diff options
| -rw-r--r-- | AUTHORS | 3 | ||||
| -rw-r--r-- | ChangeLog | 30 | ||||
| -rw-r--r-- | INSTALL | 4 | ||||
| -rw-r--r-- | Makefile.in | 14 | ||||
| -rw-r--r-- | NEWS | 14 | ||||
| -rw-r--r-- | README | 12 | ||||
| -rw-r--r-- | compress.cc | 55 | ||||
| -rwxr-xr-x | configure | 6 | ||||
| -rw-r--r-- | decompress.cc | 90 | ||||
| -rw-r--r-- | doc/plzip.1 | 8 | ||||
| -rw-r--r-- | doc/plzip.info | 84 | ||||
| -rw-r--r-- | doc/plzip.texinfo | 106 | ||||
| -rw-r--r-- | main.cc | 149 | ||||
| -rw-r--r-- | plzip.h | 7 | ||||
| -rwxr-xr-x | testsuite/check.sh | 22 | ||||
| -rw-r--r-- | testsuite/test.txt (renamed from testsuite/test1) | 0 | ||||
| -rw-r--r-- | testsuite/test_v0.lz (renamed from testsuite/test1.lz) | bin | 11540 -> 11540 bytes | |||
| -rw-r--r-- | testsuite/test_v1.lz | bin | 0 -> 11548 bytes |
18 files changed, 317 insertions, 287 deletions
@@ -1,4 +1 @@ Plzip was written by Laszlo Ersek and Antonio Diaz Diaz. - -Plzip uses a simplified version of the LZMA algorithm. -The original LZMA algorithm was designed by Igor Pavlov. @@ -1,9 +1,21 @@ +2010-12-03 Antonio Diaz Diaz <ant_diaz@teleline.es> + + * Version 0.7 released. + * Match length limits set by options -1 to -9 have been changed + to match those of lzip 1.11. + * decompress.cc: A limit has been set on the number of packets + produced by workers to limit the amount of memory used. + * main.cc (open_instream): Do not show the message + " and `--stdout' was not specified" for directories, etc. + * main.cc: Fixed warning about fchown return value being ignored. + * testsuite: `test1' renamed to `test.txt'. Added new tests. + 2010-03-20 Antonio Diaz Diaz <ant_diaz@teleline.es> * Version 0.6 released. * Small portability fixes. - * Added chapter "Program Design" and description of option - "--threads" to manual. + * Added chapter `Program Design' and description of option + `--threads' to manual. * Debug stats have been fixed. 2010-02-10 Antonio Diaz Diaz <ant_diaz@teleline.es> @@ -21,19 +33,19 @@ 2010-01-24 Antonio Diaz Diaz <ant_diaz@teleline.es> * Version 0.3 released. - * Implemented option "--data-size". + * Implemented option `--data-size'. * Output file is now removed if plzip is interrupted. * This version automatically chooses the smallest possible dictionary size for each member during compression, saving memory during decompression. - * main.cc: New constant "o_binary". + * main.cc: New constant `o_binary'. 2010-01-17 Antonio Diaz Diaz <ant_diaz@teleline.es> * Version 0.2 released. - * Implemented option "--dictionary-size". - * Implemented option "--match-length". - * "lacos_rbtree" has been replaced with a circular buffer. + * Implemented option `--dictionary-size'. + * Implemented option `--match-length'. + * `lacos_rbtree' has been replaced with a circular buffer. 2009-12-05 Antonio Diaz Diaz <ant_diaz@teleline.es> @@ -54,5 +66,5 @@ Copyright (C) 2009, 2010 Antonio Diaz Diaz. This file is a collection of facts, and thus it is not copyrightable, -but just in case, I give you unlimited permission to copy, distribute -and modify it. +but just in case, you have unlimited permission to copy, distribute and +modify it. @@ -1,9 +1,9 @@ Requirements ------------ You will need a C++ compiler and the lzlib compression library installed. -I use gcc 4.3.4 and 3.3.6, but the code should compile with any +I use gcc 4.3.5 and 3.3.6, but the code should compile with any standards compliant compiler. -Lzlib must be version 0.8 or newer. +Lzlib must be version 1.0 or newer. Gcc is available at http://gcc.gnu.org. Lzlib is available at http://www.nongnu.org/lzip/lzlib.html. diff --git a/Makefile.in b/Makefile.in index ca6b899..02f9cd8 100644 --- a/Makefile.in +++ b/Makefile.in @@ -17,10 +17,10 @@ objs = arg_parser.o compress.o decompress.o main.o all : $(progname) $(progname) : $(objs) - $(CXX) $(LDFLAGS) -o $(progname) $(objs) $(LIBS) + $(CXX) $(LDFLAGS) -o $@ $^ $(LIBS) $(progname)_profiled : $(objs) - $(CXX) $(LDFLAGS) -pg -o $(progname)_profiled $(objs) $(LIBS) + $(CXX) $(LDFLAGS) -pg -o $@ $^ $(LIBS) main.o : main.cc $(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $< @@ -44,14 +44,14 @@ $(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texinfo man : $(VPATH)/doc/$(progname).1 $(VPATH)/doc/$(progname).1 : $(progname) - help2man -n 'data compressor based on the LZMA algorithm' \ - -o $(VPATH)/doc/$(progname).1 ./$(progname) + help2man -n 'reduces the size of files' \ + -o $@ ./$(progname) Makefile : $(VPATH)/configure $(VPATH)/Makefile.in ./config.status check : all - @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite + @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite $(pkgversion) install : all install-info install-man if [ ! -d "$(DESTDIR)$(bindir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(bindir)" ; fi @@ -94,8 +94,8 @@ dist : doc $(DISTNAME)/doc/$(pkgname).info \ $(DISTNAME)/doc/$(pkgname).texinfo \ $(DISTNAME)/testsuite/check.sh \ - $(DISTNAME)/testsuite/test1 \ - $(DISTNAME)/testsuite/test1.lz \ + $(DISTNAME)/testsuite/test.txt \ + $(DISTNAME)/testsuite/test_v[01].lz \ $(DISTNAME)/*.h \ $(DISTNAME)/*.cc rm -f $(DISTNAME) @@ -1,6 +1,12 @@ -Changes in version 0.6: +Changes in version 0.7: -Some small portability problems have been fixed. +Match length limits set by options -1 to -9 have been changed to match +those of lzip 1.11. -The chapter "Program Design" and a description of option "--threads" -have been added to the manual. +A limit has been set on the number of packets produced by decompresor +worker threads to limit the amount of memory used. + +Do not show the message "and `--stdout' was not specified" for file +types that can't be read (directories, etc). + +A warning about fchown's return value being ignored has been fixed. @@ -1,10 +1,10 @@ Description Plzip is a massively parallel (multi-threaded), lossless data compressor -based on the LZMA algorithm, with very safe integrity checking and a -user interface similar to the one of gzip or bzip2. Plzip uses the lzip -file format; the files produced by plzip are fully compatible with -lzip-1.4 or newer. +based on the lzlib compression library, with very safe integrity +checking and a user interface similar to the one of bzip2, gzip or lzip. +Plzip uses the lzip file format; the files produced by plzip are fully +compatible with lzip-1.4 or newer. Plzip is intended for faster compression/decompression of big files on multiprocessor machines, which makes it specially well suited for @@ -18,5 +18,5 @@ This file is free documentation: you have unlimited permission to copy, distribute and modify it. The file Makefile.in is a data file used by configure to produce the -Makefile. It has the same copyright owner and permissions that this -file. +Makefile. It has the same copyright owner and permissions that configure +itself. diff --git a/compress.cc b/compress.cc index f055b03..7945cf0 100644 --- a/compress.cc +++ b/compress.cc @@ -48,11 +48,14 @@ void xinit( pthread_cond_t * cond, pthread_mutex_t * mutex ) { - int errcode = pthread_mutex_init( mutex, 0 ); - if( errcode ) { show_error( "pthread_mutex_init", errcode ); fatal(); } - - errcode = pthread_cond_init( cond, 0 ); + int errcode = pthread_cond_init( cond, 0 ); if( errcode ) { show_error( "pthread_cond_init", errcode ); fatal(); } + + if( mutex ) + { + errcode = pthread_mutex_init( mutex, 0 ); + if( errcode ) { show_error( "pthread_mutex_init", errcode ); fatal(); } + } } @@ -61,8 +64,11 @@ void xdestroy( pthread_cond_t * cond, pthread_mutex_t * mutex ) int errcode = pthread_cond_destroy( cond ); if( errcode ) { show_error( "pthread_cond_destroy", errcode ); fatal(); } - errcode = pthread_mutex_destroy( mutex ); - if( errcode ) { show_error( "pthread_mutex_destroy", errcode ); fatal(); } + if( mutex ) + { + errcode = pthread_mutex_destroy( mutex ); + if( errcode ) { show_error( "pthread_mutex_destroy", errcode ); fatal(); } + } } @@ -125,16 +131,16 @@ public: private: unsigned long long receive_id; // id assigned to next packet received unsigned long long deliver_id; // id of next packet to be delivered - Slot_tally slot_tally; + Slot_tally slot_tally; // limits the number of input packets std::queue< Packet * > packet_queue; std::vector< Packet * > circular_buffer; - int num_working; // Number of workers still running + int num_working; // number of workers still running const int num_slots; // max packets in circulation pthread_mutex_t imutex; pthread_cond_t iav_or_eof; // input packet available or splitter done pthread_mutex_t omutex; pthread_cond_t oav_or_exit; // output packet available or all workers exited - bool eof; // splitter done + bool eof; // splitter done public: Packet_courier( const int num_workers, const int slots ) @@ -148,6 +154,8 @@ public: ~Packet_courier() { xdestroy( &iav_or_eof, &imutex ); xdestroy( &oav_or_exit, &omutex ); } + const Slot_tally & tally() const { return slot_tally; } + // make a packet with data received from splitter void receive_packet( uint8_t * const data, const int size ) { @@ -182,10 +190,9 @@ public: xunlock( &imutex ); if( ipacket == 0 ) { - // Notify muxer when last worker exits + // notify muxer when last worker exits xlock( &omutex ); - if( --num_working == 0 ) - xsignal( &oav_or_exit ); + if( --num_working == 0 ) xsignal( &oav_or_exit ); xunlock( &omutex ); } return ipacket; @@ -198,7 +205,7 @@ public: // id collision shouldn't happen if( circular_buffer[opacket->id%num_slots] != 0 ) internal_error( "id collision in collect_packet" ); - // Merge packet into circular buffer + // merge packet into circular buffer circular_buffer[opacket->id%num_slots] = opacket; if( opacket->id == deliver_id ) xsignal( &oav_or_exit ); xunlock( &omutex ); @@ -240,8 +247,6 @@ public: if( circular_buffer[i] != 0 ) return false; return true; } - - const Slot_tally & tally() const { return slot_tally; } }; @@ -267,10 +272,10 @@ extern "C" void * csplitter( void * arg ) for( bool first_post = true; ; first_post = false ) { uint8_t * data = new( std::nothrow ) uint8_t[data_size]; - if( data == 0 ) { pp( "not enough memory" ); fatal(); } + if( data == 0 ) { pp( "Not enough memory" ); fatal(); } const int size = readblock( infd, data, data_size ); if( size != data_size && errno ) - { pp(); show_error( "read error", errno ); fatal(); } + { pp(); show_error( "Read error", errno ); fatal(); } if( size > 0 || first_post ) // first packet can be empty { @@ -314,7 +319,7 @@ extern "C" void * cworker( void * arg ) const int compr_size = 42 + packet->size + ( ( packet->size + 7 ) / 8 ); uint8_t * const new_data = new( std::nothrow ) uint8_t[compr_size]; - if( new_data == 0 ) { pp( "not enough memory" ); fatal(); } + if( new_data == 0 ) { pp( "Not enough memory" ); fatal(); } const int dict_size = std::max( LZ_min_dictionary_size(), std::min( dictionary_size, packet->size ) ); LZ_Encoder * const encoder = @@ -322,7 +327,7 @@ extern "C" void * cworker( void * arg ) if( !encoder || LZ_compress_errno( encoder ) != LZ_ok ) { if( !encoder || LZ_compress_errno( encoder ) == LZ_mem_error ) - pp( "not enough memory. Try a smaller dictionary size" ); + pp( "Not enough memory. Try a smaller dictionary size" ); else internal_error( "invalid argument to encoder" ); fatal(); @@ -386,7 +391,7 @@ void muxer( Packet_courier & courier, const Pretty_print & pp, const int outfd ) { const int wr = writeblock( outfd, opacket->data, opacket->size ); if( wr != opacket->size ) - { pp(); show_error( "write error", errno ); fatal(); } + { pp(); show_error( "Write error", errno ); fatal(); } } delete[] opacket->data; delete opacket; @@ -416,7 +421,7 @@ int compress( const int data_size, const int dictionary_size, pthread_t splitter_thread; int errcode = pthread_create( &splitter_thread, 0, csplitter, &splitter_arg ); if( errcode ) - { show_error( "can't create splitter thread", errcode ); fatal(); } + { show_error( "Can't create splitter thread", errcode ); fatal(); } Worker_arg worker_arg; worker_arg.courier = &courier; @@ -426,12 +431,12 @@ int compress( const int data_size, const int dictionary_size, pthread_t * worker_threads = new( std::nothrow ) pthread_t[num_workers]; if( worker_threads == 0 ) - { pp( "not enough memory" ); fatal(); } + { pp( "Not enough memory" ); fatal(); } for( int i = 0; i < num_workers; ++i ) { errcode = pthread_create( &worker_threads[i], 0, cworker, &worker_arg ); if( errcode ) - { show_error( "can't create worker threads", errcode ); fatal(); } + { show_error( "Can't create worker threads", errcode ); fatal(); } } muxer( courier, pp, outfd ); @@ -440,13 +445,13 @@ int compress( const int data_size, const int dictionary_size, { errcode = pthread_join( worker_threads[i], 0 ); if( errcode ) - { show_error( "can't join worker threads", errcode ); fatal(); } + { show_error( "Can't join worker threads", errcode ); fatal(); } } delete[] worker_threads; worker_threads = 0; errcode = pthread_join( splitter_thread, 0 ); if( errcode ) - { show_error( "can't join splitter thread", errcode ); fatal(); } + { show_error( "Can't join splitter thread", errcode ); fatal(); } if( verbosity >= 1 ) { @@ -5,12 +5,12 @@ # This configure script is free software: you have unlimited permission # to copy, distribute and modify it. # -# Date of this version: 2010-03-20 +# Date of this version: 2010-12-03 args= no_create= pkgname=plzip -pkgversion=0.6 +pkgversion=0.7 progname=plzip srctrigger=plzip.h @@ -80,7 +80,7 @@ while [ -n "$1" ] ; do bindir=`echo ${optarg} | sed -e 's,/$,,'` ;; --datadir* | --da*) datadir=`echo ${optarg} | sed -e 's,/$,,'` ;; - --infodir* | --in*) + --infodir* | --inf*) infodir=`echo ${optarg} | sed -e 's,/$,,'` ;; --mandir* | --ma*) mandir=`echo ${optarg} | sed -e 's,/$,,'` ;; diff --git a/decompress.cc b/decompress.cc index a5d4994..df8d88e 100644 --- a/decompress.cc +++ b/decompress.cc @@ -38,6 +38,7 @@ namespace { +enum { max_packet_size = 1 << 20 }; long long in_size = 0; long long out_size = 0; @@ -59,17 +60,18 @@ public: private: int receive_worker_id; // worker queue currently receiving packets int deliver_worker_id; // worker queue currently delivering packets - Slot_tally slot_tally; + Slot_tally slot_tally; // limits the number of input packets std::vector< std::queue< Packet * > > ipacket_queues; std::vector< std::queue< Packet * > > opacket_queues; - int num_working; // Number of workers still running - const int num_workers; // Number of workers - const int num_slots; // max packets in circulation + int num_working; // number of workers still running + const int num_workers; // number of workers + int num_free; // remaining free output slots pthread_mutex_t imutex; pthread_cond_t iav_or_eof; // input packet available or splitter done pthread_mutex_t omutex; pthread_cond_t oav_or_exit; // output packet available or all workers exited - bool eof; // splitter done + pthread_cond_t slot_av; // free output slot available + bool eof; // splitter done public: Packet_courier( const int workers, const int slots ) @@ -78,11 +80,19 @@ public: receive_worker_id( 0 ), deliver_worker_id( 0 ), slot_tally( slots ), ipacket_queues( workers ), opacket_queues( workers ), num_working( workers ), - num_workers( workers ), num_slots( slots ), eof( false ) - { xinit( &iav_or_eof, &imutex ); xinit( &oav_or_exit, &omutex ); } + num_workers( workers ), num_free( 8 * slots ), eof( false ) + { + xinit( &iav_or_eof, &imutex ); + xinit( &oav_or_exit, &omutex ); xinit( &slot_av, 0 ); + } ~Packet_courier() - { xdestroy( &iav_or_eof, &imutex ); xdestroy( &oav_or_exit, &omutex ); } + { + xdestroy( &iav_or_eof, &imutex ); + xdestroy( &oav_or_exit, &omutex ); xdestroy( &slot_av, 0 ); + } + + const Slot_tally & tally() const { return slot_tally; } // make a packet with data received from splitter // if data == 0, move to next queue @@ -123,10 +133,9 @@ public: { if( ipacket->data != 0 ) slot_tally.leave_slot(); } else { - // Notify muxer when last worker exits + // notify muxer when last worker exits xlock( &omutex ); - if( --num_working == 0 ) - xsignal( &oav_or_exit ); + if( --num_working == 0 ) xsignal( &oav_or_exit ); xunlock( &omutex ); } return ipacket; @@ -136,6 +145,12 @@ public: void collect_packet( Packet * const opacket, const int worker_id ) { xlock( &omutex ); + if( opacket->data != 0 ) + { + while( worker_id != deliver_worker_id && num_free <= 0 ) + xwait( &slot_av, &omutex ); + --num_free; + } opacket_queues[worker_id].push( opacket ); if( worker_id == deliver_worker_id ) xsignal( &oav_or_exit ); xunlock( &omutex ); @@ -159,12 +174,14 @@ public: if( opacket_queues[deliver_worker_id].empty() ) break; opacket = opacket_queues[deliver_worker_id].front(); opacket_queues[deliver_worker_id].pop(); - if( opacket->data != 0 ) break; - else + if( opacket->data != 0 ) { - if( ++deliver_worker_id >= num_workers ) deliver_worker_id = 0; - delete opacket; opacket = 0; + if( ++num_free == 1 ) xsignal( &slot_av ); + break; } + if( ++deliver_worker_id >= num_workers ) deliver_worker_id = 0; + xbroadcast( &slot_av ); // restart deliver_worker_id thread + delete opacket; opacket = 0; } xunlock( &omutex ); return opacket; @@ -187,8 +204,6 @@ public: if( !opacket_queues[i].empty() ) return false; return true; } - - const Slot_tally & tally() const { return slot_tally; } }; @@ -197,7 +212,6 @@ struct Splitter_arg Packet_courier * courier; const Pretty_print * pp; int infd; - int packet_size; }; @@ -211,19 +225,19 @@ extern "C" void * dsplitter( void * arg ) const int infd = tmp.infd; const int hsize = 6; // header size const int tsize = 20; // trailer size - const int buffer_size = tmp.packet_size; + const int buffer_size = max_packet_size; const int base_buffer_size = tsize + buffer_size + hsize; uint8_t * const base_buffer = new( std::nothrow ) uint8_t[base_buffer_size]; - if( base_buffer == 0 ) { pp( "not enough memory" ); fatal(); } + if( base_buffer == 0 ) { pp( "Not enough memory" ); fatal(); } uint8_t * const buffer = base_buffer + tsize; int size = readblock( infd, buffer, buffer_size + hsize ) - hsize; bool at_stream_end = ( size < buffer_size ); if( size != buffer_size && errno ) - { pp(); show_error( "read error", errno ); fatal(); } + { pp(); show_error( "Read error", errno ); fatal(); } if( size <= tsize || buffer[0] != 'L' || buffer[1] != 'Z' || buffer[2] != 'I' || buffer[3] != 'P' ) - { pp( "bad magic number (file not in lzip format)" ); fatal(); } + { pp( "Bad magic number (file not in lzip format)" ); fatal(); } long long partial_member_size = 0; while( true ) @@ -239,7 +253,7 @@ extern "C" void * dsplitter( void * arg ) if( partial_member_size + newpos - pos == member_size ) { // header found uint8_t * data = new( std::nothrow ) uint8_t[newpos - pos]; - if( data == 0 ) { pp( "not enough memory" ); fatal(); } + if( data == 0 ) { pp( "Not enough memory" ); fatal(); } std::memcpy( data, buffer + pos, newpos - pos ); courier.receive_packet( data, newpos - pos ); courier.receive_packet( 0, 0 ); // end of member token @@ -251,7 +265,7 @@ extern "C" void * dsplitter( void * arg ) if( at_stream_end ) { uint8_t * data = new( std::nothrow ) uint8_t[size + hsize - pos]; - if( data == 0 ) { pp( "not enough memory" ); fatal(); } + if( data == 0 ) { pp( "Not enough memory" ); fatal(); } std::memcpy( data, buffer + pos, size + hsize - pos ); courier.receive_packet( data, size + hsize - pos ); courier.receive_packet( 0, 0 ); // end of member token @@ -261,7 +275,7 @@ extern "C" void * dsplitter( void * arg ) { partial_member_size += buffer_size - pos; uint8_t * data = new( std::nothrow ) uint8_t[buffer_size - pos]; - if( data == 0 ) { pp( "not enough memory" ); fatal(); } + if( data == 0 ) { pp( "Not enough memory" ); fatal(); } std::memcpy( data, buffer + pos, buffer_size - pos ); courier.receive_packet( data, buffer_size - pos ); } @@ -269,7 +283,7 @@ extern "C" void * dsplitter( void * arg ) size = readblock( infd, buffer + hsize, buffer_size ); at_stream_end = ( size < buffer_size ); if( size != buffer_size && errno ) - { pp(); show_error( "read error", errno ); fatal(); } + { pp(); show_error( "Read error", errno ); fatal(); } } delete[] base_buffer; courier.finish(); // no more packets to send @@ -282,7 +296,6 @@ struct Worker_arg Packet_courier * courier; const Pretty_print * pp; int worker_id; - int packet_size; }; @@ -294,12 +307,12 @@ extern "C" void * dworker( void * arg ) Packet_courier & courier = *tmp.courier; const Pretty_print & pp = *tmp.pp; const int worker_id = tmp.worker_id; - const int new_data_size = tmp.packet_size; + const int new_data_size = max_packet_size; uint8_t * new_data = new( std::nothrow ) uint8_t[new_data_size]; LZ_Decoder * const decoder = LZ_decompress_open(); if( !new_data || !decoder || LZ_decompress_errno( decoder ) != LZ_ok ) - { pp( "not enough memory" ); fatal(); } + { pp( "Not enough memory" ); fatal(); } int new_pos = 0; while( true ) @@ -345,7 +358,7 @@ extern "C" void * dworker( void * arg ) courier.collect_packet( opacket, worker_id ); new_pos = 0; new_data = new( std::nothrow ) uint8_t[new_data_size]; - if( new_data == 0 ) { pp( "not enough memory" ); fatal(); } + if( new_data == 0 ) { pp( "Not enough memory" ); fatal(); } } if( LZ_decompress_finished( decoder ) == 1 ) { @@ -367,7 +380,7 @@ extern "C" void * dworker( void * arg ) delete[] new_data; if( LZ_decompress_total_in_size( decoder ) != 0 ) - { pp( "error, remaining data in decoder" ); fatal(); } + { pp( "Error, some data remains in decoder" ); fatal(); } LZ_decompress_close( decoder ); return 0; } @@ -388,7 +401,7 @@ void muxer( Packet_courier & courier, const Pretty_print & pp, const int outfd ) { const int wr = writeblock( outfd, opacket->data, opacket->size ); if( wr != opacket->size ) - { pp(); show_error( "write error", errno ); fatal(); } + { pp(); show_error( "Write error", errno ); fatal(); } } delete[] opacket->data; delete opacket; @@ -406,33 +419,30 @@ int decompress( const int num_workers, const int num_slots, { in_size = 0; out_size = 0; - const int packet_size = 1 << 20; Packet_courier courier( num_workers, num_slots ); Splitter_arg splitter_arg; splitter_arg.courier = &courier; splitter_arg.pp = &pp; splitter_arg.infd = infd; - splitter_arg.packet_size = packet_size; pthread_t splitter_thread; int errcode = pthread_create( &splitter_thread, 0, dsplitter, &splitter_arg ); if( errcode ) - { show_error( "can't create splitter thread", errcode ); fatal(); } + { show_error( "Can't create splitter thread", errcode ); fatal(); } Worker_arg * worker_args = new( std::nothrow ) Worker_arg[num_workers]; pthread_t * worker_threads = new( std::nothrow ) pthread_t[num_workers]; if( worker_args == 0 || worker_threads == 0 ) - { pp( "not enough memory" ); fatal(); } + { pp( "Not enough memory" ); fatal(); } for( int i = 0; i < num_workers; ++i ) { worker_args[i].courier = &courier; worker_args[i].pp = &pp; worker_args[i].worker_id = i; - worker_args[i].packet_size = packet_size; errcode = pthread_create( &worker_threads[i], 0, dworker, &worker_args[i] ); if( errcode ) - { show_error( "can't create worker threads", errcode ); fatal(); } + { show_error( "Can't create worker threads", errcode ); fatal(); } } muxer( courier, pp, outfd ); @@ -441,14 +451,14 @@ int decompress( const int num_workers, const int num_slots, { errcode = pthread_join( worker_threads[i], 0 ); if( errcode ) - { show_error( "can't join worker threads", errcode ); fatal(); } + { show_error( "Can't join worker threads", errcode ); fatal(); } } delete[] worker_threads; worker_threads = 0; delete[] worker_args; worker_args = 0; errcode = pthread_join( splitter_thread, 0 ); if( errcode ) - { show_error( "can't join splitter thread", errcode ); fatal(); } + { show_error( "Can't join splitter thread", errcode ); fatal(); } if( verbosity >= 2 ) std::fprintf( stderr, "decompressed size %9lld, size %9lld. ", diff --git a/doc/plzip.1 b/doc/plzip.1 index bad484c..5fe6e3b 100644 --- a/doc/plzip.1 +++ b/doc/plzip.1 @@ -1,7 +1,7 @@ .\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1. -.TH PLZIP "1" "March 2010" "Plzip 0.6" "User Commands" +.TH PLZIP "1" "December 2010" "Plzip 0.7" "User Commands" .SH NAME -Plzip \- data compressor based on the LZMA algorithm +Plzip \- reduces the size of files .SH SYNOPSIS .B plzip [\fIoptions\fR] [\fIfiles\fR] @@ -31,7 +31,7 @@ overwrite existing output files keep (don't delete) input files .TP \fB\-m\fR, \fB\-\-match\-length=\fR<n> -set match length limit in bytes [80] +set match length limit in bytes [36] .TP \fB\-n\fR, \fB\-\-threads=\fR<n> set the number of (de)compression threads @@ -72,7 +72,7 @@ Plzip home page: http://www.nongnu.org/lzip/plzip.html Copyright \(co 2009 Laszlo Ersek. .br Copyright \(co 2010 Antonio Diaz Diaz. -Using Lzlib 1.0\-rc1 +Using Lzlib 1.1\-rc1 License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html> .br This is free software: you are free to change and redistribute it. diff --git a/doc/plzip.info b/doc/plzip.info index 037a286..22f0052 100644 --- a/doc/plzip.info +++ b/doc/plzip.info @@ -12,16 +12,16 @@ File: plzip.info, Node: Top, Next: Introduction, Up: (dir) Plzip Manual ************ -This manual is for Plzip (version 0.6, 20 March 2010). +This manual is for Plzip (version 0.7, 3 December 2010). * Menu: -* Introduction:: Purpose and features of plzip -* Invoking Plzip:: Command line interface -* Program Design:: Internal structure of plzip -* File Format:: Detailed format of the compressed file -* Problems:: Reporting bugs -* Concept Index:: Index of concepts +* Introduction:: Purpose and features of plzip +* Invoking Plzip:: Command line interface +* Program Design:: Internal structure of plzip +* File Format:: Detailed format of the compressed file +* Problems:: Reporting bugs +* Concept Index:: Index of concepts Copyright (C) 2009, 2010 Antonio Diaz Diaz. @@ -36,10 +36,10 @@ File: plzip.info, Node: Introduction, Next: Invoking Plzip, Prev: Top, Up: T ************** Plzip is a massively parallel (multi-threaded), lossless data compressor -based on the LZMA algorithm, with very safe integrity checking and a -user interface similar to the one of gzip or bzip2. Plzip uses the lzip -file format; the files produced by plzip are fully compatible with -lzip-1.4 or newer. +based on the lzlib compression library, with very safe integrity +checking and a user interface similar to the one of bzip2, gzip or lzip. +Plzip uses the lzip file format; the files produced by plzip are fully +compatible with lzip-1.4 or newer. Plzip is intended for faster compression/decompression of big files on multiprocessor machines, which makes it specially well suited for @@ -98,80 +98,80 @@ The format for running plzip is: Plzip supports the following options: -`--help' `-h' +`--help' Print an informative help message describing the options and exit. -`--version' `-V' +`--version' Print the version number of plzip on the standard output and exit. -`--data-size=SIZE' `-B' +`--data-size=SIZE' Set the input data block size in bytes. The input file will be divided in chunks of this size before compression is performed. Valid values range from 8KiB to 1GiB. Default value is two times the dictionary size. Plzip will reduce the dictionary size if it is larger than the chosen data size. -`--stdout' `-c' +`--stdout' Compress or decompress to standard output. Needed when reading from a named pipe (fifo) or from a device. -`--decompress' `-d' +`--decompress' Decompress. -`--force' `-f' +`--force' Force overwrite of output file. -`--keep' `-k' +`--keep' Keep (don't delete) input files during compression or decompression. -`--match-length=LENGTH' `-m LENGTH' +`--match-length=LENGTH' Set the match length limit in bytes. Valid values range from 5 to 273. Larger values usually give better compression ratios but longer compression times. -`--threads=THREADS' `-n THREADS' +`--threads=THREADS' Set the number of worker threads. Valid values range from 1 to "as many as your system can support". If this option is not used, plzip tries to detect the number of processors in the system and use it as default value. -`--output=FILE' `-o FILE' +`--output=FILE' When reading from standard input and `--stdout' has not been specified, use `FILE' as the virtual name of the uncompressed file. This produces a file named `FILE' when decompressing, and a file named `FILE.lz' when compressing. -`--quiet' `-q' +`--quiet' Quiet operation. Suppress all messages. -`--dictionary-size=SIZE' `-s SIZE' +`--dictionary-size=SIZE' Set the dictionary size limit in bytes. Valid values range from 4KiB to 512MiB. Note that dictionary sizes are quantized. If the specified size does not match one of the valid sizes, it will be rounded upwards. -`--test' `-t' +`--test' Check integrity of the specified file(s), but don't decompress them. This really performs a trial decompression and throws away the result. Use `-tvv' or `-tvvv' to see information about the file. -`--verbose' `-v' +`--verbose' Verbose mode. Show the compression ratio for each file processed. Further -v's increase the verbosity level. @@ -180,15 +180,21 @@ The format for running plzip is: limit) as shown in the table below. Note that `-9' can be much slower than `-1'. These options have no effect when decompressing. + The bidimensional parameter space of LZMA can't be mapped to a + linear scale optimal for all files. If your files are large, very + repetitive, etc, you may need to use the `--match-length' and + `--dictionary-size' options directly to achieve optimal + performance. + Level Dictionary size Match length limit - -1 1 MiB 10 bytes - -2 1.5 MiB 12 bytes - -3 2 MiB 17 bytes - -4 3 MiB 26 bytes - -5 4 MiB 44 bytes - -6 8 MiB 80 bytes - -7 16 MiB 108 bytes - -8 24 MiB 163 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' @@ -328,11 +334,11 @@ Concept Index Tag Table: Node: Top223 -Node: Introduction791 -Node: Invoking Plzip3533 -Node: Program Design7499 -Node: File Format8161 -Node: Problems10117 -Node: Concept Index10646 +Node: Introduction833 +Node: Invoking Plzip3592 +Node: Program Design7840 +Node: File Format8502 +Node: Problems10458 +Node: Concept Index10987 End Tag Table diff --git a/doc/plzip.texinfo b/doc/plzip.texinfo index 8867c7f..517dc11 100644 --- a/doc/plzip.texinfo +++ b/doc/plzip.texinfo @@ -5,8 +5,8 @@ @finalout @c %**end of header -@set UPDATED 20 March 2010 -@set VERSION 0.6 +@set UPDATED 3 December 2010 +@set VERSION 0.7 @dircategory Data Compression @direntry @@ -14,9 +14,10 @@ @end direntry +@ifnothtml @titlepage @title Plzip -@subtitle A data compressor based on the LZMA algorithm +@subtitle Parallel compressor compatible with lzip @subtitle for Plzip version @value{VERSION}, @value{UPDATED} @author by Antonio Diaz Diaz @@ -25,6 +26,7 @@ @end titlepage @contents +@end ifnothtml @node Top @top @@ -32,12 +34,12 @@ This manual is for Plzip (version @value{VERSION}, @value{UPDATED}). @menu -* Introduction:: Purpose and features of plzip -* Invoking Plzip:: Command line interface -* Program Design:: Internal structure of plzip -* File Format:: Detailed format of the compressed file -* Problems:: Reporting bugs -* Concept Index:: Index of concepts +* Introduction:: Purpose and features of plzip +* Invoking Plzip:: Command line interface +* Program Design:: Internal structure of plzip +* File Format:: Detailed format of the compressed file +* Problems:: Reporting bugs +* Concept Index:: Index of concepts @end menu @sp 1 @@ -52,10 +54,10 @@ to copy, distribute and modify it. @cindex introduction Plzip is a massively parallel (multi-threaded), lossless data compressor -based on the LZMA algorithm, with very safe integrity checking and a -user interface similar to the one of gzip or bzip2. Plzip uses the lzip -file format; the files produced by plzip are fully compatible with -lzip-1.4 or newer. +based on the lzlib compression library, with very safe integrity +checking and a user interface similar to the one of bzip2, gzip or lzip. +Plzip uses the lzip file format; the files produced by plzip are fully +compatible with lzip-1.4 or newer. Plzip is intended for faster compression/decompression of big files on multiprocessor machines, which makes it specially well suited for @@ -121,77 +123,77 @@ plzip [@var{options}] [@var{files}] Plzip supports the following options: @table @samp -@item --help -@itemx -h +@item -h +@itemx --help Print an informative help message describing the options and exit. -@item --version -@itemx -V +@item -V +@itemx --version Print the version number of plzip on the standard output and exit. -@item --data-size=@var{size} -@itemx -B +@item -B +@itemx --data-size=@var{size} Set the input data block size in bytes. The input file will be divided in chunks of this size before compression is performed. Valid values range from 8KiB to 1GiB. Default value is two times the dictionary size. Plzip will reduce the dictionary size if it is larger than the chosen data size. -@item --stdout -@itemx -c +@item -c +@itemx --stdout Compress or decompress to standard output. Needed when reading from a named pipe (fifo) or from a device. -@item --decompress -@itemx -d +@item -d +@itemx --decompress Decompress. -@item --force -@itemx -f +@item -f +@itemx --force Force overwrite of output file. -@item --keep -@itemx -k +@item -k +@itemx --keep Keep (don't delete) input files during compression or decompression. -@item --match-length=@var{length} -@itemx -m @var{length} +@item -m @var{length} +@itemx --match-length=@var{length} Set the match length limit in bytes. Valid values range from 5 to 273. Larger values usually give better compression ratios but longer compression times. -@item --threads=@var{threads} -@itemx -n @var{threads} +@item -n @var{threads} +@itemx --threads=@var{threads} Set the number of worker threads. Valid values range from 1 to "as many as your system can support". If this option is not used, plzip tries to detect the number of processors in the system and use it as default value. -@item --output=@var{file} -@itemx -o @var{file} +@item -o @var{file} +@itemx --output=@var{file} When reading from standard input and @samp{--stdout} has not been specified, use @samp{@var{file}} as the virtual name of the uncompressed file. This produces a file named @samp{@var{file}} when decompressing, and a file named @samp{@var{file}.lz} when compressing. -@item --quiet -@itemx -q +@item -q +@itemx --quiet Quiet operation. Suppress all messages. -@item --dictionary-size=@var{size} -@itemx -s @var{size} +@item -s @var{size} +@itemx --dictionary-size=@var{size} Set the dictionary size limit in bytes. Valid values range from 4KiB to 512MiB. Note that dictionary sizes are quantized. If the specified size does not match one of the valid sizes, it will be rounded upwards. -@item --test -@itemx -t +@item -t +@itemx --test Check integrity of the specified file(s), but don't decompress them. This really performs a trial decompression and throws away the result. Use @samp{-tvv} or @samp{-tvvv} to see information about the file. -@item --verbose -@itemx -v +@item -v +@itemx --verbose Verbose mode. Show the compression ratio for each file processed. Further -v's increase the verbosity level. @@ -200,16 +202,22 @@ Set the compression parameters (dictionary size and match length limit) as shown in the table below. Note that @samp{-9} can be much slower than @samp{-1}. These options have no effect when decompressing. +The bidimensional parameter space of LZMA can't be mapped to a linear +scale optimal for all files. If your files are large, very repetitive, +etc, you may need to use the @samp{--match-length} and +@samp{--dictionary-size} options directly to achieve optimal +performance. + @multitable {Level} {Dictionary size} {Match length limit} @item Level @tab Dictionary size @tab Match length limit -@item -1 @tab 1 MiB @tab 10 bytes -@item -2 @tab 1.5 MiB @tab 12 bytes -@item -3 @tab 2 MiB @tab 17 bytes -@item -4 @tab 3 MiB @tab 26 bytes -@item -5 @tab 4 MiB @tab 44 bytes -@item -6 @tab 8 MiB @tab 80 bytes -@item -7 @tab 16 MiB @tab 108 bytes -@item -8 @tab 24 MiB @tab 163 bytes +@item -1 @tab 1 MiB @tab 5 bytes +@item -2 @tab 1.5 MiB @tab 6 bytes +@item -3 @tab 2 MiB @tab 8 bytes +@item -4 @tab 3 MiB @tab 12 bytes +@item -5 @tab 4 MiB @tab 20 bytes +@item -6 @tab 8 MiB @tab 36 bytes +@item -7 @tab 16 MiB @tab 68 bytes +@item -8 @tab 24 MiB @tab 132 bytes @item -9 @tab 32 MiB @tab 273 bytes @end multitable @@ -61,10 +61,10 @@ namespace { +const char * const Program_name = "Plzip"; +const char * const program_name = "plzip"; +const char * const program_year = "2010"; const char * invocation_name = 0; -const char * const Program_name = "Plzip"; -const char * const program_name = "plzip"; -const char * const program_year = "2010"; #ifdef O_BINARY const int o_binary = O_BINARY; @@ -83,7 +83,7 @@ struct Lzma_options int match_len_limit; // 5..273 }; -enum Mode { m_compress = 0, m_decompress, m_test }; +enum Mode { m_compress, m_decompress, m_test }; std::string output_filename; int outfd = -1; @@ -105,7 +105,7 @@ void show_help() throw() std::printf( " -d, --decompress decompress\n" ); std::printf( " -f, --force overwrite existing output files\n" ); std::printf( " -k, --keep keep (don't delete) input files\n" ); - std::printf( " -m, --match-length=<n> set match length limit in bytes [80]\n" ); + std::printf( " -m, --match-length=<n> set match length limit in bytes [36]\n" ); std::printf( " -n, --threads=<n> set the number of (de)compression threads\n" ); std::printf( " -o, --output=<file> if reading stdin, place the output into <file>\n" ); std::printf( " -q, --quiet suppress all messages\n" ); @@ -140,30 +140,6 @@ void show_version() throw() } -const char * format_num( long long num, long long limit = 9999, - const int set_prefix = 0 ) throw() - { - const char * const si_prefix[8] = - { "k", "M", "G", "T", "P", "E", "Z", "Y" }; - const char * const binary_prefix[8] = - { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" }; - static bool si = false; - static char buf[16]; - - if( set_prefix ) si = ( set_prefix > 0 ); - const int factor = ( si ) ? 1000 : 1024; - const char * const *prefix = ( si ) ? si_prefix : binary_prefix; - const char *p = ""; - limit = std::max( 999LL, std::min( 999999LL, limit ) ); - - for( int i = 0; i < 8 && ( llabs( num ) > limit || - ( llabs( num ) >= factor && num % factor == 0 ) ); ++i ) - { num /= factor; p = prefix[i]; } - snprintf( buf, sizeof buf, "%lld %s", num, p ); - return buf; - } - - long long getnum( const char * const ptr, const int bs = 0, const long long llimit = LLONG_MIN + 1, const long long ulimit = LLONG_MAX ) throw() @@ -173,7 +149,7 @@ long long getnum( const char * const ptr, const int bs = 0, long long result = strtoll( ptr, &tail, 0 ); if( tail == ptr ) { - show_error( "bad or missing numerical argument", 0, true ); + show_error( "Bad or missing numerical argument.", 0, true ); std::exit( 1 ); } @@ -203,7 +179,7 @@ long long getnum( const char * const ptr, const int bs = 0, } if( bad_multiplier ) { - show_error( "bad multiplier in numerical argument", 0, true ); + show_error( "Bad multiplier in numerical argument.", 0, true ); std::exit( 1 ); } for( int i = 0; i < exponent; ++i ) @@ -215,7 +191,7 @@ long long getnum( const char * const ptr, const int bs = 0, if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE; if( errno ) { - show_error( "numerical argument out of limits" ); + show_error( "Numerical argument out of limits." ); std::exit( 1 ); } return result; @@ -254,7 +230,7 @@ int open_instream( const std::string & name, struct stat * const in_statsp, if( program_mode == m_compress && !force && eindex >= 0 ) { if( verbosity >= 0 ) - std::fprintf( stderr, "%s: input file `%s' already has `%s' suffix.\n", + std::fprintf( stderr, "%s: Input file `%s' already has `%s' suffix.\n", program_name, name.c_str(), known_extensions[eindex].from ); } @@ -271,14 +247,16 @@ int open_instream( const std::string & name, struct stat * const in_statsp, { const int i = fstat( infd, in_statsp ); const mode_t & mode = in_statsp->st_mode; - if( i < 0 || !( S_ISREG( mode ) || ( to_stdout && - ( S_ISFIFO( mode ) || S_ISSOCK( mode ) || - S_ISBLK( mode ) || S_ISCHR( mode ) ) ) ) ) + const bool can_read = ( i == 0 && + ( S_ISBLK( mode ) || S_ISCHR( mode ) || + S_ISFIFO( mode ) || S_ISSOCK( mode ) ) ); + if( i != 0 || ( !S_ISREG( mode ) && ( !to_stdout || !can_read ) ) ) { if( verbosity >= 0 ) - std::fprintf( stderr, "%s: input file `%s' is not a regular file%s.\n", + std::fprintf( stderr, "%s: Input file `%s' is not a regular file%s.\n", program_name, name.c_str(), - to_stdout ? "" : " and `--stdout' was not specified" ); + ( can_read && !to_stdout ) ? + " and `--stdout' was not specified" : "" ); close( infd ); infd = -1; } @@ -309,7 +287,7 @@ void set_d_outname( const std::string & name, const int i ) throw() } output_filename = name; output_filename += ".out"; if( verbosity >= 0 ) - std::fprintf( stderr, "%s: can't guess original name for `%s' -- using `%s'.\n", + std::fprintf( stderr, "%s: Can't guess original name for `%s' -- using `%s'.\n", program_name, name.c_str(), output_filename.c_str() ); } @@ -320,18 +298,14 @@ bool open_outstream( const bool force ) throw() if( force ) flags |= O_TRUNC; else flags |= O_EXCL; outfd = open( output_filename.c_str(), flags, outfd_mode ); - if( outfd < 0 ) + if( outfd < 0 && verbosity >= 0 ) { - if( errno == EEXIST ) outfd = -2; else outfd = -1; - if( verbosity >= 0 ) - { - if( outfd == -2 ) - std::fprintf( stderr, "%s: Output file %s already exists, skipping.\n", - program_name, output_filename.c_str() ); - else - std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n", - program_name, output_filename.c_str(), std::strerror( errno ) ); - } + if( errno == EEXIST ) + std::fprintf( stderr, "%s: Output file `%s' already exists, skipping.\n", + program_name, output_filename.c_str() ); + else + std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n", + program_name, output_filename.c_str(), std::strerror( errno ) ); } return ( outfd >= 0 ); } @@ -339,7 +313,7 @@ bool open_outstream( const bool force ) throw() bool check_tty( const int infd, const Mode program_mode ) throw() { - if( program_mode == m_compress && isatty( outfd ) ) + if( program_mode == m_compress && outfd >= 0 && isatty( outfd ) ) { show_error( "I won't write compressed data to a terminal.", 0, true ); return false; @@ -376,8 +350,9 @@ void close_and_set_permissions( const struct stat * const in_statsp ) bool error = false; if( in_statsp ) { - if( fchmod( outfd, in_statsp->st_mode ) != 0 ) error = true; - else (void)fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ); + if( fchmod( outfd, in_statsp->st_mode ) != 0 || + ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 && + errno != EPERM ) ) error = true; // fchown will in many cases return with EPERM, which can be safely ignored. } if( close( outfd ) == 0 ) outfd = -1; @@ -393,7 +368,7 @@ void close_and_set_permissions( const struct stat * const in_statsp ) } if( error ) { - show_error( "I can't change output file attributes." ); + show_error( "Can't change output file attributes." ); cleanup_and_fail( 1 ); } } @@ -409,15 +384,11 @@ extern "C" void signal_handler( int sig ) throw() } -void set_signals( const bool to_file ) throw() +void set_signals() throw() { - if( to_file ) - { - std::signal( SIGHUP, signal_handler ); - std::signal( SIGINT, signal_handler ); - std::signal( SIGTERM, signal_handler ); - } - std::signal( SIGUSR1, signal_handler ); + std::signal( SIGHUP, signal_handler ); + std::signal( SIGINT, signal_handler ); + std::signal( SIGTERM, signal_handler ); } } // end namespace @@ -453,22 +424,24 @@ void show_error( const char * const msg, const int errcode, const bool help ) th { if( verbosity >= 0 ) { - if( msg && msg[0] != 0 ) + if( msg && msg[0] ) { std::fprintf( stderr, "%s: %s", program_name, msg ); - if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) ); + if( errcode > 0 ) + std::fprintf( stderr, ": %s", std::strerror( errcode ) ); std::fprintf( stderr, "\n" ); } - if( help && invocation_name && invocation_name[0] != 0 ) - std::fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name ); + if( help && invocation_name && invocation_name[0] ) + std::fprintf( stderr, "Try `%s --help' for more information.\n", + invocation_name ); } } void internal_error( const char * const msg ) { - std::string s( "internal error: " ); s += msg; - show_error( s.c_str() ); + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: internal error: %s.\n", program_name, msg ); std::exit( 3 ); } @@ -516,21 +489,21 @@ int main( const int argc, const char * const argv[] ) // to the corresponding LZMA compression modes. const Lzma_options option_mapping[] = { - { 1 << 16, 5 }, // -0 - { 1 << 20, 10 }, // -1 - { 3 << 19, 12 }, // -2 - { 1 << 21, 17 }, // -3 - { 3 << 20, 26 }, // -4 - { 1 << 22, 44 }, // -5 - { 1 << 23, 80 }, // -6 - { 1 << 24, 108 }, // -7 - { 3 << 23, 163 }, // -8 + { 1 << 20, 5 }, // -0 + { 1 << 20, 5 }, // -1 + { 3 << 19, 6 }, // -2 + { 1 << 21, 8 }, // -3 + { 3 << 20, 12 }, // -4 + { 1 << 22, 20 }, // -5 + { 1 << 23, 36 }, // -6 + { 1 << 24, 68 }, // -7 + { 3 << 23, 132 }, // -8 { 1 << 25, 273 } }; // -9 Lzma_options encoder_options = option_mapping[6]; // default = "-6" int data_size = 0; int debug_level = 0; int infd = -1; - int num_workers = 0; // Start this many worker threads + int num_workers = 0; // start this many worker threads Mode program_mode = m_compress; bool force = false; bool keep_input_files = false; @@ -554,8 +527,8 @@ int main( const int argc, const char * const argv[] ) const Arg_parser::Option options[] = { - { '0', 0, Arg_parser::no }, - { '1', "fast", Arg_parser::no }, + { '0', "fast", Arg_parser::no }, + { '1', 0, Arg_parser::no }, { '2', 0, Arg_parser::no }, { '3', 0, Arg_parser::no }, { '4', 0, Arg_parser::no }, @@ -584,7 +557,7 @@ int main( const int argc, const char * const argv[] ) { 'V', "version", Arg_parser::no }, { 0 , 0, Arg_parser::no } }; - Arg_parser parser( argc, argv, options ); + const Arg_parser parser( argc, argv, options ); if( parser.error().size() ) // bad option { show_error( parser.error().c_str(), 0, true ); return 1; } @@ -605,7 +578,7 @@ int main( const int argc, const char * const argv[] ) case 'c': to_stdout = true; break; case 'd': program_mode = m_decompress; break; case 'D': debug_level = getnum( arg, 0, 0, 3 ); break; - case 'e': break; + case 'e': break; // ignored by now case 'f': force = true; break; case 'h': show_help(); return 0; case 'k': keep_input_files = true; break; @@ -623,7 +596,7 @@ int main( const int argc, const char * const argv[] ) case 'V': show_version(); return 0; default : internal_error( "uncaught option" ); } - } + } // end process options if( data_size <= 0 ) data_size = 2 * std::max( 65536, encoder_options.dictionary_size ); @@ -646,8 +619,10 @@ int main( const int argc, const char * const argv[] ) } if( filenames.empty() ) filenames.push_back("-"); - set_signals( !to_stdout && program_mode != m_test && - ( filenames_given || default_output_filename.size() ) ); + if( !to_stdout && program_mode != m_test && + ( filenames_given || default_output_filename.size() ) ) + set_signals(); + std::signal( SIGUSR1, signal_handler ); Pretty_print pp( filenames ); if( program_mode == m_test ) @@ -737,9 +712,7 @@ int main( const int argc, const char * const argv[] ) } if( outfd >= 0 && close( outfd ) != 0 ) { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Can't close stdout: %s.\n", - program_name, std::strerror( errno ) ); + show_error( "Can't close stdout", errno ); if( retval < 1 ) retval = 1; } return retval; @@ -19,16 +19,15 @@ class Pretty_print { const char * const stdin_name; - const unsigned int stdin_name_len; unsigned int longest_name; std::string name_; mutable bool first_post; public: Pretty_print( const std::vector< std::string > & filenames ) - : stdin_name( "(stdin)" ), stdin_name_len( std::strlen( stdin_name ) ), - longest_name( 0 ), first_post( false ) + : stdin_name( "(stdin)" ), longest_name( 0 ), first_post( false ) { + const unsigned int stdin_name_len = std::strlen( stdin_name ); for( unsigned int i = 0; i < filenames.size(); ++i ) { const std::string & s = filenames[i]; @@ -119,7 +118,7 @@ int decompress( const int num_workers, const int num_slots, extern int verbosity; -void fatal(); // Terminate the process +void fatal(); // terminate the program void show_error( const char * const msg, const int errcode = 0, const bool help = false ) throw(); void internal_error( const char * const msg ); diff --git a/testsuite/check.sh b/testsuite/check.sh index 580a74e..c640b3b 100755 --- a/testsuite/check.sh +++ b/testsuite/check.sh @@ -19,15 +19,24 @@ fi if [ -d tmp ] ; then rm -rf tmp ; fi mkdir tmp -printf "testing plzip..." +printf "testing plzip-%s..." "$2" cd "${objdir}"/tmp -cat "${testdir}"/test1 > in || framework_failure +cat "${testdir}"/test.txt > in || framework_failure cat in in in in > in4 || framework_failure fail=0 -"${LZIP}" -cd "${testdir}"/test1.lz > copy || fail=1 +"${LZIP}" -t "${testdir}"/test_v0.lz || fail=1 +printf . +"${LZIP}" -cd "${testdir}"/test_v0.lz > copy || fail=1 cmp in copy || fail=1 +printf . + +"${LZIP}" -t "${testdir}"/test_v1.lz || fail=1 +printf . +"${LZIP}" -cd "${testdir}"/test_v1.lz > copy || fail=1 +cmp in copy || fail=1 +printf . for i in s4Ki 0 1 2 3 4 5 6 7 8 9 ; do "${LZIP}" -k -$i in || fail=1 @@ -54,12 +63,17 @@ for i in s4Ki 0 1 2 3 4 5 6 7 8 9 ; do done for i in s4Ki 0 1 2 3 4 5 6 7 8 9 ; do - "${LZIP}" -fe -$i -o out < in || fail=1 + "${LZIP}" -f -$i -o out < in || fail=1 "${LZIP}" -df -o copy < out.lz || fail=1 cmp in copy || fail=1 printf . done +"${LZIP}" -$i < in > anyothername || fail=1 +"${LZIP}" -dq anyothername || fail=1 +cmp in anyothername.out || fail=1 +printf . + for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 ; do "${LZIP}" -s4Ki -B8Ki -n$i < in4 > out4 || fail=1 "${LZIP}" -d -n$i < out4 > copy4 || fail=1 diff --git a/testsuite/test1 b/testsuite/test.txt index 5b244d5..5b244d5 100644 --- a/testsuite/test1 +++ b/testsuite/test.txt diff --git a/testsuite/test1.lz b/testsuite/test_v0.lz Binary files differindex a09b1e8..a09b1e8 100644 --- a/testsuite/test1.lz +++ b/testsuite/test_v0.lz diff --git a/testsuite/test_v1.lz b/testsuite/test_v1.lz Binary files differnew file mode 100644 index 0000000..f1c79eb --- /dev/null +++ b/testsuite/test_v1.lz |