Merging upstream version 1.5.
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
parent
5e1f92d2a0
commit
66060d80f9
GPG key ID:
FBB4F0E80A80222F
20 changed files with 632 additions and 272 deletions
28
ChangeLog
28
ChangeLog
|
|
@ -1,3 +1,15 @@
|
|||
2016-05-14 Antonio Diaz Diaz <antonio@gnu.org>
|
||||
|
||||
* Version 1.5 released.
|
||||
* main.cc: Added new option '-a, --trailing-error'.
|
||||
* main.cc (main): Delete '--output' file if infd is a terminal.
|
||||
* main.cc (main): Don't use stdin more than once.
|
||||
* lzip.texi: Added chapters 'Trailing data' and 'Examples'.
|
||||
* configure: Avoid warning on some shells when testing for g++.
|
||||
* Makefile.in: Detect the existence of install-info.
|
||||
* testsuite/check.sh: A POSIX shell is required to run the tests.
|
||||
* testsuite/check.sh: Don't check error messages.
|
||||
|
||||
2015-07-09 Antonio Diaz Diaz <antonio@gnu.org>
|
||||
|
||||
* Version 1.4 released.
|
||||
|
|
@ -6,11 +18,11 @@
|
|||
2015-01-22 Antonio Diaz Diaz <antonio@gnu.org>
|
||||
|
||||
* Version 1.3 released.
|
||||
* dec_stream.cc: Do not use output packets or muxer when testing.
|
||||
* dec_stream.cc: Don't use output packets or muxer when testing.
|
||||
* Make '-dvvv' and '-tvvv' show dictionary size like lzip.
|
||||
* lzip.h: Added missing 'const' to the declaration of 'compress'.
|
||||
* Added chapters 'Memory requirements' and 'Minimum file sizes'
|
||||
to manual.
|
||||
* lzip.texi: Added chapters 'Memory requirements' and
|
||||
'Minimum file sizes'.
|
||||
* Makefile.in: Added new targets 'install*-compress'.
|
||||
|
||||
2014-08-29 Antonio Diaz Diaz <antonio@gnu.org>
|
||||
|
|
@ -27,7 +39,7 @@
|
|||
|
||||
* Version 1.1 released.
|
||||
* Show progress of compression at verbosity level 2 (-vv).
|
||||
* SIGUSR1 and SIGUSR2 are no more used to signal a fatal error.
|
||||
* SIGUSR1 and SIGUSR2 are no longer used to signal a fatal error.
|
||||
|
||||
2013-05-29 Antonio Diaz Diaz <antonio@gnu.org>
|
||||
|
||||
|
|
@ -69,7 +81,7 @@
|
|||
to match those of lzip 1.11.
|
||||
* decompress.cc: A limit has been set on the number of packets
|
||||
produced by workers to limit the amount of memory used.
|
||||
* main.cc (open_instream): Do not show the message
|
||||
* main.cc (open_instream): Don't show the message
|
||||
" and '--stdout' was not specified" for directories, etc.
|
||||
* main.cc: Fixed warning about fchown return value being ignored.
|
||||
* testsuite: 'test1' renamed to 'test.txt'. Added new tests.
|
||||
|
|
@ -78,8 +90,8 @@
|
|||
|
||||
* Version 0.6 released.
|
||||
* Small portability fixes.
|
||||
* Added chapter 'Program Design' and description of option
|
||||
'--threads' to manual.
|
||||
* lzip.texinfo: Added chapter 'Program Design' and description
|
||||
of option '--threads'.
|
||||
* Debug stats have been fixed.
|
||||
|
||||
2010-02-10 Antonio Diaz Diaz <ant_diaz@teleline.es>
|
||||
|
|
@ -127,7 +139,7 @@
|
|||
until something better appears on the net.
|
||||
|
||||
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This file is a collection of facts, and thus it is not copyrightable,
|
||||
but just in case, you have unlimited permission to copy, distribute and
|
||||
|
|
|
|||
4
INSTALL
4
INSTALL
|
|
@ -1,7 +1,7 @@
|
|||
Requirements
|
||||
------------
|
||||
You will need a C++ compiler and the lzlib compression library installed.
|
||||
I use gcc 4.9.1 and 4.1.2, but the code should compile with any
|
||||
I use gcc 5.3.0 and 4.1.2, but the code should compile with any
|
||||
standards compliant compiler.
|
||||
Lzlib must be version 1.0 or newer, but the fast encoder is only
|
||||
available in lzlib 1.7 or newer.
|
||||
|
|
@ -65,7 +65,7 @@ After running 'configure', you can run 'make' and 'make install' as
|
|||
explained above.
|
||||
|
||||
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This file is free documentation: you have unlimited permission to copy,
|
||||
distribute and modify it.
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@ INSTALL_DATA = $(INSTALL) -m 644
|
|||
INSTALL_DIR = $(INSTALL) -d -m 755
|
||||
LIBS = -llz -lpthread
|
||||
SHELL = /bin/sh
|
||||
CAN_RUN_INSTALLINFO = $(SHELL) -c "install-info --version" > /dev/null 2>&1
|
||||
|
||||
objs = arg_parser.o file_index.o compress.o dec_stdout.o dec_stream.o \
|
||||
decompress.o main.o
|
||||
|
|
@ -72,7 +73,9 @@ install-info :
|
|||
if [ ! -d "$(DESTDIR)$(infodir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(infodir)" ; fi
|
||||
-rm -f "$(DESTDIR)$(infodir)/$(pkgname).info"*
|
||||
$(INSTALL_DATA) $(VPATH)/doc/$(pkgname).info "$(DESTDIR)$(infodir)/$(pkgname).info"
|
||||
-install-info --info-dir="$(DESTDIR)$(infodir)" "$(DESTDIR)$(infodir)/$(pkgname).info"
|
||||
-if $(CAN_RUN_INSTALLINFO) ; then \
|
||||
install-info --info-dir="$(DESTDIR)$(infodir)" "$(DESTDIR)$(infodir)/$(pkgname).info" ; \
|
||||
fi
|
||||
|
||||
install-info-compress : install-info
|
||||
lzip -v -9 "$(DESTDIR)$(infodir)/$(pkgname).info"
|
||||
|
|
@ -95,7 +98,9 @@ uninstall-bin :
|
|||
-rm -f "$(DESTDIR)$(bindir)/$(progname)"
|
||||
|
||||
uninstall-info :
|
||||
-install-info --info-dir="$(DESTDIR)$(infodir)" --remove "$(DESTDIR)$(infodir)/$(pkgname).info"
|
||||
-if $(CAN_RUN_INSTALLINFO) ; then \
|
||||
install-info --info-dir="$(DESTDIR)$(infodir)" --remove "$(DESTDIR)$(infodir)/$(pkgname).info" ; \
|
||||
fi
|
||||
-rm -f "$(DESTDIR)$(infodir)/$(pkgname).info"*
|
||||
|
||||
uninstall-man :
|
||||
|
|
|
|||
17
NEWS
17
NEWS
|
|
@ -1,5 +1,14 @@
|
|||
Changes in version 1.4:
|
||||
Changes in version 1.5:
|
||||
|
||||
The option "-0" has been modified to use the new fast encoder of lzlib
|
||||
1.7, which achieves a compression speed and ratio comparable to those of
|
||||
pigz's default compression level.
|
||||
The option "-a, --trailing-error", which makes plzip exit with error
|
||||
status 2 if any remaining input is detected after decompressing the last
|
||||
member, has been added.
|
||||
|
||||
When decompressing, the file specified with the '--output' option is now
|
||||
deleted if the input is a terminal.
|
||||
|
||||
The new chapters "Trailing data" and "Examples" have been added to the
|
||||
manual.
|
||||
|
||||
A harmless check failure on Windows, caused by the failed comparison of
|
||||
a message in text mode, has been fixed.
|
||||
|
|
|
|||
4
README
4
README
|
|
@ -13,7 +13,7 @@ plzip is no faster than lzip.
|
|||
|
||||
When compressing, plzip divides the input file into chunks and
|
||||
compresses as many chunks simultaneously as worker threads are chosen,
|
||||
creating a multi-member compressed file.
|
||||
creating a multimember compressed file.
|
||||
|
||||
When decompressing, plzip decompresses as many members simultaneously as
|
||||
worker threads are chosen. Files that were compressed with lzip will not
|
||||
|
|
@ -88,7 +88,7 @@ corresponding uncompressed files. Integrity testing of concatenated
|
|||
compressed files is also supported.
|
||||
|
||||
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This file is free documentation: you have unlimited permission to copy,
|
||||
distribute and modify it.
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
/* Arg_parser - POSIX/GNU command line argument parser. (C++ version)
|
||||
Copyright (C) 2006-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2006-2016 Antonio Diaz Diaz.
|
||||
|
||||
This library is free software. Redistribution and use in source and
|
||||
binary forms, with or without modification, are permitted provided
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
/* Arg_parser - POSIX/GNU command line argument parser. (C++ version)
|
||||
Copyright (C) 2006-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2006-2016 Antonio Diaz Diaz.
|
||||
|
||||
This library is free software. Redistribution and use in source and
|
||||
binary forms, with or without modification, are permitted provided
|
||||
|
|
|
|||
18
compress.cc
18
compress.cc
|
|
@ -1,6 +1,6 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009 Laszlo Ersek.
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -77,14 +77,14 @@ int writeblock( const int fd, const uint8_t * const buf, const int size )
|
|||
}
|
||||
|
||||
|
||||
void xinit( pthread_mutex_t * const mutex )
|
||||
void xinit_mutex( pthread_mutex_t * const mutex )
|
||||
{
|
||||
const int errcode = pthread_mutex_init( mutex, 0 );
|
||||
if( errcode )
|
||||
{ show_error( "pthread_mutex_init", errcode ); cleanup_and_fail(); }
|
||||
}
|
||||
|
||||
void xinit( pthread_cond_t * const cond )
|
||||
void xinit_cond( pthread_cond_t * const cond )
|
||||
{
|
||||
const int errcode = pthread_cond_init( cond, 0 );
|
||||
if( errcode )
|
||||
|
|
@ -92,14 +92,14 @@ void xinit( pthread_cond_t * const cond )
|
|||
}
|
||||
|
||||
|
||||
void xdestroy( pthread_mutex_t * const mutex )
|
||||
void xdestroy_mutex( pthread_mutex_t * const mutex )
|
||||
{
|
||||
const int errcode = pthread_mutex_destroy( mutex );
|
||||
if( errcode )
|
||||
{ show_error( "pthread_mutex_destroy", errcode ); cleanup_and_fail(); }
|
||||
}
|
||||
|
||||
void xdestroy( pthread_cond_t * const cond )
|
||||
void xdestroy_cond( pthread_cond_t * const cond )
|
||||
{
|
||||
const int errcode = pthread_cond_destroy( cond );
|
||||
if( errcode )
|
||||
|
|
@ -196,14 +196,14 @@ public:
|
|||
slot_tally( slots ), circular_buffer( slots, (Packet *) 0 ),
|
||||
num_working( workers ), num_slots( slots ), eof( false )
|
||||
{
|
||||
xinit( &imutex ); xinit( &iav_or_eof );
|
||||
xinit( &omutex ); xinit( &oav_or_exit );
|
||||
xinit_mutex( &imutex ); xinit_cond( &iav_or_eof );
|
||||
xinit_mutex( &omutex ); xinit_cond( &oav_or_exit );
|
||||
}
|
||||
|
||||
~Packet_courier()
|
||||
{
|
||||
xdestroy( &oav_or_exit ); xdestroy( &omutex );
|
||||
xdestroy( &iav_or_eof ); xdestroy( &imutex );
|
||||
xdestroy_cond( &oav_or_exit ); xdestroy_mutex( &omutex );
|
||||
xdestroy_cond( &iav_or_eof ); xdestroy_mutex( &imutex );
|
||||
}
|
||||
|
||||
// make a packet with data received from splitter
|
||||
|
|
|
|||
14
configure
vendored
14
configure
vendored
|
|
@ -1,12 +1,12 @@
|
|||
#! /bin/sh
|
||||
# configure script for Plzip - Parallel compressor compatible with lzip
|
||||
# Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
# Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
#
|
||||
# This configure script is free software: you have unlimited permission
|
||||
# to copy, distribute and modify it.
|
||||
|
||||
pkgname=plzip
|
||||
pkgversion=1.4
|
||||
pkgversion=1.5
|
||||
progname=plzip
|
||||
srctrigger=doc/${pkgname}.texi
|
||||
|
||||
|
|
@ -26,8 +26,8 @@ CXXFLAGS='-Wall -W -O2'
|
|||
LDFLAGS=
|
||||
|
||||
# checking whether we are using GNU C++.
|
||||
${CXX} --version > /dev/null 2>&1
|
||||
if [ $? != 0 ] ; then
|
||||
if /bin/sh -c "${CXX} --version" > /dev/null 2>&1 ; then true
|
||||
else
|
||||
CXX=c++
|
||||
CXXFLAGS='-W -O2'
|
||||
fi
|
||||
|
|
@ -139,7 +139,7 @@ if [ -z "${no_create}" ] ; then
|
|||
rm -f config.status
|
||||
cat > config.status << EOF
|
||||
#! /bin/sh
|
||||
# This file was generated automatically by configure. Do not edit.
|
||||
# This file was generated automatically by configure. Don't edit.
|
||||
# Run this file to recreate the current configuration.
|
||||
#
|
||||
# This script is free software: you have unlimited permission
|
||||
|
|
@ -165,8 +165,8 @@ echo "LDFLAGS = ${LDFLAGS}"
|
|||
rm -f Makefile
|
||||
cat > Makefile << EOF
|
||||
# Makefile for Plzip - Parallel compressor compatible with lzip
|
||||
# Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
# This file was generated automatically by configure. Do not edit.
|
||||
# Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
# This file was generated automatically by configure. Don't edit.
|
||||
#
|
||||
# This Makefile is free software: you have unlimited permission
|
||||
# to copy, distribute and modify it.
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009 Laszlo Ersek.
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -76,14 +76,14 @@ public:
|
|||
opacket_queues( workers ), num_working( workers ),
|
||||
num_workers( workers ), out_slots( slots ), slot_av( workers )
|
||||
{
|
||||
xinit( &omutex ); xinit( &oav_or_exit );
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xinit( &slot_av[i] );
|
||||
xinit_mutex( &omutex ); xinit_cond( &oav_or_exit );
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xinit_cond( &slot_av[i] );
|
||||
}
|
||||
|
||||
~Packet_courier()
|
||||
{
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xdestroy( &slot_av[i] );
|
||||
xdestroy( &oav_or_exit ); xdestroy( &omutex );
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xdestroy_cond( &slot_av[i] );
|
||||
xdestroy_cond( &oav_or_exit ); xdestroy_mutex( &omutex );
|
||||
}
|
||||
|
||||
void worker_finished()
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009 Laszlo Ersek.
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -88,16 +88,16 @@ public:
|
|||
num_workers( workers ), out_slots( oslots ), slot_av( workers ),
|
||||
eof( false )
|
||||
{
|
||||
xinit( &imutex ); xinit( &iav_or_eof );
|
||||
xinit( &omutex ); xinit( &oav_or_exit );
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xinit( &slot_av[i] );
|
||||
xinit_mutex( &imutex ); xinit_cond( &iav_or_eof );
|
||||
xinit_mutex( &omutex ); xinit_cond( &oav_or_exit );
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xinit_cond( &slot_av[i] );
|
||||
}
|
||||
|
||||
~Packet_courier()
|
||||
{
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xdestroy( &slot_av[i] );
|
||||
xdestroy( &oav_or_exit ); xdestroy( &omutex );
|
||||
xdestroy( &iav_or_eof ); xdestroy( &imutex );
|
||||
for( unsigned i = 0; i < slot_av.size(); ++i ) xdestroy_cond( &slot_av[i] );
|
||||
xdestroy_cond( &oav_or_exit ); xdestroy_mutex( &omutex );
|
||||
xdestroy_cond( &iav_or_eof ); xdestroy_mutex( &imutex );
|
||||
}
|
||||
|
||||
// make a packet with data received from splitter
|
||||
|
|
@ -345,6 +345,7 @@ struct Worker_arg
|
|||
Packet_courier * courier;
|
||||
const Pretty_print * pp;
|
||||
int worker_id;
|
||||
bool ignore_trailing;
|
||||
bool testing;
|
||||
};
|
||||
|
||||
|
|
@ -357,6 +358,7 @@ extern "C" void * dworker_s( void * arg )
|
|||
Packet_courier & courier = *tmp.courier;
|
||||
const Pretty_print & pp = *tmp.pp;
|
||||
const int worker_id = tmp.worker_id;
|
||||
const bool ignore_trailing = tmp.ignore_trailing;
|
||||
const bool testing = tmp.testing;
|
||||
|
||||
uint8_t * new_data = new( std::nothrow ) uint8_t[max_packet_size];
|
||||
|
|
@ -392,7 +394,11 @@ extern "C" void * dworker_s( void * arg )
|
|||
if( rd < 0 )
|
||||
{
|
||||
if( LZ_decompress_errno( decoder ) == LZ_header_error )
|
||||
{
|
||||
trailing_garbage_found = true;
|
||||
if( !ignore_trailing )
|
||||
{ pp( "Trailing data not allowed." ); cleanup_and_fail( 2 ); }
|
||||
}
|
||||
else
|
||||
cleanup_and_fail( decompress_read_error( decoder, pp, worker_id ) );
|
||||
}
|
||||
|
|
@ -461,7 +467,8 @@ void muxer( Packet_courier & courier, const Pretty_print & pp, const int outfd )
|
|||
// init the courier, then start the splitter and the workers and,
|
||||
// if not testing, call the muxer.
|
||||
int dec_stream( const int num_workers, const int infd, const int outfd,
|
||||
const Pretty_print & pp, const int debug_level )
|
||||
const Pretty_print & pp, const int debug_level,
|
||||
const bool ignore_trailing )
|
||||
{
|
||||
const int in_slots_per_worker = 2;
|
||||
const int out_slots = 32;
|
||||
|
|
@ -490,6 +497,7 @@ int dec_stream( const int num_workers, const int infd, const int outfd,
|
|||
worker_args[i].courier = &courier;
|
||||
worker_args[i].pp = &pp;
|
||||
worker_args[i].worker_id = i;
|
||||
worker_args[i].ignore_trailing = ignore_trailing;
|
||||
worker_args[i].testing = ( outfd < 0 );
|
||||
errcode = pthread_create( &worker_threads[i], 0, dworker_s, &worker_args[i] );
|
||||
if( errcode )
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009 Laszlo Ersek.
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -45,7 +45,7 @@ void Pretty_print::operator()( const char * const msg ) const
|
|||
{
|
||||
first_post = false;
|
||||
std::fprintf( stderr, " %s: ", name_.c_str() );
|
||||
for( unsigned i = 0; i < longest_name - name_.size(); ++i )
|
||||
for( unsigned i = name_.size(); i < longest_name; ++i )
|
||||
std::fputc( ' ', stderr );
|
||||
if( !msg ) std::fflush( stderr );
|
||||
}
|
||||
|
|
@ -213,16 +213,16 @@ extern "C" void * dworker( void * arg )
|
|||
// start the workers and wait for them to finish.
|
||||
int decompress( int num_workers, const int infd, const int outfd,
|
||||
const Pretty_print & pp, const int debug_level,
|
||||
const bool infd_isreg )
|
||||
const bool ignore_trailing, const bool infd_isreg )
|
||||
{
|
||||
if( !infd_isreg )
|
||||
return dec_stream( num_workers, infd, outfd, pp, debug_level );
|
||||
return dec_stream( num_workers, infd, outfd, pp, debug_level, ignore_trailing );
|
||||
|
||||
const File_index file_index( infd );
|
||||
const File_index file_index( infd, ignore_trailing );
|
||||
if( file_index.retval() == 1 )
|
||||
{
|
||||
lseek( infd, 0, SEEK_SET );
|
||||
return dec_stream( num_workers, infd, outfd, pp, debug_level );
|
||||
return dec_stream( num_workers, infd, outfd, pp, debug_level, ignore_trailing );
|
||||
}
|
||||
if( file_index.retval() != 0 )
|
||||
{ pp( file_index.error().c_str() ); return file_index.retval(); }
|
||||
|
|
|
|||
22
doc/plzip.1
22
doc/plzip.1
|
|
@ -1,5 +1,5 @@
|
|||
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.46.1.
|
||||
.TH PLZIP "1" "July 2015" "plzip 1.4" "User Commands"
|
||||
.TH PLZIP "1" "May 2016" "plzip 1.5" "User Commands"
|
||||
.SH NAME
|
||||
plzip \- reduces the size of files
|
||||
.SH SYNOPSIS
|
||||
|
|
@ -15,11 +15,14 @@ display this help and exit
|
|||
\fB\-V\fR, \fB\-\-version\fR
|
||||
output version information and exit
|
||||
.TP
|
||||
\fB\-a\fR, \fB\-\-trailing\-error\fR
|
||||
exit with error status if trailing data
|
||||
.TP
|
||||
\fB\-B\fR, \fB\-\-data\-size=\fR<bytes>
|
||||
set size of input data blocks [2x8=16 MiB]
|
||||
.TP
|
||||
\fB\-c\fR, \fB\-\-stdout\fR
|
||||
send output to standard output
|
||||
write to standard output, keep input files
|
||||
.TP
|
||||
\fB\-d\fR, \fB\-\-decompress\fR
|
||||
decompress
|
||||
|
|
@ -40,7 +43,7 @@ set match length limit in bytes [36]
|
|||
set number of (de)compression threads [2]
|
||||
.TP
|
||||
\fB\-o\fR, \fB\-\-output=\fR<file>
|
||||
if reading stdin, place the output into <file>
|
||||
if reading standard input, write to <file>
|
||||
.TP
|
||||
\fB\-q\fR, \fB\-\-quiet\fR
|
||||
suppress all messages
|
||||
|
|
@ -63,13 +66,16 @@ alias for \fB\-0\fR
|
|||
\fB\-\-best\fR
|
||||
alias for \fB\-9\fR
|
||||
.PP
|
||||
If no file names are given, plzip compresses or decompresses
|
||||
from standard input to standard output.
|
||||
If no file names are given, or if a file is '\-', plzip compresses or
|
||||
decompresses from standard input to standard output.
|
||||
Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,
|
||||
Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...
|
||||
Dictionary sizes 12 to 29 are interpreted as powers of two, meaning 2^12
|
||||
to 2^29 bytes.
|
||||
.PP
|
||||
The bidimensional parameter space of LZMA can't be mapped to a linear
|
||||
scale optimal for all files. If your files are large, very repetitive,
|
||||
etc, you may need to use the \fB\-\-match\-length\fR and \fB\-\-dictionary\-size\fR
|
||||
etc, you may need to use the \fB\-\-dictionary\-size\fR and \fB\-\-match\-length\fR
|
||||
options directly to achieve optimal performance.
|
||||
.PP
|
||||
Exit status: 0 for a normal exit, 1 for environmental problems (file
|
||||
|
|
@ -83,8 +89,8 @@ Plzip home page: http://www.nongnu.org/lzip/plzip.html
|
|||
.SH COPYRIGHT
|
||||
Copyright \(co 2009 Laszlo Ersek.
|
||||
.br
|
||||
Copyright \(co 2015 Antonio Diaz Diaz.
|
||||
Using lzlib 1.7
|
||||
Copyright \(co 2016 Antonio Diaz Diaz.
|
||||
Using lzlib 1.8
|
||||
License GPLv2+: GNU GPL version 2 or later <http://gnu.org/licenses/gpl.html>
|
||||
.br
|
||||
This is free software: you are free to change and redistribute it.
|
||||
|
|
|
|||
206
doc/plzip.info
206
doc/plzip.info
|
|
@ -11,7 +11,7 @@ File: plzip.info, Node: Top, Next: Introduction, Up: (dir)
|
|||
Plzip Manual
|
||||
************
|
||||
|
||||
This manual is for Plzip (version 1.4, 9 July 2015).
|
||||
This manual is for Plzip (version 1.5, 14 May 2016).
|
||||
|
||||
* Menu:
|
||||
|
||||
|
|
@ -21,11 +21,13 @@ This manual is for Plzip (version 1.4, 9 July 2015).
|
|||
* File format:: Detailed format of the compressed file
|
||||
* Memory requirements:: Memory required to compress and decompress
|
||||
* Minimum file sizes:: Minimum file sizes required for full speed
|
||||
* Trailing data:: Extra data appended to the file
|
||||
* Examples:: A small tutorial with examples
|
||||
* Problems:: Reporting bugs
|
||||
* Concept index:: Index of concepts
|
||||
|
||||
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This manual is free documentation: you have unlimited permission to
|
||||
copy, distribute and modify it.
|
||||
|
|
@ -59,7 +61,7 @@ availability:
|
|||
recovery means. The lziprecover program can repair bit-flip errors
|
||||
(one of the most common forms of data corruption) in lzip files,
|
||||
and provides data recovery capabilities, including error-checked
|
||||
merging of damaged copies of a file. *note Data safety:
|
||||
merging of damaged copies of a file. *Note Data safety:
|
||||
(lziprecover)Data safety.
|
||||
|
||||
* The lzip format is as simple as possible (but not simpler). The
|
||||
|
|
@ -115,13 +117,6 @@ two or more compressed files. The result is the concatenation of the
|
|||
corresponding uncompressed files. Integrity testing of concatenated
|
||||
compressed files is also supported.
|
||||
|
||||
WARNING! Even if plzip is bug-free, other causes may result in a
|
||||
corrupt compressed file (bugs in the system libraries, memory errors,
|
||||
etc). Therefore, if the data you are going to compress are important,
|
||||
give the '--keep' option to plzip and do not remove the original file
|
||||
until you verify the compressed file with a command like
|
||||
'plzip -cd file.lz | cmp file -'.
|
||||
|
||||
|
||||
File: plzip.info, Node: Invoking plzip, Next: Program design, Prev: Introduction, Up: Top
|
||||
|
||||
|
|
@ -132,6 +127,10 @@ The format for running plzip is:
|
|||
|
||||
plzip [OPTIONS] [FILES]
|
||||
|
||||
'-' used as a FILE argument means standard input. It can be mixed with
|
||||
other FILES and is read just once, the first time it appears in the
|
||||
command line.
|
||||
|
||||
Plzip supports the following options:
|
||||
|
||||
'-h'
|
||||
|
|
@ -142,6 +141,13 @@ The format for running plzip is:
|
|||
'--version'
|
||||
Print the version number of plzip on the standard output and exit.
|
||||
|
||||
'-a'
|
||||
'--trailing-error'
|
||||
Exit with error status 2 if any remaining input is detected after
|
||||
decompressing the last member. Such remaining input is usually
|
||||
trailing garbage that can be safely ignored. *Note
|
||||
concat-example::.
|
||||
|
||||
'-B BYTES'
|
||||
'--data-size=BYTES'
|
||||
Set the size of the input data blocks, in bytes. The input file
|
||||
|
|
@ -153,12 +159,17 @@ The format for running plzip is:
|
|||
|
||||
'-c'
|
||||
'--stdout'
|
||||
Compress or decompress to standard output. Needed when reading
|
||||
from a named pipe (fifo) or from a device.
|
||||
Compress or decompress to standard output; keep input files
|
||||
unchanged. If compressing several files, each file is compressed
|
||||
independently. This option is needed when reading from a named
|
||||
pipe (fifo) or from a device.
|
||||
|
||||
'-d'
|
||||
'--decompress'
|
||||
Decompress.
|
||||
Decompress the specified file(s). If a file does not exist or
|
||||
can't be opened, plzip continues decompressing the rest of the
|
||||
files. If a file fails to decompress, plzip exits immediately
|
||||
without decompressing the rest of the files.
|
||||
|
||||
'-f'
|
||||
'--force'
|
||||
|
|
@ -207,12 +218,13 @@ The format for running plzip is:
|
|||
|
||||
'-s BYTES'
|
||||
'--dictionary-size=BYTES'
|
||||
Set the dictionary size limit in bytes. Valid values range from 4
|
||||
KiB to 512 MiB. Plzip will use the smallest possible dictionary
|
||||
size for each file without exceeding this limit. Note that
|
||||
dictionary sizes are quantized. If the specified size does not
|
||||
match one of the valid sizes, it will be rounded upwards by adding
|
||||
up to (BYTES / 16) to it.
|
||||
Set the dictionary size limit in bytes. Plzip will use the smallest
|
||||
possible dictionary size for each file without exceeding this
|
||||
limit. Valid values range from 4 KiB to 512 MiB. Values 12 to 29
|
||||
are interpreted as powers of two, meaning 2^12 to 2^29 bytes. Note
|
||||
that dictionary sizes are quantized. If the specified size does
|
||||
not match one of the valid sizes, it will be rounded upwards by
|
||||
adding up to (BYTES / 8) to it.
|
||||
|
||||
For maximum compression you should use a dictionary size limit as
|
||||
large as possible, but keep in mind that the decompression memory
|
||||
|
|
@ -224,7 +236,8 @@ The format for running plzip is:
|
|||
Check integrity of the specified file(s), but don't decompress
|
||||
them. This really performs a trial decompression and throws away
|
||||
the result. Use it together with '-v' to see information about
|
||||
the file.
|
||||
the file(s). If a file fails the test, plzip may be unable to
|
||||
check the rest of the files.
|
||||
|
||||
'-v'
|
||||
'--verbose'
|
||||
|
|
@ -237,14 +250,14 @@ The format for running plzip is:
|
|||
|
||||
'-0 .. -9'
|
||||
Set the compression parameters (dictionary size and match length
|
||||
limit) as shown in the table below. Note that '-9' can be much
|
||||
slower than '-0'. These options have no effect when decompressing.
|
||||
limit) as shown in the table below. The default compression level
|
||||
is '-6'. Note that '-9' can be much slower than '-0'. These
|
||||
options have no effect when decompressing.
|
||||
|
||||
The bidimensional parameter space of LZMA can't be mapped to a
|
||||
linear scale optimal for all files. If your files are large, very
|
||||
repetitive, etc, you may need to use the '--match-length' and
|
||||
'--dictionary-size' options directly to achieve optimal
|
||||
performance.
|
||||
repetitive, etc, you may need to use the '--dictionary-size' and
|
||||
'--match-length' options directly to achieve optimal performance.
|
||||
|
||||
Level Dictionary size Match length limit
|
||||
-0 64 KiB 16 bytes
|
||||
|
|
@ -292,7 +305,7 @@ File: plzip.info, Node: Program design, Next: File format, Prev: Invoking plz
|
|||
|
||||
When compressing, plzip divides the input file into chunks and
|
||||
compresses as many chunks simultaneously as worker threads are chosen,
|
||||
creating a multi-member compressed file.
|
||||
creating a multimember compressed file.
|
||||
|
||||
When decompressing, plzip decompresses as many members
|
||||
simultaneously as worker threads are chosen. Files that were compressed
|
||||
|
|
@ -348,12 +361,12 @@ additional information before, between, or after them.
|
|||
|
||||
Each member has the following structure:
|
||||
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|
||||
| ID string | VN | DS | Lzma stream | CRC32 | Data size | Member size |
|
||||
| ID string | VN | DS | LZMA stream | CRC32 | Data size | Member size |
|
||||
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|
||||
|
||||
All multibyte values are stored in little endian order.
|
||||
|
||||
'ID string'
|
||||
'ID string (the "magic" bytes)'
|
||||
A four byte string, identifying the lzip format, with the value
|
||||
"LZIP" (0x4C, 0x5A, 0x49, 0x50).
|
||||
|
||||
|
|
@ -371,8 +384,8 @@ additional information before, between, or after them.
|
|||
Example: 0xD3 = 2^19 - 6 * 2^15 = 512 KiB - 6 * 32 KiB = 320 KiB
|
||||
Valid values for dictionary size range from 4 KiB to 512 MiB.
|
||||
|
||||
'Lzma stream'
|
||||
The lzma stream, finished by an end of stream marker. Uses default
|
||||
'LZMA stream'
|
||||
The LZMA stream, finished by an end of stream marker. Uses default
|
||||
values for encoder properties. *Note Stream format: (lzip)Stream
|
||||
format, for a complete description.
|
||||
|
||||
|
|
@ -386,7 +399,7 @@ additional information before, between, or after them.
|
|||
Total size of the member, including header and trailer. This field
|
||||
acts as a distributed index, allows the verification of stream
|
||||
integrity, and facilitates safe recovery of undamaged members from
|
||||
multi-member files.
|
||||
multimember files.
|
||||
|
||||
|
||||
|
||||
|
|
@ -408,7 +421,7 @@ following:
|
|||
file, or for testing of a regular file; the dictionary size.
|
||||
|
||||
(Note that regular files with more than 1024 bytes of trailing
|
||||
garbage are treated as non-seekable).
|
||||
data are treated as non-seekable).
|
||||
|
||||
* For testing of a non-seekable file or of standard input; the
|
||||
dictionary size plus up to 5 MiB.
|
||||
|
|
@ -420,14 +433,14 @@ following:
|
|||
dictionary size plus up to 35 MiB.
|
||||
|
||||
|
||||
File: plzip.info, Node: Minimum file sizes, Next: Problems, Prev: Memory requirements, Up: Top
|
||||
File: plzip.info, Node: Minimum file sizes, Next: Trailing data, Prev: Memory requirements, Up: Top
|
||||
|
||||
6 Minimum file sizes required for full compression speed
|
||||
********************************************************
|
||||
|
||||
When compressing, plzip divides the input file into chunks and
|
||||
compresses as many chunks simultaneously as worker threads are chosen,
|
||||
creating a multi-member compressed file.
|
||||
creating a multimember compressed file.
|
||||
|
||||
For this to work as expected (and roughly multiply the compression
|
||||
speed by the number of available processors), the uncompressed file
|
||||
|
|
@ -456,9 +469,106 @@ Level
|
|||
-9 128 MiB 256 MiB 512 MiB 1 GiB 4 GiB 16 GiB
|
||||
|
||||
|
||||
File: plzip.info, Node: Problems, Next: Concept index, Prev: Minimum file sizes, Up: Top
|
||||
File: plzip.info, Node: Trailing data, Next: Examples, Prev: Minimum file sizes, Up: Top
|
||||
|
||||
7 Reporting bugs
|
||||
7 Extra data appended to the file
|
||||
*********************************
|
||||
|
||||
Sometimes extra data is found appended to a lzip file after the last
|
||||
member. Such trailing data may be:
|
||||
|
||||
* Padding added to make the file size a multiple of some block size,
|
||||
for example when writing to a tape.
|
||||
|
||||
* Garbage added by some not totally successful copy operation.
|
||||
|
||||
* Useful data added by the user; a cryptographically secure hash, a
|
||||
description of file contents, etc.
|
||||
|
||||
* Malicious data added to the file in order to make its total size
|
||||
and hash value (for a chosen hash) coincide with those of another
|
||||
file.
|
||||
|
||||
* In very rare cases, trailing data could be the corrupt header of
|
||||
another member. In multimember or concatenated files the
|
||||
probability of corruption happening in the magic bytes is 5 times
|
||||
smaller than the probability of getting a false positive caused by
|
||||
the corruption of the integrity information itself. Therefore it
|
||||
can be considered to be below the noise level.
|
||||
|
||||
Trailing data can be safely ignored in most cases. In some cases,
|
||||
like that of user-added data, it is expected to be ignored. In those
|
||||
cases where a file containing trailing data must be rejected, the option
|
||||
'--trailing-error' can be used. *Note --trailing-error::.
|
||||
|
||||
|
||||
File: plzip.info, Node: Examples, Next: Problems, Prev: Trailing data, Up: Top
|
||||
|
||||
8 A small tutorial with examples
|
||||
********************************
|
||||
|
||||
WARNING! Even if plzip is bug-free, other causes may result in a corrupt
|
||||
compressed file (bugs in the system libraries, memory errors, etc).
|
||||
Therefore, if the data you are going to compress are important, give the
|
||||
'--keep' option to plzip and don't remove the original file until you
|
||||
verify the compressed file with a command like
|
||||
'plzip -cd file.lz | cmp file -'.
|
||||
|
||||
|
||||
Example 1: Replace a regular file with its compressed version 'file.lz'
|
||||
and show the compression ratio.
|
||||
|
||||
plzip -v file
|
||||
|
||||
|
||||
Example 2: Like example 1 but the created 'file.lz' has a block size of
|
||||
1 MiB. The compression ratio is not shown.
|
||||
|
||||
plzip -B 1MiB file
|
||||
|
||||
|
||||
Example 3: Restore a regular file from its compressed version
|
||||
'file.lz'. If the operation is successful, 'file.lz' is removed.
|
||||
|
||||
plzip -d file.lz
|
||||
|
||||
|
||||
Example 4: Verify the integrity of the compressed file 'file.lz' and
|
||||
show status.
|
||||
|
||||
plzip -tv file.lz
|
||||
|
||||
|
||||
Example 5: Compress a whole device in /dev/sdc and send the output to
|
||||
'file.lz'.
|
||||
|
||||
plzip -c /dev/sdc > file.lz
|
||||
|
||||
|
||||
Example 6: The right way of concatenating compressed files. *Note
|
||||
Trailing data::.
|
||||
|
||||
Don't do this
|
||||
cat file1.lz file2.lz file3.lz | plzip -d
|
||||
Do this instead
|
||||
plzip -cd file1.lz file2.lz file3.lz
|
||||
|
||||
|
||||
Example 7: Decompress 'file.lz' partially until 10 KiB of decompressed
|
||||
data are produced.
|
||||
|
||||
plzip -cd file.lz | dd bs=1024 count=10
|
||||
|
||||
|
||||
Example 8: Decompress 'file.lz' partially from decompressed byte 10000
|
||||
to decompressed byte 15000 (5000 bytes are produced).
|
||||
|
||||
plzip -cd file.lz | dd bs=1000 skip=10 count=5
|
||||
|
||||
|
||||
File: plzip.info, Node: Problems, Next: Concept index, Prev: Examples, Up: Top
|
||||
|
||||
9 Reporting bugs
|
||||
****************
|
||||
|
||||
There are probably bugs in plzip. There are certainly errors and
|
||||
|
|
@ -480,6 +590,7 @@ Concept index
|
|||
* Menu:
|
||||
|
||||
* bugs: Problems. (line 6)
|
||||
* examples: Examples. (line 6)
|
||||
* file format: File format. (line 6)
|
||||
* getting help: Problems. (line 6)
|
||||
* introduction: Introduction. (line 6)
|
||||
|
|
@ -488,6 +599,7 @@ Concept index
|
|||
* minimum file sizes: Minimum file sizes. (line 6)
|
||||
* options: Invoking plzip. (line 6)
|
||||
* program design: Program design. (line 6)
|
||||
* trailing data: Trailing data. (line 6)
|
||||
* usage: Invoking plzip. (line 6)
|
||||
* version: Invoking plzip. (line 6)
|
||||
|
||||
|
|
@ -495,15 +607,19 @@ Concept index
|
|||
|
||||
Tag Table:
|
||||
Node: Top221
|
||||
Node: Introduction984
|
||||
Node: Invoking plzip5332
|
||||
Ref: --data-size5747
|
||||
Node: Program design10972
|
||||
Node: File format12560
|
||||
Node: Memory requirements14973
|
||||
Node: Minimum file sizes16085
|
||||
Node: Problems18007
|
||||
Node: Concept index18543
|
||||
Node: Introduction1101
|
||||
Node: Invoking plzip5078
|
||||
Ref: --trailing-error5647
|
||||
Ref: --data-size5890
|
||||
Node: Program design11683
|
||||
Node: File format13270
|
||||
Node: Memory requirements15702
|
||||
Node: Minimum file sizes16811
|
||||
Node: Trailing data18737
|
||||
Node: Examples20121
|
||||
Ref: concat-example21286
|
||||
Node: Problems21823
|
||||
Node: Concept index22349
|
||||
|
||||
End Tag Table
|
||||
|
||||
|
|
|
|||
211
doc/plzip.texi
211
doc/plzip.texi
|
|
@ -6,8 +6,8 @@
|
|||
@finalout
|
||||
@c %**end of header
|
||||
|
||||
@set UPDATED 9 July 2015
|
||||
@set VERSION 1.4
|
||||
@set UPDATED 14 May 2016
|
||||
@set VERSION 1.5
|
||||
|
||||
@dircategory Data Compression
|
||||
@direntry
|
||||
|
|
@ -41,12 +41,14 @@ This manual is for Plzip (version @value{VERSION}, @value{UPDATED}).
|
|||
* File format:: Detailed format of the compressed file
|
||||
* Memory requirements:: Memory required to compress and decompress
|
||||
* Minimum file sizes:: Minimum file sizes required for full speed
|
||||
* Trailing data:: Extra data appended to the file
|
||||
* Examples:: A small tutorial with examples
|
||||
* Problems:: Reporting bugs
|
||||
* Concept index:: Index of concepts
|
||||
@end menu
|
||||
|
||||
@sp 1
|
||||
Copyright @copyright{} 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright @copyright{} 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This manual is free documentation: you have unlimited permission
|
||||
to copy, distribute and modify it.
|
||||
|
|
@ -83,7 +85,7 @@ program can repair bit-flip errors (one of the most common forms of data
|
|||
corruption) in lzip files, and provides data recovery capabilities,
|
||||
including error-checked merging of damaged copies of a file.
|
||||
@ifnothtml
|
||||
@ref{Data safety,,,lziprecover}.
|
||||
@xref{Data safety,,,lziprecover}.
|
||||
@end ifnothtml
|
||||
|
||||
@item
|
||||
|
|
@ -144,13 +146,6 @@ or more compressed files. The result is the concatenation of the
|
|||
corresponding uncompressed files. Integrity testing of concatenated
|
||||
compressed files is also supported.
|
||||
|
||||
WARNING! Even if plzip is bug-free, other causes may result in a corrupt
|
||||
compressed file (bugs in the system libraries, memory errors, etc).
|
||||
Therefore, if the data you are going to compress are important, give the
|
||||
@samp{--keep} option to plzip and do not remove the original file until
|
||||
you verify the compressed file with a command like
|
||||
@w{@samp{plzip -cd file.lz | cmp file -}}.
|
||||
|
||||
|
||||
@node Invoking plzip
|
||||
@chapter Invoking plzip
|
||||
|
|
@ -165,6 +160,11 @@ The format for running plzip is:
|
|||
plzip [@var{options}] [@var{files}]
|
||||
@end example
|
||||
|
||||
@noindent
|
||||
@samp{-} used as a @var{file} argument means standard input. It can be
|
||||
mixed with other @var{files} and is read just once, the first time it
|
||||
appears in the command line.
|
||||
|
||||
Plzip supports the following options:
|
||||
|
||||
@table @code
|
||||
|
|
@ -176,6 +176,13 @@ Print an informative help message describing the options and exit.
|
|||
@itemx --version
|
||||
Print the version number of plzip on the standard output and exit.
|
||||
|
||||
@anchor{--trailing-error}
|
||||
@item -a
|
||||
@itemx --trailing-error
|
||||
Exit with error status 2 if any remaining input is detected after
|
||||
decompressing the last member. Such remaining input is usually trailing
|
||||
garbage that can be safely ignored. @xref{concat-example}.
|
||||
|
||||
@anchor{--data-size}
|
||||
@item -B @var{bytes}
|
||||
@itemx --data-size=@var{bytes}
|
||||
|
|
@ -188,12 +195,17 @@ data size.
|
|||
|
||||
@item -c
|
||||
@itemx --stdout
|
||||
Compress or decompress to standard output. Needed when reading from a
|
||||
named pipe (fifo) or from a device.
|
||||
Compress or decompress to standard output; keep input files unchanged.
|
||||
If compressing several files, each file is compressed independently.
|
||||
This option is needed when reading from a named pipe (fifo) or from a
|
||||
device.
|
||||
|
||||
@item -d
|
||||
@itemx --decompress
|
||||
Decompress.
|
||||
Decompress the specified file(s). If a file does not exist or can't be
|
||||
opened, plzip continues decompressing the rest of the files. If a file
|
||||
fails to decompress, plzip exits immediately without decompressing the
|
||||
rest of the files.
|
||||
|
||||
@item -f
|
||||
@itemx --force
|
||||
|
|
@ -238,11 +250,13 @@ Quiet operation. Suppress all messages.
|
|||
|
||||
@item -s @var{bytes}
|
||||
@itemx --dictionary-size=@var{bytes}
|
||||
Set the dictionary size limit in bytes. Valid values range from 4 KiB to
|
||||
512 MiB. Plzip will use the smallest possible dictionary size for each
|
||||
file without exceeding this limit. Note that dictionary sizes are
|
||||
quantized. If the specified size does not match one of the valid sizes,
|
||||
it will be rounded upwards by adding up to (@var{bytes} / 16) to it.
|
||||
Set the dictionary size limit in bytes. Plzip will use the smallest
|
||||
possible dictionary size for each file without exceeding this limit.
|
||||
Valid values range from 4 KiB to 512 MiB. Values 12 to 29 are
|
||||
interpreted as powers of two, meaning 2^12 to 2^29 bytes. Note that
|
||||
dictionary sizes are quantized. If the specified size does not match one
|
||||
of the valid sizes, it will be rounded upwards by adding up to
|
||||
@w{(@var{bytes} / 8)} to it.
|
||||
|
||||
For maximum compression you should use a dictionary size limit as large
|
||||
as possible, but keep in mind that the decompression memory requirement
|
||||
|
|
@ -252,7 +266,9 @@ is affected at compression time by the choice of dictionary size limit.
|
|||
@itemx --test
|
||||
Check integrity of the specified file(s), but don't decompress them.
|
||||
This really performs a trial decompression and throws away the result.
|
||||
Use it together with @samp{-v} to see information about the file.
|
||||
Use it together with @samp{-v} to see information about the file(s). If
|
||||
a file fails the test, plzip may be unable to check the rest of the
|
||||
files.
|
||||
|
||||
@item -v
|
||||
@itemx --verbose
|
||||
|
|
@ -265,14 +281,14 @@ decompressed size, and compressed size.
|
|||
|
||||
@item -0 .. -9
|
||||
Set the compression parameters (dictionary size and match length limit)
|
||||
as shown in the table below. Note that @samp{-9} can be much slower than
|
||||
@samp{-0}. These options have no effect when decompressing.
|
||||
as shown in the table below. The default compression level is @samp{-6}.
|
||||
Note that @samp{-9} can be much slower than @samp{-0}. These options
|
||||
have no effect when decompressing.
|
||||
|
||||
The bidimensional parameter space of LZMA can't be mapped to a linear
|
||||
scale optimal for all files. If your files are large, very repetitive,
|
||||
etc, you may need to use the @samp{--match-length} and
|
||||
@samp{--dictionary-size} options directly to achieve optimal
|
||||
performance.
|
||||
etc, you may need to use the @samp{--dictionary-size} and
|
||||
@samp{--match-length} options directly to achieve optimal performance.
|
||||
|
||||
@multitable {Level} {Dictionary size} {Match length limit}
|
||||
@item Level @tab Dictionary size @tab Match length limit
|
||||
|
|
@ -324,7 +340,7 @@ caused plzip to panic.
|
|||
|
||||
When compressing, plzip divides the input file into chunks and
|
||||
compresses as many chunks simultaneously as worker threads are chosen,
|
||||
creating a multi-member compressed file.
|
||||
creating a multimember compressed file.
|
||||
|
||||
When decompressing, plzip decompresses as many members simultaneously as
|
||||
worker threads are chosen. Files that were compressed with lzip will not
|
||||
|
|
@ -383,14 +399,14 @@ additional information before, between, or after them.
|
|||
Each member has the following structure:
|
||||
@verbatim
|
||||
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|
||||
| ID string | VN | DS | Lzma stream | CRC32 | Data size | Member size |
|
||||
| ID string | VN | DS | LZMA stream | CRC32 | Data size | Member size |
|
||||
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|
||||
@end verbatim
|
||||
|
||||
All multibyte values are stored in little endian order.
|
||||
|
||||
@table @samp
|
||||
@item ID string
|
||||
@item ID string (the "magic" bytes)
|
||||
A four byte string, identifying the lzip format, with the value "LZIP"
|
||||
(0x4C, 0x5A, 0x49, 0x50).
|
||||
|
||||
|
|
@ -407,8 +423,8 @@ from the base size to obtain the dictionary size.@*
|
|||
Example: 0xD3 = 2^19 - 6 * 2^15 = 512 KiB - 6 * 32 KiB = 320 KiB@*
|
||||
Valid values for dictionary size range from 4 KiB to 512 MiB.
|
||||
|
||||
@item Lzma stream
|
||||
The lzma stream, finished by an end of stream marker. Uses default
|
||||
@item LZMA stream
|
||||
The LZMA stream, finished by an end of stream marker. Uses default
|
||||
values for encoder properties.
|
||||
@ifnothtml
|
||||
@xref{Stream format,,,lzip},
|
||||
|
|
@ -428,7 +444,7 @@ Size of the uncompressed original data.
|
|||
@item Member size (8 bytes)
|
||||
Total size of the member, including header and trailer. This field acts
|
||||
as a distributed index, allows the verification of stream integrity, and
|
||||
facilitates safe recovery of undamaged members from multi-member files.
|
||||
facilitates safe recovery of undamaged members from multimember files.
|
||||
|
||||
@end table
|
||||
|
||||
|
|
@ -453,8 +469,8 @@ times the data size. Default is 136 MiB.
|
|||
For decompression of a regular (seekable) file to another regular file,
|
||||
or for testing of a regular file; the dictionary size.
|
||||
|
||||
(Note that regular files with more than 1024 bytes of trailing garbage
|
||||
are treated as non-seekable).
|
||||
(Note that regular files with more than 1024 bytes of trailing data are
|
||||
treated as non-seekable).
|
||||
|
||||
@item
|
||||
For testing of a non-seekable file or of standard input; the dictionary
|
||||
|
|
@ -476,7 +492,7 @@ dictionary size plus up to 35 MiB.
|
|||
|
||||
When compressing, plzip divides the input file into chunks and
|
||||
compresses as many chunks simultaneously as worker threads are chosen,
|
||||
creating a multi-member compressed file.
|
||||
creating a multimember compressed file.
|
||||
|
||||
For this to work as expected (and roughly multiply the compression speed
|
||||
by the number of available processors), the uncompressed file must be at
|
||||
|
|
@ -506,6 +522,133 @@ data size for each level:
|
|||
@end multitable
|
||||
|
||||
|
||||
@node Trailing data
|
||||
@chapter Extra data appended to the file
|
||||
@cindex trailing data
|
||||
|
||||
Sometimes extra data is found appended to a lzip file after the last
|
||||
member. Such trailing data may be:
|
||||
|
||||
@itemize @bullet
|
||||
@item
|
||||
Padding added to make the file size a multiple of some block size, for
|
||||
example when writing to a tape.
|
||||
|
||||
@item
|
||||
Garbage added by some not totally successful copy operation.
|
||||
|
||||
@item
|
||||
Useful data added by the user; a cryptographically secure hash, a
|
||||
description of file contents, etc.
|
||||
|
||||
@item
|
||||
Malicious data added to the file in order to make its total size and
|
||||
hash value (for a chosen hash) coincide with those of another file.
|
||||
|
||||
@item
|
||||
In very rare cases, trailing data could be the corrupt header of another
|
||||
member. In multimember or concatenated files the probability of
|
||||
corruption happening in the magic bytes is 5 times smaller than the
|
||||
probability of getting a false positive caused by the corruption of the
|
||||
integrity information itself. Therefore it can be considered to be below
|
||||
the noise level.
|
||||
@end itemize
|
||||
|
||||
Trailing data can be safely ignored in most cases. In some cases, like
|
||||
that of user-added data, it is expected to be ignored. In those cases
|
||||
where a file containing trailing data must be rejected, the option
|
||||
@samp{--trailing-error} can be used. @xref{--trailing-error}.
|
||||
|
||||
|
||||
@node Examples
|
||||
@chapter A small tutorial with examples
|
||||
@cindex examples
|
||||
|
||||
WARNING! Even if plzip is bug-free, other causes may result in a corrupt
|
||||
compressed file (bugs in the system libraries, memory errors, etc).
|
||||
Therefore, if the data you are going to compress are important, give the
|
||||
@samp{--keep} option to plzip and don't remove the original file until
|
||||
you verify the compressed file with a command like
|
||||
@w{@samp{plzip -cd file.lz | cmp file -}}.
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 1: Replace a regular file with its compressed version
|
||||
@samp{file.lz} and show the compression ratio.
|
||||
|
||||
@example
|
||||
plzip -v file
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 2: Like example 1 but the created @samp{file.lz} has a block
|
||||
size of 1 MiB. The compression ratio is not shown.
|
||||
|
||||
@example
|
||||
plzip -B 1MiB file
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 3: Restore a regular file from its compressed version
|
||||
@samp{file.lz}. If the operation is successful, @samp{file.lz} is
|
||||
removed.
|
||||
|
||||
@example
|
||||
plzip -d file.lz
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 4: Verify the integrity of the compressed file @samp{file.lz}
|
||||
and show status.
|
||||
|
||||
@example
|
||||
plzip -tv file.lz
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 5: Compress a whole device in /dev/sdc and send the output to
|
||||
@samp{file.lz}.
|
||||
|
||||
@example
|
||||
plzip -c /dev/sdc > file.lz
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@anchor{concat-example}
|
||||
@noindent
|
||||
Example 6: The right way of concatenating compressed files.
|
||||
@xref{Trailing data}.
|
||||
|
||||
@example
|
||||
Don't do this
|
||||
cat file1.lz file2.lz file3.lz | plzip -d
|
||||
Do this instead
|
||||
plzip -cd file1.lz file2.lz file3.lz
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 7: Decompress @samp{file.lz} partially until 10 KiB of
|
||||
decompressed data are produced.
|
||||
|
||||
@example
|
||||
plzip -cd file.lz | dd bs=1024 count=10
|
||||
@end example
|
||||
|
||||
@sp 1
|
||||
@noindent
|
||||
Example 8: Decompress @samp{file.lz} partially from decompressed byte
|
||||
10000 to decompressed byte 15000 (5000 bytes are produced).
|
||||
|
||||
@example
|
||||
plzip -cd file.lz | dd bs=1000 skip=10 count=5
|
||||
@end example
|
||||
|
||||
|
||||
@node Problems
|
||||
@chapter Reporting bugs
|
||||
@cindex bugs
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -50,11 +50,11 @@ void File_index::set_num_error( const char * const msg1, unsigned long long num,
|
|||
char buf[80];
|
||||
snprintf( buf, sizeof buf, "%s%llu%s", msg1, num, msg2 );
|
||||
error_ = buf;
|
||||
retval_ = member_vector.empty() ? 1 : 2; // maybe trailing garbage
|
||||
retval_ = member_vector.empty() ? 1 : 2; // maybe trailing data
|
||||
}
|
||||
|
||||
|
||||
File_index::File_index( const int infd )
|
||||
File_index::File_index( const int infd, const bool ignore_garbage )
|
||||
: retval_( 0 )
|
||||
{
|
||||
const long long isize = lseek( infd, 0, SEEK_END );
|
||||
|
|
@ -88,7 +88,10 @@ File_index::File_index( const int infd )
|
|||
if( member_size < min_member_size || member_size > pos )
|
||||
{
|
||||
if( member_vector.empty() && isize - pos < max_garbage )
|
||||
{ --pos; continue; } // maybe trailing garbage
|
||||
{
|
||||
if( ignore_garbage ) { --pos; continue; } // maybe trailing data
|
||||
error_ = "Trailing data not allowed."; retval_ = 2; return;
|
||||
}
|
||||
set_num_error( "Member size in trailer is corrupt at pos ", pos - 8 );
|
||||
break;
|
||||
}
|
||||
|
|
@ -98,7 +101,10 @@ File_index::File_index( const int infd )
|
|||
if( !header.verify_magic() || !header.verify_version() )
|
||||
{
|
||||
if( member_vector.empty() && isize - pos < max_garbage )
|
||||
{ --pos; continue; } // maybe trailing garbage
|
||||
{
|
||||
if( ignore_garbage ) { --pos; continue; } // maybe trailing data
|
||||
error_ = "Trailing data not allowed."; retval_ = 2; return;
|
||||
}
|
||||
set_num_error( "Bad header at pos ", pos - member_size );
|
||||
break;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -57,7 +57,7 @@ class File_index
|
|||
const char * const msg2 = "" );
|
||||
|
||||
public:
|
||||
explicit File_index( const int infd );
|
||||
File_index( const int infd, const bool ignore_garbage );
|
||||
|
||||
long members() const { return member_vector.size(); }
|
||||
const std::string & error() const { return error_; }
|
||||
|
|
|
|||
37
lzip.h
37
lzip.h
|
|
@ -1,5 +1,5 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -15,6 +15,10 @@
|
|||
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
*/
|
||||
|
||||
#ifndef LZ_API_VERSION
|
||||
#define LZ_API_VERSION 1
|
||||
#endif
|
||||
|
||||
enum {
|
||||
min_dictionary_bits = 12,
|
||||
min_dictionary_size = 1 << min_dictionary_bits,
|
||||
|
|
@ -31,9 +35,11 @@ class Pretty_print
|
|||
mutable bool first_post;
|
||||
|
||||
public:
|
||||
explicit Pretty_print( const std::vector< std::string > & filenames )
|
||||
Pretty_print( const std::vector< std::string > & filenames,
|
||||
const int verbosity )
|
||||
: stdin_name( "(stdin)" ), longest_name( 0 ), first_post( false )
|
||||
{
|
||||
if( verbosity <= 0 ) return;
|
||||
const unsigned stdin_name_len = std::strlen( stdin_name );
|
||||
for( unsigned i = 0; i < filenames.size(); ++i )
|
||||
{
|
||||
|
|
@ -57,6 +63,11 @@ public:
|
|||
};
|
||||
|
||||
|
||||
inline bool isvalid_ds( const unsigned dictionary_size )
|
||||
{ return ( dictionary_size >= min_dictionary_size &&
|
||||
dictionary_size <= max_dictionary_size ); }
|
||||
|
||||
|
||||
inline int real_bits( unsigned value )
|
||||
{
|
||||
int bits = 0;
|
||||
|
|
@ -91,8 +102,7 @@ struct File_header
|
|||
|
||||
bool dictionary_size( const unsigned sz )
|
||||
{
|
||||
if( sz >= min_dictionary_size && sz <= max_dictionary_size )
|
||||
{
|
||||
if( !isvalid_ds( sz ) ) return false;
|
||||
data[5] = real_bits( sz - 1 );
|
||||
if( sz > min_dictionary_size )
|
||||
{
|
||||
|
|
@ -104,8 +114,6 @@ struct File_header
|
|||
}
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
};
|
||||
|
||||
|
||||
|
|
@ -152,10 +160,10 @@ struct File_trailer
|
|||
// defined in compress.cc
|
||||
int readblock( const int fd, uint8_t * const buf, const int size );
|
||||
int writeblock( const int fd, const uint8_t * const buf, const int size );
|
||||
void xinit( pthread_mutex_t * const mutex );
|
||||
void xinit( pthread_cond_t * const cond );
|
||||
void xdestroy( pthread_mutex_t * const mutex );
|
||||
void xdestroy( pthread_cond_t * const cond );
|
||||
void xinit_mutex( pthread_mutex_t * const mutex );
|
||||
void xinit_cond( pthread_cond_t * const cond );
|
||||
void xdestroy_mutex( pthread_mutex_t * const mutex );
|
||||
void xdestroy_cond( pthread_cond_t * const cond );
|
||||
void xlock( pthread_mutex_t * const mutex );
|
||||
void xunlock( pthread_mutex_t * const mutex );
|
||||
void xwait( pthread_cond_t * const cond, pthread_mutex_t * const mutex );
|
||||
|
|
@ -176,7 +184,8 @@ int dec_stdout( const int num_workers, const int infd, const int outfd,
|
|||
|
||||
// defined in dec_stream.cc
|
||||
int dec_stream( const int num_workers, const int infd, const int outfd,
|
||||
const Pretty_print & pp, const int debug_level );
|
||||
const Pretty_print & pp, const int debug_level,
|
||||
const bool ignore_garbage );
|
||||
|
||||
// defined in decompress.cc
|
||||
int preadblock( const int fd, uint8_t * const buf, const int size,
|
||||
|
|
@ -187,7 +196,7 @@ int decompress_read_error( struct LZ_Decoder * const decoder,
|
|||
const Pretty_print & pp, const int worker_id );
|
||||
int decompress( int num_workers, const int infd, const int outfd,
|
||||
const Pretty_print & pp, const int debug_level,
|
||||
const bool infd_isreg );
|
||||
const bool ignore_garbage, const bool infd_isreg );
|
||||
|
||||
// defined in main.cc
|
||||
extern int verbosity;
|
||||
|
|
@ -214,9 +223,9 @@ class Slot_tally
|
|||
public:
|
||||
explicit Slot_tally( const int slots )
|
||||
: num_slots( slots ), num_free( slots )
|
||||
{ xinit( &mutex ); xinit( &slot_av ); }
|
||||
{ xinit_mutex( &mutex ); xinit_cond( &slot_av ); }
|
||||
|
||||
~Slot_tally() { xdestroy( &slot_av ); xdestroy( &mutex ); }
|
||||
~Slot_tally() { xdestroy_cond( &slot_av ); xdestroy_mutex( &mutex ); }
|
||||
|
||||
bool all_free() { return ( num_free == num_slots ); }
|
||||
|
||||
|
|
|
|||
110
main.cc
110
main.cc
|
|
@ -1,6 +1,6 @@
|
|||
/* Plzip - Parallel compressor compatible with lzip
|
||||
Copyright (C) 2009 Laszlo Ersek.
|
||||
Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
|
|
@ -67,12 +67,13 @@
|
|||
#error "Environments where CHAR_BIT != 8 are not supported."
|
||||
#endif
|
||||
|
||||
int verbosity = 0;
|
||||
|
||||
namespace {
|
||||
|
||||
const char * const Program_name = "Plzip";
|
||||
const char * const program_name = "plzip";
|
||||
const char * const program_year = "2015";
|
||||
const char * const program_year = "2016";
|
||||
const char * invocation_name = 0;
|
||||
|
||||
struct { const char * from; const char * to; } const known_extensions[] = {
|
||||
|
|
@ -90,9 +91,6 @@ enum Mode { m_compress, m_decompress, m_test };
|
|||
|
||||
std::string output_filename;
|
||||
int outfd = -1;
|
||||
const mode_t usr_rw = S_IRUSR | S_IWUSR;
|
||||
const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
|
||||
mode_t outfd_mode = usr_rw;
|
||||
bool delete_output_on_interrupt = false;
|
||||
|
||||
|
||||
|
|
@ -103,15 +101,16 @@ void show_help( const long num_online )
|
|||
std::printf( "\nOptions:\n"
|
||||
" -h, --help display this help and exit\n"
|
||||
" -V, --version output version information and exit\n"
|
||||
" -a, --trailing-error exit with error status if trailing data\n"
|
||||
" -B, --data-size=<bytes> set size of input data blocks [2x8=16 MiB]\n"
|
||||
" -c, --stdout send output to standard output\n"
|
||||
" -c, --stdout write to standard output, keep input files\n"
|
||||
" -d, --decompress decompress\n"
|
||||
" -f, --force overwrite existing output files\n"
|
||||
" -F, --recompress force re-compression of compressed files\n"
|
||||
" -k, --keep keep (don't delete) input files\n"
|
||||
" -m, --match-length=<bytes> set match length limit in bytes [36]\n"
|
||||
" -n, --threads=<n> set number of (de)compression threads [%ld]\n"
|
||||
" -o, --output=<file> if reading stdin, place the output into <file>\n"
|
||||
" -o, --output=<file> if reading standard input, write to <file>\n"
|
||||
" -q, --quiet suppress all messages\n"
|
||||
" -s, --dictionary-size=<bytes> set dictionary size limit in bytes [8 MiB]\n"
|
||||
" -t, --test test compressed file integrity\n"
|
||||
|
|
@ -123,13 +122,15 @@ void show_help( const long num_online )
|
|||
{
|
||||
std::printf( " -D, --debug=<level> (0-1) print debug statistics to stderr\n" );
|
||||
}
|
||||
std::printf( "If no file names are given, plzip compresses or decompresses\n"
|
||||
"from standard input to standard output.\n"
|
||||
std::printf( "If no file names are given, or if a file is '-', plzip compresses or\n"
|
||||
"decompresses from standard input to standard output.\n"
|
||||
"Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n"
|
||||
"Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n"
|
||||
"The bidimensional parameter space of LZMA can't be mapped to a linear\n"
|
||||
"Dictionary sizes 12 to 29 are interpreted as powers of two, meaning 2^12\n"
|
||||
"to 2^29 bytes.\n"
|
||||
"\nThe bidimensional parameter space of LZMA can't be mapped to a linear\n"
|
||||
"scale optimal for all files. If your files are large, very repetitive,\n"
|
||||
"etc, you may need to use the --match-length and --dictionary-size\n"
|
||||
"etc, you may need to use the --dictionary-size and --match-length\n"
|
||||
"options directly to achieve optimal performance.\n"
|
||||
"\nExit status: 0 for a normal exit, 1 for environmental problems (file\n"
|
||||
"not found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or\n"
|
||||
|
|
@ -190,11 +191,9 @@ unsigned long long getnum( const char * const ptr,
|
|||
if( !errno && tail[0] )
|
||||
{
|
||||
const int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
|
||||
int exponent = 0;
|
||||
bool bad_multiplier = false;
|
||||
int exponent = 0; // 0 = bad multiplier
|
||||
switch( tail[0] )
|
||||
{
|
||||
case ' ': break;
|
||||
case 'Y': exponent = 8; break;
|
||||
case 'Z': exponent = 7; break;
|
||||
case 'E': exponent = 6; break;
|
||||
|
|
@ -202,13 +201,10 @@ unsigned long long getnum( const char * const ptr,
|
|||
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;
|
||||
case 'K': if( factor == 1024 ) exponent = 1; break;
|
||||
case 'k': if( factor == 1000 ) exponent = 1; break;
|
||||
}
|
||||
if( bad_multiplier )
|
||||
if( exponent <= 0 )
|
||||
{
|
||||
show_error( "Bad multiplier in numerical argument.", 0, true );
|
||||
std::exit( 1 );
|
||||
|
|
@ -238,7 +234,7 @@ int get_dict_size( const char * const arg )
|
|||
return ( 1 << bits );
|
||||
int dictionary_size = getnum( arg, LZ_min_dictionary_size(),
|
||||
LZ_max_dictionary_size() );
|
||||
if( dictionary_size == 65535 ) ++dictionary_size;
|
||||
if( dictionary_size == 65535 ) ++dictionary_size; // no fast encoder
|
||||
return dictionary_size;
|
||||
}
|
||||
|
||||
|
|
@ -283,7 +279,7 @@ int open_instream( const char * const name, struct stat * const in_statsp,
|
|||
const bool can_read = ( i == 0 &&
|
||||
( S_ISBLK( mode ) || S_ISCHR( mode ) ||
|
||||
S_ISFIFO( mode ) || S_ISSOCK( mode ) ) );
|
||||
const bool no_ofile = to_stdout || program_mode == m_test;
|
||||
const bool no_ofile = ( to_stdout || program_mode == m_test );
|
||||
if( i != 0 || ( !S_ISREG( mode ) && ( !can_read || !no_ofile ) ) )
|
||||
{
|
||||
if( verbosity >= 0 )
|
||||
|
|
@ -326,13 +322,17 @@ void set_d_outname( const std::string & name, const int i )
|
|||
}
|
||||
|
||||
|
||||
bool open_outstream( const bool force )
|
||||
bool open_outstream( const bool force, const bool from_stdin )
|
||||
{
|
||||
const mode_t usr_rw = S_IRUSR | S_IWUSR;
|
||||
const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
|
||||
const mode_t outfd_mode = from_stdin ? all_rw : usr_rw;
|
||||
int flags = O_CREAT | O_WRONLY | O_BINARY;
|
||||
if( force ) flags |= O_TRUNC; else flags |= O_EXCL;
|
||||
|
||||
outfd = open( output_filename.c_str(), flags, outfd_mode );
|
||||
if( outfd < 0 && verbosity >= 0 )
|
||||
if( outfd >= 0 ) delete_output_on_interrupt = true;
|
||||
else if( verbosity >= 0 )
|
||||
{
|
||||
if( errno == EEXIST )
|
||||
std::fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n",
|
||||
|
|
@ -403,7 +403,11 @@ void close_and_set_permissions( const struct stat * const in_statsp )
|
|||
fchmod( outfd, mode & ~( S_ISUID | S_ISGID | S_ISVTX ) ) != 0 )
|
||||
warning = true;
|
||||
}
|
||||
if( close( outfd ) != 0 ) cleanup_and_fail( 1 );
|
||||
if( close( outfd ) != 0 )
|
||||
{
|
||||
show_error( "Error closing output file", errno );
|
||||
cleanup_and_fail( 1 );
|
||||
}
|
||||
outfd = -1;
|
||||
delete_output_on_interrupt = false;
|
||||
if( in_statsp )
|
||||
|
|
@ -435,25 +439,19 @@ void set_signals()
|
|||
} // end namespace
|
||||
|
||||
|
||||
int verbosity = 0;
|
||||
|
||||
|
||||
void show_error( const char * const msg, const int errcode, const bool help )
|
||||
{
|
||||
if( verbosity >= 0 )
|
||||
{
|
||||
if( verbosity < 0 ) return;
|
||||
if( msg && msg[0] )
|
||||
{
|
||||
std::fprintf( stderr, "%s: %s", program_name, msg );
|
||||
if( errcode > 0 )
|
||||
std::fprintf( stderr, ": %s", std::strerror( errcode ) );
|
||||
if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) );
|
||||
std::fputc( '\n', stderr );
|
||||
}
|
||||
if( help )
|
||||
std::fprintf( stderr, "Try '%s --help' for more information.\n",
|
||||
invocation_name );
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
void internal_error( const char * const msg )
|
||||
|
|
@ -473,8 +471,7 @@ void show_progress( const int packet_size,
|
|||
static const Pretty_print * pp = 0;
|
||||
static pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
|
||||
|
||||
if( verbosity >= 2 )
|
||||
{
|
||||
if( verbosity < 2 ) return;
|
||||
if( p ) // initialize static vars
|
||||
{ csize = cfile_size; pos = 0; pp = p; }
|
||||
if( pp )
|
||||
|
|
@ -488,7 +485,6 @@ void show_progress( const int packet_size,
|
|||
xunlock( &mutex );
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
int main( const int argc, const char * const argv[] )
|
||||
|
|
@ -497,7 +493,7 @@ int main( const int argc, const char * const argv[] )
|
|||
to the corresponding LZMA compression modes. */
|
||||
const Lzma_options option_mapping[] =
|
||||
{
|
||||
{ 65535, 16 }, // -0
|
||||
{ 65535, 16 }, // -0 (65535,16 chooses fast encoder)
|
||||
{ 1 << 20, 5 }, // -1
|
||||
{ 3 << 19, 6 }, // -2
|
||||
{ 1 << 21, 8 }, // -3
|
||||
|
|
@ -517,13 +513,15 @@ int main( const int argc, const char * const argv[] )
|
|||
int num_workers = 0; // start this many worker threads
|
||||
Mode program_mode = m_compress;
|
||||
bool force = false;
|
||||
bool ignore_trailing = true;
|
||||
bool keep_input_files = false;
|
||||
bool recompress = false;
|
||||
bool to_stdout = false;
|
||||
invocation_name = argv[0];
|
||||
|
||||
if( LZ_version()[0] != LZ_version_string[0] )
|
||||
internal_error( "bad library version." );
|
||||
if( LZ_version()[0] < '1' )
|
||||
{ show_error( "Bad library version. At least lzlib 1.0 is required." );
|
||||
return 1; }
|
||||
|
||||
const long num_online = std::max( 1L, sysconf( _SC_NPROCESSORS_ONLN ) );
|
||||
long max_workers = sysconf( _SC_THREAD_THREADS_MAX );
|
||||
|
|
@ -542,6 +540,7 @@ int main( const int argc, const char * const argv[] )
|
|||
{ '7', 0, Arg_parser::no },
|
||||
{ '8', 0, Arg_parser::no },
|
||||
{ '9', "best", Arg_parser::no },
|
||||
{ 'a', "trailing-error", Arg_parser::no },
|
||||
{ 'b', "member-size", Arg_parser::yes },
|
||||
{ 'B', "data-size", Arg_parser::yes },
|
||||
{ 'c', "stdout", Arg_parser::no },
|
||||
|
|
@ -572,28 +571,30 @@ int main( const int argc, const char * const argv[] )
|
|||
const int code = parser.code( argind );
|
||||
if( !code ) break; // no more options
|
||||
const std::string & arg = parser.argument( argind );
|
||||
const char * const ptr = arg.c_str();
|
||||
switch( code )
|
||||
{
|
||||
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;
|
||||
case 'a': ignore_trailing = false; break;
|
||||
case 'b': break;
|
||||
case 'B': data_size = getnum( arg.c_str(), 2 * LZ_min_dictionary_size(),
|
||||
case 'B': data_size = getnum( ptr, 2 * LZ_min_dictionary_size(),
|
||||
2 * LZ_max_dictionary_size() ); break;
|
||||
case 'c': to_stdout = true; break;
|
||||
case 'd': program_mode = m_decompress; break;
|
||||
case 'D': debug_level = getnum( arg.c_str(), 0, 3 ); break;
|
||||
case 'D': debug_level = getnum( ptr, 0, 3 ); break;
|
||||
case 'f': force = true; break;
|
||||
case 'F': recompress = true; break;
|
||||
case 'h': show_help( num_online ); return 0;
|
||||
case 'k': keep_input_files = true; break;
|
||||
case 'm': encoder_options.match_len_limit =
|
||||
getnum( arg.c_str(), LZ_min_match_len_limit(),
|
||||
getnum( ptr, LZ_min_match_len_limit(),
|
||||
LZ_max_match_len_limit() ); break;
|
||||
case 'n': num_workers = getnum( arg.c_str(), 1, max_workers ); break;
|
||||
case 'n': num_workers = getnum( ptr, 1, max_workers ); break;
|
||||
case 'o': default_output_filename = arg; break;
|
||||
case 'q': verbosity = -1; break;
|
||||
case 's': encoder_options.dictionary_size = get_dict_size( arg.c_str() );
|
||||
case 's': encoder_options.dictionary_size = get_dict_size( ptr );
|
||||
break;
|
||||
case 'S': break;
|
||||
case 't': program_mode = m_test; break;
|
||||
|
|
@ -637,9 +638,10 @@ int main( const int argc, const char * const argv[] )
|
|||
( filenames_given || default_output_filename.size() ) )
|
||||
set_signals();
|
||||
|
||||
Pretty_print pp( filenames );
|
||||
Pretty_print pp( filenames, verbosity );
|
||||
|
||||
int retval = 0;
|
||||
bool stdin_used = false;
|
||||
for( unsigned i = 0; i < filenames.size(); ++i )
|
||||
{
|
||||
struct stat in_stats;
|
||||
|
|
@ -647,6 +649,7 @@ int main( const int argc, const char * const argv[] )
|
|||
|
||||
if( filenames[i].empty() || filenames[i] == "-" )
|
||||
{
|
||||
if( stdin_used ) continue; else stdin_used = true;
|
||||
input_filename.clear();
|
||||
infd = STDIN_FILENO;
|
||||
if( program_mode != m_test )
|
||||
|
|
@ -658,8 +661,7 @@ int main( const int argc, const char * const argv[] )
|
|||
if( program_mode == m_compress )
|
||||
set_c_outname( default_output_filename );
|
||||
else output_filename = default_output_filename;
|
||||
outfd_mode = all_rw;
|
||||
if( !open_outstream( force ) )
|
||||
if( !open_outstream( force, true ) )
|
||||
{
|
||||
if( retval < 1 ) retval = 1;
|
||||
close( infd ); infd = -1;
|
||||
|
|
@ -683,8 +685,7 @@ int main( const int argc, const char * const argv[] )
|
|||
if( program_mode == m_compress )
|
||||
set_c_outname( input_filename );
|
||||
else set_d_outname( input_filename, eindex );
|
||||
outfd_mode = usr_rw;
|
||||
if( !open_outstream( force ) )
|
||||
if( !open_outstream( force, false ) )
|
||||
{
|
||||
if( retval < 1 ) retval = 1;
|
||||
close( infd ); infd = -1;
|
||||
|
|
@ -694,10 +695,12 @@ int main( const int argc, const char * const argv[] )
|
|||
}
|
||||
}
|
||||
|
||||
if( !check_tty( infd, program_mode ) ) return 1;
|
||||
if( !check_tty( infd, program_mode ) )
|
||||
{
|
||||
if( retval < 1 ) retval = 1;
|
||||
cleanup_and_fail( retval );
|
||||
}
|
||||
|
||||
if( output_filename.size() && !to_stdout && program_mode != m_test )
|
||||
delete_output_on_interrupt = true;
|
||||
const struct stat * const in_statsp = input_filename.size() ? &in_stats : 0;
|
||||
const bool infd_isreg = in_statsp && S_ISREG( in_statsp->st_mode );
|
||||
pp.set_name( input_filename );
|
||||
|
|
@ -711,7 +714,8 @@ int main( const int argc, const char * const argv[] )
|
|||
num_workers, infd, outfd, pp, debug_level );
|
||||
}
|
||||
else
|
||||
tmp = decompress( num_workers, infd, outfd, pp, debug_level, infd_isreg );
|
||||
tmp = decompress( num_workers, infd, outfd, pp, debug_level,
|
||||
ignore_trailing, infd_isreg );
|
||||
if( tmp > retval ) retval = tmp;
|
||||
if( tmp && program_mode != m_test ) cleanup_and_fail( retval );
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
#! /bin/sh
|
||||
# check script for Plzip - Parallel compressor compatible with lzip
|
||||
# Copyright (C) 2009-2015 Antonio Diaz Diaz.
|
||||
# Copyright (C) 2009-2016 Antonio Diaz Diaz.
|
||||
#
|
||||
# This script is free software: you have unlimited permission
|
||||
# to copy, distribute and modify it.
|
||||
|
|
@ -17,9 +17,16 @@ if [ ! -f "${LZIP}" ] || [ ! -x "${LZIP}" ] ; then
|
|||
exit 1
|
||||
fi
|
||||
|
||||
if [ -e "${LZIP}" ] 2> /dev/null ; then true
|
||||
else
|
||||
echo "$0: a POSIX shell is required to run the tests"
|
||||
echo "Try bash -c \"$0 $1 $2\""
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ -d tmp ] ; then rm -rf tmp ; fi
|
||||
mkdir tmp
|
||||
cd "${objdir}"/tmp
|
||||
cd "${objdir}"/tmp || framework_failure
|
||||
|
||||
cat "${testdir}"/test.txt > in || framework_failure
|
||||
in_lz="${testdir}"/test.txt.lz
|
||||
|
|
@ -27,25 +34,22 @@ fail=0
|
|||
|
||||
printf "testing plzip-%s..." "$2"
|
||||
|
||||
"${LZIP}" -cqm4 in > /dev/null
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cqm274 in > /dev/null
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cqs-1 in > /dev/null
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cqs0 in > /dev/null
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cqs4095 in > /dev/null
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cqs513MiB in > /dev/null
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
printf " in: Bad magic number (file not in lzip format).\n" > msg
|
||||
"${LZIP}" -t in 2> out
|
||||
if [ $? = 2 ] && cmp out msg ; then printf . ; else printf - ; fail=1 ; fi
|
||||
printf " (stdin): Bad magic number (file not in lzip format).\n" > msg
|
||||
"${LZIP}" -t < in 2> out
|
||||
if [ $? = 2 ] && cmp out msg ; then printf . ; else printf - ; fail=1 ; fi
|
||||
rm -f out msg
|
||||
"${LZIP}" -fkqm4 in
|
||||
if [ $? = 1 ] && [ ! -e in.lz ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -fkqm274 in
|
||||
if [ $? = 1 ] && [ ! -e in.lz ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -fkqs-1 in
|
||||
if [ $? = 1 ] && [ ! -e in.lz ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -fkqs0 in
|
||||
if [ $? = 1 ] && [ ! -e in.lz ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -fkqs4095 in
|
||||
if [ $? = 1 ] && [ ! -e in.lz ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -fkqs513MiB in
|
||||
if [ $? = 1 ] && [ ! -e in.lz ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -tq in
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -tq < in
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cdq in
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cdq < in
|
||||
|
|
@ -55,26 +59,53 @@ if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
|||
dd if="${in_lz}" bs=1 count=20 2> /dev/null | "${LZIP}" -tq
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
|
||||
"${LZIP}" -t "${in_lz}" || fail=1
|
||||
printf "\ntesting decompression..."
|
||||
|
||||
"${LZIP}" -t "${in_lz}"
|
||||
if [ $? = 0 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cd "${in_lz}" > copy || fail=1
|
||||
cmp in copy || fail=1
|
||||
printf .
|
||||
|
||||
rm -f copy
|
||||
cat "${in_lz}" > copy.lz || framework_failure
|
||||
printf "to be overwritten" > copy || framework_failure
|
||||
"${LZIP}" -df copy.lz || fail=1
|
||||
"${LZIP}" -dk copy.lz || fail=1
|
||||
cmp in copy || fail=1
|
||||
printf .
|
||||
printf "to be overwritten" > copy || framework_failure
|
||||
"${LZIP}" -dq copy.lz
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -df copy.lz
|
||||
if [ $? = 0 ] && [ ! -e copy.lz ] && cmp in copy ; then
|
||||
printf . ; else printf - ; fail=1 ; fi
|
||||
|
||||
printf "to be overwritten" > copy || framework_failure
|
||||
"${LZIP}" -df -o copy < "${in_lz}" || fail=1
|
||||
cmp in copy || fail=1
|
||||
printf .
|
||||
|
||||
rm -f copy
|
||||
"${LZIP}" < in > anyothername || fail=1
|
||||
"${LZIP}" -d anyothername || fail=1
|
||||
cmp in anyothername.out || fail=1
|
||||
printf .
|
||||
"${LZIP}" -d -o copy - anyothername - < "${in_lz}"
|
||||
if [ $? = 0 ] && cmp in copy && cmp in anyothername.out ; then
|
||||
printf . ; else printf - ; fail=1 ; fi
|
||||
rm -f copy anyothername.out
|
||||
|
||||
"${LZIP}" -tq in "${in_lz}"
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -tq foo.lz "${in_lz}"
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cdq in "${in_lz}" > copy
|
||||
if [ $? = 2 ] && cat copy in | cmp in - ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cdq foo.lz "${in_lz}" > copy
|
||||
if [ $? = 1 ] && cmp in copy ; then printf . ; else printf - ; fail=1 ; fi
|
||||
rm -f copy
|
||||
cat "${in_lz}" > copy.lz || framework_failure
|
||||
"${LZIP}" -dq in copy.lz
|
||||
if [ $? = 2 ] && [ -e copy.lz ] && [ ! -e copy ] && [ ! -e in.out ] ; then
|
||||
printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -dq foo.lz copy.lz
|
||||
if [ $? = 1 ] && [ ! -e copy.lz ] && [ ! -e foo ] && cmp in copy ; then
|
||||
printf . ; else printf - ; fail=1 ; fi
|
||||
|
||||
cat in in > in2 || framework_failure
|
||||
"${LZIP}" -o copy2 < in2 || fail=1
|
||||
|
|
@ -84,12 +115,23 @@ cmp in2 copy2 || fail=1
|
|||
printf .
|
||||
|
||||
printf "garbage" >> copy2.lz || framework_failure
|
||||
rm -f copy2
|
||||
"${LZIP}" -atq copy2.lz
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -atq < copy2.lz
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -adkq copy2.lz
|
||||
if [ $? = 2 ] && [ ! -e copy2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -adkq -o copy2 < copy2.lz
|
||||
if [ $? = 2 ] && [ ! -e copy2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
printf "to be overwritten" > copy2 || framework_failure
|
||||
"${LZIP}" -df copy2.lz || fail=1
|
||||
cmp in2 copy2 || fail=1
|
||||
printf .
|
||||
|
||||
"${LZIP}" -cfq "${in_lz}" > out
|
||||
printf "\ntesting compression..."
|
||||
|
||||
"${LZIP}" -cfq "${in_lz}" > out # /dev/null is a tty on OS/2
|
||||
if [ $? = 1 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cF "${in_lz}" > out || fail=1
|
||||
"${LZIP}" -cd out | "${LZIP}" -d > copy || fail=1
|
||||
|
|
@ -162,10 +204,10 @@ printf .
|
|||
dd if="${in_lz}" bs=1024 count=6 > trunc.lz 2> /dev/null || framework_failure
|
||||
"${LZIP}" -tq trunc.lz
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cdq trunc.lz > out
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -tq < trunc.lz
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -cdq trunc.lz > out
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
"${LZIP}" -dq < trunc.lz > out
|
||||
if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue