diff options
| -rw-r--r-- | dep/PackageList.txt | 2 | ||||
| -rw-r--r-- | dep/bzip2/LICENSE | 42 | ||||
| -rw-r--r-- | dep/bzip2/README | 215 | ||||
| -rw-r--r-- | dep/bzip2/blocksort.c | 4 | ||||
| -rw-r--r-- | dep/bzip2/bzip2.c | 2034 | ||||
| -rw-r--r-- | dep/bzip2/bzip2recover.c | 514 | ||||
| -rw-r--r-- | dep/bzip2/bzlib.c | 4 | ||||
| -rw-r--r-- | dep/bzip2/bzlib.h | 4 | ||||
| -rw-r--r-- | dep/bzip2/bzlib_private.h | 6 | ||||
| -rw-r--r-- | dep/bzip2/compress.c | 4 | ||||
| -rw-r--r-- | dep/bzip2/crctable.c | 4 | ||||
| -rw-r--r-- | dep/bzip2/decompress.c | 24 | ||||
| -rw-r--r-- | dep/bzip2/huffman.c | 4 | ||||
| -rw-r--r-- | dep/bzip2/randtable.c | 4 |
14 files changed, 2845 insertions, 20 deletions
diff --git a/dep/PackageList.txt b/dep/PackageList.txt index 04cdaef9e66..d20c15db256 100644 --- a/dep/PackageList.txt +++ b/dep/PackageList.txt @@ -6,7 +6,7 @@ ACE (ADAPTIVE Communication Environment) bzip2 (a freely available, patent free, high-quality data compressor) http://www.bzip.org/ - Version: 1.0.5 + Version: 1.0.6 G3D (a commercial-grade C++ 3D engine available as Open Source (BSD License) http://g3d.sourceforge.net/ diff --git a/dep/bzip2/LICENSE b/dep/bzip2/LICENSE new file mode 100644 index 00000000000..cc614178cf7 --- /dev/null +++ b/dep/bzip2/LICENSE @@ -0,0 +1,42 @@ + +-------------------------------------------------------------------------- + +This program, "bzip2", the associated library "libbzip2", and all +documentation, are copyright (C) 1996-2010 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, jseward@bzip.org +bzip2/libbzip2 version 1.0.6 of 6 September 2010 + +-------------------------------------------------------------------------- diff --git a/dep/bzip2/README b/dep/bzip2/README new file mode 100644 index 00000000000..9fb0f636013 --- /dev/null +++ b/dep/bzip2/README @@ -0,0 +1,215 @@ + +This is the README for bzip2/libzip2. +This version is fully compatible with the previous public releases. + +------------------------------------------------------------------ +This file is part of bzip2/libbzip2, a program and library for +lossless, block-sorting data compression. + +bzip2/libbzip2 version 1.0.6 of 6 September 2010 +Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> + +Please read the WARNING, DISCLAIMER and PATENTS sections in this file. + +This program is released under the terms of the license contained +in the file LICENSE. +------------------------------------------------------------------ + +Complete documentation is available in Postscript form (manual.ps), +PDF (manual.pdf) or html (manual.html). A plain-text version of the +manual page is available as bzip2.txt. + + +HOW TO BUILD -- UNIX + +Type 'make'. This builds the library libbz2.a and then the programs +bzip2 and bzip2recover. Six self-tests are run. If the self-tests +complete ok, carry on to installation: + +To install in /usr/local/bin, /usr/local/lib, /usr/local/man and +/usr/local/include, type + + make install + +To install somewhere else, eg, /xxx/yyy/{bin,lib,man,include}, type + + make install PREFIX=/xxx/yyy + +If you are (justifiably) paranoid and want to see what 'make install' +is going to do, you can first do + + make -n install or + make -n install PREFIX=/xxx/yyy respectively. + +The -n instructs make to show the commands it would execute, but not +actually execute them. + + +HOW TO BUILD -- UNIX, shared library libbz2.so. + +Do 'make -f Makefile-libbz2_so'. This Makefile seems to work for +Linux-ELF (RedHat 7.2 on an x86 box), with gcc. I make no claims +that it works for any other platform, though I suspect it probably +will work for most platforms employing both ELF and gcc. + +bzip2-shared, a client of the shared library, is also built, but not +self-tested. So I suggest you also build using the normal Makefile, +since that conducts a self-test. A second reason to prefer the +version statically linked to the library is that, on x86 platforms, +building shared objects makes a valuable register (%ebx) unavailable +to gcc, resulting in a slowdown of 10%-20%, at least for bzip2. + +Important note for people upgrading .so's from 0.9.0/0.9.5 to version +1.0.X. All the functions in the library have been renamed, from (eg) +bzCompress to BZ2_bzCompress, to avoid namespace pollution. +Unfortunately this means that the libbz2.so created by +Makefile-libbz2_so will not work with any program which used an older +version of the library. I do encourage library clients to make the +effort to upgrade to use version 1.0, since it is both faster and more +robust than previous versions. + + +HOW TO BUILD -- Windows 95, NT, DOS, Mac, etc. + +It's difficult for me to support compilation on all these platforms. +My approach is to collect binaries for these platforms, and put them +on the master web site (http://www.bzip.org). Look there. However +(FWIW), bzip2-1.0.X is very standard ANSI C and should compile +unmodified with MS Visual C. If you have difficulties building, you +might want to read README.COMPILATION.PROBLEMS. + +At least using MS Visual C++ 6, you can build from the unmodified +sources by issuing, in a command shell: + + nmake -f makefile.msc + +(you may need to first run the MSVC-provided script VCVARS32.BAT + so as to set up paths to the MSVC tools correctly). + + +VALIDATION + +Correct operation, in the sense that a compressed file can always be +decompressed to reproduce the original, is obviously of paramount +importance. To validate bzip2, I used a modified version of Mark +Nelson's churn program. Churn is an automated test driver which +recursively traverses a directory structure, using bzip2 to compress +and then decompress each file it encounters, and checking that the +decompressed data is the same as the original. + + + +Please read and be aware of the following: + +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 disastrous loss of data. + + +DISCLAIMER: + + I TAKE NO RESPONSIBILITY FOR ANY LOSS OF DATA ARISING FROM THE + USE OF THIS PROGRAM/LIBRARY, 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 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 + to carry out a patent search. Therefore I cannot give any + guarantee of the above statement. + + + +WHAT'S NEW IN 0.9.0 (as compared to 0.1pl2) ? + + * Approx 10% faster compression, 30% faster decompression + * -t (test mode) is a lot quicker + * Can decompress concatenated compressed files + * Programming interface, so programs can directly read/write .bz2 files + * Less restrictive (BSD-style) licensing + * Flag handling more compatible with GNU gzip + * Much more documentation, i.e., a proper user manual + * Hopefully, improved portability (at least of the library) + +WHAT'S NEW IN 0.9.5 ? + + * Compression speed is much less sensitive to the input + data than in previous versions. Specifically, the very + slow performance caused by repetitive data is fixed. + * Many small improvements in file and flag handling. + * A Y2K statement. + +WHAT'S NEW IN 1.0.0 ? + + See the CHANGES file. + +WHAT'S NEW IN 1.0.2 ? + + See the CHANGES file. + +WHAT'S NEW IN 1.0.3 ? + + See the CHANGES file. + +WHAT'S NEW IN 1.0.4 ? + + See the CHANGES file. + +WHAT'S NEW IN 1.0.5 ? + + See the CHANGES file. + +WHAT'S NEW IN 1.0.6 ? + + See the CHANGES file. + + +I hope you find bzip2 useful. Feel free to contact me at + jseward@bzip.org +if you have any suggestions or queries. Many people mailed me with +comments, suggestions and patches after the releases of bzip-0.15, +bzip-0.21, and bzip2 versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1, +1.0.2 and 1.0.3, and the changes in bzip2 are largely a result of this +feedback. I thank you for your comments. + +bzip2's "home" is http://www.bzip.org/ + +Julian Seward +jseward@bzip.org +Cambridge, UK. + +18 July 1996 (version 0.15) +25 August 1996 (version 0.21) + 7 August 1997 (bzip2, version 0.1) +29 August 1997 (bzip2, version 0.1pl2) +23 August 1998 (bzip2, version 0.9.0) + 8 June 1999 (bzip2, version 0.9.5) + 4 Sept 1999 (bzip2, version 0.9.5d) + 5 May 2000 (bzip2, version 1.0pre8) +30 December 2001 (bzip2, version 1.0.2pre1) +15 February 2005 (bzip2, version 1.0.3) +20 December 2006 (bzip2, version 1.0.4) +10 December 2007 (bzip2, version 1.0.5) + 6 Sept 2010 (bzip2, version 1.0.6) diff --git a/dep/bzip2/blocksort.c b/dep/bzip2/blocksort.c index bd2dec157fa..d0d662cd4e9 100644 --- a/dep/bzip2/blocksort.c +++ b/dep/bzip2/blocksort.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. diff --git a/dep/bzip2/bzip2.c b/dep/bzip2/bzip2.c new file mode 100644 index 00000000000..6de9d1d1488 --- /dev/null +++ b/dep/bzip2/bzip2.c @@ -0,0 +1,2034 @@ + +/*-----------------------------------------------------------*/ +/*--- A block-sorting, lossless compressor bzip2.c ---*/ +/*-----------------------------------------------------------*/ + +/* ------------------------------------------------------------------ + This file is part of bzip2/libbzip2, a program and library for + lossless, block-sorting data compression. + + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> + + Please read the WARNING, DISCLAIMER and PATENTS sections in the + README file. + + This program is released under the terms of the license contained + in the file LICENSE. + ------------------------------------------------------------------ */ + + +/* 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> +#include "bzlib.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 :-) +--*/ + +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) + +/*-- + 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 ( const 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 ); +static void applySavedFileAttrToOutputFile ( IntNative fd ); + + + +/*---------------------------------------------------*/ +/*--- 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 +Bool myfeof ( FILE* f ) +{ + Int32 c = fgetc ( f ); + if (c == EOF) return True; + ungetc ( c, f ); + return False; +} + + +/*---------------------------------------------*/ +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) { + Int32 fd = fileno ( zStream ); + if (fd < 0) goto errhandler_io; + applySavedFileAttrToOutputFile ( fd ); + 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; + void* unusedTmpV; + 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, &unusedTmpV, &nUnused ); + if (bzerr != BZ_OK) panic ( "decompress:bzReadGetUnused" ); + + unusedTmp = (UChar*)unusedTmpV; + 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; + if (stream != stdout) { + Int32 fd = fileno ( stream ); + if (fd < 0) goto errhandler_io; + applySavedFileAttrToOutputFile ( fd ); + } + 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; + void* unusedTmpV; + 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, &unusedTmpV, &nUnused ); + if (bzerr != BZ_OK) panic ( "test:bzReadGetUnused" ); + + unusedTmp = (UChar*)unusedTmpV; + 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 ( const 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@bzip.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@bzip.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@bzip.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. +*/ +static +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 applySavedTimeInfoToOutputFile ( Char *dstName ) +{ +# if BZ_UNIX + IntNative retVal; + struct utimbuf uTimBuf; + + uTimBuf.actime = fileMetaInfo.st_atime; + uTimBuf.modtime = fileMetaInfo.st_mtime; + + retVal = utime ( dstName, &uTimBuf ); + ERROR_IF_NOT_ZERO ( retVal ); +# endif +} + +static +void applySavedFileAttrToOutputFile ( IntNative fd ) +{ +# if BZ_UNIX + IntNative retVal; + + retVal = fchmod ( fd, fileMetaInfo.st_mode ); + ERROR_IF_NOT_ZERO ( retVal ); + + (void) fchown ( fd, 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 + +const Char* zSuffix[BZ_N_SUFFIX_PAIRS] + = { ".bz2", ".bz", ".tbz2", ".tbz" }; +const Char* unzSuffix[BZ_N_SUFFIX_PAIRS] + = { "", "", ".tar", ".tar" }; + +static +Bool hasSuffix ( Char* s, const 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, + const Char* oldSuffix, + const 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, (Char*)"(stdin)" ); + copyFileName ( outName, (Char*)"(stdout)" ); + break; + case SM_F2F: + copyFileName ( inName, name ); + copyFileName ( outName, name ); + strcat ( outName, ".bz2" ); + break; + case SM_F2O: + copyFileName ( inName, name ); + copyFileName ( outName, (Char*)"(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 ) { + applySavedTimeInfoToOutputFile ( 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, (Char*)"(stdin)" ); + copyFileName ( outName, (Char*)"(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, (Char*)"(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 ) { + applySavedTimeInfoToOutputFile ( 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, (Char*)"(none)" ); + switch (srcMode) { + case SM_I2O: copyFileName ( inName, (Char*)"(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) 1996-2010 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 bzip2-1.0.6 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, (Char*)"(none)" ); + copyFileName ( outName, (Char*)"(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, (Char*)"BZIP2" ); + addFlagsFromEnvVar ( &argList, (Char*)"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 ---*/ +/*-----------------------------------------------------------*/ diff --git a/dep/bzip2/bzip2recover.c b/dep/bzip2/bzip2recover.c new file mode 100644 index 00000000000..f9de0496abf --- /dev/null +++ b/dep/bzip2/bzip2recover.c @@ -0,0 +1,514 @@ +/*-----------------------------------------------------------*/ +/*--- Block recoverer program for bzip2 ---*/ +/*--- bzip2recover.c ---*/ +/*-----------------------------------------------------------*/ + +/* ------------------------------------------------------------------ + This file is part of bzip2/libbzip2, a program and library for + lossless, block-sorting data compression. + + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> + + Please read the WARNING, DISCLAIMER and PATENTS sections in the + README file. + + This program is released under the terms of the license contained + in the file LICENSE. + ------------------------------------------------------------------ */ + +/* This program is a complete hack and should be rewritten properly. + It isn't very complicated. */ + +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> + + +/* This program records bit locations in the file to be recovered. + That means that if 64-bit ints are not supported, we will not + be able to recover .bz2 files over 512MB (2^32 bits) long. + On GNU supported platforms, we take advantage of the 64-bit + int support to circumvent this problem. Ditto MSVC. + + This change occurred in version 1.0.2; all prior versions have + the 512MB limitation. +*/ +#ifdef __GNUC__ + typedef unsigned long long int MaybeUInt64; +# define MaybeUInt64_FMT "%Lu" +#else +#ifdef _MSC_VER + typedef unsigned __int64 MaybeUInt64; +# define MaybeUInt64_FMT "%I64u" +#else + typedef unsigned int MaybeUInt64; +# define MaybeUInt64_FMT "%u" +#endif +#endif + +typedef unsigned int UInt32; +typedef int Int32; +typedef unsigned char UChar; +typedef char Char; +typedef unsigned char Bool; +#define True ((Bool)1) +#define False ((Bool)0) + + +#define BZ_MAX_FILENAME 2000 + +Char inFileName[BZ_MAX_FILENAME]; +Char outFileName[BZ_MAX_FILENAME]; +Char progName[BZ_MAX_FILENAME]; + +MaybeUInt64 bytesOut = 0; +MaybeUInt64 bytesIn = 0; + + +/*---------------------------------------------------*/ +/*--- 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' */ + + +/*---------------------------------------------------*/ +/*--- I/O errors ---*/ +/*---------------------------------------------------*/ + +/*---------------------------------------------*/ +static void readError ( void ) +{ + fprintf ( stderr, + "%s: I/O error reading `%s', possible reason follows.\n", + progName, inFileName ); + perror ( progName ); + fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n", + progName ); + exit ( 1 ); +} + + +/*---------------------------------------------*/ +static void writeError ( void ) +{ + fprintf ( stderr, + "%s: I/O error reading `%s', possible reason follows.\n", + progName, inFileName ); + perror ( progName ); + fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n", + progName ); + exit ( 1 ); +} + + +/*---------------------------------------------*/ +static void mallocFail ( Int32 n ) +{ + fprintf ( stderr, + "%s: malloc failed on request for %d bytes.\n", + progName, n ); + fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n", + progName ); + exit ( 1 ); +} + + +/*---------------------------------------------*/ +static void tooManyBlocks ( Int32 max_handled_blocks ) +{ + fprintf ( stderr, + "%s: `%s' appears to contain more than %d blocks\n", + progName, inFileName, max_handled_blocks ); + fprintf ( stderr, + "%s: and cannot be handled. To fix, increase\n", + progName ); + fprintf ( stderr, + "%s: BZ_MAX_HANDLED_BLOCKS in bzip2recover.c, and recompile.\n", + progName ); + exit ( 1 ); +} + + + +/*---------------------------------------------------*/ +/*--- Bit stream I/O ---*/ +/*---------------------------------------------------*/ + +typedef + struct { + FILE* handle; + Int32 buffer; + Int32 buffLive; + Char mode; + } + BitStream; + + +/*---------------------------------------------*/ +static BitStream* bsOpenReadStream ( FILE* stream ) +{ + BitStream *bs = malloc ( sizeof(BitStream) ); + if (bs == NULL) mallocFail ( sizeof(BitStream) ); + bs->handle = stream; + bs->buffer = 0; + bs->buffLive = 0; + bs->mode = 'r'; + return bs; +} + + +/*---------------------------------------------*/ +static BitStream* bsOpenWriteStream ( FILE* stream ) +{ + BitStream *bs = malloc ( sizeof(BitStream) ); + if (bs == NULL) mallocFail ( sizeof(BitStream) ); + bs->handle = stream; + bs->buffer = 0; + bs->buffLive = 0; + bs->mode = 'w'; + return bs; +} + + +/*---------------------------------------------*/ +static void bsPutBit ( BitStream* bs, Int32 bit ) +{ + if (bs->buffLive == 8) { + Int32 retVal = putc ( (UChar) bs->buffer, bs->handle ); + if (retVal == EOF) writeError(); + bytesOut++; + bs->buffLive = 1; + bs->buffer = bit & 0x1; + } else { + bs->buffer = ( (bs->buffer << 1) | (bit & 0x1) ); + bs->buffLive++; + }; +} + + +/*---------------------------------------------*/ +/*-- + Returns 0 or 1, or 2 to indicate EOF. +--*/ +static Int32 bsGetBit ( BitStream* bs ) +{ + if (bs->buffLive > 0) { + bs->buffLive --; + return ( ((bs->buffer) >> (bs->buffLive)) & 0x1 ); + } else { + Int32 retVal = getc ( bs->handle ); + if ( retVal == EOF ) { + if (errno != 0) readError(); + return 2; + } + bs->buffLive = 7; + bs->buffer = retVal; + return ( ((bs->buffer) >> 7) & 0x1 ); + } +} + + +/*---------------------------------------------*/ +static void bsClose ( BitStream* bs ) +{ + Int32 retVal; + + if ( bs->mode == 'w' ) { + while ( bs->buffLive < 8 ) { + bs->buffLive++; + bs->buffer <<= 1; + }; + retVal = putc ( (UChar) (bs->buffer), bs->handle ); + if (retVal == EOF) writeError(); + bytesOut++; + retVal = fflush ( bs->handle ); + if (retVal == EOF) writeError(); + } + retVal = fclose ( bs->handle ); + if (retVal == EOF) { + if (bs->mode == 'w') writeError(); else readError(); + } + free ( bs ); +} + + +/*---------------------------------------------*/ +static void bsPutUChar ( BitStream* bs, UChar c ) +{ + Int32 i; + for (i = 7; i >= 0; i--) + bsPutBit ( bs, (((UInt32) c) >> i) & 0x1 ); +} + + +/*---------------------------------------------*/ +static void bsPutUInt32 ( BitStream* bs, UInt32 c ) +{ + Int32 i; + + for (i = 31; i >= 0; i--) + bsPutBit ( bs, (c >> i) & 0x1 ); +} + + +/*---------------------------------------------*/ +static Bool endsInBz2 ( Char* name ) +{ + Int32 n = strlen ( name ); + if (n <= 4) return False; + return + (name[n-4] == '.' && + name[n-3] == 'b' && + name[n-2] == 'z' && + name[n-1] == '2'); +} + + +/*---------------------------------------------------*/ +/*--- ---*/ +/*---------------------------------------------------*/ + +/* This logic isn't really right when it comes to Cygwin. */ +#ifdef _WIN32 +# define BZ_SPLIT_SYM '\\' /* path splitter on Windows platform */ +#else +# define BZ_SPLIT_SYM '/' /* path splitter on Unix platform */ +#endif + +#define BLOCK_HEADER_HI 0x00003141UL +#define BLOCK_HEADER_LO 0x59265359UL + +#define BLOCK_ENDMARK_HI 0x00001772UL +#define BLOCK_ENDMARK_LO 0x45385090UL + +/* Increase if necessary. However, a .bz2 file with > 50000 blocks + would have an uncompressed size of at least 40GB, so the chances + are low you'll need to up this. +*/ +#define BZ_MAX_HANDLED_BLOCKS 50000 + +MaybeUInt64 bStart [BZ_MAX_HANDLED_BLOCKS]; +MaybeUInt64 bEnd [BZ_MAX_HANDLED_BLOCKS]; +MaybeUInt64 rbStart[BZ_MAX_HANDLED_BLOCKS]; +MaybeUInt64 rbEnd [BZ_MAX_HANDLED_BLOCKS]; + +Int32 main ( Int32 argc, Char** argv ) +{ + FILE* inFile; + FILE* outFile; + BitStream* bsIn, *bsWr; + Int32 b, wrBlock, currBlock, rbCtr; + MaybeUInt64 bitsRead; + + UInt32 buffHi, buffLo, blockCRC; + Char* p; + + strcpy ( progName, argv[0] ); + inFileName[0] = outFileName[0] = 0; + + fprintf ( stderr, + "bzip2recover 1.0.6: extracts blocks from damaged .bz2 files.\n" ); + + if (argc != 2) { + fprintf ( stderr, "%s: usage is `%s damaged_file_name'.\n", + progName, progName ); + switch (sizeof(MaybeUInt64)) { + case 8: + fprintf(stderr, + "\trestrictions on size of recovered file: None\n"); + break; + case 4: + fprintf(stderr, + "\trestrictions on size of recovered file: 512 MB\n"); + fprintf(stderr, + "\tto circumvent, recompile with MaybeUInt64 as an\n" + "\tunsigned 64-bit int.\n"); + break; + default: + fprintf(stderr, + "\tsizeof(MaybeUInt64) is not 4 or 8 -- " + "configuration error.\n"); + break; + } + exit(1); + } + + if (strlen(argv[1]) >= BZ_MAX_FILENAME-20) { + fprintf ( stderr, + "%s: supplied filename is suspiciously (>= %d chars) long. Bye!\n", + progName, (int)strlen(argv[1]) ); + exit(1); + } + + strcpy ( inFileName, argv[1] ); + + inFile = fopen ( inFileName, "rb" ); + if (inFile == NULL) { + fprintf ( stderr, "%s: can't read `%s'\n", progName, inFileName ); + exit(1); + } + + bsIn = bsOpenReadStream ( inFile ); + fprintf ( stderr, "%s: searching for block boundaries ...\n", progName ); + + bitsRead = 0; + buffHi = buffLo = 0; + currBlock = 0; + bStart[currBlock] = 0; + + rbCtr = 0; + + while (True) { + b = bsGetBit ( bsIn ); + bitsRead++; + if (b == 2) { + if (bitsRead >= bStart[currBlock] && + (bitsRead - bStart[currBlock]) >= 40) { + bEnd[currBlock] = bitsRead-1; + if (currBlock > 0) + fprintf ( stderr, " block %d runs from " MaybeUInt64_FMT + " to " MaybeUInt64_FMT " (incomplete)\n", + currBlock, bStart[currBlock], bEnd[currBlock] ); + } else + currBlock--; + break; + } + buffHi = (buffHi << 1) | (buffLo >> 31); + buffLo = (buffLo << 1) | (b & 1); + if ( ( (buffHi & 0x0000ffff) == BLOCK_HEADER_HI + && buffLo == BLOCK_HEADER_LO) + || + ( (buffHi & 0x0000ffff) == BLOCK_ENDMARK_HI + && buffLo == BLOCK_ENDMARK_LO) + ) { + if (bitsRead > 49) { + bEnd[currBlock] = bitsRead-49; + } else { + bEnd[currBlock] = 0; + } + if (currBlock > 0 && + (bEnd[currBlock] - bStart[currBlock]) >= 130) { + fprintf ( stderr, " block %d runs from " MaybeUInt64_FMT + " to " MaybeUInt64_FMT "\n", + rbCtr+1, bStart[currBlock], bEnd[currBlock] ); + rbStart[rbCtr] = bStart[currBlock]; + rbEnd[rbCtr] = bEnd[currBlock]; + rbCtr++; + } + if (currBlock >= BZ_MAX_HANDLED_BLOCKS) + tooManyBlocks(BZ_MAX_HANDLED_BLOCKS); + currBlock++; + + bStart[currBlock] = bitsRead; + } + } + + bsClose ( bsIn ); + + /*-- identified blocks run from 1 to rbCtr inclusive. --*/ + + if (rbCtr < 1) { + fprintf ( stderr, + "%s: sorry, I couldn't find any block boundaries.\n", + progName ); + exit(1); + }; + + fprintf ( stderr, "%s: splitting into blocks\n", progName ); + + inFile = fopen ( inFileName, "rb" ); + if (inFile == NULL) { + fprintf ( stderr, "%s: can't open `%s'\n", progName, inFileName ); + exit(1); + } + bsIn = bsOpenReadStream ( inFile ); + + /*-- placate gcc's dataflow analyser --*/ + blockCRC = 0; bsWr = 0; + + bitsRead = 0; + outFile = NULL; + wrBlock = 0; + while (True) { + b = bsGetBit(bsIn); + if (b == 2) break; + buffHi = (buffHi << 1) | (buffLo >> 31); + buffLo = (buffLo << 1) | (b & 1); + if (bitsRead == 47+rbStart[wrBlock]) + blockCRC = (buffHi << 16) | (buffLo >> 16); + + if (outFile != NULL && bitsRead >= rbStart[wrBlock] + && bitsRead <= rbEnd[wrBlock]) { + bsPutBit ( bsWr, b ); + } + + bitsRead++; + + if (bitsRead == rbEnd[wrBlock]+1) { + if (outFile != NULL) { + bsPutUChar ( bsWr, 0x17 ); bsPutUChar ( bsWr, 0x72 ); + bsPutUChar ( bsWr, 0x45 ); bsPutUChar ( bsWr, 0x38 ); + bsPutUChar ( bsWr, 0x50 ); bsPutUChar ( bsWr, 0x90 ); + bsPutUInt32 ( bsWr, blockCRC ); + bsClose ( bsWr ); + } + if (wrBlock >= rbCtr) break; + wrBlock++; + } else + if (bitsRead == rbStart[wrBlock]) { + /* Create the output file name, correctly handling leading paths. + (31.10.2001 by Sergey E. Kusikov) */ + Char* split; + Int32 ofs, k; + for (k = 0; k < BZ_MAX_FILENAME; k++) + outFileName[k] = 0; + strcpy (outFileName, inFileName); + split = strrchr (outFileName, BZ_SPLIT_SYM); + if (split == NULL) { + split = outFileName; + } else { + ++split; + } + /* Now split points to the start of the basename. */ + ofs = split - outFileName; + sprintf (split, "rec%5d", wrBlock+1); + for (p = split; *p != 0; p++) if (*p == ' ') *p = '0'; + strcat (outFileName, inFileName + ofs); + + if ( !endsInBz2(outFileName)) strcat ( outFileName, ".bz2" ); + + fprintf ( stderr, " writing block %d to `%s' ...\n", + wrBlock+1, outFileName ); + + outFile = fopen ( outFileName, "wb" ); + if (outFile == NULL) { + fprintf ( stderr, "%s: can't write `%s'\n", + progName, outFileName ); + exit(1); + } + bsWr = bsOpenWriteStream ( outFile ); + bsPutUChar ( bsWr, BZ_HDR_B ); + bsPutUChar ( bsWr, BZ_HDR_Z ); + bsPutUChar ( bsWr, BZ_HDR_h ); + bsPutUChar ( bsWr, BZ_HDR_0 + 9 ); + bsPutUChar ( bsWr, 0x31 ); bsPutUChar ( bsWr, 0x41 ); + bsPutUChar ( bsWr, 0x59 ); bsPutUChar ( bsWr, 0x26 ); + bsPutUChar ( bsWr, 0x53 ); bsPutUChar ( bsWr, 0x59 ); + } + } + + fprintf ( stderr, "%s: finished\n", progName ); + return 0; +} + + + +/*-----------------------------------------------------------*/ +/*--- end bzip2recover.c ---*/ +/*-----------------------------------------------------------*/ diff --git a/dep/bzip2/bzlib.c b/dep/bzip2/bzlib.c index ef86c91e695..bd358a793b8 100644 --- a/dep/bzip2/bzlib.c +++ b/dep/bzip2/bzlib.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. diff --git a/dep/bzip2/bzlib.h b/dep/bzip2/bzlib.h index c5b75d6d8ff..8277123da8c 100644 --- a/dep/bzip2/bzlib.h +++ b/dep/bzip2/bzlib.h @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. diff --git a/dep/bzip2/bzlib_private.h b/dep/bzip2/bzlib_private.h index 23427879b18..5d0217f4635 100644 --- a/dep/bzip2/bzlib_private.h +++ b/dep/bzip2/bzlib_private.h @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. @@ -36,7 +36,7 @@ /*-- General stuff. --*/ -#define BZ_VERSION "1.0.5, 10-Dec-2007" +#define BZ_VERSION "1.0.6, 6-Sept-2010" typedef char Char; typedef unsigned char Bool; diff --git a/dep/bzip2/compress.c b/dep/bzip2/compress.c index 8c80a079700..caf7696011b 100644 --- a/dep/bzip2/compress.c +++ b/dep/bzip2/compress.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. diff --git a/dep/bzip2/crctable.c b/dep/bzip2/crctable.c index 215687b2c05..1fea7e946c5 100644 --- a/dep/bzip2/crctable.c +++ b/dep/bzip2/crctable.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. diff --git a/dep/bzip2/decompress.c b/dep/bzip2/decompress.c index bba5e0fa36d..311f5668f9a 100644 --- a/dep/bzip2/decompress.c +++ b/dep/bzip2/decompress.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. @@ -381,6 +381,13 @@ Int32 BZ2_decompress ( DState* s ) es = -1; N = 1; do { + /* Check that N doesn't get too big, so that es doesn't + go negative. The maximum value that can be + RUNA/RUNB encoded is equal to the block size (post + the initial RLE), viz, 900k, so bounding N at 2 + million should guard against overflow without + rejecting any legitimate inputs. */ + if (N >= 2*1024*1024) RETURN(BZ_DATA_ERROR); if (nextSym == BZ_RUNA) es = es + (0+1) * N; else if (nextSym == BZ_RUNB) es = es + (1+1) * N; N = N * 2; @@ -485,15 +492,28 @@ Int32 BZ2_decompress ( DState* s ) RETURN(BZ_DATA_ERROR); /*-- Set up cftab to facilitate generation of T^(-1) --*/ + /* Check: unzftab entries in range. */ + for (i = 0; i <= 255; i++) { + if (s->unzftab[i] < 0 || s->unzftab[i] > nblock) + RETURN(BZ_DATA_ERROR); + } + /* Actually generate cftab. */ 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]; + /* Check: cftab entries in range. */ for (i = 0; i <= 256; i++) { if (s->cftab[i] < 0 || s->cftab[i] > nblock) { /* s->cftab[i] can legitimately be == nblock */ RETURN(BZ_DATA_ERROR); } } + /* Check: cftab entries non-descending. */ + for (i = 1; i <= 256; i++) { + if (s->cftab[i-1] > s->cftab[i]) { + RETURN(BZ_DATA_ERROR); + } + } s->state_out_len = 0; s->state_out_ch = 0; diff --git a/dep/bzip2/huffman.c b/dep/bzip2/huffman.c index 87e79e38af0..2283fdbc5a1 100644 --- a/dep/bzip2/huffman.c +++ b/dep/bzip2/huffman.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. diff --git a/dep/bzip2/randtable.c b/dep/bzip2/randtable.c index 068b76367bc..6d624599061 100644 --- a/dep/bzip2/randtable.c +++ b/dep/bzip2/randtable.c @@ -8,8 +8,8 @@ This file is part of bzip2/libbzip2, a program and library for lossless, block-sorting data compression. - bzip2/libbzip2 version 1.0.5 of 10 December 2007 - Copyright (C) 1996-2007 Julian Seward <jseward@bzip.org> + bzip2/libbzip2 version 1.0.6 of 6 September 2010 + Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org> Please read the WARNING, DISCLAIMER and PATENTS sections in the README file. |