2025-02-23 19:13:52 +01:00
|
|
|
/* Pdlzip - Data compressor based on the LZMA algorithm
|
2025-02-23 19:07:50 +01:00
|
|
|
2009-08-14 : Igor Pavlov : Public domain
|
2025-02-23 19:13:52 +01:00
|
|
|
Copyright (C) 2010, 2011 Antonio Diaz Diaz.
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
This program is free software: you have unlimited permission
|
|
|
|
to copy, distribute and modify it.
|
|
|
|
|
|
|
|
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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define _FILE_OFFSET_BITS 64
|
|
|
|
|
|
|
|
#include <errno.h>
|
|
|
|
#include <limits.h>
|
|
|
|
#include <signal.h>
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
|
|
|
|
|
|
|
#include "carg_parser.h"
|
|
|
|
#include "pdlzip.h"
|
|
|
|
#include "Alloc.h"
|
|
|
|
#include "7zFile.h"
|
|
|
|
#include "LzmaDec.h"
|
|
|
|
#include "LzmaEnc.h"
|
|
|
|
|
2025-02-23 19:09:32 +01:00
|
|
|
#if CHAR_BIT != 8
|
|
|
|
#error "Environments where CHAR_BIT != 8 are not supported."
|
|
|
|
#endif
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
#ifndef LLONG_MAX
|
|
|
|
#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL
|
|
|
|
#endif
|
|
|
|
#ifndef LLONG_MIN
|
|
|
|
#define LLONG_MIN (-LLONG_MAX - 1LL)
|
|
|
|
#endif
|
|
|
|
#ifndef ULLONG_MAX
|
|
|
|
#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL
|
|
|
|
#endif
|
|
|
|
|
|
|
|
long long int llabs( long long int number );
|
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
static void *SzAlloc(void *p, size_t size) { p = p; return MyAlloc(size); }
|
|
|
|
static void SzFree(void *p, void *address) { p = p; MyFree(address); }
|
|
|
|
static ISzAlloc g_Alloc = { SzAlloc, SzFree };
|
|
|
|
|
2025-02-23 19:13:52 +01:00
|
|
|
const char * const Program_name = "Pdlzip";
|
|
|
|
const char * const program_name = "pdlzip";
|
|
|
|
const char * const program_year = "2011";
|
2025-02-23 19:07:50 +01:00
|
|
|
const char * invocation_name = 0;
|
|
|
|
|
|
|
|
|
|
|
|
struct { const char * from; const char * to; } const known_extensions[] = {
|
2025-02-23 19:12:27 +01:00
|
|
|
{ ".lz", "" },
|
|
|
|
{ ".tlz", ".tar" },
|
|
|
|
{ ".lzma", "" },
|
|
|
|
{ 0, 0 } };
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
struct Lzma_options
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
int dictionary_size; /* 4KiB..512MiB */
|
|
|
|
int match_len_limit; /* 5..273 */
|
2025-02-23 19:07:50 +01:00
|
|
|
};
|
|
|
|
|
2025-02-23 19:13:52 +01:00
|
|
|
enum Mode { m_compress, m_decompress, m_test };
|
2025-02-23 19:07:50 +01:00
|
|
|
char * output_filename = 0;
|
|
|
|
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
/* assure at least a minimum size for buffer `buf' */
|
2025-02-23 19:07:50 +01:00
|
|
|
inline void * resize_buffer( void * buf, const int min_size )
|
|
|
|
{
|
|
|
|
if( buf ) buf = realloc( buf, min_size );
|
|
|
|
else buf = malloc( min_size );
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void show_help()
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
printf( "%s - A \"public domain\" version of the lzip data compressor\n", Program_name );
|
2025-02-23 19:13:52 +01:00
|
|
|
printf( "also able to decompress legacy lzma-alone (.lzma) files.\n" );
|
2025-02-23 19:07:50 +01:00
|
|
|
printf( "\nUsage: %s [options] [file]\n", invocation_name );
|
|
|
|
printf( "\nOptions:\n" );
|
|
|
|
printf( " -h, --help display this help and exit\n" );
|
|
|
|
printf( " -V, --version output version information and exit\n" );
|
|
|
|
printf( " -c, --stdout send output to standard output\n" );
|
|
|
|
printf( " -d, --decompress decompress\n" );
|
2025-02-23 19:12:27 +01:00
|
|
|
/* printf( " -f, --force overwrite existing output files\n" ); */
|
|
|
|
/* printf( " -k, --keep keep (don't delete) input files\n" ); */
|
|
|
|
printf( " -m, --match-length=<n> set match length limit in bytes [36]\n" );
|
2025-02-23 19:07:50 +01:00
|
|
|
printf( " -q, --quiet suppress all messages\n" );
|
|
|
|
printf( " -s, --dictionary-size=<n> set dictionary size limit in bytes [8MiB]\n" );
|
|
|
|
printf( " -t, --test test compressed file integrity\n" );
|
|
|
|
printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" );
|
|
|
|
printf( " -1 .. -9 set compression level [default 6]\n" );
|
|
|
|
printf( " --fast alias for -1\n" );
|
|
|
|
printf( " --best alias for -9\n" );
|
|
|
|
printf( "If no file name is given, %s compresses or decompresses\n", program_name );
|
|
|
|
printf( "from standard input to standard output.\n" );
|
|
|
|
printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" );
|
|
|
|
printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" );
|
|
|
|
printf( "\nReport bugs to lzip-bug@nongnu.org\n" );
|
2025-02-23 19:13:52 +01:00
|
|
|
printf( "Pdlzip home page: http://www.nongnu.org/lzip/pdlzip.html\n" );
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void show_version()
|
|
|
|
{
|
|
|
|
printf( "%s %s\n", Program_name, PROGVERSION );
|
|
|
|
printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year );
|
2025-02-23 19:11:26 +01:00
|
|
|
printf( "Public Domain 2009 Igor Pavlov.\n" );
|
2025-02-23 19:07:50 +01:00
|
|
|
printf( "This is free software: you are free to change and redistribute it.\n" );
|
|
|
|
printf( "There is NO WARRANTY, to the extent permitted by law.\n" );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:13:52 +01:00
|
|
|
static const char * format_num( long long num )
|
2025-02-23 19:12:27 +01:00
|
|
|
{
|
2025-02-23 19:13:52 +01:00
|
|
|
const char * const prefix[8] =
|
2025-02-23 19:12:27 +01:00
|
|
|
{ "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" };
|
2025-02-23 19:13:52 +01:00
|
|
|
enum { buf_size = 16, factor = 1024 };
|
|
|
|
static char buf[buf_size];
|
2025-02-23 19:12:27 +01:00
|
|
|
const char *p = "";
|
|
|
|
int i;
|
|
|
|
|
2025-02-23 19:13:52 +01:00
|
|
|
for( i = 0; i < 8 && ( llabs( num ) > 9999 ||
|
2025-02-23 19:12:27 +01:00
|
|
|
( llabs( num ) >= factor && num % factor == 0 ) ); ++i )
|
|
|
|
{ num /= factor; p = prefix[i]; }
|
2025-02-23 19:13:52 +01:00
|
|
|
snprintf( buf, buf_size, "%lld %s", num, p );
|
2025-02-23 19:12:27 +01:00
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:13:52 +01:00
|
|
|
static long long getnum( const char * const ptr,
|
2025-02-23 19:07:50 +01:00
|
|
|
const long long llimit, const long long ulimit )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
long long result;
|
2025-02-23 19:07:50 +01:00
|
|
|
char *tail;
|
2025-02-23 19:12:27 +01:00
|
|
|
|
|
|
|
errno = 0;
|
|
|
|
result = strtoll( ptr, &tail, 0 );
|
2025-02-23 19:07:50 +01:00
|
|
|
if( tail == ptr )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
show_error( "Bad or missing numerical argument.", 0, true );
|
2025-02-23 19:07:50 +01:00
|
|
|
exit( 1 );
|
|
|
|
}
|
|
|
|
|
|
|
|
if( !errno && tail[0] )
|
|
|
|
{
|
|
|
|
int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
|
2025-02-23 19:12:27 +01:00
|
|
|
int exponent = 0, i;
|
2025-02-23 19:07:50 +01:00
|
|
|
bool bad_multiplier = false;
|
|
|
|
switch( tail[0] )
|
|
|
|
{
|
|
|
|
case ' ': break;
|
|
|
|
case 'Y': exponent = 8; break;
|
|
|
|
case 'Z': exponent = 7; break;
|
|
|
|
case 'E': exponent = 6; break;
|
|
|
|
case 'P': exponent = 5; break;
|
|
|
|
case 'T': exponent = 4; break;
|
|
|
|
case 'G': exponent = 3; break;
|
|
|
|
case 'M': exponent = 2; break;
|
|
|
|
case 'K': if( factor == 1024 ) exponent = 1; else bad_multiplier = true;
|
|
|
|
break;
|
|
|
|
case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true;
|
|
|
|
break;
|
|
|
|
default : bad_multiplier = true;
|
|
|
|
}
|
|
|
|
if( bad_multiplier )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
show_error( "Bad multiplier in numerical argument.", 0, true );
|
2025-02-23 19:07:50 +01:00
|
|
|
exit( 1 );
|
|
|
|
}
|
2025-02-23 19:12:27 +01:00
|
|
|
for( i = 0; i < exponent; ++i )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
|
|
|
if( LLONG_MAX / factor >= llabs( result ) ) result *= factor;
|
|
|
|
else { errno = ERANGE; break; }
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
|
|
|
|
if( errno )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
show_error( "Numerical argument out of limits.", 0, false );
|
2025-02-23 19:07:50 +01:00
|
|
|
exit( 1 );
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int get_dict_size( const char * const arg )
|
|
|
|
{
|
|
|
|
char *tail;
|
|
|
|
int bits = strtol( arg, &tail, 0 );
|
|
|
|
if( bits >= min_dictionary_bits &&
|
|
|
|
bits <= max_dictionary_bits && *tail == 0 )
|
|
|
|
return ( 1 << bits );
|
2025-02-23 19:13:52 +01:00
|
|
|
return getnum( arg, min_dictionary_size, max_dictionary_size );
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void show_name( const char * const name )
|
|
|
|
{
|
|
|
|
if( verbosity >= 1 )
|
|
|
|
fprintf( stderr, " %s: ", ( name && name[0] ) ? name : "(stdin)" );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
#define IN_BUF_SIZE (1 << 16)
|
|
|
|
#define OUT_BUF_SIZE (1 << 16)
|
|
|
|
|
|
|
|
static bool read_inbuf( ISeqInStream * const inStream, Byte inBuf[],
|
|
|
|
size_t * const inPos, size_t * const inSize )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
size_t rest;
|
2025-02-23 19:07:50 +01:00
|
|
|
if( *inPos >= *inSize ) *inSize = 0;
|
|
|
|
else if( *inPos > 0 )
|
|
|
|
{
|
|
|
|
memmove( inBuf, inBuf + *inPos, *inSize - *inPos );
|
|
|
|
*inSize -= *inPos;
|
|
|
|
}
|
|
|
|
*inPos = 0;
|
2025-02-23 19:12:27 +01:00
|
|
|
rest = IN_BUF_SIZE - *inSize;
|
2025-02-23 19:07:50 +01:00
|
|
|
if( rest > 0 )
|
|
|
|
{
|
|
|
|
if( inStream->Read( inStream, inBuf + *inSize, &rest ) != 0 )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Read error", errno, false ); return false; }
|
2025-02-23 19:07:50 +01:00
|
|
|
*inSize += rest;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
|
|
|
|
static int lzma_Decode2( UInt64 unpackSize, CLzmaDec *state,
|
|
|
|
ISeqOutStream *outStream, ISeqInStream *inStream,
|
|
|
|
Byte inBuf[], size_t * const inPos,
|
|
|
|
size_t * const inSize, const bool testing )
|
|
|
|
{
|
|
|
|
long long total_in = 13, total_out = 0;
|
|
|
|
Byte outBuf[OUT_BUF_SIZE];
|
|
|
|
size_t outPos = 0;
|
|
|
|
const bool thereIsSize = (unpackSize != (UInt64)(Int64)-1);
|
|
|
|
LzmaDec_Init(state);
|
|
|
|
|
|
|
|
for (;;)
|
|
|
|
{
|
|
|
|
SizeT inProcessed;
|
|
|
|
SizeT outProcessed = OUT_BUF_SIZE - outPos;
|
|
|
|
ELzmaFinishMode finishMode = LZMA_FINISH_ANY;
|
|
|
|
ELzmaStatus status;
|
|
|
|
|
|
|
|
if( *inPos == *inSize && !read_inbuf( inStream, inBuf, inPos, inSize ) )
|
|
|
|
return 1;
|
|
|
|
inProcessed = *inSize - *inPos;
|
|
|
|
if (thereIsSize && outProcessed > unpackSize)
|
|
|
|
{
|
|
|
|
outProcessed = (SizeT)unpackSize;
|
|
|
|
finishMode = LZMA_FINISH_END;
|
|
|
|
}
|
|
|
|
|
|
|
|
if( LzmaDec_DecodeToBuf( state, outBuf + outPos, &outProcessed,
|
|
|
|
inBuf + *inPos, &inProcessed, finishMode, &status ) != 0 )
|
|
|
|
{ show_error( "Data error.", 0, false ); return 1; }
|
|
|
|
*inPos += inProcessed;
|
|
|
|
total_in += inProcessed;
|
|
|
|
outPos += outProcessed;
|
|
|
|
unpackSize -= outProcessed;
|
|
|
|
|
|
|
|
if (outStream)
|
|
|
|
if (outStream->Write(outStream, outBuf, outPos) != outPos)
|
|
|
|
{ show_error( "Can not write output file", errno, false ); return 1; }
|
|
|
|
|
|
|
|
total_out += outPos;
|
|
|
|
outPos = 0;
|
|
|
|
|
|
|
|
if( ( inProcessed == 0 && outProcessed == 0 ) ||
|
|
|
|
( thereIsSize && unpackSize == 0 ) )
|
|
|
|
{
|
|
|
|
if( ( thereIsSize && unpackSize != 0 ) ||
|
|
|
|
( !thereIsSize && status != LZMA_STATUS_FINISHED_WITH_MARK ) )
|
|
|
|
{ show_error( "Data error.", 0, false ); return 1; }
|
|
|
|
if( verbosity >= 2 )
|
|
|
|
fprintf( stderr, "lzma-alone, dictionary size %7sB. ",
|
2025-02-23 19:13:52 +01:00
|
|
|
format_num( state->prop.dicSize ) );
|
2025-02-23 19:12:27 +01:00
|
|
|
if( verbosity >= 3 )
|
|
|
|
fprintf( stderr, "uncompressed size %9lld, compressed size %8lld. ",
|
|
|
|
total_out, total_in );
|
|
|
|
if( verbosity >= 1 )
|
|
|
|
{ if( testing ) fprintf( stderr, "(apparently) ok\n" );
|
|
|
|
else fprintf( stderr, "(apparently) done\n" ); }
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
static int Decode2( CLzmaDec *state, ISeqOutStream *outStream,
|
|
|
|
ISeqInStream *inStream, Byte inBuf[], size_t * const inPos,
|
2025-02-23 19:11:26 +01:00
|
|
|
size_t * const inSize, const int member_version,
|
|
|
|
const bool testing )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
2025-02-23 19:09:32 +01:00
|
|
|
long long total_in = Fh_size, total_out = 0;
|
2025-02-23 19:07:50 +01:00
|
|
|
Byte outBuf[OUT_BUF_SIZE];
|
|
|
|
size_t outPos = 0;
|
2025-02-23 19:09:32 +01:00
|
|
|
uint32_t crc = 0xFFFFFFFFU;
|
2025-02-23 19:07:50 +01:00
|
|
|
LzmaDec_Init(state);
|
2025-02-23 19:12:27 +01:00
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
for (;;)
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
SizeT inProcessed;
|
|
|
|
SizeT outProcessed = OUT_BUF_SIZE - outPos;
|
|
|
|
ELzmaFinishMode finishMode = LZMA_FINISH_ANY;
|
|
|
|
ELzmaStatus status;
|
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
if( *inPos == *inSize && !read_inbuf( inStream, inBuf, inPos, inSize ) )
|
|
|
|
return 1;
|
|
|
|
if( *inPos == *inSize )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Unexpected EOF.", 0, false ); return 1; }
|
|
|
|
inProcessed = *inSize - *inPos;
|
|
|
|
|
|
|
|
if( LzmaDec_DecodeToBuf( state, outBuf + outPos, &outProcessed,
|
|
|
|
inBuf + *inPos, &inProcessed, finishMode, &status ) != 0 )
|
|
|
|
{ show_error( "Data error.", 0, false ); return 1; }
|
|
|
|
*inPos += inProcessed;
|
|
|
|
total_in += inProcessed;
|
|
|
|
outPos += outProcessed;
|
|
|
|
|
|
|
|
if (outStream)
|
|
|
|
if (outStream->Write(outStream, outBuf, outPos) != outPos)
|
|
|
|
{ show_error( "Can not write output file", errno, false ); return 1; }
|
|
|
|
|
|
|
|
CRC32_update_buf( &crc, outBuf, outPos );
|
|
|
|
total_out += outPos;
|
|
|
|
outPos = 0;
|
|
|
|
|
|
|
|
if (inProcessed == 0 && outProcessed == 0)
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
File_trailer trailer;
|
|
|
|
size_t i;
|
|
|
|
const size_t trailer_size = Ft_versioned_size( member_version );
|
|
|
|
bool error = false;
|
|
|
|
|
|
|
|
if( status != LZMA_STATUS_FINISHED_WITH_MARK )
|
|
|
|
{ show_error( "Data error.", 0, false ); return 1; }
|
|
|
|
if( *inSize - *inPos < trailer_size &&
|
|
|
|
!read_inbuf( inStream, inBuf, inPos, inSize ) ) return 1;
|
|
|
|
if( *inSize - *inPos < trailer_size )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "trailer truncated at trailer position %u;"
|
2025-02-23 19:13:52 +01:00
|
|
|
" some checks may fail.\n",
|
|
|
|
(unsigned int)(*inSize - *inPos) );
|
2025-02-23 19:12:27 +01:00
|
|
|
for( i = *inSize - *inPos; i < trailer_size; ++i )
|
|
|
|
inBuf[*inPos+i] = 0;
|
|
|
|
}
|
|
|
|
for( i = 0; i < trailer_size; ++i )
|
|
|
|
trailer[i] = inBuf[(*inPos)++];
|
|
|
|
total_in += trailer_size;
|
|
|
|
if( member_version == 0 ) Ft_set_member_size( trailer, total_in );
|
|
|
|
if( Ft_get_data_crc( trailer ) != ( crc ^ 0xFFFFFFFFU ) )
|
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "crc mismatch; trailer says %08X, data crc is %08X.\n",
|
2025-02-23 19:07:50 +01:00
|
|
|
(unsigned int)Ft_get_data_crc( trailer ),
|
2025-02-23 19:12:27 +01:00
|
|
|
(unsigned int)( crc ^ 0xFFFFFFFFU ) );
|
|
|
|
}
|
|
|
|
if( Ft_get_data_size( trailer ) != total_out )
|
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "data size mismatch; trailer says %lld, data size is %lld.\n",
|
|
|
|
Ft_get_data_size( trailer ), total_out );
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
2025-02-23 19:12:27 +01:00
|
|
|
if( Ft_get_member_size( trailer ) != total_in )
|
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "member size mismatch; trailer says %lld, member size is %lld.\n",
|
|
|
|
Ft_get_member_size( trailer ), total_in );
|
|
|
|
}
|
|
|
|
if( !error && verbosity >= 3 )
|
|
|
|
fprintf( stderr, "data crc %08X, data size %9lld, member size %8lld. ",
|
|
|
|
(unsigned int)Ft_get_data_crc( trailer ),
|
|
|
|
Ft_get_data_size( trailer ), Ft_get_member_size( trailer ) );
|
|
|
|
if( !error && verbosity >= 1 )
|
|
|
|
{ if( testing ) fprintf( stderr, "ok\n" );
|
|
|
|
else fprintf( stderr, "done\n" ); }
|
|
|
|
if( error ) return 2;
|
|
|
|
return 0;
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
static int Decode( ISeqOutStream *outStream, ISeqInStream *inStream,
|
|
|
|
const char * const name, const bool testing )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
UInt64 unpackSize = 0;
|
2025-02-23 19:07:50 +01:00
|
|
|
CLzmaDec state;
|
|
|
|
File_header header;
|
|
|
|
Byte inBuf[IN_BUF_SIZE];
|
|
|
|
size_t inPos = 0, inSize = 0;
|
|
|
|
int retval = 0;
|
2025-02-23 19:12:27 +01:00
|
|
|
bool lzma_mode = false;
|
|
|
|
bool first_member;
|
|
|
|
/* 5 bytes of LZMA properties and 8 bytes of uncompressed size */
|
|
|
|
unsigned char props[LZMA_PROPS_SIZE+8];
|
2025-02-23 19:07:50 +01:00
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
for( first_member = true; ; first_member = false )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
int i;
|
2025-02-23 19:09:32 +01:00
|
|
|
if( inSize < Fh_size &&
|
2025-02-23 19:07:50 +01:00
|
|
|
!read_inbuf( inStream, inBuf, &inPos, &inSize ) ) return 1;
|
2025-02-23 19:12:27 +01:00
|
|
|
if( inSize < Fh_size ) /* End Of File */
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
|
|
|
if( !first_member ) break;
|
2025-02-23 19:12:27 +01:00
|
|
|
show_error( "Error reading member header.", 0, false ); return 1;
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
2025-02-23 19:12:27 +01:00
|
|
|
for( i = 0; i < Fh_size; ++i )
|
|
|
|
props[i] = header[i] = inBuf[inPos++];
|
2025-02-23 19:07:50 +01:00
|
|
|
if( !Fh_verify_magic( header ) )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
if( !first_member ) break; /* trailing garbage */
|
|
|
|
if( inSize >= 13 - Fh_size ) /* try lzma-alone */
|
|
|
|
{
|
|
|
|
for( i = Fh_size; i < 13; ++i ) props[i] = inBuf[inPos++];
|
|
|
|
for( i = 0; i < 8; ++i )
|
|
|
|
unpackSize += (UInt64)props[LZMA_PROPS_SIZE+i] << (i * 8);
|
|
|
|
if( ( props[12] == 0 || props[12] == 0xFF ) && props[12] == props[11] )
|
|
|
|
lzma_mode = true;
|
|
|
|
}
|
|
|
|
if( !lzma_mode )
|
|
|
|
{
|
|
|
|
show_error( "Bad magic number (file not in lzip format).", 0, false );
|
|
|
|
return 2;
|
|
|
|
}
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
|
|
|
if( !first_member ) show_name( name );
|
2025-02-23 19:12:27 +01:00
|
|
|
if( !lzma_mode )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
int ds, i;
|
|
|
|
if( !Fh_verify_version( header ) )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "version %d member format not supported, newer %s needed.\n",
|
|
|
|
Fh_version( header ), program_name );
|
|
|
|
return 2;
|
|
|
|
}
|
|
|
|
if( Fh_get_dictionary_size( header ) < min_dictionary_size ||
|
|
|
|
Fh_get_dictionary_size( header ) > max_dictionary_size )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "invalid dictionary size in member header.\n" );
|
|
|
|
return 2;
|
|
|
|
}
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
if( verbosity >= 2 )
|
2025-02-23 19:12:27 +01:00
|
|
|
fprintf( stderr, "version %d, dictionary size %7sB. ",
|
|
|
|
Fh_version( header ),
|
2025-02-23 19:13:52 +01:00
|
|
|
format_num( Fh_get_dictionary_size( header ) ) );
|
2025-02-23 19:07:50 +01:00
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
props[0] = 93; /* (45 * 2) + (9 * 0) + 3 */
|
|
|
|
ds = Fh_get_dictionary_size( header );
|
|
|
|
for( i = 1; i <= 4; ++i ) { props[i] = ds & 0xFF; ds >>= 8; }
|
|
|
|
}
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
LzmaDec_Construct(&state);
|
|
|
|
if( LzmaDec_Allocate( &state, props, LZMA_PROPS_SIZE, &g_Alloc ) != 0 )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Can not allocate memory.", 0, false ); return 1; }
|
|
|
|
if( !lzma_mode )
|
|
|
|
retval = Decode2( &state, outStream, inStream, inBuf, &inPos,
|
|
|
|
&inSize, Fh_version( header ), testing );
|
|
|
|
else
|
|
|
|
retval = lzma_Decode2( unpackSize, &state, outStream, inStream,
|
|
|
|
inBuf, &inPos, &inSize, testing );
|
2025-02-23 19:07:50 +01:00
|
|
|
LzmaDec_Free(&state, &g_Alloc);
|
2025-02-23 19:12:27 +01:00
|
|
|
if( retval != 0 || lzma_mode ) break;
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
static int Encode( ISeqOutStream *outStream, ISeqInStream *inStream,
|
|
|
|
const struct Lzma_options * const encoder_options )
|
|
|
|
{
|
|
|
|
CLzmaEncProps props;
|
2025-02-23 19:12:27 +01:00
|
|
|
int retval = 0;
|
|
|
|
File_header header;
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
CLzmaEncHandle enc = LzmaEnc_Create(&g_Alloc);
|
|
|
|
if(enc == 0)
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Can not allocate memory.", 0, false ); return 1; }
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
LzmaEncProps_Init(&props);
|
|
|
|
props.dictSize = encoder_options->dictionary_size;
|
|
|
|
props.lc = literal_context_bits;
|
|
|
|
props.lp = 0;
|
|
|
|
props.pb = pos_state_bits;
|
|
|
|
props.fb = encoder_options->match_len_limit;
|
|
|
|
props.btMode = 1;
|
|
|
|
props.numHashBytes = 4;
|
|
|
|
props.mc = 16 + ( encoder_options->match_len_limit / 2 );
|
|
|
|
LzmaEnc_SetProps(enc, &props);
|
|
|
|
|
|
|
|
Fh_set_magic( header );
|
|
|
|
if( !Fh_set_dictionary_size( header, encoder_options->dictionary_size ) ||
|
|
|
|
encoder_options->match_len_limit < min_match_len_limit ||
|
|
|
|
encoder_options->match_len_limit > max_match_len )
|
|
|
|
internal_error( "invalid argument to encoder" );
|
|
|
|
|
2025-02-23 19:09:32 +01:00
|
|
|
if( outStream->Write( outStream, header, Fh_size ) != Fh_size )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Can not write output file", errno, false ); retval = 1; }
|
2025-02-23 19:07:50 +01:00
|
|
|
else
|
|
|
|
if( LzmaEnc_Encode(enc, outStream, inStream, NULL, &g_Alloc, &g_Alloc) != 0 )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Data error.", 0, false ); retval = 1; }
|
2025-02-23 19:07:50 +01:00
|
|
|
LzmaEnc_Destroy(enc, &g_Alloc, &g_Alloc);
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
int verbosity = 0;
|
|
|
|
|
|
|
|
|
|
|
|
void show_error( const char * const msg, const int errcode, const bool help )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
if( msg && msg[0] )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
|
|
|
fprintf( stderr, "%s: %s", program_name, msg );
|
|
|
|
if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) );
|
|
|
|
fprintf( stderr, "\n" );
|
|
|
|
}
|
2025-02-23 19:12:27 +01:00
|
|
|
if( help && invocation_name && invocation_name[0] )
|
2025-02-23 19:13:52 +01:00
|
|
|
fprintf( stderr, "Try `%s --help' for more information.\n",
|
|
|
|
invocation_name );
|
2025-02-23 19:07:50 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void internal_error( const char * const msg )
|
|
|
|
{
|
2025-02-23 19:13:52 +01:00
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "%s: internal error: %s.\n", program_name, msg );
|
2025-02-23 19:07:50 +01:00
|
|
|
exit( 3 );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int extension_index( const char * const name )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
int i;
|
|
|
|
for( i = 0; known_extensions[i].from; ++i )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
|
|
|
const char * const ext = known_extensions[i].from;
|
|
|
|
if( strlen( name ) > strlen( ext ) &&
|
|
|
|
strncmp( name + strlen( name ) - strlen( ext ), ext, strlen( ext ) ) == 0 )
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void set_c_outname( const char * const name )
|
|
|
|
{
|
|
|
|
output_filename = resize_buffer( output_filename, strlen( name ) +
|
|
|
|
strlen( known_extensions[0].from ) + 1 );
|
|
|
|
strcpy( output_filename, name );
|
|
|
|
strcat( output_filename, known_extensions[0].from );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void set_d_outname( const char * const name )
|
|
|
|
{
|
|
|
|
const int i = extension_index( name );
|
|
|
|
if( i >= 0 )
|
|
|
|
{
|
|
|
|
const char * const from = known_extensions[i].from;
|
|
|
|
if( strlen( name ) > strlen( from ) )
|
|
|
|
{
|
|
|
|
output_filename = resize_buffer( output_filename, strlen( name ) +
|
|
|
|
strlen( known_extensions[0].to ) + 1 );
|
|
|
|
strcpy( output_filename, name );
|
|
|
|
strcpy( output_filename + strlen( name ) - strlen( from ),
|
|
|
|
known_extensions[i].to );
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
output_filename = resize_buffer( output_filename, strlen( name ) + 4 + 1 );
|
|
|
|
strcpy( output_filename, name );
|
|
|
|
strcat( output_filename, ".out" );
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "%s: can't guess original name for `%s' -- using `%s'.\n",
|
|
|
|
program_name, name, output_filename );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
CRC32 crc32;
|
|
|
|
|
|
|
|
|
|
|
|
int main( const int argc, const char * const argv[] )
|
|
|
|
{
|
2025-02-23 19:12:27 +01:00
|
|
|
/* Mapping from gzip/bzip2 style 1..9 compression modes
|
|
|
|
to the corresponding LZMA compression modes. */
|
2025-02-23 19:07:50 +01:00
|
|
|
const struct Lzma_options option_mapping[] =
|
|
|
|
{
|
2025-02-23 19:13:52 +01:00
|
|
|
{ 1 << 20, 5 }, /* -0 */
|
2025-02-23 19:12:27 +01:00
|
|
|
{ 1 << 20, 5 }, /* -1 */
|
|
|
|
{ 3 << 19, 6 }, /* -2 */
|
|
|
|
{ 1 << 21, 8 }, /* -3 */
|
|
|
|
{ 3 << 20, 12 }, /* -4 */
|
|
|
|
{ 1 << 22, 20 }, /* -5 */
|
|
|
|
{ 1 << 23, 36 }, /* -6 */
|
|
|
|
{ 1 << 24, 68 }, /* -7 */
|
|
|
|
{ 3 << 23, 132 }, /* -8 */
|
|
|
|
{ 1 << 25, 273 } }; /* -9 */
|
|
|
|
struct Lzma_options encoder_options = option_mapping[6]; /* default = "-6" */
|
2025-02-23 19:07:50 +01:00
|
|
|
enum Mode program_mode = m_compress;
|
2025-02-23 19:12:27 +01:00
|
|
|
const char * input_filename = "";
|
|
|
|
CFileSeqInStream inStream;
|
|
|
|
CFileOutStream outStream;
|
|
|
|
int argind;
|
|
|
|
int retval;
|
2025-02-23 19:07:50 +01:00
|
|
|
bool force = false;
|
|
|
|
bool keep_input_files = false;
|
|
|
|
bool to_stdout = false;
|
|
|
|
|
|
|
|
const struct ap_Option options[] =
|
|
|
|
{
|
2025-02-23 19:09:32 +01:00
|
|
|
{ '0', 0, ap_no },
|
2025-02-23 19:07:50 +01:00
|
|
|
{ '1', "fast", ap_no },
|
|
|
|
{ '2', 0, ap_no },
|
|
|
|
{ '3', 0, ap_no },
|
|
|
|
{ '4', 0, ap_no },
|
|
|
|
{ '5', 0, ap_no },
|
|
|
|
{ '6', 0, ap_no },
|
|
|
|
{ '7', 0, ap_no },
|
|
|
|
{ '8', 0, ap_no },
|
|
|
|
{ '9', "best", ap_no },
|
|
|
|
{ 'b', "member-size", ap_yes },
|
|
|
|
{ 'c', "stdout", ap_no },
|
|
|
|
{ 'd', "decompress", ap_no },
|
2025-02-23 19:09:32 +01:00
|
|
|
{ 'e', "extreme", ap_no },
|
2025-02-23 19:07:50 +01:00
|
|
|
{ 'f', "force", ap_no },
|
|
|
|
{ 'h', "help", ap_no },
|
|
|
|
{ 'k', "keep", ap_no },
|
|
|
|
{ 'm', "match-length", ap_yes },
|
|
|
|
{ 'q', "quiet", ap_no },
|
|
|
|
{ 's', "dictionary-size", ap_yes },
|
|
|
|
{ 'S', "volume-size", ap_yes },
|
|
|
|
{ 't', "test", ap_no },
|
|
|
|
{ 'v', "verbose", ap_no },
|
|
|
|
{ 'V', "version", ap_no },
|
|
|
|
{ 0 , 0, ap_no } };
|
|
|
|
|
|
|
|
struct Arg_parser parser;
|
2025-02-23 19:12:27 +01:00
|
|
|
|
|
|
|
invocation_name = argv[0];
|
|
|
|
CRC32_init();
|
|
|
|
if (sizeof(UInt32) != 4 || sizeof(UInt64) != 8)
|
|
|
|
internal_error( "incorrect UInt32 or UInt64" );
|
|
|
|
|
2025-02-23 19:07:50 +01:00
|
|
|
if( !ap_init( &parser, argc, argv, options, 0 ) )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Memory exhausted.", 0, false ); return 1; }
|
|
|
|
if( ap_error( &parser ) ) /* bad option */
|
2025-02-23 19:07:50 +01:00
|
|
|
{ show_error( ap_error( &parser ), 0, true ); return 1; }
|
|
|
|
|
2025-02-23 19:12:27 +01:00
|
|
|
for( argind = 0; argind < ap_arguments( &parser ); ++argind )
|
2025-02-23 19:07:50 +01:00
|
|
|
{
|
|
|
|
const int code = ap_code( &parser, argind );
|
|
|
|
const char * const arg = ap_argument( &parser, argind );
|
2025-02-23 19:12:27 +01:00
|
|
|
if( !code ) break; /* no more options */
|
2025-02-23 19:07:50 +01:00
|
|
|
switch( code )
|
|
|
|
{
|
2025-02-23 19:09:32 +01:00
|
|
|
case '0': case '1': case '2': case '3': case '4':
|
|
|
|
case '5': case '6': case '7': case '8': case '9':
|
|
|
|
encoder_options = option_mapping[code-'0']; break;
|
2025-02-23 19:07:50 +01:00
|
|
|
case 'b': break;
|
|
|
|
case 'c': to_stdout = true; break;
|
|
|
|
case 'd': program_mode = m_decompress; break;
|
2025-02-23 19:09:32 +01:00
|
|
|
case 'e': break;
|
2025-02-23 19:07:50 +01:00
|
|
|
case 'f': force = true; break;
|
|
|
|
case 'h': show_help(); return 0;
|
|
|
|
case 'k': keep_input_files = true; break;
|
|
|
|
case 'm': encoder_options.match_len_limit =
|
2025-02-23 19:13:52 +01:00
|
|
|
getnum( arg, min_match_len_limit, max_match_len ); break;
|
2025-02-23 19:07:50 +01:00
|
|
|
case 'q': verbosity = -1; break;
|
|
|
|
case 's': encoder_options.dictionary_size = get_dict_size( arg );
|
|
|
|
break;
|
|
|
|
case 'S': break;
|
|
|
|
case 't': program_mode = m_test; break;
|
|
|
|
case 'v': if( verbosity < 4 ) ++verbosity; break;
|
|
|
|
case 'V': show_version(); return 0;
|
|
|
|
default : internal_error( "uncaught option" );
|
|
|
|
}
|
2025-02-23 19:13:52 +01:00
|
|
|
} /* end process options */
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
if( ap_arguments( &parser ) > argind &&
|
|
|
|
strcmp( ap_argument( &parser, argind ), "-" ) )
|
|
|
|
input_filename = ap_argument( &parser, argind );
|
|
|
|
if( ap_arguments( &parser ) > argind + 1 )
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Too many file names.", 0, true ); return 1; }
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
if( program_mode == m_test ) output_filename = "/dev/null";
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if( to_stdout || !input_filename[0] ) output_filename = "";
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if( program_mode == m_compress ) set_c_outname( input_filename );
|
|
|
|
else set_d_outname( input_filename );
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
FileSeqInStream_CreateVTable(&inStream);
|
|
|
|
File_Construct(&inStream.file);
|
|
|
|
|
|
|
|
FileOutStream_CreateVTable(&outStream);
|
|
|
|
File_Construct(&outStream.file);
|
|
|
|
|
|
|
|
if (InFile_Open(&inStream.file, input_filename) != 0)
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Can not open input file", errno, false ); return 1; }
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
if (OutFile_Open(&outStream.file, output_filename) != 0)
|
2025-02-23 19:12:27 +01:00
|
|
|
{ show_error( "Can not open output file", errno, false ); return 1; }
|
2025-02-23 19:07:50 +01:00
|
|
|
|
|
|
|
show_name( input_filename );
|
|
|
|
if( program_mode == m_compress )
|
|
|
|
retval = Encode( &outStream.s, &inStream.s, &encoder_options );
|
|
|
|
else
|
|
|
|
retval = Decode( &outStream.s, &inStream.s, input_filename, program_mode == m_test );
|
|
|
|
|
|
|
|
File_Close(&outStream.file);
|
|
|
|
File_Close(&inStream.file);
|
|
|
|
|
|
|
|
ap_free( &parser );
|
|
|
|
return retval;
|
|
|
|
}
|