diff options
| -rw-r--r-- | ChangeLog | 18 | ||||
| -rw-r--r-- | INSTALL | 24 | ||||
| -rw-r--r-- | Makefile.in | 7 | ||||
| -rw-r--r-- | NEWS | 17 | ||||
| -rw-r--r-- | README | 51 | ||||
| -rw-r--r-- | arg_parser.cc | 4 | ||||
| -rw-r--r-- | arg_parser.h | 4 | ||||
| -rw-r--r-- | compress.cc | 4 | ||||
| -rwxr-xr-x | configure | 31 | ||||
| -rw-r--r-- | dec_stdout.cc | 2 | ||||
| -rw-r--r-- | dec_stream.cc | 21 | ||||
| -rw-r--r-- | decompress.cc | 21 | ||||
| -rw-r--r-- | doc/plzip.1 | 50 | ||||
| -rw-r--r-- | doc/plzip.info | 234 | ||||
| -rw-r--r-- | doc/plzip.texi | 248 | ||||
| -rw-r--r-- | list.cc | 7 | ||||
| -rw-r--r-- | lzip.h | 69 | ||||
| -rw-r--r-- | lzip_index.cc | 82 | ||||
| -rw-r--r-- | lzip_index.h | 21 | ||||
| -rw-r--r-- | main.cc | 244 | ||||
| -rwxr-xr-x | testsuite/check.sh | 201 |
21 files changed, 728 insertions, 632 deletions
@@ -1,9 +1,18 @@ +2024-01-21 Antonio Diaz Diaz <antonio@gnu.org> + + * Version 1.11 released. + * main.cc: Reformat file diagnostics as 'PROGRAM: FILE: MESSAGE'. + (show_option_error): New function showing argument and option name. + (main): Make -o preserve date/mode/owner if 1 input file. + (open_outstream): Create missing intermediate directories. + * configure, Makefile.in: New variable 'MAKEINFO'. + 2022-01-24 Antonio Diaz Diaz <antonio@gnu.org> * Version 1.10 released. * main.cc (getnum): Show option name and valid range if error. (check_lib): Check that LZ_API_VERSION and LZ_version_string match. - * Set variable LIBS from configure. + * configure: Set variable LIBS. * Improve several descriptions in manual, '--help', and man page. * plzip.texi: Change GNU Texinfo category to 'Compression'. (Reported by Alfred M. Szmidt). @@ -220,8 +229,7 @@ until something better appears on the net. -Copyright (C) 2009-2022 Antonio Diaz Diaz. +Copyright (C) 2009-2024 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 -modify it. +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 modify it. @@ -1,17 +1,16 @@ Requirements ------------ -You will need a C++98 compiler with suport for 'long long', and the +You will need a C++98 compiler with support for 'long long', and the compression library lzlib installed. (gcc 3.3.6 or newer is recommended). I use gcc 6.1.0 and 3.3.6, but the code should compile with any standards compliant compiler. +Gcc is available at http://gcc.gnu.org. +Lzlib is available at http://www.nongnu.org/lzip/lzlib.html. Lzlib must be version 1.0 or newer, but the fast encoder requires lzlib 1.7 or newer, the Hamming distance (HD) = 3 detection of corrupt headers in -non-seekable multimember files requires lzlib 1.10 or newer, and the 'no -copy' optimization for testing requires lzlib 1.12 or newer. - -Gcc is available at http://gcc.gnu.org. -Lzlib is available at http://www.nongnu.org/lzip/lzlib.html. +non-seekable multimember files requires lzlib 1.10 or newer, and the +'no copy' optimization for testing requires lzlib 1.12 or newer. The operating system must allow signal handlers read access to objects with static storage duration so that the cleanup handler for Control-C can delete @@ -26,8 +25,8 @@ Procedure or lzip -cd plzip[version].tar.lz | tar -xf - -This creates the directory ./plzip[version] containing the source from -the main archive. +This creates the directory ./plzip[version] containing the source code +extracted from the archive. 2. Change to plzip directory and run configure. (Try 'configure --help' for usage instructions). @@ -54,7 +53,8 @@ the main archive. 4. Optionally, type 'make check' to run the tests that come with plzip. 5. Type 'make install' to install the program and any data files and - documentation. + documentation. You need root privileges to install into a prefix owned + by root. Or type 'make install-compress', which additionally compresses the info manual and the man page after installation. @@ -78,15 +78,15 @@ object files and executables to go and run the 'configure' script. 'configure' automatically checks for the source code in '.', in '..', and in the directory that 'configure' is in. -'configure' recognizes the option '--srcdir=DIR' to control where to -look for the sources. Usually 'configure' can determine that directory +'configure' recognizes the option '--srcdir=DIR' to control where to look +for the source code. Usually 'configure' can determine that directory automatically. After running 'configure', you can run 'make' and 'make install' as explained above. -Copyright (C) 2009-2022 Antonio Diaz Diaz. +Copyright (C) 2009-2024 Antonio Diaz Diaz. This file is free documentation: you have unlimited permission to copy, distribute, and modify it. diff --git a/Makefile.in b/Makefile.in index 2c3ff90..bb3afc0 100644 --- a/Makefile.in +++ b/Makefile.in @@ -32,6 +32,10 @@ main.o : main.cc %.o : %.cc $(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $< +# prevent 'make' from trying to remake source files +$(VPATH)/configure $(VPATH)/Makefile.in $(VPATH)/doc/$(pkgname).texi : ; +%.h %.cc : ; + $(objs) : Makefile arg_parser.o : arg_parser.h compress.o : lzip.h @@ -42,13 +46,12 @@ list.o : lzip.h lzip_index.h lzip_index.o : lzip.h lzip_index.h main.o : arg_parser.h lzip.h - doc : info man info : $(VPATH)/doc/$(pkgname).info $(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texi - cd $(VPATH)/doc && makeinfo $(pkgname).texi + cd $(VPATH)/doc && $(MAKEINFO) $(pkgname).texi man : $(VPATH)/doc/$(progname).1 @@ -1,13 +1,14 @@ -Changes in version 1.10: +Changes in version 1.11: -In case of error in a numerical argument to a command line option, plzip -now shows the name of the option and the range of valid values. +File diagnostics have been reformatted as 'PROGRAM: FILE: MESSAGE'. -'--check-lib' now checks that LZ_API_VERSION and LZ_version_string match. +Diagnostics caused by invalid arguments to command-line options now show the +argument and the name of the option. -The variable LIBS can now be set from configure. +The option '-o, --output' now preserves dates, permissions, and ownership of +the file when (de)compressing exactly one file. -Several descriptions have been improved in manual, '--help', and man page. +The option '-o, --output' now creates missing intermediate directories when +writing to a file. -The texinfo category of the manual has been changed from 'Data Compression' -to 'Compression' to match that of gzip. (Reported by Alfred M. Szmidt). +The variable MAKEINFO has been added to configure and Makefile.in. @@ -1,18 +1,19 @@ Description -Plzip is a massively parallel (multi-threaded) implementation of lzip, fully +Plzip is a massively parallel (multi-threaded) implementation of lzip, compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib. Lzip is a lossless data compressor with a user interface similar to the one of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov -chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity -checking to maximize interoperability and optimize safety. Lzip can compress -about as fast as gzip (lzip -0) or compress most files more than bzip2 -(lzip -9). Decompression speed is intermediate between gzip and bzip2. -Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip -has been designed, written, and tested with great care to replace gzip and -bzip2 as the standard general-purpose compressed format for unix-like -systems. +chain-Algorithm' (LZMA) stream format to maximize interoperability. The +maximum dictionary size is 512 MiB so that any lzip file can be decompressed +on 32-bit machines. Lzip provides accurate and robust 3-factor integrity +checking. Lzip can compress about as fast as gzip (lzip -0) or compress most +files more than bzip2 (lzip -9). Decompression speed is intermediate between +gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery +perspective. Lzip has been designed, written, and tested with great care to +replace gzip and bzip2 as the standard general-purpose compressed format for +Unix-like systems. Plzip can compress/decompress large files on multiprocessor machines much faster than lzip, at the cost of a slightly reduced compression ratio (0.4 @@ -27,11 +28,12 @@ alignment between tar members and lzip members. When compressing, plzip divides the input file into chunks and compresses as many chunks simultaneously as worker threads are chosen, creating a -multimember compressed file. +multimember compressed file. Each chunk is compressed in-place (using the +same buffer for input and output), reducing the amount of RAM required. When decompressing, plzip decompresses as many members simultaneously as -worker threads are chosen. Files that were compressed with lzip will not -be decompressed faster than using lzip (unless the option '-b' was used) +worker threads are chosen. Files that were compressed with lzip are not +decompressed faster than using lzip (unless the option '-b' was used) because lzip usually produces single-member files, which can't be decompressed in parallel. @@ -63,9 +65,9 @@ Plzip uses the same well-defined exit status values used by lzip, which makes it safer than compressors returning ambiguous warning values (like gzip) when it is used as a back end for other programs like tar or zutils. -Plzip will automatically use for each file the largest dictionary size that -does not exceed neither the file size nor the limit given. Keep in mind that -the decompression memory requirement is affected at compression time by the +Plzip automatically uses for each file the largest dictionary size that does +not exceed neither the file size nor the limit given. Keep in mind that the +decompression memory requirement is affected at compression time by the choice of dictionary size limit. When compressing, plzip replaces every file given in the command line @@ -78,20 +80,20 @@ filename.tlz becomes filename.tar anyothername becomes anyothername.out (De)compressing a file is much like copying or moving it. Therefore plzip -preserves the access and modification dates, permissions, and, when -possible, ownership of the file just as 'cp -p' does. (If the user ID or -the group ID can't be duplicated, the file permission bits S_ISUID and -S_ISGID are cleared). +preserves the access and modification dates, permissions, and, if you have +appropriate privileges, ownership of the file just as 'cp -p' does. (If the +user ID or the group ID can't be duplicated, the file permission bits +S_ISUID and S_ISGID are cleared). Plzip is able to read from some types of non-regular files if either the option '-c' or the option '-o' is specified. If no file names are specified, plzip compresses (or decompresses) from -standard input to standard output. Plzip will refuse to read compressed data +standard input to standard output. Plzip refuses to read compressed data from a terminal or write compressed data to a terminal, as this would be entirely incomprehensible and might leave the terminal in an abnormal state. -Plzip will correctly decompress a file which is the concatenation of two or +Plzip correctly decompresses a file which is the concatenation of two or more compressed files. The result is the concatenation of the corresponding decompressed files. Integrity testing of concatenated compressed files is also supported. @@ -101,11 +103,10 @@ been compressed. Decompressed is used to refer to data which have undergone the process of decompression. -Copyright (C) 2009-2022 Antonio Diaz Diaz. +Copyright (C) 2009-2024 Antonio Diaz Diaz. This file is free documentation: you have unlimited permission to copy, distribute, and modify it. -The file Makefile.in is a data file used by configure to produce the -Makefile. It has the same copyright owner and permissions that configure -itself. +The file Makefile.in is a data file used by configure to produce the Makefile. +It has the same copyright owner and permissions that configure itself. diff --git a/arg_parser.cc b/arg_parser.cc index 59998ac..0c04d8e 100644 --- a/arg_parser.cc +++ b/arg_parser.cc @@ -1,5 +1,5 @@ -/* Arg_parser - POSIX/GNU command line argument parser. (C++ version) - Copyright (C) 2006-2022 Antonio Diaz Diaz. +/* Arg_parser - POSIX/GNU command-line argument parser. (C++ version) + Copyright (C) 2006-2024 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided diff --git a/arg_parser.h b/arg_parser.h index e854838..1eeec9a 100644 --- a/arg_parser.h +++ b/arg_parser.h @@ -1,5 +1,5 @@ -/* Arg_parser - POSIX/GNU command line argument parser. (C++ version) - Copyright (C) 2006-2022 Antonio Diaz Diaz. +/* Arg_parser - POSIX/GNU command-line argument parser. (C++ version) + Copyright (C) 2006-2024 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided diff --git a/compress.cc b/compress.cc index 39dbff1..defa58d 100644 --- a/compress.cc +++ b/compress.cc @@ -1,6 +1,6 @@ /* Plzip - Massively parallel implementation of lzip Copyright (C) 2009 Laszlo Ersek. - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -34,7 +34,7 @@ #include "lzip.h" #ifndef LLONG_MAX -#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL +#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL #endif @@ -1,12 +1,12 @@ #! /bin/sh # configure script for Plzip - Massively parallel implementation of lzip -# Copyright (C) 2009-2022 Antonio Diaz Diaz. +# Copyright (C) 2009-2024 Antonio Diaz Diaz. # # This configure script is free software: you have unlimited permission # to copy, distribute, and modify it. pkgname=plzip -pkgversion=1.10 +pkgversion=1.11 progname=plzip with_mingw= srctrigger=doc/${pkgname}.texi @@ -26,6 +26,7 @@ CPPFLAGS= CXXFLAGS='-Wall -W -O2' LDFLAGS= LIBS='-llz -lpthread' +MAKEINFO=makeinfo # checking whether we are using GNU C++. /bin/sh -c "${CXX} --version" > /dev/null 2>&1 || { CXX=c++ ; CXXFLAGS=-O2 ; } @@ -59,7 +60,7 @@ while [ $# != 0 ] ; do echo "Options and variables: [defaults in brackets]" echo " -h, --help display this help and exit" echo " -V, --version output version information and exit" - echo " --srcdir=DIR find the sources in DIR [. or ..]" + echo " --srcdir=DIR find the source code in DIR [. or ..]" echo " --prefix=DIR install into DIR [${prefix}]" echo " --exec-prefix=DIR base directory for arch-dependent files [${exec_prefix}]" echo " --bindir=DIR user executables directory [${bindir}]" @@ -68,11 +69,12 @@ while [ $# != 0 ] ; do echo " --mandir=DIR man pages directory [${mandir}]" echo " --with-mingw use included pread/pwrite functions missing in MinGW" echo " CXX=COMPILER C++ compiler to use [${CXX}]" - echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]" - echo " CXXFLAGS=OPTIONS command line options for the C++ compiler [${CXXFLAGS}]" + echo " CPPFLAGS=OPTIONS command-line options for the preprocessor [${CPPFLAGS}]" + echo " CXXFLAGS=OPTIONS command-line options for the C++ compiler [${CXXFLAGS}]" echo " CXXFLAGS+=OPTIONS append options to the current value of CXXFLAGS" - echo " LDFLAGS=OPTIONS command line options for the linker [${LDFLAGS}]" + echo " LDFLAGS=OPTIONS command-line options for the linker [${LDFLAGS}]" echo " LIBS=OPTIONS libraries to pass to the linker [${LIBS}]" + echo " MAKEINFO=NAME makeinfo program to use [${MAKEINFO}]" echo exit 0 ;; --version | -V) @@ -94,7 +96,7 @@ while [ $# != 0 ] ; do --infodir=*) infodir=${optarg} ;; --mandir=*) mandir=${optarg} ;; --no-create) no_create=yes ;; - --with-mingw) with_mingw="-DWITH_MINGW" ;; + --with-mingw) with_mingw=-DWITH_MINGW ;; CXX=*) CXX=${optarg} ;; CPPFLAGS=*) CPPFLAGS=${optarg} ;; @@ -102,6 +104,7 @@ while [ $# != 0 ] ; do CXXFLAGS+=*) CXXFLAGS="${CXXFLAGS} ${optarg}" ;; LDFLAGS=*) LDFLAGS=${optarg} ;; LIBS=*) LIBS="${optarg} ${LIBS}" ;; + MAKEINFO=*) MAKEINFO=${optarg} ;; --*) echo "configure: WARNING: unrecognized option: '${option}'" 1>&2 ;; @@ -121,7 +124,7 @@ while [ $# != 0 ] ; do fi done -# Find the source files, if location was not specified. +# Find the source code, if location was not specified. srcdirtext= if [ -z "${srcdir}" ] ; then srcdirtext="or . or .." ; srcdir=. @@ -133,7 +136,7 @@ if [ -z "${srcdir}" ] ; then fi if [ ! -r "${srcdir}/${srctrigger}" ] ; then - echo "configure: Can't find sources in ${srcdir} ${srcdirtext}" 1>&2 + echo "configure: Can't find source code in ${srcdir} ${srcdirtext}" 1>&2 echo "configure: (At least ${srctrigger} is missing)." 1>&2 exit 1 fi @@ -153,7 +156,7 @@ if [ -z "${no_create}" ] ; then # This script is free software: you have unlimited permission # to copy, distribute, and modify it. -exec /bin/sh $0 ${args} --no-create +exec /bin/sh "$0" ${args} --no-create EOF chmod +x config.status fi @@ -172,10 +175,11 @@ echo "CPPFLAGS = ${CPPFLAGS}" echo "CXXFLAGS = ${CXXFLAGS}" echo "LDFLAGS = ${LDFLAGS}" echo "LIBS = ${LIBS}" +echo "MAKEINFO = ${MAKEINFO}" rm -f Makefile cat > Makefile << EOF # Makefile for Plzip - Massively parallel implementation of lzip -# Copyright (C) 2009-2022 Antonio Diaz Diaz. +# Copyright (C) 2009-2024 Antonio Diaz Diaz. # This file was generated automatically by configure. Don't edit. # # This Makefile is free software: you have unlimited permission @@ -197,9 +201,10 @@ CPPFLAGS = ${CPPFLAGS} CXXFLAGS = ${CXXFLAGS} LDFLAGS = ${LDFLAGS} LIBS = ${LIBS} +MAKEINFO = ${MAKEINFO} EOF cat "${srcdir}/Makefile.in" >> Makefile echo "OK. Now you can run make." -echo "If make fails, verify that the compression library lzlib is correctly" -echo "installed (see INSTALL)." +echo "If make fails, check that the compression library lzlib is correctly installed" +echo "(see INSTALL)." diff --git a/dec_stdout.cc b/dec_stdout.cc index fe4c36d..6ffed07 100644 --- a/dec_stdout.cc +++ b/dec_stdout.cc @@ -1,6 +1,6 @@ /* Plzip - Massively parallel implementation of lzip Copyright (C) 2009 Laszlo Ersek. - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 diff --git a/dec_stream.cc b/dec_stream.cc index b75e49d..6ea4ed7 100644 --- a/dec_stream.cc +++ b/dec_stream.cc @@ -1,6 +1,6 @@ /* Plzip - Massively parallel implementation of lzip Copyright (C) 2009 Laszlo Ersek. - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -443,10 +443,10 @@ fail: ( size <= 0 ) ? "File ends unexpectedly at member header." : "Input file is too short." ); goto fail; } const Lzip_header & header = *(const Lzip_header *)buffer; - if( !header.verify_magic() ) + if( !header.check_magic() ) { if( shared_retval.set_value( 2 ) ) { show_file_error( pp.name(), bad_magic_msg ); } goto fail; } - if( !header.verify_version() ) + if( !header.check_version() ) { if( shared_retval.set_value( 2 ) ) { pp( bad_version( header.version() ) ); } goto fail; } tmp.dictionary_size = header.dictionary_size(); @@ -474,10 +474,10 @@ fail: *(const Lzip_trailer *)(buffer + newpos - tsize); const unsigned long long member_size = trailer.member_size(); if( partial_member_size + newpos - pos == member_size && - trailer.verify_consistency() ) + trailer.check_consistency() ) { // header found const Lzip_header & header = *(const Lzip_header *)(buffer + newpos); - if( !header.verify_version() ) + if( !header.check_version() ) { if( shared_retval.set_value( 2 ) ) { pp( bad_version( header.version() ) ); } goto fail; } const unsigned dictionary_size = header.dictionary_size(); @@ -565,11 +565,10 @@ void muxer( Packet_courier & courier, const Pretty_print & pp, /* Init the courier, then start the splitter and the workers and, if not testing, call the muxer. */ -int dec_stream( const unsigned long long cfile_size, - const int num_workers, const int infd, const int outfd, +int dec_stream( const unsigned long long cfile_size, const int num_workers, + const int infd, const int outfd, const Cl_options & cl_opts, const Pretty_print & pp, const int debug_level, - const int in_slots, const int out_slots, - const bool ignore_trailing, const bool loose_trailing ) + const int in_slots, const int out_slots ) { const int total_in_slots = ( INT_MAX / num_workers >= in_slots ) ? num_workers * in_slots : INT_MAX; @@ -596,8 +595,8 @@ int dec_stream( const unsigned long long cfile_size, splitter_arg.worker_arg.pp = &pp; splitter_arg.worker_arg.shared_retval = &shared_retval; splitter_arg.worker_arg.worker_id = 0; - splitter_arg.worker_arg.ignore_trailing = ignore_trailing; - splitter_arg.worker_arg.loose_trailing = loose_trailing; + splitter_arg.worker_arg.ignore_trailing = cl_opts.ignore_trailing; + splitter_arg.worker_arg.loose_trailing = cl_opts.loose_trailing; splitter_arg.worker_arg.testing = ( outfd < 0 ); splitter_arg.worker_arg.nocopy = nocopy; splitter_arg.worker_args = worker_args; diff --git a/decompress.cc b/decompress.cc index 291e5eb..5b0e68f 100644 --- a/decompress.cc +++ b/decompress.cc @@ -1,6 +1,6 @@ /* Plzip - Massively parallel implementation of lzip Copyright (C) 2009 Laszlo Ersek. - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -266,22 +266,21 @@ done: // start the workers and wait for them to finish. int decompress( const unsigned long long cfile_size, int num_workers, - const int infd, const int outfd, const Pretty_print & pp, - const int debug_level, const int in_slots, - const int out_slots, const bool ignore_trailing, - const bool loose_trailing, const bool infd_isreg, - const bool one_to_one ) + const int infd, const int outfd, const Cl_options & cl_opts, + const Pretty_print & pp, const int debug_level, + const int in_slots, const int out_slots, + const bool infd_isreg, const bool one_to_one ) { if( !infd_isreg ) - return dec_stream( cfile_size, num_workers, infd, outfd, pp, debug_level, - in_slots, out_slots, ignore_trailing, loose_trailing ); + return dec_stream( cfile_size, num_workers, infd, outfd, cl_opts, pp, + debug_level, in_slots, out_slots ); - const Lzip_index lzip_index( infd, ignore_trailing, loose_trailing ); + const Lzip_index lzip_index( infd, cl_opts ); if( lzip_index.retval() == 1 ) // decompress as stream if seek fails { lseek( infd, 0, SEEK_SET ); - return dec_stream( cfile_size, num_workers, infd, outfd, pp, debug_level, - in_slots, out_slots, ignore_trailing, loose_trailing ); + return dec_stream( cfile_size, num_workers, infd, outfd, cl_opts, pp, + debug_level, in_slots, out_slots ); } if( lzip_index.retval() != 0 ) // corrupt or invalid input file { diff --git a/doc/plzip.1 b/doc/plzip.1 index 4be148d..3985e5b 100644 --- a/doc/plzip.1 +++ b/doc/plzip.1 @@ -1,24 +1,25 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH PLZIP "1" "January 2022" "plzip 1.10" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH PLZIP "1" "January 2024" "plzip 1.11" "User Commands" .SH NAME plzip \- reduces the size of files .SH SYNOPSIS .B plzip [\fI\,options\/\fR] [\fI\,files\/\fR] .SH DESCRIPTION -Plzip is a massively parallel (multi\-threaded) implementation of lzip, fully +Plzip is a massively parallel (multi\-threaded) implementation of lzip, compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib. .PP Lzip is a lossless data compressor with a user interface similar to the one of gzip or bzip2. Lzip uses a simplified form of the 'Lempel\-Ziv\-Markov -chain\-Algorithm' (LZMA) stream format and provides a 3 factor integrity -checking to maximize interoperability and optimize safety. Lzip can compress -about as fast as gzip (lzip \fB\-0\fR) or compress most files more than bzip2 -(lzip \fB\-9\fR). Decompression speed is intermediate between gzip and bzip2. -Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip -has been designed, written, and tested with great care to replace gzip and -bzip2 as the standard general\-purpose compressed format for unix\-like -systems. +chain\-Algorithm' (LZMA) stream format to maximize interoperability. The +maximum dictionary size is 512 MiB so that any lzip file can be decompressed +on 32\-bit machines. Lzip provides accurate and robust 3\-factor integrity +checking. Lzip can compress about as fast as gzip (lzip \fB\-0\fR) or compress most +files more than bzip2 (lzip \fB\-9\fR). Decompression speed is intermediate between +gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery +perspective. Lzip has been designed, written, and tested with great care to +replace gzip and bzip2 as the standard general\-purpose compressed format for +Unix\-like systems. .PP Plzip can compress/decompress large files on multiprocessor machines much faster than lzip, at the cost of a slightly reduced compression ratio (0.4 @@ -44,7 +45,7 @@ set size of input data blocks [2x8=16 MiB] write to standard output, keep input files .TP \fB\-d\fR, \fB\-\-decompress\fR -decompress +decompress, test compressed file integrity .TP \fB\-f\fR, \fB\-\-force\fR overwrite existing output files @@ -104,21 +105,21 @@ 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. +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 options \fB\-\-dictionary\-size\fR and \fB\-\-match\-length\fR -directly to achieve optimal performance. +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 options \fB\-\-dictionary\-size\fR and \fB\-\-match\-length\fR directly +to achieve optimal performance. .PP To extract all the files from archive 'foo.tar.lz', use the commands \&'tar \fB\-xf\fR foo.tar.lz' or 'plzip \fB\-cd\fR foo.tar.lz | tar \fB\-xf\fR \-'. .PP -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, 3 for an internal consistency error (e.g., bug) which -caused plzip to panic. +Exit status: 0 for a normal exit, 1 for environmental problems +(file not found, invalid command\-line options, I/O errors, etc), 2 to +indicate a corrupt or invalid input file, 3 for an internal consistency +error (e.g., bug) which caused plzip to panic. .SH "REPORTING BUGS" Report bugs to lzip\-bug@nongnu.org .br @@ -126,12 +127,13 @@ Plzip home page: http://www.nongnu.org/lzip/plzip.html .SH COPYRIGHT Copyright \(co 2009 Laszlo Ersek. .br -Copyright \(co 2022 Antonio Diaz Diaz. -Using lzlib 1.13 +Copyright \(co 2024 Antonio Diaz Diaz. 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. There is NO WARRANTY, to the extent permitted by law. +Using lzlib 1.14 +Using LZ_API_VERSION = 1014 .SH "SEE ALSO" The full documentation for .B plzip diff --git a/doc/plzip.info b/doc/plzip.info index c38ea5c..becd133 100644 --- a/doc/plzip.info +++ b/doc/plzip.info @@ -11,13 +11,13 @@ File: plzip.info, Node: Top, Next: Introduction, Up: (dir) Plzip Manual ************ -This manual is for Plzip (version 1.10, 24 January 2022). +This manual is for Plzip (version 1.11, 21 January 2024). * Menu: * Introduction:: Purpose and features of plzip * Output:: Meaning of plzip's output -* Invoking plzip:: Command line interface +* Invoking plzip:: Command-line interface * Program design:: Internal structure of plzip * Memory requirements:: Memory required to compress and decompress * Minimum file sizes:: Minimum file sizes required for full speed @@ -28,7 +28,7 @@ This manual is for Plzip (version 1.10, 24 January 2022). * Concept index:: Index of concepts - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 Antonio Diaz Diaz. This manual is free documentation: you have unlimited permission to copy, distribute, and modify it. @@ -39,19 +39,20 @@ File: plzip.info, Node: Introduction, Next: Output, Prev: Top, Up: Top 1 Introduction ************** -Plzip is a massively parallel (multi-threaded) implementation of lzip, fully +Plzip is a massively parallel (multi-threaded) implementation of lzip, compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib. Lzip is a lossless data compressor with a user interface similar to the one of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov -chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity -checking to maximize interoperability and optimize safety. Lzip can compress -about as fast as gzip (lzip -0) or compress most files more than bzip2 -(lzip -9). Decompression speed is intermediate between gzip and bzip2. Lzip -is better than gzip and bzip2 from a data recovery perspective. Lzip has -been designed, written, and tested with great care to replace gzip and -bzip2 as the standard general-purpose compressed format for unix-like -systems. +chain-Algorithm' (LZMA) stream format to maximize interoperability. The +maximum dictionary size is 512 MiB so that any lzip file can be decompressed +on 32-bit machines. Lzip provides accurate and robust 3-factor integrity +checking. Lzip can compress about as fast as gzip (lzip -0) or compress most +files more than bzip2 (lzip -9). Decompression speed is intermediate between +gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery +perspective. Lzip has been designed, written, and tested with great care to +replace gzip and bzip2 as the standard general-purpose compressed format for +Unix-like systems. Plzip can compress/decompress large files on multiprocessor machines much faster than lzip, at the cost of a slightly reduced compression ratio (0.4 @@ -94,10 +95,10 @@ byte near the beginning is a thing of the past. makes it safer than compressors returning ambiguous warning values (like gzip) when it is used as a back end for other programs like tar or zutils. - Plzip will automatically use for each file the largest dictionary size -that does not exceed neither the file size nor the limit given. Keep in -mind that the decompression memory requirement is affected at compression -time by the choice of dictionary size limit. *Note Memory requirements::. + Plzip automatically uses for each file the largest dictionary size that +does not exceed neither the file size nor the limit given. Keep in mind +that the decompression memory requirement is affected at compression time +by the choice of dictionary size limit. *Note Memory requirements::. When compressing, plzip replaces every file given in the command line with a compressed version of itself, with the name "original_name.lz". When @@ -109,22 +110,22 @@ filename.tlz becomes filename.tar anyothername becomes anyothername.out (De)compressing a file is much like copying or moving it. Therefore plzip -preserves the access and modification dates, permissions, and, when -possible, ownership of the file just as 'cp -p' does. (If the user ID or -the group ID can't be duplicated, the file permission bits S_ISUID and -S_ISGID are cleared). +preserves the access and modification dates, permissions, and, if you have +appropriate privileges, ownership of the file just as 'cp -p' does. (If the +user ID or the group ID can't be duplicated, the file permission bits +S_ISUID and S_ISGID are cleared). Plzip is able to read from some types of non-regular files if either the option '-c' or the option '-o' is specified. - Plzip will refuse to read compressed data from a terminal or write -compressed data to a terminal, as this would be entirely incomprehensible -and might leave the terminal in an abnormal state. + Plzip refuses to read compressed data from a terminal or write compressed +data to a terminal, as this would be entirely incomprehensible and might +leave the terminal in an abnormal state. - Plzip will correctly decompress a file which is the concatenation of two -or more compressed files. The result is the concatenation of the -corresponding decompressed files. Integrity testing of concatenated -compressed files is also supported. + Plzip correctly decompresses a file which is the concatenation of two or +more compressed files. The result is the concatenation of the corresponding +decompressed files. Integrity testing of concatenated compressed files is +also supported. File: plzip.info, Node: Output, Next: Invoking plzip, Prev: Introduction, Up: Top @@ -185,7 +186,8 @@ The format for running plzip is: If no file names are specified, plzip compresses (or decompresses) from standard input to standard output. A hyphen '-' 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. +once, the first time it appears in the command line. Remember to prepend +'./' to any file name beginning with a hyphen, or use '--'. plzip supports the following options: *Note Argument syntax: (arg_parser)Argument syntax. @@ -208,30 +210,32 @@ once, the first time it appears in the command line. '-B BYTES' '--data-size=BYTES' When compressing, set the size in bytes of the input data blocks. The - input file will be divided in chunks of this size before compression is + input file is divided in chunks of this size before compression is performed. Valid values range from 8 KiB to 1 GiB. Default value is two times the dictionary size, except for option '-0' where it - defaults to 1 MiB. Plzip will reduce the dictionary size if it is - larger than the data size specified. *Note Minimum file sizes::. + defaults to 1 MiB. Plzip reduces the dictionary size if it is larger + than the data size specified. *Note Minimum file sizes::. '-c' '--stdout' Compress or decompress to standard output; keep input files unchanged. If compressing several files, each file is compressed independently. - This option (or '-o') is needed when reading from a named pipe (fifo) - or from a device. Use 'lziprecover -cd -i' to recover as much of the - decompressed data as possible when decompressing a corrupt file. '-c' - overrides '-o'. '-c' has no effect when testing or listing. + (The output consists of a sequence of independently compressed + members). This option (or '-o') is needed when reading from a named + pipe (fifo) or from a device. Use 'lziprecover -cd -i' to recover as + much of the decompressed data as possible when decompressing a corrupt + file. '-c' overrides '-o'. '-c' has no effect when testing or listing. '-d' '--decompress' - Decompress the files specified. If a file does not exist, can't be - opened, or the destination file already exists and '--force' has not - been specified, plzip continues decompressing the rest of the files - and exits with error status 1. If a file fails to decompress, or is a - terminal, plzip exits immediately with error status 2 without - decompressing the rest of the files. A terminal is considered an - uncompressed file, and therefore invalid. + Decompress the files specified. The integrity of the files specified is + checked. If a file does not exist, can't be opened, or the destination + file already exists and '--force' has not been specified, plzip + continues decompressing the rest of the files and exits with error + status 1. If a file fails to decompress, or is a terminal, plzip exits + immediately with error status 2 without decompressing the rest of the + files. A terminal is considered an uncompressed file, and therefore + invalid. '-f' '--force' @@ -258,18 +262,18 @@ once, the first time it appears in the command line. printed. If any file is damaged, does not exist, can't be opened, or is not - regular, the final exit status will be > 0. '-lq' can be used to verify + regular, the final exit status is > 0. '-lq' can be used to check quickly (without decompressing) the structural integrity of the files - specified. (Use '--test' to verify the data integrity). '-alq' - additionally verifies that none of the files specified contain - trailing data. + specified. (Use '--test' to check the data integrity). '-alq' + additionally checks that none of the files specified contain trailing + data. '-m BYTES' '--match-length=BYTES' When compressing, set the match length limit in bytes. After a match this long is found, the search is finished. Valid values range from 5 - to 273. Larger values usually give better compression ratios but longer - compression times. + to 273. Larger values usually give better compression ratios but + longer compression times. '-n N' '--threads=N' @@ -291,10 +295,12 @@ once, the first time it appears in the command line. '-o FILE' '--output=FILE' - If '-c' has not been also specified, write the (de)compressed output to - FILE; keep input files unchanged. If compressing several files, each - file is compressed independently. This option (or '-c') is needed when - reading from a named pipe (fifo) or from a device. '-o -' is + If '-c' has not been also specified, write the (de)compressed output + to FILE, automatically creating any missing parent directories; keep + input files unchanged. If compressing several files, each file is + compressed independently. (The output consists of a sequence of + independently compressed members). This option (or '-c') is needed + when reading from a named pipe (fifo) or from a device. '-o -' is equivalent to '-c'. '-o' has no effect when testing or listing. In order to keep backward compatibility with plzip versions prior to @@ -311,14 +317,14 @@ once, the first time it appears in the command line. '-s BYTES' '--dictionary-size=BYTES' - When compressing, set the dictionary size limit in bytes. Plzip will - use for each file the largest dictionary size that does not exceed - neither the file size nor 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. Dictionary sizes are quantized so that they can be - coded in just one byte (*note coded-dict-size::). If the size specified - does not match one of the valid sizes, it will be rounded upwards by - adding up to (BYTES / 8) to it. + When compressing, set the dictionary size limit in bytes. Plzip uses + for each file the largest dictionary size that does not exceed neither + the file size nor 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. Dictionary sizes are quantized so that they can be coded in + just one byte (*note coded-dict-size::). If the size specified does + not match one of the valid sizes, it is 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 requirement @@ -330,7 +336,7 @@ once, the first time it appears in the command line. really performs a trial decompression and throws away the result. Use it together with '-v' to see information about the files. If a file fails the test, does not exist, can't be opened, or is a terminal, - plzip continues checking the rest of the files. A final diagnostic is + plzip continues testing the rest of the files. A final diagnostic is shown at verbosity level 1 or higher if any file fails the test when testing multiple files. @@ -408,26 +414,29 @@ once, the first time it appears in the command line. (lzlib)Library version. - Numbers given as arguments to options may be followed by a multiplier -and an optional 'B' for "byte". + Numbers given as arguments to options may be expressed in decimal, +hexadecimal, or octal (using the same syntax as integer constants in C++), +and may be followed by a multiplier and an optional 'B' for "byte". Table of SI and binary prefixes (unit multipliers): -Prefix Value | Prefix Value -k kilobyte (10^3 = 1000) | Ki kibibyte (2^10 = 1024) -M megabyte (10^6) | Mi mebibyte (2^20) -G gigabyte (10^9) | Gi gibibyte (2^30) -T terabyte (10^12) | Ti tebibyte (2^40) -P petabyte (10^15) | Pi pebibyte (2^50) -E exabyte (10^18) | Ei exbibyte (2^60) -Z zettabyte (10^21) | Zi zebibyte (2^70) -Y yottabyte (10^24) | Yi yobibyte (2^80) +Prefix Value | Prefix Value +k kilobyte (10^3 = 1000) | Ki kibibyte (2^10 = 1024) +M megabyte (10^6) | Mi mebibyte (2^20) +G gigabyte (10^9) | Gi gibibyte (2^30) +T terabyte (10^12) | Ti tebibyte (2^40) +P petabyte (10^15) | Pi pebibyte (2^50) +E exabyte (10^18) | Ei exbibyte (2^60) +Z zettabyte (10^21) | Zi zebibyte (2^70) +Y yottabyte (10^24) | Yi yobibyte (2^80) +R ronnabyte (10^27) | Ri robibyte (2^90) +Q quettabyte (10^30) | Qi quebibyte (2^100) 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, 3 for an internal consistency error (e.g., bug) which caused -plzip to panic. +found, invalid command-line options, I/O errors, etc), 2 to indicate a +corrupt or invalid input file, 3 for an internal consistency error (e.g., +bug) which caused plzip to panic. File: plzip.info, Node: Program design, Next: Memory requirements, Prev: Invoking plzip, Up: Top @@ -441,7 +450,7 @@ multimember compressed file. Each chunk is compressed in-place (using the same buffer for input and output), reducing the amount of RAM required. When decompressing, plzip decompresses as many members simultaneously as -worker threads are chosen. Files that were compressed with lzip will not be +worker threads are chosen. Files that were compressed with lzip are not decompressed faster than using lzip (unless the option '-b' was used) because lzip usually produces single-member files, which can't be decompressed in parallel. @@ -535,10 +544,10 @@ 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 least as large as the number of worker threads times the chunk size (*note ---data-size::). Else some processors will not get any data to compress, and -compression will be proportionally slower. The maximum speed increase -achievable on a given file is limited by the ratio (file_size / data_size). -For example, a tarball the size of gcc or linux will scale up to 10 or 14 +--data-size::). Else some processors do not get any data to compress, and +compression is proportionally slower. The maximum speed increase achievable +on a given file is limited by the ratio (file_size / data_size). For +example, a tarball the size of gcc or linux scales up to 10 or 14 processors at level -9. The following table shows the minimum uncompressed file size needed for @@ -585,7 +594,7 @@ when there is no longer anything to take away. represents a variable number of bytes. - A lzip file consists of a series of independent "members" (compressed + A lzip file consists of one or more independent "members" (compressed data sets). The members simply appear one after another in the file, with no additional information before, between, or after them. Each member can encode in compressed form up to 16 EiB - 1 byte of uncompressed data. The @@ -629,10 +638,10 @@ size of a multimember file is unlimited. '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 the safe recovery of undamaged members from - multimember files. Member size should be limited to 2 PiB to prevent - the data size field from overflowing. + as a distributed index, improves the checking of stream integrity, and + facilitates the safe recovery of undamaged members from multimember + files. Lzip limits the member size to 2 PiB to prevent the data size + field from overflowing. @@ -648,12 +657,13 @@ member. Such trailing data may be: example when writing to a tape. It is safe to append any amount of padding zero bytes to a lzip file. - * Useful data added by the user; a cryptographically secure hash, a + * Useful data added by the user; an "End Of File" string (to check that + the file has not been truncated), a cryptographically secure hash, a description of file contents, etc. It is safe to append any amount of - text to a lzip file as long as none of the first four bytes of the text - match the corresponding byte in the string "LZIP", and the text does - not contain any zero bytes (null characters). Nonzero bytes and zero - bytes can't be safely mixed in trailing data. + text to a lzip file as long as none of the first four bytes of the + text matches the corresponding byte in the string "LZIP", and the text + does not contain any zero bytes (null characters). Nonzero bytes and + zero bytes can't be safely mixed in trailing data. * Garbage added by some not totally successful copy operation. @@ -669,7 +679,7 @@ member. Such trailing data may be: discriminate trailing data from a corrupt header has a Hamming distance (HD) of 3, and the 3 bit flips must happen in different magic bytes for the test to fail. In any case, the option '--trailing-error' - guarantees that any corrupt header will be detected. + guarantees that any corrupt header is detected. Trailing data are in no way part of the lzip file format, but tools reading lzip files are expected to behave as correctly and usefully as @@ -689,12 +699,12 @@ File: plzip.info, Node: Examples, Next: Problems, Prev: Trailing data, Up: T 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 -option '--keep' 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 -'. Most RAM errors happening during -compression can only be detected by comparing the compressed file with the -original because the corruption happens before plzip compresses the RAM -contents, resulting in a valid compressed file containing wrong data. +option '--keep' to plzip and don't remove the original file until you check +the compressed file with a command like 'plzip -cd file.lz | cmp file -'. +Most RAM errors happening during compression can only be detected by +comparing the compressed file with the original because the corruption +happens before plzip compresses the RAM contents, resulting in a valid +compressed file containing wrong data. Example 1: Extract all the files from archive 'foo.tar.lz'. @@ -722,7 +732,7 @@ the operation is successful, 'file.lz' is removed. plzip -d file.lz -Example 5: Verify the integrity of the compressed file 'file.lz' and show +Example 5: Check the integrity of the compressed file 'file.lz' and show status. plzip -tv file.lz @@ -800,20 +810,20 @@ Concept index Tag Table: Node: Top217 Node: Introduction1156 -Node: Output5829 -Node: Invoking plzip7392 -Ref: --trailing-error8187 -Ref: --data-size8425 -Node: Program design18819 -Node: Memory requirements21122 -Node: Minimum file sizes22807 -Node: File format24821 -Ref: coded-dict-size26260 -Node: Trailing data27514 -Node: Examples29775 -Ref: concat-example31210 -Node: Problems31967 -Node: Concept index32522 +Node: Output5934 +Node: Invoking plzip7497 +Ref: --trailing-error8372 +Ref: --data-size8610 +Node: Program design19519 +Node: Memory requirements21818 +Node: Minimum file sizes23503 +Node: File format25506 +Ref: coded-dict-size26945 +Node: Trailing data28195 +Node: Examples30531 +Ref: concat-example31964 +Node: Problems32721 +Node: Concept index33276 End Tag Table diff --git a/doc/plzip.texi b/doc/plzip.texi index 818ecf5..323fad1 100644 --- a/doc/plzip.texi +++ b/doc/plzip.texi @@ -6,8 +6,8 @@ @finalout @c %**end of header -@set UPDATED 24 January 2022 -@set VERSION 1.10 +@set UPDATED 21 January 2024 +@set VERSION 1.11 @dircategory Compression @direntry @@ -38,7 +38,7 @@ This manual is for Plzip (version @value{VERSION}, @value{UPDATED}). @menu * Introduction:: Purpose and features of plzip * Output:: Meaning of plzip's output -* Invoking plzip:: Command line interface +* Invoking plzip:: Command-line interface * Program design:: Internal structure of plzip * Memory requirements:: Memory required to compress and decompress * Minimum file sizes:: Minimum file sizes required for full speed @@ -50,7 +50,7 @@ This manual is for Plzip (version @value{VERSION}, @value{UPDATED}). @end menu @sp 1 -Copyright @copyright{} 2009-2022 Antonio Diaz Diaz. +Copyright @copyright{} 2009-2024 Antonio Diaz Diaz. This manual is free documentation: you have unlimited permission to copy, distribute, and modify it. @@ -62,21 +62,22 @@ distribute, and modify it. @cindex introduction @uref{http://www.nongnu.org/lzip/plzip.html,,Plzip} -is a massively parallel (multi-threaded) implementation of lzip, fully +is a massively parallel (multi-threaded) implementation of lzip, compatible with lzip 1.4 or newer. Plzip uses the compression library @uref{http://www.nongnu.org/lzip/lzlib.html,,lzlib}. @uref{http://www.nongnu.org/lzip/lzip.html,,Lzip} is a lossless data compressor with a user interface similar to the one of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov -chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity -checking to maximize interoperability and optimize safety. Lzip can compress -about as fast as gzip @w{(lzip -0)} or compress most files more than bzip2 -@w{(lzip -9)}. Decompression speed is intermediate between gzip and bzip2. -Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip -has been designed, written, and tested with great care to replace gzip and -bzip2 as the standard general-purpose compressed format for unix-like -systems. +chain-Algorithm' (LZMA) stream format to maximize interoperability. The +maximum dictionary size is 512 MiB so that any lzip file can be decompressed +on 32-bit machines. Lzip provides accurate and robust 3-factor integrity +checking. Lzip can compress about as fast as gzip @w{(lzip -0)} or compress most +files more than bzip2 @w{(lzip -9)}. Decompression speed is intermediate between +gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery +perspective. Lzip has been designed, written, and tested with great care to +replace gzip and bzip2 as the standard general-purpose compressed format for +Unix-like systems. Plzip can compress/decompress large files on multiprocessor machines much faster than lzip, at the cost of a slightly reduced compression ratio (0.4 @@ -130,9 +131,9 @@ Plzip uses the same well-defined exit status values used by lzip, which makes it safer than compressors returning ambiguous warning values (like gzip) when it is used as a back end for other programs like tar or zutils. -Plzip will automatically use for each file the largest dictionary size that -does not exceed neither the file size nor the limit given. Keep in mind that -the decompression memory requirement is affected at compression time by the +Plzip automatically uses for each file the largest dictionary size that does +not exceed neither the file size nor the limit given. Keep in mind that the +decompression memory requirement is affected at compression time by the choice of dictionary size limit. @xref{Memory requirements}. When compressing, plzip replaces every file given in the command line @@ -147,19 +148,19 @@ file from that of the compressed file as follows: @end multitable (De)compressing a file is much like copying or moving it. Therefore plzip -preserves the access and modification dates, permissions, and, when -possible, ownership of the file just as @w{@samp{cp -p}} does. (If the user ID or -the group ID can't be duplicated, the file permission bits S_ISUID and -S_ISGID are cleared). +preserves the access and modification dates, permissions, and, if you have +appropriate privileges, ownership of the file just as @w{@samp{cp -p}} does. +(If the user ID or the group ID can't be duplicated, the file permission +bits S_ISUID and S_ISGID are cleared). Plzip is able to read from some types of non-regular files if either the -option @samp{-c} or the option @samp{-o} is specified. +option @option{-c} or the option @option{-o} is specified. -Plzip will refuse to read compressed data from a terminal or write compressed +Plzip refuses to read compressed data from a terminal or write compressed data to a terminal, as this would be entirely incomprehensible and might leave the terminal in an abnormal state. -Plzip will correctly decompress a file which is the concatenation of two or +Plzip correctly decompresses a file which is the concatenation of two or more compressed files. The result is the concatenation of the corresponding decompressed files. Integrity testing of concatenated compressed files is also supported. @@ -231,7 +232,8 @@ plzip [@var{options}] [@var{files}] If no file names are specified, plzip compresses (or decompresses) from standard input to standard output. A hyphen @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. +read just once, the first time it appears in the command line. Remember to +prepend @file{./} to any file name beginning with a hyphen, or use @samp{--}. plzip supports the following @uref{http://www.nongnu.org/arg-parser/manual/arg_parser_manual.html#Argument-syntax,,options}: @@ -259,30 +261,32 @@ garbage that can be safely ignored. @xref{concat-example}. @anchor{--data-size} @item -B @var{bytes} @itemx --data-size=@var{bytes} -When compressing, set the size in bytes of the input data blocks. The -input file will be divided in chunks of this size before compression is -performed. Valid values range from @w{8 KiB} to @w{1 GiB}. Default value -is two times the dictionary size, except for option @samp{-0} where it -defaults to @w{1 MiB}. Plzip will reduce the dictionary size if it is -larger than the data size specified. @xref{Minimum file sizes}. +When compressing, set the size in bytes of the input data blocks. The input +file is divided in chunks of this size before compression is performed. +Valid values range from @w{8 KiB} to @w{1 GiB}. Default value is two times +the dictionary size, except for option @option{-0} where it defaults to +@w{1 MiB}. Plzip reduces the dictionary size if it is larger than the data +size specified. @xref{Minimum file sizes}. @item -c @itemx --stdout Compress or decompress to standard output; keep input files unchanged. If -compressing several files, each file is compressed independently. This -option (or @samp{-o}) is needed when reading from a named pipe (fifo) or +compressing several files, each file is compressed independently. (The +output consists of a sequence of independently compressed members). This +option (or @option{-o}) is needed when reading from a named pipe (fifo) or from a device. Use @w{@samp{lziprecover -cd -i}} to recover as much of the -decompressed data as possible when decompressing a corrupt file. @samp{-c} -overrides @samp{-o}. @samp{-c} has no effect when testing or listing. +decompressed data as possible when decompressing a corrupt file. @option{-c} +overrides @option{-o}. @option{-c} has no effect when testing or listing. @item -d @itemx --decompress -Decompress the files specified. If a file does not exist, can't be opened, -or the destination file already exists and @samp{--force} has not been -specified, plzip continues decompressing the rest of the files and exits with -error status 1. If a file fails to decompress, or is a terminal, plzip exits -immediately with error status 2 without decompressing the rest of the files. -A terminal is considered an uncompressed file, and therefore invalid. +Decompress the files specified. The integrity of the files specified is +checked. If a file does not exist, can't be opened, or the destination file +already exists and @option{--force} has not been specified, plzip continues +decompressing the rest of the files and exits with error status 1. If a file +fails to decompress, or is a terminal, plzip exits immediately with error +status 2 without decompressing the rest of the files. A terminal is +considered an uncompressed file, and therefore invalid. @item -f @itemx --force @@ -302,23 +306,23 @@ Keep (don't delete) input files during compression or decompression. Print the uncompressed size, compressed size, and percentage saved of the files specified. Trailing data are ignored. The values produced are correct even for multimember files. If more than one file is given, a final line -containing the cumulative sizes is printed. With @samp{-v}, the dictionary +containing the cumulative sizes is printed. With @option{-v}, the dictionary size, the number of members in the file, and the amount of trailing data (if -any) are also printed. With @samp{-vv}, the positions and sizes of each +any) are also printed. With @option{-vv}, the positions and sizes of each member in multimember files are also printed. If any file is damaged, does not exist, can't be opened, or is not regular, -the final exit status will be @w{> 0}. @samp{-lq} can be used to verify -quickly (without decompressing) the structural integrity of the files -specified. (Use @samp{--test} to verify the data integrity). @samp{-alq} -additionally verifies that none of the files specified contain trailing data. +the final exit status is @w{> 0}. @option{-lq} can be used to check quickly +(without decompressing) the structural integrity of the files specified. +(Use @option{--test} to check the data integrity). @option{-alq} +additionally checks that none of the files specified contain trailing data. @item -m @var{bytes} @itemx --match-length=@var{bytes} -When compressing, set the match length limit in bytes. After a match -this long is found, the search is finished. Valid values range from 5 to -273. Larger values usually give better compression ratios but longer -compression times. +When compressing, set the match length limit in bytes. After a match this +long is found, the search is finished. Valid values range from 5 to 273. +Larger values usually give better compression ratios but longer compression +times. @item -n @var{n} @itemx --threads=@var{n} @@ -339,17 +343,19 @@ can find the number of members in a lzip file by running @item -o @var{file} @itemx --output=@var{file} -If @samp{-c} has not been also specified, write the (de)compressed output to -@var{file}; keep input files unchanged. If compressing several files, each -file is compressed independently. This option (or @samp{-c}) is needed when -reading from a named pipe (fifo) or from a device. @w{@samp{-o -}} is -equivalent to @samp{-c}. @samp{-o} has no effect when testing or listing. +If @option{-c} has not been also specified, write the (de)compressed output +to @var{file}, automatically creating any missing parent directories; keep +input files unchanged. If compressing several files, each file is compressed +independently. (The output consists of a sequence of independently +compressed members). This option (or @option{-c}) is needed when reading +from a named pipe (fifo) or from a device. @w{@option{-o -}} is equivalent +to @option{-c}. @option{-o} has no effect when testing or listing. In order to keep backward compatibility with plzip versions prior to 1.9, when compressing from standard input and no other file names are given, the extension @samp{.lz} is appended to @var{file} unless it already ends in @samp{.lz} or @samp{.tlz}. This feature will be removed in a future version -of plzip. Meanwhile, redirection may be used instead of @samp{-o} to write +of plzip. Meanwhile, redirection may be used instead of @option{-o} to write the compressed output to a file without the extension @samp{.lz} in its name: @w{@samp{plzip < file > foo}}. @@ -359,14 +365,14 @@ Quiet operation. Suppress all messages. @item -s @var{bytes} @itemx --dictionary-size=@var{bytes} -When compressing, set the dictionary size limit in bytes. Plzip will use -for each file the largest dictionary size that does not exceed neither -the file size nor this limit. Valid values range from @w{4 KiB} to -@w{512 MiB}. Values 12 to 29 are interpreted as powers of two, meaning -2^12 to 2^29 bytes. Dictionary sizes are quantized so that they can be -coded in just one byte (@pxref{coded-dict-size}). If the size specified -does not match one of the valid sizes, it will be rounded upwards by -adding up to @w{(@var{bytes} / 8)} to it. +When compressing, set the dictionary size limit in bytes. Plzip uses for +each file the largest dictionary size that does not exceed neither the file +size nor this limit. Valid values range from @w{4 KiB} to @w{512 MiB}. +Values 12 to 29 are interpreted as powers of two, meaning 2^12 to 2^29 +bytes. Dictionary sizes are quantized so that they can be coded in just one +byte (@pxref{coded-dict-size}). If the size specified does not match one of +the valid sizes, it is 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 @@ -376,11 +382,11 @@ is affected at compression time by the choice of dictionary size limit. @itemx --test Check integrity of the files specified, 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 files. If a file +together with @option{-v} to see information about the files. If a file fails the test, does not exist, can't be opened, or is a terminal, plzip -continues checking the rest of the files. A final diagnostic is shown at -verbosity level 1 or higher if any file fails the test when testing -multiple files. +continues testing the rest of the files. A final diagnostic is shown at +verbosity level 1 or higher if any file fails the test when testing multiple +files. @item -v @itemx --verbose @@ -390,24 +396,24 @@ processed.@* When decompressing or testing, further -v's (up to 4) increase the verbosity level, showing status, compression ratio, dictionary size, decompressed size, and compressed size.@* -Two or more @samp{-v} options show the progress of (de)compression, +Two or more @option{-v} options show the progress of (de)compression, except for single-member files. @item -0 .. -9 Compression level. Set the compression parameters (dictionary size and match length limit) as shown in the table below. The default compression -level is @samp{-6}, equivalent to @w{@samp{-s8MiB -m36}}. Note that -@samp{-9} can be much slower than @samp{-0}. These options have no +level is @option{-6}, equivalent to @w{@option{-s8MiB -m36}}. Note that +@option{-9} can be much slower than @option{-0}. These options have no effect when decompressing, testing, or listing. -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 options @samp{--dictionary-size} and -@samp{--match-length} directly to achieve optimal performance. +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 options @option{--dictionary-size} and +@option{--match-length} directly to achieve optimal performance. -If several compression levels or @samp{-s} or @samp{-m} options are -given, the last setting is used. For example @w{@samp{-9 -s64MiB}} is -equivalent to @w{@samp{-s64MiB -m273}} +If several compression levels or @option{-s} or @option{-m} options are +given, the last setting is used. For example @w{@option{-9 -s64MiB}} is +equivalent to @w{@option{-s64MiB -m273}} @multitable {Level} {Dictionary size (-s)} {Match length limit (-m)} @item Level @tab Dictionary size (-s) @tab Match length limit (-m) @@ -461,28 +467,31 @@ and the value of LZ_API_VERSION (if defined). @end table -Numbers given as arguments to options may be followed by a multiplier -and an optional @samp{B} for "byte". +Numbers given as arguments to options may be expressed in decimal, +hexadecimal, or octal (using the same syntax as integer constants in C++), +and may be followed by a multiplier and an optional @samp{B} for "byte". Table of SI and binary prefixes (unit multipliers): -@multitable {Prefix} {kilobyte (10^3 = 1000)} {|} {Prefix} {kibibyte (2^10 = 1024)} +@multitable {Prefix} {kilobyte (10^3 = 1000)} {|} {Prefix} {kibibyte (2^10 = 1024)} @item Prefix @tab Value @tab | @tab Prefix @tab Value -@item k @tab kilobyte (10^3 = 1000) @tab | @tab Ki @tab kibibyte (2^10 = 1024) -@item M @tab megabyte (10^6) @tab | @tab Mi @tab mebibyte (2^20) -@item G @tab gigabyte (10^9) @tab | @tab Gi @tab gibibyte (2^30) -@item T @tab terabyte (10^12) @tab | @tab Ti @tab tebibyte (2^40) -@item P @tab petabyte (10^15) @tab | @tab Pi @tab pebibyte (2^50) -@item E @tab exabyte (10^18) @tab | @tab Ei @tab exbibyte (2^60) -@item Z @tab zettabyte (10^21) @tab | @tab Zi @tab zebibyte (2^70) -@item Y @tab yottabyte (10^24) @tab | @tab Yi @tab yobibyte (2^80) +@item k @tab kilobyte (10^3 = 1000) @tab | @tab Ki @tab kibibyte (2^10 = 1024) +@item M @tab megabyte (10^6) @tab | @tab Mi @tab mebibyte (2^20) +@item G @tab gigabyte (10^9) @tab | @tab Gi @tab gibibyte (2^30) +@item T @tab terabyte (10^12) @tab | @tab Ti @tab tebibyte (2^40) +@item P @tab petabyte (10^15) @tab | @tab Pi @tab pebibyte (2^50) +@item E @tab exabyte (10^18) @tab | @tab Ei @tab exbibyte (2^60) +@item Z @tab zettabyte (10^21) @tab | @tab Zi @tab zebibyte (2^70) +@item Y @tab yottabyte (10^24) @tab | @tab Yi @tab yobibyte (2^80) +@item R @tab ronnabyte (10^27) @tab | @tab Ri @tab robibyte (2^90) +@item Q @tab quettabyte (10^30) @tab | @tab Qi @tab quebibyte (2^100) @end multitable @sp 1 -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, 3 for an internal consistency error (e.g., bug) which caused -plzip to panic. +Exit status: 0 for a normal exit, 1 for environmental problems +(file not found, invalid command-line options, I/O errors, etc), 2 to +indicate a corrupt or invalid input file, 3 for an internal consistency +error (e.g., bug) which caused plzip to panic. @node Program design @@ -495,8 +504,8 @@ multimember compressed file. Each chunk is compressed in-place (using the same buffer for input and output), reducing the amount of RAM required. When decompressing, plzip decompresses as many members simultaneously as -worker threads are chosen. Files that were compressed with lzip will not -be decompressed faster than using lzip (unless the option @samp{-b} was used) +worker threads are chosen. Files that were compressed with lzip are not +decompressed faster than using lzip (unless the option @option{-b} was used) because lzip usually produces single-member files, which can't be decompressed in parallel. @@ -600,14 +609,14 @@ When compressing, plzip divides the input file into chunks and compresses as many chunks simultaneously as worker threads are chosen, 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 -least as large as the number of worker threads times the chunk size -(@pxref{--data-size}). Else some processors will not get any data to -compress, and compression will be proportionally slower. The maximum -speed increase achievable on a given file is limited by the ratio -@w{(file_size / data_size)}. For example, a tarball the size of gcc or -linux will scale up to 10 or 14 processors at level -9. +For this to work as expected (and roughly multiply the compression speed by +the number of available processors), the uncompressed file must be at least +as large as the number of worker threads times the chunk size +(@pxref{--data-size}). Else some processors do not get any data to compress, +and compression is proportionally slower. The maximum speed increase +achievable on a given file is limited by the ratio +@w{(file_size / data_size)}. For example, a tarball the size of gcc or linux +scales up to 10 or 14 processors at level -9. The following table shows the minimum uncompressed file size needed for full use of N processors at a given compression level, using the default @@ -657,7 +666,7 @@ represents one byte; a box like this: represents a variable number of bytes. @sp 1 -A lzip file consists of a series of independent "members" (compressed data +A lzip file consists of one or more independent "members" (compressed data sets). The members simply appear one after another in the file, with no additional information before, between, or after them. Each member can encode in compressed form up to @w{16 EiB - 1 byte} of uncompressed data. @@ -711,10 +720,10 @@ Size of the original uncompressed 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 +as a distributed index, improves the checking of stream integrity, and facilitates the safe recovery of undamaged members from multimember files. -Member size should be limited to @w{2 PiB} to prevent the data size field -from overflowing. +Lzip limits the member size to @w{2 PiB} to prevent the data size field from +overflowing. @end table @@ -733,12 +742,13 @@ example when writing to a tape. It is safe to append any amount of padding zero bytes to a lzip file. @item -Useful data added by the user; a cryptographically secure hash, a -description of file contents, etc. It is safe to append any amount of -text to a lzip file as long as none of the first four bytes of the text -match the corresponding byte in the string "LZIP", and the text does not -contain any zero bytes (null characters). Nonzero bytes and zero bytes -can't be safely mixed in trailing data. +Useful data added by the user; an "End Of File" string (to check that the +file has not been truncated), a cryptographically secure hash, a description +of file contents, etc. It is safe to append any amount of text to a lzip +file as long as none of the first four bytes of the text matches the +corresponding byte in the string "LZIP", and the text does not contain any +zero bytes (null characters). Nonzero bytes and zero bytes can't be safely +mixed in trailing data. @item Garbage added by some not totally successful copy operation. @@ -756,8 +766,8 @@ integrity information itself. Therefore it can be considered to be below the noise level. Additionally, the test used by plzip to discriminate trailing data from a corrupt header has a Hamming distance (HD) of 3, and the 3 bit flips must happen in different magic bytes for the test to -fail. In any case, the option @samp{--trailing-error} guarantees that -any corrupt header will be detected. +fail. In any case, the option @option{--trailing-error} guarantees that +any corrupt header is detected. @end itemize Trailing data are in no way part of the lzip file format, but tools @@ -767,7 +777,7 @@ possible in the presence of trailing data. Trailing data can be safely ignored in most cases. In some cases, like that of user-added data, they are 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}. +@option{--trailing-error} can be used. @xref{--trailing-error}. @node Examples @@ -777,8 +787,8 @@ where a file containing trailing data must be rejected, the option 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 -option @samp{--keep} to plzip and don't remove the original file until you -verify the compressed file with a command like +option @option{--keep} to plzip and don't remove the original file until you +check the compressed file with a command like @w{@samp{plzip -cd file.lz | cmp file -}}. Most RAM errors happening during compression can only be detected by comparing the compressed file with the original because the corruption happens before plzip compresses the RAM @@ -823,7 +833,7 @@ plzip -d file.lz @sp 1 @noindent -Example 5: Verify the integrity of the compressed file @samp{file.lz} and +Example 5: Check the integrity of the compressed file @samp{file.lz} and show status. @example @@ -1,5 +1,5 @@ /* Plzip - Massively parallel implementation of lzip - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -48,12 +48,13 @@ void list_line( const unsigned long long uncomp_size, int list_files( const std::vector< std::string > & filenames, - const bool ignore_trailing, const bool loose_trailing ) + const Cl_options & cl_opts ) { unsigned long long total_comp = 0, total_uncomp = 0; int files = 0, retval = 0; bool first_post = true; bool stdin_used = false; + for( unsigned i = 0; i < filenames.size(); ++i ) { const bool from_stdin = ( filenames[i] == "-" ); @@ -65,7 +66,7 @@ int list_files( const std::vector< std::string > & filenames, open_instream( input_filename, &in_stats, false, true ); if( infd < 0 ) { set_retval( retval, 1 ); continue; } - const Lzip_index lzip_index( infd, ignore_trailing, loose_trailing ); + const Lzip_index lzip_index( infd, cl_opts ); close( infd ); if( lzip_index.retval() != 0 ) { @@ -1,5 +1,5 @@ /* Plzip - Massively parallel implementation of lzip - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -68,8 +68,8 @@ public: inline bool isvalid_ds( const unsigned dictionary_size ) - { return ( dictionary_size >= min_dictionary_size && - dictionary_size <= max_dictionary_size ); } + { return dictionary_size >= min_dictionary_size && + dictionary_size <= max_dictionary_size; } inline int real_bits( unsigned value ) @@ -84,35 +84,35 @@ const uint8_t lzip_magic[4] = { 0x4C, 0x5A, 0x49, 0x50 }; // "LZIP" struct Lzip_header { - uint8_t data[6]; // 0-3 magic bytes + enum { size = 6 }; + uint8_t data[size]; // 0-3 magic bytes // 4 version // 5 coded dictionary size - enum { size = 6 }; void set_magic() { std::memcpy( data, lzip_magic, 4 ); data[4] = 1; } - bool verify_magic() const - { return ( std::memcmp( data, lzip_magic, 4 ) == 0 ); } + bool check_magic() const { return std::memcmp( data, lzip_magic, 4 ) == 0; } - bool verify_prefix( const int sz ) const // detect (truncated) header + bool check_prefix( const int sz ) const // detect (truncated) header { for( int i = 0; i < sz && i < 4; ++i ) if( data[i] != lzip_magic[i] ) return false; - return ( sz > 0 ); + return sz > 0; } - bool verify_corrupt() const // detect corrupt header + + bool check_corrupt() const // detect corrupt header { int matches = 0; for( int i = 0; i < 4; ++i ) if( data[i] == lzip_magic[i] ) ++matches; - return ( matches > 1 && matches < 4 ); + return matches > 1 && matches < 4; } uint8_t version() const { return data[4]; } - bool verify_version() const { return ( data[4] == 1 ); } + bool check_version() const { return data[4] == 1; } unsigned dictionary_size() const { - unsigned sz = ( 1 << ( data[5] & 0x1F ) ); + unsigned sz = 1 << ( data[5] & 0x1F ); if( sz > min_dictionary_size ) sz -= ( sz / 16 ) * ( ( data[5] >> 5 ) & 7 ); return sz; @@ -128,23 +128,23 @@ struct Lzip_header const unsigned fraction = base_size / 16; for( unsigned i = 7; i >= 1; --i ) if( base_size - ( i * fraction ) >= sz ) - { data[5] |= ( i << 5 ); break; } + { data[5] |= i << 5; break; } } return true; } - bool verify() const - { return verify_magic() && verify_version() && + bool check() const + { return check_magic() && check_version() && isvalid_ds( dictionary_size() ); } }; struct Lzip_trailer { - uint8_t data[20]; // 0-3 CRC32 of the uncompressed data + enum { size = 20 }; + uint8_t data[size]; // 0-3 CRC32 of the uncompressed data // 4-11 size of the uncompressed data // 12-19 member size including header and trailer - enum { size = 20 }; unsigned data_crc() const { @@ -176,7 +176,7 @@ struct Lzip_trailer void member_size( unsigned long long sz ) { for( int i = 12; i <= 19; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; } } - bool verify_consistency() const // check internal consistency + bool check_consistency() const // check internal consistency { const unsigned crc = data_crc(); const unsigned long long dsize = data_size(); @@ -192,6 +192,15 @@ struct Lzip_trailer }; +struct Cl_options // command-line options + { + bool ignore_trailing; + bool loose_trailing; + + Cl_options() : ignore_trailing( true ), loose_trailing( false ) {} + }; + + inline void set_retval( int & retval, const int new_val ) { if( retval < new_val ) retval = new_val; } @@ -220,7 +229,7 @@ int compress( const unsigned long long cfile_size, const Pretty_print & pp, const int debug_level ); // defined in lzip_index.cc -class Lzip_index; +class Lzip_index; // forward declaration // defined in dec_stdout.cc int dec_stdout( const int num_workers, const int infd, const int outfd, @@ -228,11 +237,10 @@ int dec_stdout( const int num_workers, const int infd, const int outfd, const int out_slots, const Lzip_index & lzip_index ); // defined in dec_stream.cc -int dec_stream( const unsigned long long cfile_size, - const int num_workers, const int infd, const int outfd, +int dec_stream( const unsigned long long cfile_size, const int num_workers, + const int infd, const int outfd, const Cl_options & cl_opts, const Pretty_print & pp, const int debug_level, - const int in_slots, const int out_slots, - const bool ignore_trailing, const bool loose_trailing ); + const int in_slots, const int out_slots ); // defined in decompress.cc int preadblock( const int fd, uint8_t * const buf, const int size, @@ -245,15 +253,14 @@ void show_results( const unsigned long long in_size, const unsigned long long out_size, const unsigned dictionary_size, const bool testing ); int decompress( const unsigned long long cfile_size, int num_workers, - const int infd, const int outfd, const Pretty_print & pp, - const int debug_level, const int in_slots, - const int out_slots, const bool ignore_trailing, - const bool loose_trailing, const bool infd_isreg, - const bool one_to_one ); + const int infd, const int outfd, const Cl_options & cl_opts, + const Pretty_print & pp, const int debug_level, + const int in_slots, const int out_slots, + const bool infd_isreg, const bool one_to_one ); // defined in list.cc int list_files( const std::vector< std::string > & filenames, - const bool ignore_trailing, const bool loose_trailing ); + const Cl_options & cl_opts ); // defined in main.cc struct stat; @@ -290,7 +297,7 @@ public: ~Slot_tally() { xdestroy_cond( &slot_av ); xdestroy_mutex( &mutex ); } - bool all_free() { return ( num_free == num_slots ); } + bool all_free() { return num_free == num_slots; } void get_slot() // wait for a free slot { diff --git a/lzip_index.cc b/lzip_index.cc index b681261..8d1aa0c 100644 --- a/lzip_index.cc +++ b/lzip_index.cc @@ -1,5 +1,5 @@ /* Plzip - Massively parallel implementation of lzip - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -43,17 +43,16 @@ int seek_read( const int fd, uint8_t * const buf, const int size, } // end namespace -bool Lzip_index::check_header_error( const Lzip_header & header, - const bool first ) +bool Lzip_index::check_header( const Lzip_header & header, const bool first ) { - if( !header.verify_magic() ) + if( !header.check_magic() ) { error_ = bad_magic_msg; retval_ = 2; if( first ) bad_magic_ = true; - return true; } - if( !header.verify_version() ) - { error_ = bad_version( header.version() ); retval_ = 2; return true; } + return false; } + if( !header.check_version() ) + { error_ = bad_version( header.version() ); retval_ = 2; return false; } if( !isvalid_ds( header.dictionary_size() ) ) - { error_ = bad_dict_msg; retval_ = 2; return true; } - return false; + { error_ = bad_dict_msg; retval_ = 2; return false; } + return true; } void Lzip_index::set_errno_error( const char * const msg ) @@ -74,7 +73,7 @@ void Lzip_index::set_num_error( const char * const msg, unsigned long long num ) bool Lzip_index::read_header( const int fd, Lzip_header & header, const long long pos ) { - if( seek_read( fd, header.data, Lzip_header::size, pos ) != Lzip_header::size ) + if( seek_read( fd, header.data, header.size, pos ) != header.size ) { set_errno_error( "Error reading member header: " ); return false; } return true; } @@ -82,8 +81,7 @@ bool Lzip_index::read_header( const int fd, Lzip_header & header, // If successful, push last member and set pos to member header. bool Lzip_index::skip_trailing_data( const int fd, unsigned long long & pos, - const bool ignore_trailing, - const bool loose_trailing ) + const Cl_options & cl_opts ) { if( pos < min_member_size ) return false; enum { block_size = 16384, @@ -104,34 +102,33 @@ bool Lzip_index::skip_trailing_data( const int fd, unsigned long long & pos, if( buffer[i-1] <= max_msb ) // most significant byte of member_size { const Lzip_trailer & trailer = - *(const Lzip_trailer *)( buffer + i - Lzip_trailer::size ); + *(const Lzip_trailer *)( buffer + i - trailer.size ); const unsigned long long member_size = trailer.member_size(); if( member_size == 0 ) // skip trailing zeros - { while( i > Lzip_trailer::size && buffer[i-9] == 0 ) --i; continue; } - if( member_size > ipos + i || !trailer.verify_consistency() ) - continue; + { while( i > trailer.size && buffer[i-9] == 0 ) --i; continue; } + if( member_size > ipos + i || !trailer.check_consistency() ) continue; Lzip_header header; if( !read_header( fd, header, ipos + i - member_size ) ) return false; - if( !header.verify() ) continue; + if( !header.check() ) continue; const Lzip_header & header2 = *(const Lzip_header *)( buffer + i ); - const bool full_h2 = bsize - i >= Lzip_header::size; - if( header2.verify_prefix( bsize - i ) ) // last member + const bool full_h2 = bsize - i >= header.size; + if( header2.check_prefix( bsize - i ) ) // last member { if( !full_h2 ) error_ = "Last member in input file is truncated."; - else if( !check_header_error( header2, false ) ) + else if( check_header( header2, false ) ) error_ = "Last member in input file is truncated or corrupt."; retval_ = 2; return false; } - if( !loose_trailing && full_h2 && header2.verify_corrupt() ) + if( !cl_opts.loose_trailing && full_h2 && header2.check_corrupt() ) { error_ = corrupt_mm_msg; retval_ = 2; return false; } - if( !ignore_trailing ) + if( !cl_opts.ignore_trailing ) { error_ = trailing_msg; retval_ = 2; return false; } - pos = ipos + i - member_size; + pos = ipos + i - member_size; // good member const unsigned dictionary_size = header.dictionary_size(); - member_vector.push_back( Member( 0, trailer.data_size(), pos, - member_size, dictionary_size ) ); if( dictionary_size_ < dictionary_size ) dictionary_size_ = dictionary_size; + member_vector.push_back( Member( 0, trailer.data_size(), pos, + member_size, dictionary_size ) ); return true; } if( ipos == 0 ) @@ -146,8 +143,7 @@ bool Lzip_index::skip_trailing_data( const int fd, unsigned long long & pos, } -Lzip_index::Lzip_index( const int infd, const bool ignore_trailing, - const bool loose_trailing ) +Lzip_index::Lzip_index( const int infd, const Cl_options & cl_opts ) : insize( lseek( infd, 0, SEEK_END ) ), retval_( 0 ), dictionary_size_( 0 ), bad_magic_( false ) { @@ -160,42 +156,38 @@ Lzip_index::Lzip_index( const int infd, const bool ignore_trailing, retval_ = 2; return; } Lzip_header header; - if( !read_header( infd, header, 0 ) ) return; - if( check_header_error( header, true ) ) return; + if( !read_header( infd, header, 0 ) || + !check_header( header, true ) ) return; unsigned long long pos = insize; // always points to a header or to EOF while( pos >= min_member_size ) { Lzip_trailer trailer; - if( seek_read( infd, trailer.data, Lzip_trailer::size, - pos - Lzip_trailer::size ) != Lzip_trailer::size ) + if( seek_read( infd, trailer.data, trailer.size, pos - trailer.size ) != + trailer.size ) { set_errno_error( "Error reading member trailer: " ); break; } const unsigned long long member_size = trailer.member_size(); - if( member_size > pos || !trailer.verify_consistency() ) // bad trailer + if( member_size > pos || !trailer.check_consistency() ) // bad trailer { if( member_vector.empty() ) - { if( skip_trailing_data( infd, pos, ignore_trailing, loose_trailing ) ) - continue; else return; } - set_num_error( "Bad trailer at pos ", pos - Lzip_trailer::size ); - break; + { if( skip_trailing_data( infd, pos, cl_opts ) ) continue; return; } + set_num_error( "Bad trailer at pos ", pos - trailer.size ); break; } if( !read_header( infd, header, pos - member_size ) ) break; - if( !header.verify() ) // bad header + if( !header.check() ) // bad header { if( member_vector.empty() ) - { if( skip_trailing_data( infd, pos, ignore_trailing, loose_trailing ) ) - continue; else return; } - set_num_error( "Bad header at pos ", pos - member_size ); - break; + { if( skip_trailing_data( infd, pos, cl_opts ) ) continue; return; } + set_num_error( "Bad header at pos ", pos - member_size ); break; } - pos -= member_size; + pos -= member_size; // good member const unsigned dictionary_size = header.dictionary_size(); - member_vector.push_back( Member( 0, trailer.data_size(), pos, - member_size, dictionary_size ) ); if( dictionary_size_ < dictionary_size ) dictionary_size_ = dictionary_size; + member_vector.push_back( Member( 0, trailer.data_size(), pos, + member_size, dictionary_size ) ); } - if( pos != 0 || member_vector.empty() ) + if( pos != 0 || member_vector.empty() || retval_ != 0 ) { member_vector.clear(); if( retval_ == 0 ) { error_ = "Can't create file index."; retval_ = 2; } diff --git a/lzip_index.h b/lzip_index.h index c8699a7..a994f1c 100644 --- a/lzip_index.h +++ b/lzip_index.h @@ -1,5 +1,5 @@ /* Plzip - Massively parallel implementation of lzip - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -16,13 +16,13 @@ */ #ifndef INT64_MAX -#define INT64_MAX 0x7FFFFFFFFFFFFFFFLL +#define INT64_MAX 0x7FFFFFFFFFFFFFFFLL #endif class Block { - long long pos_, size_; // pos + size <= INT64_MAX + long long pos_, size_; // pos >= 0, size >= 0, pos + size <= INT64_MAX public: Block( const long long p, const long long s ) : pos_( p ), size_( s ) {} @@ -43,9 +43,11 @@ class Lzip_index Block dblock, mblock; // data block, member block unsigned dictionary_size; - Member( const long long dp, const long long ds, - const long long mp, const long long ms, const unsigned dict_size ) - : dblock( dp, ds ), mblock( mp, ms ), dictionary_size( dict_size ) {} + Member( const long long dpos, const long long dsize, + const long long mpos, const long long msize, + const unsigned dict_size ) + : dblock( dpos, dsize ), mblock( mpos, msize ), + dictionary_size( dict_size ) {} }; std::vector< Member > member_vector; @@ -55,16 +57,15 @@ class Lzip_index unsigned dictionary_size_; // largest dictionary size in the file bool bad_magic_; // bad magic in first header - bool check_header_error( const Lzip_header & header, const bool first ); + bool check_header( const Lzip_header & header, const bool first ); void set_errno_error( const char * const msg ); void set_num_error( const char * const msg, unsigned long long num ); bool read_header( const int fd, Lzip_header & header, const long long pos ); bool skip_trailing_data( const int fd, unsigned long long & pos, - const bool ignore_trailing, const bool loose_trailing ); + const Cl_options & cl_opts ); public: - Lzip_index( const int infd, const bool ignore_trailing, - const bool loose_trailing ); + Lzip_index( const int infd, const Cl_options & cl_opts ); long members() const { return member_vector.size(); } const std::string & error() const { return error_; } @@ -1,6 +1,6 @@ /* Plzip - Massively parallel implementation of lzip Copyright (C) 2009 Laszlo Ersek. - Copyright (C) 2009-2022 Antonio Diaz Diaz. + Copyright (C) 2009-2024 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 @@ -17,16 +17,16 @@ */ /* 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, 3 for an internal consistency error - (e.g., bug) which caused plzip to panic. + (file not found, invalid command-line options, I/O errors, etc), 2 to + indicate a corrupt or invalid input file, 3 for an internal consistency + error (e.g., bug) which caused plzip to panic. */ #define _FILE_OFFSET_BITS 64 #include <algorithm> #include <cerrno> -#include <climits> +#include <climits> // SSIZE_MAX #include <csignal> #include <cstdio> #include <cstdlib> @@ -34,7 +34,7 @@ #include <string> #include <vector> #include <fcntl.h> -#include <stdint.h> +#include <stdint.h> // SIZE_MAX #include <unistd.h> #include <utime.h> #include <sys/stat.h> @@ -77,7 +77,7 @@ int verbosity = 0; namespace { const char * const program_name = "plzip"; -const char * const program_year = "2022"; +const char * const program_year = "2024"; const char * invocation_name = program_name; // default value const struct { const char * from; const char * to; } known_extensions[] = { @@ -102,18 +102,19 @@ bool delete_output_on_interrupt = false; void show_help( const long num_online ) { - std::printf( "Plzip is a massively parallel (multi-threaded) implementation of lzip, fully\n" + std::printf( "Plzip is a massively parallel (multi-threaded) implementation of lzip,\n" "compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib.\n" "\nLzip is a lossless data compressor with a user interface similar to the one\n" "of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov\n" - "chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity\n" - "checking to maximize interoperability and optimize safety. Lzip can compress\n" - "about as fast as gzip (lzip -0) or compress most files more than bzip2\n" - "(lzip -9). Decompression speed is intermediate between gzip and bzip2.\n" - "Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip\n" - "has been designed, written, and tested with great care to replace gzip and\n" - "bzip2 as the standard general-purpose compressed format for unix-like\n" - "systems.\n" + "chain-Algorithm' (LZMA) stream format to maximize interoperability. The\n" + "maximum dictionary size is 512 MiB so that any lzip file can be decompressed\n" + "on 32-bit machines. Lzip provides accurate and robust 3-factor integrity\n" + "checking. Lzip can compress about as fast as gzip (lzip -0) or compress most\n" + "files more than bzip2 (lzip -9). Decompression speed is intermediate between\n" + "gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery\n" + "perspective. Lzip has been designed, written, and tested with great care to\n" + "replace gzip and bzip2 as the standard general-purpose compressed format for\n" + "Unix-like systems.\n" "\nPlzip can compress/decompress large files on multiprocessor machines much\n" "faster than lzip, at the cost of a slightly reduced compression ratio (0.4\n" "to 2 percent larger compressed files). Note that the number of usable\n" @@ -127,7 +128,7 @@ void show_help( const long num_online ) " -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 write to standard output, keep input files\n" - " -d, --decompress decompress\n" + " -d, --decompress decompress, test compressed file integrity\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" @@ -155,32 +156,46 @@ void show_help( const long num_online ) "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" - "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 options --dictionary-size and --match-length\n" - "directly to achieve optimal performance.\n" + "Dictionary sizes 12 to 29 are interpreted as powers of two, meaning 2^12 to\n" + "2^29 bytes.\n" + "\nThe bidimensional parameter space of LZMA can't be mapped to a linear scale\n" + "optimal for all files. If your files are large, very repetitive, etc, you\n" + "may need to use the options --dictionary-size and --match-length directly\n" + "to achieve optimal performance.\n" "\nTo extract all the files from archive 'foo.tar.lz', use the commands\n" "'tar -xf foo.tar.lz' or 'plzip -cd foo.tar.lz | tar -xf -'.\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" - "invalid input file, 3 for an internal consistency error (e.g., bug) which\n" - "caused plzip to panic.\n" + "\nExit status: 0 for a normal exit, 1 for environmental problems\n" + "(file not found, invalid command-line options, I/O errors, etc), 2 to\n" + "indicate a corrupt or invalid input file, 3 for an internal consistency\n" + "error (e.g., bug) which caused plzip to panic.\n" "\nReport bugs to lzip-bug@nongnu.org\n" "Plzip home page: http://www.nongnu.org/lzip/plzip.html\n" ); } +void show_lzlib_version() + { + std::printf( "Using lzlib %s\n", LZ_version() ); +#if !defined LZ_API_VERSION + std::fputs( "LZ_API_VERSION is not defined.\n", stdout ); +#elif LZ_API_VERSION >= 1012 + std::printf( "Using LZ_API_VERSION = %u\n", LZ_api_version() ); +#else + std::printf( "Compiled with LZ_API_VERSION = %u. " + "Using an unknown LZ_API_VERSION\n", LZ_API_VERSION ); +#endif + } + + void show_version() { std::printf( "%s %s\n", program_name, PROGVERSION ); std::printf( "Copyright (C) 2009 Laszlo Ersek.\n" ); std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); - std::printf( "Using lzlib %s\n", LZ_version() ); std::printf( "License GPLv2+: GNU GPL version 2 or later <http://gnu.org/licenses/gpl.html>\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" ); + show_lzlib_version(); } @@ -226,18 +241,7 @@ int check_lib() std::printf( "warning: LZ_API_VERSION != LZ_api_version() (%u vs %u)\n", LZ_API_VERSION, LZ_api_version() ); } #endif - if( verbosity >= 1 ) - { - std::printf( "Using lzlib %s\n", LZ_version() ); -#if !defined LZ_API_VERSION - std::fputs( "LZ_API_VERSION is not defined.\n", stdout ); -#elif LZ_API_VERSION >= 1012 - std::printf( "Using LZ_API_VERSION = %u\n", LZ_api_version() ); -#else - std::printf( "Compiled with LZ_API_VERSION = %u. " - "Using an unknown LZ_API_VERSION\n", LZ_API_VERSION ); -#endif - } + if( verbosity >= 1 ) show_lzlib_version(); return retval; } @@ -267,16 +271,15 @@ const char * bad_version( const unsigned version ) const char * format_ds( const unsigned dictionary_size ) { - enum { bufsize = 16, factor = 1024 }; + enum { bufsize = 16, factor = 1024, n = 3 }; static char buf[bufsize]; - const char * const prefix[8] = - { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" }; + const char * const prefix[n] = { "Ki", "Mi", "Gi" }; const char * p = ""; const char * np = " "; unsigned num = dictionary_size; bool exact = ( num % factor == 0 ); - for( int i = 0; i < 8 && ( num > 9999 || ( exact && num >= factor ) ); ++i ) + for( int i = 0; i < n && ( num > 9999 || ( exact && num >= factor ) ); ++i ) { num /= factor; if( num % factor != 0 ) exact = false; p = prefix[i]; np = ""; } snprintf( buf, bufsize, "%s%4u %sB", np, num, p ); @@ -291,12 +294,12 @@ void show_header( const unsigned dictionary_size ) namespace { -// separate large numbers >= 100_000 in groups of 3 digits using '_' +// separate numbers of 5 or more digits in groups of 3 digits using '_' const char * format_num3( unsigned long long num ) { - const char * const si_prefix = "kMGTPEZY"; - const char * const binary_prefix = "KMGTPEZY"; - enum { buffers = 8, bufsize = 4 * sizeof (long long) }; + enum { buffers = 8, bufsize = 4 * sizeof num, n = 10 }; + const char * const si_prefix = "kMGTPEZYRQ"; + const char * const binary_prefix = "KMGTPEZYRQ"; static char buffer[buffers][bufsize]; // circle of static buffers for printf static int current = 0; @@ -306,15 +309,15 @@ const char * format_num3( unsigned long long num ) if( num > 1024 ) { char prefix = 0; // try binary first, then si - for( int i = 0; i < 8 && num >= 1024 && num % 1024 == 0; ++i ) + for( int i = 0; i < n && num != 0 && num % 1024 == 0; ++i ) { num /= 1024; prefix = binary_prefix[i]; } if( prefix ) *(--p) = 'i'; else - for( int i = 0; i < 8 && num >= 1000 && num % 1000 == 0; ++i ) + for( int i = 0; i < n && num != 0 && num % 1000 == 0; ++i ) { num /= 1000; prefix = si_prefix[i]; } if( prefix ) *(--p) = prefix; } - const bool split = num >= 100000; + const bool split = num >= 10000; for( int i = 0; ; ) { @@ -325,6 +328,16 @@ const char * format_num3( unsigned long long num ) } +void show_option_error( const char * const arg, const char * const msg, + const char * const option_name ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: '%s': %s option '%s'.\n", + program_name, arg, msg, option_name ); + } + + +// Recognized formats: <num>k, <num>Ki, <num>[MGTPEZYRQ][i] unsigned long long getnum( const char * const arg, const char * const option_name, const unsigned long long llimit, @@ -334,12 +347,8 @@ unsigned long long getnum( const char * const arg, errno = 0; unsigned long long result = strtoull( arg, &tail, 0 ); if( tail == arg ) - { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Bad or missing numerical argument in " - "option '%s'.\n", program_name, option_name ); - std::exit( 1 ); - } + { show_option_error( arg, "Bad or missing numerical argument in", + option_name ); std::exit( 1 ); } if( !errno && tail[0] ) { @@ -347,6 +356,8 @@ unsigned long long getnum( const char * const arg, int exponent = 0; // 0 = bad multiplier switch( tail[0] ) { + case 'Q': exponent = 10; break; + case 'R': exponent = 9; break; case 'Y': exponent = 8; break; case 'Z': exponent = 7; break; case 'E': exponent = 6; break; @@ -358,12 +369,8 @@ unsigned long long getnum( const char * const arg, case 'k': if( factor == 1000 ) exponent = 1; break; } if( exponent <= 0 ) - { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Bad multiplier in numerical argument of " - "option '%s'.\n", program_name, option_name ); - std::exit( 1 ); - } + { show_option_error( arg, "Bad multiplier in numerical argument of", + option_name ); std::exit( 1 ); } for( int i = 0; i < exponent; ++i ) { if( ulimit / factor >= result ) result *= factor; @@ -374,8 +381,8 @@ unsigned long long getnum( const char * const arg, if( errno ) { if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Numerical argument out of limits [%s,%s] " - "in option '%s'.\n", program_name, format_num3( llimit ), + std::fprintf( stderr, "%s: '%s': Value out of limits [%s,%s] in " + "option '%s'.\n", program_name, arg, format_num3( llimit ), format_num3( ulimit ), option_name ); std::exit( 1 ); } @@ -447,7 +454,7 @@ void set_d_outname( const std::string & name, const int eindex ) } output_filename = name; output_filename += ".out"; if( verbosity >= 1 ) - std::fprintf( stderr, "%s: Can't guess original name for '%s' -- using '%s'\n", + std::fprintf( stderr, "%s: %s: Can't guess original name -- using '%s'\n", program_name, name.c_str(), output_filename.c_str() ); } @@ -469,9 +476,9 @@ int open_instream( const char * const name, struct stat * const in_statsp, if( i != 0 || ( !S_ISREG( mode ) && ( !can_read || one_to_one ) ) ) { if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Input file '%s' is not a regular file%s.\n", + std::fprintf( stderr, "%s: %s: Input file is not a regular file%s.\n", program_name, name, ( can_read && one_to_one ) ? - ",\n and neither '-c' nor '-o' were specified" : "" ); + ",\n and neither '-c' nor '-o' were specified" : "" ); close( infd ); infd = -1; } @@ -488,7 +495,7 @@ int open_instream2( const char * const name, struct stat * const in_statsp, if( program_mode == m_compress && !recompress && eindex >= 0 ) { if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Input file '%s' already has '%s' suffix.\n", + std::fprintf( stderr, "%s: %s: Input file already has '%s' suffix.\n", program_name, name, known_extensions[eindex].from ); return -1; } @@ -496,6 +503,33 @@ int open_instream2( const char * const name, struct stat * const in_statsp, } +bool make_dirs( const std::string & name ) + { + int i = name.size(); + while( i > 0 && name[i-1] != '/' ) --i; // remove last component + while( i > 0 && name[i-1] == '/' ) --i; // remove slash(es) + const int dirsize = i; // size of dirname without trailing slash(es) + + for( i = 0; i < dirsize; ) // if dirsize == 0, dirname is '/' or empty + { + while( i < dirsize && name[i] == '/' ) ++i; + const int first = i; + while( i < dirsize && name[i] != '/' ) ++i; + if( first < i ) + { + const std::string partial( name, 0, i ); + const mode_t mode = S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH; + struct stat st; + if( stat( partial.c_str(), &st ) == 0 ) + { if( !S_ISDIR( st.st_mode ) ) { errno = ENOTDIR; return false; } } + else if( mkdir( partial.c_str(), mode ) != 0 && errno != EEXIST ) + return false; // if EEXIST, another process created the dir + } + } + return true; + } + + bool open_outstream( const bool force, const bool protect ) { const mode_t usr_rw = S_IRUSR | S_IWUSR; @@ -504,18 +538,21 @@ bool open_outstream( const bool force, const bool protect ) 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 ) delete_output_on_interrupt = true; - else if( verbosity >= 0 ) - { + outfd = -1; + if( output_filename.size() && + output_filename[output_filename.size()-1] == '/' ) errno = EISDIR; + else { + if( !protect && !make_dirs( output_filename ) ) + { show_file_error( output_filename.c_str(), + "Error creating intermediate directory", errno ); return false; } + outfd = open( output_filename.c_str(), flags, outfd_mode ); + if( outfd >= 0 ) { delete_output_on_interrupt = true; return true; } if( errno == EEXIST ) - std::fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n", - program_name, output_filename.c_str() ); - else - std::fprintf( stderr, "%s: Can't create output file '%s': %s\n", - program_name, output_filename.c_str(), std::strerror( errno ) ); + { show_file_error( output_filename.c_str(), + "Output file already exists, skipping." ); return false; } } - return ( outfd >= 0 ); + show_file_error( output_filename.c_str(), "Can't create output file", errno ); + return false; } @@ -545,13 +582,13 @@ void cleanup_and_fail( const int retval ) { delete_output_on_interrupt = false; if( saved_verbosity >= 0 ) - std::fprintf( stderr, "%s: Deleting output file '%s', if it exists.\n", + std::fprintf( stderr, "%s: %s: Deleting output file, if it exists.\n", program_name, output_filename.c_str() ); if( outfd >= 0 ) { close( outfd ); outfd = -1; } if( std::remove( output_filename.c_str() ) != 0 && errno != ENOENT && saved_verbosity >= 0 ) - std::fprintf( stderr, "%s: WARNING: deletion of output file " - "(apparently) failed.\n", program_name ); + std::fprintf( stderr, "%s: warning: deletion of output file failed: %s\n", + program_name, std::strerror( errno ) ); } std::exit( retval ); } @@ -596,7 +633,7 @@ void close_and_set_permissions( const struct stat * const in_statsp ) if( in_statsp ) { const mode_t mode = in_statsp->st_mode; - // fchown will in many cases return with EPERM, which can be safely ignored. + // fchown in many cases returns with EPERM, which can be safely ignored. if( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) == 0 ) { if( fchmod( outfd, mode ) != 0 ) warning = true; } else @@ -605,10 +642,8 @@ void close_and_set_permissions( const struct stat * const in_statsp ) warning = true; } if( close( outfd ) != 0 ) - { - show_error( "Error closing output file", errno ); - cleanup_and_fail( 1 ); - } + { show_file_error( output_filename.c_str(), "Error closing output file", + errno ); cleanup_and_fail( 1 ); } outfd = -1; delete_output_on_interrupt = false; if( in_statsp ) @@ -619,7 +654,8 @@ void close_and_set_permissions( const struct stat * const in_statsp ) if( utime( output_filename.c_str(), &t ) != 0 ) warning = true; } if( warning && verbosity >= 1 ) - show_error( "Can't change output file attributes." ); + show_file_error( output_filename.c_str(), + "warning: can't change output file attributes", errno ); } } // end namespace @@ -708,8 +744,8 @@ long sysconf( int flag ) int main( const int argc, const char * const argv[] ) { - /* Mapping from gzip/bzip2 style 1..9 compression modes - to the corresponding LZMA compression modes. */ + /* Mapping from gzip/bzip2 style 0..9 compression levels to the + corresponding LZMA compression parameters. */ const Lzma_options option_mapping[] = { { 65535, 16 }, // -0 (65535,16 chooses fast encoder) @@ -730,10 +766,9 @@ int main( const int argc, const char * const argv[] ) int in_slots = 4; int out_slots = 64; Mode program_mode = m_compress; + Cl_options cl_opts; // command-line options bool force = false; - bool ignore_trailing = true; bool keep_input_files = false; - bool loose_trailing = false; bool recompress = false; bool to_stdout = false; if( argc > 0 ) invocation_name = argv[0]; @@ -799,7 +834,7 @@ int main( const int argc, const char * const argv[] ) 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 'a': cl_opts.ignore_trailing = false; break; case 'b': break; case 'B': data_size = getnum( arg, pn, 2 * LZ_min_dictionary_size(), 2 * LZ_max_dictionary_size() ); break; @@ -826,9 +861,9 @@ int main( const int argc, const char * const argv[] ) case opt_chk: return check_lib(); case opt_dbg: debug_level = getnum( arg, pn, 0, 3 ); break; case opt_in: in_slots = getnum( arg, pn, 1, 64 ); break; - case opt_lt: loose_trailing = true; break; + case opt_lt: cl_opts.loose_trailing = true; break; case opt_out: out_slots = getnum( arg, pn, 1, 1024 ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options @@ -850,8 +885,7 @@ int main( const int argc, const char * const argv[] ) } if( filenames.empty() ) filenames.push_back("-"); - if( program_mode == m_list ) - return list_files( filenames, ignore_trailing, loose_trailing ); + if( program_mode == m_list ) return list_files( filenames, cl_opts ); const bool fast = encoder_options.dictionary_size == 65535 && encoder_options.match_len_limit == 16; @@ -896,11 +930,11 @@ int main( const int argc, const char * const argv[] ) int retval = 0; const bool one_to_one = !to_stdout && program_mode != m_test && !to_file; bool stdin_used = false; + struct stat in_stats; for( unsigned i = 0; i < filenames.size(); ++i ) { std::string input_filename; int infd; - struct stat in_stats; pp.set_name( filenames[i] ); if( filenames[i] == "-" ) @@ -917,7 +951,7 @@ int main( const int argc, const char * const argv[] ) eindex, one_to_one, recompress ); if( infd < 0 ) { set_retval( retval, 1 ); continue; } if( !check_tty_in( pp.name(), infd, program_mode, retval ) ) continue; - if( one_to_one ) // open outfd after verifying infd + if( one_to_one ) // open outfd after checking infd { if( program_mode == m_compress ) set_c_outname( input_filename, true, true ); @@ -930,7 +964,7 @@ int main( const int argc, const char * const argv[] ) if( one_to_one && !check_tty_out( program_mode ) ) { set_retval( retval, 1 ); return retval; } // don't delete a tty - if( to_file && outfd < 0 ) // open outfd after verifying infd + if( to_file && outfd < 0 ) // open outfd after checking infd { if( program_mode == m_compress ) set_c_outname( default_output_filename, filenames_given, false ); @@ -950,9 +984,9 @@ int main( const int argc, const char * const argv[] ) encoder_options.match_len_limit, num_workers, infd, outfd, pp, debug_level ); else - tmp = decompress( cfile_size, num_workers, infd, outfd, pp, - debug_level, in_slots, out_slots, ignore_trailing, - loose_trailing, infd_isreg, one_to_one ); + tmp = decompress( cfile_size, num_workers, infd, outfd, cl_opts, pp, + debug_level, in_slots, out_slots, infd_isreg, + one_to_one ); if( close( infd ) != 0 ) { show_file_error( pp.name(), "Error closing input file", errno ); set_retval( tmp, 1 ); } @@ -966,7 +1000,9 @@ int main( const int argc, const char * const argv[] ) if( input_filename.size() && !keep_input_files && one_to_one ) std::remove( input_filename.c_str() ); } - if( delete_output_on_interrupt ) close_and_set_permissions( 0 ); // -o + if( delete_output_on_interrupt ) // -o + close_and_set_permissions( ( retval == 0 && !stdin_used && + filenames_given && filenames.size() == 1 ) ? &in_stats : 0 ); else if( outfd >= 0 && close( outfd ) != 0 ) // -c { show_error( "Error closing stdout", errno ); diff --git a/testsuite/check.sh b/testsuite/check.sh index a6343f5..7ec899e 100755 --- a/testsuite/check.sh +++ b/testsuite/check.sh @@ -1,6 +1,6 @@ #! /bin/sh # check script for Plzip - Massively parallel implementation of lzip -# Copyright (C) 2009-2022 Antonio Diaz Diaz. +# Copyright (C) 2009-2024 Antonio Diaz Diaz. # # This script is free software: you have unlimited permission # to copy, distribute, and modify it. @@ -45,6 +45,7 @@ lzlib_1_10() { [ ${lwarn10} = 0 ] && "${LZIP}" --check-lib # just print warning [ $? != 2 ] || test_failed $LINENO # unless bad lzlib.h + printf "testing plzip-%s..." "$2" "${LZIP}" -fkqm4 in @@ -81,9 +82,9 @@ done # these are for code coverage "${LZIP}" -lt "${in_lz}" 2> /dev/null [ $? = 1 ] || test_failed $LINENO -"${LZIP}" -cdl "${in_lz}" > out 2> /dev/null +"${LZIP}" -cdl "${in_lz}" 2> /dev/null [ $? = 1 ] || test_failed $LINENO -"${LZIP}" -cdt "${in_lz}" > out 2> /dev/null +"${LZIP}" -cdt "${in_lz}" 2> /dev/null [ $? = 1 ] || test_failed $LINENO "${LZIP}" -t -- nx_file.lz 2> /dev/null [ $? = 1 ] || test_failed $LINENO @@ -108,50 +109,50 @@ done printf "LZIP\001-.............................." | "${LZIP}" -t 2> /dev/null printf "LZIP\002-.............................." | "${LZIP}" -t 2> /dev/null printf "LZIP\001+.............................." | "${LZIP}" -t 2> /dev/null -rm -f out || framework_failure printf "\ntesting decompression..." for i in "${in_lz}" "${in_em}" ; do "${LZIP}" -lq "$i" || test_failed $LINENO "$i" "${LZIP}" -t "$i" || test_failed $LINENO "$i" - "${LZIP}" -d "$i" -o copy || test_failed $LINENO "$i" - cmp in copy || test_failed $LINENO "$i" - "${LZIP}" -cd "$i" > copy || test_failed $LINENO "$i" - cmp in copy || test_failed $LINENO "$i" - "${LZIP}" -d "$i" -o - > copy || test_failed $LINENO "$i" - cmp in copy || test_failed $LINENO "$i" - "${LZIP}" -d < "$i" > copy || test_failed $LINENO "$i" - cmp in copy || test_failed $LINENO "$i" - rm -f copy || framework_failure + "${LZIP}" -d "$i" -o out || test_failed $LINENO "$i" + cmp in out || test_failed $LINENO "$i" + "${LZIP}" -cd "$i" > out || test_failed $LINENO "$i" + cmp in out || test_failed $LINENO "$i" + "${LZIP}" -d "$i" -o - > out || test_failed $LINENO "$i" + cmp in out || test_failed $LINENO "$i" + "${LZIP}" -d < "$i" > out || test_failed $LINENO "$i" + cmp in out || test_failed $LINENO "$i" + rm -f out || framework_failure done -lines=$("${LZIP}" -tvv "${in_em}" 2>&1 | wc -l) || test_failed $LINENO +lines=`"${LZIP}" -tvv "${in_em}" 2>&1 | wc -l` || test_failed $LINENO [ "${lines}" -eq 1 ] || test_failed $LINENO "${lines}" -lines=$("${LZIP}" -lvv "${in_em}" | wc -l) || test_failed $LINENO +lines=`"${LZIP}" -lvv "${in_em}" | wc -l` || test_failed $LINENO [ "${lines}" -eq 11 ] || test_failed $LINENO "${lines}" -"${LZIP}" -cd "${fox_lz}" > fox || test_failed $LINENO -cat "${in_lz}" > copy.lz || framework_failure -"${LZIP}" -dk copy.lz || test_failed $LINENO -cmp in copy || test_failed $LINENO -cat fox > copy || framework_failure cat "${in_lz}" > out.lz || framework_failure +"${LZIP}" -dk out.lz || test_failed $LINENO +cmp in out || test_failed $LINENO rm -f out || framework_failure +"${LZIP}" -cd "${fox_lz}" > fox || test_failed $LINENO +cat fox > copy || framework_failure +cat "${in_lz}" > copy.lz || framework_failure "${LZIP}" -d copy.lz out.lz 2> /dev/null # skip copy, decompress out [ $? = 1 ] || test_failed $LINENO +[ ! -e out.lz ] || test_failed $LINENO cmp fox copy || test_failed $LINENO cmp in out || test_failed $LINENO "${LZIP}" -df copy.lz || test_failed $LINENO [ ! -e copy.lz ] || test_failed $LINENO cmp in copy || test_failed $LINENO -rm -f fox out || framework_failure +rm -f copy out || framework_failure -printf "to be overwritten" > copy || framework_failure -"${LZIP}" -df -o copy < "${in_lz}" || test_failed $LINENO -cmp in copy || test_failed $LINENO -rm -f out copy || framework_failure +printf "to be overwritten" > out || framework_failure +"${LZIP}" -df -o out < "${in_lz}" || test_failed $LINENO +cmp in out || test_failed $LINENO +rm -f out || framework_failure "${LZIP}" -d -o ./- "${in_lz}" || test_failed $LINENO cmp in ./- || test_failed $LINENO rm -f ./- || framework_failure @@ -160,11 +161,11 @@ cmp in ./- || test_failed $LINENO rm -f ./- || framework_failure cat "${in_lz}" > anyothername || framework_failure -"${LZIP}" -dv - anyothername - < "${in_lz}" > copy 2> /dev/null || +"${LZIP}" -dv - anyothername - < "${in_lz}" > out 2> /dev/null || test_failed $LINENO -cmp in copy || test_failed $LINENO +cmp in out || test_failed $LINENO cmp in anyothername.out || test_failed $LINENO -rm -f copy anyothername.out || framework_failure +rm -f out anyothername.out || framework_failure "${LZIP}" -lq in "${in_lz}" [ $? = 2 ] || test_failed $LINENO @@ -174,62 +175,73 @@ rm -f copy anyothername.out || framework_failure [ $? = 2 ] || test_failed $LINENO "${LZIP}" -tq nx_file.lz "${in_lz}" [ $? = 1 ] || test_failed $LINENO -"${LZIP}" -cdq in "${in_lz}" > copy +"${LZIP}" -cdq in "${in_lz}" > out [ $? = 2 ] || test_failed $LINENO -cat copy in | cmp in - || test_failed $LINENO # copy must be empty -"${LZIP}" -cdq nx_file.lz "${in_lz}" > copy +cat out in | cmp in - || test_failed $LINENO # out must be empty +"${LZIP}" -cdq nx_file.lz "${in_lz}" > out # skip nx_file, decompress in [ $? = 1 ] || test_failed $LINENO -cmp in copy || test_failed $LINENO -rm -f copy || framework_failure -cat "${in_lz}" > copy.lz || framework_failure +cmp in out || test_failed $LINENO +rm -f out || framework_failure +cat "${in_lz}" > out.lz || framework_failure for i in 1 2 3 4 5 6 7 ; do - printf "g" >> copy.lz || framework_failure - "${LZIP}" -alvv copy.lz "${in_lz}" > /dev/null 2>&1 + printf "g" >> out.lz || framework_failure + "${LZIP}" -alvv out.lz "${in_lz}" > /dev/null 2>&1 [ $? = 2 ] || test_failed $LINENO $i - "${LZIP}" -atvvvv copy.lz "${in_lz}" 2> /dev/null + "${LZIP}" -atvvvv out.lz "${in_lz}" 2> /dev/null [ $? = 2 ] || test_failed $LINENO $i done -"${LZIP}" -dq in copy.lz +"${LZIP}" -dq in out.lz [ $? = 2 ] || test_failed $LINENO -[ -e copy.lz ] || test_failed $LINENO -[ ! -e copy ] || test_failed $LINENO +[ -e out.lz ] || test_failed $LINENO +[ ! -e out ] || test_failed $LINENO [ ! -e in.out ] || test_failed $LINENO -"${LZIP}" -dq nx_file.lz copy.lz +"${LZIP}" -dq nx_file.lz out.lz [ $? = 1 ] || test_failed $LINENO -[ ! -e copy.lz ] || test_failed $LINENO +[ ! -e out.lz ] || test_failed $LINENO [ ! -e nx_file ] || test_failed $LINENO -cmp in copy || test_failed $LINENO +cmp in out || test_failed $LINENO +rm -f out || framework_failure cat in in > in2 || framework_failure "${LZIP}" -lq "${in_lz}" "${in_lz}" || test_failed $LINENO "${LZIP}" -t "${in_lz}" "${in_lz}" || test_failed $LINENO -"${LZIP}" -cd "${in_lz}" "${in_lz}" -o out > copy2 || test_failed $LINENO +"${LZIP}" -cd "${in_lz}" "${in_lz}" -o out > out2 || test_failed $LINENO [ ! -e out ] || test_failed $LINENO # override -o -cmp in2 copy2 || test_failed $LINENO -rm -f copy2 || framework_failure -"${LZIP}" -d "${in_lz}" "${in_lz}" -o copy2 || test_failed $LINENO -cmp in2 copy2 || test_failed $LINENO -rm -f copy2 || framework_failure - -cat "${in_lz}" "${in_lz}" > copy2.lz || framework_failure -printf "\ngarbage" >> copy2.lz || framework_failure -"${LZIP}" -tvvvv copy2.lz 2> /dev/null || test_failed $LINENO -"${LZIP}" -alq copy2.lz +cmp in2 out2 || test_failed $LINENO +rm -f out2 || framework_failure +"${LZIP}" -d "${in_lz}" "${in_lz}" -o out2 || test_failed $LINENO +cmp in2 out2 || test_failed $LINENO +rm -f out2 || framework_failure + +cat "${in_lz}" "${in_lz}" > out2.lz || framework_failure +printf "\ngarbage" >> out2.lz || framework_failure +"${LZIP}" -tvvvv out2.lz 2> /dev/null || test_failed $LINENO +"${LZIP}" -alq out2.lz [ $? = 2 ] || test_failed $LINENO -"${LZIP}" -atq copy2.lz +"${LZIP}" -atq out2.lz [ $? = 2 ] || test_failed $LINENO -"${LZIP}" -atq < copy2.lz +"${LZIP}" -atq < out2.lz [ $? = 2 ] || test_failed $LINENO -"${LZIP}" -adkq copy2.lz +"${LZIP}" -adkq out2.lz [ $? = 2 ] || test_failed $LINENO -[ ! -e copy2 ] || test_failed $LINENO -"${LZIP}" -adkq -o copy2 < copy2.lz +[ ! -e out2 ] || test_failed $LINENO +"${LZIP}" -adkq -o out2 < out2.lz [ $? = 2 ] || test_failed $LINENO -[ ! -e copy2 ] || test_failed $LINENO -printf "to be overwritten" > copy2 || framework_failure -"${LZIP}" -df copy2.lz || test_failed $LINENO -cmp in2 copy2 || test_failed $LINENO -rm -f copy2 || framework_failure +[ ! -e out2 ] || test_failed $LINENO +printf "to be overwritten" > out2 || framework_failure +"${LZIP}" -df out2.lz || test_failed $LINENO +cmp in2 out2 || test_failed $LINENO +rm -f out2 || framework_failure + +"${LZIP}" -d "${fox_lz}" -o a/b/c/fox || test_failed $LINENO +cmp fox a/b/c/fox || test_failed $LINENO +rm -rf a || framework_failure +"${LZIP}" -d -o a/b/c/fox < "${fox_lz}" || test_failed $LINENO +cmp fox a/b/c/fox || test_failed $LINENO +rm -rf a || framework_failure +"${LZIP}" -dq "${fox_lz}" -o a/b/c/ +[ $? = 1 ] || test_failed $LINENO +[ ! -e a ] || test_failed $LINENO printf "\ntesting compression..." @@ -237,14 +249,16 @@ printf "\ntesting compression..." [ ! -e out3.lz ] || test_failed $LINENO # override -o "${LZIP}" -0f in in --output=copy2.lz || test_failed $LINENO "${LZIP}" -d copy2.lz -o out2 || test_failed $LINENO +[ -e copy2.lz ] || test_failed $LINENO cmp in2 out2 || test_failed $LINENO rm -f in2 out2 copy2.lz || framework_failure -"${LZIP}" -cf "${in_lz}" > out 2> /dev/null # /dev/null is a tty on OS/2 +"${LZIP}" -cf "${in_lz}" > lzlz 2> /dev/null # /dev/null is a tty on OS/2 [ $? = 1 ] || test_failed $LINENO -"${LZIP}" -Fvvm36 -o - "${in_lz}" > out 2> /dev/null || test_failed $LINENO -"${LZIP}" -cd out | "${LZIP}" -d > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO +"${LZIP}" -Fvvm36 -o - "${in_lz}" > lzlz 2> /dev/null || test_failed $LINENO +"${LZIP}" -cd lzlz | "${LZIP}" -d > out || test_failed $LINENO +cmp in out || test_failed $LINENO +rm -f lzlz out || framework_failure "${LZIP}" -0 -o ./- in || test_failed $LINENO "${LZIP}" -cd ./- | cmp in - || test_failed $LINENO @@ -256,10 +270,10 @@ rm -f ./-.lz || framework_failure for i in s4Ki 0 1 2 3 4 5 6 7 8 9 ; do "${LZIP}" -k -$i in || test_failed $LINENO $i - mv -f in.lz copy.lz || test_failed $LINENO $i - printf "garbage" >> copy.lz || framework_failure - "${LZIP}" -df copy.lz || test_failed $LINENO $i - cmp in copy || test_failed $LINENO $i + mv in.lz out.lz || test_failed $LINENO $i + printf "garbage" >> out.lz || framework_failure + "${LZIP}" -df out.lz || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i "${LZIP}" -$i in -c > out || test_failed $LINENO $i "${LZIP}" -$i in -o o_out || test_failed $LINENO $i # don't add .lz @@ -281,7 +295,7 @@ for i in s4Ki 0 1 2 3 4 5 6 7 8 9 ; do "${LZIP}" -df -o copy < out.lz || test_failed $LINENO $i cmp in copy || test_failed $LINENO $i done -rm -f out out.lz || framework_failure +rm -f copy out.lz || framework_failure cat in in in in > in4 || framework_failure for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 ; do @@ -304,21 +318,28 @@ for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 ; do "${LZIP}" -d -n$i out4.lz || test_failed $LINENO $i cmp in4 out4 || test_failed $LINENO $i done -rm -f out4 || framework_failure +rm -f in4 out4 || framework_failure cat in in in in in in in in | "${LZIP}" -1s4Ki | "${LZIP}" -t || test_failed $LINENO +"${LZIP}" fox -o a/b/c/fox.lz || test_failed $LINENO +cmp "${fox_lz}" a/b/c/fox.lz || test_failed $LINENO +rm -rf a || framework_failure +"${LZIP}" -o a/b/c/fox.lz < fox || test_failed $LINENO +cmp "${fox_lz}" a/b/c/fox.lz || test_failed $LINENO +rm -rf a fox || framework_failure + printf "\ntesting bad input..." headers='LZIp LZiP LZip LzIP LzIp LziP lZIP lZIp lZiP lzIP' body='\001\014\000\203\377\373\377\377\300\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000$\000\000\000\000\000\000\000' -cat "${in_lz}" > int.lz -printf "LZIP${body}" >> int.lz +cat "${in_lz}" > int.lz || framework_failure +printf "LZIP${body}" >> int.lz || framework_failure if "${LZIP}" -tq int.lz ; then for header in ${headers} ; do - printf "${header}${body}" > int.lz # first member - "${LZIP}" -lq int.lz + printf "${header}${body}" > int.lz || framework_failure + "${LZIP}" -lq int.lz # first member [ $? = 2 ] || test_failed $LINENO ${header} "${LZIP}" -tq int.lz [ $? = 2 ] || test_failed $LINENO ${header} @@ -334,9 +355,9 @@ if "${LZIP}" -tq int.lz ; then [ $? = 2 ] || test_failed $LINENO ${header} "${LZIP}" -cdq --loose-trailing int.lz > /dev/null [ $? = 2 ] || test_failed $LINENO ${header} - cat "${in_lz}" > int.lz - printf "${header}${body}" >> int.lz # trailing data - "${LZIP}" -lq int.lz + cat "${in_lz}" > int.lz || framework_failure + printf "${header}${body}" >> int.lz || framework_failure + "${LZIP}" -lq int.lz # trailing data [ $? = 2 ] || test_failed $LINENO ${header} "${LZIP}" -tq int.lz [ $? = 2 ] || test_failed $LINENO ${header} @@ -384,15 +405,15 @@ if dd if=in3.lz of=trunc.lz bs=14752 count=1 2> /dev/null && [ $? = 2 ] || test_failed $LINENO $i "${LZIP}" -tq < trunc.lz [ $? = 2 ] || lzlib_1_8 # requires lzlib 1.8 - "${LZIP}" -cdq trunc.lz > out + "${LZIP}" -cdq trunc.lz > /dev/null [ $? = 2 ] || test_failed $LINENO $i - "${LZIP}" -dq < trunc.lz > out + "${LZIP}" -dq < trunc.lz > /dev/null [ $? = 2 ] || lzlib_1_8 # requires lzlib 1.8 done else printf "\nwarning: skipping truncation test: 'dd' does not work on your system." fi -rm -f in2.lz in3.lz trunc.lz out || framework_failure +rm -f in2.lz in3.lz trunc.lz || framework_failure cat "${in_lz}" > ingin.lz || framework_failure printf "g" >> ingin.lz || framework_failure @@ -403,18 +424,18 @@ cat "${in_lz}" >> ingin.lz || framework_failure [ $? = 2 ] || test_failed $LINENO "${LZIP}" -atq < ingin.lz [ $? = 2 ] || test_failed $LINENO -"${LZIP}" -acdq ingin.lz > out +"${LZIP}" -acdq ingin.lz > /dev/null [ $? = 2 ] || test_failed $LINENO -"${LZIP}" -adq < ingin.lz > out +"${LZIP}" -adq < ingin.lz > /dev/null [ $? = 2 ] || test_failed $LINENO "${LZIP}" -tq ingin.lz [ $? = 2 ] || test_failed $LINENO "${LZIP}" -t < ingin.lz || test_failed $LINENO -"${LZIP}" -cdq ingin.lz > copy +"${LZIP}" -cdq ingin.lz > out [ $? = 2 ] || test_failed $LINENO -"${LZIP}" -d < ingin.lz > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -rm -f copy ingin.lz out || framework_failure +"${LZIP}" -d < ingin.lz > out || test_failed $LINENO +cmp in out || test_failed $LINENO +rm -f out ingin.lz || framework_failure echo if [ ${fail} = 0 ] ; then |