| 1 |
#!/usr/bin/perl |
| 2 |
# -*- mode: cperl; indent-tabs-mode: nil; tab-width: 3; cperl-indent-level: 3; -*- |
| 3 |
use warnings; |
| 4 |
use strict; |
| 5 |
use utf8; |
| 6 |
BEGIN { |
| 7 |
$| = 1; |
| 8 |
binmode(STDIN, ':encoding(UTF-8)'); |
| 9 |
binmode(STDOUT, ':encoding(UTF-8)'); |
| 10 |
} |
| 11 |
use open qw( :encoding(UTF-8) :std ); |
| 12 |
|
| 13 |
use Getopt::Long; |
| 14 |
Getopt::Long::Configure('bundling'); |
| 15 |
Getopt::Long::Configure('no_ignore_case'); |
| 16 |
my %opts = (); |
| 17 |
GetOptions(\%opts, ('weight|w:s', 'reverse|r', 'first|1', 'help|?')); |
| 18 |
|
| 19 |
sub print_help { |
| 20 |
print <<'XOUT'; |
| 21 |
Usage: cg-sort [OPTIONS] |
| 22 |
|
| 23 |
Pipe a CG stream through this to sort and unique the readings of each cohort. |
| 24 |
|
| 25 |
Options: |
| 26 |
-?, --help outputs this help |
| 27 |
-w, --weight sorts by a numeric tag; defaults to W |
| 28 |
-r, --reverse reverses the sort order |
| 29 |
-1, --first only keep the first reading |
| 30 |
|
| 31 |
XOUT |
| 32 |
} |
| 33 |
|
| 34 |
if (defined $opts{'help'}) { |
| 35 |
print_help(); |
| 36 |
exit(0); |
| 37 |
} |
| 38 |
|
| 39 |
my $W = 'W'; |
| 40 |
if (exists($opts{weight}) && length($opts{weight})) { |
| 41 |
$W = $opts{weight}; |
| 42 |
} |
| 43 |
|
| 44 |
my $in_cohort = 0; |
| 45 |
my %readings = (); |
| 46 |
my %deleted = (); |
| 47 |
my $trail = ''; |
| 48 |
|
| 49 |
sub sort_weight { |
| 50 |
my $wa = 0.0; |
| 51 |
my $wb = 0.0; |
| 52 |
if ($a =~ m/(?:^|\s)<\Q$W\E:([\d.]+)>(?:\s|$)/ || $a =~ m/(?:^|\s)\Q$W\E:([\d.]+)(?:\s|$)/) { |
| 53 |
$wa = $1; |
| 54 |
} |
| 55 |
if ($b =~ m/(?:^|\s)<\Q$W\E:([\d.]+)>(?:\s|$)/ || $b =~ m/(?:^|\s)\Q$W\E:([\d.]+)(?:\s|$)/) { |
| 56 |
$wb = $1; |
| 57 |
} |
| 58 |
|
| 59 |
if ($wa == $wb) { |
| 60 |
return $a cmp $b; |
| 61 |
} |
| 62 |
return $wa <=> $wb; |
| 63 |
} |
| 64 |
|
| 65 |
sub print_sorted_readings { |
| 66 |
if (!@_) { |
| 67 |
return; |
| 68 |
} |
| 69 |
if (exists($opts{weight})) { |
| 70 |
@_ = sort sort_weight @_; |
| 71 |
} |
| 72 |
else { |
| 73 |
@_ = sort @_; |
| 74 |
} |
| 75 |
if (exists($opts{reverse})) { |
| 76 |
@_ = reverse @_; |
| 77 |
} |
| 78 |
if (exists($opts{first})) { |
| 79 |
print $_[0]; |
| 80 |
} |
| 81 |
else { |
| 82 |
print join('', @_); |
| 83 |
} |
| 84 |
} |
| 85 |
|
| 86 |
sub print_sorted { |
| 87 |
if (!$in_cohort) { |
| 88 |
return; |
| 89 |
} |
| 90 |
|
| 91 |
print_sorted_readings(keys(%readings)); |
| 92 |
print_sorted_readings(keys(%deleted)); |
| 93 |
|
| 94 |
print $trail; |
| 95 |
|
| 96 |
%readings = (); |
| 97 |
%deleted = (); |
| 98 |
$trail = ''; |
| 99 |
$in_cohort = 0; |
| 100 |
} |
| 101 |
|
| 102 |
my $fh = *STDIN; |
| 103 |
if (defined $ARGV[0]) { |
| 104 |
open($fh, '<', $ARGV[0]) or die $!; |
| 105 |
} |
| 106 |
|
| 107 |
while (<$fh>) { |
| 108 |
if (m/^"<.+?>"/) { |
| 109 |
print_sorted(); |
| 110 |
$in_cohort = 1; |
| 111 |
} |
| 112 |
elsif ($in_cohort) { |
| 113 |
if (m/^\s+".+?"/) { |
| 114 |
$readings{$_} = 1; |
| 115 |
} |
| 116 |
elsif (m/^;\s+".+?"/) { |
| 117 |
$deleted{$_} = 1; |
| 118 |
} |
| 119 |
else { |
| 120 |
$trail .= $_; |
| 121 |
} |
| 122 |
next; |
| 123 |
} |
| 124 |
print; |
| 125 |
} |
| 126 |
|
| 127 |
print_sorted(); |