1
0
Fork 0

Merging upstream version 0.3.

Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-20 14:26:47 +01:00
parent 4a29881d2b
commit 01cd6a6972
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
9 changed files with 193 additions and 186 deletions

View file

@ -1,3 +1,8 @@
2013-07-24 Antonio Diaz Diaz <antonio@gnu.org>
* Version 0.3 released.
* decoder.cc and main.cc have been merged into lzd.cc.
2013-05-06 Antonio Diaz Diaz <antonio@gnu.org>
* Version 0.2 released.

View file

@ -1,7 +1,7 @@
Requirements
------------
You will need a C++ compiler.
I use gcc 4.8.0 and 3.3.6, but the code should compile with any
I use gcc 4.8.1 and 3.3.6, but the code should compile with any
standards compliant compiler.
Gcc is available at http://gcc.gnu.org.
@ -10,9 +10,9 @@ Procedure
---------
1. Unpack the archive if you have not done so already:
lzip -cd lzd[version].tar.lz | tar -xf -
tar -xf lzd[version].tar.lz
or
gzip -cd lzd[version].tar.gz | tar -xf -
lzip -cd lzd[version].tar.lz | tar -xf -
This creates the directory ./lzd[version] containing the source from
the main archive.

View file

@ -6,7 +6,7 @@ INSTALL_DATA = $(INSTALL) -p -m 644
INSTALL_DIR = $(INSTALL) -d -m 755
SHELL = /bin/sh
objs = main.o
objs = lzd.o
.PHONY : all install install-bin install-info install-man install-strip \
@ -21,14 +21,10 @@ $(progname) : $(objs)
$(progname)_profiled : $(objs)
$(CXX) $(LDFLAGS) -pg -o $@ $(objs)
main.o : main.cc
%.o : %.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $<
%.o : %.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
$(objs) : Makefile
main.o : decoder.cc
$(objs) : Makefile
doc :

4
NEWS
View file

@ -1,3 +1,3 @@
Changes in version 0.2:
Changes in version 0.3:
Added a missing "#include" for OS/2.
All the code is now contained in a single file (lzd.cc).

2
README
View file

@ -1,6 +1,6 @@
Description
Lzd is a very simplified decompressor for lzip files with an educational
Lzd is a simplified decompressor for lzip files with an educational
purpose. Studying its source is a good first step to understand how lzip
works. It is not safe to use lzd for any real work.

46
configure vendored
View file

@ -5,12 +5,10 @@
# This configure script is free software: you have unlimited permission
# to copy, distribute and modify it.
args=
no_create=
pkgname=lzd
pkgversion=0.2
pkgversion=0.3
progname=lzd
srctrigger=decoder.cc
srctrigger=lzd.cc
# clear some things potentially inherited from environment.
LC_ALL=C
@ -28,18 +26,19 @@ CXXFLAGS='-Wall -W -O2'
LDFLAGS=
# checking whether we are using GNU C++.
if [ ! -x /bin/g++ ] &&
[ ! -x /usr/bin/g++ ] &&
[ ! -x /usr/local/bin/g++ ] ; then
${CXX} --version > /dev/null 2>&1
if [ $? != 0 ] ; then
CXX=c++
CXXFLAGS='-W -O2'
fi
# Loop over all args
while [ -n "$1" ] ; do
args=
no_create=
while [ $# != 0 ] ; do
# Get the first arg, and shuffle
option=$1
option=$1 ; arg2=no
shift
# Add the argument quoted to args
@ -74,6 +73,14 @@ while [ -n "$1" ] ; do
--version | -V)
echo "Configure script for ${pkgname} version ${pkgversion}"
exit 0 ;;
--srcdir) srcdir=$1 ; arg2=yes ;;
--prefix) prefix=$1 ; arg2=yes ;;
--exec-prefix) exec_prefix=$1 ; arg2=yes ;;
--bindir) bindir=$1 ; arg2=yes ;;
--datarootdir) datarootdir=$1 ; arg2=yes ;;
--infodir) infodir=$1 ; arg2=yes ;;
--mandir) mandir=$1 ; arg2=yes ;;
--srcdir=*) srcdir=${optarg} ;;
--prefix=*) prefix=${optarg} ;;
--exec-prefix=*) exec_prefix=${optarg} ;;
@ -88,11 +95,22 @@ while [ -n "$1" ] ; do
CXXFLAGS=*) CXXFLAGS=${optarg} ;;
LDFLAGS=*) LDFLAGS=${optarg} ;;
--* | *=* | *-*-*) ;;
--*)
echo "configure: WARNING: unrecognized option: '${option}'" 1>&2 ;;
*=* | *-*-*) ;;
*)
echo "configure: Unrecognized option: \"${option}\"; use --help for usage." 1>&2
echo "configure: unrecognized option: '${option}'" 1>&2
echo "Try 'configure --help' for more information." 1>&2
exit 1 ;;
esac
# Check if the option took a separate argument
if [ "${arg2}" = yes ] ; then
if [ $# != 0 ] ; then args="${args} \"$1\"" ; shift
else echo "configure: Missing argument to '${option}'" 1>&2
exit 1
fi
fi
done
# Find the source files, if location was not specified.
@ -107,10 +125,8 @@ if [ -z "${srcdir}" ] ; then
fi
if [ ! -r "${srcdir}/${srctrigger}" ] ; then
exec 1>&2
echo
echo "configure: Can't find sources in ${srcdir} ${srcdirtext}"
echo "configure: (At least ${srctrigger} is missing)."
echo "configure: Can't find sources in ${srcdir} ${srcdirtext}" 1>&2
echo "configure: (At least ${srctrigger} is missing)." 1>&2
exit 1
fi

View file

@ -8,6 +8,24 @@
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
*/
/*
Exit status: 0 for a normal exit, 1 for environmental problems
(file not found, invalid flags, I/O errors, etc), 2 to indicate a
corrupt or invalid input file.
*/
#include <algorithm>
#include <cerrno>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <stdint.h>
#include <unistd.h>
#if defined(__MSVCRT__) || defined(__OS2__)
#include <fcntl.h>
#include <io.h>
#endif
class State
{
@ -24,20 +42,20 @@ public:
static const int next[states] = { 0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5 };
st = next[st];
}
void set_match() { st = ( ( st < 7 ) ? 7 : 10 ); }
void set_rep() { st = ( ( st < 7 ) ? 8 : 11 ); }
void set_short_rep() { st = ( ( st < 7 ) ? 9 : 11 ); }
void set_match() { st = ( st < 7 ) ? 7 : 10; }
void set_rep() { st = ( st < 7 ) ? 8 : 11; }
void set_short_rep() { st = ( st < 7 ) ? 9 : 11; }
};
enum {
min_dictionary_size = 1 << 12,
max_dictionary_size = 1 << 29,
literal_context_bits = 3,
pos_state_bits = 2,
pos_states = 1 << pos_state_bits,
pos_state_mask = pos_states - 1,
max_dis_states = 4,
dis_slot_bits = 6,
start_dis_model = 4,
end_dis_model = 14,
@ -52,13 +70,14 @@ enum {
len_mid_symbols = 1 << len_mid_bits,
len_high_symbols = 1 << len_high_bits,
max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols,
min_match_len = 2, // must be 2
max_dis_states = 4,
bit_model_move_bits = 5,
bit_model_total_bits = 11,
bit_model_total = 1 << bit_model_total_bits };
struct Bit_model
{
int probability;
@ -75,6 +94,39 @@ struct Len_model
};
class CRC32
{
uint32_t data[256]; // Table of CRCs of all 8-bit messages.
public:
CRC32()
{
for( unsigned n = 0; n < 256; ++n )
{
unsigned c = n;
for( int k = 0; k < 8; ++k )
{ if( c & 1 ) c = 0xEDB88320U ^ ( c >> 1 ); else c >>= 1; }
data[n] = c;
}
}
void update( uint32_t & crc, const uint8_t * const buffer, const int size ) const
{
for( int i = 0; i < size; ++i )
crc = data[(crc^buffer[i])&0xFF] ^ ( crc >> 8 );
}
};
const CRC32 crc32;
typedef uint8_t File_header[6]; // 0-3 magic, 4 version, 5 coded_dict_size
typedef uint8_t File_trailer[20];
// 0-3 CRC32 of the uncompressed data
// 4-11 size of the uncompressed data
// 12-19 member size including header and trailer
class Range_decoder
{
uint32_t code;
@ -83,9 +135,11 @@ class Range_decoder
public:
Range_decoder() : code( 0 ), range( 0xFFFFFFFFU )
{
for( int i = 0; i < 5; ++i ) code = (code << 8) | std::getc( stdin );
for( int i = 0; i < 5; ++i ) code = (code << 8) | get_byte();
}
uint8_t get_byte() { return std::getc( stdin ); }
int decode( const int num_bits )
{
int symbol = 0;
@ -95,7 +149,7 @@ public:
symbol <<= 1;
if( code >= range ) { code -= range; symbol |= 1; }
if( range <= 0x00FFFFFFU ) // normalize
{ range <<= 8; code = (code << 8) | std::getc( stdin ); }
{ range <<= 8; code = (code << 8) | get_byte(); }
}
return symbol;
}
@ -118,7 +172,7 @@ public:
symbol = 1;
}
if( range <= 0x00FFFFFFU ) // normalize
{ range <<= 8; code = (code << 8) | std::getc( stdin ); }
{ range <<= 8; code = (code << 8) | get_byte(); }
return symbol;
}
@ -164,12 +218,11 @@ public:
int decode_len( Len_model & lm, const int pos_state )
{
if( decode_bit( lm.choice1 ) == 0 )
return min_match_len +
decode_tree( lm.bm_low[pos_state], len_low_bits );
return decode_tree( lm.bm_low[pos_state], len_low_bits );
if( decode_bit( lm.choice2 ) == 0 )
return min_match_len + len_low_symbols +
return len_low_symbols +
decode_tree( lm.bm_mid[pos_state], len_mid_bits );
return min_match_len + len_low_symbols + len_mid_symbols +
return len_low_symbols + len_mid_symbols +
decode_tree( lm.bm_high, len_high_bits );
}
};
@ -189,8 +242,8 @@ class LZ_decoder
uint8_t get_byte( const unsigned distance ) const
{
int i = pos - distance - 1;
if( i < 0 ) i += dictionary_size;
unsigned i = pos - distance - 1;
if( pos <= distance ) i += dictionary_size;
return buffer[i];
}
@ -220,32 +273,6 @@ public:
};
class CRC32
{
uint32_t data[256]; // Table of CRCs of all 8-bit messages.
public:
CRC32()
{
for( unsigned n = 0; n < 256; ++n )
{
unsigned c = n;
for( int k = 0; k < 8; ++k )
{ if( c & 1 ) c = 0xEDB88320U ^ ( c >> 1 ); else c >>= 1; }
data[n] = c;
}
}
void update( uint32_t & crc, const uint8_t * buffer, const int size ) const
{
for( int i = 0; i < size; ++i )
crc = data[(crc^buffer[i])&0xFF] ^ ( crc >> 8 );
}
};
const CRC32 crc32;
void LZ_decoder::flush_data()
{
if( pos > stream_pos )
@ -322,13 +349,13 @@ bool LZ_decoder::decode_member() // Returns false if error
rep1 = rep0;
rep0 = distance;
}
len = rdec.decode_len( rep_len_model, pos_state );
len = min_match_len + rdec.decode_len( rep_len_model, pos_state );
state.set_rep();
}
else
{
rep3 = rep2; rep2 = rep1; rep1 = rep0;
len = rdec.decode_len( match_len_model, pos_state );
len = min_match_len + rdec.decode_len( match_len_model, pos_state );
const int dis_state = std::min( len - min_match_len, max_dis_states - 1 );
const int dis_slot =
rdec.decode_tree( bm_dis_slot[dis_state], dis_slot_bits );
@ -361,3 +388,72 @@ bool LZ_decoder::decode_member() // Returns false if error
}
return false;
}
int main( const int argc, const char * const argv[] )
{
if( argc > 1 )
{
std::printf( "Lzd %s - Educational decompressor for lzip files.\n",
PROGVERSION );
std::printf( "Study the source to learn how a lzip decompressor works.\n"
"See the lzip manual for an explanation of the code.\n"
"It is not safe to use lzd for any real work.\n"
"\nUsage: %s < file.lz > file\n", argv[0] );
std::printf( "Lzd decompresses from standard input to standard output.\n"
"\nCopyright (C) 2013 Antonio Diaz Diaz.\n"
"This is free software: you are free to change and redistribute it.\n"
"There is NO WARRANTY, to the extent permitted by law.\n"
"Report bugs to lzip-bug@nongnu.org\n"
"Lzip home page: http://www.nongnu.org/lzip/lzip.html\n" );
return 0;
}
#if defined(__MSVCRT__) || defined(__OS2__)
setmode( STDIN_FILENO, O_BINARY );
setmode( STDOUT_FILENO, O_BINARY );
#endif
for( bool first_member = true; ; first_member = false )
{
File_header header;
for( int i = 0; i < 6; ++i )
header[i] = std::getc( stdin );
if( std::feof( stdin ) || std::memcmp( header, "LZIP", 4 ) != 0 )
{
if( first_member )
{ std::fprintf( stderr, "Bad magic number (file not in lzip format)\n" );
return 2; }
break;
}
if( header[4] != 1 )
{
std::fprintf( stderr, "Version %d member format not supported.\n",
header[4] );
return 2;
}
unsigned dict_size = 1 << ( header[5] & 0x1F );
dict_size -= ( dict_size / 16 ) * ( ( header[5] >> 5 ) & 7 );
if( dict_size < min_dictionary_size || dict_size > max_dictionary_size )
{ std::fprintf( stderr, "Invalid dictionary size in member header\n" );
return 2; }
LZ_decoder decoder( dict_size );
if( !decoder.decode_member() )
{ std::fprintf( stderr, "Data error\n" ); return 2; }
File_trailer trailer;
for( int i = 0; i < 20; ++i ) trailer[i] = std::getc( stdin );
unsigned crc = 0;
for( int i = 3; i >= 0; --i ) { crc <<= 8; crc += trailer[i]; }
unsigned long long data_size = 0;
for( int i = 11; i >= 4; --i ) { data_size <<= 8; data_size += trailer[i]; }
if( crc != decoder.crc() || data_size != decoder.data_position() )
{ std::fprintf( stderr, "CRC error\n" ); return 2; }
}
if( std::fclose( stdout ) != 0 )
{ std::fprintf( stderr, "Can't close stdout: %s\n", std::strerror( errno ) );
return 1; }
return 0;
}

115
main.cc
View file

@ -1,115 +0,0 @@
/* Lzd - Educational decompressor for lzip files
Copyright (C) 2013 Antonio Diaz Diaz.
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.
*/
/*
Exit status: 0 for a normal exit, 1 for environmental problems
(file not found, invalid flags, I/O errors, etc), 2 to indicate a
corrupt or invalid input file.
*/
#include <algorithm>
#include <cerrno>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <stdint.h>
#include <unistd.h>
#if defined(__MSVCRT__) || defined(__OS2__)
#include <fcntl.h>
#include <io.h>
#endif
#include "decoder.cc"
enum { min_dictionary_size = 1 << 12,
max_dictionary_size = 1 << 29 };
typedef uint8_t File_header[6]; // 0-3 magic, 4 version, 5 coded_dict_size
typedef uint8_t File_trailer[20];
// 0-3 CRC32 of the uncompressed data
// 4-11 size of the uncompressed data
// 12-19 member size including header and trailer
int main( const int argc, const char * const argv[] )
{
if( argc > 1 )
{
std::printf( "Lzd %s - Educational decompressor for lzip files.\n",
PROGVERSION );
std::printf( "Study the source to learn how a simple lzip decompressor works.\n"
"It is not safe to use it for any real work.\n"
"\nUsage: %s < file.lz > file\n", argv[0] );
std::printf( "Lzd decompresses from standard input to standard output.\n"
"\nCopyright (C) 2013 Antonio Diaz Diaz.\n"
"This is free software: you are free to change and redistribute it.\n"
"There is NO WARRANTY, to the extent permitted by law.\n"
"Report bugs to lzip-bug@nongnu.org\n"
"Lzip home page: http://www.nongnu.org/lzip/lzip.html\n" );
return 0;
}
#if defined(__MSVCRT__) || defined(__OS2__)
setmode( STDIN_FILENO, O_BINARY );
setmode( STDOUT_FILENO, O_BINARY );
#endif
if( isatty( STDIN_FILENO ) )
{
std::fprintf( stderr, "I won't read compressed data from a terminal.\n"
"Try '%s --help' for more information.\n", argv[0] );
return 1;
}
for( bool first_member = true; ; first_member = false )
{
File_header header;
for( int i = 0; i < 6; ++i )
header[i] = std::getc( stdin );
if( std::feof( stdin ) || std::memcmp( header, "LZIP", 4 ) != 0 )
{
if( first_member )
{ std::fprintf( stderr, "Bad magic number (file not in lzip format)\n" );
return 2; }
break;
}
if( header[4] != 1 )
{
std::fprintf( stderr, "Version %d member format not supported.\n",
header[4] );
return 2;
}
unsigned dict_size = 1 << ( header[5] & 0x1F );
dict_size -= ( dict_size / 16 ) * ( ( header[5] >> 5 ) & 7 );
if( dict_size < min_dictionary_size || dict_size > max_dictionary_size )
{ std::fprintf( stderr, "Invalid dictionary size in member header\n" );
return 2; }
LZ_decoder decoder( dict_size );
if( !decoder.decode_member() )
{ std::fprintf( stderr, "Data error\n" ); return 2; }
File_trailer trailer;
for( int i = 0; i < 20; ++i ) trailer[i] = std::getc( stdin );
unsigned crc = 0;
for( int i = 3; i >= 0; --i ) { crc <<= 8; crc += trailer[i]; }
unsigned long long data_size = 0;
for( int i = 11; i >= 4; --i ) { data_size <<= 8; data_size += trailer[i]; }
if( crc != decoder.crc() || data_size != decoder.data_position() )
{ std::fprintf( stderr, "CRC error\n" ); return 2; }
}
if( std::fclose( stdout ) != 0 )
{ std::fprintf( stderr, "Can't close stdout: %s\n", std::strerror( errno ) );
return 1; }
return 0;
}

View file

@ -27,6 +27,15 @@ fail=0
printf "testing lzd-%s..." "$2"
"${LZIP}" < "${in_lz}" > /dev/full 2> /dev/null
if [ $? = 1 ] ; then printf . ; else fail=1 ; printf - ; fi
"${LZIP}" < "${in}" 2> /dev/null
if [ $? = 2 ] ; then printf . ; else fail=1 ; printf - ; fi
dd if="${in_lz}" bs=1 count=6 2> /dev/null | "${LZIP}" 2> /dev/null
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
dd if="${in_lz}" bs=1 count=20 2> /dev/null | "${LZIP}" 2> /dev/null
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
"${LZIP}" < "${in_lz}" > copy || fail=1
cmp "${in}" copy || fail=1
printf .