock_used;
- Int32 c_k0 = s->k0;
- UInt32* c_tt = s->tt;
- UInt32 c_tPos = s->tPos;
- char* cs_next_out = s->strm->next_out;
- unsigned int cs_avail_out = s->strm->avail_out;
- /* end restore */
-
- UInt32 avail_out_INIT = cs_avail_out;
- Int32 s_save_nblockPP = s->save_nblock+1;
- unsigned int total_out_lo32_old;
-
- while (True) {
-
- /* try to finish existing run */
- if (c_state_out_len > 0) {
- while (True) {
- if (cs_avail_out == 0) goto return_notr;
- if (c_state_out_len == 1) break;
- *( (UChar*)(cs_next_out) ) = c_state_out_ch;
- BZ_UPDATE_CRC ( c_calculatedBlockCRC, c_state_out_ch );
- c_state_out_len--;
- cs_next_out++;
- cs_avail_out--;
- }
- s_state_out_len_eq_one:
- {
- if (cs_avail_out == 0) {
- c_state_out_len = 1; goto return_notr;
- };
- *( (UChar*)(cs_next_out) ) = c_state_out_ch;
- BZ_UPDATE_CRC ( c_calculatedBlockCRC, c_state_out_ch );
- cs_next_out++;
- cs_avail_out--;
- }
- }
- /* can a new run be started? */
- if (c_nblock_used == s_save_nblockPP) {
- c_state_out_len = 0; goto return_notr;
- };
- c_state_out_ch = c_k0;
- BZ_GET_FAST_C(k1); c_nblock_used++;
- if (k1 != c_k0) {
- c_k0 = k1; goto s_state_out_len_eq_one;
- };
- if (c_nblock_used == s_save_nblockPP)
- goto s_state_out_len_eq_one;
-
- c_state_out_len = 2;
- BZ_GET_FAST_C(k1); c_nblock_used++;
- if (c_nblock_used == s_save_nblockPP) continue;
- if (k1 != c_k0) { c_k0 = k1; continue; };
-
- c_state_out_len = 3;
- BZ_GET_FAST_C(k1); c_nblock_used++;
- if (c_nblock_used == s_save_nblockPP) continue;
- if (k1 != c_k0) { c_k0 = k1; continue; };
-
- BZ_GET_FAST_C(k1); c_nblock_used++;
- c_state_out_len = ((Int32)k1) + 4;
- BZ_GET_FAST_C(c_k0); c_nblock_used++;
- }
-
- return_notr:
- total_out_lo32_old = s->strm->total_out_lo32;
- s->strm->total_out_lo32 += (avail_out_INIT - cs_avail_out);
- if (s->strm->total_out_lo32 < total_out_lo32_old)
- s->strm->total_out_hi32++;
-
- /* save */
- s->calculatedBlockCRC = c_calculatedBlockCRC;
- s->state_out_ch = c_state_out_ch;
- s->state_out_len = c_state_out_len;
- s->nblock_used = c_nblock_used;
- s->k0 = c_k0;
- s->tt = c_tt;
- s->tPos = c_tPos;
- s->strm->next_out = cs_next_out;
- s->strm->avail_out = cs_avail_out;
- /* end save */
- }
-}
-
-
-
-/*---------------------------------------------------*/
-Int32 BZ2_indexIntoF ( Int32 indx, Int32 *cftab )
-{
- Int32 nb, na, mid;
- nb = 0;
- na = 256;
- do {
- mid = (nb + na) >> 1;
- if (indx >= cftab[mid]) nb = mid; else na = mid;
- }
- while (na - nb != 1);
- return nb;
-}
-
-
-/*---------------------------------------------------*/
-static
-void unRLE_obuf_to_output_SMALL ( DState* s )
-{
- UChar k1;
-
- if (s->blockRandomised) {
-
- while (True) {
- /* try to finish existing run */
- while (True) {
- if (s->strm->avail_out == 0) return;
- if (s->state_out_len == 0) break;
- *( (UChar*)(s->strm->next_out) ) = s->state_out_ch;
- BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch );
- s->state_out_len--;
- s->strm->next_out++;
- s->strm->avail_out--;
- s->strm->total_out_lo32++;
- if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++;
- }
-
- /* can a new run be started? */
- if (s->nblock_used == s->save_nblock+1) return;
-
-
- s->state_out_len = 1;
- s->state_out_ch = s->k0;
- BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- s->state_out_len = 2;
- BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- s->state_out_len = 3;
- BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK;
- k1 ^= BZ_RAND_MASK; s->nblock_used++;
- s->state_out_len = ((Int32)k1) + 4;
- BZ_GET_SMALL(s->k0); BZ_RAND_UPD_MASK;
- s->k0 ^= BZ_RAND_MASK; s->nblock_used++;
- }
-
- } else {
-
- while (True) {
- /* try to finish existing run */
- while (True) {
- if (s->strm->avail_out == 0) return;
- if (s->state_out_len == 0) break;
- *( (UChar*)(s->strm->next_out) ) = s->state_out_ch;
- BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch );
- s->state_out_len--;
- s->strm->next_out++;
- s->strm->avail_out--;
- s->strm->total_out_lo32++;
- if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++;
- }
-
- /* can a new run be started? */
- if (s->nblock_used == s->save_nblock+1) return;
-
- s->state_out_len = 1;
- s->state_out_ch = s->k0;
- BZ_GET_SMALL(k1); s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- s->state_out_len = 2;
- BZ_GET_SMALL(k1); s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- s->state_out_len = 3;
- BZ_GET_SMALL(k1); s->nblock_used++;
- if (s->nblock_used == s->save_nblock+1) continue;
- if (k1 != s->k0) { s->k0 = k1; continue; };
-
- BZ_GET_SMALL(k1); s->nblock_used++;
- s->state_out_len = ((Int32)k1) + 4;
- BZ_GET_SMALL(s->k0); s->nblock_used++;
- }
-
- }
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzDecompress) ( bz_stream *strm )
-{
- DState* s;
- if (strm == NULL) return BZ_PARAM_ERROR;
- s = strm->state;
- if (s == NULL) return BZ_PARAM_ERROR;
- if (s->strm != strm) return BZ_PARAM_ERROR;
-
- while (True) {
- if (s->state == BZ_X_IDLE) return BZ_SEQUENCE_ERROR;
- if (s->state == BZ_X_OUTPUT) {
- if (s->smallDecompress)
- unRLE_obuf_to_output_SMALL ( s ); else
- unRLE_obuf_to_output_FAST ( s );
- if (s->nblock_used == s->save_nblock+1 && s->state_out_len == 0) {
- BZ_FINALISE_CRC ( s->calculatedBlockCRC );
- if (s->verbosity >= 3)
- VPrintf2 ( " {0x%x, 0x%x}", s->storedBlockCRC,
- s->calculatedBlockCRC );
- if (s->verbosity >= 2) VPrintf0 ( "]" );
- if (s->calculatedBlockCRC != s->storedBlockCRC)
- return BZ_DATA_ERROR;
- s->calculatedCombinedCRC
- = (s->calculatedCombinedCRC << 1) |
- (s->calculatedCombinedCRC >> 31);
- s->calculatedCombinedCRC ^= s->calculatedBlockCRC;
- s->state = BZ_X_BLKHDR_1;
- } else {
- return BZ_OK;
- }
- }
- if (s->state >= BZ_X_MAGIC_1) {
- Int32 r = BZ2_decompress ( s );
- if (r == BZ_STREAM_END) {
- if (s->verbosity >= 3)
- VPrintf2 ( "\n combined CRCs: stored = 0x%x, computed = 0x%x",
- s->storedCombinedCRC, s->calculatedCombinedCRC );
- if (s->calculatedCombinedCRC != s->storedCombinedCRC)
- return BZ_DATA_ERROR;
- return r;
- }
- if (s->state != BZ_X_OUTPUT) return r;
- }
- }
-
- AssertH ( 0, 6001 );
-
- return 0; /*NOTREACHED*/
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzDecompressEnd) ( bz_stream *strm )
-{
- DState* s;
- if (strm == NULL) return BZ_PARAM_ERROR;
- s = strm->state;
- if (s == NULL) return BZ_PARAM_ERROR;
- if (s->strm != strm) return BZ_PARAM_ERROR;
-
- if (s->tt != NULL) BZFREE(s->tt);
- if (s->ll16 != NULL) BZFREE(s->ll16);
- if (s->ll4 != NULL) BZFREE(s->ll4);
-
- BZFREE(strm->state);
- strm->state = NULL;
-
- return BZ_OK;
-}
-
-
-#ifndef BZ_NO_STDIO
-/*---------------------------------------------------*/
-/*--- File I/O stuff ---*/
-/*---------------------------------------------------*/
-
-#define BZ_SETERR(eee) \
-{ \
- if (bzerror != NULL) *bzerror = eee; \
- if (bzf != NULL) bzf->lastErr = eee; \
-}
-
-typedef
- struct {
- FILE* handle;
- Char buf[BZ_MAX_UNUSED];
- Int32 bufN;
- Bool writing;
- bz_stream strm;
- Int32 lastErr;
- Bool initialisedOk;
- }
- bzFile;
-
-
-/*---------------------------------------------*/
-static Bool myfeof ( FILE* f )
-{
- Int32 c = fgetc ( f );
- if (c == EOF) return True;
- ungetc ( c, f );
- return False;
-}
-
-
-/*---------------------------------------------------*/
-BZFILE* BZ_API(BZ2_bzWriteOpen)
- ( int* bzerror,
- FILE* f,
- int blockSize100k,
- int verbosity,
- int workFactor )
-{
- Int32 ret;
- bzFile* bzf = NULL;
-
- BZ_SETERR(BZ_OK);
-
- if (f == NULL ||
- (blockSize100k < 1 || blockSize100k > 9) ||
- (workFactor < 0 || workFactor > 250) ||
- (verbosity < 0 || verbosity > 4))
- { BZ_SETERR(BZ_PARAM_ERROR); return NULL; };
-
- if (ferror(f))
- { BZ_SETERR(BZ_IO_ERROR); return NULL; };
-
- bzf = malloc ( sizeof(bzFile) );
- if (bzf == NULL)
- { BZ_SETERR(BZ_MEM_ERROR); return NULL; };
-
- BZ_SETERR(BZ_OK);
- bzf->initialisedOk = False;
- bzf->bufN = 0;
- bzf->handle = f;
- bzf->writing = True;
- bzf->strm.bzalloc = NULL;
- bzf->strm.bzfree = NULL;
- bzf->strm.opaque = NULL;
-
- if (workFactor == 0) workFactor = 30;
- ret = BZ2_bzCompressInit ( &(bzf->strm), blockSize100k,
- verbosity, workFactor );
- if (ret != BZ_OK)
- { BZ_SETERR(ret); free(bzf); return NULL; };
-
- bzf->strm.avail_in = 0;
- bzf->initialisedOk = True;
- return bzf;
-}
-
-
-
-/*---------------------------------------------------*/
-void BZ_API(BZ2_bzWrite)
- ( int* bzerror,
- BZFILE* b,
- void* buf,
- int len )
-{
- Int32 n, n2, ret;
- bzFile* bzf = (bzFile*)b;
-
- BZ_SETERR(BZ_OK);
- if (bzf == NULL || buf == NULL || len < 0)
- { BZ_SETERR(BZ_PARAM_ERROR); return; };
- if (!(bzf->writing))
- { BZ_SETERR(BZ_SEQUENCE_ERROR); return; };
- if (ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return; };
-
- if (len == 0)
- { BZ_SETERR(BZ_OK); return; };
-
- bzf->strm.avail_in = len;
- bzf->strm.next_in = buf;
-
- while (True) {
- bzf->strm.avail_out = BZ_MAX_UNUSED;
- bzf->strm.next_out = bzf->buf;
- ret = BZ2_bzCompress ( &(bzf->strm), BZ_RUN );
- if (ret != BZ_RUN_OK)
- { BZ_SETERR(ret); return; };
-
- if (bzf->strm.avail_out < BZ_MAX_UNUSED) {
- n = BZ_MAX_UNUSED - bzf->strm.avail_out;
- n2 = fwrite ( (void*)(bzf->buf), sizeof(UChar),
- n, bzf->handle );
- if (n != n2 || ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return; };
- }
-
- if (bzf->strm.avail_in == 0)
- { BZ_SETERR(BZ_OK); return; };
- }
-}
-
-
-/*---------------------------------------------------*/
-void BZ_API(BZ2_bzWriteClose)
- ( int* bzerror,
- BZFILE* b,
- int abandon,
- unsigned int* nbytes_in,
- unsigned int* nbytes_out )
-{
- BZ2_bzWriteClose64 ( bzerror, b, abandon,
- nbytes_in, NULL, nbytes_out, NULL );
-}
-
-
-void BZ_API(BZ2_bzWriteClose64)
- ( int* bzerror,
- BZFILE* b,
- int abandon,
- unsigned int* nbytes_in_lo32,
- unsigned int* nbytes_in_hi32,
- unsigned int* nbytes_out_lo32,
- unsigned int* nbytes_out_hi32 )
-{
- Int32 n, n2, ret;
- bzFile* bzf = (bzFile*)b;
-
- if (bzf == NULL)
- { BZ_SETERR(BZ_OK); return; };
- if (!(bzf->writing))
- { BZ_SETERR(BZ_SEQUENCE_ERROR); return; };
- if (ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return; };
-
- if (nbytes_in_lo32 != NULL) *nbytes_in_lo32 = 0;
- if (nbytes_in_hi32 != NULL) *nbytes_in_hi32 = 0;
- if (nbytes_out_lo32 != NULL) *nbytes_out_lo32 = 0;
- if (nbytes_out_hi32 != NULL) *nbytes_out_hi32 = 0;
-
- if ((!abandon) && bzf->lastErr == BZ_OK) {
- while (True) {
- bzf->strm.avail_out = BZ_MAX_UNUSED;
- bzf->strm.next_out = bzf->buf;
- ret = BZ2_bzCompress ( &(bzf->strm), BZ_FINISH );
- if (ret != BZ_FINISH_OK && ret != BZ_STREAM_END)
- { BZ_SETERR(ret); return; };
-
- if (bzf->strm.avail_out < BZ_MAX_UNUSED) {
- n = BZ_MAX_UNUSED - bzf->strm.avail_out;
- n2 = fwrite ( (void*)(bzf->buf), sizeof(UChar),
- n, bzf->handle );
- if (n != n2 || ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return; };
- }
-
- if (ret == BZ_STREAM_END) break;
- }
- }
-
- if ( !abandon && !ferror ( bzf->handle ) ) {
- fflush ( bzf->handle );
- if (ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return; };
- }
-
- if (nbytes_in_lo32 != NULL)
- *nbytes_in_lo32 = bzf->strm.total_in_lo32;
- if (nbytes_in_hi32 != NULL)
- *nbytes_in_hi32 = bzf->strm.total_in_hi32;
- if (nbytes_out_lo32 != NULL)
- *nbytes_out_lo32 = bzf->strm.total_out_lo32;
- if (nbytes_out_hi32 != NULL)
- *nbytes_out_hi32 = bzf->strm.total_out_hi32;
-
- BZ_SETERR(BZ_OK);
- BZ2_bzCompressEnd ( &(bzf->strm) );
- free ( bzf );
-}
-
-
-/*---------------------------------------------------*/
-BZFILE* BZ_API(BZ2_bzReadOpen)
- ( int* bzerror,
- FILE* f,
- int verbosity,
- int small,
- void* unused,
- int nUnused )
-{
- bzFile* bzf = NULL;
- int ret;
-
- BZ_SETERR(BZ_OK);
-
- if (f == NULL ||
- (small != 0 && small != 1) ||
- (verbosity < 0 || verbosity > 4) ||
- (unused == NULL && nUnused != 0) ||
- (unused != NULL && (nUnused < 0 || nUnused > BZ_MAX_UNUSED)))
- { BZ_SETERR(BZ_PARAM_ERROR); return NULL; };
-
- if (ferror(f))
- { BZ_SETERR(BZ_IO_ERROR); return NULL; };
-
- bzf = malloc ( sizeof(bzFile) );
- if (bzf == NULL)
- { BZ_SETERR(BZ_MEM_ERROR); return NULL; };
-
- BZ_SETERR(BZ_OK);
-
- bzf->initialisedOk = False;
- bzf->handle = f;
- bzf->bufN = 0;
- bzf->writing = False;
- bzf->strm.bzalloc = NULL;
- bzf->strm.bzfree = NULL;
- bzf->strm.opaque = NULL;
-
- while (nUnused > 0) {
- bzf->buf[bzf->bufN] = *((UChar*)(unused)); bzf->bufN++;
- unused = ((void*)( 1 + ((UChar*)(unused)) ));
- nUnused--;
- }
-
- ret = BZ2_bzDecompressInit ( &(bzf->strm), verbosity, small );
- if (ret != BZ_OK)
- { BZ_SETERR(ret); free(bzf); return NULL; };
-
- bzf->strm.avail_in = bzf->bufN;
- bzf->strm.next_in = bzf->buf;
-
- bzf->initialisedOk = True;
- return bzf;
-}
-
-
-/*---------------------------------------------------*/
-void BZ_API(BZ2_bzReadClose) ( int *bzerror, BZFILE *b )
-{
- bzFile* bzf = (bzFile*)b;
-
- BZ_SETERR(BZ_OK);
- if (bzf == NULL)
- { BZ_SETERR(BZ_OK); return; };
-
- if (bzf->writing)
- { BZ_SETERR(BZ_SEQUENCE_ERROR); return; };
-
- if (bzf->initialisedOk)
- (void)BZ2_bzDecompressEnd ( &(bzf->strm) );
- free ( bzf );
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzRead)
- ( int* bzerror,
- BZFILE* b,
- void* buf,
- int len )
-{
- Int32 n, ret;
- bzFile* bzf = (bzFile*)b;
-
- BZ_SETERR(BZ_OK);
-
- if (bzf == NULL || buf == NULL || len < 0)
- { BZ_SETERR(BZ_PARAM_ERROR); return 0; };
-
- if (bzf->writing)
- { BZ_SETERR(BZ_SEQUENCE_ERROR); return 0; };
-
- if (len == 0)
- { BZ_SETERR(BZ_OK); return 0; };
-
- bzf->strm.avail_out = len;
- bzf->strm.next_out = buf;
-
- while (True) {
-
- if (ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return 0; };
-
- if (bzf->strm.avail_in == 0 && !myfeof(bzf->handle)) {
- n = fread ( bzf->buf, sizeof(UChar),
- BZ_MAX_UNUSED, bzf->handle );
- if (ferror(bzf->handle))
- { BZ_SETERR(BZ_IO_ERROR); return 0; };
- bzf->bufN = n;
- bzf->strm.avail_in = bzf->bufN;
- bzf->strm.next_in = bzf->buf;
- }
-
- ret = BZ2_bzDecompress ( &(bzf->strm) );
-
- if (ret != BZ_OK && ret != BZ_STREAM_END)
- { BZ_SETERR(ret); return 0; };
-
- if (ret == BZ_OK && myfeof(bzf->handle) &&
- bzf->strm.avail_in == 0 && bzf->strm.avail_out > 0)
- { BZ_SETERR(BZ_UNEXPECTED_EOF); return 0; };
-
- if (ret == BZ_STREAM_END)
- { BZ_SETERR(BZ_STREAM_END);
- return len - bzf->strm.avail_out; };
- if (bzf->strm.avail_out == 0)
- { BZ_SETERR(BZ_OK); return len; };
-
- }
-
- return 0; /*not reached*/
-}
-
-
-/*---------------------------------------------------*/
-void BZ_API(BZ2_bzReadGetUnused)
- ( int* bzerror,
- BZFILE* b,
- void** unused,
- int* nUnused )
-{
- bzFile* bzf = (bzFile*)b;
- if (bzf == NULL)
- { BZ_SETERR(BZ_PARAM_ERROR); return; };
- if (bzf->lastErr != BZ_STREAM_END)
- { BZ_SETERR(BZ_SEQUENCE_ERROR); return; };
- if (unused == NULL || nUnused == NULL)
- { BZ_SETERR(BZ_PARAM_ERROR); return; };
-
- BZ_SETERR(BZ_OK);
- *nUnused = bzf->strm.avail_in;
- *unused = bzf->strm.next_in;
-}
-#endif
-
-
-/*---------------------------------------------------*/
-/*--- Misc convenience stuff ---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzBuffToBuffCompress)
- ( char* dest,
- unsigned int* destLen,
- char* source,
- unsigned int sourceLen,
- int blockSize100k,
- int verbosity,
- int workFactor )
-{
- bz_stream strm;
- int ret;
-
- if (dest == NULL || destLen == NULL ||
- source == NULL ||
- blockSize100k < 1 || blockSize100k > 9 ||
- verbosity < 0 || verbosity > 4 ||
- workFactor < 0 || workFactor > 250)
- return BZ_PARAM_ERROR;
-
- if (workFactor == 0) workFactor = 30;
- strm.bzalloc = NULL;
- strm.bzfree = NULL;
- strm.opaque = NULL;
- ret = BZ2_bzCompressInit ( &strm, blockSize100k,
- verbosity, workFactor );
- if (ret != BZ_OK) return ret;
-
- strm.next_in = source;
- strm.next_out = dest;
- strm.avail_in = sourceLen;
- strm.avail_out = *destLen;
-
- ret = BZ2_bzCompress ( &strm, BZ_FINISH );
- if (ret == BZ_FINISH_OK) goto output_overflow;
- if (ret != BZ_STREAM_END) goto errhandler;
-
- /* normal termination */
- *destLen -= strm.avail_out;
- BZ2_bzCompressEnd ( &strm );
- return BZ_OK;
-
- output_overflow:
- BZ2_bzCompressEnd ( &strm );
- return BZ_OUTBUFF_FULL;
-
- errhandler:
- BZ2_bzCompressEnd ( &strm );
- return ret;
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzBuffToBuffDecompress)
- ( char* dest,
- unsigned int* destLen,
- char* source,
- unsigned int sourceLen,
- int small,
- int verbosity )
-{
- bz_stream strm;
- int ret;
-
- if (dest == NULL || destLen == NULL ||
- source == NULL ||
- (small != 0 && small != 1) ||
- verbosity < 0 || verbosity > 4)
- return BZ_PARAM_ERROR;
-
- strm.bzalloc = NULL;
- strm.bzfree = NULL;
- strm.opaque = NULL;
- ret = BZ2_bzDecompressInit ( &strm, verbosity, small );
- if (ret != BZ_OK) return ret;
-
- strm.next_in = source;
- strm.next_out = dest;
- strm.avail_in = sourceLen;
- strm.avail_out = *destLen;
-
- ret = BZ2_bzDecompress ( &strm );
- if (ret == BZ_OK) goto output_overflow_or_eof;
- if (ret != BZ_STREAM_END) goto errhandler;
-
- /* normal termination */
- *destLen -= strm.avail_out;
- BZ2_bzDecompressEnd ( &strm );
- return BZ_OK;
-
- output_overflow_or_eof:
- if (strm.avail_out > 0) {
- BZ2_bzDecompressEnd ( &strm );
- return BZ_UNEXPECTED_EOF;
- } else {
- BZ2_bzDecompressEnd ( &strm );
- return BZ_OUTBUFF_FULL;
- };
-
- errhandler:
- BZ2_bzDecompressEnd ( &strm );
- return ret;
-}
-
-
-/*---------------------------------------------------*/
-/*--
- Code contributed by Yoshioka Tsuneo
- (QWF00133 at niftyserve.or.jp/tsuneo-y at is.aist-nara.ac.jp),
- to support better zlib compatibility.
- This code is not _officially_ part of libbzip2 (yet);
- I haven't tested it, documented it, or considered the
- threading-safeness of it.
- If this code breaks, please contact both Yoshioka and me.
---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------------*/
-/*--
- return version like "0.9.0c".
---*/
-const char * BZ_API(BZ2_bzlibVersion)(void)
-{
- return BZ_VERSION;
-}
-
-
-#ifndef BZ_NO_STDIO
-/*---------------------------------------------------*/
-
-static
-BZFILE * bzopen_or_bzdopen
- ( const char *path, /* no use when bzdopen */
- int fd, /* no use when bzdopen */
- const char *mode,
- int open_mode) /* bzopen: 0, bzdopen:1 */
-{
- int bzerr;
- char unused[BZ_MAX_UNUSED];
- int blockSize100k = 9;
- int writing = 0;
- char mode2[10] = "";
- FILE *fp = NULL;
- BZFILE *bzfp = NULL;
- int verbosity = 0;
- int workFactor = 30;
- int smallMode = 0;
- int nUnused = 0;
-
- if (mode == NULL) return NULL;
- while (*mode) {
- switch (*mode) {
- case 'r':
- writing = 0; break;
- case 'w':
- writing = 1; break;
- case 's':
- smallMode = 1; break;
- default:
- if (isdigit((int)(*mode))) {
- blockSize100k = *mode-BZ_HDR_0;
- }
- }
- mode++;
- }
- strcat(mode2, writing ? "w" : "r" );
- strcat(mode2,"b"); /* binary mode */
-
- if (open_mode==0) {
- if (path==NULL || strcmp(path,"")==0) {
- fp = (writing ? stdout : stdin);
- } else {
- fp = fopen(path,mode2);
- }
- } else {
-#ifdef BZ_STRICT_ANSI
- fp = NULL;
-#else
- fp = fdopen(fd,mode2);
-#endif
- }
- if (fp == NULL) return NULL;
-
- if (writing) {
- /* Guard against total chaos and anarchy -- JRS */
- if (blockSize100k < 1) blockSize100k = 1;
- if (blockSize100k > 9) blockSize100k = 9;
- bzfp = BZ2_bzWriteOpen(&bzerr,fp,blockSize100k,
- verbosity,workFactor);
- } else {
- bzfp = BZ2_bzReadOpen(&bzerr,fp,verbosity,smallMode,
- unused,nUnused);
- }
- if (bzfp == NULL) {
- if (fp != stdin && fp != stdout) fclose(fp);
- return NULL;
- }
- return bzfp;
-}
-
-
-/*---------------------------------------------------*/
-/*--
- open file for read or write.
- ex) bzopen("file","w9")
- case path="" or NULL => use stdin or stdout.
---*/
-BZFILE * BZ_API(BZ2_bzopen)
- ( const char *path,
- const char *mode )
-{
- return bzopen_or_bzdopen(path,-1,mode,/*bzopen*/0);
-}
-
-
-/*---------------------------------------------------*/
-BZFILE * BZ_API(BZ2_bzdopen)
- ( int fd,
- const char *mode )
-{
- return bzopen_or_bzdopen(NULL,fd,mode,/*bzdopen*/1);
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzread) (BZFILE* b, void* buf, int len )
-{
- int bzerr, nread;
- if (((bzFile*)b)->lastErr == BZ_STREAM_END) return 0;
- nread = BZ2_bzRead(&bzerr,b,buf,len);
- if (bzerr == BZ_OK || bzerr == BZ_STREAM_END) {
- return nread;
- } else {
- return -1;
- }
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzwrite) (BZFILE* b, void* buf, int len )
-{
- int bzerr;
-
- BZ2_bzWrite(&bzerr,b,buf,len);
- if(bzerr == BZ_OK){
- return len;
- }else{
- return -1;
- }
-}
-
-
-/*---------------------------------------------------*/
-int BZ_API(BZ2_bzflush) (BZFILE *b)
-{
- /* do nothing now... */
- return 0;
-}
-
-
-/*---------------------------------------------------*/
-void BZ_API(BZ2_bzclose) (BZFILE* b)
-{
- int bzerr;
- FILE *fp = ((bzFile *)b)->handle;
-
- if (b==NULL) {return;}
- if(((bzFile*)b)->writing){
- BZ2_bzWriteClose(&bzerr,b,0,NULL,NULL);
- if(bzerr != BZ_OK){
- BZ2_bzWriteClose(NULL,b,1,NULL,NULL);
- }
- }else{
- BZ2_bzReadClose(&bzerr,b);
- }
- if(fp!=stdin && fp!=stdout){
- fclose(fp);
- }
-}
-
-
-/*---------------------------------------------------*/
-/*--
- return last error code
---*/
-static char *bzerrorstrings[] = {
- "OK"
- ,"SEQUENCE_ERROR"
- ,"PARAM_ERROR"
- ,"MEM_ERROR"
- ,"DATA_ERROR"
- ,"DATA_ERROR_MAGIC"
- ,"IO_ERROR"
- ,"UNEXPECTED_EOF"
- ,"OUTBUFF_FULL"
- ,"CONFIG_ERROR"
- ,"???" /* for future */
- ,"???" /* for future */
- ,"???" /* for future */
- ,"???" /* for future */
- ,"???" /* for future */
- ,"???" /* for future */
-};
-
-
-const char * BZ_API(BZ2_bzerror) (BZFILE *b, int *errnum)
-{
- int err = ((bzFile *)b)->lastErr;
-
- if(err>0) err = 0;
- *errnum = err;
- return bzerrorstrings[err*-1];
-}
-#endif
-
-
-/*-------------------------------------------------------------*/
-/*--- end bzlib.c ---*/
-/*-------------------------------------------------------------*/
-
-/*-----------------------------------------------------------*/
-/*--- A block-sorting, lossless compressor bzip2.c ---*/
-/*-----------------------------------------------------------*/
-
-
-
-/*----------------------------------------------------*/
-/*--- IMPORTANT ---*/
-/*----------------------------------------------------*/
-
-/*--
- WARNING:
- This program and library (attempts to) compress data by
- performing several non-trivial transformations on it.
- Unless you are 100% familiar with *all* the algorithms
- contained herein, and with the consequences of modifying them,
- you should NOT meddle with the compression or decompression
- machinery. Incorrect changes can and very likely *will*
- lead to disasterous loss of data.
-
- DISCLAIMER:
- I TAKE NO RESPONSIBILITY FOR ANY LOSS OF DATA ARISING FROM THE
- USE OF THIS PROGRAM, HOWSOEVER CAUSED.
-
- Every compression of a file implies an assumption that the
- compressed file can be decompressed to reproduce the original.
- Great efforts in design, coding and testing have been made to
- ensure that this program works correctly. However, the
- complexity of the algorithms, and, in particular, the presence
- of various special cases in the code which occur with very low
- but non-zero probability make it impossible to rule out the
- possibility of bugs remaining in the program. DO NOT COMPRESS
- ANY DATA WITH THIS PROGRAM AND/OR LIBRARY UNLESS YOU ARE PREPARED
- TO ACCEPT THE POSSIBILITY, HOWEVER SMALL, THAT THE DATA WILL
- NOT BE RECOVERABLE.
-
- That is not to say this program is inherently unreliable.
- Indeed, I very much hope the opposite is true. bzip2/libbzip2
- has been carefully constructed and extensively tested.
-
- PATENTS:
- To the best of my knowledge, bzip2/libbzip2 does not use any
- patented algorithms. However, I do not have the resources
- available to carry out a full patent search. Therefore I cannot
- give any guarantee of the above statement.
---*/
-
-
-
-/*----------------------------------------------------*/
-/*--- and now for something much more pleasant :-) ---*/
-/*----------------------------------------------------*/
-
-/*---------------------------------------------*/
-/*--
- Place a 1 beside your platform, and 0 elsewhere.
---*/
-
-/*--
- Generic 32-bit Unix.
- Also works on 64-bit Unix boxes.
- This is the default.
---*/
-#define BZ_UNIX 1
-
-/*--
- Win32, as seen by Jacob Navia's excellent
- port of (Chris Fraser & David Hanson)'s excellent
- lcc compiler. Or with MS Visual C.
- This is selected automatically if compiled by a compiler which
- defines _WIN32, not including the Cygwin GCC.
---*/
-#define BZ_LCCWIN32 0
-
-#if defined(_WIN32) && !defined(__CYGWIN__)
-#undef BZ_LCCWIN32
-#define BZ_LCCWIN32 1
-#undef BZ_UNIX
-#define BZ_UNIX 0
-#endif
-
-
-/*---------------------------------------------*/
-/*--
- Some stuff for all platforms.
---*/
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <signal.h>
-#include <math.h>
-#include <errno.h>
-#include <ctype.h>
-
-#define ERROR_IF_EOF(i) { if ((i) == EOF) ioError(); }
-#define ERROR_IF_NOT_ZERO(i) { if ((i) != 0) ioError(); }
-#define ERROR_IF_MINUS_ONE(i) { if ((i) == (-1)) ioError(); }
-
-
-/*---------------------------------------------*/
-/*--
- Platform-specific stuff.
---*/
-
-#if BZ_UNIX
-# include <fcntl.h>
-# include <sys/types.h>
-# include <utime.h>
-# include <unistd.h>
-# include <sys/stat.h>
-# include <sys/times.h>
-
-# define PATH_SEP '/'
-# define MY_LSTAT lstat
-# define MY_STAT stat
-# define MY_S_ISREG S_ISREG
-# define MY_S_ISDIR S_ISDIR
-
-# define APPEND_FILESPEC(root, name) \
- root=snocString((root), (name))
-
-# define APPEND_FLAG(root, name) \
- root=snocString((root), (name))
-
-# define SET_BINARY_MODE(fd) /**/
-
-# ifdef __GNUC__
-# define NORETURN __attribute__ ((noreturn))
-# else
-# define NORETURN /**/
-# endif
-
-# ifdef __DJGPP__
-# include <io.h>
-# include <fcntl.h>
-# undef MY_LSTAT
-# undef MY_STAT
-# define MY_LSTAT stat
-# define MY_STAT stat
-# undef SET_BINARY_MODE
-# define SET_BINARY_MODE(fd) \
- do { \
- int retVal = setmode ( fileno ( fd ), \
- O_BINARY ); \
- ERROR_IF_MINUS_ONE ( retVal ); \
- } while ( 0 )
-# endif
-
-# ifdef __CYGWIN__
-# include <io.h>
-# include <fcntl.h>
-# undef SET_BINARY_MODE
-# define SET_BINARY_MODE(fd) \
- do { \
- int retVal = setmode ( fileno ( fd ), \
- O_BINARY ); \
- ERROR_IF_MINUS_ONE ( retVal ); \
- } while ( 0 )
-# endif
-#endif /* BZ_UNIX */
-
-
-
-#if BZ_LCCWIN32
-# include <io.h>
-# include <fcntl.h>
-# include <sys\stat.h>
-
-# define NORETURN /**/
-# define PATH_SEP '\\'
-# define MY_LSTAT _stat
-# define MY_STAT _stat
-# define MY_S_ISREG(x) ((x) & _S_IFREG)
-# define MY_S_ISDIR(x) ((x) & _S_IFDIR)
-
-# define APPEND_FLAG(root, name) \
- root=snocString((root), (name))
-
-# define APPEND_FILESPEC(root, name) \
- root = snocString ((root), (name))
-
-# define SET_BINARY_MODE(fd) \
- do { \
- int retVal = setmode ( fileno ( fd ), \
- O_BINARY ); \
- ERROR_IF_MINUS_ONE ( retVal ); \
- } while ( 0 )
-
-#endif /* BZ_LCCWIN32 */
-
-
-/*---------------------------------------------*/
-/*--
- Some more stuff for all platforms :-)
---*/
-
-#define True ((Bool)1)
-#define False ((Bool)0)
-
-/*--
- IntNative is your platform's `native' int size.
- Only here to avoid probs with 64-bit platforms.
---*/
-typedef int IntNative;
-
-
-/*---------------------------------------------------*/
-/*--- Misc (file handling) data decls ---*/
-/*---------------------------------------------------*/
-
-Int32 verbosity;
-Bool keepInputFiles, smallMode, deleteOutputOnInterrupt;
-Bool forceOverwrite, testFailsExist, unzFailsExist, noisy;
-Int32 numFileNames, numFilesProcessed, blockSize100k;
-Int32 exitValue;
-
-/*-- source modes; F==file, I==stdin, O==stdout --*/
-#define SM_I2O 1
-#define SM_F2O 2
-#define SM_F2F 3
-
-/*-- operation modes --*/
-#define OM_Z 1
-#define OM_UNZ 2
-#define OM_TEST 3
-
-Int32 opMode;
-Int32 srcMode;
-
-#define FILE_NAME_LEN 1034
-
-Int32 longestFileName;
-Char inName [FILE_NAME_LEN];
-Char outName[FILE_NAME_LEN];
-Char tmpName[FILE_NAME_LEN];
-Char *progName;
-Char progNameReally[FILE_NAME_LEN];
-FILE *outputHandleJustInCase;
-Int32 workFactor;
-
-static void panic ( Char* ) NORETURN;
-static void ioError ( void ) NORETURN;
-static void outOfMemory ( void ) NORETURN;
-static void configError ( void ) NORETURN;
-static void crcError ( void ) NORETURN;
-static void cleanUpAndFail ( Int32 ) NORETURN;
-static void compressedStreamEOF ( void ) NORETURN;
-
-static void copyFileName ( Char*, Char* );
-static void* myMalloc ( Int32 );
-
-
-
-/*---------------------------------------------------*/
-/*--- An implementation of 64-bit ints. Sigh. ---*/
-/*--- Roll on widespread deployment of ANSI C9X ! ---*/
-/*---------------------------------------------------*/
-
-typedef
- struct { UChar b[8]; }
- UInt64;
-
-
-static
-void uInt64_from_UInt32s ( UInt64* n, UInt32 lo32, UInt32 hi32 )
-{
- n->b[7] = (UChar)((hi32 >> 24) & 0xFF);
- n->b[6] = (UChar)((hi32 >> 16) & 0xFF);
- n->b[5] = (UChar)((hi32 >> 8) & 0xFF);
- n->b[4] = (UChar) (hi32 & 0xFF);
- n->b[3] = (UChar)((lo32 >> 24) & 0xFF);
- n->b[2] = (UChar)((lo32 >> 16) & 0xFF);
- n->b[1] = (UChar)((lo32 >> 8) & 0xFF);
- n->b[0] = (UChar) (lo32 & 0xFF);
-}
-
-
-static
-double uInt64_to_double ( UInt64* n )
-{
- Int32 i;
- double base = 1.0;
- double sum = 0.0;
- for (i = 0; i < 8; i++) {
- sum += base * (double)(n->b[i]);
- base *= 256.0;
- }
- return sum;
-}
-
-
-static
-Bool uInt64_isZero ( UInt64* n )
-{
- Int32 i;
- for (i = 0; i < 8; i++)
- if (n->b[i] != 0) return 0;
- return 1;
-}
-
-
-/* Divide *n by 10, and return the remainder. */
-static
-Int32 uInt64_qrm10 ( UInt64* n )
-{
- UInt32 rem, tmp;
- Int32 i;
- rem = 0;
- for (i = 7; i >= 0; i--) {
- tmp = rem * 256 + n->b[i];
- n->b[i] = tmp / 10;
- rem = tmp % 10;
- }
- return rem;
-}
-
-
-/* ... and the Whole Entire Point of all this UInt64 stuff is
- so that we can supply the following function.
-*/
-static
-void uInt64_toAscii ( char* outbuf, UInt64* n )
-{
- Int32 i, q;
- UChar buf[32];
- Int32 nBuf = 0;
- UInt64 n_copy = *n;
- do {
- q = uInt64_qrm10 ( &n_copy );
- buf[nBuf] = q + '0';
- nBuf++;
- } while (!uInt64_isZero(&n_copy));
- outbuf[nBuf] = 0;
- for (i = 0; i < nBuf; i++)
- outbuf[i] = buf[nBuf-i-1];
-}
-
-
-/*---------------------------------------------------*/
-/*--- Processing of complete files and streams ---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------*/
-
-/*---------------------------------------------*/
-static
-void compressStream ( FILE *stream, FILE *zStream )
-{
- BZFILE* bzf = NULL;
- UChar ibuf[5000];
- Int32 nIbuf;
- UInt32 nbytes_in_lo32, nbytes_in_hi32;
- UInt32 nbytes_out_lo32, nbytes_out_hi32;
- Int32 bzerr, bzerr_dummy, ret;
-
- SET_BINARY_MODE(stream);
- SET_BINARY_MODE(zStream);
-
- if (ferror(stream)) goto errhandler_io;
- if (ferror(zStream)) goto errhandler_io;
-
- bzf = BZ2_bzWriteOpen ( &bzerr, zStream,
- blockSize100k, verbosity, workFactor );
- if (bzerr != BZ_OK) goto errhandler;
-
- if (verbosity >= 2) fprintf ( stderr, "\n" );
-
- while (True) {
-
- if (myfeof(stream)) break;
- nIbuf = fread ( ibuf, sizeof(UChar), 5000, stream );
- if (ferror(stream)) goto errhandler_io;
- if (nIbuf > 0) BZ2_bzWrite ( &bzerr, bzf, (void*)ibuf, nIbuf );
- if (bzerr != BZ_OK) goto errhandler;
-
- }
-
- BZ2_bzWriteClose64 ( &bzerr, bzf, 0,
- &nbytes_in_lo32, &nbytes_in_hi32,
- &nbytes_out_lo32, &nbytes_out_hi32 );
- if (bzerr != BZ_OK) goto errhandler;
-
- if (ferror(zStream)) goto errhandler_io;
- ret = fflush ( zStream );
- if (ret == EOF) goto errhandler_io;
- if (zStream != stdout) {
- ret = fclose ( zStream );
- outputHandleJustInCase = NULL;
- if (ret == EOF) goto errhandler_io;
- }
- outputHandleJustInCase = NULL;
- if (ferror(stream)) goto errhandler_io;
- ret = fclose ( stream );
- if (ret == EOF) goto errhandler_io;
-
- if (verbosity >= 1) {
- if (nbytes_in_lo32 == 0 && nbytes_in_hi32 == 0) {
- fprintf ( stderr, " no data compressed.\n");
- } else {
- Char buf_nin[32], buf_nout[32];
- UInt64 nbytes_in, nbytes_out;
- double nbytes_in_d, nbytes_out_d;
- uInt64_from_UInt32s ( &nbytes_in,
- nbytes_in_lo32, nbytes_in_hi32 );
- uInt64_from_UInt32s ( &nbytes_out,
- nbytes_out_lo32, nbytes_out_hi32 );
- nbytes_in_d = uInt64_to_double ( &nbytes_in );
- nbytes_out_d = uInt64_to_double ( &nbytes_out );
- uInt64_toAscii ( buf_nin, &nbytes_in );
- uInt64_toAscii ( buf_nout, &nbytes_out );
- fprintf ( stderr, "%6.3f:1, %6.3f bits/byte, "
- "%5.2f%% saved, %s in, %s out.\n",
- nbytes_in_d / nbytes_out_d,
- (8.0 * nbytes_out_d) / nbytes_in_d,
- 100.0 * (1.0 - nbytes_out_d / nbytes_in_d),
- buf_nin,
- buf_nout
- );
- }
- }
-
- return;
-
- errhandler:
- BZ2_bzWriteClose64 ( &bzerr_dummy, bzf, 1,
- &nbytes_in_lo32, &nbytes_in_hi32,
- &nbytes_out_lo32, &nbytes_out_hi32 );
- switch (bzerr) {
- case BZ_CONFIG_ERROR:
- configError(); break;
- case BZ_MEM_ERROR:
- outOfMemory (); break;
- case BZ_IO_ERROR:
- errhandler_io:
- ioError(); break;
- default:
- panic ( "compress:unexpected error" );
- }
-
- panic ( "compress:end" );
- /*notreached*/
-}
-
-
-
-/*---------------------------------------------*/
-static
-Bool uncompressStream ( FILE *zStream, FILE *stream )
-{
- BZFILE* bzf = NULL;
- Int32 bzerr, bzerr_dummy, ret, nread, streamNo, i;
- UChar obuf[5000];
- UChar unused[BZ_MAX_UNUSED];
- Int32 nUnused;
- UChar* unusedTmp;
-
- nUnused = 0;
- streamNo = 0;
-
- SET_BINARY_MODE(stream);
- SET_BINARY_MODE(zStream);
-
- if (ferror(stream)) goto errhandler_io;
- if (ferror(zStream)) goto errhandler_io;
-
- while (True) {
-
- bzf = BZ2_bzReadOpen (
- &bzerr, zStream, verbosity,
- (int)smallMode, unused, nUnused
- );
- if (bzf == NULL || bzerr != BZ_OK) goto errhandler;
- streamNo++;
-
- while (bzerr == BZ_OK) {
- nread = BZ2_bzRead ( &bzerr, bzf, obuf, 5000 );
- if (bzerr == BZ_DATA_ERROR_MAGIC) goto trycat;
- if ((bzerr == BZ_OK || bzerr == BZ_STREAM_END) && nread > 0)
- fwrite ( obuf, sizeof(UChar), nread, stream );
- if (ferror(stream)) goto errhandler_io;
- }
- if (bzerr != BZ_STREAM_END) goto errhandler;
-
- BZ2_bzReadGetUnused ( &bzerr, bzf, (void**)(&unusedTmp), &nUnused );
- if (bzerr != BZ_OK) panic ( "decompress:bzReadGetUnused" );
-
- for (i = 0; i < nUnused; i++) unused[i] = unusedTmp[i];
-
- BZ2_bzReadClose ( &bzerr, bzf );
- if (bzerr != BZ_OK) panic ( "decompress:bzReadGetUnused" );
-
- if (nUnused == 0 && myfeof(zStream)) break;
- }
-
- closeok:
- if (ferror(zStream)) goto errhandler_io;
- ret = fclose ( zStream );
- if (ret == EOF) goto errhandler_io;
-
- if (ferror(stream)) goto errhandler_io;
- ret = fflush ( stream );
- if (ret != 0) goto errhandler_io;
- if (stream != stdout) {
- ret = fclose ( stream );
- outputHandleJustInCase = NULL;
- if (ret == EOF) goto errhandler_io;
- }
- outputHandleJustInCase = NULL;
- if (verbosity >= 2) fprintf ( stderr, "\n " );
- return True;
-
- trycat:
- if (forceOverwrite) {
- rewind(zStream);
- while (True) {
- if (myfeof(zStream)) break;
- nread = fread ( obuf, sizeof(UChar), 5000, zStream );
- if (ferror(zStream)) goto errhandler_io;
- if (nread > 0) fwrite ( obuf, sizeof(UChar), nread, stream );
- if (ferror(stream)) goto errhandler_io;
- }
- goto closeok;
- }
-
- errhandler:
- BZ2_bzReadClose ( &bzerr_dummy, bzf );
- switch (bzerr) {
- case BZ_CONFIG_ERROR:
- configError(); break;
- case BZ_IO_ERROR:
- errhandler_io:
- ioError(); break;
- case BZ_DATA_ERROR:
- crcError();
- case BZ_MEM_ERROR:
- outOfMemory();
- case BZ_UNEXPECTED_EOF:
- compressedStreamEOF();
- case BZ_DATA_ERROR_MAGIC:
- if (zStream != stdin) fclose(zStream);
- if (stream != stdout) fclose(stream);
- if (streamNo == 1) {
- return False;
- } else {
- if (noisy)
- fprintf ( stderr,
- "\n%s: %s: trailing garbage after EOF ignored\n",
- progName, inName );
- return True;
- }
- default:
- panic ( "decompress:unexpected error" );
- }
-
- panic ( "decompress:end" );
- return True; /*notreached*/
-}
-
-
-/*---------------------------------------------*/
-static
-Bool testStream ( FILE *zStream )
-{
- BZFILE* bzf = NULL;
- Int32 bzerr, bzerr_dummy, ret, nread, streamNo, i;
- UChar obuf[5000];
- UChar unused[BZ_MAX_UNUSED];
- Int32 nUnused;
- UChar* unusedTmp;
-
- nUnused = 0;
- streamNo = 0;
-
- SET_BINARY_MODE(zStream);
- if (ferror(zStream)) goto errhandler_io;
-
- while (True) {
-
- bzf = BZ2_bzReadOpen (
- &bzerr, zStream, verbosity,
- (int)smallMode, unused, nUnused
- );
- if (bzf == NULL || bzerr != BZ_OK) goto errhandler;
- streamNo++;
-
- while (bzerr == BZ_OK) {
- nread = BZ2_bzRead ( &bzerr, bzf, obuf, 5000 );
- if (bzerr == BZ_DATA_ERROR_MAGIC) goto errhandler;
- }
- if (bzerr != BZ_STREAM_END) goto errhandler;
-
- BZ2_bzReadGetUnused ( &bzerr, bzf, (void**)(&unusedTmp), &nUnused );
- if (bzerr != BZ_OK) panic ( "test:bzReadGetUnused" );
-
- for (i = 0; i < nUnused; i++) unused[i] = unusedTmp[i];
-
- BZ2_bzReadClose ( &bzerr, bzf );
- if (bzerr != BZ_OK) panic ( "test:bzReadGetUnused" );
- if (nUnused == 0 && myfeof(zStream)) break;
-
- }
-
- if (ferror(zStream)) goto errhandler_io;
- ret = fclose ( zStream );
- if (ret == EOF) goto errhandler_io;
-
- if (verbosity >= 2) fprintf ( stderr, "\n " );
- return True;
-
- errhandler:
- BZ2_bzReadClose ( &bzerr_dummy, bzf );
- if (verbosity == 0)
- fprintf ( stderr, "%s: %s: ", progName, inName );
- switch (bzerr) {
- case BZ_CONFIG_ERROR:
- configError(); break;
- case BZ_IO_ERROR:
- errhandler_io:
- ioError(); break;
- case BZ_DATA_ERROR:
- fprintf ( stderr,
- "data integrity (CRC) error in data\n" );
- return False;
- case BZ_MEM_ERROR:
- outOfMemory();
- case BZ_UNEXPECTED_EOF:
- fprintf ( stderr,
- "file ends unexpectedly\n" );
- return False;
- case BZ_DATA_ERROR_MAGIC:
- if (zStream != stdin) fclose(zStream);
- if (streamNo == 1) {
- fprintf ( stderr,
- "bad magic number (file not created by bzip2)\n" );
- return False;
- } else {
- if (noisy)
- fprintf ( stderr,
- "trailing garbage after EOF ignored\n" );
- return True;
- }
- default:
- panic ( "test:unexpected error" );
- }
-
- panic ( "test:end" );
- return True; /*notreached*/
-}
-
-
-/*---------------------------------------------------*/
-/*--- Error [non-] handling grunge ---*/
-/*---------------------------------------------------*/
-
-/*---------------------------------------------*/
-static
-void setExit ( Int32 v )
-{
- if (v > exitValue) exitValue = v;
-}
-
-
-/*---------------------------------------------*/
-static
-void cadvise ( void )
-{
- if (noisy)
- fprintf (
- stderr,
- "\nIt is possible that the compressed file(s) have become corrupted.\n"
- "You can use the -tvv option to test integrity of such files.\n\n"
- "You can use the `bzip2recover' program to attempt to recover\n"
- "data from undamaged sections of corrupted files.\n\n"
- );
-}
-
-
-/*---------------------------------------------*/
-static
-void showFileNames ( void )
-{
- if (noisy)
- fprintf (
- stderr,
- "\tInput file = %s, output file = %s\n",
- inName, outName
- );
-}
-
-
-/*---------------------------------------------*/
-static
-void cleanUpAndFail ( Int32 ec )
-{
- IntNative retVal;
- struct MY_STAT statBuf;
-
- if ( srcMode == SM_F2F
- && opMode != OM_TEST
- && deleteOutputOnInterrupt ) {
-
- /* Check whether input file still exists. Delete output file
- only if input exists to avoid loss of data. Joerg Prante, 5
- January 2002. (JRS 06-Jan-2002: other changes in 1.0.2 mean
- this is less likely to happen. But to be ultra-paranoid, we
- do the check anyway.) */
- retVal = MY_STAT ( inName, &statBuf );
- if (retVal == 0) {
- if (noisy)
- fprintf ( stderr,
- "%s: Deleting output file %s, if it exists.\n",
- progName, outName );
- if (outputHandleJustInCase != NULL)
- fclose ( outputHandleJustInCase );
- retVal = remove ( outName );
- if (retVal != 0)
- fprintf ( stderr,
- "%s: WARNING: deletion of output file "
- "(apparently) failed.\n",
- progName );
- } else {
- fprintf ( stderr,
- "%s: WARNING: deletion of output file suppressed\n",
- progName );
- fprintf ( stderr,
- "%s: since input file no longer exists. Output file\n",
- progName );
- fprintf ( stderr,
- "%s: `%s' may be incomplete.\n",
- progName, outName );
- fprintf ( stderr,
- "%s: I suggest doing an integrity test (bzip2 -tv)"
- " of it.\n",
- progName );
- }
- }
-
- if (noisy && numFileNames > 0 && numFilesProcessed < numFileNames) {
- fprintf ( stderr,
- "%s: WARNING: some files have not been processed:\n"
- "%s: %d specified on command line, %d not processed yet.\n\n",
- progName, progName,
- numFileNames, numFileNames - numFilesProcessed );
- }
- setExit(ec);
- exit(exitValue);
-}
-
-
-/*---------------------------------------------*/
-static
-void panic ( Char* s )
-{
- fprintf ( stderr,
- "\n%s: PANIC -- internal consistency error:\n"
- "\t%s\n"
- "\tThis is a BUG. Please report it to me at:\n"
- "\tjseward at acm.org\n",
- progName, s );
- showFileNames();
- cleanUpAndFail( 3 );
-}
-
-
-/*---------------------------------------------*/
-static
-void crcError ( void )
-{
- fprintf ( stderr,
- "\n%s: Data integrity error when decompressing.\n",
- progName );
- showFileNames();
- cadvise();
- cleanUpAndFail( 2 );
-}
-
-
-/*---------------------------------------------*/
-static
-void compressedStreamEOF ( void )
-{
- if (noisy) {
- fprintf ( stderr,
- "\n%s: Compressed file ends unexpectedly;\n\t"
- "perhaps it is corrupted? *Possible* reason follows.\n",
- progName );
- perror ( progName );
- showFileNames();
- cadvise();
- }
- cleanUpAndFail( 2 );
-}
-
-
-/*---------------------------------------------*/
-static
-void ioError ( void )
-{
- fprintf ( stderr,
- "\n%s: I/O or other error, bailing out. "
- "Possible reason follows.\n",
- progName );
- perror ( progName );
- showFileNames();
- cleanUpAndFail( 1 );
-}
-
-
-/*---------------------------------------------*/
-static
-void mySignalCatcher ( IntNative n )
-{
- fprintf ( stderr,
- "\n%s: Control-C or similar caught, quitting.\n",
- progName );
- cleanUpAndFail(1);
-}
-
-
-/*---------------------------------------------*/
-static
-void mySIGSEGVorSIGBUScatcher ( IntNative n )
-{
- if (opMode == OM_Z)
- fprintf (
- stderr,
- "\n%s: Caught a SIGSEGV or SIGBUS whilst compressing.\n"
- "\n"
- " Possible causes are (most likely first):\n"
- " (1) This computer has unreliable memory or cache hardware\n"
- " (a surprisingly common problem; try a different machine.)\n"
- " (2) A bug in the compiler used to create this executable\n"
- " (unlikely, if you didn't compile bzip2 yourself.)\n"
- " (3) A real bug in bzip2 -- I hope this should never be the case.\n"
- " The user's manual, Section 4.3, has more info on (1) and (2).\n"
- " \n"
- " If you suspect this is a bug in bzip2, or are unsure about (1)\n"
- " or (2), feel free to report it to me at: jseward at acm.org.\n"
- " Section 4.3 of the user's manual describes the info a useful\n"
- " bug report should have. If the manual is available on your\n"
- " system, please try and read it before mailing me. If you don't\n"
- " have the manual or can't be bothered to read it, mail me anyway.\n"
- "\n",
- progName );
- else
- fprintf (
- stderr,
- "\n%s: Caught a SIGSEGV or SIGBUS whilst decompressing.\n"
- "\n"
- " Possible causes are (most likely first):\n"
- " (1) The compressed data is corrupted, and bzip2's usual checks\n"
- " failed to detect this. Try bzip2 -tvv my_file.bz2.\n"
- " (2) This computer has unreliable memory or cache hardware\n"
- " (a surprisingly common problem; try a different machine.)\n"
- " (3) A bug in the compiler used to create this executable\n"
- " (unlikely, if you didn't compile bzip2 yourself.)\n"
- " (4) A real bug in bzip2 -- I hope this should never be the case.\n"
- " The user's manual, Section 4.3, has more info on (2) and (3).\n"
- " \n"
- " If you suspect this is a bug in bzip2, or are unsure about (2)\n"
- " or (3), feel free to report it to me at: jseward at acm.org.\n"
- " Section 4.3 of the user's manual describes the info a useful\n"
- " bug report should have. If the manual is available on your\n"
- " system, please try and read it before mailing me. If you don't\n"
- " have the manual or can't be bothered to read it, mail me anyway.\n"
- "\n",
- progName );
-
- showFileNames();
- if (opMode == OM_Z)
- cleanUpAndFail( 3 ); else
- { cadvise(); cleanUpAndFail( 2 ); }
-}
-
-
-/*---------------------------------------------*/
-static
-void outOfMemory ( void )
-{
- fprintf ( stderr,
- "\n%s: couldn't allocate enough memory\n",
- progName );
- showFileNames();
- cleanUpAndFail(1);
-}
-
-
-/*---------------------------------------------*/
-static
-void configError ( void )
-{
- fprintf ( stderr,
- "bzip2: I'm not configured correctly for this platform!\n"
- "\tI require Int32, Int16 and Char to have sizes\n"
- "\tof 4, 2 and 1 bytes to run properly, and they don't.\n"
- "\tProbably you can fix this by defining them correctly,\n"
- "\tand recompiling. Bye!\n" );
- setExit(3);
- exit(exitValue);
-}
-
-
-/*---------------------------------------------------*/
-/*--- The main driver machinery ---*/
-/*---------------------------------------------------*/
-
-/* All rather crufty. The main problem is that input files
- are stat()d multiple times before use. This should be
- cleaned up.
-*/
-
-/*---------------------------------------------*/
-static
-void pad ( Char *s )
-{
- Int32 i;
- if ( (Int32)strlen(s) >= longestFileName ) return;
- for (i = 1; i <= longestFileName - (Int32)strlen(s); i++)
- fprintf ( stderr, " " );
-}
-
-
-/*---------------------------------------------*/
-static
-void copyFileName ( Char* to, Char* from )
-{
- if ( strlen(from) > FILE_NAME_LEN-10 ) {
- fprintf (
- stderr,
- "bzip2: file name\n`%s'\n"
- "is suspiciously (more than %d chars) long.\n"
- "Try using a reasonable file name instead. Sorry! :-)\n",
- from, FILE_NAME_LEN-10
- );
- setExit(1);
- exit(exitValue);
- }
-
- strncpy(to,from,FILE_NAME_LEN-10);
- to[FILE_NAME_LEN-10]='\0';
-}
-
-
-/*---------------------------------------------*/
-static
-Bool fileExists ( Char* name )
-{
- FILE *tmp = fopen ( name, "rb" );
- Bool exists = (tmp != NULL);
- if (tmp != NULL) fclose ( tmp );
- return exists;
-}
-
-
-/*---------------------------------------------*/
-/* Open an output file safely with O_EXCL and good permissions.
- This avoids a race condition in versions < 1.0.2, in which
- the file was first opened and then had its interim permissions
- set safely. We instead use open() to create the file with
- the interim permissions required. (--- --- rw-).
-
- For non-Unix platforms, if we are not worrying about
- security issues, simple this simply behaves like fopen.
-*/
-FILE* fopen_output_safely ( Char* name, const char* mode )
-{
-# if BZ_UNIX
- FILE* fp;
- IntNative fh;
- fh = open(name, O_WRONLY|O_CREAT|O_EXCL, S_IWUSR|S_IRUSR);
- if (fh == -1) return NULL;
- fp = fdopen(fh, mode);
- if (fp == NULL) close(fh);
- return fp;
-# else
- return fopen(name, mode);
-# endif
-}
-
-
-/*---------------------------------------------*/
-/*--
- if in doubt, return True
---*/
-static
-Bool notAStandardFile ( Char* name )
-{
- IntNative i;
- struct MY_STAT statBuf;
-
- i = MY_LSTAT ( name, &statBuf );
- if (i != 0) return True;
- if (MY_S_ISREG(statBuf.st_mode)) return False;
- return True;
-}
-
-
-/*---------------------------------------------*/
-/*--
- rac 11/21/98 see if file has hard links to it
---*/
-static
-Int32 countHardLinks ( Char* name )
-{
- IntNative i;
- struct MY_STAT statBuf;
-
- i = MY_LSTAT ( name, &statBuf );
- if (i != 0) return 0;
- return (statBuf.st_nlink - 1);
-}
-
-
-/*---------------------------------------------*/
-/* Copy modification date, access date, permissions and owner from the
- source to destination file. We have to copy this meta-info off
- into fileMetaInfo before starting to compress / decompress it,
- because doing it afterwards means we get the wrong access time.
-
- To complicate matters, in compress() and decompress() below, the
- sequence of tests preceding the call to saveInputFileMetaInfo()
- involves calling fileExists(), which in turn establishes its result
- by attempting to fopen() the file, and if successful, immediately
- fclose()ing it again. So we have to assume that the fopen() call
- does not cause the access time field to be updated.
-
- Reading of the man page for stat() (man 2 stat) on RedHat 7.2 seems
- to imply that merely doing open() will not affect the access time.
- Therefore we merely need to hope that the C library only does
- open() as a result of fopen(), and not any kind of read()-ahead
- cleverness.
-
- It sounds pretty fragile to me. Whether this carries across
- robustly to arbitrary Unix-like platforms (or even works robustly
- on this one, RedHat 7.2) is unknown to me. Nevertheless ...
-*/
-#if BZ_UNIX
-static
-struct MY_STAT fileMetaInfo;
-#endif
-
-static
-void saveInputFileMetaInfo ( Char *srcName )
-{
-# if BZ_UNIX
- IntNative retVal;
- /* Note use of stat here, not lstat. */
- retVal = MY_STAT( srcName, &fileMetaInfo );
- ERROR_IF_NOT_ZERO ( retVal );
-# endif
-}
-
-
-static
-void applySavedMetaInfoToOutputFile ( Char *dstName )
-{
-# if BZ_UNIX
- IntNative retVal;
- struct utimbuf uTimBuf;
-
- uTimBuf.actime = fileMetaInfo.st_atime;
- uTimBuf.modtime = fileMetaInfo.st_mtime;
-
- retVal = chmod ( dstName, fileMetaInfo.st_mode );
- ERROR_IF_NOT_ZERO ( retVal );
-
- retVal = utime ( dstName, &uTimBuf );
- ERROR_IF_NOT_ZERO ( retVal );
-
- retVal = chown ( dstName, fileMetaInfo.st_uid, fileMetaInfo.st_gid );
- /* chown() will in many cases return with EPERM, which can
- be safely ignored.
- */
-# endif
-}
-
-
-/*---------------------------------------------*/
-static
-Bool containsDubiousChars ( Char* name )
-{
-# if BZ_UNIX
- /* On unix, files can contain any characters and the file expansion
- * is performed by the shell.
- */
- return False;
-# else /* ! BZ_UNIX */
- /* On non-unix (Win* platforms), wildcard characters are not allowed in
- * filenames.
- */
- for (; *name != '\0'; name++)
- if (*name == '?' || *name == '*') return True;
- return False;
-# endif /* BZ_UNIX */
-}
-
-
-/*---------------------------------------------*/
-#define BZ_N_SUFFIX_PAIRS 4
-
-Char* zSuffix[BZ_N_SUFFIX_PAIRS]
- = { ".bz2", ".bz", ".tbz2", ".tbz" };
-Char* unzSuffix[BZ_N_SUFFIX_PAIRS]
- = { "", "", ".tar", ".tar" };
-
-static
-Bool hasSuffix ( Char* s, Char* suffix )
-{
- Int32 ns = strlen(s);
- Int32 nx = strlen(suffix);
- if (ns < nx) return False;
- if (strcmp(s + ns - nx, suffix) == 0) return True;
- return False;
-}
-
-static
-Bool mapSuffix ( Char* name,
- Char* oldSuffix, Char* newSuffix )
-{
- if (!hasSuffix(name,oldSuffix)) return False;
- name[strlen(name)-strlen(oldSuffix)] = 0;
- strcat ( name, newSuffix );
- return True;
-}
-
-
-/*---------------------------------------------*/
-static
-void compress ( Char *name )
-{
- FILE *inStr;
- FILE *outStr;
- Int32 n, i;
- struct MY_STAT statBuf;
-
- deleteOutputOnInterrupt = False;
-
- if (name == NULL && srcMode != SM_I2O)
- panic ( "compress: bad modes\n" );
-
- switch (srcMode) {
- case SM_I2O:
- copyFileName ( inName, "(stdin)" );
- copyFileName ( outName, "(stdout)" );
- break;
- case SM_F2F:
- copyFileName ( inName, name );
- copyFileName ( outName, name );
- strcat ( outName, ".bz2" );
- break;
- case SM_F2O:
- copyFileName ( inName, name );
- copyFileName ( outName, "(stdout)" );
- break;
- }
-
- if ( srcMode != SM_I2O && containsDubiousChars ( inName ) ) {
- if (noisy)
- fprintf ( stderr, "%s: There are no files matching `%s'.\n",
- progName, inName );
- setExit(1);
- return;
- }
- if ( srcMode != SM_I2O && !fileExists ( inName ) ) {
- fprintf ( stderr, "%s: Can't open input file %s: %s.\n",
- progName, inName, strerror(errno) );
- setExit(1);
- return;
- }
- for (i = 0; i < BZ_N_SUFFIX_PAIRS; i++) {
- if (hasSuffix(inName, zSuffix[i])) {
- if (noisy)
- fprintf ( stderr,
- "%s: Input file %s already has %s suffix.\n",
- progName, inName, zSuffix[i] );
- setExit(1);
- return;
- }
- }
- if ( srcMode == SM_F2F || srcMode == SM_F2O ) {
- MY_STAT(inName, &statBuf);
- if ( MY_S_ISDIR(statBuf.st_mode) ) {
- fprintf( stderr,
- "%s: Input file %s is a directory.\n",
- progName,inName);
- setExit(1);
- return;
- }
- }
- if ( srcMode == SM_F2F && !forceOverwrite && notAStandardFile ( inName )) {
- if (noisy)
- fprintf ( stderr, "%s: Input file %s is not a normal file.\n",
- progName, inName );
- setExit(1);
- return;
- }
- if ( srcMode == SM_F2F && fileExists ( outName ) ) {
- if (forceOverwrite) {
- remove(outName);
- } else {
- fprintf ( stderr, "%s: Output file %s already exists.\n",
- progName, outName );
- setExit(1);
- return;
- }
- }
- if ( srcMode == SM_F2F && !forceOverwrite &&
- (n=countHardLinks ( inName )) > 0) {
- fprintf ( stderr, "%s: Input file %s has %d other link%s.\n",
- progName, inName, n, n > 1 ? "s" : "" );
- setExit(1);
- return;
- }
-
- if ( srcMode == SM_F2F ) {
- /* Save the file's meta-info before we open it. Doing it later
- means we mess up the access times. */
- saveInputFileMetaInfo ( inName );
- }
-
- switch ( srcMode ) {
-
- case SM_I2O:
- inStr = stdin;
- outStr = stdout;
- if ( isatty ( fileno ( stdout ) ) ) {
- fprintf ( stderr,
- "%s: I won't write compressed data to a terminal.\n",
- progName );
- fprintf ( stderr, "%s: For help, type: `%s --help'.\n",
- progName, progName );
- setExit(1);
- return;
- };
- break;
-
- case SM_F2O:
- inStr = fopen ( inName, "rb" );
- outStr = stdout;
- if ( isatty ( fileno ( stdout ) ) ) {
- fprintf ( stderr,
- "%s: I won't write compressed data to a terminal.\n",
- progName );
- fprintf ( stderr, "%s: For help, type: `%s --help'.\n",
- progName, progName );
- if ( inStr != NULL ) fclose ( inStr );
- setExit(1);
- return;
- };
- if ( inStr == NULL ) {
- fprintf ( stderr, "%s: Can't open input file %s: %s.\n",
- progName, inName, strerror(errno) );
- setExit(1);
- return;
- };
- break;
-
- case SM_F2F:
- inStr = fopen ( inName, "rb" );
- outStr = fopen_output_safely ( outName, "wb" );
- if ( outStr == NULL) {
- fprintf ( stderr, "%s: Can't create output file %s: %s.\n",
- progName, outName, strerror(errno) );
- if ( inStr != NULL ) fclose ( inStr );
- setExit(1);
- return;
- }
- if ( inStr == NULL ) {
- fprintf ( stderr, "%s: Can't open input file %s: %s.\n",
- progName, inName, strerror(errno) );
- if ( outStr != NULL ) fclose ( outStr );
- setExit(1);
- return;
- };
- break;
-
- default:
- panic ( "compress: bad srcMode" );
- break;
- }
-
- if (verbosity >= 1) {
- fprintf ( stderr, " %s: ", inName );
- pad ( inName );
- fflush ( stderr );
- }
-
- /*--- Now the input and output handles are sane. Do the Biz. ---*/
- outputHandleJustInCase = outStr;
- deleteOutputOnInterrupt = True;
- compressStream ( inStr, outStr );
- outputHandleJustInCase = NULL;
-
- /*--- If there was an I/O error, we won't get here. ---*/
- if ( srcMode == SM_F2F ) {
- applySavedMetaInfoToOutputFile ( outName );
- deleteOutputOnInterrupt = False;
- if ( !keepInputFiles ) {
- IntNative retVal = remove ( inName );
- ERROR_IF_NOT_ZERO ( retVal );
- }
- }
-
- deleteOutputOnInterrupt = False;
-}
-
-
-/*---------------------------------------------*/
-static
-void uncompress ( Char *name )
-{
- FILE *inStr;
- FILE *outStr;
- Int32 n, i;
- Bool magicNumberOK;
- Bool cantGuess;
- struct MY_STAT statBuf;
-
- deleteOutputOnInterrupt = False;
-
- if (name == NULL && srcMode != SM_I2O)
- panic ( "uncompress: bad modes\n" );
-
- cantGuess = False;
- switch (srcMode) {
- case SM_I2O:
- copyFileName ( inName, "(stdin)" );
- copyFileName ( outName, "(stdout)" );
- break;
- case SM_F2F:
- copyFileName ( inName, name );
- copyFileName ( outName, name );
- for (i = 0; i < BZ_N_SUFFIX_PAIRS; i++)
- if (mapSuffix(outName,zSuffix[i],unzSuffix[i]))
- goto zzz;
- cantGuess = True;
- strcat ( outName, ".out" );
- break;
- case SM_F2O:
- copyFileName ( inName, name );
- copyFileName ( outName, "(stdout)" );
- break;
- }
-
- zzz:
- if ( srcMode != SM_I2O && containsDubiousChars ( inName ) ) {
- if (noisy)
- fprintf ( stderr, "%s: There are no files matching `%s'.\n",
- progName, inName );
- setExit(1);
- return;
- }
- if ( srcMode != SM_I2O && !fileExists ( inName ) ) {
- fprintf ( stderr, "%s: Can't open input file %s: %s.\n",
- progName, inName, strerror(errno) );
- setExit(1);
- return;
- }
- if ( srcMode == SM_F2F || srcMode == SM_F2O ) {
- MY_STAT(inName, &statBuf);
- if ( MY_S_ISDIR(statBuf.st_mode) ) {
- fprintf( stderr,
- "%s: Input file %s is a directory.\n",
- progName,inName);
- setExit(1);
- return;
- }
- }
- if ( srcMode == SM_F2F && !forceOverwrite && notAStandardFile ( inName )) {
- if (noisy)
- fprintf ( stderr, "%s: Input file %s is not a normal file.\n",
- progName, inName );
- setExit(1);
- return;
- }
- if ( /* srcMode == SM_F2F implied && */ cantGuess ) {
- if (noisy)
- fprintf ( stderr,
- "%s: Can't guess original name for %s -- using %s\n",
- progName, inName, outName );
- /* just a warning, no return */
- }
- if ( srcMode == SM_F2F && fileExists ( outName ) ) {
- if (forceOverwrite) {
- remove(outName);
- } else {
- fprintf ( stderr, "%s: Output file %s already exists.\n",
- progName, outName );
- setExit(1);
- return;
- }
- }
- if ( srcMode == SM_F2F && !forceOverwrite &&
- (n=countHardLinks ( inName ) ) > 0) {
- fprintf ( stderr, "%s: Input file %s has %d other link%s.\n",
- progName, inName, n, n > 1 ? "s" : "" );
- setExit(1);
- return;
- }
-
- if ( srcMode == SM_F2F ) {
- /* Save the file's meta-info before we open it. Doing it later
- means we mess up the access times. */
- saveInputFileMetaInfo ( inName );
- }
-
- switch ( srcMode ) {
-
- case SM_I2O:
- inStr = stdin;
- outStr = stdout;
- if ( isatty ( fileno ( stdin ) ) ) {
- fprintf ( stderr,
- "%s: I won't read compressed data from a terminal.\n",
- progName );
- fprintf ( stderr, "%s: For help, type: `%s --help'.\n",
- progName, progName );
- setExit(1);
- return;
- };
- break;
-
- case SM_F2O:
- inStr = fopen ( inName, "rb" );
- outStr = stdout;
- if ( inStr == NULL ) {
- fprintf ( stderr, "%s: Can't open input file %s:%s.\n",
- progName, inName, strerror(errno) );
- if ( inStr != NULL ) fclose ( inStr );
- setExit(1);
- return;
- };
- break;
-
- case SM_F2F:
- inStr = fopen ( inName, "rb" );
- outStr = fopen_output_safely ( outName, "wb" );
- if ( outStr == NULL) {
- fprintf ( stderr, "%s: Can't create output file %s: %s.\n",
- progName, outName, strerror(errno) );
- if ( inStr != NULL ) fclose ( inStr );
- setExit(1);
- return;
- }
- if ( inStr == NULL ) {
- fprintf ( stderr, "%s: Can't open input file %s: %s.\n",
- progName, inName, strerror(errno) );
- if ( outStr != NULL ) fclose ( outStr );
- setExit(1);
- return;
- };
- break;
-
- default:
- panic ( "uncompress: bad srcMode" );
- break;
- }
-
- if (verbosity >= 1) {
- fprintf ( stderr, " %s: ", inName );
- pad ( inName );
- fflush ( stderr );
- }
-
- /*--- Now the input and output handles are sane. Do the Biz. ---*/
- outputHandleJustInCase = outStr;
- deleteOutputOnInterrupt = True;
- magicNumberOK = uncompressStream ( inStr, outStr );
- outputHandleJustInCase = NULL;
-
- /*--- If there was an I/O error, we won't get here. ---*/
- if ( magicNumberOK ) {
- if ( srcMode == SM_F2F ) {
- applySavedMetaInfoToOutputFile ( outName );
- deleteOutputOnInterrupt = False;
- if ( !keepInputFiles ) {
- IntNative retVal = remove ( inName );
- ERROR_IF_NOT_ZERO ( retVal );
- }
- }
- } else {
- unzFailsExist = True;
- deleteOutputOnInterrupt = False;
- if ( srcMode == SM_F2F ) {
- IntNative retVal = remove ( outName );
- ERROR_IF_NOT_ZERO ( retVal );
- }
- }
- deleteOutputOnInterrupt = False;
-
- if ( magicNumberOK ) {
- if (verbosity >= 1)
- fprintf ( stderr, "done\n" );
- } else {
- setExit(2);
- if (verbosity >= 1)
- fprintf ( stderr, "not a bzip2 file.\n" ); else
- fprintf ( stderr,
- "%s: %s is not a bzip2 file.\n",
- progName, inName );
- }
-
-}
-
-
-/*---------------------------------------------*/
-static
-void testf ( Char *name )
-{
- FILE *inStr;
- Bool allOK;
- struct MY_STAT statBuf;
-
- deleteOutputOnInterrupt = False;
-
- if (name == NULL && srcMode != SM_I2O)
- panic ( "testf: bad modes\n" );
-
- copyFileName ( outName, "(none)" );
- switch (srcMode) {
- case SM_I2O: copyFileName ( inName, "(stdin)" ); break;
- case SM_F2F: copyFileName ( inName, name ); break;
- case SM_F2O: copyFileName ( inName, name ); break;
- }
-
- if ( srcMode != SM_I2O && containsDubiousChars ( inName ) ) {
- if (noisy)
- fprintf ( stderr, "%s: There are no files matching `%s'.\n",
- progName, inName );
- setExit(1);
- return;
- }
- if ( srcMode != SM_I2O && !fileExists ( inName ) ) {
- fprintf ( stderr, "%s: Can't open input %s: %s.\n",
- progName, inName, strerror(errno) );
- setExit(1);
- return;
- }
- if ( srcMode != SM_I2O ) {
- MY_STAT(inName, &statBuf);
- if ( MY_S_ISDIR(statBuf.st_mode) ) {
- fprintf( stderr,
- "%s: Input file %s is a directory.\n",
- progName,inName);
- setExit(1);
- return;
- }
- }
-
- switch ( srcMode ) {
-
- case SM_I2O:
- if ( isatty ( fileno ( stdin ) ) ) {
- fprintf ( stderr,
- "%s: I won't read compressed data from a terminal.\n",
- progName );
- fprintf ( stderr, "%s: For help, type: `%s --help'.\n",
- progName, progName );
- setExit(1);
- return;
- };
- inStr = stdin;
- break;
-
- case SM_F2O: case SM_F2F:
- inStr = fopen ( inName, "rb" );
- if ( inStr == NULL ) {
- fprintf ( stderr, "%s: Can't open input file %s:%s.\n",
- progName, inName, strerror(errno) );
- setExit(1);
- return;
- };
- break;
-
- default:
- panic ( "testf: bad srcMode" );
- break;
- }
-
- if (verbosity >= 1) {
- fprintf ( stderr, " %s: ", inName );
- pad ( inName );
- fflush ( stderr );
- }
-
- /*--- Now the input handle is sane. Do the Biz. ---*/
- outputHandleJustInCase = NULL;
- allOK = testStream ( inStr );
-
- if (allOK && verbosity >= 1) fprintf ( stderr, "ok\n" );
- if (!allOK) testFailsExist = True;
-}
-
-
-/*---------------------------------------------*/
-static
-void license ( void )
-{
- fprintf ( stderr,
-
- "bzip2, a block-sorting file compressor. "
- "Version %s.\n"
- " \n"
- " Copyright (C) 1996-2002 by Julian Seward.\n"
- " \n"
- " This program is free software; you can redistribute it and/or modify\n"
- " it under the terms set out in the LICENSE file, which is included\n"
- " in the bzip2-1.0 source distribution.\n"
- " \n"
- " This program is distributed in the hope that it will be useful,\n"
- " but WITHOUT ANY WARRANTY; without even the implied warranty of\n"
- " MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n"
- " LICENSE file for more details.\n"
- " \n",
- BZ2_bzlibVersion()
- );
-}
-
-
-/*---------------------------------------------*/
-static
-void usage ( Char *fullProgName )
-{
- fprintf (
- stderr,
- "bzip2, a block-sorting file compressor. "
- "Version %s.\n"
- "\n usage: %s [flags and input files in any order]\n"
- "\n"
- " -h --help print this message\n"
- " -d --decompress force decompression\n"
- " -z --compress force compression\n"
- " -k --keep keep (don't delete) input files\n"
- " -f --force overwrite existing output files\n"
- " -t --test test compressed file integrity\n"
- " -c --stdout output to standard out\n"
- " -q --quiet suppress noncritical error messages\n"
- " -v --verbose be verbose (a 2nd -v gives more)\n"
- " -L --license display software version & license\n"
- " -V --version display software version & license\n"
- " -s --small use less memory (at most 2500k)\n"
- " -1 .. -9 set block size to 100k .. 900k\n"
- " --fast alias for -1\n"
- " --best alias for -9\n"
- "\n"
- " If invoked as `bzip2', default action is to compress.\n"
- " as `bunzip2', default action is to decompress.\n"
- " as `bzcat', default action is to decompress to stdout.\n"
- "\n"
- " If no file names are given, bzip2 compresses or decompresses\n"
- " from standard input to standard output. You can combine\n"
- " short flags, so `-v -4' means the same as -v4 or -4v, &c.\n"
-# if BZ_UNIX
- "\n"
-# endif
- ,
-
- BZ2_bzlibVersion(),
- fullProgName
- );
-}
-
-
-/*---------------------------------------------*/
-static
-void redundant ( Char* flag )
-{
- fprintf (
- stderr,
- "%s: %s is redundant in versions 0.9.5 and above\n",
- progName, flag );
-}
-
-
-/*---------------------------------------------*/
-/*--
- All the garbage from here to main() is purely to
- implement a linked list of command-line arguments,
- into which main() copies argv[1 .. argc-1].
-
- The purpose of this exercise is to facilitate
- the expansion of wildcard characters * and ? in
- filenames for OSs which don't know how to do it
- themselves, like MSDOS, Windows 95 and NT.
-
- The actual Dirty Work is done by the platform-
- specific macro APPEND_FILESPEC.
---*/
-
-typedef
- struct zzzz {
- Char *name;
- struct zzzz *link;
- }
- Cell;
-
-
-/*---------------------------------------------*/
-static
-void *myMalloc ( Int32 n )
-{
- void* p;
-
- p = malloc ( (size_t)n );
- if (p == NULL) outOfMemory ();
- return p;
-}
-
-
-/*---------------------------------------------*/
-static
-Cell *mkCell ( void )
-{
- Cell *c;
-
- c = (Cell*) myMalloc ( sizeof ( Cell ) );
- c->name = NULL;
- c->link = NULL;
- return c;
-}
-
-
-/*---------------------------------------------*/
-static
-Cell *snocString ( Cell *root, Char *name )
-{
- if (root == NULL) {
- Cell *tmp = mkCell();
- tmp->name = (Char*) myMalloc ( 5 + strlen(name) );
- strcpy ( tmp->name, name );
- return tmp;
- } else {
- Cell *tmp = root;
- while (tmp->link != NULL) tmp = tmp->link;
- tmp->link = snocString ( tmp->link, name );
- return root;
- }
-}
-
-
-/*---------------------------------------------*/
-static
-void addFlagsFromEnvVar ( Cell** argList, Char* varName )
-{
- Int32 i, j, k;
- Char *envbase, *p;
-
- envbase = getenv(varName);
- if (envbase != NULL) {
- p = envbase;
- i = 0;
- while (True) {
- if (p[i] == 0) break;
- p += i;
- i = 0;
- while (isspace((Int32)(p[0]))) p++;
- while (p[i] != 0 && !isspace((Int32)(p[i]))) i++;
- if (i > 0) {
- k = i; if (k > FILE_NAME_LEN-10) k = FILE_NAME_LEN-10;
- for (j = 0; j < k; j++) tmpName[j] = p[j];
- tmpName[k] = 0;
- APPEND_FLAG(*argList, tmpName);
- }
- }
- }
-}
-
-
-/*---------------------------------------------*/
-#define ISFLAG(s) (strcmp(aa->name, (s))==0)
-
-IntNative main ( IntNative argc, Char *argv[] )
-{
- Int32 i, j;
- Char *tmp;
- Cell *argList;
- Cell *aa;
- Bool decode;
-
- /*-- Be really really really paranoid :-) --*/
- if (sizeof(Int32) != 4 || sizeof(UInt32) != 4 ||
- sizeof(Int16) != 2 || sizeof(UInt16) != 2 ||
- sizeof(Char) != 1 || sizeof(UChar) != 1)
- configError();
-
- /*-- Initialise --*/
- outputHandleJustInCase = NULL;
- smallMode = False;
- keepInputFiles = False;
- forceOverwrite = False;
- noisy = True;
- verbosity = 0;
- blockSize100k = 9;
- testFailsExist = False;
- unzFailsExist = False;
- numFileNames = 0;
- numFilesProcessed = 0;
- workFactor = 30;
- deleteOutputOnInterrupt = False;
- exitValue = 0;
- i = j = 0; /* avoid bogus warning from egcs-1.1.X */
-
- /*-- Set up signal handlers for mem access errors --*/
- signal (SIGSEGV, mySIGSEGVorSIGBUScatcher);
-# if BZ_UNIX
-# ifndef __DJGPP__
- signal (SIGBUS, mySIGSEGVorSIGBUScatcher);
-# endif
-# endif
-
- copyFileName ( inName, "(none)" );
- copyFileName ( outName, "(none)" );
-
- copyFileName ( progNameReally, argv[0] );
- progName = &progNameReally[0];
- for (tmp = &progNameReally[0]; *tmp != '\0'; tmp++)
- if (*tmp == PATH_SEP) progName = tmp + 1;
-
-
- /*-- Copy flags from env var BZIP2, and
- expand filename wildcards in arg list.
- --*/
- argList = NULL;
- addFlagsFromEnvVar ( &argList, "BZIP2" );
- addFlagsFromEnvVar ( &argList, "BZIP" );
- for (i = 1; i <= argc-1; i++)
- APPEND_FILESPEC(argList, argv[i]);
-
-
- /*-- Find the length of the longest filename --*/
- longestFileName = 7;
- numFileNames = 0;
- decode = True;
- for (aa = argList; aa != NULL; aa = aa->link) {
- if (ISFLAG("--")) { decode = False; continue; }
- if (aa->name[0] == '-' && decode) continue;
- numFileNames++;
- if (longestFileName < (Int32)strlen(aa->name) )
- longestFileName = (Int32)strlen(aa->name);
- }
-
-
- /*-- Determine source modes; flag handling may change this too. --*/
- if (numFileNames == 0)
- srcMode = SM_I2O; else srcMode = SM_F2F;
-
-
- /*-- Determine what to do (compress/uncompress/test/cat). --*/
- /*-- Note that subsequent flag handling may change this. --*/
- opMode = OM_Z;
-
- if ( (strstr ( progName, "unzip" ) != 0) ||
- (strstr ( progName, "UNZIP" ) != 0) )
- opMode = OM_UNZ;
-
- if ( (strstr ( progName, "z2cat" ) != 0) ||
- (strstr ( progName, "Z2CAT" ) != 0) ||
- (strstr ( progName, "zcat" ) != 0) ||
- (strstr ( progName, "ZCAT" ) != 0) ) {
- opMode = OM_UNZ;
- srcMode = (numFileNames == 0) ? SM_I2O : SM_F2O;
- }
-
-
- /*-- Look at the flags. --*/
- for (aa = argList; aa != NULL; aa = aa->link) {
- if (ISFLAG("--")) break;
- if (aa->name[0] == '-' && aa->name[1] != '-') {
- for (j = 1; aa->name[j] != '\0'; j++) {
- switch (aa->name[j]) {
- case 'c': srcMode = SM_F2O; break;
- case 'd': opMode = OM_UNZ; break;
- case 'z': opMode = OM_Z; break;
- case 'f': forceOverwrite = True; break;
- case 't': opMode = OM_TEST; break;
- case 'k': keepInputFiles = True; break;
- case 's': smallMode = True; break;
- case 'q': noisy = False; break;
- case '1': blockSize100k = 1; break;
- case '2': blockSize100k = 2; break;
- case '3': blockSize100k = 3; break;
- case '4': blockSize100k = 4; break;
- case '5': blockSize100k = 5; break;
- case '6': blockSize100k = 6; break;
- case '7': blockSize100k = 7; break;
- case '8': blockSize100k = 8; break;
- case '9': blockSize100k = 9; break;
- case 'V':
- case 'L': license(); break;
- case 'v': verbosity++; break;
- case 'h': usage ( progName );
- exit ( 0 );
- break;
- default: fprintf ( stderr, "%s: Bad flag `%s'\n",
- progName, aa->name );
- usage ( progName );
- exit ( 1 );
- break;
- }
- }
- }
- }
-
- /*-- And again ... --*/
- for (aa = argList; aa != NULL; aa = aa->link) {
- if (ISFLAG("--")) break;
- if (ISFLAG("--stdout")) srcMode = SM_F2O; else
- if (ISFLAG("--decompress")) opMode = OM_UNZ; else
- if (ISFLAG("--compress")) opMode = OM_Z; else
- if (ISFLAG("--force")) forceOverwrite = True; else
- if (ISFLAG("--test")) opMode = OM_TEST; else
- if (ISFLAG("--keep")) keepInputFiles = True; else
- if (ISFLAG("--small")) smallMode = True; else
- if (ISFLAG("--quiet")) noisy = False; else
- if (ISFLAG("--version")) license(); else
- if (ISFLAG("--license")) license(); else
- if (ISFLAG("--exponential")) workFactor = 1; else
- if (ISFLAG("--repetitive-best")) redundant(aa->name); else
- if (ISFLAG("--repetitive-fast")) redundant(aa->name); else
- if (ISFLAG("--fast")) blockSize100k = 1; else
- if (ISFLAG("--best")) blockSize100k = 9; else
- if (ISFLAG("--verbose")) verbosity++; else
- if (ISFLAG("--help")) { usage ( progName ); exit ( 0 ); }
- else
- if (strncmp ( aa->name, "--", 2) == 0) {
- fprintf ( stderr, "%s: Bad flag `%s'\n", progName, aa->name );
- usage ( progName );
- exit ( 1 );
- }
- }
-
- if (verbosity > 4) verbosity = 4;
- if (opMode == OM_Z && smallMode && blockSize100k > 2)
- blockSize100k = 2;
-
- if (opMode == OM_TEST && srcMode == SM_F2O) {
- fprintf ( stderr, "%s: -c and -t cannot be used together.\n",
- progName );
- exit ( 1 );
- }
-
- if (srcMode == SM_F2O && numFileNames == 0)
- srcMode = SM_I2O;
-
- if (opMode != OM_Z) blockSize100k = 0;
-
- if (srcMode == SM_F2F) {
- signal (SIGINT, mySignalCatcher);
- signal (SIGTERM, mySignalCatcher);
-# if BZ_UNIX
- signal (SIGHUP, mySignalCatcher);
-# endif
- }
-
- if (opMode == OM_Z) {
- if (srcMode == SM_I2O) {
- compress ( NULL );
- } else {
- decode = True;
- for (aa = argList; aa != NULL; aa = aa->link) {
- if (ISFLAG("--")) { decode = False; continue; }
- if (aa->name[0] == '-' && decode) continue;
- numFilesProcessed++;
- compress ( aa->name );
- }
- }
- }
- else
-
- if (opMode == OM_UNZ) {
- unzFailsExist = False;
- if (srcMode == SM_I2O) {
- uncompress ( NULL );
- } else {
- decode = True;
- for (aa = argList; aa != NULL; aa = aa->link) {
- if (ISFLAG("--")) { decode = False; continue; }
- if (aa->name[0] == '-' && decode) continue;
- numFilesProcessed++;
- uncompress ( aa->name );
- }
- }
- if (unzFailsExist) {
- setExit(2);
- exit(exitValue);
- }
- }
-
- else {
- testFailsExist = False;
- if (srcMode == SM_I2O) {
- testf ( NULL );
- } else {
- decode = True;
- for (aa = argList; aa != NULL; aa = aa->link) {
- if (ISFLAG("--")) { decode = False; continue; }
- if (aa->name[0] == '-' && decode) continue;
- numFilesProcessed++;
- testf ( aa->name );
- }
- }
- if (testFailsExist && noisy) {
- fprintf ( stderr,
- "\n"
- "You can use the `bzip2recover' program to attempt to recover\n"
- "data from undamaged sections of corrupted files.\n\n"
- );
- setExit(2);
- exit(exitValue);
- }
- }
-
- /* Free the argument list memory to mollify leak detectors
- (eg) Purify, Checker. Serves no other useful purpose.
- */
- aa = argList;
- while (aa != NULL) {
- Cell* aa2 = aa->link;
- if (aa->name != NULL) free(aa->name);
- free(aa);
- aa = aa2;
- }
-
- return exitValue;
-}
-
-
-/*-----------------------------------------------------------*/
-/*--- end bzip2.c ---*/
-/*-----------------------------------------------------------*/
Removed: dragonegg/trunk/test/compilator/local/gzip.c
URL: http://llvm.org/viewvc/llvm-project/dragonegg/trunk/test/compilator/local/gzip.c?rev=152714&view=auto
==============================================================================
--- dragonegg/trunk/test/compilator/local/gzip.c (original)
+++ dragonegg/trunk/test/compilator/local/gzip.c (removed)
@@ -1,8606 +0,0 @@
-#include <ctype.h>
-#include <dirent.h>
-#include <errno.h>
-#include <fcntl.h>
-#include <limits.h>
-#include <malloc.h>
-#include <memory.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/dir.h>
-#include <sys/file.h>
-#include <sys/stat.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <time.h>
-#include <unistd.h>
-#include <utime.h>
-
-#define HAVE_CONFIG_H 1
-
-/* config.h. Generated by configure. */
-/* config.h.in. Generated from configure.in by autoheader. */
-
-/* Define if an assembler version of longest_match is available. */
-/* #undef ASMV */
-
-/* Define to 1 if you have the <dirent.h> header file, and it defines `DIR'.
- */
-#define HAVE_DIRENT_H 1
-
-/* Define to 1 if you have the <fcntl.h> header file. */
-#define HAVE_FCNTL_H 1
-
-/* Define to 1 if you have the <inttypes.h> header file. */
-#define HAVE_INTTYPES_H 1
-
-/* Define to 1 if you have the <limits.h> header file. */
-#define HAVE_LIMITS_H 1
-
-/* Define to 1 if you have the `lstat' function. */
-#define HAVE_LSTAT 1
-
-/* Define to 1 if you have the <memory.h> header file. */
-#define HAVE_MEMORY_H 1
-
-/* Define to 1 if you have the <ndir.h> header file, and it defines `DIR'. */
-/* #undef HAVE_NDIR_H */
-
-/* Define to 1 if you have the `rpmatch' function. */
-/* #undef HAVE_RPMATCH */
-
-/* Define to 1 if you have the <stdint.h> header file. */
-#define HAVE_STDINT_H 1
-
-/* Define to 1 if you have the <stdlib.h> header file. */
-#define HAVE_STDLIB_H 1
-
-/* Define to 1 if you have the <strings.h> header file. */
-#define HAVE_STRINGS_H 1
-
-/* Define to 1 if you have the <string.h> header file. */
-#define HAVE_STRING_H 1
-
-/* Define to 1 if you have the <sys/dir.h> header file, and it defines `DIR'.
- */
-/* #undef HAVE_SYS_DIR_H */
-
-/* Define to 1 if you have the <sys/ndir.h> header file, and it defines `DIR'.
- */
-/* #undef HAVE_SYS_NDIR_H */
-
-/* Define to 1 if you have the <sys/stat.h> header file. */
-#define HAVE_SYS_STAT_H 1
-
-/* Define to 1 if you have the <sys/types.h> header file. */
-#define HAVE_SYS_TYPES_H 1
-
-/* Define to 1 if you have the <sys/utime.h> header file. */
-/* #undef HAVE_SYS_UTIME_H */
-
-/* Define to 1 if you have the <time.h> header file. */
-#define HAVE_TIME_H 1
-
-/* Define to 1 if you have the <unistd.h> header file. */
-#define HAVE_UNISTD_H 1
-
-/* Define to 1 if you have the `utime' function. */
-#define HAVE_UTIME 1
-
-/* Define to 1 if you have the <utime.h> header file. */
-#define HAVE_UTIME_H 1
-
-/* Name of package */
-#define PACKAGE "gzip"
-
-/* Define to the address where bug reports for this package should be sent. */
-#define PACKAGE_BUGREPORT "bug-gzip at gnu.org"
-
-/* Define to the full name of this package. */
-#define PACKAGE_NAME "gzip"
-
-/* Define to the full name and version of this package. */
-#define PACKAGE_STRING "gzip 1.3.5"
-
-/* Define to the one symbol short name of this package. */
-#define PACKAGE_TARNAME "gzip"
-
-/* Define to the version of this package. */
-#define PACKAGE_VERSION "1.3.5"
-
-/* Define as the return type of signal handlers (`int' or `void'). */
-#define RETSIGTYPE void
-
-/* Define to 1 if you have the ANSI C header files. */
-#define STDC_HEADERS 1
-
-/* Version number of package */
-#define VERSION "1.3.5"
-
-/* Define to 1 if on AIX 3.
- System headers sometimes define this.
- We just want to avoid a redefinition error message. */
-#ifndef _ALL_SOURCE
-/* # undef _ALL_SOURCE */
-#endif
-
-/* Number of bits in a file offset, on hosts where this is settable. */
-#define _FILE_OFFSET_BITS 64
-
-/* Enable GNU extensions on systems that have them. */
-#ifndef _GNU_SOURCE
-# define _GNU_SOURCE 1
-#endif
-
-/* Define for large files, on AIX-style hosts. */
-/* #undef _LARGE_FILES */
-
-/* Define to 1 if on MINIX. */
-/* #undef _MINIX */
-
-/* Define to 2 if the system does not provide POSIX.1 features except with
- this defined. */
-/* #undef _POSIX_1_SOURCE */
-
-/* Define to 1 if you need to in order for `stat' and other things to work. */
-/* #undef _POSIX_SOURCE */
-
-/* Define to empty if `const' does not conform to ANSI C. */
-/* #undef const */
-
-/* Define to `long' if <sys/types.h> does not define. */
-/* #undef off_t */
-
-/* Define to `unsigned' if <sys/types.h> does not define. */
-/* #undef size_t */
-
-
-/* bits.c -- output variable-length bit strings
- * 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.
- */
-
-
-/*
- * PURPOSE
- *
- * Output variable-length bit strings. Compression can be done
- * to a file or to memory. (The latter is not supported in this version.)
- *
- * DISCUSSION
- *
- * The PKZIP "deflate" file format interprets compressed file data
- * as a sequence of bits. Multi-bit strings in the file may cross
- * byte boundaries without restriction.
- *
- * The first bit of each byte is the low-order bit.
- *
- * The routines in this file allow a variable-length bit value to
- * be output right-to-left (useful for literal values). For
- * left-to-right output (useful for code strings from the tree routines),
- * the bits must have been reversed first with bi_reverse().
- *
- * For in-memory compression, the compressed bit stream goes directly
- * into the requested output buffer. The input data is read in blocks
- * by the mem_read() function. The buffer is limited to 64K on 16 bit
- * machines.
- *
- * INTERFACE
- *
- * void bi_init (FILE *zipfile)
- * Initialize the bit string routines.
- *
- * void send_bits (int value, int length)
- * Write out a bit string, taking the source bits right to
- * left.
- *
- * int bi_reverse (int value, int length)
- * Reverse the bits of a bit string, taking the source bits left to
- * right and emitting them right to left.
- *
- * void bi_windup (void)
- * Write out any remaining bits in an incomplete byte.
- *
- * void copy_block(char *buf, unsigned len, int header)
- * Copy a stored block to the zip file, storing first the length and
- * its one's complement if requested.
- *
- */
-
-/* tailor.h -- target dependent definitions
- * 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.
- */
-
-/* The target dependent definitions should be defined here only.
- * The target dependent functions should be defined in tailor.c.
- */
-
-/* $Id: tailor.h,v 0.18 1993/06/14 19:32:20 jloup Exp $ */
-
-#if defined(__MSDOS__) && !defined(MSDOS)
-# define MSDOS
-#endif
-
-#if defined(__OS2__) && !defined(OS2)
-# define OS2
-#endif
-
-#if defined(OS2) && defined(MSDOS) /* MS C under OS/2 */
-# undef MSDOS
-#endif
-
-#if defined(ATARI) || defined(atarist)
-# ifndef STDC_HEADERS
-# define STDC_HEADERS
-# define HAVE_UNISTD_H
-# define HAVE_DIRENT_H
-# endif
-# define ASMV
-# define OS_CODE 0x05
-# ifdef TOSFS
-# define PATH_SEP2 '\\'
-# define PATH_SEP3 ':'
-# define MAX_PATH_LEN 128
-# define NO_MULTIPLE_DOTS
-# define MAX_EXT_CHARS 3
-# define Z_SUFFIX "z"
-# define casemap(c) tolow(c) /* Force file names to lower case */
-# endif
-#endif
-
-#ifdef MACOS
-# define PATH_SEP ':'
-# define DYN_ALLOC
-# define PROTO
-# define NO_STDIN_FSTAT
-# define chmod(file, mode) (0)
-# define OPEN(name, flags, mode) open(name, flags)
-# define OS_CODE 0x07
-# ifdef MPW
-# define isatty(fd) ((fd) <= 2)
-# endif
-#endif
-
-#ifdef __50SERIES /* Prime/PRIMOS */
-# define PATH_SEP '>'
-# define STDC_HEADERS
-# define NO_STDIN_FSTAT
-# define NO_SIZE_CHECK
-# define RECORD_IO 1
-# define casemap(c) tolow(c) /* Force file names to lower case */
-# define put_char(c) put_byte((c) & 0x7F)
-# define get_char(c) ascii2pascii(get_byte())
-# define OS_CODE 0x0F /* temporary, subject to change */
-# ifdef SIGTERM
-# undef SIGTERM /* We don't want a signal handler for SIGTERM */
-# endif
-#endif
-
-#if defined(pyr) && !defined(NOMEMCPY) /* Pyramid */
-# define NOMEMCPY /* problem with overlapping copies */
-#endif
-
-#ifdef TOPS20
-# define OS_CODE 0x0a
-#endif
-
-#ifndef unix
-# define NO_ST_INO /* don't rely on inode numbers */
-#endif
-
-
- /* Common defaults */
-
-#ifndef OS_CODE
-# define OS_CODE 0x03 /* assume Unix */
-#endif
-
-#ifndef PATH_SEP
-# define PATH_SEP '/'
-#endif
-
-#ifndef casemap
-# define casemap(c) (c)
-#endif
-
-#ifndef OPTIONS_VAR
-# define OPTIONS_VAR "GZIP"
-#endif
-
-#ifndef Z_SUFFIX
-# define Z_SUFFIX ".gz"
-#endif
-
-#ifdef MAX_EXT_CHARS
-# define MAX_SUFFIX MAX_EXT_CHARS
-#else
-# define MAX_SUFFIX 30
-#endif
-
-#ifndef MAKE_LEGAL_NAME
-# ifdef NO_MULTIPLE_DOTS
-# define MAKE_LEGAL_NAME(name) make_simple_name(name)
-# else
-# define MAKE_LEGAL_NAME(name)
-# endif
-#endif
-
-#ifndef MIN_PART
-# define MIN_PART 3
- /* keep at least MIN_PART chars between dots in a file name. */
-#endif
-
-#ifndef EXPAND
-# define EXPAND(argc,argv)
-#endif
-
-#ifndef RECORD_IO
-# define RECORD_IO 0
-#endif
-
-#ifndef SET_BINARY_MODE
-# define SET_BINARY_MODE(fd)
-#endif
-
-#ifndef OPEN
-# define OPEN(name, flags, mode) open(name, flags, mode)
-#endif
-
-#ifndef get_char
-# define get_char() get_byte()
-#endif
-
-#ifndef put_char
-# define put_char(c) put_byte(c)
-#endif
-
-
-/* gzip.h -- common declarations for all gzip modules
- * Copyright (C) 1997, 1998, 1999, 2001 Free Software Foundation, Inc.
- * 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.
- */
-
-#if defined(__STDC__) || defined(PROTO)
-# define OF(args) args
-#else
-# define OF(args) ()
-#endif
-
-#ifdef __STDC__
- typedef void *voidp;
-#else
- typedef char *voidp;
-#endif
-
-# define memzero(s, n) memset ((voidp)(s), 0, (n))
-
-#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
-
-#define near
-
-#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 int rsync; /* deflate into rsyncable chunks */
-
-extern off_t bytes_in; /* number of input bytes */
-extern off_t bytes_out; /* number of output bytes */
-extern off_t header_bytes;/* number of bytes in gzip header */
-
-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 time_t time_stamp; /* original time stamp (modification time) */
-extern off_t 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 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) ? tolower (c) : (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_signal OF((void));
-
- /* in deflate.c */
-void lm_init OF((int pack_level, ush *flags));
-off_t deflate OF((void));
-
- /* in trees.c */
-void ct_init OF((ush *attr, int *method));
-int ct_tally OF((int dist, int lc));
-off_t flush_block OF((char *buf, ulg stored_len, int pad, 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 *base_name OF((char *fname));
-extern int xunlink 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 warning OF((char *m));
-extern void read_error OF((void));
-extern void write_error OF((void));
-extern void display_ratio OF((off_t num, off_t den, FILE *file));
-extern void fprint_off OF((FILE *, off_t, int));
-extern voidp xmalloc OF((unsigned int size));
-
- /* in inflate.c */
-extern int inflate OF((void));
-
- /* in yesno.c */
-extern int yesno OF((void));
-
-
-/* crypt.h (dummy version) -- do not perform encryption
- * Hardly worth copyrighting :-)
- */
-
-#ifdef CRYPT
-# undef CRYPT /* dummy version */
-#endif
-
-#define RAND_HEAD_LEN 12 /* length of encryption random header */
-
-#define zencode
-#define zdecode
-
-
-#ifdef RCSID
-static char rcsid[] = "$Id: bits.c,v 0.9 1993/06/11 10:16:58 jloup Exp $";
-#endif
-
-/* ===========================================================================
- * Local data used by the "bit string" routines.
- */
-
-local file_t zfile; /* output gzip file */
-
-local unsigned short bi_buf;
-/* Output buffer. bits are inserted starting at the bottom (least significant
- * bits).
- */
-
-#define Buf_size (8 * 2*sizeof(char))
-/* Number of bits used within bi_buf. (bi_buf might be implemented on
- * more than 16 bits on some systems.)
- */
-
-local int bi_valid;
-/* Number of valid bits in bi_buf. All bits above the last valid bit
- * are always zero.
- */
-
-int (*read_buf) OF((char *buf, unsigned size));
-/* Current input function. Set to mem_read for in-memory compression */
-
-#ifdef DEBUG
- off_t bits_sent; /* bit length of the compressed data */
-#endif
-
-/* ===========================================================================
- * Initialize the bit string routines.
- */
-void bi_init (zipfile)
- file_t zipfile; /* output zip file, NO_FILE for in-memory compression */
-{
- zfile = zipfile;
- bi_buf = 0;
- bi_valid = 0;
-#ifdef DEBUG
- bits_sent = 0L;
-#endif
-
- /* Set the defaults for file compression. They are set by memcompress
- * for in-memory compression.
- */
- if (zfile != NO_FILE) {
- read_buf = file_read;
- }
-}
-
-/* ===========================================================================
- * Send a value on a given number of bits.
- * IN assertion: length <= 16 and value fits in length bits.
- */
-void send_bits(value, length)
- int value; /* value to send */
- int length; /* number of bits */
-{
-#ifdef DEBUG
- Tracev((stderr," l %2d v %4x ", length, value));
- Assert(length > 0 && length <= 15, "invalid length");
- bits_sent += (off_t)length;
-#endif
- /* If not enough room in bi_buf, use (valid) bits from bi_buf and
- * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid))
- * unused bits in value.
- */
- if (bi_valid > (int)Buf_size - length) {
- bi_buf |= (value << bi_valid);
- put_short(bi_buf);
- bi_buf = (ush)value >> (Buf_size - bi_valid);
- bi_valid += length - Buf_size;
- } else {
- bi_buf |= value << bi_valid;
- bi_valid += length;
- }
-}
-
-/* ===========================================================================
- * Reverse the first len bits of a code, using straightforward code (a faster
- * method would use a table)
- * IN assertion: 1 <= len <= 15
- */
-unsigned bi_reverse(code, len)
- unsigned code; /* the value to invert */
- int len; /* its bit length */
-{
- register unsigned res = 0;
- do {
- res |= code & 1;
- code >>= 1, res <<= 1;
- } while (--len > 0);
- return res >> 1;
-}
-
-/* ===========================================================================
- * Write out any remaining bits in an incomplete byte.
- */
-void bi_windup()
-{
- if (bi_valid > 8) {
- put_short(bi_buf);
- } else if (bi_valid > 0) {
- put_byte(bi_buf);
- }
- bi_buf = 0;
- bi_valid = 0;
-#ifdef DEBUG
- bits_sent = (bits_sent+7) & ~7;
-#endif
-}
-
-/* ===========================================================================
- * Copy a stored block to the zip file, storing first the length and its
- * one's complement if requested.
- */
-void copy_block(buf, len, header)
- char *buf; /* the input data */
- unsigned len; /* its length */
- int header; /* true if block header must be written */
-{
- bi_windup(); /* align on byte boundary */
-
- if (header) {
- put_short((ush)len);
- put_short((ush)~len);
-#ifdef DEBUG
- bits_sent += 2*16;
-#endif
- }
-#ifdef DEBUG
- bits_sent += (off_t)len<<3;
-#endif
- while (len--) {
-#ifdef CRYPT
- int t;
- if (key) zencode(*buf, t);
-#endif
- put_byte(*buf++);
- }
-}
-/* crypt.c (dummy version) -- do not perform encryption
- * Hardly worth copyrighting :-)
- */
-#ifdef RCSID
-static char rcsid[] = "$Id: crypt.c,v 0.6 1993/03/22 09:48:47 jloup Exp $";
-#endif
-/* deflate.c -- compress data using the deflation algorithm
- * 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.
- */
-
-/*
- * PURPOSE
- *
- * Identify new text as repetitions of old text within a fixed-
- * length sliding window trailing behind the new text.
- *
- * DISCUSSION
- *
- * The "deflation" process depends on being able to identify portions
- * of the input text which are identical to earlier input (within a
- * sliding window trailing behind the input currently being processed).
- *
- * The most straightforward technique turns out to be the fastest for
- * most input files: try all possible matches and select the longest.
- * The key feature of this algorithm is that insertions into the string
- * dictionary are very simple and thus fast, and deletions are avoided
- * completely. Insertions are performed at each input character, whereas
- * string matches are performed only when the previous match ends. So it
- * is preferable to spend more time in matches to allow very fast string
- * insertions and avoid deletions. The matching algorithm for small
- * strings is inspired from that of Rabin & Karp. A brute force approach
- * is used to find longer strings when a small match has been found.
- * A similar algorithm is used in comic (by Jan-Mark Wams) and freeze
- * (by Leonid Broukhis).
- * A previous version of this file used a more sophisticated algorithm
- * (by Fiala and Greene) which is guaranteed to run in linear amortized
- * time, but has a larger average cost, uses more memory and is patented.
- * However the F&G algorithm may be faster for some highly redundant
- * files if the parameter max_chain_length (described below) is too large.
- *
- * ACKNOWLEDGEMENTS
- *
- * The idea of lazy evaluation of matches is due to Jan-Mark Wams, and
- * I found it in 'freeze' written by Leonid Broukhis.
- * Thanks to many info-zippers for bug reports and testing.
- *
- * REFERENCES
- *
- * APPNOTE.TXT documentation file in PKZIP 1.93a distribution.
- *
- * A description of the Rabin and Karp algorithm is given in the book
- * "Algorithms" by R. Sedgewick, Addison-Wesley, p252.
- *
- * Fiala,E.R., and Greene,D.H.
- * Data Compression with Finite Windows, Comm.ACM, 32,4 (1989) 490-595
- *
- * INTERFACE
- *
- * void lm_init (int pack_level, ush *flags)
- * Initialize the "longest match" routines for a new file
- *
- * off_t deflate (void)
- * Processes a new input file and return its compressed length. Sets
- * the compressed length, crc, deflate flags and internal file
- * attributes.
- */
-
-
-/* lzw.h -- define the lzw functions.
- * 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.
- */
-
-#ifndef BITS
-# define BITS 16
-#endif
-#define INIT_BITS 9 /* Initial number of bits per code */
-
-#define LZW_MAGIC "\037\235" /* Magic header for lzw files, 1F 9D */
-
-#define BIT_MASK 0x1f /* Mask for 'number of compression bits' */
-/* Mask 0x20 is reserved to mean a fourth header byte, and 0x40 is free.
- * It's a pity that old uncompress does not check bit 0x20. That makes
- * extension of the format actually undesirable because old compress
- * would just crash on the new format instead of giving a meaningful
- * error message. It does check the number of bits, but it's more
- * helpful to say "unsupported format, get a new version" than
- * "can only handle 16 bits".
- */
-
-#define BLOCK_MODE 0x80
-/* Block compression: if table is full and compression rate is dropping,
- * clear the dictionary.
- */
-
-#define LZW_RESERVED 0x60 /* reserved bits */
-
-#define CLEAR 256 /* flush the dictionary */
-#define FIRST (CLEAR+1) /* first free entry */
-
-extern int maxbits; /* max bits per code for LZW */
-extern int block_mode; /* block compress mode -C compatible with 2.0 */
-
-extern int lzw OF((int in, int out));
-extern int unlzw OF((int in, int out));
-
-
-#ifdef RCSID
-static char rcsid[] = "$Id: deflate.c,v 0.15 1993/06/24 10:53:53 jloup Exp $";
-#endif
-
-/* ===========================================================================
- * Configuration parameters
- */
-
-/* Compile with MEDIUM_MEM to reduce the memory requirements or
- * with SMALL_MEM to use as little memory as possible. Use BIG_MEM if the
- * entire input file can be held in memory (not possible on 16 bit systems).
- * Warning: defining these symbols affects HASH_BITS (see below) and thus
- * affects the compression ratio. The compressed output
- * is still correct, and might even be smaller in some cases.
- */
-
-#ifdef SMALL_MEM
-# define HASH_BITS 13 /* Number of bits used to hash strings */
-#endif
-#ifdef MEDIUM_MEM
-# define HASH_BITS 14
-#endif
-#ifndef HASH_BITS
-# define HASH_BITS 15
- /* For portability to 16 bit machines, do not use values above 15. */
-#endif
-
-/* To save space (see unlzw.c), we overlay prev+head with tab_prefix and
- * window with tab_suffix. Check that we can do this:
- */
-#if (WSIZE<<1) > (1<<BITS)
- error: cannot overlay window with tab_suffix and prev with tab_prefix0
-#endif
-#if HASH_BITS > BITS-1
- error: cannot overlay head with tab_prefix1
-#endif
-
-#define HASH_SIZE (unsigned)(1<<HASH_BITS)
-#define HASH_MASK (HASH_SIZE-1)
-#define WMASK (WSIZE-1)
-/* HASH_SIZE and WSIZE must be powers of two */
-
-#define NIL 0
-/* Tail of hash chains */
-
-#define FAST 4
-#define SLOW 2
-/* speed options for the general purpose bit flag */
-
-#ifndef TOO_FAR
-# define TOO_FAR 4096
-#endif
-/* Matches of length 3 are discarded if their distance exceeds TOO_FAR */
-
-#ifndef RSYNC_WIN
-# define RSYNC_WIN 4096
-#endif
-/* Size of rsync window, must be < MAX_DIST */
-
-#define RSYNC_SUM_MATCH(sum) ((sum) % RSYNC_WIN == 0)
-/* Whether window sum matches magic value */
-
-/* ===========================================================================
- * Local data used by the "longest match" routines.
- */
-
-typedef ush Pos;
-typedef unsigned IPos;
-/* A Pos is an index in the character window. We use short instead of int to
- * save space in the various tables. IPos is used only for parameter passing.
- */
-
-/* DECLARE(uch, window, 2L*WSIZE); */
-/* Sliding window. Input bytes are read into the second half of the window,
- * and move to the first half later to keep a dictionary of at least WSIZE
- * bytes. With this organization, matches are limited to a distance of
- * WSIZE-MAX_MATCH bytes, but this ensures that IO is always
- * performed with a length multiple of the block size. Also, it limits
- * the window size to 64K, which is quite useful on MSDOS.
- * To do: limit the window size to WSIZE+BSZ if SMALL_MEM (the code would
- * be less efficient).
- */
-
-/* DECLARE(Pos, prev, WSIZE); */
-/* Link to older string with same hash index. To limit the size of this
- * array to 64K, this link is maintained only for the last 32K strings.
- * An index in this array is thus a window index modulo 32K.
- */
-
-/* DECLARE(Pos, head, 1<<HASH_BITS); */
-/* Heads of the hash chains or NIL. */
-
-ulg window_size = (ulg)2*WSIZE;
-/* window size, 2*WSIZE except for MMAP or BIG_MEM, where it is the
- * input file length plus MIN_LOOKAHEAD.
- */
-
-long block_start;
-/* window position at the beginning of the current output block. Gets
- * negative when the window is moved backwards.
- */
-
-local unsigned ins_h; /* hash index of string to be inserted */
-
-#define H_SHIFT ((HASH_BITS+MIN_MATCH-1)/MIN_MATCH)
-/* Number of bits by which ins_h and del_h must be shifted at each
- * input step. It must be such that after MIN_MATCH steps, the oldest
- * byte no longer takes part in the hash key, that is:
- * H_SHIFT * MIN_MATCH >= HASH_BITS
- */
-
-unsigned int near prev_length;
-/* Length of the best match at previous step. Matches not greater than this
- * are discarded. This is used in the lazy match evaluation.
- */
-
- unsigned near strstart; /* start of string to insert */
- unsigned near match_start; /* start of matching string */
-local int eofile; /* flag set at end of input file */
-local unsigned lookahead; /* number of valid bytes ahead in window */
-
-unsigned near max_chain_length;
-/* To speed up deflation, hash chains are never searched beyond this length.
- * A higher limit improves compression ratio but degrades the speed.
- */
-
-local unsigned int max_lazy_match;
-/* Attempt to find a better match only when the current match is strictly
- * smaller than this value. This mechanism is used only for compression
- * levels >= 4.
- */
-#define max_insert_length max_lazy_match
-/* Insert new strings in the hash table only if the match length
- * is not greater than this length. This saves time but degrades compression.
- * max_insert_length is used only for compression levels <= 3.
- */
-
-local int compr_level;
-/* compression level (1..9) */
-
-unsigned near good_match;
-/* Use a faster search when the previous match is longer than this */
-
-local ulg rsync_sum; /* rolling sum of rsync window */
-local ulg rsync_chunk_end; /* next rsync sequence point */
-
-/* Values for max_lazy_match, good_match and max_chain_length, depending on
- * the desired pack level (0..9). The values given below have been tuned to
- * exclude worst case performance for pathological files. Better values may be
- * found for specific files.
- */
-
-typedef struct config {
- ush good_length; /* reduce lazy search above this match length */
- ush max_lazy; /* do not perform lazy search above this match length */
- ush nice_length; /* quit search above this match length */
- ush max_chain;
-} config;
-
-#ifdef FULL_SEARCH
-# define nice_match MAX_MATCH
-#else
- int near nice_match; /* Stop searching when current match exceeds this */
-#endif
-
-local config configuration_table[10] = {
-/* good lazy nice chain */
-/* 0 */ {0, 0, 0, 0}, /* store only */
-/* 1 */ {4, 4, 8, 4}, /* maximum speed, no lazy matches */
-/* 2 */ {4, 5, 16, 8},
-/* 3 */ {4, 6, 32, 32},
-
-/* 4 */ {4, 4, 16, 16}, /* lazy matches */
-/* 5 */ {8, 16, 32, 32},
-/* 6 */ {8, 16, 128, 128},
-/* 7 */ {8, 32, 128, 256},
-/* 8 */ {32, 128, 258, 1024},
-/* 9 */ {32, 258, 258, 4096}}; /* maximum compression */
-
-/* Note: the deflate() code requires max_lazy >= MIN_MATCH and max_chain >= 4
- * For deflate_fast() (levels <= 3) good is ignored and lazy has a different
- * meaning.
- */
-
-#define EQUAL 0
-/* result of memcmp for equal strings */
-
-/* ===========================================================================
- * Prototypes for local functions.
- */
-local void fill_window OF((void));
-local off_t deflate_fast OF((void));
-
- int longest_match OF((IPos cur_match));
-#ifdef ASMV
- void match_init OF((void)); /* asm code initialization */
-#endif
-
-#ifdef DEBUG
-local void check_match OF((IPos start, IPos match, int length));
-#endif
-
-/* ===========================================================================
- * Update a hash value with the given input byte
- * IN assertion: all calls to to UPDATE_HASH are made with consecutive
- * input characters, so that a running hash key can be computed from the
- * previous key instead of complete recalculation each time.
- */
-#define UPDATE_HASH(h,c) (h = (((h)<<H_SHIFT) ^ (c)) & HASH_MASK)
-
-/* ===========================================================================
- * Insert string s in the dictionary and set match_head to the previous head
- * of the hash chain (the most recent string with same hash key). Return
- * the previous length of the hash chain.
- * IN assertion: all calls to to INSERT_STRING are made with consecutive
- * input characters and the first MIN_MATCH bytes of s are valid
- * (except for the last MIN_MATCH-1 bytes of the input file).
- */
-#define INSERT_STRING(s, match_head) \
- (UPDATE_HASH(ins_h, window[(s) + MIN_MATCH-1]), \
- prev[(s) & WMASK] = match_head = head[ins_h], \
- head[ins_h] = (s))
-
-/* ===========================================================================
- * Initialize the "longest match" routines for a new file
- */
-void lm_init (pack_level, flags)
- int pack_level; /* 0: store, 1: best speed, 9: best compression */
- ush *flags; /* general purpose bit flag */
-{
- register unsigned j;
-
- if (pack_level < 1 || pack_level > 9) error("bad pack level");
- compr_level = pack_level;
-
- /* Initialize the hash table. */
-#if defined(MAXSEG_64K) && HASH_BITS == 15
- for (j = 0; j < HASH_SIZE; j++) head[j] = NIL;
-#else
- memzero((char*)head, HASH_SIZE*sizeof(*head));
-#endif
- /* prev will be initialized on the fly */
-
- /* rsync params */
- rsync_chunk_end = 0xFFFFFFFFUL;
- rsync_sum = 0;
-
- /* Set the default configuration parameters:
- */
- max_lazy_match = configuration_table[pack_level].max_lazy;
- good_match = configuration_table[pack_level].good_length;
-#ifndef FULL_SEARCH
- nice_match = configuration_table[pack_level].nice_length;
-#endif
- max_chain_length = configuration_table[pack_level].max_chain;
- if (pack_level == 1) {
- *flags |= FAST;
- } else if (pack_level == 9) {
- *flags |= SLOW;
- }
- /* ??? reduce max_chain_length for binary files */
-
- strstart = 0;
- block_start = 0L;
-#ifdef ASMV
- match_init(); /* initialize the asm code */
-#endif
-
- lookahead = read_buf((char*)window,
- sizeof(int) <= 2 ? (unsigned)WSIZE : 2*WSIZE);
-
- if (lookahead == 0 || lookahead == (unsigned)EOF) {
- eofile = 1, lookahead = 0;
- return;
- }
- eofile = 0;
- /* Make sure that we always have enough lookahead. This is important
- * if input comes from a device such as a tty.
- */
- while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window();
-
- ins_h = 0;
- for (j=0; j<MIN_MATCH-1; j++) UPDATE_HASH(ins_h, window[j]);
- /* If lookahead < MIN_MATCH, ins_h is garbage, but this is
- * not important since only literal bytes will be emitted.
- */
-}
-
-/* ===========================================================================
- * Set match_start to the longest match starting at the given string and
- * return its length. Matches shorter or equal to prev_length are discarded,
- * in which case the result is equal to prev_length and match_start is
- * garbage.
- * IN assertions: cur_match is the head of the hash chain for the current
- * string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1
- */
-#ifndef ASMV
-/* For MSDOS, OS/2 and 386 Unix, an optimized version is in match.asm or
- * match.s. The code is functionally equivalent, so you can use the C version
- * if desired.
- */
-int longest_match(cur_match)
- IPos cur_match; /* current match */
-{
- unsigned chain_length = max_chain_length; /* max hash chain length */
- register uch *scan = window + strstart; /* current string */
- register uch *match; /* matched string */
- register int len; /* length of current match */
- int best_len = prev_length; /* best match length so far */
- IPos limit = strstart > (IPos)MAX_DIST ? strstart - (IPos)MAX_DIST : NIL;
- /* Stop when cur_match becomes <= limit. To simplify the code,
- * we prevent matches with the string of window index 0.
- */
-
-/* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16.
- * It is easy to get rid of this optimization if necessary.
- */
-#if HASH_BITS < 8 || MAX_MATCH != 258
- error: Code too clever
-#endif
-
-#ifdef UNALIGNED_OK
- /* Compare two bytes at a time. Note: this is not always beneficial.
- * Try with and without -DUNALIGNED_OK to check.
- */
- register uch *strend = window + strstart + MAX_MATCH - 1;
- register ush scan_start = *(ush*)scan;
- register ush scan_end = *(ush*)(scan+best_len-1);
-#else
- register uch *strend = window + strstart + MAX_MATCH;
- register uch scan_end1 = scan[best_len-1];
- register uch scan_end = scan[best_len];
-#endif
-
- /* Do not waste too much time if we already have a good match: */
- if (prev_length >= good_match) {
- chain_length >>= 2;
- }
- Assert(strstart <= window_size-MIN_LOOKAHEAD, "insufficient lookahead");
-
- do {
- Assert(cur_match < strstart, "no future");
- match = window + cur_match;
-
- /* Skip to next match if the match length cannot increase
- * or if the match length is less than 2:
- */
-#if (defined(UNALIGNED_OK) && MAX_MATCH == 258)
- /* This code assumes sizeof(unsigned short) == 2. Do not use
- * UNALIGNED_OK if your compiler uses a different size.
- */
- if (*(ush*)(match+best_len-1) != scan_end ||
- *(ush*)match != scan_start) continue;
-
- /* It is not necessary to compare scan[2] and match[2] since they are
- * always equal when the other bytes match, given that the hash keys
- * are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at
- * strstart+3, +5, ... up to strstart+257. We check for insufficient
- * lookahead only every 4th comparison; the 128th check will be made
- * at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is
- * necessary to put more guard bytes at the end of the window, or
- * to check more often for insufficient lookahead.
- */
- scan++, match++;
- do {
- } while (*(ush*)(scan+=2) == *(ush*)(match+=2) &&
- *(ush*)(scan+=2) == *(ush*)(match+=2) &&
- *(ush*)(scan+=2) == *(ush*)(match+=2) &&
- *(ush*)(scan+=2) == *(ush*)(match+=2) &&
- scan < strend);
- /* The funny "do {}" generates better code on most compilers */
-
- /* Here, scan <= window+strstart+257 */
- Assert(scan <= window+(unsigned)(window_size-1), "wild scan");
- if (*scan == *match) scan++;
-
- len = (MAX_MATCH - 1) - (int)(strend-scan);
- scan = strend - (MAX_MATCH-1);
-
-#else /* UNALIGNED_OK */
-
- if (match[best_len] != scan_end ||
- match[best_len-1] != scan_end1 ||
- *match != *scan ||
- *++match != scan[1]) continue;
-
- /* The check at best_len-1 can be removed because it will be made
- * again later. (This heuristic is not always a win.)
- * It is not necessary to compare scan[2] and match[2] since they
- * are always equal when the other bytes match, given that
- * the hash keys are equal and that HASH_BITS >= 8.
- */
- scan += 2, match++;
-
- /* We check for insufficient lookahead only every 8th comparison;
- * the 256th check will be made at strstart+258.
- */
- do {
- } while (*++scan == *++match && *++scan == *++match &&
- *++scan == *++match && *++scan == *++match &&
- *++scan == *++match && *++scan == *++match &&
- *++scan == *++match && *++scan == *++match &&
- scan < strend);
-
- len = MAX_MATCH - (int)(strend - scan);
- scan = strend - MAX_MATCH;
-
-#endif /* UNALIGNED_OK */
-
- if (len > best_len) {
- match_start = cur_match;
- best_len = len;
- if (len >= nice_match) break;
-#ifdef UNALIGNED_OK
- scan_end = *(ush*)(scan+best_len-1);
-#else
- scan_end1 = scan[best_len-1];
- scan_end = scan[best_len];
-#endif
- }
- } while ((cur_match = prev[cur_match & WMASK]) > limit
- && --chain_length != 0);
-
- return best_len;
-}
-#endif /* ASMV */
-
-#ifdef DEBUG
-/* ===========================================================================
- * Check that the match at match_start is indeed a match.
- */
-local void check_match(start, match, length)
- IPos start, match;
- int length;
-{
- /* check that the match is indeed a match */
- if (memcmp((char*)window + match,
- (char*)window + start, length) != EQUAL) {
- fprintf(stderr,
- " start %d, match %d, length %d\n",
- start, match, length);
- error("invalid match");
- }
- if (verbose > 1) {
- fprintf(stderr,"\\[%d,%d]", start-match, length);
- do { putc(window[start++], stderr); } while (--length != 0);
- }
-}
-#else
-# define check_match(start, match, length)
-#endif
-
-/* ===========================================================================
- * Fill the window when the lookahead becomes insufficient.
- * Updates strstart and lookahead, and sets eofile if end of input file.
- * IN assertion: lookahead < MIN_LOOKAHEAD && strstart + lookahead > 0
- * OUT assertions: at least one byte has been read, or eofile is set;
- * file reads are performed for at least two bytes (required for the
- * translate_eol option).
- */
-local void fill_window()
-{
- register unsigned n, m;
- unsigned more = (unsigned)(window_size - (ulg)lookahead - (ulg)strstart);
- /* Amount of free space at the end of the window. */
-
- /* If the window is almost full and there is insufficient lookahead,
- * move the upper half to the lower one to make room in the upper half.
- */
- if (more == (unsigned)EOF) {
- /* Very unlikely, but possible on 16 bit machine if strstart == 0
- * and lookahead == 1 (input done one byte at time)
- */
- more--;
- } else if (strstart >= WSIZE+MAX_DIST) {
- /* By the IN assertion, the window is not empty so we can't confuse
- * more == 0 with more == 64K on a 16 bit machine.
- */
- Assert(window_size == (ulg)2*WSIZE, "no sliding with BIG_MEM");
-
- memcpy((char*)window, (char*)window+WSIZE, (unsigned)WSIZE);
- match_start -= WSIZE;
- strstart -= WSIZE; /* we now have strstart >= MAX_DIST: */
- if (rsync_chunk_end != 0xFFFFFFFFUL)
- rsync_chunk_end -= WSIZE;
-
- block_start -= (long) WSIZE;
-
- for (n = 0; n < HASH_SIZE; n++) {
- m = head[n];
- head[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL);
- }
- for (n = 0; n < WSIZE; n++) {
- m = prev[n];
- prev[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL);
- /* If n is not on any hash chain, prev[n] is garbage but
- * its value will never be used.
- */
- }
- more += WSIZE;
- }
- /* At this point, more >= 2 */
- if (!eofile) {
- n = read_buf((char*)window+strstart+lookahead, more);
- if (n == 0 || n == (unsigned)EOF) {
- eofile = 1;
- } else {
- lookahead += n;
- }
- }
-}
-
-local void rsync_roll(start, num)
- unsigned start;
- unsigned num;
-{
- unsigned i;
-
- if (start < RSYNC_WIN) {
- /* before window fills. */
- for (i = start; i < RSYNC_WIN; i++) {
- if (i == start + num) return;
- rsync_sum += (ulg)window[i];
- }
- num -= (RSYNC_WIN - start);
- start = RSYNC_WIN;
- }
-
- /* buffer after window full */
- for (i = start; i < start+num; i++) {
- /* New character in */
- rsync_sum += (ulg)window[i];
- /* Old character out */
- rsync_sum -= (ulg)window[i - RSYNC_WIN];
- if (rsync_chunk_end == 0xFFFFFFFFUL && RSYNC_SUM_MATCH(rsync_sum))
- rsync_chunk_end = i;
- }
-}
-
-/* ===========================================================================
- * Set rsync_chunk_end if window sum matches magic value.
- */
-#define RSYNC_ROLL(s, n) \
- do { if (rsync) rsync_roll((s), (n)); } while(0)
-
-/* ===========================================================================
- * Flush the current block, with given end-of-file flag.
- * IN assertion: strstart is set to the end of the current match.
- */
-#define FLUSH_BLOCK(eof) \
- flush_block(block_start >= 0L ? (char*)&window[(unsigned)block_start] : \
- (char*)NULL, (long)strstart - block_start, flush-1, (eof))
-
-/* ===========================================================================
- * Processes a new input file and return its compressed length. This
- * function does not perform lazy evaluationof matches and inserts
- * new strings in the dictionary only for unmatched strings or for short
- * matches. It is used only for the fast compression options.
- */
-local off_t deflate_fast()
-{
- IPos hash_head; /* head of the hash chain */
- int flush; /* set if current block must be flushed, 2=>and padded */
- unsigned match_length = 0; /* length of best match */
-
- prev_length = MIN_MATCH-1;
- while (lookahead != 0) {
- /* Insert the string window[strstart .. strstart+2] in the
- * dictionary, and set hash_head to the head of the hash chain:
- */
- INSERT_STRING(strstart, hash_head);
-
- /* Find the longest match, discarding those <= prev_length.
- * At this point we have always match_length < MIN_MATCH
- */
- if (hash_head != NIL && strstart - hash_head <= MAX_DIST &&
- strstart <= window_size - MIN_LOOKAHEAD) {
- /* To simplify the code, we prevent matches with the string
- * of window index 0 (in particular we have to avoid a match
- * of the string with itself at the start of the input file).
- */
- match_length = longest_match (hash_head);
- /* longest_match() sets match_start */
- if (match_length > lookahead) match_length = lookahead;
- }
- if (match_length >= MIN_MATCH) {
- check_match(strstart, match_start, match_length);
-
- flush = ct_tally(strstart-match_start, match_length - MIN_MATCH);
-
- lookahead -= match_length;
-
- RSYNC_ROLL(strstart, match_length);
- /* Insert new strings in the hash table only if the match length
- * is not too large. This saves time but degrades compression.
- */
- if (match_length <= max_insert_length) {
- match_length--; /* string at strstart already in hash table */
- do {
- strstart++;
- INSERT_STRING(strstart, hash_head);
- /* strstart never exceeds WSIZE-MAX_MATCH, so there are
- * always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH
- * these bytes are garbage, but it does not matter since
- * the next lookahead bytes will be emitted as literals.
- */
- } while (--match_length != 0);
- strstart++;
- } else {
- strstart += match_length;
- match_length = 0;
- ins_h = window[strstart];
- UPDATE_HASH(ins_h, window[strstart+1]);
-#if MIN_MATCH != 3
- Call UPDATE_HASH() MIN_MATCH-3 more times
-#endif
- }
- } else {
- /* No match, output a literal byte */
- Tracevv((stderr,"%c",window[strstart]));
- flush = ct_tally (0, window[strstart]);
- RSYNC_ROLL(strstart, 1);
- lookahead--;
- strstart++;
- }
- if (rsync && strstart > rsync_chunk_end) {
- rsync_chunk_end = 0xFFFFFFFFUL;
- flush = 2;
- }
- if (flush) FLUSH_BLOCK(0), block_start = strstart;
-
- /* Make sure that we always have enough lookahead, except
- * at the end of the input file. We need MAX_MATCH bytes
- * for the next match, plus MIN_MATCH bytes to insert the
- * string following the next match.
- */
- while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window();
-
- }
- return FLUSH_BLOCK(1); /* eof */
-}
-
-/* ===========================================================================
- * Same as above, but achieves better compression. We use a lazy
- * evaluation for matches: a match is finally adopted only if there is
- * no better match at the next window position.
- */
-off_t deflate()
-{
- IPos hash_head; /* head of hash chain */
- IPos prev_match; /* previous match */
- int flush; /* set if current block must be flushed */
- int match_available = 0; /* set if previous match exists */
- register unsigned match_length = MIN_MATCH-1; /* length of best match */
-
- if (compr_level <= 3) return deflate_fast(); /* optimized for speed */
-
- /* Process the input block. */
- while (lookahead != 0) {
- /* Insert the string window[strstart .. strstart+2] in the
- * dictionary, and set hash_head to the head of the hash chain:
- */
- INSERT_STRING(strstart, hash_head);
-
- /* Find the longest match, discarding those <= prev_length.
- */
- prev_length = match_length, prev_match = match_start;
- match_length = MIN_MATCH-1;
-
- if (hash_head != NIL && prev_length < max_lazy_match &&
- strstart - hash_head <= MAX_DIST &&
- strstart <= window_size - MIN_LOOKAHEAD) {
- /* To simplify the code, we prevent matches with the string
- * of window index 0 (in particular we have to avoid a match
- * of the string with itself at the start of the input file).
- */
- match_length = longest_match (hash_head);
- /* longest_match() sets match_start */
- if (match_length > lookahead) match_length = lookahead;
-
- /* Ignore a length 3 match if it is too distant: */
- if (match_length == MIN_MATCH && strstart-match_start > TOO_FAR){
- /* If prev_match is also MIN_MATCH, match_start is garbage
- * but we will ignore the current match anyway.
- */
- match_length--;
- }
- }
- /* If there was a match at the previous step and the current
- * match is not better, output the previous match:
- */
- if (prev_length >= MIN_MATCH && match_length <= prev_length) {
-
- check_match(strstart-1, prev_match, prev_length);
-
- flush = ct_tally(strstart-1-prev_match, prev_length - MIN_MATCH);
-
- /* Insert in hash table all strings up to the end of the match.
- * strstart-1 and strstart are already inserted.
- */
- lookahead -= prev_length-1;
- prev_length -= 2;
- RSYNC_ROLL(strstart, prev_length+1);
- do {
- strstart++;
- INSERT_STRING(strstart, hash_head);
- /* strstart never exceeds WSIZE-MAX_MATCH, so there are
- * always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH
- * these bytes are garbage, but it does not matter since the
- * next lookahead bytes will always be emitted as literals.
- */
- } while (--prev_length != 0);
- match_available = 0;
- match_length = MIN_MATCH-1;
- strstart++;
-
- if (rsync && strstart > rsync_chunk_end) {
- rsync_chunk_end = 0xFFFFFFFFUL;
- flush = 2;
- }
- if (flush) FLUSH_BLOCK(0), block_start = strstart;
- } else if (match_available) {
- /* If there was no match at the previous position, output a
- * single literal. If there was a match but the current match
- * is longer, truncate the previous match to a single literal.
- */
- Tracevv((stderr,"%c",window[strstart-1]));
- flush = ct_tally (0, window[strstart-1]);
- if (rsync && strstart > rsync_chunk_end) {
- rsync_chunk_end = 0xFFFFFFFFUL;
- flush = 2;
- }
- if (flush) FLUSH_BLOCK(0), block_start = strstart;
- RSYNC_ROLL(strstart, 1);
- strstart++;
- lookahead--;
- } else {
- /* There is no previous match to compare with, wait for
- * the next step to decide.
- */
- if (rsync && strstart > rsync_chunk_end) {
- /* Reset huffman tree */
- rsync_chunk_end = 0xFFFFFFFFUL;
- flush = 2;
- FLUSH_BLOCK(0), block_start = strstart;
- }
- match_available = 1;
- RSYNC_ROLL(strstart, 1);
- strstart++;
- lookahead--;
- }
- Assert (strstart <= bytes_in && lookahead <= bytes_in, "a bit too far");
-
- /* Make sure that we always have enough lookahead, except
- * at the end of the input file. We need MAX_MATCH bytes
- * for the next match, plus MIN_MATCH bytes to insert the
- * string following the next match.
- */
- while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window();
- }
- if (match_available) ct_tally (0, window[strstart-1]);
-
- return FLUSH_BLOCK(1); /* eof */
-}
-/* Getopt for GNU.
- NOTE: getopt is now part of the C library, so if you don't know what
- "Keep this file name-space clean" means, talk to drepper at gnu.org
- before changing it!
- Copyright (C) 1987,88,89,90,91,92,93,94,95,96,98,99,2000,2001
- Free Software Foundation, Inc.
- This file is part of the GNU C Library.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software Foundation,
- Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
-
-/* This tells Alpha OSF/1 not to define a getopt prototype in <stdio.h>.
- Ditto for AIX 3.2 and <stdlib.h>. */
-#ifndef _NO_PROTO
-# define _NO_PROTO
-#endif
-
-#if !defined __STDC__ || !__STDC__
-/* This is a separate conditional since some stdc systems
- reject `defined (const)'. */
-# ifndef const
-# define const
-# endif
-#endif
-
-/* This needs to come after some library #include
- to get __GNU_LIBRARY__ defined. */
-
-# define _(msgid) (msgid)
-
-/* This version of `getopt' appears to the caller like standard Unix `getopt'
- but it behaves differently for the user, since it allows the user
- to intersperse the options with the other arguments.
-
- As `getopt' works, it permutes the elements of ARGV so that,
- when it is done, all the options precede everything else. Thus
- all application programs are extended to handle flexible argument order.
-
- Setting the environment variable POSIXLY_CORRECT disables permutation.
- Then the behavior is completely standard.
-
- GNU application programs can use a third alternative mode in which
- they can distinguish the relative order of options and other arguments. */
-
-/* Declarations for getopt.
- Copyright (C) 1989-1994, 1996-1999, 2001 Free Software Foundation, Inc.
- This file is part of the GNU C Library.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software Foundation,
- Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
-
-#ifndef _GETOPT_H
-
-#ifndef __need_getopt
-# define _GETOPT_H 1
-#endif
-
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* For communication from `getopt' to the caller.
- When `getopt' finds an option that takes an argument,
- the argument value is returned here.
- Also, when `ordering' is RETURN_IN_ORDER,
- each non-option ARGV-element is returned here. */
-
-extern char *optarg;
-
-/* Index in ARGV of the next element to be scanned.
- This is used for communication to and from the caller
- and for communication between successive calls to `getopt'.
-
- On entry to `getopt', zero means this is the first call; initialize.
-
- When `getopt' returns -1, this is the index of the first of the
- non-option elements that the caller should itself scan.
-
- Otherwise, `optind' communicates from one call to the next
- how much of ARGV has been scanned so far. */
-
-extern int optind;
-
-/* Callers store zero here to inhibit the error message `getopt' prints
- for unrecognized options. */
-
-extern int opterr;
-
-/* Set to an option character which was unrecognized. */
-
-extern int optopt;
-
-/* Describe the long-named options requested by the application.
- The LONG_OPTIONS argument to getopt_long or getopt_long_only is a vector
- of `struct option' terminated by an element containing a name which is
- zero.
-
- The field `has_arg' is:
- no_argument (or 0) if the option does not take an argument,
- required_argument (or 1) if the option requires an argument,
- optional_argument (or 2) if the option takes an optional argument.
-
- If the field `flag' is not NULL, it points to a variable that is set
- to the value given in the field `val' when the option is found, but
- left unchanged if the option is not found.
-
- To have a long-named option do something other than set an `int' to
- a compiled-in constant, such as set a value from `optarg', set the
- option's `flag' field to zero and its `val' field to a nonzero
- value (the equivalent single-letter option character, if there is
- one). For long options that have a zero `flag' field, `getopt'
- returns the contents of the `val' field. */
-
-struct option
-{
-# if (defined __STDC__ && __STDC__) || defined __cplusplus
- const char *name;
-# else
- char *name;
-# endif
- /* has_arg can't be an enum because some compilers complain about
- type mismatches in all the code that assumes it is an int. */
- int has_arg;
- int *flag;
- int val;
-};
-
-/* Names for the values of the `has_arg' field of `struct option'. */
-
-# define no_argument 0
-# define required_argument 1
-# define optional_argument 2
-
-
-/* Get definitions and prototypes for functions to process the
- arguments in ARGV (ARGC of them, minus the program name) for
- options given in OPTS.
-
- Return the option character from OPTS just read. Return -1 when
- there are no more options. For unrecognized options, or options
- missing arguments, `optopt' is set to the option letter, and '?' is
- returned.
-
- The OPTS string is a list of characters which are recognized option
- letters, optionally followed by colons, specifying that that letter
- takes an argument, to be placed in `optarg'.
-
- If a letter in OPTS is followed by two colons, its argument is
- optional. This behavior is specific to the GNU `getopt'.
-
- The argument `--' causes premature termination of argument
- scanning, explicitly telling `getopt' that there are no more
- options.
-
- If OPTS begins with `--', then non-option arguments are treated as
- arguments to the option '\0'. This behavior is specific to the GNU
- `getopt'. */
-
-#if (defined __STDC__ && __STDC__) || defined __cplusplus
-# ifdef __GNU_LIBRARY__
-/* Many other libraries have conflicting prototypes for getopt, with
- differences in the consts, in stdlib.h. To avoid compilation
- errors, only prototype getopt for the GNU C library. */
-extern int getopt (int __argc, char *const *__argv, const char *__shortopts);
-# else /* not __GNU_LIBRARY__ */
-extern int getopt ();
-# endif /* __GNU_LIBRARY__ */
-
-# ifndef __need_getopt
-extern int getopt_long (int __argc, char *const *__argv, const char *__shortopts,
- const struct option *__longopts, int *__longind);
-extern int getopt_long_only (int __argc, char *const *__argv,
- const char *__shortopts,
- const struct option *__longopts, int *__longind);
-
-/* Internal only. Users should not call this directly. */
-extern int _getopt_internal (int __argc, char *const *__argv,
- const char *__shortopts,
- const struct option *__longopts, int *__longind,
- int __long_only);
-# endif
-#else /* not __STDC__ */
-extern int getopt ();
-# ifndef __need_getopt
-extern int getopt_long ();
-extern int getopt_long_only ();
-
-extern int _getopt_internal ();
-# endif
-#endif /* __STDC__ */
-
-#ifdef __cplusplus
-}
-#endif
-
-/* Make sure we later can get all the definitions and declarations. */
-#undef __need_getopt
-
-#endif /* getopt.h */
-
-
-/* For communication from `getopt' to the caller.
- When `getopt' finds an option that takes an argument,
- the argument value is returned here.
- Also, when `ordering' is RETURN_IN_ORDER,
- each non-option ARGV-element is returned here. */
-
-char *optarg;
-
-/* Index in ARGV of the next element to be scanned.
- This is used for communication to and from the caller
- and for communication between successive calls to `getopt'.
-
- On entry to `getopt', zero means this is the first call; initialize.
-
- When `getopt' returns -1, this is the index of the first of the
- non-option elements that the caller should itself scan.
-
- Otherwise, `optind' communicates from one call to the next
- how much of ARGV has been scanned so far. */
-
-/* 1003.2 says this must be 1 before any call. */
-int optind = 1;
-
-/* Formerly, initialization of getopt depended on optind==0, which
- causes problems with re-calling getopt as programs generally don't
- know that. */
-
-int __getopt_initialized;
-
-/* The next char to be scanned in the option-element
- in which the last option character we returned was found.
- This allows us to pick up the scan where we left off.
-
- If this is zero, or a null string, it means resume the scan
- by advancing to the next ARGV-element. */
-
-static char *nextchar;
-
-/* Callers store zero here to inhibit the error message
- for unrecognized options. */
-
-int opterr = 1;
-
-/* Set to an option character which was unrecognized.
- This must be initialized on some systems to avoid linking in the
- system's own getopt implementation. */
-
-int optopt = '?';
-
-/* Describe how to deal with options that follow non-option ARGV-elements.
-
- If the caller did not specify anything,
- the default is REQUIRE_ORDER if the environment variable
- POSIXLY_CORRECT is defined, PERMUTE otherwise.
-
- REQUIRE_ORDER means don't recognize them as options;
- stop option processing when the first non-option is seen.
- This is what Unix does.
- This mode of operation is selected by either setting the environment
- variable POSIXLY_CORRECT, or using `+' as the first character
- of the list of option characters.
-
- PERMUTE is the default. We permute the contents of ARGV as we scan,
- so that eventually all the non-options are at the end. This allows options
- to be given in any order, even with programs that were not written to
- expect this.
-
- RETURN_IN_ORDER is an option available to programs that were written
- to expect options and other ARGV-elements in any order and that care about
- the ordering of the two. We describe each non-option ARGV-element
- as if it were the argument of an option with character code 1.
- Using `-' as the first character of the list of option characters
- selects this mode of operation.
-
- The special argument `--' forces an end of option-scanning regardless
- of the value of `ordering'. In the case of RETURN_IN_ORDER, only
- `--' can cause `getopt' to return -1 with `optind' != ARGC. */
-
-static enum
-{
- REQUIRE_ORDER, PERMUTE, RETURN_IN_ORDER
-} ordering;
-
-/* Value of POSIXLY_CORRECT environment variable. */
-static char *posixly_correct;
-
-
-/* Avoid depending on library functions or files
- whose names are inconsistent. */
-
-#ifndef getenv
-extern char *getenv ();
-#endif
-
-static char *
-my_index (str, chr)
- const char *str;
- int chr;
-{
- while (*str)
- {
- if (*str == chr)
- return (char *) str;
- str++;
- }
- return 0;
-}
-
-/* If using GCC, we can safely declare strlen this way.
- If not using GCC, it is ok not to declare it. */
-#ifdef __GNUC__
-/* Note that Motorola Delta 68k R3V7 comes with GCC but not stddef.h.
- That was relevant to code that was here before. */
-# if (!defined __STDC__ || !__STDC__) && !defined strlen
-/* gcc with -traditional declares the built-in strlen to return int,
- and has done so at least since version 2.4.5. -- rms. */
-extern int strlen (const char *);
-# endif /* not __STDC__ */
-#endif /* __GNUC__ */
-
-
-/* Handle permutation of arguments. */
-
-/* Describe the part of ARGV that contains non-options that have
- been skipped. `first_nonopt' is the index in ARGV of the first of them;
- `last_nonopt' is the index after the last of them. */
-
-static int first_nonopt;
-static int last_nonopt;
-
-#ifdef _LIBC
-/* Bash 2.0 gives us an environment variable containing flags
- indicating ARGV elements that should not be considered arguments. */
-
-#ifdef USE_NONOPTION_FLAGS
-/* Defined in getopt_init.c */
-extern char *__getopt_nonoption_flags;
-
-static int nonoption_flags_max_len;
-static int nonoption_flags_len;
-#endif
-
-static int original_argc;
-static char *const *original_argv;
-
-/* Make sure the environment variable bash 2.0 puts in the environment
- is valid for the getopt call we must make sure that the ARGV passed
- to getopt is that one passed to the process. */
-static void
-__attribute__ ((unused))
-store_args_and_env (int argc, char *const *argv)
-{
- /* XXX This is no good solution. We should rather copy the args so
- that we can compare them later. But we must not use malloc(3). */
- original_argc = argc;
- original_argv = argv;
-}
-# ifdef text_set_element
-text_set_element (__libc_subinit, store_args_and_env);
-# endif /* text_set_element */
-
-# ifdef USE_NONOPTION_FLAGS
-# define SWAP_FLAGS(ch1, ch2) \
- if (nonoption_flags_len > 0) \
- { \
- char __tmp = __getopt_nonoption_flags[ch1]; \
- __getopt_nonoption_flags[ch1] = __getopt_nonoption_flags[ch2]; \
- __getopt_nonoption_flags[ch2] = __tmp; \
- }
-# else
-# define SWAP_FLAGS(ch1, ch2)
-# endif
-#else /* !_LIBC */
-# define SWAP_FLAGS(ch1, ch2)
-#endif /* _LIBC */
-
-/* Exchange two adjacent subsequences of ARGV.
- One subsequence is elements [first_nonopt,last_nonopt)
- which contains all the non-options that have been skipped so far.
- The other is elements [last_nonopt,optind), which contains all
- the options processed since those non-options were skipped.
-
- `first_nonopt' and `last_nonopt' are relocated so that they describe
- the new indices of the non-options in ARGV after they are moved. */
-
-#if defined __STDC__ && __STDC__
-static void exchange (char **);
-#endif
-
-static void
-exchange (argv)
- char **argv;
-{
- int bottom = first_nonopt;
- int middle = last_nonopt;
- int top = optind;
- char *tem;
-
- /* Exchange the shorter segment with the far end of the longer segment.
- That puts the shorter segment into the right place.
- It leaves the longer segment in the right place overall,
- but it consists of two parts that need to be swapped next. */
-
-#if defined _LIBC && defined USE_NONOPTION_FLAGS
- /* First make sure the handling of the `__getopt_nonoption_flags'
- string can work normally. Our top argument must be in the range
- of the string. */
- if (nonoption_flags_len > 0 && top >= nonoption_flags_max_len)
- {
- /* We must extend the array. The user plays games with us and
- presents new arguments. */
- char *new_str = malloc (top + 1);
- if (new_str == NULL)
- nonoption_flags_len = nonoption_flags_max_len = 0;
- else
- {
- memset (__mempcpy (new_str, __getopt_nonoption_flags,
- nonoption_flags_max_len),
- '\0', top + 1 - nonoption_flags_max_len);
- nonoption_flags_max_len = top + 1;
- __getopt_nonoption_flags = new_str;
- }
- }
-#endif
-
- while (top > middle && middle > bottom)
- {
- if (top - middle > middle - bottom)
- {
- /* Bottom segment is the short one. */
- int len = middle - bottom;
- register int i;
-
- /* Swap it with the top part of the top segment. */
- for (i = 0; i < len; i++)
- {
- tem = argv[bottom + i];
- argv[bottom + i] = argv[top - (middle - bottom) + i];
- argv[top - (middle - bottom) + i] = tem;
- SWAP_FLAGS (bottom + i, top - (middle - bottom) + i);
- }
- /* Exclude the moved bottom segment from further swapping. */
- top -= len;
- }
- else
- {
- /* Top segment is the short one. */
- int len = top - middle;
- register int i;
-
- /* Swap it with the bottom part of the bottom segment. */
- for (i = 0; i < len; i++)
- {
- tem = argv[bottom + i];
- argv[bottom + i] = argv[middle + i];
- argv[middle + i] = tem;
- SWAP_FLAGS (bottom + i, middle + i);
- }
- /* Exclude the moved top segment from further swapping. */
- bottom += len;
- }
- }
-
- /* Update records for the slots the non-options now occupy. */
-
- first_nonopt += (optind - last_nonopt);
- last_nonopt = optind;
-}
-
-/* Initialize the internal data when the first call is made. */
-
-#if defined __STDC__ && __STDC__
-static const char *_getopt_initialize (int, char *const *, const char *);
-#endif
-static const char *
-_getopt_initialize (argc, argv, optstring)
- int argc;
- char *const *argv;
- const char *optstring;
-{
- /* Start processing options with ARGV-element 1 (since ARGV-element 0
- is the program name); the sequence of previously skipped
- non-option ARGV-elements is empty. */
-
- first_nonopt = last_nonopt = optind;
-
- nextchar = NULL;
-
- posixly_correct = getenv ("POSIXLY_CORRECT");
-
- /* Determine how to handle the ordering of options and nonoptions. */
-
- if (optstring[0] == '-')
- {
- ordering = RETURN_IN_ORDER;
- ++optstring;
- }
- else if (optstring[0] == '+')
- {
- ordering = REQUIRE_ORDER;
- ++optstring;
- }
- else if (posixly_correct != NULL)
- ordering = REQUIRE_ORDER;
- else
- ordering = PERMUTE;
-
-#if defined _LIBC && defined USE_NONOPTION_FLAGS
- if (posixly_correct == NULL
- && argc == original_argc && argv == original_argv)
- {
- if (nonoption_flags_max_len == 0)
- {
- if (__getopt_nonoption_flags == NULL
- || __getopt_nonoption_flags[0] == '\0')
- nonoption_flags_max_len = -1;
- else
- {
- const char *orig_str = __getopt_nonoption_flags;
- int len = nonoption_flags_max_len = strlen (orig_str);
- if (nonoption_flags_max_len < argc)
- nonoption_flags_max_len = argc;
- __getopt_nonoption_flags =
- (char *) malloc (nonoption_flags_max_len);
- if (__getopt_nonoption_flags == NULL)
- nonoption_flags_max_len = -1;
- else
- memset (__mempcpy (__getopt_nonoption_flags, orig_str, len),
- '\0', nonoption_flags_max_len - len);
- }
- }
- nonoption_flags_len = nonoption_flags_max_len;
- }
- else
- nonoption_flags_len = 0;
-#endif
-
- return optstring;
-}
-
-/* Scan elements of ARGV (whose length is ARGC) for option characters
- given in OPTSTRING.
-
- If an element of ARGV starts with '-', and is not exactly "-" or "--",
- then it is an option element. The characters of this element
- (aside from the initial '-') are option characters. If `getopt'
- is called repeatedly, it returns successively each of the option characters
- from each of the option elements.
-
- If `getopt' finds another option character, it returns that character,
- updating `optind' and `nextchar' so that the next call to `getopt' can
- resume the scan with the following option character or ARGV-element.
-
- If there are no more option characters, `getopt' returns -1.
- Then `optind' is the index in ARGV of the first ARGV-element
- that is not an option. (The ARGV-elements have been permuted
- so that those that are not options now come last.)
-
- OPTSTRING is a string containing the legitimate option characters.
- If an option character is seen that is not listed in OPTSTRING,
- return '?' after printing an error message. If you set `opterr' to
- zero, the error message is suppressed but we still return '?'.
-
- If a char in OPTSTRING is followed by a colon, that means it wants an arg,
- so the following text in the same ARGV-element, or the text of the following
- ARGV-element, is returned in `optarg'. Two colons mean an option that
- wants an optional arg; if there is text in the current ARGV-element,
- it is returned in `optarg', otherwise `optarg' is set to zero.
-
- If OPTSTRING starts with `-' or `+', it requests different methods of
- handling the non-option ARGV-elements.
- See the comments about RETURN_IN_ORDER and REQUIRE_ORDER, above.
-
- Long-named options begin with `--' instead of `-'.
- Their names may be abbreviated as long as the abbreviation is unique
- or is an exact match for some defined option. If they have an
- argument, it follows the option name in the same ARGV-element, separated
- from the option name by a `=', or else the in next ARGV-element.
- When `getopt' finds a long-named option, it returns 0 if that option's
- `flag' field is nonzero, the value of the option's `val' field
- if the `flag' field is zero.
-
- The elements of ARGV aren't really const, because we permute them.
- But we pretend they're const in the prototype to be compatible
- with other systems.
-
- LONGOPTS is a vector of `struct option' terminated by an
- element containing a name which is zero.
-
- LONGIND returns the index in LONGOPT of the long-named option found.
- It is only valid when a long-named option has been found by the most
- recent call.
-
- If LONG_ONLY is nonzero, '-' as well as '--' can introduce
- long-named options. */
-
-int
-_getopt_internal (argc, argv, optstring, longopts, longind, long_only)
- int argc;
- char *const *argv;
- const char *optstring;
- const struct option *longopts;
- int *longind;
- int long_only;
-{
- int print_errors = opterr;
- if (optstring[0] == ':')
- print_errors = 0;
-
- if (argc < 1)
- return -1;
-
- optarg = NULL;
-
- if (optind == 0 || !__getopt_initialized)
- {
- if (optind == 0)
- optind = 1; /* Don't scan ARGV[0], the program name. */
- optstring = _getopt_initialize (argc, argv, optstring);
- __getopt_initialized = 1;
- }
-
- /* Test whether ARGV[optind] points to a non-option argument.
- Either it does not have option syntax, or there is an environment flag
- from the shell indicating it is not an option. The later information
- is only used when the used in the GNU libc. */
-#if defined _LIBC && defined USE_NONOPTION_FLAGS
-# define NONOPTION_P (argv[optind][0] != '-' || argv[optind][1] == '\0' \
- || (optind < nonoption_flags_len \
- && __getopt_nonoption_flags[optind] == '1'))
-#else
-# define NONOPTION_P (argv[optind][0] != '-' || argv[optind][1] == '\0')
-#endif
-
- if (nextchar == NULL || *nextchar == '\0')
- {
- /* Advance to the next ARGV-element. */
-
- /* Give FIRST_NONOPT & LAST_NONOPT rational values if OPTIND has been
- moved back by the user (who may also have changed the arguments). */
- if (last_nonopt > optind)
- last_nonopt = optind;
- if (first_nonopt > optind)
- first_nonopt = optind;
-
- if (ordering == PERMUTE)
- {
- /* If we have just processed some options following some non-options,
- exchange them so that the options come first. */
-
- if (first_nonopt != last_nonopt && last_nonopt != optind)
- exchange ((char **) argv);
- else if (last_nonopt != optind)
- first_nonopt = optind;
-
- /* Skip any additional non-options
- and extend the range of non-options previously skipped. */
-
- while (optind < argc && NONOPTION_P)
- optind++;
- last_nonopt = optind;
- }
-
- /* The special ARGV-element `--' means premature end of options.
- Skip it like a null option,
- then exchange with previous non-options as if it were an option,
- then skip everything else like a non-option. */
-
- if (optind != argc && !strcmp (argv[optind], "--"))
- {
- optind++;
-
- if (first_nonopt != last_nonopt && last_nonopt != optind)
- exchange ((char **) argv);
- else if (first_nonopt == last_nonopt)
- first_nonopt = optind;
- last_nonopt = argc;
-
- optind = argc;
- }
-
- /* If we have done all the ARGV-elements, stop the scan
- and back over any non-options that we skipped and permuted. */
-
- if (optind == argc)
- {
- /* Set the next-arg-index to point at the non-options
- that we previously skipped, so the caller will digest them. */
- if (first_nonopt != last_nonopt)
- optind = first_nonopt;
- return -1;
- }
-
- /* If we have come to a non-option and did not permute it,
- either stop the scan or describe it to the caller and pass it by. */
-
- if (NONOPTION_P)
- {
- if (ordering == REQUIRE_ORDER)
- return -1;
- optarg = argv[optind++];
- return 1;
- }
-
- /* We have found another option-ARGV-element.
- Skip the initial punctuation. */
-
- nextchar = (argv[optind] + 1
- + (longopts != NULL && argv[optind][1] == '-'));
- }
-
- /* Decode the current option-ARGV-element. */
-
- /* Check whether the ARGV-element is a long option.
-
- If long_only and the ARGV-element has the form "-f", where f is
- a valid short option, don't consider it an abbreviated form of
- a long option that starts with f. Otherwise there would be no
- way to give the -f short option.
-
- On the other hand, if there's a long option "fubar" and
- the ARGV-element is "-fu", do consider that an abbreviation of
- the long option, just like "--fu", and not "-f" with arg "u".
-
- This distinction seems to be the most useful approach. */
-
- if (longopts != NULL
- && (argv[optind][1] == '-'
- || (long_only && (argv[optind][2] || !my_index (optstring, argv[optind][1])))))
- {
- char *nameend;
- const struct option *p;
- const struct option *pfound = NULL;
- int exact = 0;
- int ambig = 0;
- int indfound = -1;
- int option_index;
-
- for (nameend = nextchar; *nameend && *nameend != '='; nameend++)
- /* Do nothing. */ ;
-
- /* Test all long options for either exact match
- or abbreviated matches. */
- for (p = longopts, option_index = 0; p->name; p++, option_index++)
- if (!strncmp (p->name, nextchar, nameend - nextchar))
- {
- if ((unsigned int) (nameend - nextchar)
- == (unsigned int) strlen (p->name))
- {
- /* Exact match found. */
- pfound = p;
- indfound = option_index;
- exact = 1;
- break;
- }
- else if (pfound == NULL)
- {
- /* First nonexact match found. */
- pfound = p;
- indfound = option_index;
- }
- else if (long_only
- || pfound->has_arg != p->has_arg
- || pfound->flag != p->flag
- || pfound->val != p->val)
- /* Second or later nonexact match found. */
- ambig = 1;
- }
-
- if (ambig && !exact)
- {
- if (print_errors)
- fprintf (stderr, _("%s: option `%s' is ambiguous\n"),
- argv[0], argv[optind]);
- nextchar += strlen (nextchar);
- optind++;
- optopt = 0;
- return '?';
- }
-
- if (pfound != NULL)
- {
- option_index = indfound;
- optind++;
- if (*nameend)
- {
- /* Don't test has_arg with >, because some C compilers don't
- allow it to be used on enums. */
- if (pfound->has_arg)
- optarg = nameend + 1;
- else
- {
- if (print_errors)
- {
- if (argv[optind - 1][1] == '-')
- /* --option */
- fprintf (stderr,
- _("%s: option `--%s' doesn't allow an argument\n"),
- argv[0], pfound->name);
- else
- /* +option or -option */
- fprintf (stderr,
- _("%s: option `%c%s' doesn't allow an argument\n"),
- argv[0], argv[optind - 1][0], pfound->name);
- }
-
- nextchar += strlen (nextchar);
-
- optopt = pfound->val;
- return '?';
- }
- }
- else if (pfound->has_arg == 1)
- {
- if (optind < argc)
- optarg = argv[optind++];
- else
- {
- if (print_errors)
- fprintf (stderr,
- _("%s: option `%s' requires an argument\n"),
- argv[0], argv[optind - 1]);
- nextchar += strlen (nextchar);
- optopt = pfound->val;
- return optstring[0] == ':' ? ':' : '?';
- }
- }
- nextchar += strlen (nextchar);
- if (longind != NULL)
- *longind = option_index;
- if (pfound->flag)
- {
- *(pfound->flag) = pfound->val;
- return 0;
- }
- return pfound->val;
- }
-
- /* Can't find it as a long option. If this is not getopt_long_only,
- or the option starts with '--' or is not a valid short
- option, then it's an error.
- Otherwise interpret it as a short option. */
- if (!long_only || argv[optind][1] == '-'
- || my_index (optstring, *nextchar) == NULL)
- {
- if (print_errors)
- {
- if (argv[optind][1] == '-')
- /* --option */
- fprintf (stderr, _("%s: unrecognized option `--%s'\n"),
- argv[0], nextchar);
- else
- /* +option or -option */
- fprintf (stderr, _("%s: unrecognized option `%c%s'\n"),
- argv[0], argv[optind][0], nextchar);
- }
- nextchar = (char *) "";
- optind++;
- optopt = 0;
- return '?';
- }
- }
-
- /* Look at and handle the next short option-character. */
-
- {
- char c = *nextchar++;
- char *temp = my_index (optstring, c);
-
- /* Increment `optind' when we start to process its last character. */
- if (*nextchar == '\0')
- ++optind;
-
- if (temp == NULL || c == ':')
- {
- if (print_errors)
- {
- if (posixly_correct)
- /* 1003.2 specifies the format of this message. */
- fprintf (stderr, _("%s: illegal option -- %c\n"),
- argv[0], c);
- else
- fprintf (stderr, _("%s: invalid option -- %c\n"),
- argv[0], c);
- }
- optopt = c;
- return '?';
- }
- /* Convenience. Treat POSIX -W foo same as long option --foo */
- if (temp[0] == 'W' && temp[1] == ';')
- {
- char *nameend;
- const struct option *p;
- const struct option *pfound = NULL;
- int exact = 0;
- int ambig = 0;
- int indfound = 0;
- int option_index;
-
- /* This is an option that requires an argument. */
- if (*nextchar != '\0')
- {
- optarg = nextchar;
- /* If we end this ARGV-element by taking the rest as an arg,
- we must advance to the next element now. */
- optind++;
- }
- else if (optind == argc)
- {
- if (print_errors)
- {
- /* 1003.2 specifies the format of this message. */
- fprintf (stderr, _("%s: option requires an argument -- %c\n"),
- argv[0], c);
- }
- optopt = c;
- if (optstring[0] == ':')
- c = ':';
- else
- c = '?';
- return c;
- }
- else
- /* We already incremented `optind' once;
- increment it again when taking next ARGV-elt as argument. */
- optarg = argv[optind++];
-
- /* optarg is now the argument, see if it's in the
- table of longopts. */
-
- for (nextchar = nameend = optarg; *nameend && *nameend != '='; nameend++)
- /* Do nothing. */ ;
-
- /* Test all long options for either exact match
- or abbreviated matches. */
- for (p = longopts, option_index = 0; p->name; p++, option_index++)
- if (!strncmp (p->name, nextchar, nameend - nextchar))
- {
- if ((unsigned int) (nameend - nextchar) == strlen (p->name))
- {
- /* Exact match found. */
- pfound = p;
- indfound = option_index;
- exact = 1;
- break;
- }
- else if (pfound == NULL)
- {
- /* First nonexact match found. */
- pfound = p;
- indfound = option_index;
- }
- else
- /* Second or later nonexact match found. */
- ambig = 1;
- }
- if (ambig && !exact)
- {
- if (print_errors)
- fprintf (stderr, _("%s: option `-W %s' is ambiguous\n"),
- argv[0], argv[optind]);
- nextchar += strlen (nextchar);
- optind++;
- return '?';
- }
- if (pfound != NULL)
- {
- option_index = indfound;
- if (*nameend)
- {
- /* Don't test has_arg with >, because some C compilers don't
- allow it to be used on enums. */
- if (pfound->has_arg)
- optarg = nameend + 1;
- else
- {
- if (print_errors)
- fprintf (stderr, _("\
-%s: option `-W %s' doesn't allow an argument\n"),
- argv[0], pfound->name);
-
- nextchar += strlen (nextchar);
- return '?';
- }
- }
- else if (pfound->has_arg == 1)
- {
- if (optind < argc)
- optarg = argv[optind++];
- else
- {
- if (print_errors)
- fprintf (stderr,
- _("%s: option `%s' requires an argument\n"),
- argv[0], argv[optind - 1]);
- nextchar += strlen (nextchar);
- return optstring[0] == ':' ? ':' : '?';
- }
- }
- nextchar += strlen (nextchar);
- if (longind != NULL)
- *longind = option_index;
- if (pfound->flag)
- {
- *(pfound->flag) = pfound->val;
- return 0;
- }
- return pfound->val;
- }
- nextchar = NULL;
- return 'W'; /* Let the application handle it. */
- }
- if (temp[1] == ':')
- {
- if (temp[2] == ':')
- {
- /* This is an option that accepts an argument optionally. */
- if (*nextchar != '\0')
- {
- optarg = nextchar;
- optind++;
- }
- else
- optarg = NULL;
- nextchar = NULL;
- }
- else
- {
- /* This is an option that requires an argument. */
- if (*nextchar != '\0')
- {
- optarg = nextchar;
- /* If we end this ARGV-element by taking the rest as an arg,
- we must advance to the next element now. */
- optind++;
- }
- else if (optind == argc)
- {
- if (print_errors)
- {
- /* 1003.2 specifies the format of this message. */
- fprintf (stderr,
- _("%s: option requires an argument -- %c\n"),
- argv[0], c);
- }
- optopt = c;
- if (optstring[0] == ':')
- c = ':';
- else
- c = '?';
- }
- else
- /* We already incremented `optind' once;
- increment it again when taking next ARGV-elt as argument. */
- optarg = argv[optind++];
- nextchar = NULL;
- }
- }
- return c;
- }
-}
-
-int
-getopt (argc, argv, optstring)
- int argc;
- char *const *argv;
- const char *optstring;
-{
- return _getopt_internal (argc, argv, optstring,
- (const struct option *) 0,
- (int *) 0,
- 0);
-}
-
-
-/* getopt_long and getopt_long_only entry points for GNU getopt.
- Copyright (C) 1987,88,89,90,91,92,93,94,96,97,98
- Free Software Foundation, Inc.
- This file is part of the GNU C Library.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software Foundation,
- Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
-
-
-#if !defined __STDC__ || !__STDC__
-/* This is a separate conditional since some stdc systems
- reject `defined (const)'. */
-#ifndef const
-#define const
-#endif
-#endif
-
-/* Comment out all this code if we are using the GNU C Library, and are not
- actually compiling the library itself. This code is part of the GNU C
- Library, but also included in many other GNU distributions. Compiling
- and linking in this code is a waste when using the GNU C library
- (especially if it is a shared library). Rather than having every GNU
- program understand `configure --with-gnu-libc' and omit the object files,
- it is simpler to just do this in the source for each such file. */
-
-/* gzip (GNU zip) -- compress files with zip algorithm and 'compress' interface
- * Copyright (C) 1999, 2001, 2002 Free Software Foundation, Inc.
- * Copyright (C) 1992-1993 Jean-loup Gailly
- * The unzip code was written and put in the public domain by Mark Adler.
- * Portions of the lzw code are derived from the public domain 'compress'
- * written by Spencer Thomas, Joe Orost, James Woods, Jim McKie, Steve Davies,
- * Ken Turkowski, Dave Mack and Peter Jannesen.
- *
- * See the license_msg below and the file COPYING for the software license.
- * See the file algorithm.doc for the compression algorithms and file formats.
- */
-
-static char *license_msg[] = {
-"Copyright 2002 Free Software Foundation",
-"Copyright 1992-1993 Jean-loup Gailly",
-"This program comes with ABSOLUTELY NO WARRANTY.",
-"You may redistribute copies of this program",
-"under the terms of the GNU General Public License.",
-"For more information about these matters, see the file named COPYING.",
-0};
-
-/* Compress files with zip algorithm and 'compress' interface.
- * See usage() and help() functions below for all options.
- * Outputs:
- * file.gz: compressed file with same mode, owner, and utimes
- * or stdout with -c option or if stdin used as input.
- * If the output file name had to be truncated, the original name is kept
- * in the compressed file.
- * On MSDOS, file.tmp -> file.tmz. On VMS, file.tmp -> file.tmp-gz.
- *
- * Using gz on MSDOS would create too many file name conflicts. For
- * example, foo.txt -> foo.tgz (.tgz must be reserved as shorthand for
- * tar.gz). Similarly, foo.dir and foo.doc would both be mapped to foo.dgz.
- * I also considered 12345678.txt -> 12345txt.gz but this truncates the name
- * too heavily. There is no ideal solution given the MSDOS 8+3 limitation.
- *
- * For the meaning of all compilation flags, see comments in Makefile.in.
- */
-
-#ifdef RCSID
-static char rcsid[] = "$Id: gzip.c,v 0.24 1993/06/24 10:52:07 jloup Exp $";
-#endif
-
-/* revision.h -- define the version number
- * Copyright (C) 1998, 1999, 2001, 2002 Free Software Foundation, Inc.
- * 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.
- */
-
-#define PATCHLEVEL 0
-#define REVDATE "2002-09-30"
-
-/* This version does not support compression into old compress format: */
-#ifdef LZW
-# undef LZW
-#endif
-
-/* $Id: revision.h,v 0.25 1993/06/24 08:29:52 jloup Exp $ */
-
-
- /* configuration */
-
-# define NAMLEN(direct) strlen((direct)->d_name)
-# define DIR_OPT "DIRENT"
-#ifndef NO_DIR
-# define NO_DIR 0
-#endif
-
-#ifdef CLOSEDIR_VOID
-# define CLOSEDIR(d) (closedir(d), 0)
-#else
-# define CLOSEDIR(d) closedir(d)
-#endif
-
-#if !defined(HAVE_LSTAT) && !defined(lstat)
-# define lstat(name, buf) stat(name, buf)
-#endif
-
-# define TIME_OPT "UTIME"
-
-#if !defined(S_ISDIR) && defined(S_IFDIR)
-# define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR)
-#endif
-#if !defined(S_ISREG) && defined(S_IFREG)
-# define S_ISREG(m) (((m) & S_IFMT) == S_IFREG)
-#endif
-
-typedef RETSIGTYPE (*sig_type) OF((int));
-
-#ifndef O_BINARY
-# define O_BINARY 0 /* creation mode for open() */
-#endif
-
-
-#ifndef S_IRUSR
-# define S_IRUSR 0400
-#endif
-#ifndef S_IWUSR
-# define S_IWUSR 0200
-#endif
-#define RW_USER (S_IRUSR | S_IWUSR) /* creation mode for open() */
-
-#ifndef MAX_PATH_LEN
-# define MAX_PATH_LEN 1024 /* max pathname length */
-#endif
-
-#ifndef SEEK_END
-# define SEEK_END 2
-#endif
-
-#ifndef CHAR_BIT
-# define CHAR_BIT 8
-#endif
-
-#ifdef off_t
- off_t lseek OF((int fd, off_t offset, int whence));
-#endif
-
-#ifndef OFF_T_MIN
-#define OFF_T_MIN (~ (off_t) 0 << (sizeof (off_t) * CHAR_BIT - 1))
-#endif
-
-#ifndef OFF_T_MAX
-#define OFF_T_MAX (~ (off_t) 0 - OFF_T_MIN)
-#endif
-
-/* Separator for file name parts (see shorten_name()) */
-#ifdef NO_MULTIPLE_DOTS
-# define PART_SEP "-"
-#else
-# define PART_SEP "."
-#endif
-
- /* global buffers */
-
-DECLARE(uch, inbuf, INBUFSIZ +INBUF_EXTRA);
-DECLARE(uch, outbuf, OUTBUFSIZ+OUTBUF_EXTRA);
-DECLARE(ush, d_buf, DIST_BUFSIZE);
-DECLARE(uch, window, 2L*WSIZE);
-#ifndef MAXSEG_64K
- DECLARE(ush, tab_prefix, 1L<<BITS);
-#else
- DECLARE(ush, tab_prefix0, 1L<<(BITS-1));
- DECLARE(ush, tab_prefix1, 1L<<(BITS-1));
-#endif
-
- /* local variables */
-
-int ascii = 0; /* convert end-of-lines to local OS conventions */
-int to_stdout = 0; /* output to stdout (-c) */
-int decompress = 0; /* decompress (-d) */
-int force = 0; /* don't ask questions, compress links (-f) */
-int no_name = -1; /* don't save or restore the original file name */
-int no_time = -1; /* don't save or restore the original file time */
-int recursive = 0; /* recurse through directories (-r) */
-int list = 0; /* list the file contents (-l) */
-int verbose = 0; /* be verbose (-v) */
-int quiet = 0; /* be very quiet (-q) */
-int do_lzw = 0; /* generate output compatible with old compress (-Z) */
-int test = 0; /* test .gz file integrity */
-int foreground; /* set if program run in foreground */
-char *progname; /* program name */
-int maxbits = BITS; /* max bits per code for LZW */
-int method = DEFLATED;/* compression method */
-int level = 6; /* compression level */
-int exit_code = OK; /* program exit code */
-int save_orig_name; /* set if original name must be saved */
-int last_member; /* set for .zip and .Z files */
-int part_nb; /* number of parts in .gz file */
-time_t time_stamp; /* original time stamp (modification time) */
-off_t ifile_size; /* input file size, -1 for devices (debug only) */
-char *env; /* contents of GZIP env variable */
-char **args = NULL; /* argv pointer if GZIP env variable defined */
-char *z_suffix; /* default suffix (can be set with --suffix) */
-size_t z_len; /* strlen(z_suffix) */
-
-off_t bytes_in; /* number of input bytes */
-off_t bytes_out; /* number of output bytes */
-off_t total_in; /* input bytes for all files */
-off_t total_out; /* output bytes for all files */
-char ifname[MAX_PATH_LEN]; /* input file name */
-char ofname[MAX_PATH_LEN]; /* output file name */
-int remove_ofname = 0; /* remove output file on error */
-struct stat istat; /* status for input file */
-int ifd; /* input file descriptor */
-int ofd; /* output file descriptor */
-unsigned insize; /* valid bytes in inbuf */
-unsigned inptr; /* index of next byte to be processed in inbuf */
-unsigned outcnt; /* bytes in output buffer */
-int rsync = 0; /* make ryncable chunks */
-
-struct option longopts[] =
-{
- /* { name has_arg *flag val } */
- {"ascii", 0, 0, 'a'}, /* ascii text mode */
- {"to-stdout", 0, 0, 'c'}, /* write output on standard output */
- {"stdout", 0, 0, 'c'}, /* write output on standard output */
- {"decompress", 0, 0, 'd'}, /* decompress */
- {"uncompress", 0, 0, 'd'}, /* decompress */
- /* {"encrypt", 0, 0, 'e'}, encrypt */
- {"force", 0, 0, 'f'}, /* force overwrite of output file */
- {"help", 0, 0, 'h'}, /* give help */
- /* {"pkzip", 0, 0, 'k'}, force output in pkzip format */
- {"list", 0, 0, 'l'}, /* list .gz file contents */
- {"license", 0, 0, 'L'}, /* display software license */
- {"no-name", 0, 0, 'n'}, /* don't save or restore original name & time */
- {"name", 0, 0, 'N'}, /* save or restore original name & time */
- {"quiet", 0, 0, 'q'}, /* quiet mode */
- {"silent", 0, 0, 'q'}, /* quiet mode */
- {"recursive", 0, 0, 'r'}, /* recurse through directories */
- {"suffix", 1, 0, 'S'}, /* use given suffix instead of .gz */
- {"test", 0, 0, 't'}, /* test compressed file integrity */
- {"no-time", 0, 0, 'T'}, /* don't save or restore the time stamp */
- {"verbose", 0, 0, 'v'}, /* verbose mode */
- {"version", 0, 0, 'V'}, /* display version number */
- {"fast", 0, 0, '1'}, /* compress faster */
- {"best", 0, 0, '9'}, /* compress better */
- {"lzw", 0, 0, 'Z'}, /* make output compatible with old compress */
- {"bits", 1, 0, 'b'}, /* max number of bits per code (implies -Z) */
- {"rsyncable", 0, 0, 'R'}, /* make rsync-friendly archive */
- { 0, 0, 0, 0 }
-};
-
-/* local functions */
-
-local void usage OF((void));
-local void help OF((void));
-local void license OF((void));
-local void version OF((void));
-local int input_eof OF((void));
-local void treat_stdin OF((void));
-local void treat_file OF((char *iname));
-local int create_outfile OF((void));
-local int do_stat OF((char *name, struct stat *sbuf));
-local char *get_suffix OF((char *name));
-local int get_istat OF((char *iname, struct stat *sbuf));
-local int make_ofname OF((void));
-local int same_file OF((struct stat *stat1, struct stat *stat2));
-local int name_too_long OF((char *name, struct stat *statb));
-local void shorten_name OF((char *name));
-local int get_method OF((int in));
-local void do_list OF((int ifd, int method));
-local int check_ofname OF((void));
-local void copy_stat OF((struct stat *ifstat));
-local void do_exit OF((int exitcode));
- int main OF((int argc, char **argv));
-int (*work) OF((int infile, int outfile)) = zip; /* function to call */
-
-#if ! NO_DIR
-local void treat_dir OF((char *dir));
-#endif
-#ifdef HAVE_UTIME
-local void reset_times OF((char *name, struct stat *statb));
-#endif
-
-#define strequ(s1, s2) (strcmp((s1),(s2)) == 0)
-
-/* ======================================================================== */
-local void usage()
-{
- printf ("usage: %s [-%scdfhlLnN%stvV19] [-S suffix] [file ...]\n",
- progname,
- O_BINARY ? "a" : "", NO_DIR ? "" : "r");
-}
-
-/* ======================================================================== */
-local void help()
-{
- static char *help_msg[] = {
-#if O_BINARY
- " -a --ascii ascii text; convert end-of-lines using local conventions",
-#endif
- " -c --stdout write on standard output, keep original files unchanged",
- " -d --decompress decompress",
-/* -e --encrypt encrypt */
- " -f --force force overwrite of output file and compress links",
- " -h --help give this help",
-/* -k --pkzip force output in pkzip format */
- " -l --list list compressed file contents",
- " -L --license display software license",
-#ifdef UNDOCUMENTED
- " -m --no-time do not save or restore the original modification time",
- " -M --time save or restore the original modification time",
-#endif
- " -n --no-name do not save or restore the original name and time stamp",
- " -N --name save or restore the original name and time stamp",
- " -q --quiet suppress all warnings",
-#if ! NO_DIR
- " -r --recursive operate recursively on directories",
-#endif
- " -S .suf --suffix .suf use suffix .suf on compressed files",
- " -t --test test compressed file integrity",
- " -v --verbose verbose mode",
- " -V --version display version number",
- " -1 --fast compress faster",
- " -9 --best compress better",
-#ifdef LZW
- " -Z --lzw produce output compatible with old compress",
- " -b --bits maxbits max number of bits per code (implies -Z)",
-#endif
- " --rsyncable Make rsync-friendly archive",
- " file... files to (de)compress. If none given, use standard input.",
- "Report bugs to <bug-gzip at gnu.org>.",
- 0};
- char **p = help_msg;
-
- printf ("%s %s\n(%s)\n", progname, VERSION, REVDATE);
- usage();
- while (*p) printf ("%s\n", *p++);
-}
-
-/* ======================================================================== */
-local void license()
-{
- char **p = license_msg;
-
- printf ("%s %s\n(%s)\n", progname, VERSION, REVDATE);
- while (*p) printf ("%s\n", *p++);
-}
-
-/* ======================================================================== */
-local void version()
-{
- license ();
- printf ("Compilation options:\n%s %s ", DIR_OPT, TIME_OPT);
-#ifdef STDC_HEADERS
- printf ("STDC_HEADERS ");
-#endif
-#ifdef HAVE_UNISTD_H
- printf ("HAVE_UNISTD_H ");
-#endif
-#ifdef HAVE_MEMORY_H
- printf ("HAVE_MEMORY_H ");
-#endif
-#ifdef HAVE_STRING_H
- printf ("HAVE_STRING_H ");
-#endif
-#ifdef HAVE_LSTAT
- printf ("HAVE_LSTAT ");
-#endif
-#ifdef NO_MULTIPLE_DOTS
- printf ("NO_MULTIPLE_DOTS ");
-#endif
-#ifdef HAVE_CHOWN
- printf ("HAVE_CHOWN ");
-#endif
-#ifdef PROTO
- printf ("PROTO ");
-#endif
-#ifdef ASMV
- printf ("ASMV ");
-#endif
-#ifdef DEBUG
- printf ("DEBUG ");
-#endif
-#ifdef DYN_ALLOC
- printf ("DYN_ALLOC ");
-#endif
-#ifdef MAXSEG_64K
- printf ("MAXSEG_64K");
-#endif
- printf ("\n");
- printf ("Written by Jean-loup Gailly.\n");
-}
-
-local void progerror (string)
- char *string;
-{
- int e = errno;
- fprintf(stderr, "%s: ", progname);
- errno = e;
- perror(string);
- exit_code = ERROR;
-}
-
-/* ======================================================================== */
-int main (argc, argv)
- int argc;
- char **argv;
-{
- int file_count; /* number of files to precess */
- int proglen; /* length of progname */
- int optc; /* current option */
-
- EXPAND(argc, argv); /* wild card expansion if necessary */
-
- progname = base_name (argv[0]);
- proglen = strlen(progname);
-
- /* Suppress .exe for MSDOS, OS/2 and VMS: */
- if (proglen > 4 && strequ(progname+proglen-4, ".exe")) {
- progname[proglen-4] = '\0';
- }
-
- /* Add options in GZIP environment variable if there is one */
- env = add_envopt(&argc, &argv, OPTIONS_VAR);
- if (env != NULL) args = argv;
-
- foreground = signal(SIGINT, SIG_IGN) != SIG_IGN;
- if (foreground) {
- (void) signal (SIGINT, (sig_type)abort_gzip_signal);
- }
-#ifdef SIGTERM
- if (signal(SIGTERM, SIG_IGN) != SIG_IGN) {
- (void) signal(SIGTERM, (sig_type)abort_gzip_signal);
- }
-#endif
-#ifdef SIGHUP
- if (signal(SIGHUP, SIG_IGN) != SIG_IGN) {
- (void) signal(SIGHUP, (sig_type)abort_gzip_signal);
- }
-#endif
-
-#ifndef GNU_STANDARD
- /* For compatibility with old compress, use program name as an option.
- * If you compile with -DGNU_STANDARD, this program will behave as
- * gzip even if it is invoked under the name gunzip or zcat.
- *
- * Systems which do not support links can still use -d or -dc.
- * Ignore an .exe extension for MSDOS, OS/2 and VMS.
- */
- if ( strncmp(progname, "un", 2) == 0 /* ungzip, uncompress */
- || strncmp(progname, "gun", 3) == 0) { /* gunzip */
- decompress = 1;
- } else if (strequ(progname+1, "cat") /* zcat, pcat, gcat */
- || strequ(progname, "gzcat")) { /* gzcat */
- decompress = to_stdout = 1;
- }
-#endif
-
- z_suffix = Z_SUFFIX;
- z_len = strlen(z_suffix);
-
- while ((optc = getopt_long (argc, argv, "ab:cdfhH?lLmMnNqrS:tvVZ123456789",
- longopts, (int *)0)) != -1) {
- switch (optc) {
- case 'a':
- ascii = 1; break;
- case 'b':
- maxbits = atoi(optarg);
- for (; *optarg; optarg++)
- if (! ('0' <= *optarg && *optarg <= '9'))
- {
- fprintf (stderr, "%s: -b operand is not an integer\n",
- progname);
- usage ();
- do_exit (ERROR);
- }
- break;
- case 'c':
- to_stdout = 1; break;
- case 'd':
- decompress = 1; break;
- case 'f':
- force++; break;
- case 'h': case 'H': case '?':
- help(); do_exit(OK); break;
- case 'l':
- list = decompress = to_stdout = 1; break;
- case 'L':
- license(); do_exit(OK); break;
- case 'm': /* undocumented, may change later */
- no_time = 1; break;
- case 'M': /* undocumented, may change later */
- no_time = 0; break;
- case 'n':
- no_name = no_time = 1; break;
- case 'N':
- no_name = no_time = 0; break;
- case 'q':
- quiet = 1; verbose = 0; break;
- case 'r':
-#if NO_DIR
- fprintf(stderr, "%s: -r not supported on this system\n", progname);
- usage();
- do_exit(ERROR); break;
-#else
- recursive = 1; break;
-#endif
- case 'R':
- rsync = 1; break;
-
- case 'S':
-#ifdef NO_MULTIPLE_DOTS
- if (*optarg == '.') optarg++;
-#endif
- z_len = strlen(optarg);
- z_suffix = optarg;
- break;
- case 't':
- test = decompress = to_stdout = 1;
- break;
- case 'v':
- verbose++; quiet = 0; break;
- case 'V':
- version(); do_exit(OK); break;
- case 'Z':
-#ifdef LZW
- do_lzw = 1; break;
-#else
- fprintf(stderr, "%s: -Z not supported in this version\n",
- progname);
- usage();
- do_exit(ERROR); break;
-#endif
- case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- level = optc - '0';
- break;
- default:
- /* Error message already emitted by getopt_long. */
- usage();
- do_exit(ERROR);
- }
- } /* loop on all arguments */
-
-#ifdef SIGPIPE
- /* Ignore "Broken Pipe" message with --quiet */
- if (quiet && signal (SIGPIPE, SIG_IGN) != SIG_IGN)
- signal (SIGPIPE, (sig_type) abort_gzip_signal);
-#endif
-
- /* By default, save name and timestamp on compression but do not
- * restore them on decompression.
- */
- if (no_time < 0) no_time = decompress;
- if (no_name < 0) no_name = decompress;
-
- file_count = argc - optind;
-
-#if O_BINARY
-#else
- if (ascii && !quiet) {
- fprintf(stderr, "%s: option --ascii ignored on this system\n",
- progname);
- }
-#endif
- if ((z_len == 0 && !decompress) || z_len > MAX_SUFFIX) {
- fprintf(stderr, "%s: incorrect suffix '%s'\n",
- progname, z_suffix);
- do_exit(ERROR);
- }
- if (do_lzw && !decompress) work = lzw;
-
- /* Allocate all global buffers (for DYN_ALLOC option) */
- ALLOC(uch, inbuf, INBUFSIZ +INBUF_EXTRA);
- ALLOC(uch, outbuf, OUTBUFSIZ+OUTBUF_EXTRA);
- ALLOC(ush, d_buf, DIST_BUFSIZE);
- ALLOC(uch, window, 2L*WSIZE);
-#ifndef MAXSEG_64K
- ALLOC(ush, tab_prefix, 1L<<BITS);
-#else
- ALLOC(ush, tab_prefix0, 1L<<(BITS-1));
- ALLOC(ush, tab_prefix1, 1L<<(BITS-1));
-#endif
-
- /* And get to work */
- if (file_count != 0) {
- if (to_stdout && !test && !list && (!decompress || !ascii)) {
- SET_BINARY_MODE(fileno(stdout));
- }
- while (optind < argc) {
- treat_file(argv[optind++]);
- }
- } else { /* Standard input */
- treat_stdin();
- }
- if (list && !quiet && file_count > 1) {
- do_list(-1, -1); /* print totals */
- }
- do_exit(exit_code);
- return exit_code; /* just to avoid lint warning */
-}
-
-/* Return nonzero when at end of file on input. */
-local int
-input_eof ()
-{
- if (!decompress || last_member)
- return 1;
-
- if (inptr == insize)
- {
- if (insize != INBUFSIZ || fill_inbuf (1) == EOF)
- return 1;
-
- /* Unget the char that fill_inbuf got. */
- inptr = 0;
- }
-
- return 0;
-}
-
-/* ========================================================================
- * Compress or decompress stdin
- */
-local void treat_stdin()
-{
- if (!force && !list &&
- isatty(fileno((FILE *)(decompress ? stdin : stdout)))) {
- /* Do not send compressed data to the terminal or read it from
- * the terminal. We get here when user invoked the program
- * without parameters, so be helpful. According to the GNU standards:
- *
- * If there is one behavior you think is most useful when the output
- * is to a terminal, and another that you think is most useful when
- * the output is a file or a pipe, then it is usually best to make
- * the default behavior the one that is useful with output to a
- * terminal, and have an option for the other behavior.
- *
- * Here we use the --force option to get the other behavior.
- */
- fprintf(stderr,
- "%s: compressed data not %s a terminal. Use -f to force %scompression.\n",
- progname, decompress ? "read from" : "written to",
- decompress ? "de" : "");
- fprintf(stderr,"For help, type: %s -h\n", progname);
- do_exit(ERROR);
- }
-
- if (decompress || !ascii) {
- SET_BINARY_MODE(fileno(stdin));
- }
- if (!test && !list && (!decompress || !ascii)) {
- SET_BINARY_MODE(fileno(stdout));
- }
- strcpy(ifname, "stdin");
- strcpy(ofname, "stdout");
-
- /* Get the time stamp on the input file. */
- time_stamp = 0; /* time unknown by default */
-
-#ifndef NO_STDIN_FSTAT
- if (list || !no_time) {
- if (fstat(fileno(stdin), &istat) != 0) {
- progerror("standard input");
- do_exit(ERROR);
- }
-# ifdef NO_PIPE_TIMESTAMP
- if (S_ISREG(istat.st_mode))
-# endif
- time_stamp = istat.st_mtime;
-#endif /* NO_STDIN_FSTAT */
- }
- ifile_size = -1L; /* convention for unknown size */
-
- clear_bufs(); /* clear input and output buffers */
- to_stdout = 1;
- part_nb = 0;
-
- if (decompress) {
- method = get_method(ifd);
- if (method < 0) {
- do_exit(exit_code); /* error message already emitted */
- }
- }
- if (list) {
- do_list(ifd, method);
- return;
- }
-
- /* Actually do the compression/decompression. Loop over zipped members.
- */
- for (;;) {
- if ((*work)(fileno(stdin), fileno(stdout)) != OK) return;
-
- if (input_eof ())
- break;
-
- method = get_method(ifd);
- if (method < 0) return; /* error message already emitted */
- bytes_out = 0; /* required for length check */
- }
-
- if (verbose) {
- if (test) {
- fprintf(stderr, " OK\n");
-
- } else if (!decompress) {
- display_ratio(bytes_in-(bytes_out-header_bytes), bytes_in, stderr);
- fprintf(stderr, "\n");
-#ifdef DISPLAY_STDIN_RATIO
- } else {
- display_ratio(bytes_out-(bytes_in-header_bytes), bytes_out,stderr);
- fprintf(stderr, "\n");
-#endif
- }
- }
-}
-
-/* ========================================================================
- * Compress or decompress the given file
- */
-local void treat_file(iname)
- char *iname;
-{
- /* Accept "-" as synonym for stdin */
- if (strequ(iname, "-")) {
- int cflag = to_stdout;
- treat_stdin();
- to_stdout = cflag;
- return;
- }
-
- /* Check if the input file is present, set ifname and istat: */
- if (get_istat(iname, &istat) != OK) return;
-
- /* If the input name is that of a directory, recurse or ignore: */
- if (S_ISDIR(istat.st_mode)) {
-#if ! NO_DIR
- if (recursive) {
- struct stat st;
- st = istat;
- treat_dir(iname);
- /* Warning: ifname is now garbage */
-# ifndef NO_UTIME
- reset_times (iname, &st);
-# endif
- } else
-#endif
- WARN((stderr,"%s: %s is a directory -- ignored\n", progname, ifname));
- return;
- }
- if (!S_ISREG(istat.st_mode)) {
- WARN((stderr,
- "%s: %s is not a directory or a regular file - ignored\n",
- progname, ifname));
- return;
- }
- if (istat.st_nlink > 1 && !to_stdout && !force) {
- WARN((stderr, "%s: %s has %lu other link%c -- unchanged\n",
- progname, ifname, (unsigned long) istat.st_nlink - 1,
- istat.st_nlink > 2 ? 's' : ' '));
- return;
- }
-
- ifile_size = istat.st_size;
- time_stamp = no_time && !list ? 0 : istat.st_mtime;
-
- /* Generate output file name. For -r and (-t or -l), skip files
- * without a valid gzip suffix (check done in make_ofname).
- */
- if (to_stdout && !list && !test) {
- strcpy(ofname, "stdout");
-
- } else if (make_ofname() != OK) {
- return;
- }
-
- /* Open the input file and determine compression method. The mode
- * parameter is ignored but required by some systems (VMS) and forbidden
- * on other systems (MacOS).
- */
- ifd = OPEN(ifname, ascii && !decompress ? O_RDONLY : O_RDONLY | O_BINARY,
- RW_USER);
- if (ifd == -1) {
- progerror(ifname);
- return;
- }
- clear_bufs(); /* clear input and output buffers */
- part_nb = 0;
-
- if (decompress) {
- method = get_method(ifd); /* updates ofname if original given */
- if (method < 0) {
- close(ifd);
- return; /* error message already emitted */
- }
- }
- if (list) {
- do_list(ifd, method);
- close(ifd);
- return;
- }
-
- /* If compressing to a file, check if ofname is not ambiguous
- * because the operating system truncates names. Otherwise, generate
- * a new ofname and save the original name in the compressed file.
- */
- if (to_stdout) {
- ofd = fileno(stdout);
- /* keep remove_ofname as zero */
- } else {
- if (create_outfile() != OK) return;
-
- if (!decompress && save_orig_name && !verbose && !quiet) {
- fprintf(stderr, "%s: %s compressed to %s\n",
- progname, ifname, ofname);
- }
- }
- /* Keep the name even if not truncated except with --no-name: */
- if (!save_orig_name) save_orig_name = !no_name;
-
- if (verbose) {
- fprintf(stderr, "%s:\t", ifname);
- }
-
- /* Actually do the compression/decompression. Loop over zipped members.
- */
- for (;;) {
- if ((*work)(ifd, ofd) != OK) {
- method = -1; /* force cleanup */
- break;
- }
-
- if (input_eof ())
- break;
-
- method = get_method(ifd);
- if (method < 0) break; /* error message already emitted */
- bytes_out = 0; /* required for length check */
- }
-
- close(ifd);
- if (!to_stdout) {
- /* Copy modes, times, ownership, and remove the input file */
- copy_stat(&istat);
- if (close(ofd))
- write_error();
- }
- if (method == -1) {
- if (!to_stdout) xunlink (ofname);
- return;
- }
- /* Display statistics */
- if(verbose) {
- if (test) {
- fprintf(stderr, " OK");
- } else if (decompress) {
- display_ratio(bytes_out-(bytes_in-header_bytes), bytes_out,stderr);
- } else {
- display_ratio(bytes_in-(bytes_out-header_bytes), bytes_in, stderr);
- }
- if (!test && !to_stdout) {
- fprintf(stderr, " -- replaced with %s", ofname);
- }
- fprintf(stderr, "\n");
- }
-}
-
-/* ========================================================================
- * Create the output file. Return OK or ERROR.
- * Try several times if necessary to avoid truncating the z_suffix. For
- * example, do not create a compressed file of name "1234567890123."
- * Sets save_orig_name to true if the file name has been truncated.
- * IN assertions: the input file has already been open (ifd is set) and
- * ofname has already been updated if there was an original name.
- * OUT assertions: ifd and ofd are closed in case of error.
- */
-local int create_outfile()
-{
- struct stat ostat; /* stat for ofname */
- int flags = O_WRONLY | O_CREAT | O_EXCL | O_BINARY;
-
- if (ascii && decompress) {
- flags &= ~O_BINARY; /* force ascii text mode */
- }
- for (;;) {
- /* Make sure that ofname is not an existing file */
- if (check_ofname() != OK) {
- close(ifd);
- return ERROR;
- }
- /* Create the output file */
- remove_ofname = 1;
- ofd = OPEN(ofname, flags, RW_USER);
- if (ofd == -1) {
- progerror(ofname);
- close(ifd);
- return ERROR;
- }
-
- /* Check for name truncation on new file (1234567890123.gz) */
-#ifdef NO_FSTAT
- if (stat(ofname, &ostat) != 0) {
-#else
- if (fstat(ofd, &ostat) != 0) {
-#endif
- progerror(ofname);
- close(ifd); close(ofd);
- xunlink (ofname);
- return ERROR;
- }
- if (!name_too_long(ofname, &ostat)) return OK;
-
- if (decompress) {
- /* name might be too long if an original name was saved */
- WARN((stderr, "%s: %s: warning, name truncated\n",
- progname, ofname));
- return OK;
- }
- close(ofd);
- xunlink (ofname);
-#ifdef NO_MULTIPLE_DOTS
- /* Should never happen, see check_ofname() */
- fprintf(stderr, "%s: %s: name too long\n", progname, ofname);
- do_exit(ERROR);
-#endif
- shorten_name(ofname);
- }
-}
-
-/* ========================================================================
- * Use lstat if available, except for -c or -f. Use stat otherwise.
- * This allows links when not removing the original file.
- */
-local int do_stat(name, sbuf)
- char *name;
- struct stat *sbuf;
-{
- errno = 0;
- if (!to_stdout && !force) {
- return lstat(name, sbuf);
- }
- return stat(name, sbuf);
-}
-
-/* ========================================================================
- * Return a pointer to the 'z' suffix of a file name, or NULL. For all
- * systems, ".gz", ".z", ".Z", ".taz", ".tgz", "-gz", "-z" and "_z" are
- * accepted suffixes, in addition to the value of the --suffix option.
- * ".tgz" is a useful convention for tar.z files on systems limited
- * to 3 characters extensions. On such systems, ".?z" and ".??z" are
- * also accepted suffixes. For Unix, we do not want to accept any
- * .??z suffix as indicating a compressed file; some people use .xyz
- * to denote volume data.
- * On systems allowing multiple versions of the same file (such as VMS),
- * this function removes any version suffix in the given name.
- */
-local char *get_suffix(name)
- char *name;
-{
- int nlen, slen;
- char suffix[MAX_SUFFIX+3]; /* last chars of name, forced to lower case */
- static char *known_suffixes[] =
- {NULL, ".gz", ".z", ".taz", ".tgz", "-gz", "-z", "_z",
-#ifdef MAX_EXT_CHARS
- "z",
-#endif
- NULL};
- char **suf = known_suffixes;
-
- *suf = z_suffix;
- if (strequ(z_suffix, "z")) suf++; /* check long suffixes first */
-
-#ifdef SUFFIX_SEP
- /* strip a version number from the file name */
- {
- char *v = strrchr(name, SUFFIX_SEP);
- if (v != NULL) *v = '\0';
- }
-#endif
- nlen = strlen(name);
- if (nlen <= MAX_SUFFIX+2) {
- strcpy(suffix, name);
- } else {
- strcpy(suffix, name+nlen-MAX_SUFFIX-2);
- }
- strlwr(suffix);
- slen = strlen(suffix);
- do {
- int s = strlen(*suf);
- if (slen > s && suffix[slen-s-1] != PATH_SEP
- && strequ(suffix + slen - s, *suf)) {
- return name+nlen-s;
- }
- } while (*++suf != NULL);
-
- return NULL;
-}
-
-
-/* ========================================================================
- * Set ifname to the input file name (with a suffix appended if necessary)
- * and istat to its stats. For decompression, if no file exists with the
- * original name, try adding successively z_suffix, .gz, .z, -z and .Z.
- * For MSDOS, we try only z_suffix and z.
- * Return OK or ERROR.
- */
-local int get_istat(iname, sbuf)
- char *iname;
- struct stat *sbuf;
-{
- int ilen; /* strlen(ifname) */
- int z_suffix_errno = 0;
- static char *suffixes[] = {NULL, ".gz", ".z", "-z", ".Z", NULL};
- char **suf = suffixes;
- char *s;
-#ifdef NO_MULTIPLE_DOTS
- char *dot; /* pointer to ifname extension, or NULL */
-#endif
-
- *suf = z_suffix;
-
- if (sizeof ifname - 1 <= strlen (iname))
- goto name_too_long;
-
- strcpy(ifname, iname);
-
- /* If input file exists, return OK. */
- if (do_stat(ifname, sbuf) == 0) return OK;
-
- if (!decompress || errno != ENOENT) {
- progerror(ifname);
- return ERROR;
- }
- /* file.ext doesn't exist, try adding a suffix (after removing any
- * version number for VMS).
- */
- s = get_suffix(ifname);
- if (s != NULL) {
- progerror(ifname); /* ifname already has z suffix and does not exist */
- return ERROR;
- }
-#ifdef NO_MULTIPLE_DOTS
- dot = strrchr(ifname, '.');
- if (dot == NULL) {
- strcat(ifname, ".");
- dot = strrchr(ifname, '.');
- }
-#endif
- ilen = strlen(ifname);
- if (strequ(z_suffix, ".gz")) suf++;
-
- /* Search for all suffixes */
- do {
- char *s0 = s = *suf;
- strcpy (ifname, iname);
-#ifdef NO_MULTIPLE_DOTS
- if (*s == '.') s++;
- if (*dot == '\0') strcpy (dot, ".");
-#endif
-#ifdef MAX_EXT_CHARS
- if (MAX_EXT_CHARS < strlen (s) + strlen (dot + 1))
- dot[MAX_EXT_CHARS + 1 - strlen (s)] = '\0';
-#endif
- if (sizeof ifname <= ilen + strlen (s))
- goto name_too_long;
- strcat(ifname, s);
- if (do_stat(ifname, sbuf) == 0) return OK;
- if (strequ (s0, z_suffix))
- z_suffix_errno = errno;
- } while (*++suf != NULL);
-
- /* No suffix found, complain using z_suffix: */
- strcpy(ifname, iname);
-#ifdef NO_MULTIPLE_DOTS
- if (*dot == '\0') strcpy(dot, ".");
-#endif
-#ifdef MAX_EXT_CHARS
- if (MAX_EXT_CHARS < z_len + strlen (dot + 1))
- dot[MAX_EXT_CHARS + 1 - z_len] = '\0';
-#endif
- strcat(ifname, z_suffix);
- errno = z_suffix_errno;
- progerror(ifname);
- return ERROR;
-
- name_too_long:
- fprintf (stderr, "%s: %s: file name too long\n", progname, iname);
- exit_code = ERROR;
- return ERROR;
-}
-
-/* ========================================================================
- * Generate ofname given ifname. Return OK, or WARNING if file must be skipped.
- * Sets save_orig_name to true if the file name has been truncated.
- */
-local int make_ofname()
-{
- char *suff; /* ofname z suffix */
-
- strcpy(ofname, ifname);
- /* strip a version number if any and get the gzip suffix if present: */
- suff = get_suffix(ofname);
-
- if (decompress) {
- if (suff == NULL) {
- /* With -t or -l, try all files (even without .gz suffix)
- * except with -r (behave as with just -dr).
- */
- if (!recursive && (list || test)) return OK;
-
- /* Avoid annoying messages with -r */
- if (verbose || (!recursive && !quiet)) {
- WARN((stderr,"%s: %s: unknown suffix -- ignored\n",
- progname, ifname));
- }
- return WARNING;
- }
- /* Make a special case for .tgz and .taz: */
- strlwr(suff);
- if (strequ(suff, ".tgz") || strequ(suff, ".taz")) {
- strcpy(suff, ".tar");
- } else {
- *suff = '\0'; /* strip the z suffix */
- }
- /* ofname might be changed later if infile contains an original name */
-
- } else if (suff != NULL) {
- /* Avoid annoying messages with -r (see treat_dir()) */
- if (verbose || (!recursive && !quiet)) {
- /* don't use WARN -- it will cause an exit_code of 2 */
- fprintf(stderr, "%s: %s already has %s suffix -- unchanged\n",
- progname, ifname, suff);
- }
- return WARNING;
- } else {
- save_orig_name = 0;
-
-#ifdef NO_MULTIPLE_DOTS
- suff = strrchr(ofname, '.');
- if (suff == NULL) {
- if (sizeof ofname <= strlen (ofname) + 1)
- goto name_too_long;
- strcat(ofname, ".");
-# ifdef MAX_EXT_CHARS
- if (strequ(z_suffix, "z")) {
- if (sizeof ofname <= strlen (ofname) + 2)
- goto name_too_long;
- strcat(ofname, "gz"); /* enough room */
- return OK;
- }
- /* On the Atari and some versions of MSDOS, name_too_long()
- * does not work correctly because of a bug in stat(). So we
- * must truncate here.
- */
- } else if (strlen(suff)-1 + z_len > MAX_SUFFIX) {
- suff[MAX_SUFFIX+1-z_len] = '\0';
- save_orig_name = 1;
-# endif
- }
-#endif /* NO_MULTIPLE_DOTS */
- if (sizeof ofname <= strlen (ofname) + z_len)
- goto name_too_long;
- strcat(ofname, z_suffix);
-
- } /* decompress ? */
- return OK;
-
- name_too_long:
- WARN ((stderr, "%s: %s: file name too long\n", progname, ifname));
- return WARNING;
-}
-
-
-/* ========================================================================
- * Check the magic number of the input file and update ofname if an
- * original name was given and to_stdout is not set.
- * Return the compression method, -1 for error, -2 for warning.
- * Set inptr to the offset of the next byte to be processed.
- * Updates time_stamp if there is one and --no-time is not used.
- * This function may be called repeatedly for an input file consisting
- * of several contiguous gzip'ed members.
- * IN assertions: there is at least one remaining compressed member.
- * If the member is a zip file, it must be the only one.
- */
-local int get_method(in)
- int in; /* input file descriptor */
-{
- uch flags; /* compression flags */
- char magic[2]; /* magic header */
- int imagic1; /* like magic[1], but can represent EOF */
- ulg stamp; /* time stamp */
-
- /* If --force and --stdout, zcat == cat, so do not complain about
- * premature end of file: use try_byte instead of get_byte.
- */
- if (force && to_stdout) {
- magic[0] = (char)try_byte();
- imagic1 = try_byte ();
- magic[1] = (char) imagic1;
- /* If try_byte returned EOF, magic[1] == (char) EOF. */
- } else {
- magic[0] = (char)get_byte();
- magic[1] = (char)get_byte();
- imagic1 = 0; /* avoid lint warning */
- }
- method = -1; /* unknown yet */
- part_nb++; /* number of parts in gzip file */
- header_bytes = 0;
- last_member = RECORD_IO;
- /* assume multiple members in gzip file except for record oriented I/O */
-
- if (memcmp(magic, GZIP_MAGIC, 2) == 0
- || memcmp(magic, OLD_GZIP_MAGIC, 2) == 0) {
-
- method = (int)get_byte();
- if (method != DEFLATED) {
- fprintf(stderr,
- "%s: %s: unknown method %d -- not supported\n",
- progname, ifname, method);
- exit_code = ERROR;
- return -1;
- }
- work = unzip;
- flags = (uch)get_byte();
-
- if ((flags & ENCRYPTED) != 0) {
- fprintf(stderr,
- "%s: %s is encrypted -- not supported\n",
- progname, ifname);
- exit_code = ERROR;
- return -1;
- }
- if ((flags & CONTINUATION) != 0) {
- fprintf(stderr,
- "%s: %s is a a multi-part gzip file -- not supported\n",
- progname, ifname);
- exit_code = ERROR;
- if (force <= 1) return -1;
- }
- if ((flags & RESERVED) != 0) {
- fprintf(stderr,
- "%s: %s has flags 0x%x -- not supported\n",
- progname, ifname, flags);
- exit_code = ERROR;
- if (force <= 1) return -1;
- }
- stamp = (ulg)get_byte();
- stamp |= ((ulg)get_byte()) << 8;
- stamp |= ((ulg)get_byte()) << 16;
- stamp |= ((ulg)get_byte()) << 24;
- if (stamp != 0 && !no_time) time_stamp = stamp;
-
- (void)get_byte(); /* Ignore extra flags for the moment */
- (void)get_byte(); /* Ignore OS type for the moment */
-
- if ((flags & CONTINUATION) != 0) {
- unsigned part = (unsigned)get_byte();
- part |= ((unsigned)get_byte())<<8;
- if (verbose) {
- fprintf(stderr,"%s: %s: part number %u\n",
- progname, ifname, part);
- }
- }
- if ((flags & EXTRA_FIELD) != 0) {
- unsigned len = (unsigned)get_byte();
- len |= ((unsigned)get_byte())<<8;
- if (verbose) {
- fprintf(stderr,"%s: %s: extra field of %u bytes ignored\n",
- progname, ifname, len);
- }
- while (len--) (void)get_byte();
- }
-
- /* Get original file name if it was truncated */
- if ((flags & ORIG_NAME) != 0) {
- if (no_name || (to_stdout && !list) || part_nb > 1) {
- /* Discard the old name */
- char c; /* dummy used for NeXTstep 3.0 cc optimizer bug */
- do {c=get_byte();} while (c != 0);
- } else {
- /* Copy the base name. Keep a directory prefix intact. */
- char *p = base_name (ofname);
- char *base = p;
- char *base2;
- for (;;) {
- *p = (char)get_char();
- if (*p++ == '\0') break;
- if (p >= ofname+sizeof(ofname)) {
- error("corrupted input -- file name too large");
- }
- }
- base2 = base_name (base);
- strcpy(base, base2);
- /* If necessary, adapt the name to local OS conventions: */
- if (!list) {
- MAKE_LEGAL_NAME(base);
- if (base) list=0; /* avoid warning about unused variable */
- }
- } /* no_name || to_stdout */
- } /* ORIG_NAME */
-
- /* Discard file comment if any */
- if ((flags & COMMENT) != 0) {
- while (get_char() != 0) /* null */ ;
- }
- if (part_nb == 1) {
- header_bytes = inptr + 2*sizeof(long); /* include crc and size */
- }
-
- } else if (memcmp(magic, PKZIP_MAGIC, 2) == 0 && inptr == 2
- && memcmp((char*)inbuf, PKZIP_MAGIC, 4) == 0) {
- /* To simplify the code, we support a zip file when alone only.
- * We are thus guaranteed that the entire local header fits in inbuf.
- */
- inptr = 0;
- work = unzip;
- if (check_zipfile(in) != OK) return -1;
- /* check_zipfile may get ofname from the local header */
- last_member = 1;
-
- } else if (memcmp(magic, PACK_MAGIC, 2) == 0) {
- work = unpack;
- method = PACKED;
-
- } else if (memcmp(magic, LZW_MAGIC, 2) == 0) {
- work = unlzw;
- method = COMPRESSED;
- last_member = 1;
-
- } else if (memcmp(magic, LZH_MAGIC, 2) == 0) {
- work = unlzh;
- method = LZHED;
- last_member = 1;
-
- } else if (force && to_stdout && !list) { /* pass input unchanged */
- method = STORED;
- work = copy;
- inptr = 0;
- last_member = 1;
- }
- if (method >= 0) return method;
-
- if (part_nb == 1) {
- fprintf(stderr, "\n%s: %s: not in gzip format\n", progname, ifname);
- exit_code = ERROR;
- return -1;
- } else {
- if (magic[0] == 0)
- {
- int inbyte;
- for (inbyte = imagic1; inbyte == 0; inbyte = try_byte ())
- continue;
- if (inbyte == EOF)
- {
- if (verbose)
- WARN ((stderr, "\n%s: %s: decompression OK, trailing zero bytes ignored\n",
- progname, ifname));
- return -3;
- }
- }
-
- WARN((stderr, "\n%s: %s: decompression OK, trailing garbage ignored\n",
- progname, ifname));
- return -2;
- }
-}
-
-/* ========================================================================
- * Display the characteristics of the compressed file.
- * If the given method is < 0, display the accumulated totals.
- * IN assertions: time_stamp, header_bytes and ifile_size are initialized.
- */
-local void do_list(ifd, method)
- int ifd; /* input file descriptor */
- int method; /* compression method */
-{
- ulg crc; /* original crc */
- static int first_time = 1;
- static char* methods[MAX_METHODS] = {
- "store", /* 0 */
- "compr", /* 1 */
- "pack ", /* 2 */
- "lzh ", /* 3 */
- "", "", "", "", /* 4 to 7 reserved */
- "defla"}; /* 8 */
- char *date;
- int positive_off_t_width = 1;
- off_t o;
-
- for (o = OFF_T_MAX; 9 < o; o /= 10) {
- positive_off_t_width++;
- }
-
- if (first_time && method >= 0) {
- first_time = 0;
- if (verbose) {
- printf("method crc date time ");
- }
- if (!quiet) {
- printf("%*.*s %*.*s ratio uncompressed_name\n",
- positive_off_t_width, positive_off_t_width, "compressed",
- positive_off_t_width, positive_off_t_width, "uncompressed");
- }
- } else if (method < 0) {
- if (total_in <= 0 || total_out <= 0) return;
- if (verbose) {
- printf(" ");
- }
- if (verbose || !quiet) {
- fprint_off(stdout, total_in, positive_off_t_width);
- printf(" ");
- fprint_off(stdout, total_out, positive_off_t_width);
- printf(" ");
- }
- display_ratio(total_out-(total_in-header_bytes), total_out, stdout);
- /* header_bytes is not meaningful but used to ensure the same
- * ratio if there is a single file.
- */
- printf(" (totals)\n");
- return;
- }
- crc = (ulg)~0; /* unknown */
- bytes_out = -1L;
- bytes_in = ifile_size;
-
-#if RECORD_IO == 0
- if (method == DEFLATED && !last_member) {
- /* Get the crc and uncompressed size for gzip'ed (not zip'ed) files.
- * If the lseek fails, we could use read() to get to the end, but
- * --list is used to get quick results.
- * Use "gunzip < foo.gz | wc -c" to get the uncompressed size if
- * you are not concerned about speed.
- */
- bytes_in = lseek(ifd, (off_t)(-8), SEEK_END);
- if (bytes_in != -1L) {
- uch buf[8];
- bytes_in += 8L;
- if (read(ifd, (char*)buf, sizeof(buf)) != sizeof(buf)) {
- read_error();
- }
- crc = LG(buf);
- bytes_out = LG(buf+4);
- }
- }
-#endif /* RECORD_IO */
- date = ctime((time_t*)&time_stamp) + 4; /* skip the day of the week */
- date[12] = '\0'; /* suppress the 1/100sec and the year */
- if (verbose) {
- printf("%5s %08lx %11s ", methods[method], crc, date);
- }
- fprint_off(stdout, bytes_in, positive_off_t_width);
- printf(" ");
- fprint_off(stdout, bytes_out, positive_off_t_width);
- printf(" ");
- if (bytes_in == -1L) {
- total_in = -1L;
- bytes_in = bytes_out = header_bytes = 0;
- } else if (total_in >= 0) {
- total_in += bytes_in;
- }
- if (bytes_out == -1L) {
- total_out = -1L;
- bytes_in = bytes_out = header_bytes = 0;
- } else if (total_out >= 0) {
- total_out += bytes_out;
- }
- display_ratio(bytes_out-(bytes_in-header_bytes), bytes_out, stdout);
- printf(" %s\n", ofname);
-}
-
-/* ========================================================================
- * Return true if the two stat structures correspond to the same file.
- */
-local int same_file(stat1, stat2)
- struct stat *stat1;
- struct stat *stat2;
-{
- return stat1->st_ino == stat2->st_ino
- && stat1->st_dev == stat2->st_dev
-#ifdef NO_ST_INO
- /* Can't rely on st_ino and st_dev, use other fields: */
- && stat1->st_mode == stat2->st_mode
- && stat1->st_uid == stat2->st_uid
- && stat1->st_gid == stat2->st_gid
- && stat1->st_size == stat2->st_size
- && stat1->st_atime == stat2->st_atime
- && stat1->st_mtime == stat2->st_mtime
- && stat1->st_ctime == stat2->st_ctime
-#endif
- ;
-}
-
-/* ========================================================================
- * Return true if a file name is ambiguous because the operating system
- * truncates file names.
- */
-local int name_too_long(name, statb)
- char *name; /* file name to check */
- struct stat *statb; /* stat buf for this file name */
-{
- int s = strlen(name);
- char c = name[s-1];
- struct stat tstat; /* stat for truncated name */
- int res;
-
- tstat = *statb; /* Just in case OS does not fill all fields */
- name[s-1] = '\0';
- res = lstat(name, &tstat) == 0 && same_file(statb, &tstat);
- name[s-1] = c;
- Trace((stderr, " too_long(%s) => %d\n", name, res));
- return res;
-}
-
-/* ========================================================================
- * Shorten the given name by one character, or replace a .tar extension
- * with .tgz. Truncate the last part of the name which is longer than
- * MIN_PART characters: 1234.678.012.gz -> 123.678.012.gz. If the name
- * has only parts shorter than MIN_PART truncate the longest part.
- * For decompression, just remove the last character of the name.
- *
- * IN assertion: for compression, the suffix of the given name is z_suffix.
- */
-local void shorten_name(name)
- char *name;
-{
- int len; /* length of name without z_suffix */
- char *trunc = NULL; /* character to be truncated */
- int plen; /* current part length */
- int min_part = MIN_PART; /* current minimum part length */
- char *p;
-
- len = strlen(name);
- if (decompress) {
- if (len <= 1) error("name too short");
- name[len-1] = '\0';
- return;
- }
- p = get_suffix(name);
- if (p == NULL) error("can't recover suffix\n");
- *p = '\0';
- save_orig_name = 1;
-
- /* compress 1234567890.tar to 1234567890.tgz */
- if (len > 4 && strequ(p-4, ".tar")) {
- strcpy(p-4, ".tgz");
- return;
- }
- /* Try keeping short extensions intact:
- * 1234.678.012.gz -> 123.678.012.gz
- */
- do {
- p = strrchr(name, PATH_SEP);
- p = p ? p+1 : name;
- while (*p) {
- plen = strcspn(p, PART_SEP);
- p += plen;
- if (plen > min_part) trunc = p-1;
- if (*p) p++;
- }
- } while (trunc == NULL && --min_part != 0);
-
- if (trunc != NULL) {
- do {
- trunc[0] = trunc[1];
- } while (*trunc++);
- trunc--;
- } else {
- trunc = strrchr(name, PART_SEP[0]);
- if (trunc == NULL) error("internal error in shorten_name");
- if (trunc[1] == '\0') trunc--; /* force truncation */
- }
- strcpy(trunc, z_suffix);
-}
-
-/* ========================================================================
- * If compressing to a file, check if ofname is not ambiguous
- * because the operating system truncates names. Otherwise, generate
- * a new ofname and save the original name in the compressed file.
- * If the compressed file already exists, ask for confirmation.
- * The check for name truncation is made dynamically, because different
- * file systems on the same OS might use different truncation rules (on SVR4
- * s5 truncates to 14 chars and ufs does not truncate).
- * This function returns -1 if the file must be skipped, and
- * updates save_orig_name if necessary.
- * IN assertions: save_orig_name is already set if ofname has been
- * already truncated because of NO_MULTIPLE_DOTS. The input file has
- * already been open and istat is set.
- */
-local int check_ofname()
-{
- struct stat ostat; /* stat for ofname */
-
-#ifdef ENAMETOOLONG
- /* Check for strictly conforming Posix systems (which return ENAMETOOLONG
- * instead of silently truncating filenames).
- */
- errno = 0;
- while (lstat(ofname, &ostat) != 0) {
- if (errno != ENAMETOOLONG) return 0; /* ofname does not exist */
- shorten_name(ofname);
- }
-#else
- if (lstat(ofname, &ostat) != 0) return 0;
-#endif
- /* Check for name truncation on existing file. Do this even on systems
- * defining ENAMETOOLONG, because on most systems the strict Posix
- * behavior is disabled by default (silent name truncation allowed).
- */
- if (!decompress && name_too_long(ofname, &ostat)) {
- shorten_name(ofname);
- if (lstat(ofname, &ostat) != 0) return 0;
- }
-
- /* Check that the input and output files are different (could be
- * the same by name truncation or links).
- */
- if (same_file(&istat, &ostat)) {
- if (strequ(ifname, ofname)) {
- fprintf(stderr, "%s: %s: cannot %scompress onto itself\n",
- progname, ifname, decompress ? "de" : "");
- } else {
- fprintf(stderr, "%s: %s and %s are the same file\n",
- progname, ifname, ofname);
- }
- exit_code = ERROR;
- return ERROR;
- }
- /* Ask permission to overwrite the existing file */
- if (!force) {
- int ok = 0;
- fprintf(stderr, "%s: %s already exists;", progname, ofname);
- if (foreground && isatty(fileno(stdin))) {
- fprintf(stderr, " do you wish to overwrite (y or n)? ");
- fflush(stderr);
- ok = yesno();
- }
- if (!ok) {
- fprintf(stderr, "\tnot overwritten\n");
- if (exit_code == OK) exit_code = WARNING;
- return ERROR;
- }
- }
- if (xunlink (ofname)) {
- progerror(ofname);
- return ERROR;
- }
- return OK;
-}
-
-
-#ifndef NO_UTIME
-/* ========================================================================
- * Set the access and modification times from the given stat buffer.
- */
-local void reset_times (name, statb)
- char *name;
- struct stat *statb;
-{
- struct utimbuf timep;
-
- /* Copy the time stamp */
- timep.actime = statb->st_atime;
- timep.modtime = statb->st_mtime;
-
- /* Some systems (at least OS/2) do not support utime on directories */
- if (utime(name, &timep) && !S_ISDIR(statb->st_mode)) {
- int e = errno;
- WARN((stderr, "%s: ", progname));
- if (!quiet) {
- errno = e;
- perror(ofname);
- }
- }
-}
-#endif
-
-
-/* ========================================================================
- * Copy modes, times, ownership from input file to output file.
- * IN assertion: to_stdout is false.
- */
-local void copy_stat(ifstat)
- struct stat *ifstat;
-{
-#ifndef NO_UTIME
- if (decompress && time_stamp != 0 && ifstat->st_mtime != time_stamp) {
- ifstat->st_mtime = time_stamp;
- if (verbose > 1) {
- fprintf(stderr, "%s: time stamp restored\n", ofname);
- }
- }
- reset_times(ofname, ifstat);
-#endif
- /* Copy the protection modes */
- if (fchmod(ofd, ifstat->st_mode & 07777)) {
- int e = errno;
- WARN((stderr, "%s: ", progname));
- if (!quiet) {
- errno = e;
- perror(ofname);
- }
- }
-#ifndef NO_CHOWN
- fchown(ofd, ifstat->st_uid, ifstat->st_gid); /* Copy ownership */
-#endif
- remove_ofname = 0;
- /* It's now safe to remove the input file: */
- if (xunlink (ifname)) {
- int e = errno;
- WARN((stderr, "%s: ", progname));
- if (!quiet) {
- errno = e;
- perror(ifname);
- }
- }
-}
-
-#if ! NO_DIR
-
-/* ========================================================================
- * Recurse through the given directory. This code is taken from ncompress.
- */
-local void treat_dir(dir)
- char *dir;
-{
- struct dirent *dp;
- DIR *dirp;
- char nbuf[MAX_PATH_LEN];
- int len;
-
- dirp = opendir(dir);
-
- if (dirp == NULL) {
- progerror(dir);
- return ;
- }
- /*
- ** WARNING: the following algorithm could occasionally cause
- ** compress to produce error warnings of the form "<filename>.gz
- ** already has .gz suffix - ignored". This occurs when the
- ** .gz output file is inserted into the directory below
- ** readdir's current pointer.
- ** These warnings are harmless but annoying, so they are suppressed
- ** with option -r (except when -v is on). An alternative
- ** to allowing this would be to store the entire directory
- ** list in memory, then compress the entries in the stored
- ** list. Given the depth-first recursive algorithm used here,
- ** this could use up a tremendous amount of memory. I don't
- ** think it's worth it. -- Dave Mack
- ** (An other alternative might be two passes to avoid depth-first.)
- */
-
- while ((errno = 0, dp = readdir(dirp)) != NULL) {
-
- if (strequ(dp->d_name,".") || strequ(dp->d_name,"..")) {
- continue;
- }
- len = strlen(dir);
- if (len + NAMLEN(dp) + 1 < MAX_PATH_LEN - 1) {
- strcpy(nbuf,dir);
- if (len != 0 /* dir = "" means current dir on Amiga */
-#ifdef PATH_SEP2
- && dir[len-1] != PATH_SEP2
-#endif
-#ifdef PATH_SEP3
- && dir[len-1] != PATH_SEP3
-#endif
- ) {
- nbuf[len++] = PATH_SEP;
- }
- strcpy(nbuf+len, dp->d_name);
- treat_file(nbuf);
- } else {
- fprintf(stderr,"%s: %s/%s: pathname too long\n",
- progname, dir, dp->d_name);
- exit_code = ERROR;
- }
- }
- if (errno != 0)
- progerror(dir);
- if (CLOSEDIR(dirp) != 0)
- progerror(dir);
-}
-#endif /* ! NO_DIR */
-
-/* ========================================================================
- * Free all dynamically allocated variables and exit with the given code.
- */
-local void do_exit(exitcode)
- int exitcode;
-{
- static int in_exit = 0;
-
- if (in_exit) exit(exitcode);
- in_exit = 1;
- if (env != NULL) free(env), env = NULL;
- if (args != NULL) free((char*)args), args = NULL;
- FREE(inbuf);
- FREE(outbuf);
- FREE(d_buf);
- FREE(window);
-#ifndef MAXSEG_64K
- FREE(tab_prefix);
-#else
- FREE(tab_prefix0);
- FREE(tab_prefix1);
-#endif
- exit(exitcode);
-}
-
-/* ========================================================================
- * Close and unlink the output file if appropriate. This routine must be
- * async-signal-safe.
- */
-local void do_remove() {
- if (remove_ofname) {
- close(ofd);
- xunlink (ofname);
- }
-}
-
-/* ========================================================================
- * Error handler.
- */
-RETSIGTYPE abort_gzip()
-{
- do_remove();
- do_exit(ERROR);
-}
-
-/* ========================================================================
- * Signal handler.
- */
-RETSIGTYPE abort_gzip_signal()
-{
- do_remove();
- _exit(ERROR);
-}
-
-/* Inflate deflated data
-
- Copyright (C) 1997, 1998, 1999, 2002 Free Software Foundation, Inc.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; see the file COPYING.
- If not, write to the Free Software Foundation,
- 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
-
-/* 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 multi-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[] = "$Id: inflate.c,v 0.14 1993/06/10 13:27:04 jloup Exp $";
-#endif
-
-#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.
- The macros also use the variable w, which is a cached copy of wp.
-
- 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
-};
-
-#define GETBYTE() (inptr < insize ? inbuf[inptr++] : (wp = w, fill_inbuf(0)))
-
-#ifdef CRYPT
- uch cc;
-# define NEXTBYTE() \
- (decrypt ? (cc = GETBYTE(), zdecode(cc), cc) : GETBYTE())
-#else
-# define NEXTBYTE() (uch)GETBYTE()
-#endif
-#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}}
-#define DUMPBITS(n) {b>>=(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;
- }
-
-
- /* 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 */
- unsigned w; /* current window position */
- 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;
- w = wp;
-
-
- /* 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 */
- unsigned w; /* current window position */
- register ulg b; /* bit buffer */
- register unsigned k; /* number of bits in bit buffer */
-
-
- /* make local bit buffer */
- b = bb;
- k = bk;
- w = wp;
-
-
- /* 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;
-}
-/* lzw.c -- compress files in LZW format.
- * This is a dummy version avoiding patent problems.
- */
-
-#ifdef RCSID
-static char rcsid[] = "$Id: lzw.c,v 0.9 1993/06/10 13:27:31 jloup Exp $";
-#endif
-
-static int msg_done = 0;
-
-/* Compress in to out with lzw method. */
-int lzw(in, out)
- int in, out;
-{
- if (msg_done) return ERROR;
- msg_done = 1;
- fprintf(stderr,"output in compress .Z format not supported\n");
- if (in != out) { /* avoid warnings on unused variables */
- exit_code = ERROR;
- }
- return ERROR;
-}
-/* trees.c -- output deflated data using Huffman coding
- * 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.
- */
-
-/*
- * PURPOSE
- *
- * Encode various sets of source values using variable-length
- * binary code trees.
- *
- * DISCUSSION
- *
- * The PKZIP "deflation" process uses several Huffman trees. The more
- * common source values are represented by shorter bit sequences.
- *
- * Each code tree is stored in the ZIP file in a compressed form
- * which is itself a Huffman encoding of the lengths of
- * all the code strings (in ascending order by source values).
- * The actual code strings are reconstructed from the lengths in
- * the UNZIP process, as described in the "application note"
- * (APPNOTE.TXT) distributed as part of PKWARE's PKZIP program.
- *
- * REFERENCES
- *
- * Lynch, Thomas J.
- * Data Compression: Techniques and Applications, pp. 53-55.
- * Lifetime Learning Publications, 1985. ISBN 0-534-03418-7.
- *
- * Storer, James A.
- * Data Compression: Methods and Theory, pp. 49-50.
- * Computer Science Press, 1988. ISBN 0-7167-8156-5.
- *
- * Sedgewick, R.
- * Algorithms, p290.
- * Addison-Wesley, 1983. ISBN 0-201-06672-6.
- *
- * INTERFACE
- *
- * void ct_init (ush *attr, int *methodp)
- * Allocate the match buffer, initialize the various tables and save
- * the location of the internal file attribute (ascii/binary) and
- * method (DEFLATE/STORE)
- *
- * void ct_tally (int dist, int lc);
- * Save the match info and tally the frequency counts.
- *
- * off_t flush_block (char *buf, ulg stored_len, int pad, int eof)
- * Determine the best encoding for the current block: dynamic trees,
- * static trees or store, and output the encoded block to the zip
- * file. If pad is set, pads the block to the next
- * byte. Returns the total compressed length for the file so
- * far.
- * */
-
-#ifdef RCSID
-static char rcsid[] = "$Id: trees.c,v 0.12 1993/06/10 13:27:54 jloup Exp $";
-#endif
-
-/* ===========================================================================
- * Constants
- */
-
-#define MAX_BITS 15
-/* All codes must not exceed MAX_BITS bits */
-
-#define MAX_BL_BITS 7
-/* Bit length codes must not exceed MAX_BL_BITS bits */
-
-#define LENGTH_CODES 29
-/* number of length codes, not counting the special END_BLOCK code */
-
-#define LITERALS 256
-/* number of literal bytes 0..255 */
-
-#define END_BLOCK 256
-/* end of block literal code */
-
-#define L_CODES (LITERALS+1+LENGTH_CODES)
-/* number of Literal or Length codes, including the END_BLOCK code */
-
-#define D_CODES 30
-/* number of distance codes */
-
-#define BL_CODES 19
-/* number of codes used to transfer the bit lengths */
-
-
-local int near extra_lbits[LENGTH_CODES] /* extra bits for each length code */
- = {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};
-
-local int near extra_dbits[D_CODES] /* extra bits for each distance code */
- = {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};
-
-local int near extra_blbits[BL_CODES]/* extra bits for each bit length code */
- = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,3,7};
-
-#define STORED_BLOCK 0
-#define STATIC_TREES 1
-#define DYN_TREES 2
-/* The three kinds of block type */
-
-#ifndef LIT_BUFSIZE
-# ifdef SMALL_MEM
-# define LIT_BUFSIZE 0x2000
-# else
-# ifdef MEDIUM_MEM
-# define LIT_BUFSIZE 0x4000
-# else
-# define LIT_BUFSIZE 0x8000
-# endif
-# endif
-#endif
-#ifndef DIST_BUFSIZE
-# define DIST_BUFSIZE LIT_BUFSIZE
-#endif
-/* Sizes of match buffers for literals/lengths and distances. There are
- * 4 reasons for limiting LIT_BUFSIZE to 64K:
- * - frequencies can be kept in 16 bit counters
- * - if compression is not successful for the first block, all input data is
- * still in the window so we can still emit a stored block even when input
- * comes from standard input. (This can also be done for all blocks if
- * LIT_BUFSIZE is not greater than 32K.)
- * - if compression is not successful for a file smaller than 64K, we can
- * even emit a stored file instead of a stored block (saving 5 bytes).
- * - creating new Huffman trees less frequently may not provide fast
- * adaptation to changes in the input data statistics. (Take for
- * example a binary file with poorly compressible code followed by
- * a highly compressible string table.) Smaller buffer sizes give
- * fast adaptation but have of course the overhead of transmitting trees
- * more frequently.
- * - I can't count above 4
- * The current code is general and allows DIST_BUFSIZE < LIT_BUFSIZE (to save
- * memory at the expense of compression). Some optimizations would be possible
- * if we rely on DIST_BUFSIZE == LIT_BUFSIZE.
- */
-#if LIT_BUFSIZE > INBUFSIZ
- error cannot overlay l_buf and inbuf
-#endif
-
-#define REP_3_6 16
-/* repeat previous bit length 3-6 times (2 bits of repeat count) */
-
-#define REPZ_3_10 17
-/* repeat a zero length 3-10 times (3 bits of repeat count) */
-
-#define REPZ_11_138 18
-/* repeat a zero length 11-138 times (7 bits of repeat count) */
-
-/* ===========================================================================
- * Local data
- */
-
-/* Data structure describing a single value and its code string. */
-typedef struct ct_data {
- union {
- ush freq; /* frequency count */
- ush code; /* bit string */
- } fc;
- union {
- ush dad; /* father node in Huffman tree */
- ush len; /* length of bit string */
- } dl;
-} ct_data;
-
-#define Freq fc.freq
-#define Code fc.code
-#define Dad dl.dad
-#define Len dl.len
-
-#define HEAP_SIZE (2*L_CODES+1)
-/* maximum heap size */
-
-local ct_data near dyn_ltree[HEAP_SIZE]; /* literal and length tree */
-local ct_data near dyn_dtree[2*D_CODES+1]; /* distance tree */
-
-local ct_data near static_ltree[L_CODES+2];
-/* The static literal tree. Since the bit lengths are imposed, there is no
- * need for the L_CODES extra codes used during heap construction. However
- * The codes 286 and 287 are needed to build a canonical tree (see ct_init
- * below).
- */
-
-local ct_data near static_dtree[D_CODES];
-/* The static distance tree. (Actually a trivial tree since all codes use
- * 5 bits.)
- */
-
-local ct_data near bl_tree[2*BL_CODES+1];
-/* Huffman tree for the bit lengths */
-
-typedef struct tree_desc {
- ct_data near *dyn_tree; /* the dynamic tree */
- ct_data near *static_tree; /* corresponding static tree or NULL */
- int near *extra_bits; /* extra bits for each code or NULL */
- int extra_base; /* base index for extra_bits */
- int elems; /* max number of elements in the tree */
- int max_length; /* max bit length for the codes */
- int max_code; /* largest code with non zero frequency */
-} tree_desc;
-
-local tree_desc near l_desc =
-{dyn_ltree, static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS, 0};
-
-local tree_desc near d_desc =
-{dyn_dtree, static_dtree, extra_dbits, 0, D_CODES, MAX_BITS, 0};
-
-local tree_desc near bl_desc =
-{bl_tree, (ct_data near *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS, 0};
-
-
-local ush near bl_count[MAX_BITS+1];
-/* number of codes at each bit length for an optimal tree */
-
-local uch near bl_order[BL_CODES]
- = {16,17,18,0,8,7,9,6,10,5,11,4,12,3,13,2,14,1,15};
-/* The lengths of the bit length codes are sent in order of decreasing
- * probability, to avoid transmitting the lengths for unused bit length codes.
- */
-
-local int near heap[2*L_CODES+1]; /* heap used to build the Huffman trees */
-local int heap_len; /* number of elements in the heap */
-local int heap_max; /* element of largest frequency */
-/* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used.
- * The same heap array is used to build all trees.
- */
-
-local uch near depth[2*L_CODES+1];
-/* Depth of each subtree used as tie breaker for trees of equal frequency */
-
-local uch length_code[MAX_MATCH-MIN_MATCH+1];
-/* length code for each normalized match length (0 == MIN_MATCH) */
-
-local uch dist_code[512];
-/* distance codes. The first 256 values correspond to the distances
- * 3 .. 258, the last 256 values correspond to the top 8 bits of
- * the 15 bit distances.
- */
-
-local int near base_length[LENGTH_CODES];
-/* First normalized length for each code (0 = MIN_MATCH) */
-
-local int near base_dist[D_CODES];
-/* First normalized distance for each code (0 = distance of 1) */
-
-#define l_buf inbuf
-/* DECLARE(uch, l_buf, LIT_BUFSIZE); buffer for literals or lengths */
-
-/* DECLARE(ush, d_buf, DIST_BUFSIZE); buffer for distances */
-
-local uch near flag_buf[(LIT_BUFSIZE/8)];
-/* flag_buf is a bit array distinguishing literals from lengths in
- * l_buf, thus indicating the presence or absence of a distance.
- */
-
-local unsigned last_lit; /* running index in l_buf */
-local unsigned last_dist; /* running index in d_buf */
-local unsigned last_flags; /* running index in flag_buf */
-local uch flags; /* current flags not yet saved in flag_buf */
-local uch flag_bit; /* current bit used in flags */
-/* bits are filled in flags starting at bit 0 (least significant).
- * Note: these flags are overkill in the current code since we don't
- * take advantage of DIST_BUFSIZE == LIT_BUFSIZE.
- */
-
-local ulg opt_len; /* bit length of current block with optimal trees */
-local ulg static_len; /* bit length of current block with static trees */
-
-local off_t compressed_len; /* total bit length of compressed file */
-
-local off_t input_len; /* total byte length of input file */
-/* input_len is for debugging only since we can get it by other means. */
-
-ush *file_type; /* pointer to UNKNOWN, BINARY or ASCII */
-int *file_method; /* pointer to DEFLATE or STORE */
-
-#ifdef DEBUG
-extern off_t bits_sent; /* bit length of the compressed data */
-#endif
-
-extern long block_start; /* window offset of current block */
-extern unsigned near strstart; /* window offset of current string */
-
-/* ===========================================================================
- * Local (static) routines in this file.
- */
-
-local void init_block OF((void));
-local void pqdownheap OF((ct_data near *tree, int k));
-local void gen_bitlen OF((tree_desc near *desc));
-local void gen_codes OF((ct_data near *tree, int max_code));
-local void build_tree_1 OF((tree_desc near *desc));
-local void scan_tree OF((ct_data near *tree, int max_code));
-local void send_tree OF((ct_data near *tree, int max_code));
-local int build_bl_tree OF((void));
-local void send_all_trees OF((int lcodes, int dcodes, int blcodes));
-local void compress_block OF((ct_data near *ltree, ct_data near *dtree));
-local void set_file_type OF((void));
-
-
-#ifndef DEBUG
-# define send_code(c, tree) send_bits(tree[c].Code, tree[c].Len)
- /* Send a code of the given tree. c and tree must not have side effects */
-
-#else /* DEBUG */
-# define send_code(c, tree) \
- { if (verbose>1) fprintf(stderr,"\ncd %3d ",(c)); \
- send_bits(tree[c].Code, tree[c].Len); }
-#endif
-
-#define d_code(dist) \
- ((dist) < 256 ? dist_code[dist] : dist_code[256+((dist)>>7)])
-/* Mapping from a distance to a distance code. dist is the distance - 1 and
- * must not have side effects. dist_code[256] and dist_code[257] are never
- * used.
- */
-
-#define MAX(a,b) (a >= b ? a : b)
-/* the arguments must not have side effects */
-
-/* ===========================================================================
- * Allocate the match buffer, initialize the various tables and save the
- * location of the internal file attribute (ascii/binary) and method
- * (DEFLATE/STORE).
- */
-void ct_init(attr, methodp)
- ush *attr; /* pointer to internal file attribute */
- int *methodp; /* pointer to compression method */
-{
- int n; /* iterates over tree elements */
- int bits; /* bit counter */
- int length; /* length value */
- int code; /* code value */
- int dist; /* distance index */
-
- file_type = attr;
- file_method = methodp;
- compressed_len = input_len = 0L;
-
- if (static_dtree[0].Len != 0) return; /* ct_init already called */
-
- /* Initialize the mapping length (0..255) -> length code (0..28) */
- length = 0;
- for (code = 0; code < LENGTH_CODES-1; code++) {
- base_length[code] = length;
- for (n = 0; n < (1<<extra_lbits[code]); n++) {
- length_code[length++] = (uch)code;
- }
- }
- Assert (length == 256, "ct_init: length != 256");
- /* Note that the length 255 (match length 258) can be represented
- * in two different ways: code 284 + 5 bits or code 285, so we
- * overwrite length_code[255] to use the best encoding:
- */
- length_code[length-1] = (uch)code;
-
- /* Initialize the mapping dist (0..32K) -> dist code (0..29) */
- dist = 0;
- for (code = 0 ; code < 16; code++) {
- base_dist[code] = dist;
- for (n = 0; n < (1<<extra_dbits[code]); n++) {
- dist_code[dist++] = (uch)code;
- }
- }
- Assert (dist == 256, "ct_init: dist != 256");
- dist >>= 7; /* from now on, all distances are divided by 128 */
- for ( ; code < D_CODES; code++) {
- base_dist[code] = dist << 7;
- for (n = 0; n < (1<<(extra_dbits[code]-7)); n++) {
- dist_code[256 + dist++] = (uch)code;
- }
- }
- Assert (dist == 256, "ct_init: 256+dist != 512");
-
- /* Construct the codes of the static literal tree */
- for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0;
- n = 0;
- while (n <= 143) static_ltree[n++].Len = 8, bl_count[8]++;
- while (n <= 255) static_ltree[n++].Len = 9, bl_count[9]++;
- while (n <= 279) static_ltree[n++].Len = 7, bl_count[7]++;
- while (n <= 287) static_ltree[n++].Len = 8, bl_count[8]++;
- /* Codes 286 and 287 do not exist, but we must include them in the
- * tree construction to get a canonical Huffman tree (longest code
- * all ones)
- */
- gen_codes((ct_data near *)static_ltree, L_CODES+1);
-
- /* The static distance tree is trivial: */
- for (n = 0; n < D_CODES; n++) {
- static_dtree[n].Len = 5;
- static_dtree[n].Code = bi_reverse(n, 5);
- }
-
- /* Initialize the first block of the first file: */
- init_block();
-}
-
-/* ===========================================================================
- * Initialize a new block.
- */
-local void init_block()
-{
- int n; /* iterates over tree elements */
-
- /* Initialize the trees. */
- for (n = 0; n < L_CODES; n++) dyn_ltree[n].Freq = 0;
- for (n = 0; n < D_CODES; n++) dyn_dtree[n].Freq = 0;
- for (n = 0; n < BL_CODES; n++) bl_tree[n].Freq = 0;
-
- dyn_ltree[END_BLOCK].Freq = 1;
- opt_len = static_len = 0L;
- last_lit = last_dist = last_flags = 0;
- flags = 0; flag_bit = 1;
-}
-
-#define SMALLEST 1
-/* Index within the heap array of least frequent node in the Huffman tree */
-
-
-/* ===========================================================================
- * Remove the smallest element from the heap and recreate the heap with
- * one less element. Updates heap and heap_len.
- */
-#define pqremove(tree, top) \
-{\
- top = heap[SMALLEST]; \
- heap[SMALLEST] = heap[heap_len--]; \
- pqdownheap(tree, SMALLEST); \
-}
-
-/* ===========================================================================
- * Compares to subtrees, using the tree depth as tie breaker when
- * the subtrees have equal frequency. This minimizes the worst case length.
- */
-#define smaller(tree, n, m) \
- (tree[n].Freq < tree[m].Freq || \
- (tree[n].Freq == tree[m].Freq && depth[n] <= depth[m]))
-
-/* ===========================================================================
- * Restore the heap property by moving down the tree starting at node k,
- * exchanging a node with the smallest of its two sons if necessary, stopping
- * when the heap property is re-established (each father smaller than its
- * two sons).
- */
-local void pqdownheap(tree, k)
- ct_data near *tree; /* the tree to restore */
- int k; /* node to move down */
-{
- int v = heap[k];
- int j = k << 1; /* left son of k */
- while (j <= heap_len) {
- /* Set j to the smallest of the two sons: */
- if (j < heap_len && smaller(tree, heap[j+1], heap[j])) j++;
-
- /* Exit if v is smaller than both sons */
- if (smaller(tree, v, heap[j])) break;
-
- /* Exchange v with the smallest son */
- heap[k] = heap[j]; k = j;
-
- /* And continue down the tree, setting j to the left son of k */
- j <<= 1;
- }
- heap[k] = v;
-}
-
-/* ===========================================================================
- * Compute the optimal bit lengths for a tree and update the total bit length
- * for the current block.
- * IN assertion: the fields freq and dad are set, heap[heap_max] and
- * above are the tree nodes sorted by increasing frequency.
- * OUT assertions: the field len is set to the optimal bit length, the
- * array bl_count contains the frequencies for each bit length.
- * The length opt_len is updated; static_len is also updated if stree is
- * not null.
- */
-local void gen_bitlen(desc)
- tree_desc near *desc; /* the tree descriptor */
-{
- ct_data near *tree = desc->dyn_tree;
- int near *extra = desc->extra_bits;
- int base = desc->extra_base;
- int max_code = desc->max_code;
- int max_length = desc->max_length;
- ct_data near *stree = desc->static_tree;
- int h; /* heap index */
- int n, m; /* iterate over the tree elements */
- int bits; /* bit length */
- int xbits; /* extra bits */
- ush f; /* frequency */
- int overflow = 0; /* number of elements with bit length too large */
-
- for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0;
-
- /* In a first pass, compute the optimal bit lengths (which may
- * overflow in the case of the bit length tree).
- */
- tree[heap[heap_max]].Len = 0; /* root of the heap */
-
- for (h = heap_max+1; h < HEAP_SIZE; h++) {
- n = heap[h];
- bits = tree[tree[n].Dad].Len + 1;
- if (bits > max_length) bits = max_length, overflow++;
- tree[n].Len = (ush)bits;
- /* We overwrite tree[n].Dad which is no longer needed */
-
- if (n > max_code) continue; /* not a leaf node */
-
- bl_count[bits]++;
- xbits = 0;
- if (n >= base) xbits = extra[n-base];
- f = tree[n].Freq;
- opt_len += (ulg)f * (bits + xbits);
- if (stree) static_len += (ulg)f * (stree[n].Len + xbits);
- }
- if (overflow == 0) return;
-
- Trace((stderr,"\nbit length overflow\n"));
- /* This happens for example on obj2 and pic of the Calgary corpus */
-
- /* Find the first bit length which could increase: */
- do {
- bits = max_length-1;
- while (bl_count[bits] == 0) bits--;
- bl_count[bits]--; /* move one leaf down the tree */
- bl_count[bits+1] += 2; /* move one overflow item as its brother */
- bl_count[max_length]--;
- /* The brother of the overflow item also moves one step up,
- * but this does not affect bl_count[max_length]
- */
- overflow -= 2;
- } while (overflow > 0);
-
- /* Now recompute all bit lengths, scanning in increasing frequency.
- * h is still equal to HEAP_SIZE. (It is simpler to reconstruct all
- * lengths instead of fixing only the wrong ones. This idea is taken
- * from 'ar' written by Haruhiko Okumura.)
- */
- for (bits = max_length; bits != 0; bits--) {
- n = bl_count[bits];
- while (n != 0) {
- m = heap[--h];
- if (m > max_code) continue;
- if (tree[m].Len != (unsigned) bits) {
- Trace((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits));
- opt_len += ((long)bits-(long)tree[m].Len)*(long)tree[m].Freq;
- tree[m].Len = (ush)bits;
- }
- n--;
- }
- }
-}
-
-/* ===========================================================================
- * Generate the codes for a given tree and bit counts (which need not be
- * optimal).
- * IN assertion: the array bl_count contains the bit length statistics for
- * the given tree and the field len is set for all tree elements.
- * OUT assertion: the field code is set for all tree elements of non
- * zero code length.
- */
-local void gen_codes (tree, max_code)
- ct_data near *tree; /* the tree to decorate */
- int max_code; /* largest code with non zero frequency */
-{
- ush next_code[MAX_BITS+1]; /* next code value for each bit length */
- ush code = 0; /* running code value */
- int bits; /* bit index */
- int n; /* code index */
-
- /* The distribution counts are first used to generate the code values
- * without bit reversal.
- */
- for (bits = 1; bits <= MAX_BITS; bits++) {
- next_code[bits] = code = (code + bl_count[bits-1]) << 1;
- }
- /* Check that the bit counts in bl_count are consistent. The last code
- * must be all ones.
- */
- Assert (code + bl_count[MAX_BITS]-1 == (1<<MAX_BITS)-1,
- "inconsistent bit counts");
- Tracev((stderr,"\ngen_codes: max_code %d ", max_code));
-
- for (n = 0; n <= max_code; n++) {
- int len = tree[n].Len;
- if (len == 0) continue;
- /* Now reverse the bits */
- tree[n].Code = bi_reverse(next_code[len]++, len);
-
- Tracec(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ",
- n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1));
- }
-}
-
-/* ===========================================================================
- * Construct one Huffman tree and assigns the code bit strings and lengths.
- * Update the total bit length for the current block.
- * IN assertion: the field freq is set for all tree elements.
- * OUT assertions: the fields len and code are set to the optimal bit length
- * and corresponding code. The length opt_len is updated; static_len is
- * also updated if stree is not null. The field max_code is set.
- */
-local void build_tree_1(desc)
- tree_desc near *desc; /* the tree descriptor */
-{
- ct_data near *tree = desc->dyn_tree;
- ct_data near *stree = desc->static_tree;
- int elems = desc->elems;
- int n, m; /* iterate over heap elements */
- int max_code = -1; /* largest code with non zero frequency */
- int node = elems; /* next internal node of the tree */
-
- /* Construct the initial heap, with least frequent element in
- * heap[SMALLEST]. The sons of heap[n] are heap[2*n] and heap[2*n+1].
- * heap[0] is not used.
- */
- heap_len = 0, heap_max = HEAP_SIZE;
-
- for (n = 0; n < elems; n++) {
- if (tree[n].Freq != 0) {
- heap[++heap_len] = max_code = n;
- depth[n] = 0;
- } else {
- tree[n].Len = 0;
- }
- }
-
- /* The pkzip format requires that at least one distance code exists,
- * and that at least one bit should be sent even if there is only one
- * possible code. So to avoid special checks later on we force at least
- * two codes of non zero frequency.
- */
- while (heap_len < 2) {
- int new = heap[++heap_len] = (max_code < 2 ? ++max_code : 0);
- tree[new].Freq = 1;
- depth[new] = 0;
- opt_len--; if (stree) static_len -= stree[new].Len;
- /* new is 0 or 1 so it does not have extra bits */
- }
- desc->max_code = max_code;
-
- /* The elements heap[heap_len/2+1 .. heap_len] are leaves of the tree,
- * establish sub-heaps of increasing lengths:
- */
- for (n = heap_len/2; n >= 1; n--) pqdownheap(tree, n);
-
- /* Construct the Huffman tree by repeatedly combining the least two
- * frequent nodes.
- */
- do {
- pqremove(tree, n); /* n = node of least frequency */
- m = heap[SMALLEST]; /* m = node of next least frequency */
-
- heap[--heap_max] = n; /* keep the nodes sorted by frequency */
- heap[--heap_max] = m;
-
- /* Create a new node father of n and m */
- tree[node].Freq = tree[n].Freq + tree[m].Freq;
- depth[node] = (uch) (MAX(depth[n], depth[m]) + 1);
- tree[n].Dad = tree[m].Dad = (ush)node;
-#ifdef DUMP_BL_TREE
- if (tree == bl_tree) {
- fprintf(stderr,"\nnode %d(%d), sons %d(%d) %d(%d)",
- node, tree[node].Freq, n, tree[n].Freq, m, tree[m].Freq);
- }
-#endif
- /* and insert the new node in the heap */
- heap[SMALLEST] = node++;
- pqdownheap(tree, SMALLEST);
-
- } while (heap_len >= 2);
-
- heap[--heap_max] = heap[SMALLEST];
-
- /* At this point, the fields freq and dad are set. We can now
- * generate the bit lengths.
- */
- gen_bitlen((tree_desc near *)desc);
-
- /* The field len is now set, we can generate the bit codes */
- gen_codes ((ct_data near *)tree, max_code);
-}
-
-/* ===========================================================================
- * Scan a literal or distance tree to determine the frequencies of the codes
- * in the bit length tree. Updates opt_len to take into account the repeat
- * counts. (The contribution of the bit length codes will be added later
- * during the construction of bl_tree.)
- */
-local void scan_tree (tree, max_code)
- ct_data near *tree; /* the tree to be scanned */
- int max_code; /* and its largest code of non zero frequency */
-{
- int n; /* iterates over all tree elements */
- int prevlen = -1; /* last emitted length */
- int curlen; /* length of current code */
- int nextlen = tree[0].Len; /* length of next code */
- int count = 0; /* repeat count of the current code */
- int max_count = 7; /* max repeat count */
- int min_count = 4; /* min repeat count */
-
- if (nextlen == 0) max_count = 138, min_count = 3;
- tree[max_code+1].Len = (ush)0xffff; /* guard */
-
- for (n = 0; n <= max_code; n++) {
- curlen = nextlen; nextlen = tree[n+1].Len;
- if (++count < max_count && curlen == nextlen) {
- continue;
- } else if (count < min_count) {
- bl_tree[curlen].Freq += count;
- } else if (curlen != 0) {
- if (curlen != prevlen) bl_tree[curlen].Freq++;
- bl_tree[REP_3_6].Freq++;
- } else if (count <= 10) {
- bl_tree[REPZ_3_10].Freq++;
- } else {
- bl_tree[REPZ_11_138].Freq++;
- }
- count = 0; prevlen = curlen;
- if (nextlen == 0) {
- max_count = 138, min_count = 3;
- } else if (curlen == nextlen) {
- max_count = 6, min_count = 3;
- } else {
- max_count = 7, min_count = 4;
- }
- }
-}
-
-/* ===========================================================================
- * Send a literal or distance tree in compressed form, using the codes in
- * bl_tree.
- */
-local void send_tree (tree, max_code)
- ct_data near *tree; /* the tree to be scanned */
- int max_code; /* and its largest code of non zero frequency */
-{
- int n; /* iterates over all tree elements */
- int prevlen = -1; /* last emitted length */
- int curlen; /* length of current code */
- int nextlen = tree[0].Len; /* length of next code */
- int count = 0; /* repeat count of the current code */
- int max_count = 7; /* max repeat count */
- int min_count = 4; /* min repeat count */
-
- /* tree[max_code+1].Len = -1; */ /* guard already set */
- if (nextlen == 0) max_count = 138, min_count = 3;
-
- for (n = 0; n <= max_code; n++) {
- curlen = nextlen; nextlen = tree[n+1].Len;
- if (++count < max_count && curlen == nextlen) {
- continue;
- } else if (count < min_count) {
- do { send_code(curlen, bl_tree); } while (--count != 0);
-
- } else if (curlen != 0) {
- if (curlen != prevlen) {
- send_code(curlen, bl_tree); count--;
- }
- Assert(count >= 3 && count <= 6, " 3_6?");
- send_code(REP_3_6, bl_tree); send_bits(count-3, 2);
-
- } else if (count <= 10) {
- send_code(REPZ_3_10, bl_tree); send_bits(count-3, 3);
-
- } else {
- send_code(REPZ_11_138, bl_tree); send_bits(count-11, 7);
- }
- count = 0; prevlen = curlen;
- if (nextlen == 0) {
- max_count = 138, min_count = 3;
- } else if (curlen == nextlen) {
- max_count = 6, min_count = 3;
- } else {
- max_count = 7, min_count = 4;
- }
- }
-}
-
-/* ===========================================================================
- * Construct the Huffman tree for the bit lengths and return the index in
- * bl_order of the last bit length code to send.
- */
-local int build_bl_tree()
-{
- int max_blindex; /* index of last bit length code of non zero freq */
-
- /* Determine the bit length frequencies for literal and distance trees */
- scan_tree((ct_data near *)dyn_ltree, l_desc.max_code);
- scan_tree((ct_data near *)dyn_dtree, d_desc.max_code);
-
- /* Build the bit length tree: */
- build_tree_1((tree_desc near *)(&bl_desc));
- /* opt_len now includes the length of the tree representations, except
- * the lengths of the bit lengths codes and the 5+5+4 bits for the counts.
- */
-
- /* Determine the number of bit length codes to send. The pkzip format
- * requires that at least 4 bit length codes be sent. (appnote.txt says
- * 3 but the actual value used is 4.)
- */
- for (max_blindex = BL_CODES-1; max_blindex >= 3; max_blindex--) {
- if (bl_tree[bl_order[max_blindex]].Len != 0) break;
- }
- /* Update opt_len to include the bit length tree and counts */
- opt_len += 3*(max_blindex+1) + 5+5+4;
- Tracev((stderr, "\ndyn trees: dyn %lu, stat %lu", opt_len, static_len));
-
- return max_blindex;
-}
-
-/* ===========================================================================
- * Send the header for a block using dynamic Huffman trees: the counts, the
- * lengths of the bit length codes, the literal tree and the distance tree.
- * IN assertion: lcodes >= 257, dcodes >= 1, blcodes >= 4.
- */
-local void send_all_trees(lcodes, dcodes, blcodes)
- int lcodes, dcodes, blcodes; /* number of codes for each tree */
-{
- int rank; /* index in bl_order */
-
- Assert (lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes");
- Assert (lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES,
- "too many codes");
- Tracev((stderr, "\nbl counts: "));
- send_bits(lcodes-257, 5); /* not +255 as stated in appnote.txt */
- send_bits(dcodes-1, 5);
- send_bits(blcodes-4, 4); /* not -3 as stated in appnote.txt */
- for (rank = 0; rank < blcodes; rank++) {
- Tracev((stderr, "\nbl code %2d ", bl_order[rank]));
- send_bits(bl_tree[bl_order[rank]].Len, 3);
- }
-
- send_tree((ct_data near *)dyn_ltree, lcodes-1); /* send the literal tree */
-
- send_tree((ct_data near *)dyn_dtree, dcodes-1); /* send the distance tree */
-}
-
-/* ===========================================================================
- * Determine the best encoding for the current block: dynamic trees, static
- * trees or store, and output the encoded block to the zip file. This function
- * returns the total compressed length for the file so far.
- */
-off_t flush_block(buf, stored_len, pad, eof)
- char *buf; /* input block, or NULL if too old */
- ulg stored_len; /* length of input block */
- int pad; /* pad output to byte boundary */
- int eof; /* true if this is the last block for a file */
-{
- ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */
- int max_blindex; /* index of last bit length code of non zero freq */
-
- flag_buf[last_flags] = flags; /* Save the flags for the last 8 items */
-
- /* Check if the file is ascii or binary */
- if (*file_type == (ush)UNKNOWN) set_file_type();
-
- /* Construct the literal and distance trees */
- build_tree_1((tree_desc near *)(&l_desc));
- Tracev((stderr, "\nlit data: dyn %lu, stat %lu", opt_len, static_len));
-
- build_tree_1((tree_desc near *)(&d_desc));
- Tracev((stderr, "\ndist data: dyn %lu, stat %lu", opt_len, static_len));
- /* At this point, opt_len and static_len are the total bit lengths of
- * the compressed block data, excluding the tree representations.
- */
-
- /* Build the bit length tree for the above two trees, and get the index
- * in bl_order of the last bit length code to send.
- */
- max_blindex = build_bl_tree();
-
- /* Determine the best encoding. Compute first the block length in bytes */
- opt_lenb = (opt_len+3+7)>>3;
- static_lenb = (static_len+3+7)>>3;
- input_len += stored_len; /* for debugging only */
-
- Trace((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u dist %u ",
- opt_lenb, opt_len, static_lenb, static_len, stored_len,
- last_lit, last_dist));
-
- if (static_lenb <= opt_lenb) opt_lenb = static_lenb;
-
- /* If compression failed and this is the first and last block,
- * and if the zip file can be seeked (to rewrite the local header),
- * the whole file is transformed into a stored file:
- */
-#ifdef FORCE_METHOD
- if (level == 1 && eof && compressed_len == 0L) { /* force stored file */
-#else
- if (stored_len <= opt_lenb && eof && compressed_len == 0L && seekable()) {
-#endif
- /* Since LIT_BUFSIZE <= 2*WSIZE, the input data must be there: */
- if (buf == (char*)0) error ("block vanished");
-
- copy_block(buf, (unsigned)stored_len, 0); /* without header */
- compressed_len = stored_len << 3;
- *file_method = STORED;
-
-#ifdef FORCE_METHOD
- } else if (level == 2 && buf != (char*)0) { /* force stored block */
-#else
- } else if (stored_len+4 <= opt_lenb && buf != (char*)0) {
- /* 4: two words for the lengths */
-#endif
- /* The test buf != NULL is only necessary if LIT_BUFSIZE > WSIZE.
- * Otherwise we can't have processed more than WSIZE input bytes since
- * the last block flush, because compression would have been
- * successful. If LIT_BUFSIZE <= WSIZE, it is never too late to
- * transform a block into a stored block.
- */
- send_bits((STORED_BLOCK<<1)+eof, 3); /* send block type */
- compressed_len = (compressed_len + 3 + 7) & ~7L;
- compressed_len += (stored_len + 4) << 3;
-
- copy_block(buf, (unsigned)stored_len, 1); /* with header */
-
-#ifdef FORCE_METHOD
- } else if (level == 3) { /* force static trees */
-#else
- } else if (static_lenb == opt_lenb) {
-#endif
- send_bits((STATIC_TREES<<1)+eof, 3);
- compress_block((ct_data near *)static_ltree, (ct_data near *)static_dtree);
- compressed_len += 3 + static_len;
- } else {
- send_bits((DYN_TREES<<1)+eof, 3);
- send_all_trees(l_desc.max_code+1, d_desc.max_code+1, max_blindex+1);
- compress_block((ct_data near *)dyn_ltree, (ct_data near *)dyn_dtree);
- compressed_len += 3 + opt_len;
- }
- Assert (compressed_len == bits_sent, "bad compressed size");
- init_block();
-
- if (eof) {
- Assert (input_len == bytes_in, "bad input size");
- bi_windup();
- compressed_len += 7; /* align on byte boundary */
- } else if (pad && (compressed_len % 8) != 0) {
- send_bits((STORED_BLOCK<<1)+eof, 3); /* send block type */
- compressed_len = (compressed_len + 3 + 7) & ~7L;
- copy_block(buf, 0, 1); /* with header */
- }
-
- return compressed_len >> 3;
-}
-
-/* ===========================================================================
- * Save the match info and tally the frequency counts. Return true if
- * the current block must be flushed.
- */
-int ct_tally (dist, lc)
- int dist; /* distance of matched string */
- int lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */
-{
- l_buf[last_lit++] = (uch)lc;
- if (dist == 0) {
- /* lc is the unmatched char */
- dyn_ltree[lc].Freq++;
- } else {
- /* Here, lc is the match length - MIN_MATCH */
- dist--; /* dist = match distance - 1 */
- Assert((ush)dist < (ush)MAX_DIST &&
- (ush)lc <= (ush)(MAX_MATCH-MIN_MATCH) &&
- (ush)d_code(dist) < (ush)D_CODES, "ct_tally: bad match");
-
- dyn_ltree[length_code[lc]+LITERALS+1].Freq++;
- dyn_dtree[d_code(dist)].Freq++;
-
- d_buf[last_dist++] = (ush)dist;
- flags |= flag_bit;
- }
- flag_bit <<= 1;
-
- /* Output the flags if they fill a byte: */
- if ((last_lit & 7) == 0) {
- flag_buf[last_flags++] = flags;
- flags = 0, flag_bit = 1;
- }
- /* Try to guess if it is profitable to stop the current block here */
- if (level > 2 && (last_lit & 0xfff) == 0) {
- /* Compute an upper bound for the compressed length */
- ulg out_length = (ulg)last_lit*8L;
- ulg in_length = (ulg)strstart-block_start;
- int dcode;
- for (dcode = 0; dcode < D_CODES; dcode++) {
- out_length += (ulg)dyn_dtree[dcode].Freq*(5L+extra_dbits[dcode]);
- }
- out_length >>= 3;
- Trace((stderr,"\nlast_lit %u, last_dist %u, in %ld, out ~%ld(%ld%%) ",
- last_lit, last_dist, in_length, out_length,
- 100L - out_length*100L/in_length));
- if (last_dist < last_lit/2 && out_length < in_length/2) return 1;
- }
- return (last_lit == LIT_BUFSIZE-1 || last_dist == DIST_BUFSIZE);
- /* We avoid equality with LIT_BUFSIZE because of wraparound at 64K
- * on 16 bit machines and because stored blocks are restricted to
- * 64K-1 bytes.
- */
-}
-
-/* ===========================================================================
- * Send the block data compressed using the given Huffman trees
- */
-local void compress_block(ltree, dtree)
- ct_data near *ltree; /* literal tree */
- ct_data near *dtree; /* distance tree */
-{
- unsigned dist; /* distance of matched string */
- int lc; /* match length or unmatched char (if dist == 0) */
- unsigned lx = 0; /* running index in l_buf */
- unsigned dx = 0; /* running index in d_buf */
- unsigned fx = 0; /* running index in flag_buf */
- uch flag = 0; /* current flags */
- unsigned code; /* the code to send */
- int extra; /* number of extra bits to send */
-
- if (last_lit != 0) do {
- if ((lx & 7) == 0) flag = flag_buf[fx++];
- lc = l_buf[lx++];
- if ((flag & 1) == 0) {
- send_code(lc, ltree); /* send a literal byte */
- Tracecv(isgraph(lc), (stderr," '%c' ", lc));
- } else {
- /* Here, lc is the match length - MIN_MATCH */
- code = length_code[lc];
- send_code(code+LITERALS+1, ltree); /* send the length code */
- extra = extra_lbits[code];
- if (extra != 0) {
- lc -= base_length[code];
- send_bits(lc, extra); /* send the extra length bits */
- }
- dist = d_buf[dx++];
- /* Here, dist is the match distance - 1 */
- code = d_code(dist);
- Assert (code < D_CODES, "bad d_code");
-
- send_code(code, dtree); /* send the distance code */
- extra = extra_dbits[code];
- if (extra != 0) {
- dist -= base_dist[code];
- send_bits(dist, extra); /* send the extra distance bits */
- }
- } /* literal or match pair ? */
- flag >>= 1;
- } while (lx < last_lit);
-
- send_code(END_BLOCK, ltree);
-}
-
-/* ===========================================================================
- * Set the file type to ASCII or BINARY, using a crude approximation:
- * binary if more than 20% of the bytes are <= 6 or >= 128, ascii otherwise.
- * IN assertion: the fields freq of dyn_ltree are set and the total of all
- * frequencies does not exceed 64K (to fit in an int on 16 bit machines).
- */
-local void set_file_type()
-{
- int n = 0;
- unsigned ascii_freq = 0;
- unsigned bin_freq = 0;
- while (n < 7) bin_freq += dyn_ltree[n++].Freq;
- while (n < 128) ascii_freq += dyn_ltree[n++].Freq;
- while (n < LITERALS) bin_freq += dyn_ltree[n++].Freq;
- *file_type = bin_freq > (ascii_freq >> 2) ? BINARY : ASCII;
- if (*file_type == BINARY && translate_eol) {
- warning ("-l used on binary file");
- }
-}
-/* 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[] = "$Id: unlzh.c,v 1.2 1993/06/24 10:59:01 jloup Exp $";
-#endif
-
-/* 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 io_bitbuf;
-local unsigned subbitbuf;
-local int bitcount;
-
-local void fillbuf(n) /* Shift io_bitbuf n bits left, read n bits */
- int n;
-{
- io_bitbuf <<= n;
- while (n > bitcount) {
- io_bitbuf |= subbitbuf << (n -= bitcount);
- subbitbuf = (unsigned)try_byte();
- if ((int)subbitbuf == EOF) subbitbuf = 0;
- bitcount = CHAR_BIT;
- }
- io_bitbuf |= subbitbuf >> (bitcount -= n);
-}
-
-local unsigned getbits(n)
- int n;
-{
- unsigned x;
-
- x = io_bitbuf >> (BITBUFSIZ - n); fillbuf(n);
- return x;
-}
-
-local void init_getbits()
-{
- io_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]]++;
-
- 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");
-
- 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;
- }
-
- 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];
- 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) {
- c = io_bitbuf >> (BITBUFSIZ - 3);
- if (c == 7) {
- mask = (unsigned) 1 << (BITBUFSIZ - 1 - 3);
- while (mask & io_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 (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) {
- c = pt_table[io_bitbuf >> (BITBUFSIZ - 8)];
- if (c >= NT) {
- mask = (unsigned) 1 << (BITBUFSIZ - 1 - 8);
- do {
- if (io_bitbuf & mask) c = right[c];
- else c = left [c];
- mask >>= 1;
- } while (c >= NT);
- }
- 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;
- } 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[io_bitbuf >> (BITBUFSIZ - 12)];
- if (j >= NC) {
- mask = (unsigned) 1 << (BITBUFSIZ - 1 - 12);
- do {
- if (io_bitbuf & mask) j = right[j];
- else j = left [j];
- mask >>= 1;
- } while (j >= NC);
- }
- fillbuf((int) c_len[j]);
- return j;
-}
-
-local unsigned decode_p()
-{
- unsigned j, mask;
-
- j = pt_table[io_bitbuf >> (BITBUFSIZ - 8)];
- if (j >= NP) {
- mask = (unsigned) 1 << (BITBUFSIZ - 1 - 8);
- do {
- if (io_bitbuf & mask) j = right[j];
- else j = left [j];
- mask >>= 1;
- } while (j >= NP);
- }
- 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;
- }
- for ( ; ; ) {
- c = decode_c();
- if (c == NC) {
- done = 1;
- return r;
- }
- if (c <= UCHAR_MAX) {
- buffer[r] = c;
- 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;
- }
- }
- }
-}
-
-
-/* ===========================================================================
- * 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;
-}
-/* unlzw.c -- decompress files in LZW format.
- * The code in this file is directly derived from the public domain 'compress'
- * written by Spencer Thomas, Joe Orost, James Woods, Jim McKie, Steve Davies,
- * Ken Turkowski, Dave Mack and Peter Jannesen.
- *
- * This is a temporary version which will be rewritten in some future version
- * to accommodate in-memory decompression.
- */
-
-#ifdef RCSID
-static char rcsid[] = "$Id: unlzw.c,v 0.15 1993/06/10 13:28:35 jloup Exp $";
-#endif
-
-typedef unsigned char char_type;
-typedef long code_int;
-typedef unsigned long count_int;
-typedef unsigned short count_short;
-typedef unsigned long cmp_code_int;
-
-#define MAXCODE(n) (1L << (n))
-
-#ifndef REGISTERS
-# define REGISTERS 2
-#endif
-#define REG1
-#define REG2
-#define REG3
-#define REG4
-#define REG5
-#define REG6
-#define REG7
-#define REG8
-#define REG9
-#define REG10
-#define REG11
-#define REG12
-#define REG13
-#define REG14
-#define REG15
-#define REG16
-#if REGISTERS >= 1
-# undef REG1
-# define REG1 register
-#endif
-#if REGISTERS >= 2
-# undef REG2
-# define REG2 register
-#endif
-#if REGISTERS >= 3
-# undef REG3
-# define REG3 register
-#endif
-#if REGISTERS >= 4
-# undef REG4
-# define REG4 register
-#endif
-#if REGISTERS >= 5
-# undef REG5
-# define REG5 register
-#endif
-#if REGISTERS >= 6
-# undef REG6
-# define REG6 register
-#endif
-#if REGISTERS >= 7
-# undef REG7
-# define REG7 register
-#endif
-#if REGISTERS >= 8
-# undef REG8
-# define REG8 register
-#endif
-#if REGISTERS >= 9
-# undef REG9
-# define REG9 register
-#endif
-#if REGISTERS >= 10
-# undef REG10
-# define REG10 register
-#endif
-#if REGISTERS >= 11
-# undef REG11
-# define REG11 register
-#endif
-#if REGISTERS >= 12
-# undef REG12
-# define REG12 register
-#endif
-#if REGISTERS >= 13
-# undef REG13
-# define REG13 register
-#endif
-#if REGISTERS >= 14
-# undef REG14
-# define REG14 register
-#endif
-#if REGISTERS >= 15
-# undef REG15
-# define REG15 register
-#endif
-#if REGISTERS >= 16
-# undef REG16
-# define REG16 register
-#endif
-
-#ifndef BYTEORDER
-# define BYTEORDER 0000
-#endif
-
-#ifndef NOALLIGN
-# define NOALLIGN 0
-#endif
-
-
-union bytes {
- long word;
- struct {
-#if BYTEORDER == 4321
- char_type b1;
- char_type b2;
- char_type b3;
- char_type b4;
-#else
-#if BYTEORDER == 1234
- char_type b4;
- char_type b3;
- char_type b2;
- char_type b1;
-#else
-# undef BYTEORDER
- int dummy;
-#endif
-#endif
- } bytes;
-};
-
-#if BYTEORDER == 4321 && NOALLIGN == 1
-# define input(b,o,c,n,m){ \
- (c) = (*(long *)(&(b)[(o)>>3])>>((o)&0x7))&(m); \
- (o) += (n); \
- }
-#else
-# define input(b,o,c,n,m){ \
- REG1 char_type *p = &(b)[(o)>>3]; \
- (c) = ((((long)(p[0]))|((long)(p[1])<<8)| \
- ((long)(p[2])<<16))>>((o)&0x7))&(m); \
- (o) += (n); \
- }
-#endif
-
-#ifndef MAXSEG_64K
- /* DECLARE(ush, tab_prefix, (1<<BITS)); -- prefix code */
-# define tab_prefixof(i) tab_prefix[i]
-# define clear_tab_prefixof() memzero(tab_prefix, 256);
-#else
- /* DECLARE(ush, tab_prefix0, (1<<(BITS-1)); -- prefix for even codes */
- /* DECLARE(ush, tab_prefix1, (1<<(BITS-1)); -- prefix for odd codes */
- ush *tab_prefix[2];
-# define tab_prefixof(i) tab_prefix[(i)&1][(i)>>1]
-# define clear_tab_prefixof() \
- memzero(tab_prefix0, 128), \
- memzero(tab_prefix1, 128);
-#endif
-#define de_stack ((char_type *)(&d_buf[DIST_BUFSIZE-1]))
-#define tab_suffixof(i) tab_suffix[i]
-
-int block_mode = BLOCK_MODE; /* block compress mode -C compatible with 2.0 */
-
-/* ============================================================================
- * Decompress in to out. This routine adapts to the codes in the
- * file building the "string" table on-the-fly; requiring no table to
- * be stored in the compressed file.
- * IN assertions: the buffer inbuf contains already the beginning of
- * the compressed data, from offsets iptr to insize-1 included.
- * The magic header has already been checked and skipped.
- * bytes_in and bytes_out have been initialized.
- */
-int unlzw(in, out)
- int in, out; /* input and output file descriptors */
-{
- REG2 char_type *stackp;
- REG3 code_int code;
- REG4 int finchar;
- REG5 code_int oldcode;
- REG6 code_int incode;
- REG7 long inbits;
- REG8 long posbits;
- REG9 int outpos;
-/* REG10 int insize; (global) */
- REG11 unsigned bitmask;
- REG12 code_int free_ent;
- REG13 code_int maxcode;
- REG14 code_int maxmaxcode;
- REG15 int n_bits;
- REG16 int rsize;
-
-#ifdef MAXSEG_64K
- tab_prefix[0] = tab_prefix0;
- tab_prefix[1] = tab_prefix1;
-#endif
- maxbits = get_byte();
- block_mode = maxbits & BLOCK_MODE;
- if ((maxbits & LZW_RESERVED) != 0) {
- WARN((stderr, "\n%s: %s: warning, unknown flags 0x%x\n",
- progname, ifname, maxbits & LZW_RESERVED));
- }
- maxbits &= BIT_MASK;
- maxmaxcode = MAXCODE(maxbits);
-
- if (maxbits > BITS) {
- fprintf(stderr,
- "\n%s: %s: compressed with %d bits, can only handle %d bits\n",
- progname, ifname, maxbits, BITS);
- exit_code = ERROR;
- return ERROR;
- }
- rsize = insize;
- maxcode = MAXCODE(n_bits = INIT_BITS)-1;
- bitmask = (1<<n_bits)-1;
- oldcode = -1;
- finchar = 0;
- outpos = 0;
- posbits = inptr<<3;
-
- free_ent = ((block_mode) ? FIRST : 256);
-
- clear_tab_prefixof(); /* Initialize the first 256 entries in the table. */
-
- for (code = 255 ; code >= 0 ; --code) {
- tab_suffixof(code) = (char_type)code;
- }
- do {
- REG1 int i;
- int e;
- int o;
-
- resetbuf:
- e = insize-(o = (posbits>>3));
-
- for (i = 0 ; i < e ; ++i) {
- inbuf[i] = inbuf[i+o];
- }
- insize = e;
- posbits = 0;
-
- if (insize < INBUF_EXTRA) {
- if ((rsize = read(in, (char*)inbuf+insize, INBUFSIZ)) == -1) {
- read_error();
- }
- insize += rsize;
- bytes_in += (off_t)rsize;
- }
- inbits = ((rsize != 0) ? ((long)insize - insize%n_bits)<<3 :
- ((long)insize<<3)-(n_bits-1));
-
- while (inbits > posbits) {
- if (free_ent > maxcode) {
- posbits = ((posbits-1) +
- ((n_bits<<3)-(posbits-1+(n_bits<<3))%(n_bits<<3)));
- ++n_bits;
- if (n_bits == maxbits) {
- maxcode = maxmaxcode;
- } else {
- maxcode = MAXCODE(n_bits)-1;
- }
- bitmask = (1<<n_bits)-1;
- goto resetbuf;
- }
- input(inbuf,posbits,code,n_bits,bitmask);
- Tracev((stderr, "%d ", code));
-
- if (oldcode == -1) {
- if (code >= 256) error("corrupt input.");
- outbuf[outpos++] = (char_type)(finchar = (int)(oldcode=code));
- continue;
- }
- if (code == CLEAR && block_mode) {
- clear_tab_prefixof();
- free_ent = FIRST - 1;
- posbits = ((posbits-1) +
- ((n_bits<<3)-(posbits-1+(n_bits<<3))%(n_bits<<3)));
- maxcode = MAXCODE(n_bits = INIT_BITS)-1;
- bitmask = (1<<n_bits)-1;
- goto resetbuf;
- }
- incode = code;
- stackp = de_stack;
-
- if (code >= free_ent) { /* Special case for KwKwK string. */
- if (code > free_ent) {
-#ifdef DEBUG
- char_type *p;
-
- posbits -= n_bits;
- p = &inbuf[posbits>>3];
- fprintf(stderr,
- "code:%ld free_ent:%ld n_bits:%d insize:%u\n",
- code, free_ent, n_bits, insize);
- fprintf(stderr,
- "posbits:%ld inbuf:%02X %02X %02X %02X %02X\n",
- posbits, p[-1],p[0],p[1],p[2],p[3]);
-#endif
- if (!test && outpos > 0) {
- write_buf(out, (char*)outbuf, outpos);
- bytes_out += (off_t)outpos;
- }
- error(to_stdout ? "corrupt input." :
- "corrupt input. Use zcat to recover some data.");
- }
- *--stackp = (char_type)finchar;
- code = oldcode;
- }
-
- while ((cmp_code_int)code >= (cmp_code_int)256) {
- /* Generate output characters in reverse order */
- *--stackp = tab_suffixof(code);
- code = tab_prefixof(code);
- }
- *--stackp = (char_type)(finchar = tab_suffixof(code));
-
- /* And put them out in forward order */
- {
- REG1 int i;
-
- if (outpos+(i = (de_stack-stackp)) >= OUTBUFSIZ) {
- do {
- if (i > OUTBUFSIZ-outpos) i = OUTBUFSIZ-outpos;
-
- if (i > 0) {
- memcpy(outbuf+outpos, stackp, i);
- outpos += i;
- }
- if (outpos >= OUTBUFSIZ) {
- if (!test) {
- write_buf(out, (char*)outbuf, outpos);
- bytes_out += (off_t)outpos;
- }
- outpos = 0;
- }
- stackp+= i;
- } while ((i = (de_stack-stackp)) > 0);
- } else {
- memcpy(outbuf+outpos, stackp, i);
- outpos += i;
- }
- }
-
- if ((code = free_ent) < maxmaxcode) { /* Generate the new entry. */
-
- tab_prefixof(code) = (unsigned short)oldcode;
- tab_suffixof(code) = (char_type)finchar;
- free_ent = code+1;
- }
- oldcode = incode; /* Remember previous code. */
- }
- } while (rsize != 0);
-
- if (!test && outpos > 0) {
- write_buf(out, (char*)outbuf, outpos);
- bytes_out += (off_t)outpos;
- }
- return OK;
-}
-/* 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[] = "$Id: unpack.c,v 1.4 1993/06/11 19:25:36 jloup Exp $";
-#endif
-
-#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<<MAX_PEEK) > 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<<bits)-1.
- */
-#define look_bits(code,bits,mask) \
-{ \
- while (valid < (bits)) bitbuf = (bitbuf<<8) | (ulg)get_byte(), valid += 8; \
- code = (bitbuf >> (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 %lu, 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--) {
- 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<<peek_bits];
- for (len = 1; len <= peek_bits; len++) {
- int prefixes = leaves[len] << (peek_bits-len); /* may be 0 */
- while (prefixes--) *--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<<peek_bits)-1;
-
- /* The eob code is the largest code among all leaves of maximal length: */
- eob = leaves[max_len]-1;
- Trace((stderr, "eob %d %x\n", max_len, eob));
-
- /* Decode the input data: */
- for (;;) {
- /* Since eob is the longest code and not shorter than max_len,
- * we can peek at max_len bits without having the risk of reading
- * beyond the end of file.
- */
- look_bits(peek, peek_bits, peek_mask);
- len = prefix_len[peek];
- if (len > 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();
- if (orig_len != (ulg)(bytes_out & 0xffffffff)) {
- error("invalid compressed data--length error");
- }
- return OK;
-}
-/* unzip.c -- decompress files in gzip or pkzip 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.
- *
- * The code in this file is derived from the file funzip.c written
- * and put in the public domain by Mark Adler.
- */
-
-/*
- This version can extract files in gzip or pkzip format.
- For the latter, only the first entry is extracted, and it has to be
- either deflated or stored.
- */
-
-#ifdef RCSID
-static char rcsid[] = "$Id: unzip.c,v 0.13 1993/06/10 13:29:00 jloup Exp $";
-#endif
-
-/* PKZIP header definitions */
-#define LOCSIG 0x04034b50L /* four-byte lead-in (lsb first) */
-#define LOCFLG 6 /* offset of bit flag */
-#define CRPFLG 1 /* bit for encrypted entry */
-#define EXTFLG 8 /* bit for extended local header */
-#define LOCHOW 8 /* offset of compression method */
-#define LOCTIM 10 /* file mod time (for decryption) */
-#define LOCCRC 14 /* offset of crc */
-#define LOCSIZ 18 /* offset of compressed size */
-#define LOCLEN 22 /* offset of uncompressed length */
-#define LOCFIL 26 /* offset of file name field length */
-#define LOCEXT 28 /* offset of extra field length */
-#define LOCHDR 30 /* size of local header, including sig */
-#define EXTHDR 16 /* size of extended local header, inc sig */
-#define RAND_HEAD_LEN 12 /* length of encryption random header */
-
-
-/* Globals */
-
-int decrypt; /* flag to turn on decryption */
-char *key; /* not used--needed to link crypt.c */
-int pkzip = 0; /* set for a pkzip file */
-int ext_header = 0; /* set if extended local header */
-
-/* ===========================================================================
- * Check zip file and advance inptr to the start of the compressed data.
- * Get ofname from the local header if necessary.
- */
-int check_zipfile(in)
- int in; /* input file descriptors */
-{
- uch *h = inbuf + inptr; /* first local header */
-
- ifd = in;
-
- /* Check validity of local header, and skip name and extra fields */
- inptr += LOCHDR + SH(h + LOCFIL) + SH(h + LOCEXT);
-
- if (inptr > insize || LG(h) != LOCSIG) {
- fprintf(stderr, "\n%s: %s: not a valid zip file\n",
- progname, ifname);
- exit_code = ERROR;
- return ERROR;
- }
- method = h[LOCHOW];
- if (method != STORED && method != DEFLATED) {
- fprintf(stderr,
- "\n%s: %s: first entry not deflated or stored -- use unzip\n",
- progname, ifname);
- exit_code = ERROR;
- return ERROR;
- }
-
- /* If entry encrypted, decrypt and validate encryption header */
- if ((decrypt = h[LOCFLG] & CRPFLG) != 0) {
- fprintf(stderr, "\n%s: %s: encrypted file -- use unzip\n",
- progname, ifname);
- exit_code = ERROR;
- return ERROR;
- }
-
- /* Save flags for unzip() */
- ext_header = (h[LOCFLG] & EXTFLG) != 0;
- pkzip = 1;
-
- /* Get ofname and time stamp from local header (to be done) */
- return OK;
-}
-
-/* ===========================================================================
- * Unzip in to out. This routine works on both gzip and pkzip files.
- *
- * 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 unzip(in, out)
- int in, out; /* input and output file descriptors */
-{
- ulg orig_crc = 0; /* original crc */
- ulg orig_len = 0; /* original uncompressed length */
- int n;
- uch buf[EXTHDR]; /* extended local header */
- int err = OK;
-
- ifd = in;
- ofd = out;
-
- updcrc(NULL, 0); /* initialize crc */
-
- if (pkzip && !ext_header) { /* crc and length at the end otherwise */
- orig_crc = LG(inbuf + LOCCRC);
- orig_len = LG(inbuf + LOCLEN);
- }
-
- /* Decompress */
- if (method == DEFLATED) {
-
- int res = inflate();
-
- if (res == 3) {
- error("out of memory");
- } else if (res != 0) {
- error("invalid compressed data--format violated");
- }
-
- } else if (pkzip && method == STORED) {
-
- register ulg n = LG(inbuf + LOCLEN);
-
- if (n != LG(inbuf + LOCSIZ) - (decrypt ? RAND_HEAD_LEN : 0)) {
-
- fprintf(stderr, "len %ld, siz %ld\n", n, LG(inbuf + LOCSIZ));
- error("invalid compressed data--length mismatch");
- }
- while (n--) {
- uch c = (uch)get_byte();
- put_ubyte(c);
- }
- flush_window();
- } else {
- error("internal error, invalid method");
- }
-
- /* Get the crc and original length */
- if (!pkzip) {
- /* crc32 (see algorithm.doc)
- * uncompressed input size modulo 2^32
- */
- for (n = 0; n < 8; n++) {
- buf[n] = (uch)get_byte(); /* may cause an error if EOF */
- }
- orig_crc = LG(buf);
- orig_len = LG(buf+4);
-
- } else if (ext_header) { /* If extended header, check it */
- /* signature - 4bytes: 0x50 0x4b 0x07 0x08
- * CRC-32 value
- * compressed size 4-bytes
- * uncompressed size 4-bytes
- */
- for (n = 0; n < EXTHDR; n++) {
- buf[n] = (uch)get_byte(); /* may cause an error if EOF */
- }
- orig_crc = LG(buf+4);
- orig_len = LG(buf+12);
- }
-
- /* Validate decompression */
- if (orig_crc != updcrc(outbuf, 0)) {
- fprintf(stderr, "\n%s: %s: invalid compressed data--crc error\n",
- progname, ifname);
- err = ERROR;
- }
- if (orig_len != (ulg)(bytes_out & 0xffffffff)) {
- fprintf(stderr, "\n%s: %s: invalid compressed data--length error\n",
- progname, ifname);
- err = ERROR;
- }
-
- /* Check if there are more entries in a pkzip file */
- if (pkzip && inptr + 4 < insize && LG(inbuf+inptr) == LOCSIG) {
- if (to_stdout) {
- WARN((stderr,
- "%s: %s has more than one entry--rest ignored\n",
- progname, ifname));
- } else {
- /* Don't destroy the input zip file */
- fprintf(stderr,
- "%s: %s has more than one entry -- unchanged\n",
- progname, ifname);
- err = ERROR;
- }
- }
- ext_header = pkzip = 0; /* for next file */
- if (err == OK) return OK;
- exit_code = ERROR;
- if (!test) abort_gzip();
- return err;
-}
-/* util.c -- utility functions for gzip support
- * Copyright (C) 1997, 1998, 1999, 2001 Free Software Foundation, Inc.
- * 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[] = "$Id: util.c,v 0.15 1993/06/15 09:04:13 jloup Exp $";
-#endif
-
-#ifndef CHAR_BIT
-# define CHAR_BIT 8
-#endif
-
-extern ulg crc_32_tab[]; /* crc table, defined below */
-
-/* ===========================================================================
- * Copy input to output unchanged: zcat == cat with --force.
- * IN assertion: insize bytes have already been read in inbuf.
- */
-int copy(in, out)
- int in, out; /* input and output file descriptors */
-{
- errno = 0;
- while (insize != 0 && (int)insize != -1) {
- write_buf(out, (char*)inbuf, insize);
- bytes_out += insize;
- insize = read(in, (char*)inbuf, INBUFSIZ);
- }
- if ((int)insize == -1) {
- read_error();
- }
- bytes_in = bytes_out;
- return OK;
-}
-
-/* ===========================================================================
- * 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.
- */
-ulg updcrc(s, n)
- uch *s; /* pointer to bytes to pump through */
- unsigned n; /* number of bytes in s[] */
-{
- register ulg c; /* temporary variable */
-
- static ulg crc = (ulg)0xffffffffL; /* shift register contents */
-
- if (s == NULL) {
- c = 0xffffffffL;
- } else {
- c = crc;
- if (n) do {
- c = crc_32_tab[((int)c ^ (*s++)) & 0xff] ^ (c >> 8);
- } while (--n);
- }
- crc = c;
- return c ^ 0xffffffffL; /* (instead of ~c for 64-bit machines) */
-}
-
-/* ===========================================================================
- * Clear input and output buffers
- */
-void clear_bufs()
-{
- outcnt = 0;
- insize = inptr = 0;
- bytes_in = bytes_out = 0L;
-}
-
-/* ===========================================================================
- * Fill the input buffer. This is called only when the buffer is empty.
- */
-int fill_inbuf(eof_ok)
- int eof_ok; /* set if EOF acceptable as a result */
-{
- int len;
-
- /* Read as much as possible */
- insize = 0;
- do {
- len = read(ifd, (char*)inbuf+insize, INBUFSIZ-insize);
- if (len == 0) break;
- if (len == -1) {
- read_error();
- break;
- }
- insize += len;
- } while (insize < INBUFSIZ);
-
- if (insize == 0) {
- if (eof_ok) return EOF;
- flush_window();
- errno = 0;
- read_error();
- }
- bytes_in += (off_t)insize;
- inptr = 1;
- return inbuf[0];
-}
-
-/* ===========================================================================
- * Write the output buffer outbuf[0..outcnt-1] and update bytes_out.
- * (used for the compressed data only)
- */
-void flush_outbuf()
-{
- if (outcnt == 0) return;
-
- write_buf(ofd, (char *)outbuf, outcnt);
- bytes_out += (off_t)outcnt;
- outcnt = 0;
-}
-
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-void flush_window()
-{
- if (outcnt == 0) return;
- updcrc(window, outcnt);
-
- if (!test) {
- write_buf(ofd, (char *)window, outcnt);
- }
- bytes_out += (off_t)outcnt;
- outcnt = 0;
-}
-
-/* ===========================================================================
- * Does the same as write(), but also handles partial pipe writes and checks
- * for error return.
- */
-void write_buf(fd, buf, cnt)
- int fd;
- voidp buf;
- unsigned cnt;
-{
- unsigned n;
-
- while ((n = write(fd, buf, cnt)) != cnt) {
- if (n == (unsigned)(-1)) {
- write_error();
- }
- cnt -= n;
- buf = (voidp)((char*)buf+n);
- }
-}
-
-/* ========================================================================
- * Put string s in lower case, return s.
- */
-char *strlwr(s)
- char *s;
-{
- char *t;
- for (t = s; *t; t++)
- *t = tolow ((unsigned char) *t);
- return s;
-}
-
-/* ========================================================================
- * Return the base name of a file (remove any directory prefix and
- * any version suffix). For systems with file names that are not
- * case sensitive, force the base name to lower case.
- */
-char *base_name(fname)
- char *fname;
-{
- char *p;
-
- if ((p = strrchr(fname, PATH_SEP)) != NULL) fname = p+1;
-#ifdef PATH_SEP2
- if ((p = strrchr(fname, PATH_SEP2)) != NULL) fname = p+1;
-#endif
-#ifdef PATH_SEP3
- if ((p = strrchr(fname, PATH_SEP3)) != NULL) fname = p+1;
-#endif
-#ifdef SUFFIX_SEP
- if ((p = strrchr(fname, SUFFIX_SEP)) != NULL) *p = '\0';
-#endif
- if (casemap('A') == 'a') strlwr(fname);
- return fname;
-}
-
-/* ========================================================================
- * Unlink a file, working around the unlink readonly bug (if present).
- */
-int xunlink (filename)
- char *filename;
-{
- int r = unlink (filename);
-
-#ifdef UNLINK_READONLY_BUG
- if (r != 0)
- {
- int e = errno;
- if (chmod (filename, S_IWUSR) != 0)
- {
- errno = e;
- return -1;
- }
-
- r = unlink (filename);
- }
-#endif
-
- return r;
-}
-
-/* ========================================================================
- * Make a file name legal for file systems not allowing file names with
- * multiple dots or starting with a dot (such as MSDOS), by changing
- * all dots except the last one into underlines. A target dependent
- * function can be used instead of this simple function by defining the macro
- * MAKE_LEGAL_NAME in tailor.h and providing the function in a target
- * dependent module.
- */
-void make_simple_name(name)
- char *name;
-{
- char *p = strrchr(name, '.');
- if (p == NULL) return;
- if (p == name) p++;
- do {
- if (*--p == '.') *p = '_';
- } while (p != name);
-}
-
-
-#if !defined HAVE_STRING_H && !defined STDC_HEADERS
-
-/* Provide missing strspn and strcspn functions. */
-
-# ifndef __STDC__
-# define const
-# endif
-
-int strspn OF((const char *s, const char *accept));
-int strcspn OF((const char *s, const char *reject));
-
-/* ========================================================================
- * Return the length of the maximum initial segment
- * of s which contains only characters in accept.
- */
-int strspn(s, accept)
- const char *s;
- const char *accept;
-{
- register const char *p;
- register const char *a;
- register int count = 0;
-
- for (p = s; *p != '\0'; ++p) {
- for (a = accept; *a != '\0'; ++a) {
- if (*p == *a) break;
- }
- if (*a == '\0') return count;
- ++count;
- }
- return count;
-}
-
-/* ========================================================================
- * Return the length of the maximum inital segment of s
- * which contains no characters from reject.
- */
-int strcspn(s, reject)
- const char *s;
- const char *reject;
-{
- register int count = 0;
-
- while (*s != '\0') {
- if (strchr(reject, *s++) != NULL) return count;
- ++count;
- }
- return count;
-}
-
-#endif
-
-/* ========================================================================
- * Add an environment variable (if any) before argv, and update argc.
- * Return the expanded environment variable to be freed later, or NULL
- * if no options were added to argv.
- */
-#define SEPARATOR " \t" /* separators in env variable */
-
-char *add_envopt(argcp, argvp, env)
- int *argcp; /* pointer to argc */
- char ***argvp; /* pointer to argv */
- char *env; /* name of environment variable */
-{
- char *p; /* running pointer through env variable */
- char **oargv; /* runs through old argv array */
- char **nargv; /* runs through new argv array */
- int oargc = *argcp; /* old argc */
- int nargc = 0; /* number of arguments in env variable */
-
- env = (char*)getenv(env);
- if (env == NULL) return NULL;
-
- p = (char*)xmalloc(strlen(env)+1);
- env = strcpy(p, env); /* keep env variable intact */
-
- for (p = env; *p; nargc++ ) { /* move through env */
- p += strspn(p, SEPARATOR); /* skip leading separators */
- if (*p == '\0') break;
-
- p += strcspn(p, SEPARATOR); /* find end of word */
- if (*p) *p++ = '\0'; /* mark it */
- }
- if (nargc == 0) {
- free(env);
- return NULL;
- }
- *argcp += nargc;
- /* Allocate the new argv array, with an extra element just in case
- * the original arg list did not end with a NULL.
- */
- nargv = (char**)calloc(*argcp+1, sizeof(char *));
- if (nargv == NULL) error("out of memory");
- oargv = *argvp;
- *argvp = nargv;
-
- /* Copy the program name first */
- if (oargc-- < 0) error("argc<=0");
- *(nargv++) = *(oargv++);
-
- /* Then copy the environment args */
- for (p = env; nargc > 0; nargc--) {
- p += strspn(p, SEPARATOR); /* skip separators */
- *(nargv++) = p; /* store start */
- while (*p++) ; /* skip over word */
- }
-
- /* Finally copy the old args and add a NULL (usual convention) */
- while (oargc--) *(nargv++) = *(oargv++);
- *nargv = NULL;
- return env;
-}
-
-/* ========================================================================
- * Error handlers.
- */
-void error(m)
- char *m;
-{
- fprintf(stderr, "\n%s: %s: %s\n", progname, ifname, m);
- abort_gzip();
-}
-
-void warning (m)
- char *m;
-{
- WARN ((stderr, "%s: %s: warning: %s\n", progname, ifname, m));
-}
-
-void read_error()
-{
- int e = errno;
- fprintf(stderr, "\n%s: ", progname);
- if (e != 0) {
- errno = e;
- perror(ifname);
- } else {
- fprintf(stderr, "%s: unexpected end of file\n", ifname);
- }
- abort_gzip();
-}
-
-void write_error()
-{
- int e = errno;
- fprintf(stderr, "\n%s: ", progname);
- errno = e;
- perror(ofname);
- abort_gzip();
-}
-
-/* ========================================================================
- * Display compression ratio on the given stream on 6 characters.
- */
-void display_ratio(num, den, file)
- off_t num;
- off_t den;
- FILE *file;
-{
- fprintf(file, "%5.1f%%", den == 0 ? 0 : 100.0 * num / den);
-}
-
-/* ========================================================================
- * Print an off_t. There's no completely portable way to use printf,
- * so we do it ourselves.
- */
-void fprint_off(file, offset, width)
- FILE *file;
- off_t offset;
- int width;
-{
- char buf[CHAR_BIT * sizeof (off_t)];
- char *p = buf + sizeof buf;
-
- /* Don't negate offset here; it might overflow. */
- if (offset < 0) {
- do
- *--p = '0' - offset % 10;
- while ((offset /= 10) != 0);
-
- *--p = '-';
- } else {
- do
- *--p = '0' + offset % 10;
- while ((offset /= 10) != 0);
- }
-
- width -= buf + sizeof buf - p;
- while (0 < width--) {
- putc (' ', file);
- }
- for (; p < buf + sizeof buf; p++)
- putc (*p, file);
-}
-
-/* ========================================================================
- * Semi-safe malloc -- never returns NULL.
- */
-voidp xmalloc (size)
- unsigned size;
-{
- voidp cp = (voidp)malloc (size);
-
- if (cp == NULL) error("out of memory");
- return cp;
-}
-
-/* ========================================================================
- * 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
-};
-/* yesno.c -- read a yes/no response from stdin
- Copyright (C) 1990, 1998 Free Software Foundation, Inc.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software Foundation,
- Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
-
-/* Read one line from standard input
- and return nonzero if that line begins with y or Y,
- otherwise return 0. */
-
-int rpmatch ();
-
-int
-yesno ()
-{
- /* We make some assumptions here:
- a) leading white space in the response are not vital
- b) the first 128 characters of the answer are enough (the rest can
- be ignored)
- I cannot think for a situation where this is not ok. --drepper at gnu */
- char buf[128];
- int len = 0;
- int c;
-
- while ((c = getchar ()) != EOF && c != '\n')
- if ((len > 0 && len < 127) || (len == 0 && !isspace (c)))
- buf[len++] = c;
- buf[len] = '\0';
-
- return rpmatch (buf) == 1;
-}
-/* zip.c -- compress files to the gzip or pkzip 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[] = "$Id: zip.c,v 0.17 1993/06/10 13:29:25 jloup Exp $";
-#endif
-
-local ulg crc; /* crc on uncompressed file data */
-off_t header_bytes; /* number of bytes in gzip header */
-
-/* ===========================================================================
- * Deflate in to out.
- * IN assertions: the input and output buffers are cleared.
- * The variables time_stamp and save_orig_name are initialized.
- */
-int zip(in, out)
- int in, out; /* input and output file descriptors */
-{
- uch flags = 0; /* general purpose bit flags */
- ush attr = 0; /* ascii/binary flag */
- ush deflate_flags = 0; /* pkzip -es, -en or -ex equivalent */
-
- ifd = in;
- ofd = out;
- outcnt = 0;
-
- /* Write the header to the gzip file. See algorithm.doc for the format */
-
- method = DEFLATED;
- put_byte(GZIP_MAGIC[0]); /* magic header */
- put_byte(GZIP_MAGIC[1]);
- put_byte(DEFLATED); /* compression method */
-
- if (save_orig_name) {
- flags |= ORIG_NAME;
- }
- put_byte(flags); /* general flags */
- put_long(time_stamp == (time_stamp & 0xffffffff)
- ? (ulg)time_stamp : (ulg)0);
-
- /* Write deflated file to zip file */
- crc = updcrc(0, 0);
-
- bi_init(out);
- ct_init(&attr, &method);
- lm_init(level, &deflate_flags);
-
- put_byte((uch)deflate_flags); /* extra flags */
- put_byte(OS_CODE); /* OS identifier */
-
- if (save_orig_name) {
- char *p = base_name(ifname); /* Don't save the directory part. */
- do {
- put_char(*p);
- } while (*p++);
- }
- header_bytes = (off_t)outcnt;
-
- (void)deflate();
-
-#if !defined(NO_SIZE_CHECK) && !defined(RECORD_IO)
- /* Check input size (but not in VMS -- variable record lengths mess it up)
- * and not on MSDOS -- diet in TSR mode reports an incorrect file size)
- */
- if (ifile_size != -1L && bytes_in != ifile_size) {
- fprintf(stderr, "%s: %s: file size changed while zipping\n",
- progname, ifname);
- }
-#endif
-
- /* Write the crc and uncompressed size */
- put_long(crc);
- put_long((ulg)bytes_in);
- header_bytes += 2*sizeof(long);
-
- flush_outbuf();
- return OK;
-}
-
-
-/* ===========================================================================
- * Read a new buffer from the current input file, perform end-of-line
- * translation, and update the crc and input file size.
- * IN assertion: size >= 2 (for end-of-line translation)
- */
-int file_read(buf, size)
- char *buf;
- unsigned size;
-{
- unsigned len;
-
- Assert(insize == 0, "inbuf not empty");
-
- len = read(ifd, buf, size);
- if (len == 0) return (int)len;
- if (len == (unsigned)-1) {
- read_error();
- return EOF;
- }
-
- crc = updcrc((uch*)buf, len);
- bytes_in += (off_t)len;
- return (int)len;
-}
-
-/* Determine whether string value is affirmation or negative response
- according to current locale's data.
- Copyright (C) 1996, 1998, 2000 Free Software Foundation, Inc.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software Foundation,
- Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
-
-int
-rpmatch (const char *response)
-{
- /* Test against "^[yY]" and "^[nN]", hardcoded to avoid requiring regex */
- return (*response == 'y' || *response == 'Y' ? 1
- : *response == 'n' || *response == 'N' ? 0 : -1);
-}
-
-
-int
-getopt_long (argc, argv, options, long_options, opt_index)
- int argc;
- char *const *argv;
- const char *options;
- const struct option *long_options;
- int *opt_index;
-{
- return _getopt_internal (argc, argv, options, long_options, opt_index, 0);
-}
-
-/* Like getopt_long, but '-' as well as '--' can indicate a long option.
- If an option that starts with '-' (not '--') doesn't match a long option,
- but does match a short option, it is parsed as a short option
- instead. */
-
-int
-getopt_long_only (argc, argv, options, long_options, opt_index)
- int argc;
- char *const *argv;
- const char *options;
- const struct option *long_options;
- int *opt_index;
-{
- return _getopt_internal (argc, argv, options, long_options, opt_index, 1);
-}
More information about the llvm-commits
mailing list