Adding upstream version 1.10.

Signed-off-by: Daniel Baumann <daniel@debian.org>

ChangeLog

@@ -1,3 +1,13 @@
+2022-01-24  Antonio Diaz Diaz  <antonio@gnu.org>
+
+	* Version 1.10 released.
+	* main.cc (getnum): Show option name and valid range if error.
+	  (check_lib): Check that LZ_API_VERSION and LZ_version_string match.
+	* Set variable LIBS from configure.
+	* Improve several descriptions in manual, '--help', and man page.
+	* plzip.texi: Change GNU Texinfo category to 'Compression'.
+	  (Reported by Alfred M. Szmidt).
+
 2021-01-03  Antonio Diaz Diaz  <antonio@gnu.org>
 
 	* Version 1.9 released.
@@ -37,7 +47,7 @@
 	* main.cc (main): Check return value of close( infd ).
 	* plzip.texi: Improve description of '-0..-9', '-m', and '-s'.
 	* configure: New option '--with-mingw'.
-	* configure: Accept appending to CXXFLAGS, 'CXXFLAGS+=OPTIONS'.
+	* configure: Accept appending to CXXFLAGS; 'CXXFLAGS+=OPTIONS'.
 	* INSTALL: Document use of CXXFLAGS+='-D __USE_MINGW_ANSI_STDIO'.
 
 2018-02-07  Antonio Diaz Diaz  <antonio@gnu.org>
@@ -164,7 +174,7 @@
 	* Small portability fixes.
 	* plzip.texinfo: New chapter 'Program Design'.
 	  Add missing description of option '-n, --threads'.
-	* Debug stats have been fixed.
+	* Fix debug statistics.
 
 2010-02-10  Antonio Diaz Diaz  <ant_diaz@teleline.es>
 
@@ -210,7 +220,7 @@
             until something better appears on the net.
 
 
-Copyright (C) 2009-2021 Antonio Diaz Diaz.
+Copyright (C) 2009-2022 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

INSTALL

@@ -1,8 +1,8 @@
 Requirements
 ------------
-You will need a C++11 compiler and the compression library lzlib installed.
+You will need a C++98 compiler with suport for 'long long', and the
-(gcc 3.3.6 or newer is recommended).
+compression library lzlib installed. (gcc 3.3.6 or newer is recommended).
-I use gcc 6.1.0 and 4.1.2, but the code should compile with any standards
+I use gcc 6.1.0 and 3.3.6, but the code should compile with any standards
 compliant compiler.
 
 Lzlib must be version 1.0 or newer, but the fast encoder requires lzlib 1.7
@@ -86,7 +86,7 @@ After running 'configure', you can run 'make' and 'make install' as
 explained above.
 
 
-Copyright (C) 2009-2021 Antonio Diaz Diaz.
+Copyright (C) 2009-2022 Antonio Diaz Diaz.
 
 This file is free documentation: you have unlimited permission to copy,
 distribute, and modify it.

Makefile.in

@@ -4,7 +4,6 @@ INSTALL = install
 INSTALL_PROGRAM = $(INSTALL) -m 755
 INSTALL_DATA = $(INSTALL) -m 644
 INSTALL_DIR = $(INSTALL) -d -m 755
-LIBS = -llz -lpthread
 SHELL = /bin/sh
 CAN_RUN_INSTALLINFO = $(SHELL) -c "install-info --version" > /dev/null 2>&1
 
@@ -22,7 +21,7 @@ objs = arg_parser.o lzip_index.o list.o compress.o dec_stdout.o \
 all : $(progname)
 
 $(progname) : $(objs)
-	$(CXX) $(LDFLAGS) $(CXXFLAGS) -o $@ $(objs) $(LIBS)
+	$(CXX) $(CXXFLAGS) $(LDFLAGS) -o $@ $(objs) $(LIBS)
 
 decompress.o : decompress.cc
 	$(CXX) $(CPPFLAGS) $(CXXFLAGS) $(with_mingw) -c -o $@ $<
@@ -129,6 +128,7 @@ dist : doc
 	  $(DISTNAME)/*.cc \
 	  $(DISTNAME)/testsuite/check.sh \
 	  $(DISTNAME)/testsuite/test.txt \
+	  $(DISTNAME)/testsuite/fox.lz \
 	  $(DISTNAME)/testsuite/fox_*.lz \
 	  $(DISTNAME)/testsuite/test.txt.lz \
 	  $(DISTNAME)/testsuite/test_em.txt.lz

NEWS

@@ -1,58 +1,13 @@
-Changes in version 1.9:
+Changes in version 1.10:
 
-Plzip now reports an error if a file name is empty (plzip -t "").
+In case of error in a numerical argument to a command line option, plzip
+now shows the name of the option and the range of valid values.
 
-Option '-o, --output' now behaves like '-c, --stdout', but sending the
+'--check-lib' now checks that LZ_API_VERSION and LZ_version_string match.
-output unconditionally to a file instead of to standard output. See the new
-description of '-o' in the manual. This change is backwards compatible only
-when (de)compressing from standard input alone. Therefore commands like:
-  plzip -o foo.lz - bar < foo
-must now be split into:
-  plzip -o foo.lz - < foo
-  plzip bar
-or rewritten as:
-  plzip - bar < foo > foo.lz
 
-When using '-c' or '-o', plzip now checks whether the output is a terminal
+The variable LIBS can now be set from configure.
-only once.
 
-Plzip now does not even open the output file if the input file is a terminal.
+Several descriptions have been improved in manual, '--help', and man page.
 
-The new option '--check-lib', which compares the version of lzlib used to
+The texinfo category of the manual has been changed from 'Data Compression'
-compile plzip with the version actually being used at run time, has been added.
+to 'Compression' to match that of gzip. (Reported by Alfred M. Szmidt).
-
-The words 'decompressed' and 'compressed' have been replaced with the
-shorter 'out' and 'in' in the verbose output when decompressing or testing.
-
-When checking the integrity of multiple files, plzip is now able to continue
-checking the rest of the files (instead of exiting) if some of them fail the
-test, allowing 'plzip --test' to show a final diagnostic with the number of
-files that failed (just as 'lzip --test').
-
-Testing is now slightly (1.6%) faster when using lzlib 1.12.
-
-When compressing, or when decompressing or testing from a non-seekable file
-or from standard input, plzip now starts only the number of worker threads
-required.
-
-When decompressing or testing from a non-seekable file or from standard
-input, trailing data are now not counted in the compressed size shown.
-
-When decompressing or testing a multimember file, plzip now shows the
-largest dictionary size of all members in the file instead of showing the
-dictionary size of the first member.
-
-Option '--list' now reports corruption or truncation of the last header in a
-multimenber file specifically instead of showing the generic message "Last
-member in input file is truncated or corrupt."
-
-The error messages for 'Data error' and 'Unexpected EOF' have been shortened.
-
-The commands needed to extract files from a tar.lz archive have been
-documented in the manual, in the output of '--help', and in the man page.
-
-Tarlz is mentioned in the manual as an alternative to tar + plzip.
-
-Several fixes and improvements have been made to the manual.
-
-8 new test files have been added to the testsuite.

README

@@ -5,13 +5,14 @@ compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib.
 
 Lzip is a lossless data compressor with a user interface similar to the one
 of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov
-chain-Algorithm' (LZMA) stream format, chosen to maximize safety and
+chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity
-interoperability. Lzip can compress about as fast as gzip (lzip -0) or
+checking to maximize interoperability and optimize safety. Lzip can compress
-compress most files more than bzip2 (lzip -9). Decompression speed is
+about as fast as gzip (lzip -0) or compress most files more than bzip2
-intermediate between gzip and bzip2. Lzip is better than gzip and bzip2 from
+(lzip -9). Decompression speed is intermediate between gzip and bzip2.
-a data recovery perspective. Lzip has been designed, written, and tested
+Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip
-with great care to replace gzip and bzip2 as the standard general-purpose
+has been designed, written, and tested with great care to replace gzip and
-compressed format for unix-like systems.
+bzip2 as the standard general-purpose compressed format for unix-like
+systems.
 
 Plzip can compress/decompress large files on multiprocessor machines much
 faster than lzip, at the cost of a slightly reduced compression ratio (0.4
@@ -76,7 +77,7 @@ filename.lz    becomes   filename
 filename.tlz   becomes   filename.tar
 anyothername   becomes   anyothername.out
 
-(De)compressing a file is much like copying or moving it; therefore plzip
+(De)compressing a file is much like copying or moving it. Therefore plzip
 preserves the access and modification dates, permissions, and, when
 possible, ownership of the file just as 'cp -p' does. (If the user ID or
 the group ID can't be duplicated, the file permission bits S_ISUID and
@@ -100,7 +101,7 @@ been compressed. Decompressed is used to refer to data which have undergone
 the process of decompression.
 
 
-Copyright (C) 2009-2021 Antonio Diaz Diaz.
+Copyright (C) 2009-2022 Antonio Diaz Diaz.
 
 This file is free documentation: you have unlimited permission to copy,
 distribute, and modify it.

arg_parser.cc

@@ -1,5 +1,5 @@
 /* Arg_parser - POSIX/GNU command line argument parser. (C++ version)
-   Copyright (C) 2006-2021 Antonio Diaz Diaz.
+   Copyright (C) 2006-2022 Antonio Diaz Diaz.
 
    This library is free software. Redistribution and use in source and
    binary forms, with or without modification, are permitted provided
@@ -35,9 +35,10 @@ bool Arg_parser::parse_long_option( const char * const opt, const char * const a
 
   // Test all long options for either exact match or abbreviated matches.
   for( int i = 0; options[i].code != 0; ++i )
-    if( options[i].name && std::strncmp( options[i].name, &opt[2], len ) == 0 )
+    if( options[i].long_name &&
+        std::strncmp( options[i].long_name, &opt[2], len ) == 0 )
       {
-      if( std::strlen( options[i].name ) == len )	// Exact match found
+      if( std::strlen( options[i].long_name ) == len )	// Exact match found
         { index = i; exact = true; break; }
       else if( index < 0 ) index = i;		// First nonexact match found
       else if( options[index].code != options[i].code ||
@@ -58,19 +59,19 @@ bool Arg_parser::parse_long_option( const char * const opt, const char * const a
     }
 
   ++argind;
-  data.push_back( Record( options[index].code ) );
+  data.push_back( Record( options[index].code, options[index].long_name ) );
 
   if( opt[len+2] )		// '--<long_option>=<argument>' syntax
     {
     if( options[index].has_arg == no )
       {
-      error_ = "option '--"; error_ += options[index].name;
+      error_ = "option '--"; error_ += options[index].long_name;
       error_ += "' doesn't allow an argument";
       return false;
       }
     if( options[index].has_arg == yes && !opt[len+3] )
       {
-      error_ = "option '--"; error_ += options[index].name;
+      error_ = "option '--"; error_ += options[index].long_name;
       error_ += "' requires an argument";
       return false;
       }
@@ -82,7 +83,7 @@ bool Arg_parser::parse_long_option( const char * const opt, const char * const a
     {
     if( !arg || !arg[0] )
       {
-      error_ = "option '--"; error_ += options[index].name;
+      error_ = "option '--"; error_ += options[index].long_name;
       error_ += "' requires an argument";
       return false;
       }

arg_parser.h

@@ -1,5 +1,5 @@
 /* Arg_parser - POSIX/GNU command line argument parser. (C++ version)
-   Copyright (C) 2006-2021 Antonio Diaz Diaz.
+   Copyright (C) 2006-2022 Antonio Diaz Diaz.
 
    This library is free software. Redistribution and use in source and
    binary forms, with or without modification, are permitted provided
@@ -23,9 +23,9 @@
    In case of error, 'error' returns a non-empty error message.
 
    'options' is an array of 'struct Option' terminated by an element
-   containing a code which is zero. A null name means a short-only
+   containing a code which is zero. A null long_name means a short-only
-   option. A code value outside the unsigned char range means a
+   option. A code value outside the unsigned char range means a long-only
-   long-only option.
+   option.
 
    Arg_parser normally makes it appear as if all the option arguments
    were specified before all the non-option arguments for the purposes
@@ -48,7 +48,7 @@ public:
   struct Option
     {
     int code;			// Short option letter or code ( code != 0 )
-    const char * name;		// Long option name (maybe null)
+    const char * long_name;	// Long option name (maybe null)
     Has_arg has_arg;
     };
 
@@ -56,8 +56,12 @@ private:
   struct Record
     {
     int code;
+    std::string parsed_name;
     std::string argument;
-    explicit Record( const int c ) : code( c ) {}
+    explicit Record( const unsigned char c )
+      : code( c ), parsed_name( "-" ) { parsed_name += c; }
+    Record( const int c, const char * const long_name )
+      : code( c ), parsed_name( "--" ) { parsed_name += long_name; }
     explicit Record( const char * const arg ) : code( 0 ), argument( arg ) {}
     };
 
@@ -91,6 +95,13 @@ public:
     else return 0;
     }
 
+  // Full name of the option parsed (short or long).
+  const std::string & parsed_name( const int i ) const
+    {
+    if( i >= 0 && i < arguments() ) return data[i].parsed_name;
+    else return empty_arg;
+    }
+
   const std::string & argument( const int i ) const
     {
     if( i >= 0 && i < arguments() ) return data[i].argument;

compress.cc

@@ -1,6 +1,6 @@
 /* Plzip - Massively parallel implementation of lzip
    Copyright (C) 2009 Laszlo Ersek.
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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
@@ -38,8 +38,8 @@
 #endif
 
 
-/* Returns the number of bytes really read.
+/* Return the number of bytes really read.
-   If (returned value < size) and (errno == 0), means EOF was reached.
+   If (value returned < size) and (errno == 0), means EOF was reached.
 */
 int readblock( const int fd, uint8_t * const buf, const int size )
   {
@@ -57,8 +57,8 @@ int readblock( const int fd, uint8_t * const buf, const int size )
   }
 
 
-/* Returns the number of bytes really written.
+/* Return the number of bytes really written.
-   If (returned value < size), it is always an error.
+   If (value returned < size), it is always an error.
 */
 int writeblock( const int fd, const uint8_t * const buf, const int size )
   {
@@ -483,7 +483,7 @@ int compress( const unsigned long long cfile_size,
               const int infd, const int outfd,
               const Pretty_print & pp, const int debug_level )
   {
-  const int offset = data_size / 8;
+  const int offset = data_size / 8;	// offset for compression in-place
   const int slots_per_worker = 2;
   const int num_slots =
     ( ( num_workers > 1 ) ? num_workers * slots_per_worker : 1 );

configure

@@ -1,12 +1,12 @@
 #! /bin/sh
 # configure script for Plzip - Massively parallel implementation of lzip
-# Copyright (C) 2009-2021 Antonio Diaz Diaz.
+# Copyright (C) 2009-2022 Antonio Diaz Diaz.
 #
 # This configure script is free software: you have unlimited permission
 # to copy, distribute, and modify it.
 
 pkgname=plzip
-pkgversion=1.9
+pkgversion=1.10
 progname=plzip
 with_mingw=
 srctrigger=doc/${pkgname}.texi
@@ -25,6 +25,7 @@ CXX=g++
 CPPFLAGS=
 CXXFLAGS='-Wall -W -O2'
 LDFLAGS=
+LIBS='-llz -lpthread'
 
 # checking whether we are using GNU C++.
 /bin/sh -c "${CXX} --version" > /dev/null 2>&1 || { CXX=c++ ; CXXFLAGS=-O2 ; }
@@ -71,6 +72,7 @@ while [ $# != 0 ] ; do
 		echo "  CXXFLAGS=OPTIONS      command line options for the C++ compiler [${CXXFLAGS}]"
 		echo "  CXXFLAGS+=OPTIONS     append options to the current value of CXXFLAGS"
 		echo "  LDFLAGS=OPTIONS       command line options for the linker [${LDFLAGS}]"
+		echo "  LIBS=OPTIONS          libraries to pass to the linker [${LIBS}]"
 		echo
 		exit 0 ;;
 	--version | -V)
@@ -99,6 +101,7 @@ while [ $# != 0 ] ; do
 	CXXFLAGS=*)  CXXFLAGS=${optarg} ;;
 	CXXFLAGS+=*) CXXFLAGS="${CXXFLAGS} ${optarg}" ;;
 	LDFLAGS=*)    LDFLAGS=${optarg} ;;
+	LIBS=*)          LIBS="${optarg} ${LIBS}" ;;
 
 	--*)
 		echo "configure: WARNING: unrecognized option: '${option}'" 1>&2 ;;
@@ -168,10 +171,11 @@ echo "CXX = ${CXX}"
 echo "CPPFLAGS = ${CPPFLAGS}"
 echo "CXXFLAGS = ${CXXFLAGS}"
 echo "LDFLAGS = ${LDFLAGS}"
+echo "LIBS = ${LIBS}"
 rm -f Makefile
 cat > Makefile << EOF
 # Makefile for Plzip - Massively parallel implementation of lzip
-# Copyright (C) 2009-2021 Antonio Diaz Diaz.
+# Copyright (C) 2009-2022 Antonio Diaz Diaz.
 # This file was generated automatically by configure. Don't edit.
 #
 # This Makefile is free software: you have unlimited permission
@@ -192,6 +196,7 @@ CXX = ${CXX}
 CPPFLAGS = ${CPPFLAGS}
 CXXFLAGS = ${CXXFLAGS}
 LDFLAGS = ${LDFLAGS}
+LIBS = ${LIBS}
 EOF
 cat "${srcdir}/Makefile.in" >> Makefile
 

dec_stdout.cc

@@ -1,6 +1,6 @@
 /* Plzip - Massively parallel implementation of lzip
    Copyright (C) 2009 Laszlo Ersek.
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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

dec_stream.cc

@@ -1,6 +1,6 @@
 /* Plzip - Massively parallel implementation of lzip
    Copyright (C) 2009 Laszlo Ersek.
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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

decompress.cc

@@ -1,6 +1,6 @@
 /* Plzip - Massively parallel implementation of lzip
    Copyright (C) 2009 Laszlo Ersek.
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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
@@ -39,7 +39,7 @@
 /* This code is based on a patch by Hannes Domani, <ssbssa@yahoo.de> to make
    possible compiling plzip under MS Windows (with MINGW compiler).
 */
-#if defined(__MSVCRT__) && defined(WITH_MINGW)
+#if defined __MSVCRT__ && defined WITH_MINGW
 #include <windows.h>
 #warning "Parallel I/O is not guaranteed to work on Windows."
 
@@ -76,8 +76,8 @@ ssize_t pwrite( int fd, const void *buf, size_t count, uint64_t offset )
 #endif	// __MSVCRT__
 
 
-/* Returns the number of bytes really read.
+/* Return the number of bytes really read.
-   If (returned value < size) and (errno == 0), means EOF was reached.
+   If (value returned < size) and (errno == 0), means EOF was reached.
 */
 int preadblock( const int fd, uint8_t * const buf, const int size,
                 const long long pos )
@@ -96,8 +96,8 @@ int preadblock( const int fd, uint8_t * const buf, const int size,
   }
 
 
-/* Returns the number of bytes really written.
+/* Return the number of bytes really written.
-   If (returned value < size), it is always an error.
+   If (value returned < size), it is always an error.
 */
 int pwriteblock( const int fd, const uint8_t * const buf, const int size,
                  const long long pos )

doc/plzip.1

@@ -1,5 +1,5 @@
 .\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.16.
-.TH PLZIP "1" "January 2021" "plzip 1.9" "User Commands"
+.TH PLZIP "1" "January 2022" "plzip 1.10" "User Commands"
 .SH NAME
 plzip \- reduces the size of files
 .SH SYNOPSIS
@@ -11,13 +11,14 @@ compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib.
 .PP
 Lzip is a lossless data compressor with a user interface similar to the one
 of gzip or bzip2. Lzip uses a simplified form of the 'Lempel\-Ziv\-Markov
-chain\-Algorithm' (LZMA) stream format, chosen to maximize safety and
+chain\-Algorithm' (LZMA) stream format and provides a 3 factor integrity
-interoperability. Lzip can compress about as fast as gzip (lzip \fB\-0\fR) or
+checking to maximize interoperability and optimize safety. Lzip can compress
-compress most files more than bzip2 (lzip \fB\-9\fR). Decompression speed is
+about as fast as gzip (lzip \fB\-0\fR) or compress most files more than bzip2
-intermediate between gzip and bzip2. Lzip is better than gzip and bzip2 from
+(lzip \fB\-9\fR). Decompression speed is intermediate between gzip and bzip2.
-a data recovery perspective. Lzip has been designed, written, and tested
+Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip
-with great care to replace gzip and bzip2 as the standard general\-purpose
+has been designed, written, and tested with great care to replace gzip and
-compressed format for unix\-like systems.
+bzip2 as the standard general\-purpose compressed format for unix\-like
+systems.
 .PP
 Plzip can compress/decompress large files on multiprocessor machines much
 faster than lzip, at the cost of a slightly reduced compression ratio (0.4
@@ -116,7 +117,7 @@ To extract all the files from archive 'foo.tar.lz', use the commands
 .PP
 Exit status: 0 for a normal exit, 1 for environmental problems (file
 not found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or
-invalid input file, 3 for an internal consistency error (eg, bug) which
+invalid input file, 3 for an internal consistency error (e.g., bug) which
 caused plzip to panic.
 .SH "REPORTING BUGS"
 Report bugs to lzip\-bug@nongnu.org
@@ -125,8 +126,8 @@ Plzip home page: http://www.nongnu.org/lzip/plzip.html
 .SH COPYRIGHT
 Copyright \(co 2009 Laszlo Ersek.
 .br
-Copyright \(co 2021 Antonio Diaz Diaz.
+Copyright \(co 2022 Antonio Diaz Diaz.
-Using lzlib 1.12
+Using lzlib 1.13
 License GPLv2+: GNU GPL version 2 or later <http://gnu.org/licenses/gpl.html>
 .br
 This is free software: you are free to change and redistribute it.

doc/plzip.info

@@ -1,6 +1,6 @@
 This is plzip.info, produced by makeinfo version 4.13+ from plzip.texi.
 
-INFO-DIR-SECTION Data Compression
+INFO-DIR-SECTION Compression
 START-INFO-DIR-ENTRY
 * Plzip: (plzip).               Massively parallel implementation of lzip
 END-INFO-DIR-ENTRY
@@ -11,7 +11,7 @@ File: plzip.info,  Node: Top,  Next: Introduction,  Up: (dir)
 Plzip Manual
 ************
 
-This manual is for Plzip (version 1.9, 3 January 2021).
+This manual is for Plzip (version 1.10, 24 January 2022).
 
 * Menu:
 
@@ -19,16 +19,16 @@ This manual is for Plzip (version 1.9, 3 January 2021).
 * Output::                 Meaning of plzip's output
 * Invoking plzip::         Command line interface
 * Program design::         Internal structure of plzip
-* File format::            Detailed format of the compressed file
 * Memory requirements::    Memory required to compress and decompress
 * Minimum file sizes::     Minimum file sizes required for full speed
+* File format::            Detailed format of the compressed file
 * Trailing data::          Extra data appended to the file
 * Examples::               A small tutorial with examples
 * Problems::               Reporting bugs
 * Concept index::          Index of concepts
 
 
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 Antonio Diaz Diaz.
 
    This manual is free documentation: you have unlimited permission to copy,
 distribute, and modify it.
@@ -44,13 +44,14 @@ compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib.
 
    Lzip is a lossless data compressor with a user interface similar to the
 one of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov
-chain-Algorithm' (LZMA) stream format, chosen to maximize safety and
+chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity
-interoperability. Lzip can compress about as fast as gzip (lzip -0) or
+checking to maximize interoperability and optimize safety. Lzip can compress
-compress most files more than bzip2 (lzip -9). Decompression speed is
+about as fast as gzip (lzip -0) or compress most files more than bzip2
-intermediate between gzip and bzip2. Lzip is better than gzip and bzip2 from
+(lzip -9). Decompression speed is intermediate between gzip and bzip2. Lzip
-a data recovery perspective. Lzip has been designed, written, and tested
+is better than gzip and bzip2 from a data recovery perspective. Lzip has
-with great care to replace gzip and bzip2 as the standard general-purpose
+been designed, written, and tested with great care to replace gzip and
-compressed format for unix-like systems.
+bzip2 as the standard general-purpose compressed format for unix-like
+systems.
 
    Plzip can compress/decompress large files on multiprocessor machines much
 faster than lzip, at the cost of a slightly reduced compression ratio (0.4
@@ -107,7 +108,7 @@ filename.lz    becomes   filename
 filename.tlz   becomes   filename.tar
 anyothername   becomes   anyothername.out
 
-   (De)compressing a file is much like copying or moving it; therefore plzip
+   (De)compressing a file is much like copying or moving it. Therefore plzip
 preserves the access and modification dates, permissions, and, when
 possible, ownership of the file just as 'cp -p' does. (If the user ID or
 the group ID can't be duplicated, the file permission bits S_ISUID and
@@ -206,7 +207,7 @@ once, the first time it appears in the command line.
 
 '-B BYTES'
 '--data-size=BYTES'
-     When compressing, set the size of the input data blocks in bytes. The
+     When compressing, set the size in bytes of the input data blocks. The
      input file will be divided in chunks of this size before compression is
      performed. Valid values range from 8 KiB to 1 GiB. Default value is
      two times the dictionary size, except for option '-0' where it
@@ -224,10 +225,13 @@ once, the first time it appears in the command line.
 
 '-d'
 '--decompress'
-     Decompress the files specified. If a file does not exist or can't be
+     Decompress the files specified. If a file does not exist, can't be
-     opened, plzip continues decompressing the rest of the files. If a file
+     opened, or the destination file already exists and '--force' has not
-     fails to decompress, or is a terminal, plzip exits immediately without
+     been specified, plzip continues decompressing the rest of the files
-     decompressing the rest of the files.
+     and exits with error status 1. If a file fails to decompress, or is a
+     terminal, plzip exits immediately with error status 2 without
+     decompressing the rest of the files. A terminal is considered an
+     uncompressed file, and therefore invalid.
 
 '-f'
 '--force'
@@ -253,10 +257,12 @@ once, the first time it appears in the command line.
      positions and sizes of each member in multimember files are also
      printed.
 
-     '-lq' can be used to verify quickly (without decompressing) the
+     If any file is damaged, does not exist, can't be opened, or is not
-     structural integrity of the files specified. (Use '--test' to verify
+     regular, the final exit status will be > 0. '-lq' can be used to verify
-     the data integrity). '-alq' additionally verifies that none of the
+     quickly (without decompressing) the structural integrity of the files
-     files specified contain trailing data.
+     specified. (Use '--test' to verify the data integrity). '-alq'
+     additionally verifies that none of the files specified contain
+     trailing data.
 
 '-m BYTES'
 '--match-length=BYTES'
@@ -395,9 +401,10 @@ once, the first time it appears in the command line.
      actually being used at run time and exit. Report any differences
      found. Exit with error status 1 if differences are found. A mismatch
      may indicate that lzlib is not correctly installed or that a different
-     version of lzlib has been installed after compiling plzip.
+     version of lzlib has been installed after compiling plzip. Exit with
+     error status 2 if LZ_API_VERSION and LZ_version_string don't match.
      'plzip -v --check-lib' shows the version of lzlib being used and the
-     value of 'LZ_API_VERSION' (if defined). *Note Library version:
+     value of LZ_API_VERSION (if defined). *Note Library version:
      (lzlib)Library version.
 
 
@@ -419,18 +426,19 @@ Y        yottabyte (10^24)         |   Yi       yobibyte (2^80)
 
    Exit status: 0 for a normal exit, 1 for environmental problems (file not
 found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or invalid
-input file, 3 for an internal consistency error (eg, bug) which caused
+input file, 3 for an internal consistency error (e.g., bug) which caused
 plzip to panic.
 
 
-File: plzip.info,  Node: Program design,  Next: File format,  Prev: Invoking plzip,  Up: Top
+File: plzip.info,  Node: Program design,  Next: Memory requirements,  Prev: Invoking plzip,  Up: Top
 
 4 Internal structure of plzip
 *****************************
 
 When compressing, plzip divides the input file into chunks and compresses as
 many chunks simultaneously as worker threads are chosen, creating a
-multimember compressed file.
+multimember compressed file. Each chunk is compressed in-place (using the
+same buffer for input and output), reducing the amount of RAM required.
 
    When decompressing, plzip decompresses as many members simultaneously as
 worker threads are chosen. Files that were compressed with lzip will not be
@@ -448,14 +456,14 @@ to the workers. The workers (de)compress the blocks received from the
 splitter. The muxer collects processed packets from the workers, and writes
 them to the output file.
 
-                             ,------------,
+                             .------------.
                          ,-->| worker   0 |--,
                          |   `------------'  |
-,-------,   ,----------, |   ,------------,  |   ,-------,   ,--------,
+.-------.   .----------. |   .------------.  |   .-------.   .--------.
 | input |-->| splitter |-+-->| worker   1 |--+-->| muxer |-->| output |
 | file  |   `----------' |   `------------'  |   `-------'   |  file  |
 `-------'                |        ...        |               `--------'
-                         |   ,------------,  |
+                         |   .------------.  |
                          `-->| worker N-1 |--'
                              `------------'
 
@@ -467,82 +475,9 @@ reduced and the decompression speed of large files with many members is
 only limited by the number of processors available and by I/O speed.
 
 
-File: plzip.info,  Node: File format,  Next: Memory requirements,  Prev: Program design,  Up: Top
+File: plzip.info,  Node: Memory requirements,  Next: Minimum file sizes,  Prev: Program design,  Up: Top
 
-5 File format
+5 Memory required to compress and decompress
-*************
-
-Perfection is reached, not when there is no longer anything to add, but
-when there is no longer anything to take away.
--- Antoine de Saint-Exupery
-
-
-   In the diagram below, a box like this:
-
-+---+
-|   | <-- the vertical bars might be missing
-+---+
-
-   represents one byte; a box like this:
-
-+==============+
-|              |
-+==============+
-
-   represents a variable number of bytes.
-
-
-   A lzip file consists of a series of "members" (compressed data sets).
-The members simply appear one after another in the file, with no additional
-information before, between, or after them.
-
-   Each member has the following structure:
-
-+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-| ID string | VN | DS | LZMA stream | CRC32 |   Data size   |  Member size  |
-+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-
-   All multibyte values are stored in little endian order.
-
-'ID string (the "magic" bytes)'
-     A four byte string, identifying the lzip format, with the value "LZIP"
-     (0x4C, 0x5A, 0x49, 0x50).
-
-'VN (version number, 1 byte)'
-     Just in case something needs to be modified in the future. 1 for now.
-
-'DS (coded dictionary size, 1 byte)'
-     The dictionary size is calculated by taking a power of 2 (the base
-     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 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.
-
-'LZMA stream'
-     The LZMA stream, finished by an end of stream marker. Uses default
-     values for encoder properties. *Note Stream format: (lzip)Stream
-     format, for a complete description.
-
-'CRC32 (4 bytes)'
-     Cyclic Redundancy Check (CRC) of the uncompressed original data.
-
-'Data size (8 bytes)'
-     Size of the uncompressed original data.
-
-'Member size (8 bytes)'
-     Total size of the member, including header and trailer. This field acts
-     as a distributed index, allows the verification of stream integrity,
-     and facilitates safe recovery of undamaged members from multimember
-     files.
-
-
-
-File: plzip.info,  Node: Memory requirements,  Next: Minimum file sizes,  Prev: File format,  Up: Top
-
-6 Memory required to compress and decompress
 ********************************************
 
 The amount of memory required *per worker thread* for decompression or
@@ -588,9 +523,9 @@ Level   Memory required
 -9      568 MiB
 
 
-File: plzip.info,  Node: Minimum file sizes,  Next: Trailing data,  Prev: Memory requirements,  Up: Top
+File: plzip.info,  Node: Minimum file sizes,  Next: File format,  Prev: Memory requirements,  Up: Top
 
-7 Minimum file sizes required for full compression speed
+6 Minimum file sizes required for full compression speed
 ********************************************************
 
 When compressing, plzip divides the input file into chunks and compresses
@@ -625,7 +560,83 @@ Level
 -9           128 MiB   256 MiB   512 MiB   1 GiB     4 GiB     16 GiB
 
 
-File: plzip.info,  Node: Trailing data,  Next: Examples,  Prev: Minimum file sizes,  Up: Top
+File: plzip.info,  Node: File format,  Next: Trailing data,  Prev: Minimum file sizes,  Up: Top
+
+7 File format
+*************
+
+Perfection is reached, not when there is no longer anything to add, but
+when there is no longer anything to take away.
+-- Antoine de Saint-Exupery
+
+
+   In the diagram below, a box like this:
+
++---+
+|   | <-- the vertical bars might be missing
++---+
+
+   represents one byte; a box like this:
+
++==============+
+|              |
++==============+
+
+   represents a variable number of bytes.
+
+
+   A lzip file consists of a series of independent "members" (compressed
+data sets). The members simply appear one after another in the file, with no
+additional information before, between, or after them. Each member can
+encode in compressed form up to 16 EiB - 1 byte of uncompressed data. The
+size of a multimember file is unlimited.
+
+   Each member has the following structure:
+
++--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+| ID string | VN | DS | LZMA stream | CRC32 |   Data size   |  Member size  |
++--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+   All multibyte values are stored in little endian order.
+
+'ID string (the "magic" bytes)'
+     A four byte string, identifying the lzip format, with the value "LZIP"
+     (0x4C, 0x5A, 0x49, 0x50).
+
+'VN (version number, 1 byte)'
+     Just in case something needs to be modified in the future. 1 for now.
+
+'DS (coded dictionary size, 1 byte)'
+     The dictionary size is calculated by taking a power of 2 (the base
+     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 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.
+
+'LZMA stream'
+     The LZMA stream, finished by an "End Of Stream" marker. Uses default
+     values for encoder properties. *Note Stream format: (lzip)Stream
+     format, for a complete description.
+
+'CRC32 (4 bytes)'
+     Cyclic Redundancy Check (CRC) of the original uncompressed data.
+
+'Data size (8 bytes)'
+     Size of the original uncompressed data.
+
+'Member size (8 bytes)'
+     Total size of the member, including header and trailer. This field acts
+     as a distributed index, allows the verification of stream integrity,
+     and facilitates the safe recovery of undamaged members from
+     multimember files. Member size should be limited to 2 PiB to prevent
+     the data size field from overflowing.
+
+
+
+File: plzip.info,  Node: Trailing data,  Next: Examples,  Prev: File format,  Up: Top
 
 8 Extra data appended to the file
 *********************************
@@ -699,7 +710,7 @@ show the compression ratio.
      plzip -v file
 
 
-Example 3: Like example 1 but the created 'file.lz' has a block size of
+Example 3: Like example 2 but the created 'file.lz' has a block size of
 1 MiB. The compression ratio is not shown.
 
      plzip -B 1MiB file
@@ -717,15 +728,7 @@ status.
      plzip -tv file.lz
 
 
-Example 6: Compress a whole device in /dev/sdc and send the output to
+Example 6: The right way of concatenating the decompressed output of two or
-'file.lz'.
-
-       plzip -c /dev/sdc > file.lz
-     or
-       plzip /dev/sdc -o file.lz
-
-
-Example 7: The right way of concatenating the decompressed output of two or
 more compressed files. *Note Trailing data::.
 
      Don't do this
@@ -734,17 +737,25 @@ more compressed files. *Note Trailing data::.
        plzip -cd file1.lz file2.lz file3.lz
 
 
-Example 8: Decompress 'file.lz' partially until 10 KiB of decompressed data
+Example 7: Decompress 'file.lz' partially until 10 KiB of decompressed data
 are produced.
 
      plzip -cd file.lz | dd bs=1024 count=10
 
 
-Example 9: Decompress 'file.lz' partially from decompressed byte at offset
+Example 8: Decompress 'file.lz' partially from decompressed byte at offset
 10000 to decompressed byte at offset 14999 (5000 bytes are produced).
 
      plzip -cd file.lz | dd bs=1000 skip=10 count=5
 
+
+Example 9: Compress a whole device in /dev/sdc and send the output to
+'file.lz'.
+
+       plzip -c /dev/sdc > file.lz
+     or
+       plzip /dev/sdc -o file.lz
+
 
 File: plzip.info,  Node: Problems,  Next: Concept index,  Prev: Examples,  Up: Top
 
@@ -758,7 +769,7 @@ eternity, if not longer.
 
    If you find a bug in plzip, please send electronic mail to
 <lzip-bug@nongnu.org>. Include the version number, which you can find by
-running 'plzip --version'.
+running 'plzip --version' and 'plzip -v --check-lib'.
 
 
 File: plzip.info,  Node: Concept index,  Prev: Problems,  Up: Top
@@ -787,22 +798,22 @@ Concept index
 
 
 Tag Table:
-Node: Top222
+Node: Top217
-Node: Introduction1159
+Node: Introduction1156
-Node: Output5788
+Node: Output5829
-Node: Invoking plzip7351
+Node: Invoking plzip7392
-Ref: --trailing-error8146
+Ref: --trailing-error8187
-Ref: --data-size8384
+Ref: --data-size8425
-Node: Program design18364
+Node: Program design18819
-Node: File format20542
+Node: Memory requirements21122
-Ref: coded-dict-size21840
+Node: Minimum file sizes22807
-Node: Memory requirements22995
+Node: File format24821
-Node: Minimum file sizes24677
+Ref: coded-dict-size26260
-Node: Trailing data26693
+Node: Trailing data27514
-Node: Examples28961
+Node: Examples29775
-Ref: concat-example30556
+Ref: concat-example31210
-Node: Problems31153
+Node: Problems31967
-Node: Concept index31681
+Node: Concept index32522
 
 End Tag Table
 

doc/plzip.texi

@@ -6,10 +6,10 @@
 @finalout
 @c %**end of header
 
-@set UPDATED 3 January 2021
+@set UPDATED 24 January 2022
-@set VERSION 1.9
+@set VERSION 1.10
 
-@dircategory Data Compression
+@dircategory Compression
 @direntry
 * Plzip: (plzip).               Massively parallel implementation of lzip
 @end direntry
@@ -40,9 +40,9 @@ This manual is for Plzip (version @value{VERSION}, @value{UPDATED}).
 * Output::                 Meaning of plzip's output
 * Invoking plzip::         Command line interface
 * Program design::         Internal structure of plzip
-* File format::            Detailed format of the compressed file
 * Memory requirements::    Memory required to compress and decompress
 * Minimum file sizes::     Minimum file sizes required for full speed
+* File format::            Detailed format of the compressed file
 * Trailing data::          Extra data appended to the file
 * Examples::               A small tutorial with examples
 * Problems::               Reporting bugs
@@ -50,7 +50,7 @@ This manual is for Plzip (version @value{VERSION}, @value{UPDATED}).
 @end menu
 
 @sp 1
-Copyright @copyright{} 2009-2021 Antonio Diaz Diaz.
+Copyright @copyright{} 2009-2022 Antonio Diaz Diaz.
 
 This manual is free documentation: you have unlimited permission to copy,
 distribute, and modify it.
@@ -69,13 +69,14 @@ compatible with lzip 1.4 or newer. Plzip uses the compression library
 @uref{http://www.nongnu.org/lzip/lzip.html,,Lzip}
 is a lossless data compressor with a user interface similar to the one
 of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov
-chain-Algorithm' (LZMA) stream format, chosen to maximize safety and
+chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity
-interoperability. Lzip can compress about as fast as gzip @w{(lzip -0)} or
+checking to maximize interoperability and optimize safety. Lzip can compress
-compress most files more than bzip2 @w{(lzip -9)}. Decompression speed is
+about as fast as gzip @w{(lzip -0)} or compress most files more than bzip2
-intermediate between gzip and bzip2. Lzip is better than gzip and bzip2 from
+@w{(lzip -9)}. Decompression speed is intermediate between gzip and bzip2.
-a data recovery perspective. Lzip has been designed, written, and tested
+Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip
-with great care to replace gzip and bzip2 as the standard general-purpose
+has been designed, written, and tested with great care to replace gzip and
-compressed format for unix-like systems.
+bzip2 as the standard general-purpose compressed format for unix-like
+systems.
 
 Plzip can compress/decompress large files on multiprocessor machines much
 faster than lzip, at the cost of a slightly reduced compression ratio (0.4
@@ -85,8 +86,8 @@ hundreds of processors, but on files of only a few MB plzip is no faster
 than lzip. @xref{Minimum file sizes}.
 
 For creation and manipulation of compressed tar archives
-@uref{http://www.nongnu.org/lzip/manual/tarlz_manual.html,,tarlz} can be
+@uref{http://www.nongnu.org/lzip/manual/tarlz_manual.html,,tarlz} can be more
-more efficient than using tar and plzip because tarlz is able to keep the
+efficient than using tar and plzip because tarlz is able to keep the
 alignment between tar members and lzip members.
 @ifnothtml
 @xref{Top,tarlz manual,,tarlz}.
@@ -112,8 +113,8 @@ 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
+the data from a lzip file long after quantum computers eventually
-LZMA obsolete.
+render LZMA obsolete.
 
 @item
 Additionally the lzip reference implementation is copylefted, which
@@ -145,9 +146,9 @@ file from that of the compressed file as follows:
 @item anyothername @tab becomes @tab anyothername.out
 @end multitable
 
-(De)compressing a file is much like copying or moving it; therefore plzip
+(De)compressing a file is much like copying or moving it. Therefore plzip
 preserves the access and modification dates, permissions, and, when
-possible, ownership of the file just as @samp{cp -p} does. (If the user ID or
+possible, ownership of the file just as @w{@samp{cp -p}} does. (If the user ID or
 the group ID can't be duplicated, the file permission bits S_ISUID and
 S_ISGID are cleared).
 
@@ -258,7 +259,7 @@ garbage that can be safely ignored. @xref{concat-example}.
 @anchor{--data-size}
 @item -B @var{bytes}
 @itemx --data-size=@var{bytes}
-When compressing, set the size of the input data blocks in bytes. The
+When compressing, set the size in bytes of the input data blocks. The
 input file will be divided in chunks of this size before compression is
 performed. Valid values range from @w{8 KiB} to @w{1 GiB}. Default value
 is two times the dictionary size, except for option @samp{-0} where it
@@ -276,10 +277,12 @@ overrides @samp{-o}. @samp{-c} has no effect when testing or listing.
 
 @item -d
 @itemx --decompress
-Decompress the files specified. If a file does not exist or can't be
+Decompress the files specified. If a file does not exist, can't be opened,
-opened, plzip continues decompressing the rest of the files. If a file
+or the destination file already exists and @samp{--force} has not been
-fails to decompress, or is a terminal, plzip exits immediately without
+specified, plzip continues decompressing the rest of the files and exits with
-decompressing the rest of the files.
+error status 1. If a file fails to decompress, or is a terminal, plzip exits
+immediately with error status 2 without decompressing the rest of the files.
+A terminal is considered an uncompressed file, and therefore invalid.
 
 @item -f
 @itemx --force
@@ -304,10 +307,11 @@ size, the number of members in the file, and the amount of trailing data (if
 any) are also printed. With @samp{-vv}, the positions and sizes of each
 member in multimember files are also printed.
 
-@samp{-lq} can be used to verify quickly (without decompressing) the
+If any file is damaged, does not exist, can't be opened, or is not regular,
-structural integrity of the files specified. (Use @samp{--test} to verify
+the final exit status will be @w{> 0}. @samp{-lq} can be used to verify
-the data integrity). @samp{-alq} additionally verifies that none of the
+quickly (without decompressing) the structural integrity of the files
-files specified contain trailing data.
+specified. (Use @samp{--test} to verify the data integrity). @samp{-alq}
+additionally verifies that none of the files specified contain trailing data.
 
 @item -m @var{bytes}
 @itemx --match-length=@var{bytes}
@@ -448,8 +452,9 @@ used to compile plzip with the version actually being used at run time and
 exit. Report any differences found. Exit with error status 1 if differences
 are found. A mismatch may indicate that lzlib is not correctly installed or
 that a different version of lzlib has been installed after compiling plzip.
-@w{@samp{plzip -v --check-lib}} shows the version of lzlib being used and
+Exit with error status 2 if LZ_API_VERSION and LZ_version_string don't
-the value of @samp{LZ_API_VERSION} (if defined).
+match. @w{@samp{plzip -v --check-lib}} shows the version of lzlib being used
+and the value of LZ_API_VERSION (if defined).
 @ifnothtml
 @xref{Library version,,,lzlib}.
 @end ifnothtml
@@ -475,9 +480,9 @@ Table of SI and binary prefixes (unit multipliers):
 
 @sp 1
 Exit status: 0 for a normal exit, 1 for environmental problems (file not
-found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or
+found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or invalid
-invalid input file, 3 for an internal consistency error (eg, bug) which
+input file, 3 for an internal consistency error (e.g., bug) which caused
-caused plzip to panic.
+plzip to panic.
 
 
 @node Program design
@@ -486,7 +491,8 @@ caused plzip to panic.
 
 When compressing, plzip divides the input file into chunks and compresses as
 many chunks simultaneously as worker threads are chosen, creating a
-multimember compressed file.
+multimember compressed file. Each chunk is compressed in-place (using the
+same buffer for input and output), reducing the amount of RAM required.
 
 When decompressing, plzip decompresses as many members simultaneously as
 worker threads are chosen. Files that were compressed with lzip will not
@@ -505,14 +511,14 @@ splitter. The muxer collects processed packets from the workers, and
 writes them to the output file.
 
 @verbatim
-                             ,------------,
+                             .------------.
                          ,-->| worker   0 |--,
                          |   `------------'  |
-,-------,   ,----------, |   ,------------,  |   ,-------,   ,--------,
+.-------.   .----------. |   .------------.  |   .-------.   .--------.
 | input |-->| splitter |-+-->| worker   1 |--+-->| muxer |-->| output |
 | file  |   `----------' |   `------------'  |   `-------'   |  file  |
 `-------'                |        ...        |               `--------'
-                         |   ,------------,  |
+                         |   .------------.  |
                          `-->| worker N-1 |--'
                              `------------'
 @end verbatim
@@ -525,92 +531,6 @@ reduced and the decompression speed of large files with many members is
 only limited by the number of processors available and by I/O speed.
 
 
-@node File format
-@chapter File format
-@cindex file format
-
-Perfection is reached, not when there is no longer anything to add, but
-when there is no longer anything to take away.@*
---- Antoine de Saint-Exupery
-
-@sp 1
-In the diagram below, a box like this:
-
-@verbatim
-+---+
-|   | <-- the vertical bars might be missing
-+---+
-@end verbatim
-
-represents one byte; a box like this:
-
-@verbatim
-+==============+
-|              |
-+==============+
-@end verbatim
-
-represents a variable number of bytes.
-
-@sp 1
-A lzip file consists of a series of "members" (compressed data sets).
-The members simply appear one after another in the file, with no
-additional information before, between, or after them.
-
-Each member has the following structure:
-
-@verbatim
-+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-| ID string | VN | DS | LZMA stream | CRC32 |   Data size   |  Member size  |
-+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-@end verbatim
-
-All multibyte values are stored in little endian order.
-
-@table @samp
-@item ID string (the "magic" bytes)
-A four byte string, identifying the lzip format, with the value "LZIP"
-(0x4C, 0x5A, 0x49, 0x50).
-
-@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 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 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.
-
-@item LZMA stream
-The LZMA stream, finished by an end of stream marker. Uses default values
-for encoder properties.
-@ifnothtml
-@xref{Stream format,,,lzip},
-@end ifnothtml
-@ifhtml
-See
-@uref{http://www.nongnu.org/lzip/manual/lzip_manual.html#Stream-format,,Stream format}
-@end ifhtml
-for a complete description.
-
-@item CRC32 (4 bytes)
-Cyclic Redundancy Check (CRC) of the uncompressed original data.
-
-@item Data size (8 bytes)
-Size of the uncompressed original data.
-
-@item Member size (8 bytes)
-Total size of the member, including header and trailer. This field acts
-as a distributed index, allows the verification of stream integrity, and
-facilitates safe recovery of undamaged members from multimember files.
-
-@end table
-
-
 @node Memory requirements
 @chapter Memory required to compress and decompress
 @cindex memory requirements
@@ -709,6 +629,96 @@ data size for each level:
 @end multitable
 
 
+@node File format
+@chapter File format
+@cindex file format
+
+Perfection is reached, not when there is no longer anything to add, but
+when there is no longer anything to take away.@*
+--- Antoine de Saint-Exupery
+
+@sp 1
+In the diagram below, a box like this:
+
+@verbatim
++---+
+|   | <-- the vertical bars might be missing
++---+
+@end verbatim
+
+represents one byte; a box like this:
+
+@verbatim
++==============+
+|              |
++==============+
+@end verbatim
+
+represents a variable number of bytes.
+
+@sp 1
+A lzip file consists of a series of independent "members" (compressed data
+sets). The members simply appear one after another in the file, with no
+additional information before, between, or after them. Each member can
+encode in compressed form up to @w{16 EiB - 1 byte} of uncompressed data.
+The size of a multimember file is unlimited.
+
+Each member has the following structure:
+
+@verbatim
++--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+| ID string | VN | DS | LZMA stream | CRC32 |   Data size   |  Member size  |
++--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+@end verbatim
+
+All multibyte values are stored in little endian order.
+
+@table @samp
+@item ID string (the "magic" bytes)
+A four byte string, identifying the lzip format, with the value "LZIP"
+(0x4C, 0x5A, 0x49, 0x50).
+
+@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 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 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.
+
+@item LZMA stream
+The LZMA stream, finished by an "End Of Stream" marker. Uses default values
+for encoder properties.
+@ifnothtml
+@xref{Stream format,,,lzip},
+@end ifnothtml
+@ifhtml
+See
+@uref{http://www.nongnu.org/lzip/manual/lzip_manual.html#Stream-format,,Stream format}
+@end ifhtml
+for a complete description.
+
+@item CRC32 (4 bytes)
+Cyclic Redundancy Check (CRC) of the original uncompressed data.
+
+@item Data size (8 bytes)
+Size of the original uncompressed data.
+
+@item Member size (8 bytes)
+Total size of the member, including header and trailer. This field acts
+as a distributed index, allows the verification of stream integrity, and
+facilitates the safe recovery of undamaged members from multimember files.
+Member size should be limited to @w{2 PiB} to prevent the data size field
+from overflowing.
+
+@end table
+
+
 @node Trailing data
 @chapter Extra data appended to the file
 @cindex trailing data
@@ -795,7 +805,7 @@ plzip -v file
 
 @sp 1
 @noindent
-Example 3: Like example 1 but the created @samp{file.lz} has a block size of
+Example 3: Like example 2 but the created @samp{file.lz} has a block size of
 @w{1 MiB}. The compression ratio is not shown.
 
 @example
@@ -820,21 +830,10 @@ show status.
 plzip -tv file.lz
 @end example
 
-@sp 1
-@noindent
-Example 6: Compress a whole device in /dev/sdc and send the output to
-@samp{file.lz}.
-
-@example
-  plzip -c /dev/sdc > file.lz
-or
-  plzip /dev/sdc -o file.lz
-@end example
-
 @sp 1
 @anchor{concat-example}
 @noindent
-Example 7: The right way of concatenating the decompressed output of two or
+Example 6: The right way of concatenating the decompressed output of two or
 more compressed files. @xref{Trailing data}.
 
 @example
@@ -846,7 +845,7 @@ Do this instead
 
 @sp 1
 @noindent
-Example 8: Decompress @samp{file.lz} partially until @w{10 KiB} of
+Example 7: Decompress @samp{file.lz} partially until @w{10 KiB} of
 decompressed data are produced.
 
 @example
@@ -855,13 +854,24 @@ plzip -cd file.lz | dd bs=1024 count=10
 
 @sp 1
 @noindent
-Example 9: Decompress @samp{file.lz} partially from decompressed byte at
+Example 8: Decompress @samp{file.lz} partially from decompressed byte at
 offset 10000 to decompressed byte at offset 14999 (5000 bytes are produced).
 
 @example
 plzip -cd file.lz | dd bs=1000 skip=10 count=5
 @end example
 
+@sp 1
+@noindent
+Example 9: Compress a whole device in /dev/sdc and send the output to
+@samp{file.lz}.
+
+@example
+  plzip -c /dev/sdc > file.lz
+or
+  plzip /dev/sdc -o file.lz
+@end example
+
 
 @node Problems
 @chapter Reporting bugs
@@ -875,7 +885,8 @@ for all eternity, if not longer.
 
 If you find a bug in plzip, please send electronic mail to
 @email{lzip-bug@@nongnu.org}. Include the version number, which you can
-find by running @w{@samp{plzip --version}}.
+find by running @w{@samp{plzip --version}} and
+@w{@samp{plzip -v --check-lib}}.
 
 
 @node Concept index

list.cc

@@ -1,5 +1,5 @@
 /* Plzip - Massively parallel implementation of lzip
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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
@@ -73,8 +73,7 @@ int list_files( const std::vector< std::string > & filenames,
       set_retval( retval, lzip_index.retval() );
       continue;
       }
-    if( verbosity >= 0 )
+    if( verbosity < 0 ) continue;
-      {
     const unsigned long long udata_size = lzip_index.udata_size();
     const unsigned long long cdata_size = lzip_index.cdata_size();
     total_comp += cdata_size; total_uncomp += udata_size; ++files;
@@ -86,9 +85,8 @@ int list_files( const std::vector< std::string > & filenames,
       std::fputs( "  uncompressed     compressed   saved  name\n", stdout );
       }
     if( verbosity >= 1 )
-        std::printf( "%s %5ld %6lld ",
+      std::printf( "%s %5ld %6lld ", format_ds( lzip_index.dictionary_size() ),
-                     format_ds( lzip_index.dictionary_size() ), members,
+                   members, lzip_index.file_size() - cdata_size );
-                     lzip_index.file_size() - cdata_size );
     list_line( udata_size, cdata_size, input_filename );
 
     if( verbosity >= 2 && members > 1 )
@@ -105,7 +103,6 @@ int list_files( const std::vector< std::string > & filenames,
       }
     std::fflush( stdout );
     }
-    }
   if( verbosity >= 0 && files > 1 )
     {
     if( verbosity >= 1 ) std::fputs( "                      ", stdout );

lzip.h

@@ -1,5 +1,5 @@
 /* Plzip - Massively parallel implementation of lzip
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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

lzip_index.cc

@@ -1,5 +1,5 @@
 /* Plzip - Massively parallel implementation of lzip
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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

lzip_index.h

@@ -1,5 +1,5 @@
 /* Plzip - Massively parallel implementation of lzip
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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

main.cc

@@ -1,6 +1,6 @@
 /* Plzip - Massively parallel implementation of lzip
    Copyright (C) 2009 Laszlo Ersek.
-   Copyright (C) 2009-2021 Antonio Diaz Diaz.
+   Copyright (C) 2009-2022 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
@@ -19,7 +19,7 @@
    Exit status: 0 for a normal exit, 1 for environmental problems
    (file not found, invalid flags, I/O errors, etc), 2 to indicate a
    corrupt or invalid input file, 3 for an internal consistency error
-   (eg, bug) which caused plzip to panic.
+   (e.g., bug) which caused plzip to panic.
 */
 
 #define _FILE_OFFSET_BITS 64
@@ -39,9 +39,9 @@
 #include <utime.h>
 #include <sys/stat.h>
 #include <lzlib.h>
-#if defined(__MSVCRT__) || defined(__OS2__)
+#if defined __MSVCRT__ || defined __OS2__
 #include <io.h>
-#if defined(__MSVCRT__)
+#if defined __MSVCRT__
 #define fchmod(x,y) 0
 #define fchown(x,y,z) 0
 #define strtoull std::strtoul
@@ -67,12 +67,17 @@
 #error "Environments where CHAR_BIT != 8 are not supported."
 #endif
 
+#if ( defined  SIZE_MAX &&  SIZE_MAX < UINT_MAX ) || \
+    ( defined SSIZE_MAX && SSIZE_MAX <  INT_MAX )
+#error "Environments where 'size_t' is narrower than 'int' are not supported."
+#endif
+
 int verbosity = 0;
 
 namespace {
 
 const char * const program_name = "plzip";
-const char * const program_year = "2021";
+const char * const program_year = "2022";
 const char * invocation_name = program_name;		// default value
 
 const struct { const char * from; const char * to; } known_extensions[] = {
@@ -101,13 +106,14 @@ void show_help( const long num_online )
                "compatible with lzip 1.4 or newer. Plzip uses the compression library lzlib.\n"
                "\nLzip is a lossless data compressor with a user interface similar to the one\n"
                "of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov\n"
-               "chain-Algorithm' (LZMA) stream format, chosen to maximize safety and\n"
+               "chain-Algorithm' (LZMA) stream format and provides a 3 factor integrity\n"
-               "interoperability. Lzip can compress about as fast as gzip (lzip -0) or\n"
+               "checking to maximize interoperability and optimize safety. Lzip can compress\n"
-               "compress most files more than bzip2 (lzip -9). Decompression speed is\n"
+               "about as fast as gzip (lzip -0) or compress most files more than bzip2\n"
-               "intermediate between gzip and bzip2. Lzip is better than gzip and bzip2 from\n"
+               "(lzip -9). Decompression speed is intermediate between gzip and bzip2.\n"
-               "a data recovery perspective. Lzip has been designed, written, and tested\n"
+               "Lzip is better than gzip and bzip2 from a data recovery perspective. Lzip\n"
-               "with great care to replace gzip and bzip2 as the standard general-purpose\n"
+               "has been designed, written, and tested with great care to replace gzip and\n"
-               "compressed format for unix-like systems.\n"
+               "bzip2 as the standard general-purpose compressed format for unix-like\n"
+               "systems.\n"
                "\nPlzip can compress/decompress large files on multiprocessor machines much\n"
                "faster than lzip, at the cost of a slightly reduced compression ratio (0.4\n"
                "to 2 percent larger compressed files). Note that the number of usable\n"
@@ -159,7 +165,7 @@ void show_help( const long num_online )
                "'tar -xf foo.tar.lz' or 'plzip -cd foo.tar.lz | tar -xf -'.\n"
                "\nExit status: 0 for a normal exit, 1 for environmental problems (file\n"
                "not found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or\n"
-               "invalid input file, 3 for an internal consistency error (eg, bug) which\n"
+               "invalid input file, 3 for an internal consistency error (e.g., bug) which\n"
                "caused plzip to panic.\n"
                "\nReport bugs to lzip-bug@nongnu.org\n"
                "Plzip home page: http://www.nongnu.org/lzip/plzip.html\n" );
@@ -178,17 +184,44 @@ void show_version()
   }
 
 
+int check_lzlib_ver()	// <major>.<minor> or <major>.<minor>[a-z.-]*
+  {
+#if defined LZ_API_VERSION && LZ_API_VERSION >= 1012
+  const unsigned char * p = (unsigned char *)LZ_version_string;
+  unsigned major = 0, minor = 0;
+  while( major < 100000 && isdigit( *p ) )
+    { major *= 10; major += *p - '0'; ++p; }
+  if( *p == '.' ) ++p;
+  else
+out: { show_error( "Invalid LZ_version_string in lzlib.h" ); return 2; }
+  while( minor < 100 && isdigit( *p ) )
+    { minor *= 10; minor += *p - '0'; ++p; }
+  if( *p && *p != '-' && *p != '.' && !std::islower( *p ) ) goto out;
+  const unsigned version = major * 1000 + minor;
+  if( LZ_API_VERSION != version )
+    {
+    if( verbosity >= 0 )
+      std::fprintf( stderr, "%s: Version mismatch in lzlib.h: "
+                    "LZ_API_VERSION = %u, should be %u.\n",
+                    program_name, LZ_API_VERSION, version );
+    return 2;
+    }
+#endif
+  return 0;
+  }
+
+
 int check_lib()
   {
-  bool warning = false;
+  int retval = check_lzlib_ver();
   if( std::strcmp( LZ_version_string, LZ_version() ) != 0 )
-    { warning = true;
+    { set_retval( retval, 1 );
       if( verbosity >= 0 )
         std::printf( "warning: LZ_version_string != LZ_version() (%s vs %s)\n",
                      LZ_version_string, LZ_version() ); }
 #if defined LZ_API_VERSION && LZ_API_VERSION >= 1012
   if( LZ_API_VERSION != LZ_api_version() )
-    { warning = true;
+    { set_retval( retval, 1 );
       if( verbosity >= 0 )
         std::printf( "warning: LZ_API_VERSION != LZ_api_version() (%u vs %u)\n",
                      LZ_API_VERSION, LZ_api_version() ); }
@@ -205,15 +238,14 @@ int check_lib()
                  "Using an unknown LZ_API_VERSION\n", LZ_API_VERSION );
 #endif
     }
-  return warning;
+  return retval;
   }
 
 } // end namespace
 
 void Pretty_print::operator()( const char * const msg ) const
   {
-  if( verbosity >= 0 )
+  if( verbosity < 0 ) return;
-    {
   if( first_post )
     {
     first_post = false;
@@ -222,7 +254,6 @@ void Pretty_print::operator()( const char * const msg ) const
     }
   if( msg ) std::fprintf( stderr, "%s\n", msg );
   }
-  }
 
 
 const char * bad_version( const unsigned version )
@@ -260,16 +291,53 @@ void show_header( const unsigned dictionary_size )
 
 namespace {
 
-unsigned long long getnum( const char * const ptr,
+// separate large numbers >= 100_000 in groups of 3 digits using '_'
+const char * format_num3( unsigned long long num )
+  {
+  const char * const si_prefix = "kMGTPEZY";
+  const char * const binary_prefix = "KMGTPEZY";
+  enum { buffers = 8, bufsize = 4 * sizeof (long long) };
+  static char buffer[buffers][bufsize];	// circle of static buffers for printf
+  static int current = 0;
+
+  char * const buf = buffer[current++]; current %= buffers;
+  char * p = buf + bufsize - 1;		// fill the buffer backwards
+  *p = 0;	// terminator
+  if( num > 1024 )
+    {
+    char prefix = 0;			// try binary first, then si
+    for( int i = 0; i < 8 && num >= 1024 && num % 1024 == 0; ++i )
+      { num /= 1024; prefix = binary_prefix[i]; }
+    if( prefix ) *(--p) = 'i';
+    else
+      for( int i = 0; i < 8 && num >= 1000 && num % 1000 == 0; ++i )
+        { num /= 1000; prefix = si_prefix[i]; }
+    if( prefix ) *(--p) = prefix;
+    }
+  const bool split = num >= 100000;
+
+  for( int i = 0; ; )
+    {
+    *(--p) = num % 10 + '0'; num /= 10; if( num == 0 ) break;
+    if( split && ++i >= 3 ) { i = 0; *(--p) = '_'; }
+    }
+  return p;
+  }
+
+
+unsigned long long getnum( const char * const arg,
+                           const char * const option_name,
                            const unsigned long long llimit,
                            const unsigned long long ulimit )
   {
   char * tail;
   errno = 0;
-  unsigned long long result = strtoull( ptr, &tail, 0 );
+  unsigned long long result = strtoull( arg, &tail, 0 );
-  if( tail == ptr )
+  if( tail == arg )
     {
-    show_error( "Bad or missing numerical argument.", 0, true );
+    if( verbosity >= 0 )
+      std::fprintf( stderr, "%s: Bad or missing numerical argument in "
+                    "option '%s'.\n", program_name, option_name );
     std::exit( 1 );
     }
 
@@ -291,7 +359,9 @@ unsigned long long getnum( const char * const ptr,
       }
     if( exponent <= 0 )
       {
-      show_error( "Bad multiplier in numerical argument.", 0, true );
+      if( verbosity >= 0 )
+        std::fprintf( stderr, "%s: Bad multiplier in numerical argument of "
+                      "option '%s'.\n", program_name, option_name );
       std::exit( 1 );
       }
     for( int i = 0; i < exponent; ++i )
@@ -303,21 +373,24 @@ unsigned long long getnum( const char * const ptr,
   if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
   if( errno )
     {
-    show_error( "Numerical argument out of limits." );
+    if( verbosity >= 0 )
+      std::fprintf( stderr, "%s: Numerical argument out of limits [%s,%s] "
+                    "in option '%s'.\n", program_name, format_num3( llimit ),
+                    format_num3( ulimit ), option_name );
     std::exit( 1 );
     }
   return result;
   }
 
 
-int get_dict_size( const char * const arg )
+int get_dict_size( const char * const arg, const char * const option_name )
   {
   char * tail;
   const long bits = std::strtol( arg, &tail, 0 );
   if( bits >= LZ_min_dictionary_bits() &&
       bits <= LZ_max_dictionary_bits() && *tail == 0 )
     return 1 << bits;
-  int dictionary_size = getnum( arg, LZ_min_dictionary_size(),
+  int dictionary_size = getnum( arg, option_name, LZ_min_dictionary_size(),
                                                   LZ_max_dictionary_size() );
   if( dictionary_size == 65535 ) ++dictionary_size;	// no fast encoder
   return dictionary_size;
@@ -499,7 +572,7 @@ bool check_tty_in( const char * const input_filename, const int infd,
       isatty( infd ) )				// for example /dev/tty
     { show_file_error( input_filename,
                        "I won't read compressed data from a terminal." );
-      close( infd ); set_retval( retval, 1 );
+      close( infd ); set_retval( retval, 2 );
       if( program_mode != m_test ) cleanup_and_fail( retval );
       return false; }
   return true;
@@ -613,7 +686,7 @@ void show_progress( const unsigned long long packet_size,
   }
 
 
-#if defined(__MSVCRT__)
+#if defined __MSVCRT__
 #include <windows.h>
 #define _SC_NPROCESSORS_ONLN   1
 #define _SC_THREAD_THREADS_MAX 2
@@ -651,7 +724,6 @@ int main( const int argc, const char * const argv[] )
     { 1 << 25, 273 } };		// -9
   Lzma_options encoder_options = option_mapping[6];	// default = "-6"
   std::string default_output_filename;
-  std::vector< std::string > filenames;
   int data_size = 0;
   int debug_level = 0;
   int num_workers = 0;		// start this many worker threads
@@ -719,6 +791,7 @@ int main( const int argc, const char * const argv[] )
     {
     const int code = parser.code( argind );
     if( !code ) break;					// no more options
+    const char * const pn = parser.parsed_name( argind ).c_str();
     const std::string & sarg = parser.argument( argind );
     const char * const arg = sarg.c_str();
     switch( code )
@@ -728,7 +801,7 @@ int main( const int argc, const char * const argv[] )
                 encoder_options = option_mapping[code-'0']; break;
       case 'a': ignore_trailing = false; break;
       case 'b': break;
-      case 'B': data_size = getnum( arg, 2 * LZ_min_dictionary_size(),
+      case 'B': data_size = getnum( arg, pn, 2 * LZ_min_dictionary_size(),
                                     2 * LZ_max_dictionary_size() ); break;
       case 'c': to_stdout = true; break;
       case 'd': set_mode( program_mode, m_decompress ); break;
@@ -738,23 +811,23 @@ int main( const int argc, const char * const argv[] )
       case 'k': keep_input_files = true; break;
       case 'l': set_mode( program_mode, m_list ); break;
       case 'm': encoder_options.match_len_limit =
-                  getnum( arg, LZ_min_match_len_limit(),
+                  getnum( arg, pn, LZ_min_match_len_limit(),
                                    LZ_max_match_len_limit() ); break;
-      case 'n': num_workers = getnum( arg, 1, max_workers ); break;
+      case 'n': num_workers = getnum( arg, pn, 1, max_workers ); break;
       case 'o': if( sarg == "-" ) to_stdout = true;
                 else { default_output_filename = sarg; } break;
       case 'q': verbosity = -1; break;
-      case 's': encoder_options.dictionary_size = get_dict_size( arg );
+      case 's': encoder_options.dictionary_size = get_dict_size( arg, pn );
                 break;
       case 'S': 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_chk: return check_lib();
-      case opt_dbg: debug_level = getnum( arg, 0, 3 ); break;
+      case opt_dbg: debug_level = getnum( arg, pn, 0, 3 ); break;
-      case opt_in: in_slots = getnum( arg, 1, 64 ); break;
+      case opt_in: in_slots = getnum( arg, pn, 1, 64 ); break;
       case opt_lt: loose_trailing = true; break;
-      case opt_out: out_slots = getnum( arg, 1, 1024 ); break;
+      case opt_out: out_slots = getnum( arg, pn, 1, 1024 ); break;
       default : internal_error( "uncaught option." );
       }
     } // end process options
@@ -763,11 +836,12 @@ int main( const int argc, const char * const argv[] )
     { show_error( "Wrong library version. At least lzlib 1.0 is required." );
       return 1; }
 
-#if defined(__MSVCRT__) || defined(__OS2__)
+#if defined __MSVCRT__ || defined __OS2__
   setmode( STDIN_FILENO, O_BINARY );
   setmode( STDOUT_FILENO, O_BINARY );
 #endif
 
+  std::vector< std::string > filenames;
   bool filenames_given = false;
   for( ; argind < parser.arguments(); ++argind )
     {

testsuite/check.sh

@@ -1,6 +1,6 @@
 #! /bin/sh
 # check script for Plzip - Massively parallel implementation of lzip
-# Copyright (C) 2009-2021 Antonio Diaz Diaz.
+# Copyright (C) 2009-2022 Antonio Diaz Diaz.
 #
 # This script is free software: you have unlimited permission
 # to copy, distribute, and modify it.
@@ -31,6 +31,7 @@ cd "${objdir}"/tmp || framework_failure
 cat "${testdir}"/test.txt > in || framework_failure
 in_lz="${testdir}"/test.txt.lz
 in_em="${testdir}"/test_em.txt.lz
+fox_lz="${testdir}"/fox.lz
 fail=0
 lwarn8=0
 lwarn10=0
@@ -43,6 +44,7 @@ lzlib_1_10() { [ ${lwarn10} = 0 ] &&
 	lwarn10=1 ; }
 
 "${LZIP}" --check-lib				# just print warning
+[ $? != 2 ] || test_failed $LINENO		# unless bad lzlib.h
 printf "testing plzip-%s..." "$2"
 
 "${LZIP}" -fkqm4 in
@@ -106,6 +108,7 @@ done
 printf "LZIP\001-.............................." | "${LZIP}" -t 2> /dev/null
 printf "LZIP\002-.............................." | "${LZIP}" -t 2> /dev/null
 printf "LZIP\001+.............................." | "${LZIP}" -t 2> /dev/null
+rm -f out || framework_failure
 
 printf "\ntesting decompression..."
 
@@ -129,15 +132,21 @@ lines=$("${LZIP}" -tvv "${in_em}" 2>&1 | wc -l) || test_failed $LINENO
 lines=$("${LZIP}" -lvv "${in_em}" | wc -l) || test_failed $LINENO
 [ "${lines}" -eq 11 ] || test_failed $LINENO "${lines}"
 
+"${LZIP}" -cd "${fox_lz}" > fox || test_failed $LINENO
 cat "${in_lz}" > copy.lz || framework_failure
 "${LZIP}" -dk copy.lz || test_failed $LINENO
 cmp in copy || test_failed $LINENO
-printf "to be overwritten" > copy || framework_failure
+cat fox > copy || framework_failure
-"${LZIP}" -d copy.lz 2> /dev/null
+cat "${in_lz}" > out.lz || framework_failure
+rm -f out || framework_failure
+"${LZIP}" -d copy.lz out.lz 2> /dev/null	# skip copy, decompress out
 [ $? = 1 ] || test_failed $LINENO
+cmp fox copy || test_failed $LINENO
+cmp in out || test_failed $LINENO
 "${LZIP}" -df copy.lz || test_failed $LINENO
 [ ! -e copy.lz ] || test_failed $LINENO
 cmp in copy || test_failed $LINENO
+rm -f fox out || framework_failure
 
 printf "to be overwritten" > copy || framework_failure
 "${LZIP}" -df -o copy < "${in_lz}" || test_failed $LINENO
@@ -167,7 +176,7 @@ rm -f copy anyothername.out || framework_failure
 [ $? = 1 ] || test_failed $LINENO
 "${LZIP}" -cdq in "${in_lz}" > copy
 [ $? = 2 ] || test_failed $LINENO
-cat copy in | cmp in - || test_failed $LINENO
+cat copy in | cmp in - || test_failed $LINENO		# copy must be empty
 "${LZIP}" -cdq nx_file.lz "${in_lz}" > copy
 [ $? = 1 ] || test_failed $LINENO
 cmp in copy || test_failed $LINENO
@@ -220,10 +229,17 @@ printf "\ngarbage" >> copy2.lz || framework_failure
 printf "to be overwritten" > copy2 || framework_failure
 "${LZIP}" -df copy2.lz || test_failed $LINENO
 cmp in2 copy2 || test_failed $LINENO
-rm -f in2 copy2 || framework_failure
+rm -f copy2 || framework_failure
 
 printf "\ntesting   compression..."
 
+"${LZIP}" -c -0 in in in -o out3.lz > copy2.lz || test_failed $LINENO
+[ ! -e out3.lz ] || test_failed $LINENO			# override -o
+"${LZIP}" -0f in in --output=copy2.lz || test_failed $LINENO
+"${LZIP}" -d copy2.lz -o out2 || test_failed $LINENO
+cmp in2 out2 || test_failed $LINENO
+rm -f in2 out2 copy2.lz || framework_failure
+
 "${LZIP}" -cf "${in_lz}" > out 2> /dev/null	# /dev/null is a tty on OS/2
 [ $? = 1 ] || test_failed $LINENO
 "${LZIP}" -Fvvm36 -o - "${in_lz}" > out 2> /dev/null || test_failed $LINENO