#!/usr/bin/env perl package feedgnuplot; # for the metacpan indexer use strict; use warnings; use Getopt::Long; use Time::HiRes qw( usleep gettimeofday tv_interval ); use IO::Handle; use IO::Select; use List::Util qw( first ); use List::MoreUtils 'any'; use Scalar::Util qw( looks_like_number ); use Text::ParseWords; # for shellwords use Pod::Usage; use Time::Piece; # Makefile.PL assumes this is in '' my $VERSION = '1.62'; my %options; interpretCommandline(); # list containing the plot data. Each element is a hashref of parameters. # $curve->{datastring} is a string of all the data in this curve that can be # sent directly to gnuplot. $curve->{datastring_meta} is a hashref {domain => # ..., offset_start => ...}. offset_start represents a position in the # datastring where this particular data element begins. As the data is culled # with --xlen, the offsets are preserved by using $curve->{datastring_offset} to # represent the offset IN THE ORIGINAL STRING of the current start of the # datastring my @curves = (); # Maps a curve ID to the corresponding curve my %curveFromID = (); # Whether any new data has arrived since the last replot my $haveNewData; # when the last replot happened my $last_replot_time = [gettimeofday]; # whether the previous replot was timer based my $last_replot_is_from_timer = 1; my $this_replot_is_from_timer; sub getRangeSize { my ($id) = @_; # I'd like to use //, but I guess some people are still on perl 5.8 return exists $options{rangesize_hash}{$id} ? $options{rangesize_hash}{$id} : $options{rangesize_default}; } sub interpretCommandline { # if I'm using a self-plotting data file with a #! line, then $ARGV[0] will contain ALL of the # options and $ARGV[1] will contain the data file to plot. In this case I need to split $ARGV[0] so # that GetOptions() can parse it correctly. On the other hand, if I'm plotting normally (not with # #!) a file with spaces in the filename, I don't want to split the filename. Hopefully this logic # takes care of both those cases. if (exists $ARGV[0] && !-r $ARGV[0]) { unshift @ARGV, shellwords shift @ARGV; } # everything off by default: # do not stream in the data by default # point plotting by default. # no monotonicity checks by default # normal histograms by default $options{ maxcurves } = 100; $options{ histstyle} = 'freq'; # Previously I was using 'legend=s%' and 'curvestyle=s%' for curve addressing. This had cleaner # syntax, but disregarded the order of the given options. This resulted in arbitrarily ordered # curves. I thus make parse these into lists, and then also make hashes, for later use # needed for these to be parsed into an array-ref, these default to [] $options{legend} = []; $options{curvestyle} = []; $options{style} = []; $options{every} = []; $options{using} = []; $options{histogram} = []; $options{x1y2} = []; $options{x2y1} = []; $options{x2y2} = []; $options{extracmds} = []; $options{cmds} = []; $options{set} = []; $options{unset} = []; $options{equation} = []; $options{'equation-below'} = []; $options{'equation-above'} = []; $options{curvestyleall} = ''; $options{styleall} = ''; $options{with} = ''; $options{rangesize} = []; $options{tuplesize} = []; GetOptions(\%options, 'stream:s', 'domain!', 'dataid!', 'vnlog!', 'xticlabels!', '3d!', 'colormap!', 'lines!', 'points!', 'circles', 'legend=s{2}', 'autolegend!', 'xlabel=s', 'x2label=s', 'ylabel=s', 'y2label=s', 'zlabel=s', 'cblabel=s', 'title=s', 'xlen=f', 'xmin=s', 'xmax=s', 'x2min=s', 'x2max=s', 'ymin=f', 'ymax=f', 'y2min=f', 'y2max=f', 'zmin=f', 'zmax=f', 'cbmin=f', 'cbmax=f', 'x2=s@', 'y2=s@', 'x1y2=s@', 'x2y1=s@', 'x2y2=s@', 'style=s{2}', 'curvestyle=s{2}', 'curvestyleall=s', 'styleall=s', 'with=s', 'extracmds=s@', 'cmds=s@', 'set=s@', 'unset=s@', 'every=s{2}', 'everyall=s', 'using=s{2}', 'usingall=s', 'square!', 'square_xy!', 'square-xy!', 'squarexy!', 'hardcopy=s', 'maxcurves=i', 'monotonic!', 'timefmt=s', 'equation=s@', 'equation-below=s@', 'equation-above=s@', 'image=s', 'histogram=s@', 'binwidth=f', 'histstyle=s', 'terminal=s', 'rangesize=s{2}', 'rangesizeall=i', 'tuplesize=s{2}', 'tuplesizeall=i', 'extraValuesPerPoint=i', # deprecated and undocumented 'help', 'dump', 'exit', 'version', 'geometry=s') or exit 1; # handle various cmdline-option errors if ( $options{help} ) { pod2usage( -exitval => 0, -verbose => 1, # synopsis and args -output => \*STDOUT ); } if( $options{version} ) { print "feedgnuplot version $VERSION\n"; exit 0; } # --style and --curvestyle are synonyms, as are --styleall and # --curvestyleall, so fill that in if( $options{styleall} ) { if($options{curvestyleall} ) { $options{curvestyleall} .= " $options{styleall}"; } else { $options{curvestyleall} = $options{styleall}; } delete $options{styleall}; } # various square-xy synonyms $options{'square_xy'} = 1 if $options{'square-xy'} || $options{'squarexy'}; # --extracmds is a synonym for --cmds push @{$options{extracmds}}, @{$options{cmds}}; $options{cmds} = []; push @{$options{curvestyle}}, @{$options{style}}; delete $options{style}; if( $options{curvestyleall} && $options{with} ) { print STDERR "--curvestyleall and --with are mutually exclusive. Please just use one.\n"; exit -1; } if( $options{with} ) { $options{curvestyleall} = "with $options{with}"; delete $options{with}; } if( $options{dataid} && $options{vnlog} ) { print STDERR "--dataid and --vnlog are mutually exclusive. Please just use one.\n"; exit -1; } # expand options that are given as comma-separated lists for my $listkey (qw(histogram x2 y2 x1y2 x2y1 x2y2)) { @{$options{$listkey}} = map split('\s*,\s*', $_), @{$options{$listkey}} if defined $options{$listkey}; } for my $listkey (qw(curvestyle rangesize tuplesize every using)) { next unless defined $options{$listkey}; my @in = @{$options{$listkey}}; my $N = @in / 2; my @out; for my $i (0..$N-1) { my $key = $in[2*$i]; my $value = $in[2*$i + 1]; for my $key_new (split('\s*,\s*', $key)) { push @out, $key_new, $value; } } @{$options{$listkey}} = @out; } # handle x2 == x2y1 and y2 == x1y2 push @{$options{x2y1}}, @{$options{x2}} if defined $options{x2}; push @{$options{x1y2}}, @{$options{y2}} if defined $options{y2}; $options{x2} = []; $options{y2} = []; # convert all tuplesize business to rangesize my $domainsize = $options{'3d'} ? 2 : 1; if (defined $options{tuplesizeall}) { if (defined $options{rangesizeall} ) { print STDERR "Only one of --rangesizeall and --tuplesizeall may be given\n"; exit -1; } $options{rangesizeall} = $options{tuplesizeall} - $domainsize; delete $options{tuplesizeall}; } if (defined $options{tuplesize}) { $options{rangesize} //= []; my $N = @{$options{tuplesize}} / 2; for my $i (0..$N-1) { $options{tuplesize}[2*$i + 1] -= $domainsize; } push @{$options{rangesize}}, @{$options{tuplesize}}; delete $options{tuplesize}; } # If we're plotting histograms, then set the default histogram options for # each histogram curve # # Apply this to plain (non-cumulative) histograms if( !$options{curvestyleall} && $options{histstyle} =~ /freq|fnorm/ ) { for my $hist_curve(@{$options{histogram}}) { # If we don't specify any options specifically for this histogram, use # the defaults: filled boxes with borders if( !any { $options{curvestyle}[$_*2] eq $hist_curve } 0..(@{$options{curvestyle}}/2 - 1) ) { push @{$options{curvestyle}}, ($hist_curve, 'with boxes fill solid border lt -1'); } } } # --legend and --curvestyle options are conceptually hashes, but are parsed as # arrays in order to preserve the ordering. I parse both of these into hashes # because those are useful to have later. After this I can access individual # legends with $options{legend_hash}{curveid} for my $listkey (qw(legend curvestyle rangesize every using)) { $options{"${listkey}_hash"} = {}; my $n = scalar @{$options{$listkey}}/2; foreach my $idx (0..$n-1) { $options{"${listkey}_hash"}{$options{$listkey}[$idx*2]} = $options{$listkey}[$idx*2 + 1]; } } if ( defined $options{hardcopy} && defined $options{stream} ) { print STDERR "--stream doesn't make sense together with --hardcopy\n"; exit -1; } if ( defined $options{rangesizeall} && defined $options{extraValuesPerPoint} ) { print STDERR "Only one of --rangesizeall and --extraValuesPerPoint may be given\n"; exit -1; } # I now set up the rangesize to always be # # $options{rangesize_hash}{$id} // $options{rangesize_default} # # which is available as getRangeSize($id) if ( $options{rangesizeall} ) { $options{rangesize_default} = $options{rangesizeall}; } else { $options{rangesize_default} = 1; $options{rangesize_default} += $options{extraValuesPerPoint} if ($options{extraValuesPerPoint}); $options{rangesize_default}++ if ($options{colormap}); $options{rangesize_default}++ if ($options{circles} ); } # parse stream option. Allowed only numbers >= 0 or 'trigger'. After this code # $options{stream} is # -1 for triggered replotting # >0 for timed replotting # undef if not streaming # # Note that '0' is not allowed, so !$options{stream} will do the expected # thing if(defined $options{stream}) { # if no streaming period is given, default to 1Hz. $options{stream} = 1 if $options{stream} eq ''; if( !looks_like_number $options{stream} ) { if($options{stream} eq 'trigger') { $options{stream} = 0; } else { print STDERR "--stream can only take in values >=0 or 'trigger'\n"; exit -1; } } if ( $options{stream} == 0 ) { $options{stream} = -1; } elsif ( $options{stream} <= 0) { print STDERR "--stream can only take in values >=0 or 'trigger'\n"; exit -1; } } if ($options{colormap}) { # colormap styles all curves with palette. Seems like there should be a way to do this with a # global setting, but I can't get that to work $options{curvestyleall} .= ' palette'; } if ( defined $options{binwidth} && !@{$options{histogram}} ) { print STDERR "--binwidth doesn't make sense without any histograms\n"; exit -1; } if ( $options{'3d'} ) { if ( !$options{domain} ) { print STDERR "--3d only makes sense with --domain\n"; exit -1; } if ( $options{timefmt} ) { print STDERR "--3d makes no sense with --timefmt\n"; exit -1; } if ( defined $options{x2min} || defined $options{x2max} || defined $options{y2min} || defined $options{y2max} || @{$options{x1y2}} || @{$options{x2y1}} || @{$options{x2y2}} ) { print STDERR "--3d does not make sense with --x2... or --y2...\n"; exit -1; } if ( defined $options{xlen} ) { print STDERR "--3d does not make sense with --xlen\n"; exit -1; } if ( defined $options{monotonic} ) { print STDERR "--3d does not make sense with --monotonic\n"; exit -1; } if ( @{$options{histogram}} ) { print STDERR "--3d does not make sense with histograms\n"; exit -1; } if ( defined $options{circles} ) { print STDERR "--3d does not make sense with circles (gnuplot doesn't support this)\n"; exit -1; } if ( $options{xticlabels} ) { print STDERR "--3d makes no sense with --xticlabels\n"; exit -1; } } else { if ( $options{timefmt} && !$options{domain} && !@{$options{histogram}} ) { print STDERR "--timefmt makes sense only with --domain or --histogram\n"; exit -1; } if ( defined $options{square_xy} ) { print STDERR "--square_xy only makes sense with --3d\n"; exit -1; } if ( $options{xticlabels} && @{$options{histogram}}) { print STDERR "--histogram makes no sense with --xticlabels\n"; exit -1; } for my $hist_curve(@{$options{histogram}}) { my $hist_dim = getRangeSize($hist_curve); if( $hist_dim != 1 ) { print STDERR "I only support 1D histograms, but curve '$hist_curve' has '$hist_dim'-D data\n"; exit -1; } } } if(defined $options{xlen} && !$options{stream} ) { print STDERR "--xlen does not make sense without --stream\n"; exit -1; } if($options{stream} && defined $options{xlen} && ( defined $options{xmin} || defined $options{xmax}) && !defined $options{histogram}) { print STDERR "With --stream and --xlen the X bounds are set, so neither --xmin nor --xmax make sense\n"; exit -1; } # --xlen implies an order to the data, so I force monotonicity $options{monotonic} = 1 if defined $options{xlen}; if( $options{histstyle} !~ /freq|cum|uniq|cnorm|fnorm/ ) { print STDERR "unknown histstyle. Allowed are 'freq...', 'fnorm...', 'cum...', 'uniq...', 'cnorm...'\n"; exit -1; } # deal with timefmt if ( $options{timefmt} ) { # I need to compute a regex to match the time field and I need to count how # many whilespace-separated fields there are. # strip leading and trailing whitespace $options{timefmt} =~ s/^\s*//; $options{timefmt} =~ s/\s*$//; my $Nfields = () = split /\s+/, $options{timefmt}, -1; $options{timefmt_Ncols} = $Nfields; # make sure --xlen is an integer. With a timefmt xlen goes through strptime # and strftime, and those are integer-only if( defined $options{xlen} ) { if( $options{xlen} - int($options{xlen}) ) { print STDERR "When streaming --xlen MUST be an integer. Rounding up to the nearest second\n"; $options{xlen} = 1 + int($options{xlen}); } } } # deal with --image. I just fill in --equation, and reverse the y extents if # none are explicitly given if( defined $options{image} ) { # images generally have the origin at the top-left instead of the # bottom-left, so given nothing else, I flip the y axis if( !defined $options{xmin} && !defined $options{xmax} && !defined $options{ymin} && !defined $options{ymax} && ! any { /^ *xrange\b/ } @{$options{set}} && ! any { /^ *yrange\b/ } @{$options{set}} ) { push @{$options{set}}, "xrange [:] noextend"; push @{$options{set}}, "yrange [:] reverse noextend"; } if ( ! -r $options{image} ) { die "Couldn't read image '$options{image}'"; } unshift @{$options{equation}}, qq{"$options{image}" binary filetype=auto flipy with rgbimage title "$options{image}"}; delete $options{image}; } # --equation-below is a synonym of --equation push @{$options{equation}}, @{$options{'equation-below'}}; @{$options{'equation-below'}} = []; } sub getGnuplotVersion { open(GNUPLOT_VERSION, 'gnuplot --version |') or die "Couldn't run gnuplot"; my ($gnuplotVersion) = =~ /gnuplot\s*(\d*\.\d*)/; if (!$gnuplotVersion) { print STDERR "Couldn't find the version of gnuplot. Does it work? Trying anyway...\n"; $gnuplotVersion = 0; } close(GNUPLOT_VERSION); return $gnuplotVersion; } sub sendRangeCommand { my ($name, $min, $max) = @_; return unless defined $min || defined $max; if( defined $min ) { $min = "\"$min\""; } else { $min = ''; } if( defined $max ) { $max = "\"$max\""; } else { $max = ''; } my $cmd = "set $name [$min:$max]\n"; print PIPE $cmd; } sub makeDomainNumeric { my ($domain0) = @_; if ( $options{timefmt} ) { my $timepiece = Time::Piece->strptime( $domain0, $options{timefmt} ) or die "Couldn't parse time format. String '$domain0' doesn't fit format '$options{timefmt}'"; return $timepiece->epoch(); } return $domain0; } my $prev_timed_replot_time = [gettimeofday]; my $pipe_in; my $selector; my $line_number = 0; my $is_stdin = !@ARGV; # read stdin only if no data files given on the cmdline sub openNextFile { my $fd; if($is_stdin) { $fd = IO::Handle->new(); $fd->fdopen(fileno(STDIN), "r") or die "Couldn't open STDIN"; } else { my $filename = shift @ARGV; $fd = IO::File->new($filename, "r") or die "Couldn't open file '$filename'"; } my $selector = IO::Select->new( $fd ); return ($fd, $selector); } sub getNextLine { sub getline_internal { while(1) { my $line = $pipe_in->getline(); if( !$is_stdin && !defined $line && $pipe_in->eof() && @ARGV) { # I got to the end of one file, so open the next one (which I'm # sure exists) ($pipe_in, $selector) = openNextFile(); next; } return $line; } } if( !defined $pipe_in ) { ($pipe_in, $selector) = openNextFile(); } while(1) { $this_replot_is_from_timer = undef; # if we're not streaming, or we're doing triggered-only replotting, simply # do a blocking read if (! $options{stream} || $options{stream} < 0) { $line_number++; return getline_internal(); } my $now = [gettimeofday]; my $time_remaining = $options{stream} - tv_interval($prev_timed_replot_time, $now); if ( $time_remaining < 0 ) { $prev_timed_replot_time = $now; $this_replot_is_from_timer = 1; return 'replot'; } if ($selector->can_read($time_remaining)) { $line_number++; return getline_internal(); } } } sub mainThread { local *PIPE; my $outputfile; my $outputfileType; if( defined $options{hardcopy}) { $outputfile = $options{hardcopy}; if( $outputfile =~ /^[^|] # starts with anything other than | .* # stuff in the middle \.(eps|ps|pdf|png|svg|gp)$/ix) # ends with a known extension { $outputfileType = lc $1; } my %terminalOpts = ( eps => 'postscript noenhanced solid color eps', ps => 'postscript noenhanced solid color landscape 12', pdf => 'pdfcairo noenhanced solid color font ",12" size 8in,6in', png => 'pngcairo noenhanced size 1024,768 transparent crop font ",12"', svg => 'svg noenhanced solid dynamic size 800,600 font ",14"', gp => 'gp'); if( !defined $options{terminal} && defined $outputfileType && $terminalOpts{$outputfileType} ) { $options{terminal} = $terminalOpts{$outputfileType}; } die "Asked to plot to file '$outputfile', but I don't know which terminal to use, and no --terminal given" unless $options{terminal}; } sub gpterminal { return defined $options{terminal} && $options{terminal} eq 'gp'; } sub datadump_only { return exists $options{dump} || gpterminal(); } sub search_PATH { for my $pathdir (File::Spec->path()) { my $gnuplot_execpath = File::Spec->catfile($pathdir, $_[0]); return $gnuplot_execpath if -x $gnuplot_execpath && ! -d $gnuplot_execpath; } return undef; } if(datadump_only()) { if(gpterminal()) { open PIPE, '>', $outputfile; my $gnuplotpath = search_PATH('gnuplot'); if(!defined $gnuplotpath) { print STDERR "Couldn't find the gnuplot executable path. Creating .gp file still, but omitting #!. This will NOT be self-executable"; } else { chmod 0755, $outputfile; print PIPE "#!$gnuplotpath\n"; } } else { *PIPE = *STDOUT; } } else { my $dopersist = ''; if ( getGnuplotVersion() >= 4.3 && # --persist not available before this # --persist is needed for the "half-alive" state (see documentation for # --exit). This state is only used with these options: !$options{stream} && $options{exit}) { $dopersist = '--persist'; } # We trap SIGINT to kill the data input, but keep the plot up. see # documentation for --exit if ($options{stream} && !$options{exit}) { $SIG{INT} = sub { print STDERR "$0 received SIGINT. Send again to quit\n"; $SIG{INT} = undef; }; } my $geometry = defined $options{geometry} ? "-geometry $options{geometry}" : ''; open PIPE, "|gnuplot $geometry $dopersist" or die "Can't initialize gnuplot\n"; autoflush PIPE 1; } if(!gpterminal()) { print PIPE "set terminal $options{terminal}\n" if $options{terminal}; print PIPE "set output \"$outputfile\"\n" if $outputfile; } # set up plotting style my $style = ''; if($options{lines}) { $style .= 'lines';} if($options{points}) { $style .= 'points';} if($options{circles}) { $options{curvestyleall} = "with circles $options{curvestyleall}"; } # Required to ignore all lines that have '-' values, such as may come from # vnl-filter -p "dx=diff(x)" ... output. For instance, this plot is broken # without this extra line: # (echo '# x'; seq 5) | vnl-filter --noskipempty -p 'd=diff(x)' | ./feedgnuplot --lines print PIPE "set datafile missing \"-\"\n"; print PIPE "set style data $style\n" if $style; print PIPE "set grid\n"; print(PIPE "set xlabel \"$options{xlabel }\"\n") if defined $options{xlabel}; print(PIPE "set x2label \"$options{x2label}\"\n") if defined $options{x2label}; print(PIPE "set ylabel \"$options{ylabel }\"\n") if defined $options{ylabel}; print(PIPE "set y2label \"$options{y2label}\"\n") if defined $options{y2label}; print(PIPE "set zlabel \"$options{zlabel }\"\n") if defined $options{zlabel}; print(PIPE "set cblabel \"$options{cblabel}\"\n") if defined $options{cblabel}; print(PIPE "set title \"$options{title }\"\n") if defined $options{title}; if($options{square}) { # set a square aspect ratio. Gnuplot does this differently for 2D and 3D plots if(! $options{'3d'}) { print(PIPE "set size ratio -1\n"); } else { print(PIPE "set view equal xyz\n"); } } if($options{square_xy}) { print(PIPE "set view equal xy\n"); } for my $what_options_prefix_suffix ( ['curvestyle', 'extraoptions', '', ' ' ], ['every', 'everyoptions', 'every ', ' ' ], ['using', 'usingoptions', 'using ', ' ' ], ['legend', 'title', '', '' ]) { my ($what, $options, $prefix, $suffix) = @$what_options_prefix_suffix; # @{$options{$what}} is a list where consecutive pairs are (curveID, style). if (@{$options{$what}}) { my $n = scalar @{$options{$what}}/2; foreach my $idx (0..$n-1) { addOption($options{$what}[$idx*2 ], $options, $prefix . $options{$what}[$idx*2 + 1] . $suffix); } } } addOption($_, 'extraoptions', 'axes x1y2 ') foreach (@{$options{x1y2}}); addOption($_, 'extraoptions', 'axes x2y1 ') foreach (@{$options{x2y1}}); addOption($_, 'extraoptions', 'axes x2y2 ') foreach (@{$options{x2y2}}); # timefmt my $histcol; if( $options{timefmt} ) { print(PIPE "set timefmt '$options{timefmt}'\n"); print(PIPE "set xdata time\n"); $histcol = qq{timecolumn(2,"$options{timefmt}")}; } else { $histcol = '$2'; } # set up histograms $options{binwidth} ||= 1; # if no binwidth given, set it to 1 print PIPE "set boxwidth $options{binwidth}\n" . "histbin(x) = $options{binwidth} * floor(0.5 + x/$options{binwidth})\n"; foreach my $id (@{$options{histogram}}) { # With histograms I have 2d plots with rangesize=1. I thus give gnuplot two # values for each point: a domain and a range. For histograms I ignore the # domain, so I get the statistics of the 2nd column: $2 addOption($id, 'usingoptions', 'using (histbin(' . $histcol . ')):(1.0) smooth ' . $options{histstyle}, 'do-not-override'); } if(@{$options{x2y1}} || @{$options{x2y2}}) { print PIPE "set xtics nomirror\n"; print PIPE "set x2tics\n"; # if any of the ranges are given, set the range sendRangeCommand( "x2range", $options{x2min}, $options{x2max} ); } if(@{$options{x1y2}} || @{$options{x2y2}}) { print PIPE "set ytics nomirror\n"; print PIPE "set y2tics\n"; # if any of the ranges are given, set the range sendRangeCommand( "y2range", $options{y2min}, $options{y2max} ); } # if any of the ranges are given, set the range sendRangeCommand( "xrange", $options{xmin}, $options{xmax} ); sendRangeCommand( "yrange", $options{ymin}, $options{ymax} ); sendRangeCommand( "zrange", $options{zmin}, $options{zmax} ); if($options{colormap}) { # legacy behavior. Nobody should really be using --colormap sendRangeCommand( "cbrange", $options{zmin}, $options{zmax} ); } else { sendRangeCommand( "cbrange", $options{cbmin},$options{cbmax}); } # add the extra global options print(PIPE "$_\n") foreach (@{$options{extracmds}}); print(PIPE "set $_\n") foreach (@{$options{set}}); print(PIPE "unset $_\n") foreach (@{$options{unset}}); # latest domain variable present in our data my $latestX; # column headers from vnlog my @vnlog_headers; if($options{vnlog}) { require Vnlog::Parser; require Vnlog::Util; if ( !defined $pipe_in ) { ($pipe_in, $selector) = openNextFile(); } my $parser = Vnlog::Parser->new(); while (defined ($_ = Vnlog::Util::get_unbuffered_line($pipe_in))) { if ( !$parser->parse($_) ) { die "Error parsing vnlog: $parser->{error}; looking at line '$_'"; } my $keys = $parser->getKeys(); if (defined $keys) { @vnlog_headers = @$keys; last; } } if(!@vnlog_headers) { die "Looked through all of the first file, and never saw a vnlog legend"; } } # The x-axis domain represented as a number. This is exactly the same as # $domain[0] unless the x-axis domain uses a timefmt. Then this is the # number of seconds since the UNIX epoch. my $domain0_numeric; while( defined ($_ = getNextLine()) ) { next if /^#/o; if( $options{stream} ) { if(/^clear/o ) { clearCurves(); next; } if(/^replot/o ) { replot( $domain0_numeric ); next; } last if /^exit/o; } # parse the incoming data lines. The format is # x xticlabels id0 dat0 id1 dat1 .... # where idX is the ID of the curve that datX corresponds to # # - $options{domain} indicates whether the initial 'x' is given or not (if not, the line # number is used) # # - $options{xticlabels} indicates whether the 'xticlabels' is given or not # # - $options{dataid} indicates whether idX is given or not (if not, the point order in the # line is used) # # - 3d plots require $options{domain}, and dictate "x y" for the domain instead of just "x" # The domain of the current point my @domain; # The x-axis tic label for this point. Used only if --xticlabels my $xticlabel = ''; my @fields = split; my $i_column = 0; if($options{domain}) { if( $options{timefmt} ) { # no point in doing anything unless I have at least the domain and # 1 piece of data next if @fields < $options{timefmt_Ncols}+1; $domain[0] = join (' ', splice( @fields, 0, $options{timefmt_Ncols}) ); $domain0_numeric = makeDomainNumeric( $domain[0] ); $i_column += $options{timefmt_Ncols}; } elsif(!$options{'3d'}) { # no point in doing anything unless I have at least the domain and # 1 piece of data next if @fields < 1+1; $domain[0] = $domain0_numeric = shift @fields; $i_column += 1; } else { # no point in doing anything unless I have at least the domain and # 1 piece of data next if @fields < 2+1; @domain = splice(@fields, 0, 2); $i_column += 2; } if( $options{monotonic} ) { if( defined $latestX && $domain0_numeric < $latestX ) { # the x-coordinate of the new point is in the past, so I wipe out # all the data and start anew. Before I wipe the old data, I # replot the old data replot( $domain0_numeric ); clearCurves(); $latestX = undef; } else { $latestX = $domain0_numeric; } } } else { $domain[0] = $line_number; $domain0_numeric = $line_number; } if ($options{xticlabels}) { # no point in doing anything unless I have at least the xticlabel # and 1 piece of data next if @fields < 1+1; $xticlabel = '"' . (shift @fields) . '"'; $i_column += 1; } my $id = -1; while(@fields) { if ($options{dataid}) { $id = shift @fields; } elsif($options{vnlog} ) { if( $i_column >= @vnlog_headers ) { # Got more columns than vnlog headers. The data is probably # bogus, but I don't want to barf at the user, so I silently # ignore the data last; } $id = $vnlog_headers[$i_column]; } else { $id++; } my $rangesize = getRangeSize($id); last if @fields < $rangesize; # Done. The curve is created. I add a point to the plot. my $curve = getCurve($id); push @{$curve->{datastring_meta}}, { offset_start => length( $curve->{datastring} ) + $curve->{datastring_offset}, domain => $domain0_numeric }; $curve->{datastring} .= join(' ', @domain, $xticlabel, splice( @fields, 0, $rangesize ) ) . "\n"; $haveNewData = 1; $i_column += $rangesize; } } # finished reading in all. Plot what we have plotStoredData() unless $options{stream} && $options{exit}; if ( defined $options{hardcopy} && !gpterminal()) { print PIPE "set output\n"; # sleep until the plot file exists, and it is closed. Sometimes the output # is still being written at this point. If the output filename starts with # '|', gnuplot pipes the output to that process, instead of writing to a # file. In that case I don't make sure the file exists, since there IS no # file if( $options{hardcopy} !~ /^\|/ ) { usleep(100_000) until -e $outputfile; usleep(100_000) until(system("fuser -s \"$outputfile\"")); } print "Wrote output to $outputfile\n"; return; } # data exhausted. If we're killed now, then we should peacefully die. if($options{stream} && !$options{exit}) { print STDERR "Input data exhausted\n"; $SIG{INT} = undef; } # we persist gnuplot, so we shouldn't need this sleep. However, once # gnuplot exits, but the persistent window sticks around, you can no # longer interactively zoom the plot. So we still sleep if(gpterminal()) { print PIPE "pause mouse close\n"; close PIPE; } elsif(!($options{dump} || $options{exit})) { print PIPE "pause mouse close\n"; } } sub pruneOldData { my ($oldestx) = @_; foreach my $curve (@curves) { next unless $curve->{datastring}; my $meta = $curve->{datastring_meta}; my $firstInWindow = first {$meta->[$_]{domain} >= $oldestx} 0..$#$meta; if ( !defined $firstInWindow ) { # everything is too old. Clear out all the data $curve->{datastring} = ''; $curve->{datastring_meta} = []; $curve->{datastring_offset} = 0; } elsif ( $firstInWindow >= 2 ) { # clear out everything that's too old, except for one point. This point # will be off the plot, but if we're plotting lines there will be a # connecting line to it. Some of the line will be visible substr( $curve->{datastring}, 0, $meta->[$firstInWindow-1]{offset_start} - $curve->{datastring_offset}, '' ); $curve->{datastring_offset} = $meta->[$firstInWindow-1]{offset_start}; } } } sub plotStoredData { # get the options for those curves that havse any data my @nonemptyCurves = grep { $_->{datastring} } @curves; my @extraopts = map {$_->{options}} @nonemptyCurves; my @components = (@{$options{equation}}, map({ "'-' $_" } @extraopts), @{$options{'equation-above'}}); my $body = join(',', @components); if($options{'3d'}) { print PIPE "splot $body\n"; } else { print PIPE "plot $body\n"; } foreach my $curve (@nonemptyCurves) { print PIPE $curve->{datastring}; print PIPE "e\n"; } } sub updateCurveOptions { # generates the 'options' string for a curve, based on its legend title and its other options # These could be integrated into a single string, but that raises an issue in the no-title # case. When no title is specified, gnuplot will still add a legend entry with an unhelpful '-' # label. Thus I explicitly do 'notitle' for that case my ($curve, $id) = @_; # use the given title, unless we're generating a legend automatically. Given titles # override autolegend my $title; if(defined $curve->{title} && length($curve->{title})) { $title = $curve->{title}; } elsif( $options{autolegend} ) { $title = $id; } my $titleoption = defined $title ? "title \"$title\"" : "notitle"; my $usingoptions = $curve->{usingoptions}; if( length($usingoptions) ) { # user specified a 'using' option. I just do that, and don't look at # anything else } elsif( $options{timefmt} ) { # with --timefmt I need an explicit 'using' specification. I specify the # columns as 1:2:3..... I need the right number of columns (this is given # as 1 + rangesize). I also need to start the range at the first column # past the timefmt my @rest = map {$_ + $options{timefmt_Ncols}} (1..getRangeSize($id)); $usingoptions = "using 1:" . join(':', @rest); } elsif( $options{xticlabels}) { # if no --domain: I ignore the sequential first column, and I do # 3:4...:xticlabels(2) # if --domain: I do NOT ignore the domain, and I do # 1:3:4...:xticlabels(2) my @rest = map {$_ + 2} (1..getRangeSize($id)); if ( $options{domain}) { $usingoptions = "using 1:" . join(':', @rest) . ":xticlabels(2)"; } else { $usingoptions = "using " . join(':', @rest) . ":xticlabels(2)"; } } $curve->{options} = "$curve->{everyoptions} $usingoptions $titleoption $curve->{extraoptions}"; } sub getCurve { # This function returns the curve corresponding to a particular label, creating a new curve if # necessary if(scalar @curves >= $options{maxcurves}) { print STDERR "Tried to exceed the --maxcurves setting.\n"; print STDERR "Invoke with a higher --maxcurves limit if you really want to do this.\n"; exit -1; } my ($id) = @_; if( !exists $curveFromID{$id} ) { my $curve = {# if we have a catch-all style and no specific style, use # the catch-all style extraoptions => (!exists $options{curvestyle_hash}{$id} && exists $options{curvestyleall}) ? "$options{curvestyleall} " : ' ', everyoptions => (!exists $options{every_hash}{$id} && exists $options{everyall}) ? "every $options{everyall} " : ' ', usingoptions => (!exists $options{using_hash}{$id} && exists $options{usingall}) ? "using $options{usingall} " : '', title => '', datastring => '', datastring_meta => [], datastring_offset => 0}; # push a curve with no data and no options push @curves, $curve; # push a curve with no data and no options $curveFromID{$id} = $curve; updateCurveOptions($curve, $id); # --xlen has a meaning if we're not plotting histograms at all or if we're # plotting ONLY histograms. If we're doing both at the same time, there's no # consistent way to assign meaning to xlen if ( defined $options{xlen} && # have at least some histograms @{$options{histogram}} && # there are more curves than histogram curves, i.e. there're some # non-histogram curves @curves > @{$options{histogram}} ) { print STDERR "--xlen only makes sense when plotting ONLY histograms or ONLY NON-histograms\n"; exit -1; } return $curve; } return $curveFromID{$id}; } sub addOption { my ($id, $which, $str, $do_not_override) = @_; my $curve = getCurve($id); if(!$do_not_override || length($curve->{$which})==0) { $curve->{$which} .= $str; updateCurveOptions($curve, $id); } } # remove all the curve data sub clearCurves { foreach my $curve(@curves) { $curve->{datastring} = ''; $curve->{datastring_meta} = []; $curve->{datastring_offset} = 0; } } sub replot { return unless $haveNewData; $haveNewData = undef; return if !$options{stream}; # The logic involving domain rollover replotting due to --monotonic is a bit # tricky. I want this: # if( domain rolls over slowly ) # { # should update on a timer; # when the domain rolls over, --monotonic should force a replot # } # if( domain rolls over quickly ) # { # should update when the domain rolls over, # at most as quickly as the timer indicates # } my ($domain0_numeric) = @_; my $now = [gettimeofday]; if( # If there is no replot timer at all, replot at any indication $options{stream} < 0 || # if the last replot was timer-based, but this one isn't, force a replot. # This makes sure that a replot happens for a domain rollover shortly # after a timer replot !$this_replot_is_from_timer && $last_replot_is_from_timer || # if enough time has elapsed since the last replot, it's ok to replot tv_interval ( $last_replot_time, $now ) > 0.8*$options{stream} ) { # ok, then. We really need to replot if ( defined $options{xlen} ) { # we have an --xlen, so we need to clean out the old data pruneOldData( $domain0_numeric - $options{xlen} ); my ($xmin, $xmax) = ($domain0_numeric - $options{xlen}, $domain0_numeric); if ( defined $options{timefmt} ) { # if we're using a timefmt, I need to convert my xmin range from # seconds-since-the-epoch BACK to the timefmt. Sheesh ($xmin, $xmax) = map {Time::Piece->strptime( $_, '%s' )->strftime( $options{timefmt} ) } ($xmin, $xmax); } # if we have any histograms, then I'm not really visualizing the domain at # all, and I don't set the range. sendRangeCommand( "xrange", $xmin, $xmax ) unless @{$options{histogram}}; } plotStoredData(); # update replot state $last_replot_time = $now; $last_replot_is_from_timer = $this_replot_is_from_timer; } } mainThread(); =head1 NAME feedgnuplot - General purpose pipe-oriented plotting tool =head1 SYNOPSIS Simple plotting of piped data: $ seq 5 | awk '{print 2*$1, $1*$1}' 2 1 4 4 6 9 8 16 10 25 $ seq 5 | awk '{print 2*$1, $1*$1}' | feedgnuplot \ --terminal 'dumb 80,40' --exit \ --lines \ --points \ --title "Test plot" \ --y2 1 \ --unset key \ --unset grid Test plot 10 +-----------------------------------------------------------------+ 25 | + + + + + + + ##*| | ##* | | ## * | 9 |-+ ## ** | | ## * | | ## * | | ## ** +-| 20 8 |-+ B * | | ## * | | ## ** | | ## * | | ## A | 7 |-+ ## ** | | ## ** +-| 15 | ## * | | ## ** | 6 |-+ #B ** | | ## ** | | ## * | | ## ** +-| 10 5 |-+ ## ** | | ## *A | | ## ** | | ## ** | 4 |-+ B *** | | ## ** | | ## ** +-| 5 | ## ** | | ## **A* | 3 |-+ ## **** | | ##**** | | ##** | |## + + + + + + + | 2 +-----------------------------------------------------------------+ 0 1 1.5 2 2.5 3 3.5 4 4.5 5 Simple real-time plotting example: plot how much data is received on the wlan0 network interface in bytes/second. This plot updates at 1Hz, and shows the last 10sec of history. The plot shown here is the final state of a sample run $ while true; do sleep 1; cat /proc/net/dev; done \ | gawk '/wlan0/ {if(b) {print $2-b; N++; fflush()} b=$2} N==15 {exit}' \ | feedgnuplot \ --terminal 'dumb 80,40' --exit \ --lines \ --title "wlan0 throughput" \ --stream \ --xlen 10 \ --ylabel 'Bytes/sec' \ --xlabel seconds \ --unset key \ --unset grid wlan0 throughput 300000 +---------------------------------------------------------------+ | + + + + + | | | | | | * | 250000 |-+ * +-| | ** | | * * | | * * | | * * | | * * | 200000 |-+ * * +-| | * * | | * * | | * * | | * * | 150000 |-+ * *+-| | * * | | * * | | * * | | * * | | * * | 100000 |-+ * *-| | * * | | * *| | ** * *| | *** * * *| 50000 |-+ *** * **** * +*| | ** ** ***** ** * | | ** * *** ** * | | ***** * ***** ** | |** *** | | + + + + + | 0 +---------------------------------------------------------------+ 6 8 10 12 14 seconds =head1 DESCRIPTION This is a flexible, command-line-oriented frontend to Gnuplot. It creates plots from data coming in on STDIN or given in a filename passed on the commandline. Various data representations are supported, as is hardcopy output and streaming display of live data. For a tutorial and a gallery please see the guide at L A simple example: $ seq 5 | awk '{print 2*$1, $1*$1}' | feedgnuplot You should see a plot with two curves. The C command generates some data to plot and the C reads it in from STDIN and generates the plot. The C invocation is just an example; more interesting things would be plotted in normal usage. No commandline-options are required for the most basic plotting. Input parsing is flexible; every line need not have the same number of points. New curves will be created as needed. The most commonly used functionality of gnuplot is supported directly by the script. Anything not directly supported can still be done with options such as C<--set>, C<--cmds> C<--style>, etc. Arbitrary gnuplot commands can be passed in with C<--cmds>. For example, to turn off the grid, you can pass in C<--cmds 'unset grid'>. Commands C<--set> and C<--unset> exists to provide nicer syntax, so this is equivalent to passing C<--unset grid>. As many of these options as needed can be passed in. To add arbitrary curve styles, use C<--style curveID extrastyle>. Pass these more than once to affect more than one curve. To apply an extra style to I the curves that lack an explicit C<--style>, pass in C<--styleall extrastyle>. In the most common case, the extra style is C. To support this more simply, you can pass in C<--with something> instead of C<--styleall 'with something'>. C<--styleall> and C<--with> are mutually exclusive. Furthermore any curve-specific C<--style> overrides the global C<--styleall> or C<--with> setting. =head2 Data formats By default, each value present in the incoming data represents a distinct data point, as demonstrated in the original example above (we had 10 numbers in the input and 10 points in the plot). If requested, the script supports more sophisticated interpretation of input data =head3 Domain selection If C<--domain> is passed in, the first value on each line of input is interpreted as the I-value for the rest of the data on that line. Without C<--domain> the I-value is the line number, and the first value on a line is a plain data point like the others. Default is C<--nodomain>. Thus the original example above produces 2 curves, with B<1,2,3,4,5> as the I-values. If we run the same command with C<--domain>: $ seq 5 | awk '{print 2*$1, $1*$1}' | feedgnuplot --domain we get only 1 curve, with B<2,4,6,8,10> as the I-values. As many points as desired can appear on a single line, but all points on a line are associated with the I-value at the start of that line. =head3 Curve indexing We index the curves in one of 3 ways: sequentially, explicitly with a C<--dataid> or by C<--vnlog> headers. By default, each column represents a separate curve. The first column (after any domain) is curve C<0>. The next one is curve C<1> and so on. This is fine unless sparse data is to be plotted. With the C<--dataid> option, each point is represented by 2 values: a string identifying the curve, and the value itself. If we add C<--dataid> to the original example: $ seq 5 | awk '{print 2*$1, $1*$1}' | feedgnuplot --dataid --autolegend we get 5 different curves with one point in each. The first column, as produced by C, is B<2,4,6,8,10>. These are interpreted as the IDs of the curves to be plotted. If we're plotting C data (L) then we can get the curve IDs from the vnlog header. Vnlog is a trivial data format where lines starting with C<#> are comments and the first comment contains column labels. If we have such data, C can interpret these column labels if the C perl modules are available. The C<--autolegend> option adds a legend using the given IDs to label the curves. The IDs need not be numbers; generic strings are accepted. As many points as desired can appear on a single line. C<--domain> can be used in conjunction with C<--dataid> or C<--vnlog>. =head3 Multi-value style support Depending on how gnuplot is plotting the data, more than one value may be needed to represent the range of a single point. Basic 2D plots have 2 numbers representing each point: 1 domain and 1 range. But if plotting with C<--circles>, for instance, then there's an extra range value: the radius. Many other gnuplot styles require more data: errorbars, variable colors (C), variable sizes (C), labels and so on. The feedgnuplot tool itself does not know about all these intricacies, but they can still be used, by specifying the specific style with C<--style>, and specifying how many values are needed for each point with any of C<--rangesizeall>, C<--tuplesizeall>, C<--rangesize>, C<--tuplesize>. These options are required I for styles not explicitly supported by feedgnuplot; supported styles do the right thing automatically. Specific example: if making a 2d plot of y error bars, the exact format can be queried by running C and invoking C. This tells us that there's a 3-column form: C and a 4-column form: C. With 2d plots feedgnuplot will always output the 1-value domain C, so the rangesize is 2 and 3 respectively. Thus the following are equivalent: $ echo '1 2 0.3 2 3 0.4 3 4 0.5' | feedgnuplot --domain --rangesizeall 2 --with 'yerrorbars' $ echo '1 2 0.3 2 3 0.4 3 4 0.5' | feedgnuplot --domain --tuplesizeall 3 --with 'yerrorbars' $ echo '1 2 1.7 2.3 2 3 2.6 3.4 3 4 3.5 4.5' | feedgnuplot --domain --rangesizeall 3 --with 'yerrorbars' =head3 3D data To plot 3D data, pass in C<--3d>. C<--domain> MUST be given when plotting 3D data to avoid domain ambiguity. If 3D data is being plotted, there are by definition 2 domain values instead of one (I as a function of I and I instead of I as a function of I). Thus the first 2 values on each line are interpreted as the domain instead of just 1. The rest of the processing happens the same way as before. =head3 Time/date data If the input data domain is a time/date, this can be interpreted with C<--timefmt>. This option takes a single argument: the format to use to parse the data. The format is documented in 'set timefmt' in gnuplot, although the common flags that C understands are generally supported. The backslash sequences in the format are I supported, so if you want a tab, put in a tab instead of \t. Whitespace in the format I supported. When this flag is given, some other options act a little bit differently: =over =item C<--xlen> and C<--binwidth> are I in seconds =item C<--xmin> and C<--xmax> I use the format passed in to C<--timefmt> =back Using this option changes both the way the input is parsed I the way the x-axis tics are labelled. Gnuplot tries to be intelligent in this labelling, but it doesn't always do what the user wants. The labelling can be controlled with the gnuplot C command, which takes the same type of format string as C<--timefmt>. Example: $ sar 1 -1 | awk '$1 ~ /..:..:../ && $8 ~/^[0-9\.]*$/ {print $1,$8; fflush()}' | feedgnuplot --stream --domain --lines --timefmt '%H:%M:%S' --set 'format x "%H:%M:%S"' This plots the 'idle' CPU consumption against time. Note that while gnuplot supports the time/date on any axis, I currently supports it I as the x-axis domain. This may change in the future. =head3 'using' expressions We just described how feedgnuplot parses its input data. When passing this data to gnuplot, each curve is sent independently. The domain appears in the leading columns followed by C<--rangesize> columns to complete each row. Without C<--domain>, feedgnuplot explicitly writes out sequential integers. gnuplot then knows how many values it has for each point, and it knows which style we're using, so it's able to interpret the data appropriately, and to make the correct plot. As an example, if gnuplot is passed 2 columns of data, and it is plotting C, it will use column 1 for the x coordinate and column 2 for the y coordinate. This is the default behavior, but the meaning of each column can be controlled via a C expression in gnuplot (not feedgnuplot; keep reading). The default is sequential integers, so this example uses C by default. We can flip the meaning of the columns by passing C. Arbitrary expressions may be specified by enclosing each field in C<()>, and using C<$> to denote each data column. So to use the 2nd column as the x coordinate and the sum of the two columns as the y coordinate, C is passed. Furthermore, the number of columns can vary. For instance gnuplot can read the same two columns of data, but produce a plot with the extra column encoding the sum as the color: C. Please see the gnuplot documentation for lots of detail. That's how I works. Most of the time, I doesn't pass any C expressions at all, and gnuplot does the default thing. But if we want to do something fancy, feedgnuplot supports C<--using curveID expression> and C<--usingall expression>. So we can plot a parabola: seq 100 | feedgnuplot --lines --usingall '1:($2*$2)' This is powerful, but there are some things to keep in mind: =over =item C<--using> overrides whatever C expression feedgnuplot was going to pass. feedgnuplot passes a C expression only if C<--histogram> or C<--timefmt> or C<--xticlabels> are given. So if C<--using> is given together with any of these, the user must take care to do the right thing (whatever that means at that time). =item The C<--tuplesize> controls the data passed to feedgnuplot and the data then passed to gnuplot. It does I directly control how gnuplot eventually interprets the data: C<--using> does that. So for instance we can plot color-coded points: seq 10 | feedgnuplot --with 'points pt 7 palette' --usingall '1:2:2' Here feedgnuplot read 1 column of data. It defauled to C<--tuplesize 2>, so it passed 2 columns of data to gnuplot. gnuplot then produced 3 values for each point, and plotted them as indicated with the C style. =item You I need a column of data to generate a curve. You might want to use a C expression to plot a time series I its cumulative integral. The C expression can compute the integral, but you I pass in the data twice; once for each curve to plot: seq 100 | \ awk '{print $1,$1}' | \ feedgnuplot \ --cmds 'sum=0' \ --cmds 'accum(x) = (sum=sum+x)' \ --using 1 '1:(accum($2))' \ --lines --y2 1 =back =head2 Real-time streaming data To plot real-time data, pass in the C<--stream [refreshperiod]> option. Data will then be plotted as it is received. The plot will be updated every C seconds. If the period isn't specified, a 1Hz refresh rate is used. To refresh at specific intervals indicated by the data, set the refreshperiod to 0 or to 'trigger'. The plot will then I be refreshed when a data line 'replot' is received. This 'replot' command works in both triggered and timed modes, but in triggered mode, it's the only way to replot. Look in L for more information. To plot only the most recent data (instead of I the data), C<--xlen windowsize> can be given. This will create an constantly-updating, scrolling view of the recent past. C should be replaced by the desired length of the domain window to plot, in domain units (passed-in values if C<--domain> or line numbers otherwise). If the domain is a time/date via C<--timefmt>, then C is and I in seconds. If we're plotting a histogram, then C<--xlen> causes a histogram over a moving window to be computed. The subtlely here is that with a histogram you don't actually I the domain since only the range is analyzed. But the domain is still there, and can be utilized with C<--xlen>. With C<--xlen> we can plot I histograms or I I-histograms. =head3 Special data commands If we are reading streaming data, the input stream can contain special commands in addition to the raw data. Feedgnuplot looks for these at the start of every input line. If a command is detected, the rest of the line is discarded. These commands are =over =item C This command refreshes the plot right now, instead of waiting for the next refresh time indicated by the timer. This command works in addition to the timed refresh, as indicated by C<--stream [refreshperiod]>. =item C This command clears out the current data in the plot. The plotting process continues, however, to any data following the C. =item C This command causes feedgnuplot to exit. =back =head2 Hardcopy output The script is able to produce hardcopy output with C<--hardcopy outputfile>. The output type can be inferred from the filename, if B<.ps>, B<.eps>, B<.pdf>, B<.svg>, B<.png> or B<.gp> is requested. If any other file type is requested, C<--terminal> I be passed in to tell gnuplot how to make the plot. If C<--terminal> is passed in, then the C<--hardcopy> argument only provides the output filename. The B<.gp> output is special. Instead of asking gnuplot to plot to a particular terminal, writing to a B<.gp> simply dumps a self-executable gnuplot script into the given file. This is similar to what C<--dump> does, but writes to a file, and makes sure that the file can be self-executing. =head2 Self-plotting data files This script can be used to enable self-plotting data files. There are several ways of doing this: with a shebang (#!) or with inline perl data. =head3 Self-plotting data with a #! A self-plotting, executable data file C is formatted as $ cat data #!/usr/bin/feedgnuplot --lines --points 2 1 4 4 6 9 8 16 10 25 12 36 14 49 16 64 18 81 20 100 22 121 24 144 26 169 28 196 30 225 This is the shebang (#!) line followed by the data, formatted as before. The data file can be plotted simply with $ ./data The caveats here are that on Linux the whole #! line is limited to 127 characters and that the full path to feedgnuplot must be given. The 127 character limit is a serious limitation, but this can likely be resolved with a kernel patch. I have only tried on Linux 2.6. =head3 Self-plotting data with gnuplot Running C will create a self-executable gnuplot script in C =head3 Self-plotting data with perl inline data Perl supports storing data and code in the same file. This can also be used to create self-plotting files: $ cat plotdata.pl #!/usr/bin/perl use strict; use warnings; open PLOT, "| feedgnuplot --lines --points" or die "Couldn't open plotting pipe"; while( ) { my @xy = split; print PLOT "@xy\n"; } __DATA__ 2 1 4 4 6 9 8 16 10 25 12 36 14 49 16 64 18 81 20 100 22 121 24 144 26 169 28 196 30 225 This is especially useful if the logged data is not in a format directly supported by feedgnuplot. Raw data can be stored after the __DATA__ directive, with a small perl script to manipulate the data into a useable format and send it to the plotter. =head1 ARGUMENTS =over =item --C<[no]domain> If enabled, the first element of each line is the domain variable. If not, the point index is used =item --C<[no]dataid> If enabled, each data point is preceded by the ID of the data set that point corresponds to. This ID is interpreted as a string, NOT as just a number. If not enabled, the order of the point is used. As an example, if line 3 of the input is "0 9 1 20" then =over =item C<--nodomain --nodataid> would parse the 4 numbers as points in 4 different curves at x=3 =item C<--domain --nodataid> would parse the 4 numbers as points in 3 different curves at x=0. Here, 0 is the x-variable and 9,1,20 are the data values =item C<--nodomain --dataid> would parse the 4 numbers as points in 2 different curves at x=3. Here 0 and 1 are the data IDs and 9 and 20 are the data values =item C<--domain --dataid> would parse the 4 numbers as a single point at x=0. Here 9 is the data ID and 1 is the data value. 20 is an extra value, so it is ignored. If another value followed 20, we'd get another point in curve ID 20 =back =item C<--vnlog> Vnlog is a trivial data format where lines starting with C<#> are comments and the first comment contains column labels. Some tools for working with such data are available from the C project: L. With the C perl modules installed, we can read the vnlog column headers with C. This replaces C<--dataid>, and we can do all the normal things with these headers. For instance C will generate plot legends for each column in the vnlog, using the vnlog column label in the legend. =item C<--[no]3d> Do [not] plot in 3D. This only makes sense with C<--domain>. Each domain here is an (x,y) tuple =item --C Interpret the X data as a time/date, parsed with the given format =item C<--colormap> This is a legacy option used to who a colormapped xy plot. It does: - Adds C to C<--curvestyleall> - Adds 1 to the default C<--tuplesize> (if C<--tuplesizeall> is not given - Uses C<--zmin>, C<--zmax> to set the colorbar range It's clearer to set the relevant options explicitly, but C<--colormap> still exists for compatibility =item C<--stream [period]> Plot the data as it comes in, in realtime. If period is given, replot every period seconds. If no period is given, replot at 1Hz. If the period is given as 0 or 'trigger', replot I when the incoming data dictates this. See the L section of the man page. =item C<--[no]lines> Do [not] draw lines to connect consecutive points =item C<--[no]points> Do [not] draw points =item C<--circles> Plot with circles. This requires a radius be specified for each point. Automatically sets the C<--rangesize>/C<--tuplesize>. C supported for 3d plots. =item C<--title xxx> Set the title of the plot =item C<--legend curveID legend> Set the label for a curve plot. Use this option multiple times for multiple curves. With C<--dataid>, curveID is the ID. Otherwise, it's the index of the curve, starting at 0 =item C<--autolegend> Use the curve IDs for the legend. Titles given with C<--legend> override these =item C<--xlen xxx> When using C<--stream>, sets the size of the x-window to plot. Omit this or set it to 0 to plot ALL the data. Does not make sense with 3d plots. Implies C<--monotonic>. If we're plotting a histogram, then C<--xlen> causes a histogram over a moving window to be computed. The subtlely here is that with a histogram you don't actually I the domain since only the range is analyzed. But the domain is still there, and can be utilized with C<--xlen>. With C<--xlen> we can plot I histograms or I I-histograms. =item C<--xmin/xmax/x2min/x2max/ymin/ymax/y2min/y2max/zmin/zmax xxx> Set the range for the given axis. These x-axis bounds are ignored in a streaming plot. The x2/y2-axis bounds do not apply in 3d plots. The z-axis bounds apply I to 3d plots or colormaps. Note that there is no C<--xrange> to set both sides at once or C<--xinv> to flip the axis around: anything more than the basics supported in this option is clearly obtainable by talking to gnuplot, for instance C<--set 'xrange [20:10]'> to set the given inverted bounds. =item C<--xlabel/x2label/ylabel/y2label/zlabel/cblabel xxx> Label the given axis. The x2/y2-axis labels do not apply to 3d plots while the z-axis label applies I to 3d plots. The "cblabel" applies to the colorbar, if there is one. =item C<--x2/--y2/--x1y2/--x2y1/--x2y2 xxx> By default data is plotted against the x1 and y1 axes (the left and bottom one respectively). If we want a particular curve plotted against a different axis, we can specify that with these options. You pass C<--AXIS ID> where C defines the axis (C or C or C or C or C) and the C is the curve ID. C<--x2> is a synonym for C<--x2y1> and C<--y2> is a synonym for C<--x1y2>. The curve ID is an ordered 0-based index or a specific ID if C<--dataid> or C<--vnlog>. None of these apply to 3d plots. Can be passed multiple times for different curve IDs, multiple IDs can be passed in as a comma-separated list. By default the curves plotted against the various axes aren not drawn in any differentiated way: the viewer of the resulting plot has to be told which is which via an axes label, legend, colors, etc. Prior to version 1.25 of C the curves plotted on the y2 axis were drawn with a thicker line. This is no longer the case, but that behavior can be brought back by passing something like --y2 curveid --style curveid 'linewidth 3' =item C<--histogram curveID> Set up a this specific curve to plot a histogram. The bin width is given with the C<--binwidth> option (assumed 1.0 if omitted). If a drawing style is not specified for this curve (C<--curvestyle>) or all curves (C<--with>, C<--curvestyleall>) then the default histogram style is set: filled boxes with borders. This is what the user generally wants. This works with C<--domain> and/or C<--stream>, but in those cases the x-value is used I to cull old data because of C<--xlen> or C<--monotonic>. I.e. the domain values are I drawn in any way. Can be passed multiple times, or passed a comma- separated list =item C<--xticlabels> If given, the x-axis tic labels are not numerical, but are read from the data. This changes the interpretation of the input data: with C<--domain>, each line begins with C. Without C<--domain>, each line begins with C