From ff926339aad7083a9a96881ee50ec8513f964ce1 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Fri, 11 Jan 2019 06:24:40 +0100 Subject: Merging upstream version 1.11. Signed-off-by: Daniel Baumann --- ChangeLog | 18 +++++- INSTALL | 22 ++++++-- Makefile.in | 37 +++++++----- NEWS | 44 +++++++-------- README | 30 ++++++---- bbexample.c | 10 ++-- carg_parser.c | 2 +- carg_parser.h | 2 +- cbuffer.c | 18 +++--- configure | 20 ++++--- decoder.c | 133 +++++++++++++++++++++---------------------- decoder.h | 18 +++--- doc/lzlib.info | 162 ++++++++++++++++++++++++++++++----------------------- doc/lzlib.texi | 120 +++++++++++++++++++++++---------------- doc/minilzip.1 | 11 ++-- encoder.c | 4 +- encoder.h | 2 +- encoder_base.c | 20 ++++--- encoder_base.h | 10 ++-- fast_encoder.c | 2 +- fast_encoder.h | 6 +- lzcheck.c | 4 +- lzip.h | 57 ++++++++++--------- lzlib.c | 58 ++++++++++--------- lzlib.h | 4 +- main.c | 108 +++++++++++++++++++++-------------- testsuite/check.sh | 130 +++++++++++++++++++++++++++--------------- 27 files changed, 612 insertions(+), 440 deletions(-) diff --git a/ChangeLog b/ChangeLog index c13bf2e..7402b7a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,19 @@ +2019-01-02 Antonio Diaz Diaz + + * Version 1.11 released. + * File_* renamed to Lzip_*. + * LZ_decompress_read: Don't return error until all data is read. + * decoder.c (LZd_decode_member): Decode truncated data until EOF. + * main.c: Don't allow mixing different operations (-d and -t). + * main.c: Check return value of close( infd ). + * main.c: Compile on DOS with DJGPP. + * lzlib.texi: Improved descriptions of '-0..-9', '-m' and '-s'. + Document that 'LZ_(de)compress_finish' can be called repeatedly. + * configure: Accept appending to CFLAGS, 'CFLAGS+=OPTIONS'. + * Makefile.in: Targets 'install-bin*' renamed to 'install-lib*'. + * Makefile.in: Targets 'install-bin*' now install minilzip. + * INSTALL: Document use of CFLAGS+='-D __USE_MINGW_ANSI_STDIO'. + 2018-02-07 Antonio Diaz Diaz * Version 1.10 released. @@ -188,7 +204,7 @@ * Version 0.1 released. -Copyright (C) 2009-2018 Antonio Diaz Diaz. +Copyright (C) 2009-2019 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 diff --git a/INSTALL b/INSTALL index 735d666..b5889df 100644 --- a/INSTALL +++ b/INSTALL @@ -1,10 +1,14 @@ Requirements ------------ You will need a C compiler. -I use gcc 5.3.0 and 4.1.2, but the code should compile with any -standards compliant compiler. +I use gcc 5.3.0 and 4.1.2, but the code should compile with any standards +compliant compiler. Gcc is available at http://gcc.gnu.org. +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 +the partial output file. + Procedure --------- @@ -23,6 +27,10 @@ the main archive. cd lzlib[version] ./configure + If you are compiling on MinGW, use: + + ./configure CFLAGS+='-D __USE_MINGW_ANSI_STDIO' + 3. Run make. make @@ -37,11 +45,13 @@ the main archive. become the default in the future). You can install only the library, the info manual or the man page by - typing 'make install-bin', 'make install-info' or 'make install-man' + typing 'make install-lib', 'make install-info' or 'make install-man' respectively. - Instead of 'make install', you can type 'make install-as-lzip' to - install the library and any data files and documentation, and link + 'make install-bin' installs the minilzip program and its man page. + 'install-bin' installs a shared minilzip if the shared library has + been configured. Else it installs a static minilzip. + 'make install-as-lzip' runs 'make install-bin' and then links minilzip to the name 'lzip'. @@ -62,7 +72,7 @@ After running 'configure', you can run 'make' and 'make install' as explained above. -Copyright (C) 2009-2018 Antonio Diaz Diaz. +Copyright (C) 2009-2019 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 c493f5e..1ac03b2 100644 --- a/Makefile.in +++ b/Makefile.in @@ -15,7 +15,7 @@ objs = carg_parser.o main.o .PHONY : all install install-bin install-info install-man \ install-strip install-compress install-strip-compress \ install-bin-strip install-info-compress install-man-compress \ - install-as-lzip \ + install-lib install-lib-strip uninstall-lib install-as-lzip \ uninstall uninstall-bin uninstall-info uninstall-man \ doc info man check dist clean distclean @@ -78,12 +78,19 @@ Makefile : $(VPATH)/configure $(VPATH)/Makefile.in check : $(progname) bbexample lzcheck @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite $(pkgversion) -install : install-bin install-info -install-strip : install-bin-strip install-info -install-compress : install-bin install-info-compress -install-strip-compress : install-bin-strip install-info-compress +install : install-lib install-info +install-strip : install-lib-strip install-info +install-compress : install-lib install-info-compress +install-strip-compress : install-lib-strip install-info-compress -install-bin : all +install-bin : all install-man + if [ ! -d "$(DESTDIR)$(bindir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(bindir)" ; fi + $(INSTALL_PROGRAM) ./$(progname_lzip) "$(DESTDIR)$(bindir)/$(progname)" + +install-bin-strip : all + $(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install-bin + +install-lib : all if [ ! -d "$(DESTDIR)$(includedir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(includedir)" ; fi if [ ! -d "$(DESTDIR)$(libdir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(libdir)" ; fi $(INSTALL_DATA) $(VPATH)/$(libname)lib.h "$(DESTDIR)$(includedir)/$(libname)lib.h" @@ -104,8 +111,8 @@ install-bin : all [ -x "$(LDCONFIG)" ] ; then "$(LDCONFIG)" -n "$(DESTDIR)$(libdir)" || true ; fi ; \ fi -install-bin-strip : all - $(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install-bin +install-lib-strip : all + $(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install-lib install-info : if [ ! -d "$(DESTDIR)$(infodir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(infodir)" ; fi @@ -126,16 +133,16 @@ install-man : install-man-compress : install-man lzip -v -9 "$(DESTDIR)$(mandir)/man1/$(progname).1" -install-as-lzip : install install-man - if [ ! -d "$(DESTDIR)$(bindir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(bindir)" ; fi - $(INSTALL_PROGRAM) ./$(progname_lzip) "$(DESTDIR)$(bindir)/$(progname)" +install-as-lzip : install-bin -rm -f "$(DESTDIR)$(bindir)/lzip" cd "$(DESTDIR)$(bindir)" && ln -s $(progname) lzip -uninstall : uninstall-man uninstall-info uninstall-bin +uninstall : uninstall-info uninstall-lib -uninstall-bin : +uninstall-bin : uninstall-man -rm -f "$(DESTDIR)$(bindir)/$(progname)" + +uninstall-lib : -rm -f "$(DESTDIR)$(includedir)/$(libname)lib.h" -rm -f "$(DESTDIR)$(libdir)/lib$(libname).a" -rm -f "$(DESTDIR)$(libdir)/lib$(libname).so" @@ -171,8 +178,8 @@ dist : doc $(DISTNAME)/testsuite/check.sh \ $(DISTNAME)/testsuite/test.txt \ $(DISTNAME)/testsuite/test2.txt \ - $(DISTNAME)/testsuite/test.txt.lz \ - $(DISTNAME)/testsuite/test_sync.lz + $(DISTNAME)/testsuite/test_sync.lz \ + $(DISTNAME)/testsuite/test.txt.lz rm -f $(DISTNAME) lzip -v -9 $(DISTNAME).tar diff --git a/NEWS b/NEWS index c610506..bdf7f32 100644 --- a/NEWS +++ b/NEWS @@ -1,32 +1,30 @@ -Changes in version 1.10: +Changes in version 1.11: -The function 'LZ_compress_finish' now adjusts the dictionary size for -each member. +In case of decompression error caused by corrupt or truncated data, +LZ_decompress_read now does not signal the error immediately to the +application, but waits until all decoded bytes have been read. This +allows tools like tarlz to recover as much data as possible from damaged +members. -The option '--loose-trailing', has been added to minilzip. +It is now an error to specify two different operations to minilzip in +the command line (--decompress and --test). -The test used by lzlib to discriminate trailing data from a corrupt -header in multimember or concatenated files has been improved to a -Hamming distance (HD) of 3, and the 3 bit flips must happen in different -magic bytes for the test to fail. As a consequence, lzlib now returns a -data error when some kinds of files are appended to a lzip file as -trailing data. -The '--loose-trailing' option of minilzip can be used to ignore such -trailing data when decompressing. -Lziprecover can be used to remove conflicting trailing data from a file. +Minilzip now also checks for errors when closing the input file. -Option '-S, --volume-size' of minilzip now keeps input files unchanged. +Minilzip now compiles on DOS with DJGPP. (Patch from Robert Riebisch). -The 'bits/byte' ratio has been replaced with the inverse compression -ratio in the output of minilzip. +The descriptions of '-0..-9', '-m' and '-s' in the manual have been +improved. -minilzip now shows a final diagnostic at verbosity level 1 (-v) or -higher if any file fails the test when testing multiple files. +It has been documented that it is safe to call 'LZ_(de)compress_finish' +as many times as needed. Examples in the manual have been simplified. -minilzip no longer adds a second '.lz' extension to the argument of '-o' -if it already ends in '.lz' or '.tlz'. +The configure script now accepts appending options to CFLAGS using the +syntax 'CFLAGS+=OPTIONS'. -minilzip now shows the dictionary size at verbosity level 4 (-vvvv) when -decompressing or testing. +Makefile targets 'install-bin*' have been renamed to 'install-lib*'. New +'install-bin*' targets have been created that install a shared minilzip, +or a static minilzip if the shared library has not been configured. -The new chapter 'Invoking minilzip' has been added to the manual. +It has been documented in INSTALL the use of +CFLAGS+='-D __USE_MINGW_ANSI_STDIO' when compiling on MinGW. diff --git a/README b/README index 6a9c6f2..fa1da74 100644 --- a/README +++ b/README @@ -5,22 +5,21 @@ and decompression functions, including integrity checking of the decompressed data. The compressed data format used by the library is the lzip format. Lzlib is written in C. -The lzip file format is designed for data sharing and long-term -archiving, taking into account both data integrity and decoder -availability: +The lzip file format is designed for data sharing and long-term archiving, +taking into account both data integrity and decoder availability: * The lzip format provides very safe integrity checking and some data - recovery means. The lziprecover program can repair bit-flip errors + recovery means. The lziprecover program can repair bit flip errors (one of the most common forms of data corruption) in lzip files, and provides data recovery capabilities, including error-checked merging of damaged copies of a file. * The lzip format is as simple as possible (but not simpler). The - lzip manual provides the source code of a simple decompressor along - with a detailed explanation of how it works, so that with the only - help of the lzip manual it would be possible for a digital - archaeologist to extract the data from a lzip file long after - quantum computers eventually render LZMA obsolete. + lzip manual provides the source code of a simple decompressor + along with a detailed explanation of how it works, so that with + the only help of the lzip manual it would be possible for a + digital archaeologist to extract the data from a lzip file long + after quantum computers eventually render LZMA obsolete. * Additionally the lzip reference implementation is copylefted, which guarantees that it will remain free forever. @@ -48,7 +47,8 @@ size equal to 0. If all the data to be compressed are written in advance, lzlib will automatically adjust the header of the compressed data to use the -smallest possible dictionary size. This feature reduces the amount of +largest dictionary size that does not exceed neither the data size nor +the limit given to LZ_compress_open. This feature reduces the amount of memory needed for decompression and allows minilzip to produce identical compressed output as lzip. @@ -57,6 +57,10 @@ of two or more compressed data streams. The result is the concatenation of the corresponding decompressed data streams. Integrity testing of concatenated compressed data streams is also supported. +Lzlib is able to compress and decompress streams of unlimited size by +automatically creating multimember output. The members so created are +large, about 2 PiB each. + All the library functions are thread safe. The library does not install any signal handler. The decoder checks the consistency of the compressed data, so the library should never crash even in case of corrupted input. @@ -86,8 +90,12 @@ the definition of Markov chains), G.N.N. Martin (for the definition of range encoding), Igor Pavlov (for putting all the above together in LZMA), and Julian Seward (for bzip2's CLI). +LANGUAGE NOTE: Uncompressed = not compressed = plain data; it may never +have been compressed. Decompressed is used to refer to data which have +undergone the process of decompression. + -Copyright (C) 2009-2018 Antonio Diaz Diaz. +Copyright (C) 2009-2019 Antonio Diaz Diaz. This file is free documentation: you have unlimited permission to copy, distribute and modify it. diff --git a/bbexample.c b/bbexample.c index 8c2ff04..e953c35 100644 --- a/bbexample.c +++ b/bbexample.c @@ -1,5 +1,5 @@ /* Buffer to buffer example - Test program for the lzlib library - Copyright (C) 2010-2018 Antonio Diaz Diaz. + Copyright (C) 2010-2019 Antonio Diaz Diaz. This program is free software: you have unlimited permission to copy, distribute and modify it. @@ -26,10 +26,10 @@ /* Returns the address of a malloc'd buffer containing the file data and - its size in '*size'. - In case of error, returns 0 and does not modify '*size'. + the file size in '*file_sizep'. + In case of error, returns 0 and does not modify '*file_sizep'. */ -uint8_t * read_file( const char * const name, long * const size ) +uint8_t * read_file( const char * const name, long * const file_sizep ) { long buffer_size = 1 << 20, file_size; uint8_t * buffer, * tmp; @@ -67,7 +67,7 @@ uint8_t * read_file( const char * const name, long * const size ) free( buffer ); return 0; } fclose( f ); - *size = file_size; + *file_sizep = file_size; return buffer; } diff --git a/carg_parser.c b/carg_parser.c index 10ad4dc..ce01d7b 100644 --- a/carg_parser.c +++ b/carg_parser.c @@ -1,5 +1,5 @@ /* Arg_parser - POSIX/GNU command line argument parser. (C version) - Copyright (C) 2006-2018 Antonio Diaz Diaz. + Copyright (C) 2006-2019 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/carg_parser.h b/carg_parser.h index e1c70dd..dcae2de 100644 --- a/carg_parser.h +++ b/carg_parser.h @@ -1,5 +1,5 @@ /* Arg_parser - POSIX/GNU command line argument parser. (C version) - Copyright (C) 2006-2018 Antonio Diaz Diaz. + Copyright (C) 2006-2019 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/cbuffer.c b/cbuffer.c index 5e7ab93..6b70be4 100644 --- a/cbuffer.c +++ b/cbuffer.c @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -25,9 +25,6 @@ struct Circular_buffer unsigned put; }; -static inline void Cb_reset( struct Circular_buffer * const cb ) - { cb->get = 0; cb->put = 0; } - static inline bool Cb_init( struct Circular_buffer * const cb, const unsigned buf_size ) { @@ -42,6 +39,12 @@ static inline bool Cb_init( struct Circular_buffer * const cb, static inline void Cb_free( struct Circular_buffer * const cb ) { free( cb->buffer ); cb->buffer = 0; } +static inline void Cb_reset( struct Circular_buffer * const cb ) + { cb->get = 0; cb->put = 0; } + +static inline unsigned Cb_empty( const struct Circular_buffer * const cb ) + { return cb->get == cb->put; } + static inline unsigned Cb_used_bytes( const struct Circular_buffer * const cb ) { return ( (cb->get <= cb->put) ? 0 : cb->buffer_size ) + cb->put - cb->get; } @@ -74,7 +77,8 @@ static bool Cb_unread_data( struct Circular_buffer * const cb, /* Copies up to 'out_size' bytes to 'out_buffer' and updates 'get'. - Returns the number of bytes copied. + If 'out_buffer' is null, the bytes are discarded. + Returns the number of bytes copied or discarded. */ static unsigned Cb_read_data( struct Circular_buffer * const cb, uint8_t * const out_buffer, @@ -87,7 +91,7 @@ static unsigned Cb_read_data( struct Circular_buffer * const cb, size = min( cb->buffer_size - cb->get, out_size ); if( size > 0 ) { - memcpy( out_buffer, cb->buffer + cb->get, size ); + if( out_buffer ) memcpy( out_buffer, cb->buffer + cb->get, size ); cb->get += size; if( cb->get >= cb->buffer_size ) cb->get = 0; } @@ -97,7 +101,7 @@ static unsigned Cb_read_data( struct Circular_buffer * const cb, const unsigned size2 = min( cb->put - cb->get, out_size - size ); if( size2 > 0 ) { - memcpy( out_buffer + size, cb->buffer + cb->get, size2 ); + if( out_buffer ) memcpy( out_buffer + size, cb->buffer + cb->get, size2 ); cb->get += size2; size += size2; } diff --git a/configure b/configure index 5b0c54b..60ea883 100755 --- a/configure +++ b/configure @@ -1,12 +1,12 @@ #! /bin/sh # configure script for Lzlib - Compression library for the lzip format -# Copyright (C) 2009-2018 Antonio Diaz Diaz. +# Copyright (C) 2009-2019 Antonio Diaz Diaz. # # This configure script is free software: you have unlimited permission # to copy, distribute and modify it. pkgname=lzlib -pkgversion=1.10 +pkgversion=1.11 soversion=1 progname=minilzip progname_static=${progname} @@ -84,6 +84,7 @@ while [ $# != 0 ] ; do echo " CC=COMPILER C compiler to use [${CC}]" echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]" echo " CFLAGS=OPTIONS command line options for the C compiler [${CFLAGS}]" + echo " CFLAGS+=OPTIONS append options to the current value of CFLAGS" echo " LDFLAGS=OPTIONS command line options for the linker [${LDFLAGS}]" echo exit 0 ;; @@ -114,13 +115,16 @@ while [ $# != 0 ] ; do progname_static= progname_shared=${progname}_shared progname_lzip=${progname}_shared ;; - --enable-shared) progname_shared=${progname}_shared ;; + --enable-shared) + progname_shared=${progname}_shared + progname_lzip=${progname}_shared ;; --disable-ldconfig) disable_ldconfig=yes ;; - CC=*) CC=${optarg} ;; - CPPFLAGS=*) CPPFLAGS=${optarg} ;; - CFLAGS=*) CFLAGS=${optarg} ;; - LDFLAGS=*) LDFLAGS=${optarg} ;; + CC=*) CC=${optarg} ;; + CPPFLAGS=*) CPPFLAGS=${optarg} ;; + CFLAGS=*) CFLAGS=${optarg} ;; + CFLAGS+=*) CFLAGS="${CFLAGS} ${optarg}" ;; + LDFLAGS=*) LDFLAGS=${optarg} ;; --*) echo "configure: WARNING: unrecognized option: '${option}'" 1>&2 ;; @@ -194,7 +198,7 @@ echo "LDFLAGS = ${LDFLAGS}" rm -f Makefile cat > Makefile << EOF # Makefile for Lzlib - Compression library for the lzip format -# Copyright (C) 2009-2018 Antonio Diaz Diaz. +# Copyright (C) 2009-2019 Antonio Diaz Diaz. # This file was generated automatically by configure. Don't edit. # # This Makefile is free software: you have unlimited permission diff --git a/decoder.c b/decoder.c index d659853..3dc62cc 100644 --- a/decoder.c +++ b/decoder.c @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -19,16 +19,16 @@ static int LZd_try_verify_trailer( struct LZ_decoder * const d ) { - File_trailer trailer; - if( Rd_available_bytes( d->rdec ) < Ft_size && !d->rdec->at_stream_end ) + Lzip_trailer trailer; + if( Rd_available_bytes( d->rdec ) < Lt_size && !d->rdec->at_stream_end ) return 0; d->verify_trailer_pending = false; d->member_finished = true; - if( Rd_read_data( d->rdec, trailer, Ft_size ) == Ft_size && - Ft_get_data_crc( trailer ) == LZd_crc( d ) && - Ft_get_data_size( trailer ) == LZd_data_position( d ) && - Ft_get_member_size( trailer ) == d->rdec->member_position ) return 0; + if( Rd_read_data( d->rdec, trailer, Lt_size ) == Lt_size && + Lt_get_data_crc( trailer ) == LZd_crc( d ) && + Lt_get_data_size( trailer ) == LZd_data_position( d ) && + Lt_get_member_size( trailer ) == d->rdec->member_position ) return 0; return 3; } @@ -49,15 +49,18 @@ static int LZd_decode_member( struct LZ_decoder * const d ) while( !Rd_finished( rdec ) ) { + int len; const int pos_state = LZd_data_position( d ) & pos_state_mask; /* const unsigned mpos = d->rdec->member_position; if( mpos - old_mpos > rd_min_available_bytes ) return 5; old_mpos = mpos; */ - if( !Rd_enough_available_bytes( rdec ) ) /* check unexpected eof */ - { if( !rdec->at_stream_end ) return 0; else break; } + if( !Rd_enough_available_bytes( rdec ) ) /* check unexpected EOF */ + { if( !rdec->at_stream_end ) return 0; + if( Cb_empty( &rdec->cb ) ) break; } /* decode until EOF */ if( !LZd_enough_free_bytes( d ) ) return 0; - if( Rd_decode_bit( rdec, &d->bm_match[*state][pos_state] ) == 0 ) /* 1st bit */ + if( Rd_decode_bit( rdec, &d->bm_match[*state][pos_state] ) == 0 ) /* 1st bit */ { + /* literal byte */ Bit_model * const bm = d->bm_literal[get_lit_state(LZd_peek_prev( d ))]; if( St_is_char( *state ) ) { @@ -69,79 +72,77 @@ static int LZd_decode_member( struct LZ_decoder * const d ) *state -= ( *state < 10 ) ? 3 : 6; LZd_put_byte( d, Rd_decode_matched( rdec, bm, LZd_peek( d, d->rep0 ) ) ); } + continue; } - else /* match or repeated match */ + /* match or repeated match */ + if( Rd_decode_bit( rdec, &d->bm_rep[*state] ) != 0 ) /* 2nd bit */ { - int len; - if( Rd_decode_bit( rdec, &d->bm_rep[*state] ) != 0 ) /* 2nd bit */ + if( Rd_decode_bit( rdec, &d->bm_rep0[*state] ) == 0 ) /* 3rd bit */ { - if( Rd_decode_bit( rdec, &d->bm_rep0[*state] ) == 0 ) /* 3rd bit */ - { - if( Rd_decode_bit( rdec, &d->bm_len[*state][pos_state] ) == 0 ) /* 4th bit */ - { *state = St_set_short_rep( *state ); - LZd_put_byte( d, LZd_peek( d, d->rep0 ) ); continue; } - } + if( Rd_decode_bit( rdec, &d->bm_len[*state][pos_state] ) == 0 ) /* 4th bit */ + { *state = St_set_short_rep( *state ); + LZd_put_byte( d, LZd_peek( d, d->rep0 ) ); continue; } + } + else + { + unsigned distance; + if( Rd_decode_bit( rdec, &d->bm_rep1[*state] ) == 0 ) /* 4th bit */ + distance = d->rep1; else { - unsigned distance; - if( Rd_decode_bit( rdec, &d->bm_rep1[*state] ) == 0 ) /* 4th bit */ - distance = d->rep1; + if( Rd_decode_bit( rdec, &d->bm_rep2[*state] ) == 0 ) /* 5th bit */ + distance = d->rep2; else - { - if( Rd_decode_bit( rdec, &d->bm_rep2[*state] ) == 0 ) /* 5th bit */ - distance = d->rep2; - else - { distance = d->rep3; d->rep3 = d->rep2; } - d->rep2 = d->rep1; - } - d->rep1 = d->rep0; - d->rep0 = distance; + { distance = d->rep3; d->rep3 = d->rep2; } + d->rep2 = d->rep1; } - *state = St_set_rep( *state ); - len = min_match_len + Rd_decode_len( rdec, &d->rep_len_model, pos_state ); + d->rep1 = d->rep0; + d->rep0 = distance; } - else /* match */ + *state = St_set_rep( *state ); + len = min_match_len + Rd_decode_len( rdec, &d->rep_len_model, pos_state ); + } + else /* match */ + { + unsigned distance; + len = min_match_len + Rd_decode_len( rdec, &d->match_len_model, pos_state ); + distance = Rd_decode_tree6( rdec, d->bm_dis_slot[get_len_state(len)] ); + if( distance >= start_dis_model ) { - unsigned distance; - len = min_match_len + Rd_decode_len( rdec, &d->match_len_model, pos_state ); - distance = Rd_decode_tree6( rdec, d->bm_dis_slot[get_len_state(len)] ); - if( distance >= start_dis_model ) + const unsigned dis_slot = distance; + const int direct_bits = ( dis_slot >> 1 ) - 1; + distance = ( 2 | ( dis_slot & 1 ) ) << direct_bits; + if( dis_slot < end_dis_model ) + distance += Rd_decode_tree_reversed( rdec, + d->bm_dis + ( distance - dis_slot ), direct_bits ); + else { - const unsigned dis_slot = distance; - const int direct_bits = ( dis_slot >> 1 ) - 1; - distance = ( 2 | ( dis_slot & 1 ) ) << direct_bits; - if( dis_slot < end_dis_model ) - distance += Rd_decode_tree_reversed( rdec, - d->bm_dis + ( distance - dis_slot ), direct_bits ); - else + distance += + Rd_decode( rdec, direct_bits - dis_align_bits ) << dis_align_bits; + distance += Rd_decode_tree_reversed4( rdec, d->bm_align ); + if( distance == 0xFFFFFFFFU ) /* marker found */ { - distance += - Rd_decode( rdec, direct_bits - dis_align_bits ) << dis_align_bits; - distance += Rd_decode_tree_reversed4( rdec, d->bm_align ); - if( distance == 0xFFFFFFFFU ) /* marker found */ + Rd_normalize( rdec ); + if( len == min_match_len ) /* End Of Stream marker */ + { + d->verify_trailer_pending = true; + return LZd_try_verify_trailer( d ); + } + if( len == min_match_len + 1 ) /* Sync Flush marker */ { - Rd_normalize( rdec ); - if( len == min_match_len ) /* End Of Stream marker */ - { - d->verify_trailer_pending = true; - return LZd_try_verify_trailer( d ); - } - if( len == min_match_len + 1 ) /* Sync Flush marker */ - { - if( Rd_try_reload( rdec, true ) ) { /*old_mpos += 5;*/ continue; } - else { if( !rdec->at_stream_end ) return 0; else break; } - } - return 4; + if( Rd_try_reload( rdec, true ) ) { /*old_mpos += 5;*/ continue; } + else { if( !rdec->at_stream_end ) return 0; else break; } } + return 4; } } - d->rep3 = d->rep2; d->rep2 = d->rep1; d->rep1 = d->rep0; d->rep0 = distance; - *state = St_set_match( *state ); - if( d->rep0 >= d->dictionary_size || - ( d->rep0 >= d->cb.put && !d->pos_wrapped ) ) return 1; } - LZd_copy_block( d, d->rep0, len ); + d->rep3 = d->rep2; d->rep2 = d->rep1; d->rep1 = d->rep0; d->rep0 = distance; + *state = St_set_match( *state ); + if( d->rep0 >= d->dictionary_size || + ( d->rep0 >= d->cb.put && !d->pos_wrapped ) ) return 1; } + LZd_copy_block( d, d->rep0, len ); } return 2; } diff --git a/decoder.h b/decoder.h index 090bf3a..1873d5e 100644 --- a/decoder.h +++ b/decoder.h @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -44,7 +44,7 @@ static inline void Rd_free( struct Range_decoder * const rdec ) { Cb_free( &rdec->cb ); } static inline bool Rd_finished( const struct Range_decoder * const rdec ) - { return rdec->at_stream_end && !Cb_used_bytes( &rdec->cb ); } + { return rdec->at_stream_end && Cb_empty( &rdec->cb ); } static inline void Rd_finish( struct Range_decoder * const rdec ) { rdec->at_stream_end = true; } @@ -56,7 +56,7 @@ static inline unsigned Rd_available_bytes( const struct Range_decoder * const rd { return Cb_used_bytes( &rdec->cb ); } static inline unsigned Rd_free_bytes( const struct Range_decoder * const rdec ) - { if( rdec->at_stream_end ) return 0; return Cb_free_bytes( &rdec->cb ); } + { return rdec->at_stream_end ? 0 : Cb_free_bytes( &rdec->cb ); } static inline unsigned long long Rd_purge( struct Range_decoder * const rdec ) { @@ -81,18 +81,18 @@ static bool Rd_find_header( struct Range_decoder * const rdec, *skippedp = 0; while( rdec->cb.get != rdec->cb.put ) { - if( rdec->cb.buffer[rdec->cb.get] == magic_string[0] ) + if( rdec->cb.buffer[rdec->cb.get] == lzip_magic[0] ) { unsigned get = rdec->cb.get; int i; - File_header header; - for( i = 0; i < Fh_size; ++i ) + Lzip_header header; + for( i = 0; i < Lh_size; ++i ) { if( get == rdec->cb.put ) return false; /* not enough data */ header[i] = rdec->cb.buffer[get]; if( ++get >= rdec->cb.buffer_size ) get = 0; } - if( Fh_verify( header ) ) return true; + if( Lh_verify( header ) ) return true; } if( ++rdec->cb.get >= rdec->cb.buffer_size ) rdec->cb.get = 0; ++*skippedp; @@ -110,6 +110,8 @@ static inline int Rd_write_data( struct Range_decoder * const rdec, static inline uint8_t Rd_get_byte( struct Range_decoder * const rdec ) { + /* 0xFF avoids decoder error if member is truncated at EOS marker */ + if( Rd_finished( rdec ) ) return 0xFF; ++rdec->member_position; return Cb_get_byte( &rdec->cb ); } @@ -410,7 +412,7 @@ static inline void LZd_free( struct LZ_decoder * const d ) { Cb_free( &d->cb ); } static inline bool LZd_member_finished( const struct LZ_decoder * const d ) - { return ( d->member_finished && !Cb_used_bytes( &d->cb ) ); } + { return ( d->member_finished && Cb_empty( &d->cb ) ); } static inline unsigned LZd_crc( const struct LZ_decoder * const d ) { return d->crc ^ 0xFFFFFFFFU; } diff --git a/doc/lzlib.info b/doc/lzlib.info index 23a4d21..5a1a573 100644 --- a/doc/lzlib.info +++ b/doc/lzlib.info @@ -11,7 +11,7 @@ File: lzlib.info, Node: Top, Next: Introduction, Up: (dir) Lzlib Manual ************ -This manual is for Lzlib (version 1.10, 7 February 2018). +This manual is for Lzlib (version 1.11, 2 January 2019). * Menu: @@ -30,7 +30,7 @@ This manual is for Lzlib (version 1.10, 7 February 2018). * Concept index:: Index of concepts - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This manual is free documentation: you have unlimited permission to copy, distribute and modify it. @@ -41,10 +41,10 @@ File: lzlib.info, Node: Introduction, Next: Library version, Prev: Top, Up: 1 Introduction ************** -Lzlib is a data compression library providing in-memory LZMA compression -and decompression functions, including integrity checking of the -decompressed data. The compressed data format used by the library is the -lzip format. Lzlib is written in C. +Lzlib is a data compression library providing in-memory LZMA +compression and decompression functions, including integrity checking +of the decompressed data. The compressed data format used by the +library is the lzip format. Lzlib is written in C. The lzip file format is designed for data sharing and long-term archiving, taking into account both data integrity and decoder @@ -90,15 +90,20 @@ with a SIZE equal to 0. If all the data to be compressed are written in advance, lzlib will automatically adjust the header of the compressed data to use the -smallest possible dictionary size. This feature reduces the amount of -memory needed for decompression and allows minilzip to produce identical -compressed output as lzip. +largest dictionary size that does not exceed neither the data size nor +the limit given to 'LZ_compress_open'. This feature reduces the amount +of memory needed for decompression and allows minilzip to produce +identical compressed output as lzip. Lzlib will correctly decompress a data stream which is the concatenation of two or more compressed data streams. The result is the concatenation of the corresponding decompressed data streams. Integrity testing of concatenated compressed data streams is also supported. + Lzlib is able to compress and decompress streams of unlimited size by +automatically creating multimember output. The members so created are +large, about 2 PiB each. + All the library functions are thread safe. The library does not install any signal handler. The decoder checks the consistency of the compressed data, so the library should never crash even in case of @@ -253,11 +258,13 @@ calling 'LZ_compress_errno' before using it. output as 'lzip -0'. (The dictionary size used will be rounded upwards to 64 KiB). - MEMBER_SIZE sets the member size limit in bytes. Minimum member - size limit is 100 kB. Small member size may degrade compression - ratio, so use it only when needed. To produce a single-member data - stream, give MEMBER_SIZE a value larger than the amount of data to - be produced, for example INT64_MAX. + MEMBER_SIZE sets the member size limit in bytes. Valid values + range from 100 kB to 2 PiB. Small member size may degrade + compression ratio, so use it only when needed. To produce a + single-member data stream, give MEMBER_SIZE a value larger than + the amount of data to be produced. Values larger than 2 PiB will be + reduced to 2 PiB to prevent the uncompressed size of the member + from overflowing. -- Function: int LZ_compress_close ( struct LZ_Encoder * const ENCODER ) @@ -270,6 +277,7 @@ calling 'LZ_compress_errno' before using it. ENCODER ) Use this function to tell 'lzlib' that all the data for this member have already been written (with the 'LZ_compress_write' function). + It is safe to call 'LZ_compress_finish' as many times as needed. After all the produced compressed data have been read with 'LZ_compress_read' and 'LZ_compress_member_finished' returns 1, a new member can be started with 'LZ_compress_restart_member'. @@ -322,7 +330,7 @@ calling 'LZ_compress_errno' before using it. -- Function: enum LZ_Errno LZ_compress_errno ( struct LZ_Encoder * const ENCODER ) - Returns the current error code for ENCODER (*note Error codes::). + Returns the current error code for ENCODER. *Note Error codes::. -- Function: int LZ_compress_finished ( struct LZ_Encoder * const ENCODER ) @@ -388,7 +396,8 @@ verified by calling 'LZ_decompress_errno' before using it. DECODER ) Use this function to tell 'lzlib' that all the data for this stream have already been written (with the 'LZ_decompress_write' - function). + function). It is safe to call 'LZ_decompress_finish' as many + times as needed. -- Function: int LZ_decompress_reset ( struct LZ_Decoder * const DECODER ) @@ -420,6 +429,12 @@ verified by calling 'LZ_decompress_errno' before using it. 'LZ_decompress_write' function. Note that reading less than SIZE bytes is not an error. + In case of decompression error caused by corrupt or truncated data, + 'LZ_decompress_read' does not signal the error immediately to the + application, but waits until all decoded bytes have been read. This + allows tools like tarlz to recover as much data as possible from + each damaged member. *Note tarlz manual: (tarlz)Top. + -- Function: int LZ_decompress_write ( struct LZ_Decoder * const DECODER, uint8_t * const BUFFER, const int SIZE ) The 'LZ_decompress_write' function writes up to SIZE bytes from @@ -440,7 +455,7 @@ verified by calling 'LZ_decompress_errno' before using it. -- Function: enum LZ_Errno LZ_decompress_errno ( struct LZ_Decoder * const DECODER ) - Returns the current error code for DECODER (*note Error codes::). + Returns the current error code for DECODER. *Note Error codes::. -- Function: int LZ_decompress_finished ( struct LZ_Decoder * const DECODER ) @@ -543,8 +558,8 @@ whether a call failed. If the call failed, then you can examine file. -- Constant: enum LZ_Errno LZ_library_error - A bug was detected in the library. Please, report it (*note - Problems::). + A bug was detected in the library. Please, report it. *Note + Problems::.  File: lzlib.info, Node: Error messages, Next: Invoking minilzip, Prev: Error codes, Up: Top @@ -568,6 +583,9 @@ File: lzlib.info, Node: Invoking minilzip, Next: Data format, Prev: Error mes 9 Invoking minilzip ******************* +Minilzip is a test program for the lzlib compression library, fully +compatible with lzip 1.4 or newer. + The format for running minilzip is: minilzip [OPTIONS] [FILES] @@ -585,7 +603,7 @@ command line. '-V' '--version' Print the version number of minilzip on the standard output and - exit. + exit. This version number should be included in all bug reports. '-a' '--trailing-error' @@ -654,12 +672,14 @@ command line. '-s BYTES' '--dictionary-size=BYTES' When compressing, set the dictionary size limit in bytes. Minilzip - will use the smallest possible dictionary size for each file - without exceeding this limit. Valid values range from 4 KiB to - 512 MiB. Values 12 to 29 are interpreted as powers of two, meaning - 2^12 to 2^29 bytes. Note that dictionary sizes are quantized. If - the specified size does not match one of the valid sizes, it will - be rounded upwards by adding up to (BYTES / 8) to it. + 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 specified size does not match one of + the valid sizes, it will be rounded upwards by adding up to + (BYTES / 8) to it. For maximum compression you should use a dictionary size limit as large as possible, but keep in mind that the decompression memory @@ -695,27 +715,32 @@ command line. size, and trailer contents (CRC, data size, member size). '-0 .. -9' - Set the compression parameters (dictionary size and match length - limit) as shown in the table below. The default compression level - is '-6'. Note that '-9' can be much slower than '-0'. These - options have no effect when decompressing or testing. + Compression level. Set the compression parameters (dictionary size + and match length limit) as shown in the table below. The default + compression level is '-6', equivalent to '-s8MiB -m36'. Note that + '-9' can be much slower than '-0'. These options have no effect + when decompressing or testing. 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 '--dictionary-size' and '--match-length' options directly to achieve optimal performance. - Level Dictionary size Match length limit - -0 64 KiB 16 bytes - -1 1 MiB 5 bytes - -2 1.5 MiB 6 bytes - -3 2 MiB 8 bytes - -4 3 MiB 12 bytes - -5 4 MiB 20 bytes - -6 8 MiB 36 bytes - -7 16 MiB 68 bytes - -8 24 MiB 132 bytes - -9 32 MiB 273 bytes + If several compression levels or '-s' or '-m' options are given, + the last setting is used. For example '-9 -s64MiB' is equivalent + to '-s64MiB -m273' + + Level Dictionary size (-s) Match length limit (-m) + -0 64 KiB 16 bytes + -1 1 MiB 5 bytes + -2 1.5 MiB 6 bytes + -3 2 MiB 8 bytes + -4 3 MiB 12 bytes + -5 4 MiB 20 bytes + -6 8 MiB 36 bytes + -7 16 MiB 68 bytes + -8 24 MiB 132 bytes + -9 32 MiB 273 bytes '--fast' '--best' @@ -795,11 +820,11 @@ stream, with no additional information before, between, or after them. 'DS (coded dictionary size, 1 byte)' The dictionary size is calculated by taking a power of 2 (the base - size) and substracting from it a fraction between 0/16 and 7/16 of + size) and subtracting from it a fraction between 0/16 and 7/16 of the base size. Bits 4-0 contain the base 2 logarithm of the base size (12 to 29). - Bits 7-5 contain the numerator of the fraction (0 to 7) to - substract from the base size to obtain the dictionary size. + Bits 7-5 contain the numerator of the fraction (0 to 7) to subtract + from the base size to obtain the dictionary size. Example: 0xD3 = 2^19 - 6 * 2^15 = 512 KiB - 6 * 32 KiB = 320 KiB Valid values for dictionary size range from 4 KiB to 512 MiB. @@ -845,12 +870,10 @@ Example 1: Normal compression (MEMBER_SIZE > total output). 1) LZ_compress_open 2) LZ_compress_write - 3) LZ_compress_read - 4) go back to step 2 until all input data have been written - 5) LZ_compress_finish - 6) LZ_compress_read - 7) go back to step 6 until LZ_compress_finished returns 1 - 8) LZ_compress_close + 3) if no more data to write, call LZ_compress_finish + 4) LZ_compress_read + 5) go back to step 2 until LZ_compress_finished returns 1 + 6) LZ_compress_close Example 2: Normal compression using LZ_compress_write_size. @@ -868,12 +891,10 @@ Example 3: Decompression. 1) LZ_decompress_open 2) LZ_decompress_write - 3) LZ_decompress_read - 4) go back to step 2 until all input data have been written - 5) LZ_decompress_finish - 6) LZ_decompress_read - 7) go back to step 6 until LZ_decompress_finished returns 1 - 8) LZ_decompress_close + 3) if no more data to write, call LZ_decompress_finish + 4) LZ_decompress_read + 5) go back to step 2 until LZ_decompress_finished returns 1 + 6) LZ_decompress_close Example 4: Decompression using LZ_decompress_write_size. @@ -988,20 +1009,21 @@ Concept index  Tag Table: Node: Top220 -Node: Introduction1342 -Node: Library version6154 -Node: Buffering6799 -Node: Parameter limits8024 -Node: Compression functions8983 -Node: Decompression functions15592 -Node: Error codes21762 -Node: Error messages24064 -Node: Invoking minilzip24649 -Ref: --trailing-error25243 -Node: Data format31883 -Node: Examples34454 -Node: Problems38570 -Node: Concept index39142 +Node: Introduction1341 +Node: Library version6397 +Node: Buffering7042 +Node: Parameter limits8267 +Node: Compression functions9226 +Node: Decompression functions16010 +Node: Error codes22599 +Node: Error messages24900 +Node: Invoking minilzip25485 +Ref: --trailing-error26243 +Node: Data format33248 +Ref: coded-dict-size34557 +Node: Examples35817 +Node: Problems39813 +Node: Concept index40385  End Tag Table diff --git a/doc/lzlib.texi b/doc/lzlib.texi index 34154cd..55e80c2 100644 --- a/doc/lzlib.texi +++ b/doc/lzlib.texi @@ -6,8 +6,8 @@ @finalout @c %**end of header -@set UPDATED 7 February 2018 -@set VERSION 1.10 +@set UPDATED 2 January 2019 +@set VERSION 1.11 @dircategory Data Compression @direntry @@ -51,7 +51,7 @@ This manual is for Lzlib (version @value{VERSION}, @value{UPDATED}). @end menu @sp 1 -Copyright @copyright{} 2009-2018 Antonio Diaz Diaz. +Copyright @copyright{} 2009-2019 Antonio Diaz Diaz. This manual is free documentation: you have unlimited permission to copy, distribute and modify it. @@ -61,14 +61,13 @@ to copy, distribute and modify it. @chapter Introduction @cindex introduction -Lzlib is a data compression library providing in-memory LZMA compression -and decompression functions, including integrity checking of the -decompressed data. The compressed data format used by the library is the -lzip format. Lzlib is written in C. +@uref{http://www.nongnu.org/lzip/lzlib.html,,Lzlib} is a data compression +library providing in-memory LZMA compression and decompression functions, +including integrity checking of the decompressed data. The compressed data +format used by the library is the lzip format. Lzlib is written in C. -The lzip file format is designed for data sharing and long-term -archiving, taking into account both data integrity and decoder -availability: +The lzip file format is designed for data sharing and long-term archiving, +taking into account both data integrity and decoder availability: @itemize @bullet @item @@ -118,15 +117,20 @@ data to be compressed in advance, just call the read function with a If all the data to be compressed are written in advance, lzlib will automatically adjust the header of the compressed data to use the -smallest possible dictionary size. This feature reduces the amount of -memory needed for decompression and allows minilzip to produce identical -compressed output as lzip. +largest dictionary size that does not exceed neither the data size nor +the limit given to @samp{LZ_compress_open}. This feature reduces the +amount of memory needed for decompression and allows minilzip to produce +identical compressed output as lzip. Lzlib will correctly decompress a data stream which is the concatenation of two or more compressed data streams. The result is the concatenation of the corresponding decompressed data streams. Integrity testing of concatenated compressed data streams is also supported. +Lzlib is able to compress and decompress streams of unlimited size by +automatically creating multimember output. The members so created are +large, about @w{2 PiB} each. + All the library functions are thread safe. The library does not install any signal handler. The decoder checks the consistency of the compressed data, so the library should never crash even in case of corrupted input. @@ -286,11 +290,13 @@ fast variant of LZMA is chosen, which produces identical compressed output as @code{lzip -0}. (The dictionary size used will be rounded upwards to @w{64 KiB}). -@var{member_size} sets the member size limit in bytes. Minimum member -size limit is @w{100 kB}. Small member size may degrade compression -ratio, so use it only when needed. To produce a single-member data -stream, give @var{member_size} a value larger than the amount of data to -be produced, for example INT64_MAX. +@var{member_size} sets the member size limit in bytes. Valid values +range from @w{100 kB} to @w{2 PiB}. Small member size may degrade +compression ratio, so use it only when needed. To produce a +single-member data stream, give @var{member_size} a value larger than +the amount of data to be produced. Values larger than @w{2 PiB} will be +reduced to @w{2 PiB} to prevent the uncompressed size of the member from +overflowing. @end deftypefun @@ -305,6 +311,7 @@ longer be used as an argument to any LZ_compress function. @deftypefun int LZ_compress_finish ( struct LZ_Encoder * const @var{encoder} ) Use this function to tell @samp{lzlib} that all the data for this member have already been written (with the @samp{LZ_compress_write} function). +It is safe to call @samp{LZ_compress_finish} as many times as needed. After all the produced compressed data have been read with @samp{LZ_compress_read} and @samp{LZ_compress_member_finished} returns 1, a new member can be started with @samp{LZ_compress_restart_member}. @@ -364,7 +371,7 @@ accept a @var{size} up to the returned number of bytes. @deftypefun {enum LZ_Errno} LZ_compress_errno ( struct LZ_Encoder * const @var{encoder} ) -Returns the current error code for @var{encoder} (@pxref{Error codes}). +Returns the current error code for @var{encoder}. @xref{Error codes}. @end deftypefun @@ -440,6 +447,7 @@ longer be used as an argument to any LZ_decompress function. @deftypefun int LZ_decompress_finish ( struct LZ_Decoder * const @var{decoder} ) Use this function to tell @samp{lzlib} that all the data for this stream have already been written (with the @samp{LZ_decompress_write} function). +It is safe to call @samp{LZ_decompress_finish} as many times as needed. @end deftypefun @@ -474,6 +482,16 @@ less than @var{size}; for example, if there aren't that many bytes left in the stream or if more bytes have to be yet written with the @samp{LZ_decompress_write} function. Note that reading less than @var{size} bytes is not an error. + +In case of decompression error caused by corrupt or truncated data, +@samp{LZ_decompress_read} does not signal the error immediately to the +application, but waits until all decoded bytes have been read. This +allows tools like +@uref{http://www.nongnu.org/lzip/manual/tarlz_manual.html,,tarlz} to +recover as much data as possible from each damaged member. +@ifnothtml +@xref{Top,tarlz manual,,tarlz}. +@end ifnothtml @end deftypefun @@ -498,7 +516,7 @@ will accept a @var{size} up to the returned number of bytes. @deftypefun {enum LZ_Errno} LZ_decompress_errno ( struct LZ_Decoder * const @var{decoder} ) -Returns the current error code for @var{decoder} (@pxref{Error codes}). +Returns the current error code for @var{decoder}. @xref{Error codes}. @end deftypefun @@ -616,7 +634,7 @@ used to remove conflicting trailing data from a file. @end deftypevr @deftypevr Constant {enum LZ_Errno} LZ_library_error -A bug was detected in the library. Please, report it (@pxref{Problems}). +A bug was detected in the library. Please, report it. @xref{Problems}. @end deftypevr @@ -640,6 +658,10 @@ The value of @var{lz_errno} normally comes from a call to @cindex invoking @cindex options +Minilzip is a test program for the lzlib compression library, fully +compatible with lzip 1.4 or newer. + +@noindent The format for running minilzip is: @example @@ -661,6 +683,7 @@ Print an informative help message describing the options and exit. @item -V @itemx --version Print the version number of minilzip on the standard output and exit. +This version number should be included in all bug reports. @anchor{--trailing-error} @item -a @@ -728,12 +751,13 @@ Quiet operation. Suppress all messages. @item -s @var{bytes} @itemx --dictionary-size=@var{bytes} When compressing, set the dictionary size limit in bytes. Minilzip will use -the smallest possible dictionary size for each file without exceeding -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. Note -that dictionary sizes are quantized. If the specified size does not -match one of the valid sizes, it will be rounded upwards by adding up to -@w{(@var{bytes} / 8)} to it. +for 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 specified size +does not match one of the valid sizes, it will be rounded upwards by +adding up to @w{(@var{bytes} / 8)} to it. For maximum compression you should use a dictionary size limit as large as possible, but keep in mind that the decompression memory requirement @@ -768,18 +792,23 @@ verbosity level, showing status, compression ratio, dictionary size, and trailer contents (CRC, data size, member size). @item -0 .. -9 -Set the compression parameters (dictionary size and match length limit) -as shown in the table below. The default compression level is @samp{-6}. -Note that @samp{-9} can be much slower than @samp{-0}. These options -have no effect when decompressing or testing. +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 +effect when decompressing or testing. The bidimensional parameter space of LZMA can't be mapped to a linear scale optimal for all files. If your files are large, very repetitive, etc, you may need to use the @samp{--dictionary-size} and @samp{--match-length} options directly to achieve optimal performance. -@multitable {Level} {Dictionary size} {Match length limit} -@item Level @tab Dictionary size @tab Match length limit +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}} + +@multitable {Level} {Dictionary size (-s)} {Match length limit (-m)} +@item Level @tab Dictionary size (-s) @tab Match length limit (-m) @item -0 @tab 64 KiB @tab 16 bytes @item -1 @tab 1 MiB @tab 5 bytes @item -2 @tab 1.5 MiB @tab 6 bytes @@ -875,12 +904,13 @@ A four byte string, identifying the lzip format, with the value "LZIP" @item VN (version number, 1 byte) Just in case something needs to be modified in the future. 1 for now. +@anchor{coded-dict-size} @item DS (coded dictionary size, 1 byte) The dictionary size is calculated by taking a power of 2 (the base size) -and substracting from it a fraction between 0/16 and 7/16 of the base +and subtracting from it a fraction between 0/16 and 7/16 of the base size.@* Bits 4-0 contain the base 2 logarithm of the base size (12 to 29).@* -Bits 7-5 contain the numerator of the fraction (0 to 7) to substract +Bits 7-5 contain the numerator of the fraction (0 to 7) to subtract from the base size to obtain the dictionary size.@* Example: 0xD3 = 2^19 - 6 * 2^15 = 512 KiB - 6 * 32 KiB = 320 KiB@* Valid values for dictionary size range from 4 KiB to 512 MiB. @@ -934,12 +964,10 @@ Example 1: Normal compression (@var{member_size} > total output). @example 1) LZ_compress_open 2) LZ_compress_write -3) LZ_compress_read -4) go back to step 2 until all input data have been written -5) LZ_compress_finish -6) LZ_compress_read -7) go back to step 6 until LZ_compress_finished returns 1 -8) LZ_compress_close +3) if no more data to write, call LZ_compress_finish +4) LZ_compress_read +5) go back to step 2 until LZ_compress_finished returns 1 +6) LZ_compress_close @end example @sp 1 @@ -963,12 +991,10 @@ Example 3: Decompression. @example 1) LZ_decompress_open 2) LZ_decompress_write -3) LZ_decompress_read -4) go back to step 2 until all input data have been written -5) LZ_decompress_finish -6) LZ_decompress_read -7) go back to step 6 until LZ_decompress_finished returns 1 -8) LZ_decompress_close +3) if no more data to write, call LZ_decompress_finish +4) LZ_decompress_read +5) go back to step 2 until LZ_decompress_finished returns 1 +6) LZ_decompress_close @end example @sp 1 diff --git a/doc/minilzip.1 b/doc/minilzip.1 index a5f30c8..adb6e33 100644 --- a/doc/minilzip.1 +++ b/doc/minilzip.1 @@ -1,12 +1,13 @@ .\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.46.1. -.TH MINILZIP "1" "February 2018" "minilzip 1.10" "User Commands" +.TH MINILZIP "1" "January 2019" "minilzip 1.11" "User Commands" .SH NAME minilzip \- reduces the size of files .SH SYNOPSIS .B minilzip [\fI\,options\/\fR] [\fI\,files\/\fR] .SH DESCRIPTION -Minilzip \- Test program for the lzlib library. +Minilzip is a test program for the lzlib compression library, fully +compatible with lzip 1.4 or newer. .SH OPTIONS .TP \fB\-h\fR, \fB\-\-help\fR @@ -49,7 +50,7 @@ suppress all messages set dictionary size limit in bytes [8 MiB] .TP \fB\-S\fR, \fB\-\-volume\-size=\fR -set volume size limit in bytes, implies \fB\-k\fR +set volume size limit in bytes .TP \fB\-t\fR, \fB\-\-test\fR test compressed file integrity @@ -90,8 +91,8 @@ Report bugs to lzip\-bug@nongnu.org .br Lzlib home page: http://www.nongnu.org/lzip/lzlib.html .SH COPYRIGHT -Copyright \(co 2018 Antonio Diaz Diaz. -Using lzlib 1.10 +Copyright \(co 2019 Antonio Diaz Diaz. +Using lzlib 1.11 License GPLv2+: GNU GPL version 2 or later .br This is free software: you are free to change and redistribute it. diff --git a/encoder.c b/encoder.c index 7d19235..2ec587b 100644 --- a/encoder.c +++ b/encoder.c @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -313,7 +313,7 @@ static int LZe_sequence_optimizer( struct LZ_encoder * const e, --prev_index; else /* prev_index2 >= 0 */ prev_index = prev_index2; - cur_state = 8; /* St_set_char_rep(); */ + cur_state = St_set_char_rep(); } cur_trial->state = cur_state; for( i = 0; i < num_rep_distances; ++i ) diff --git a/encoder.h b/encoder.h index 8948013..8c096df 100644 --- a/encoder.h +++ b/encoder.h @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 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/encoder_base.c b/encoder_base.c index 0dbc617..d385f2c 100644 --- a/encoder_base.c +++ b/encoder_base.c @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -24,7 +24,8 @@ static bool Mb_normalize_pos( struct Matchfinder_base * const mb ) if( !mb->at_stream_end ) { int i; - const int offset = mb->pos - mb->before_size - mb->dictionary_size; + /* offset is int32_t for the min below */ + const int32_t offset = mb->pos - mb->before_size - mb->dictionary_size; const int size = mb->stream_pos - offset; memmove( mb->buffer, mb->buffer + offset, size ); mb->partial_data_pos += offset; @@ -131,19 +132,19 @@ static void LZeb_try_full_flush( struct LZ_encoder_base * const eb ) int i; const int pos_state = Mb_data_position( &eb->mb ) & pos_state_mask; const State state = eb->state; - File_trailer trailer; + Lzip_trailer trailer; if( eb->member_finished || - Cb_free_bytes( &eb->renc.cb ) < max_marker_size + eb->renc.ff_count + Ft_size ) + Cb_free_bytes( &eb->renc.cb ) < max_marker_size + eb->renc.ff_count + Lt_size ) return; eb->member_finished = true; Re_encode_bit( &eb->renc, &eb->bm_match[state][pos_state], 1 ); Re_encode_bit( &eb->renc, &eb->bm_rep[state], 0 ); LZeb_encode_pair( eb, 0xFFFFFFFFU, min_match_len, pos_state ); Re_flush( &eb->renc ); - Ft_set_data_crc( trailer, LZeb_crc( eb ) ); - Ft_set_data_size( trailer, Mb_data_position( &eb->mb ) ); - Ft_set_member_size( trailer, Re_member_position( &eb->renc ) + Ft_size ); - for( i = 0; i < Ft_size; ++i ) + Lt_set_data_crc( trailer, LZeb_crc( eb ) ); + Lt_set_data_size( trailer, Mb_data_position( &eb->mb ) ); + Lt_set_member_size( trailer, Re_member_position( &eb->renc ) + Lt_size ); + for( i = 0; i < Lt_size; ++i ) Cb_put_byte( &eb->renc.cb, trailer[i] ); } @@ -173,7 +174,8 @@ static void LZeb_reset( struct LZ_encoder_base * const eb, { int i; Mb_reset( &eb->mb ); - eb->member_size_limit = member_size - Ft_size - max_marker_size; + eb->member_size_limit = + min( member_size, 0x0008000000000000ULL ) - Lt_size - max_marker_size; eb->crc = 0xFFFFFFFFU; Bm_array_init( eb->bm_literal[0], (1 << literal_context_bits) * 0x300 ); Bm_array_init( eb->bm_match[0], states * pos_states ); diff --git a/encoder_base.h b/encoder_base.h index ddba7e6..f0240cc 100644 --- a/encoder_base.h +++ b/encoder_base.h @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -322,7 +322,7 @@ struct Range_encoder uint32_t range; unsigned ff_count; uint8_t cache; - File_header header; + Lzip_header header; }; static inline void Re_shift_low( struct Range_encoder * const renc ) @@ -349,8 +349,8 @@ static inline void Re_reset( struct Range_encoder * const renc, renc->range = 0xFFFFFFFFU; renc->ff_count = 0; renc->cache = 0; - Fh_set_dictionary_size( renc->header, dictionary_size ); - for( i = 0; i < Fh_size; ++i ) + Lh_set_dictionary_size( renc->header, dictionary_size ); + for( i = 0; i < Lh_size; ++i ) Cb_put_byte( &renc->cb, renc->header[i] ); } @@ -360,7 +360,7 @@ static inline bool Re_init( struct Range_encoder * const renc, { if( !Cb_init( &renc->cb, 65536 + min_free_bytes ) ) return false; renc->min_free_bytes = min_free_bytes; - Fh_set_magic( renc->header ); + Lh_set_magic( renc->header ); Re_reset( renc, dictionary_size ); return true; } diff --git a/fast_encoder.c b/fast_encoder.c index 1ba80e0..48f8368 100644 --- a/fast_encoder.c +++ b/fast_encoder.c @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 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/fast_encoder.h b/fast_encoder.h index 47dfb3e..6066b85 100644 --- a/fast_encoder.h +++ b/fast_encoder.h @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -58,9 +58,9 @@ static inline bool FLZe_init( struct FLZ_encoder * const fe, /* bytes to keep in buffer after pos */ after_size = max_match_len, dict_factor = 16, + min_free_bytes = max_marker_size, num_prev_positions23 = 0, - pos_array_factor = 1, - min_free_bytes = max_marker_size }; + pos_array_factor = 1 }; return LZeb_init( &fe->eb, before_size, dict_size, after_size, dict_factor, num_prev_positions23, pos_array_factor, min_free_bytes, diff --git a/lzcheck.c b/lzcheck.c index 83e206d..deb4f2a 100644 --- a/lzcheck.c +++ b/lzcheck.c @@ -1,5 +1,5 @@ /* Lzcheck - Test program for the lzlib library - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This program is free software: you have unlimited permission to copy, distribute and modify it. @@ -119,9 +119,11 @@ int lzcheck( FILE * const file, const int dictionary_size ) { rewind( file ); if( LZ_compress_finish( encoder ) < 0 || + LZ_compress_finish( encoder ) < 0 || LZ_decompress_write( decoder, mid_buffer, LZ_compress_read( encoder, mid_buffer, buffer_size ) ) < 0 || LZ_decompress_read( decoder, out_buffer, buffer_size ) != 0 || + LZ_compress_finish( encoder ) < 0 || LZ_compress_restart_member( encoder, member_size ) < 0 ) { fprintf( stderr, "lzcheck: Can't finish member: %s\n", diff --git a/lzip.h b/lzip.h index 3fdf70f..c0ef9e8 100644 --- a/lzip.h +++ b/lzip.h @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -36,6 +36,8 @@ static inline State St_set_char( const State st ) return next[st]; } +static inline State St_set_char_rep() { return 8; } + static inline State St_set_match( const State st ) { return ( ( st < 7 ) ? 7 : 10 ); } @@ -191,43 +193,43 @@ static inline int real_bits( unsigned value ) } -static const uint8_t magic_string[4] = { 0x4C, 0x5A, 0x49, 0x50 }; /* "LZIP" */ +static const uint8_t lzip_magic[4] = { 0x4C, 0x5A, 0x49, 0x50 }; /* "LZIP" */ -typedef uint8_t File_header[6]; /* 0-3 magic bytes */ +typedef uint8_t Lzip_header[6]; /* 0-3 magic bytes */ /* 4 version */ /* 5 coded_dict_size */ -enum { Fh_size = 6 }; +enum { Lh_size = 6 }; -static inline void Fh_set_magic( File_header data ) - { memcpy( data, magic_string, 4 ); data[4] = 1; } +static inline void Lh_set_magic( Lzip_header data ) + { memcpy( data, lzip_magic, 4 ); data[4] = 1; } -static inline bool Fh_verify_magic( const File_header data ) - { return ( memcmp( data, magic_string, 4 ) == 0 ); } +static inline bool Lh_verify_magic( const Lzip_header data ) + { return ( memcmp( data, lzip_magic, 4 ) == 0 ); } /* detect (truncated) header */ -static inline bool Fh_verify_prefix( const File_header data, const int sz ) +static inline bool Lh_verify_prefix( const Lzip_header data, const int sz ) { int i; for( i = 0; i < sz && i < 4; ++i ) - if( data[i] != magic_string[i] ) return false; + if( data[i] != lzip_magic[i] ) return false; return ( sz > 0 ); } /* detect corrupt header */ -static inline bool Fh_verify_corrupt( const File_header data ) +static inline bool Lh_verify_corrupt( const Lzip_header data ) { int matches = 0; int i; for( i = 0; i < 4; ++i ) - if( data[i] == magic_string[i] ) ++matches; + if( data[i] == lzip_magic[i] ) ++matches; return ( matches > 1 && matches < 4 ); } -static inline uint8_t Fh_version( const File_header data ) +static inline uint8_t Lh_version( const Lzip_header data ) { return data[4]; } -static inline bool Fh_verify_version( const File_header data ) +static inline bool Lh_verify_version( const Lzip_header data ) { return ( data[4] == 1 ); } -static inline unsigned Fh_get_dictionary_size( const File_header data ) +static inline unsigned Lh_get_dictionary_size( const Lzip_header data ) { unsigned sz = ( 1 << ( data[5] & 0x1F ) ); if( sz > min_dictionary_size ) @@ -235,7 +237,7 @@ static inline unsigned Fh_get_dictionary_size( const File_header data ) return sz; } -static inline bool Fh_set_dictionary_size( File_header data, const unsigned sz ) +static inline bool Lh_set_dictionary_size( Lzip_header data, const unsigned sz ) { if( !isvalid_ds( sz ) ) return false; data[5] = real_bits( sz - 1 ); @@ -251,47 +253,46 @@ static inline bool Fh_set_dictionary_size( File_header data, const unsigned sz ) return true; } -static inline bool Fh_verify( const File_header data ) +static inline bool Lh_verify( const Lzip_header data ) { - if( Fh_verify_magic( data ) && Fh_verify_version( data ) ) - return isvalid_ds( Fh_get_dictionary_size( data ) ); + if( Lh_verify_magic( data ) && Lh_verify_version( data ) ) + return isvalid_ds( Lh_get_dictionary_size( data ) ); return false; } -typedef uint8_t File_trailer[20]; +typedef uint8_t Lzip_trailer[20]; /* 0-3 CRC32 of the uncompressed data */ /* 4-11 size of the uncompressed data */ /* 12-19 member size including header and trailer */ +enum { Lt_size = 20 }; -enum { Ft_size = 20 }; - -static inline unsigned Ft_get_data_crc( const File_trailer data ) +static inline unsigned Lt_get_data_crc( const Lzip_trailer data ) { unsigned tmp = 0; int i; for( i = 3; i >= 0; --i ) { tmp <<= 8; tmp += data[i]; } return tmp; } -static inline void Ft_set_data_crc( File_trailer data, unsigned crc ) +static inline void Lt_set_data_crc( Lzip_trailer data, unsigned crc ) { int i; for( i = 0; i <= 3; ++i ) { data[i] = (uint8_t)crc; crc >>= 8; } } -static inline unsigned long long Ft_get_data_size( const File_trailer data ) +static inline unsigned long long Lt_get_data_size( const Lzip_trailer data ) { unsigned long long tmp = 0; int i; for( i = 11; i >= 4; --i ) { tmp <<= 8; tmp += data[i]; } return tmp; } -static inline void Ft_set_data_size( File_trailer data, unsigned long long sz ) +static inline void Lt_set_data_size( Lzip_trailer data, unsigned long long sz ) { int i; for( i = 4; i <= 11; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; } } -static inline unsigned long long Ft_get_member_size( const File_trailer data ) +static inline unsigned long long Lt_get_member_size( const Lzip_trailer data ) { unsigned long long tmp = 0; int i; for( i = 19; i >= 12; --i ) { tmp <<= 8; tmp += data[i]; } return tmp; } -static inline void Ft_set_member_size( File_trailer data, unsigned long long sz ) +static inline void Lt_set_member_size( Lzip_trailer data, unsigned long long sz ) { int i; for( i = 12; i <= 19; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; } } diff --git a/lzlib.c b/lzlib.c index 757ad25..f9f7d2f 100644 --- a/lzlib.c +++ b/lzlib.c @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -65,7 +65,7 @@ struct LZ_Decoder struct Range_decoder * rdec; struct LZ_decoder * lz_decoder; enum LZ_Errno lz_errno; - File_header member_header; /* header of current member */ + Lzip_header member_header; /* header of current member */ bool fatal; bool first_header; /* true until first header is read */ bool seeking; @@ -79,7 +79,7 @@ static void LZ_Decoder_init( struct LZ_Decoder * const d ) d->rdec = 0; d->lz_decoder = 0; d->lz_errno = LZ_ok; - for( i = 0; i < Fh_size; ++i ) d->member_header[i] = 0; + for( i = 0; i < Lh_size; ++i ) d->member_header[i] = 0; d->fatal = false; d->first_header = true; d->seeking = false; @@ -119,7 +119,7 @@ const char * LZ_strerror( const enum LZ_Errno lz_errno ) case LZ_mem_error : return "Not enough memory"; case LZ_sequence_error: return "Sequence error"; case LZ_header_error : return "Header error"; - case LZ_unexpected_eof: return "Unexpected eof"; + case LZ_unexpected_eof: return "Unexpected EOF"; case LZ_data_error : return "Data error"; case LZ_library_error : return "Library error"; } @@ -141,12 +141,12 @@ struct LZ_Encoder * LZ_compress_open( const int dictionary_size, const int match_len_limit, const unsigned long long member_size ) { - File_header header; + Lzip_header header; struct LZ_Encoder * const e = (struct LZ_Encoder *)malloc( sizeof (struct LZ_Encoder) ); if( !e ) return 0; LZ_Encoder_init( e ); - if( !Fh_set_dictionary_size( header, dictionary_size ) || + if( !Lh_set_dictionary_size( header, dictionary_size ) || match_len_limit < min_match_len_limit || match_len_limit > max_match_len || member_size < min_dictionary_size ) @@ -163,7 +163,7 @@ struct LZ_Encoder * LZ_compress_open( const int dictionary_size, else { e->lz_encoder = (struct LZ_encoder *)malloc( sizeof (struct LZ_encoder) ); - if( e->lz_encoder && LZe_init( e->lz_encoder, Fh_get_dictionary_size( header ), + if( e->lz_encoder && LZe_init( e->lz_encoder, Lh_get_dictionary_size( header ), match_len_limit, member_size ) ) { e->lz_encoder_base = &e->lz_encoder->eb; return e; } free( e->lz_encoder ); e->lz_encoder = 0; @@ -193,10 +193,10 @@ int LZ_compress_finish( struct LZ_Encoder * const e ) /* if (open --> write --> finish) use same dictionary size as lzip. */ /* this does not save any memory. */ if( Mb_data_position( &e->lz_encoder_base->mb ) == 0 && - Re_member_position( &e->lz_encoder_base->renc ) == Fh_size ) + Re_member_position( &e->lz_encoder_base->renc ) == Lh_size ) { Mb_adjust_dictionary_size( &e->lz_encoder_base->mb ); - Fh_set_dictionary_size( e->lz_encoder_base->renc.header, + Lh_set_dictionary_size( e->lz_encoder_base->renc.header, e->lz_encoder_base->mb.dictionary_size ); e->lz_encoder_base->renc.cb.buffer[5] = e->lz_encoder_base->renc.header[5]; } @@ -400,7 +400,10 @@ int LZ_decompress_read( struct LZ_Decoder * const d, uint8_t * const buffer, const int size ) { int result; - if( !verify_decoder( d ) || d->fatal ) return -1; + if( !verify_decoder( d ) ) return -1; + if( d->fatal ) /* don't return error until pending bytes are read */ + { if( d->lz_decoder && !Cb_empty( &d->lz_decoder->cb ) ) goto get_data; + return -1; } if( d->seeking || size < 0 ) return 0; if( d->lz_decoder && LZd_member_finished( d->lz_decoder ) ) @@ -413,26 +416,26 @@ int LZ_decompress_read( struct LZ_Decoder * const d, int rd; d->partial_in_size += d->rdec->member_position; d->rdec->member_position = 0; - if( Rd_available_bytes( d->rdec ) < Fh_size + 5 && + if( Rd_available_bytes( d->rdec ) < Lh_size + 5 && !d->rdec->at_stream_end ) return 0; if( Rd_finished( d->rdec ) && !d->first_header ) return 0; - rd = Rd_read_data( d->rdec, d->member_header, Fh_size ); - if( Rd_finished( d->rdec ) ) /* End Of File */ + rd = Rd_read_data( d->rdec, d->member_header, Lh_size ); + if( rd < Lh_size || Rd_finished( d->rdec ) ) /* End Of File */ { - if( rd <= 0 || Fh_verify_prefix( d->member_header, rd ) ) + if( rd <= 0 || Lh_verify_prefix( d->member_header, rd ) ) d->lz_errno = LZ_unexpected_eof; else d->lz_errno = LZ_header_error; d->fatal = true; return -1; } - if( !Fh_verify_magic( d->member_header ) ) + if( !Lh_verify_magic( d->member_header ) ) { /* unreading the header prevents sync_to_member from skipping a member if leading garbage is shorter than a full header; "lgLZIP\x01\x0C" */ if( Rd_unread_data( d->rdec, rd ) ) { - if( d->first_header || !Fh_verify_corrupt( d->member_header ) ) + if( d->first_header || !Lh_verify_corrupt( d->member_header ) ) d->lz_errno = LZ_header_error; else d->lz_errno = LZ_data_error; /* corrupt header */ @@ -442,10 +445,12 @@ int LZ_decompress_read( struct LZ_Decoder * const d, d->fatal = true; return -1; } - if( !Fh_verify_version( d->member_header ) || - !isvalid_ds( Fh_get_dictionary_size( d->member_header ) ) ) + if( !Lh_verify_version( d->member_header ) || + !isvalid_ds( Lh_get_dictionary_size( d->member_header ) ) ) { - if( Rd_unread_data( d->rdec, 1 + !Fh_verify_version( d->member_header ) ) ) + /* Skip a possible "LZIP" leading garbage; "LZIPLZIP\x01\x0C". + Leave member_pos pointing to the first error. */ + if( Rd_unread_data( d->rdec, 1 + !Lh_verify_version( d->member_header ) ) ) d->lz_errno = LZ_data_error; /* bad version or bad dict size */ else d->lz_errno = LZ_library_error; @@ -464,7 +469,7 @@ int LZ_decompress_read( struct LZ_Decoder * const d, } d->lz_decoder = (struct LZ_decoder *)malloc( sizeof (struct LZ_decoder) ); if( !d->lz_decoder || !LZd_init( d->lz_decoder, d->rdec, - Fh_get_dictionary_size( d->member_header ) ) ) + Lh_get_dictionary_size( d->member_header ) ) ) { /* not enough free memory */ if( d->lz_decoder ) { LZd_free( d->lz_decoder ); free( d->lz_decoder ); d->lz_decoder = 0; } @@ -477,15 +482,16 @@ int LZ_decompress_read( struct LZ_Decoder * const d, result = LZd_decode_member( d->lz_decoder ); if( result != 0 ) { - if( result == 2 ) /* set position at EOF */ + if( result == 2 ) /* set input position at EOF */ { d->rdec->member_position += Cb_used_bytes( &d->rdec->cb ); Cb_reset( &d->rdec->cb ); d->lz_errno = LZ_unexpected_eof; } else if( result == 5 ) d->lz_errno = LZ_library_error; else d->lz_errno = LZ_data_error; d->fatal = true; - return -1; + if( Cb_empty( &d->lz_decoder->cb ) ) return -1; } +get_data: return Cb_read_data( &d->lz_decoder->cb, buffer, size ); } @@ -529,7 +535,7 @@ enum LZ_Errno LZ_decompress_errno( struct LZ_Decoder * const d ) int LZ_decompress_finished( struct LZ_Decoder * const d ) { - if( !verify_decoder( d ) ) return -1; + if( !verify_decoder( d ) || d->fatal ) return -1; return ( Rd_finished( d->rdec ) && ( !d->lz_decoder || LZd_member_finished( d->lz_decoder ) ) ); } @@ -537,7 +543,7 @@ int LZ_decompress_finished( struct LZ_Decoder * const d ) int LZ_decompress_member_finished( struct LZ_Decoder * const d ) { - if( !verify_decoder( d ) ) return -1; + if( !verify_decoder( d ) || d->fatal ) return -1; return ( d->lz_decoder && LZd_member_finished( d->lz_decoder ) ); } @@ -545,14 +551,14 @@ int LZ_decompress_member_finished( struct LZ_Decoder * const d ) int LZ_decompress_member_version( struct LZ_Decoder * const d ) { if( !verify_decoder( d ) ) return -1; - return Fh_version( d->member_header ); + return Lh_version( d->member_header ); } int LZ_decompress_dictionary_size( struct LZ_Decoder * const d ) { if( !verify_decoder( d ) ) return -1; - return Fh_get_dictionary_size( d->member_header ); + return Lh_get_dictionary_size( d->member_header ); } diff --git a/lzlib.h b/lzlib.h index 1eed1e0..97672a0 100644 --- a/lzlib.h +++ b/lzlib.h @@ -1,5 +1,5 @@ /* Lzlib - Compression library for the lzip format - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and binary forms, with or without modification, are permitted provided @@ -23,7 +23,7 @@ extern "C" { #define LZ_API_VERSION 1 -static const char * const LZ_version_string = "1.10"; +static const char * const LZ_version_string = "1.11"; enum LZ_Errno { LZ_ok = 0, LZ_bad_argument, LZ_mem_error, LZ_sequence_error, LZ_header_error, LZ_unexpected_eof, diff --git a/main.c b/main.c index 3e3e411..b6a13e9 100644 --- a/main.c +++ b/main.c @@ -1,5 +1,5 @@ /* Minilzip - Test program for the lzlib library - Copyright (C) 2009-2018 Antonio Diaz Diaz. + Copyright (C) 2009-2019 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 @@ -35,20 +35,25 @@ #include #include #include -#if defined(__MSVCRT__) +#if defined(__MSVCRT__) || defined(__OS2__) || defined(__DJGPP__) #include +#if defined(__MSVCRT__) #define fchmod(x,y) 0 #define fchown(x,y,z) 0 #define strtoull strtoul #define SIGHUP SIGTERM #define S_ISSOCK(x) 0 +#ifndef S_IRGRP #define S_IRGRP 0 #define S_IWGRP 0 #define S_IROTH 0 #define S_IWOTH 0 #endif -#if defined(__OS2__) -#include +#endif +#if defined(__DJGPP__) +#define S_ISSOCK(x) 0 +#define S_ISVTX 0 +#endif #endif #include "carg_parser.h" @@ -77,9 +82,8 @@ void internal_error( const char * const msg ); int verbosity = 0; -const char * const Program_name = "Minilzip"; const char * const program_name = "minilzip"; -const char * const program_year = "2018"; +const char * const program_year = "2019"; const char * invocation_name = 0; const struct { const char * from; const char * to; } known_extensions[] = { @@ -95,6 +99,8 @@ struct Lzma_options enum Mode { m_compress, m_decompress, m_test }; +/* Variables used in signal handler context. + They are not declared volatile because the handler never returns. */ char * output_filename = 0; int outfd = -1; bool delete_output_on_interrupt = false; @@ -102,8 +108,9 @@ bool delete_output_on_interrupt = false; static void show_help( void ) { - printf( "%s - Test program for the lzlib library.\n", Program_name ); - printf( "\nUsage: %s [options] [files]\n", invocation_name ); + printf( "Minilzip is a test program for the lzlib compression library, fully\n" + "compatible with lzip 1.4 or newer.\n" + "\nUsage: %s [options] [files]\n", invocation_name ); printf( "\nOptions:\n" " -h, --help display this help and exit\n" " -V, --version output version information and exit\n" @@ -118,7 +125,7 @@ static void show_help( void ) " -o, --output= if reading standard input, write to \n" " -q, --quiet suppress all messages\n" " -s, --dictionary-size= set dictionary size limit in bytes [8 MiB]\n" - " -S, --volume-size= set volume size limit in bytes, implies -k\n" + " -S, --volume-size= set volume size limit in bytes\n" " -t, --test test compressed file integrity\n" " -v, --verbose be verbose (a 2nd -v gives more)\n" " -0 .. -9 set compression level [default 6]\n" @@ -196,7 +203,7 @@ static void Pp_init( struct Pretty_print * const pp, { const char * const s = filenames[i]; const unsigned len = (strcmp( s, "-" ) == 0) ? stdin_name_len : strlen( s ); - if( len > pp->longest_name ) pp->longest_name = len; + if( pp->longest_name < len ) pp->longest_name = len; } if( pp->longest_name == 0 ) pp->longest_name = stdin_name_len; } @@ -322,6 +329,17 @@ static int get_dict_size( const char * const arg ) } +void set_mode( enum Mode * const program_modep, const enum Mode new_mode ) + { + if( *program_modep != m_compress && *program_modep != new_mode ) + { + show_error( "Only one operation can be specified.", 0, true ); + exit( 1 ); + } + *program_modep = new_mode; + } + + static int extension_index( const char * const name ) { int eindex; @@ -457,8 +475,17 @@ static bool check_tty( const char * const input_filename, const int infd, } +static void set_signals( void (*action)(int) ) + { + signal( SIGHUP, action ); + signal( SIGINT, action ); + signal( SIGTERM, action ); + } + + void cleanup_and_fail( const int retval ) { + set_signals( SIG_IGN ); /* ignore signals */ if( delete_output_on_interrupt ) { delete_output_on_interrupt = false; @@ -473,6 +500,14 @@ void cleanup_and_fail( const int retval ) } +void signal_handler( int sig ) + { + if( sig ) {} /* keep compiler happy */ + show_error( "Control-C or similar caught, quitting.", 0, false ); + cleanup_and_fail( 1 ); + } + + /* Set permissions, owner and times. */ static void close_and_set_permissions( const struct stat * const in_statsp ) { @@ -696,7 +731,8 @@ static int do_decompress( struct LZ_Decoder * const decoder, const int infd, for( first_member = true; ; ) { - const int max_in_size = min( LZ_decompress_write_size( decoder ), buffer_size ); + const int max_in_size = + min( LZ_decompress_write_size( decoder ), buffer_size ); int in_size = 0, out_size = 0; if( max_in_size > 0 ) { @@ -712,7 +748,8 @@ static int do_decompress( struct LZ_Decoder * const decoder, const int infd, } while( true ) { - const int rd = LZ_decompress_read( decoder, buffer, buffer_size ); + const int rd = + LZ_decompress_read( decoder, (outfd >= 0) ? buffer : 0, buffer_size ); if( rd > 0 ) { out_size += rd; @@ -839,31 +876,13 @@ static int decompress( const int infd, struct Pretty_print * const pp, } -void signal_handler( int sig ) - { - if( sig ) {} /* keep compiler happy */ - show_error( "Control-C or similar caught, quitting.", 0, false ); - cleanup_and_fail( 1 ); - } - - -static void set_signals( void ) - { - signal( SIGHUP, signal_handler ); - signal( SIGINT, signal_handler ); - signal( SIGTERM, signal_handler ); - } - - void show_error( const char * const msg, const int errcode, const bool help ) { if( verbosity < 0 ) return; if( msg && msg[0] ) - { - fprintf( stderr, "%s: %s", program_name, msg ); - if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) ); - fputc( '\n', stderr ); - } + fprintf( stderr, "%s: %s%s%s\n", program_name, msg, + ( errcode > 0 ) ? ": " : "", + ( errcode > 0 ) ? strerror( errcode ) : "" ); if( help ) fprintf( stderr, "Try '%s --help' for more information.\n", invocation_name ); @@ -873,10 +892,10 @@ void show_error( const char * const msg, const int errcode, const bool help ) void show_file_error( const char * const filename, const char * const msg, const int errcode ) { - if( verbosity < 0 ) return; - fprintf( stderr, "%s: %s: %s", program_name, filename, msg ); - if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) ); - fputc( '\n', stderr ); + if( verbosity >= 0 ) + fprintf( stderr, "%s: %s: %s%s%s\n", program_name, filename, msg, + ( errcode > 0 ) ? ": " : "", + ( errcode > 0 ) ? strerror( errcode ) : "" ); } @@ -987,7 +1006,7 @@ int main( const int argc, const char * const argv[] ) case 'a': ignore_trailing = false; break; case 'b': member_size = getnum( arg, 100000, max_member_size ); break; case 'c': to_stdout = true; break; - case 'd': program_mode = m_decompress; break; + case 'd': set_mode( &program_mode, m_decompress ); break; case 'f': force = true; break; case 'F': recompress = true; break; case 'h': show_help(); return 0; @@ -1001,7 +1020,7 @@ int main( const int argc, const char * const argv[] ) case 's': encoder_options.dictionary_size = get_dict_size( arg ); break; case 'S': volume_size = getnum( arg, 100000, max_volume_size ); break; - case 't': program_mode = m_test; break; + case 't': set_mode( &program_mode, m_test ); break; case 'v': if( verbosity < 4 ) ++verbosity; break; case 'V': show_version(); return 0; case opt_lt: loose_trailing = true; break; @@ -1009,7 +1028,7 @@ int main( const int argc, const char * const argv[] ) } } /* end process options */ -#if defined(__MSVCRT__) || defined(__OS2__) +#if defined(__MSVCRT__) || defined(__OS2__) || defined(__DJGPP__) setmode( STDIN_FILENO, O_BINARY ); setmode( STDOUT_FILENO, O_BINARY ); #endif @@ -1029,7 +1048,7 @@ int main( const int argc, const char * const argv[] ) if( !to_stdout && program_mode != m_test && ( filenames_given || default_output_filename[0] ) ) - set_signals(); + set_signals( signal_handler ); Pp_init( &pp, filenames, num_filenames ); @@ -1109,6 +1128,12 @@ int main( const int argc, const char * const argv[] ) else tmp = decompress( infd, &pp, ignore_trailing, loose_trailing, program_mode == m_test ); + if( close( infd ) != 0 ) + { + show_error( input_filename[0] ? "Error closing input file" : + "Error closing stdin", errno, false ); + if( tmp < 1 ) tmp = 1; + } if( tmp > retval ) retval = tmp; if( tmp ) { if( program_mode != m_test ) cleanup_and_fail( retval ); @@ -1118,7 +1143,6 @@ int main( const int argc, const char * const argv[] ) close_and_set_permissions( in_statsp ); if( input_filename[0] ) { - close( infd ); if( !keep_input_files && !to_stdout && program_mode != m_test && ( program_mode != m_compress || volume_size == 0 ) ) remove( input_filename ); diff --git a/testsuite/check.sh b/testsuite/check.sh index 929a690..026ea2b 100755 --- a/testsuite/check.sh +++ b/testsuite/check.sh @@ -1,6 +1,6 @@ #! /bin/sh # check script for Lzlib - Compression library for the lzip format -# Copyright (C) 2009-2018 Antonio Diaz Diaz. +# Copyright (C) 2009-2019 Antonio Diaz Diaz. # # This script is free software: you have unlimited permission # to copy, distribute and modify it. @@ -39,12 +39,15 @@ test_failed() { fail=1 ; printf " $1" ; [ -z "$2" ] || printf "($2)" ; } printf "testing lzlib-%s..." "$2" "${LZIP}" -fkqm4 in -{ [ $? = 1 ] && [ ! -e in.lz ] ; } || test_failed $LINENO +[ $? = 1 ] || test_failed $LINENO +[ ! -e in.lz ] || test_failed $LINENO "${LZIP}" -fkqm274 in -{ [ $? = 1 ] && [ ! -e in.lz ] ; } || test_failed $LINENO +[ $? = 1 ] || test_failed $LINENO +[ ! -e in.lz ] || test_failed $LINENO for i in bad_size -1 0 4095 513MiB 1G 1T 1P 1E 1Z 1Y 10KB ; do "${LZIP}" -fkqs $i in - { [ $? = 1 ] && [ ! -e in.lz ] ; } || test_failed $LINENO $i + [ $? = 1 ] || test_failed $LINENO $i + [ ! -e in.lz ] || test_failed $LINENO $i done "${LZIP}" -tq in [ $? = 2 ] || test_failed $LINENO @@ -57,6 +60,8 @@ done "${LZIP}" -dq -o in < "${in_lz}" [ $? = 1 ] || test_failed $LINENO # these are for code coverage +"${LZIP}" -cdt "${in_lz}" > out 2> /dev/null +[ $? = 1 ] || test_failed $LINENO "${LZIP}" -t -- nx_file 2> /dev/null [ $? = 1 ] || test_failed $LINENO "${LZIP}" --help > /dev/null || test_failed $LINENO @@ -89,41 +94,46 @@ cmp in copy || test_failed $LINENO "${LZIP}" -cd "${testdir}"/test_sync.lz > copy || test_failed $LINENO cmp in copy || test_failed $LINENO -rm -f copy +rm -f copy || framework_failure cat "${in_lz}" > copy.lz || framework_failure "${LZIP}" -dk copy.lz || test_failed $LINENO cmp in copy || test_failed $LINENO printf "to be overwritten" > copy || framework_failure "${LZIP}" -d copy.lz 2> /dev/null [ $? = 1 ] || test_failed $LINENO -"${LZIP}" -df copy.lz -{ [ $? = 0 ] && [ ! -e copy.lz ] && cmp in copy ; } || test_failed $LINENO +"${LZIP}" -df copy.lz || test_failed $LINENO +[ ! -e copy.lz ] || test_failed $LINENO +cmp in copy || test_failed $LINENO -rm -f copy +rm -f copy || framework_failure cat "${in_lz}" > copy.lz || framework_failure -"${LZIP}" -d -S100k copy.lz -{ [ $? = 0 ] && [ ! -e copy.lz ] && cmp in copy ; } || test_failed $LINENO +"${LZIP}" -d -S100k copy.lz || test_failed $LINENO # ignore -S +[ ! -e copy.lz ] || test_failed $LINENO +cmp in copy || test_failed $LINENO printf "to be overwritten" > copy || framework_failure "${LZIP}" -df -o copy < "${in_lz}" || test_failed $LINENO cmp in copy || test_failed $LINENO -rm -f copy +rm -f copy || framework_failure "${LZIP}" -s16 < in > anyothername || test_failed $LINENO -"${LZIP}" -dv --output copy - anyothername - < "${in_lz}" 2> /dev/null -{ [ $? = 0 ] && cmp in copy && cmp in anyothername.out ; } || +"${LZIP}" -dv --output copy - anyothername - < "${in_lz}" 2> /dev/null || test_failed $LINENO -rm -f copy anyothername.out +cmp in copy || test_failed $LINENO +cmp in anyothername.out || test_failed $LINENO +rm -f copy anyothername.out || framework_failure "${LZIP}" -tq in "${in_lz}" [ $? = 2 ] || test_failed $LINENO "${LZIP}" -tq nx_file.lz "${in_lz}" [ $? = 1 ] || test_failed $LINENO "${LZIP}" -cdq in "${in_lz}" > copy -{ [ $? = 2 ] && cat copy in | cmp in - ; } || test_failed $LINENO +[ $? = 2 ] || test_failed $LINENO +cat copy in | cmp in - || test_failed $LINENO "${LZIP}" -cdq nx_file.lz "${in_lz}" > copy -{ [ $? = 1 ] && cmp in copy ; } || test_failed $LINENO -rm -f copy +[ $? = 1 ] || test_failed $LINENO +cmp in copy || test_failed $LINENO +rm -f copy || framework_failure cat "${in_lz}" > copy.lz || framework_failure for i in 1 2 3 4 5 6 7 ; do printf "g" >> copy.lz || framework_failure @@ -131,11 +141,15 @@ for i in 1 2 3 4 5 6 7 ; do [ $? = 2 ] || test_failed $LINENO $i done "${LZIP}" -dq in copy.lz -{ [ $? = 2 ] && [ -e copy.lz ] && [ ! -e copy ] && [ ! -e in.out ] ; } || - test_failed $LINENO +[ $? = 2 ] || test_failed $LINENO +[ -e copy.lz ] || test_failed $LINENO +[ ! -e copy ] || test_failed $LINENO +[ ! -e in.out ] || test_failed $LINENO "${LZIP}" -dq nx_file.lz copy.lz -{ [ $? = 1 ] && [ ! -e copy.lz ] && [ ! -e nx_file ] && cmp in copy ; } || - test_failed $LINENO +[ $? = 1 ] || test_failed $LINENO +[ ! -e copy.lz ] || test_failed $LINENO +[ ! -e nx_file ] || test_failed $LINENO +cmp in copy || test_failed $LINENO cat in in > in2 || framework_failure cat "${in_lz}" "${in_lz}" > in2.lz || framework_failure @@ -150,18 +164,21 @@ cmp in2 copy2 || test_failed $LINENO printf "\ngarbage" >> copy2.lz || framework_failure "${LZIP}" -tvvvv copy2.lz 2> /dev/null || test_failed $LINENO -rm -f copy2 +rm -f copy2 || framework_failure "${LZIP}" -atq copy2.lz [ $? = 2 ] || test_failed $LINENO "${LZIP}" -atq < copy2.lz [ $? = 2 ] || test_failed $LINENO "${LZIP}" -adkq copy2.lz -{ [ $? = 2 ] && [ ! -e copy2 ] ; } || test_failed $LINENO +[ $? = 2 ] || test_failed $LINENO +[ ! -e copy2 ] || test_failed $LINENO "${LZIP}" -adkq -o copy2 < copy2.lz -{ [ $? = 2 ] && [ ! -e copy2 ] ; } || test_failed $LINENO +[ $? = 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 $LINENO +rm -f in2 copy2 || framework_failure printf "\ntesting compression..." @@ -197,36 +214,37 @@ for i in s4Ki 0 1 2 3 4 5 6 7 8 9 ; do "${LZIP}" -df -o copy < out.lz || test_failed $LINENO $i cmp in copy || test_failed $LINENO $i done +rm -f out.lz || framework_failure cat in in in in in in in in > in8 || framework_failure "${LZIP}" -1s12 -S100k in8 || test_failed $LINENO "${LZIP}" -t in800001.lz in800002.lz || test_failed $LINENO "${LZIP}" -cd in800001.lz in800002.lz | cmp in8 - || test_failed $LINENO -rm -f in800001.lz in800002.lz +rm -f in800001.lz in800002.lz || framework_failure "${LZIP}" -1s12 -S100k -o out.lz < in8 || test_failed $LINENO "${LZIP}" -t out.lz00001.lz out.lz00002.lz || test_failed $LINENO "${LZIP}" -cd out.lz00001.lz out.lz00002.lz | cmp in8 - || test_failed $LINENO -rm -f out.lz00001.lz out.lz00002.lz +rm -f out.lz00001.lz out.lz00002.lz || framework_failure "${LZIP}" -1ks4Ki -b100000 in8 || test_failed $LINENO "${LZIP}" -t in8.lz || test_failed $LINENO "${LZIP}" -cd in8.lz | cmp in8 - || test_failed $LINENO -rm -f in8 +rm -f in8 || framework_failure "${LZIP}" -0 -S100k -o out < in8.lz || test_failed $LINENO "${LZIP}" -t out00001.lz out00002.lz || test_failed $LINENO "${LZIP}" -cd out00001.lz out00002.lz | cmp in8.lz - || test_failed $LINENO -rm -f out00001.lz +rm -f out00001.lz || framework_failure "${LZIP}" -1 -S100k -o out < in8.lz || test_failed $LINENO "${LZIP}" -t out00001.lz out00002.lz || test_failed $LINENO "${LZIP}" -cd out00001.lz out00002.lz | cmp in8.lz - || test_failed $LINENO -rm -f out00001.lz out00002.lz +rm -f out00001.lz out00002.lz || framework_failure "${LZIP}" -0 -F -S100k in8.lz || test_failed $LINENO "${LZIP}" -t in8.lz00001.lz in8.lz00002.lz || test_failed $LINENO "${LZIP}" -cd in8.lz00001.lz in8.lz00002.lz | cmp in8.lz - || test_failed $LINENO -rm -f in8.lz00001.lz in8.lz00002.lz +rm -f in8.lz00001.lz in8.lz00002.lz || framework_failure "${LZIP}" -0kF -b100k in8.lz || test_failed $LINENO "${LZIP}" -t in8.lz.lz || test_failed $LINENO "${LZIP}" -cd in8.lz.lz | cmp in8.lz - || test_failed $LINENO -rm -f in8.lz in8.lz.lz +rm -f in8.lz in8.lz.lz || framework_failure "${BBEXAMPLE}" in || test_failed $LINENO "${BBEXAMPLE}" out || test_failed $LINENO @@ -240,28 +258,48 @@ printf "\ntesting bad input..." headers='LZIp LZiP LZip LzIP LzIp LziP lZIP lZIp lZiP lzIP' body='\001\014\000\203\377\373\377\377\300\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000$\000\000\000\000\000\000\000' -cat "${in_lz}" > in0.lz -printf "LZIP${body}" >> in0.lz -if "${LZIP}" -tq in0.lz ; then +cat "${in_lz}" > int.lz +printf "LZIP${body}" >> int.lz +if "${LZIP}" -tq int.lz ; then for header in ${headers} ; do - printf "${header}${body}" > in0.lz # first member - "${LZIP}" -tq in0.lz + printf "${header}${body}" > int.lz # first member + "${LZIP}" -tq int.lz + [ $? = 2 ] || test_failed $LINENO ${header} + "${LZIP}" -tq < int.lz + [ $? = 2 ] || test_failed $LINENO ${header} + "${LZIP}" -cdq int.lz > /dev/null + [ $? = 2 ] || test_failed $LINENO ${header} + "${LZIP}" -tq --loose-trailing int.lz + [ $? = 2 ] || test_failed $LINENO ${header} + "${LZIP}" -tq --loose-trailing < int.lz + [ $? = 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}" -tq int.lz + [ $? = 2 ] || test_failed $LINENO ${header} + "${LZIP}" -tq < int.lz + [ $? = 2 ] || test_failed $LINENO ${header} + "${LZIP}" -cdq int.lz > /dev/null [ $? = 2 ] || test_failed $LINENO ${header} - "${LZIP}" -tq --loose-trailing in0.lz + "${LZIP}" -t --loose-trailing int.lz || + test_failed $LINENO ${header} + "${LZIP}" -t --loose-trailing < int.lz || + test_failed $LINENO ${header} + "${LZIP}" -cd --loose-trailing int.lz > /dev/null || + test_failed $LINENO ${header} + "${LZIP}" -tq --loose-trailing --trailing-error int.lz [ $? = 2 ] || test_failed $LINENO ${header} - cat "${in_lz}" > in0.lz - printf "${header}${body}" >> in0.lz # trailing data - "${LZIP}" -tq in0.lz + "${LZIP}" -tq --loose-trailing --trailing-error < int.lz [ $? = 2 ] || test_failed $LINENO ${header} - "${LZIP}" -t --loose-trailing in0.lz - [ $? = 0 ] || test_failed $LINENO ${header} - "${LZIP}" -tq --loose-trailing --trailing-error in0.lz + "${LZIP}" -cdq --loose-trailing --trailing-error int.lz > /dev/null [ $? = 2 ] || test_failed $LINENO ${header} done else printf "\nwarning: skipping header test: 'printf' does not work on your system." fi -rm -f in0.lz +rm -f int.lz || framework_failure cat "${in_lz}" "${in_lz}" "${in_lz}" > in3.lz || framework_failure if dd if=in3.lz of=trunc.lz bs=14752 count=1 2> /dev/null && @@ -280,7 +318,7 @@ if dd if=in3.lz of=trunc.lz bs=14752 count=1 2> /dev/null && else printf "\nwarning: skipping truncation test: 'dd' does not work on your system." fi -rm -f in3.lz trunc.lz +rm -f in2.lz in3.lz trunc.lz out || framework_failure cat "${in_lz}" > ingin.lz || framework_failure printf "g" >> ingin.lz || framework_failure @@ -291,7 +329,7 @@ cmp in copy || test_failed $LINENO "${LZIP}" -t < ingin.lz || test_failed $LINENO "${LZIP}" -d < ingin.lz > copy || test_failed $LINENO cmp in copy || test_failed $LINENO -rm -f ingin.lz +rm -f copy ingin.lz || framework_failure echo if [ ${fail} = 0 ] ; then -- cgit v1.2.3