This file is indexed.

/usr/bin/tabmerge is in libtext-recordparser-perl 1.5.0-1.

This file is owned by root:root, with mode 0o755.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
#!/usr/bin/env perl

use strict;
use warnings;
use version;
use English qw( -no_match_vars );
use File::Basename;
use Getopt::Long;
use Pod::Usage;
use Readonly;
use Text::RecordParser;
use Text::TabularDisplay;

Readonly our $VERSION    => 1.12;
Readonly my $COMMA       => q{,};
Readonly my $COMMA_SPACE => q{, };
Readonly my $DASH        => q{-};
Readonly my $EMPTY_STR   => q{};
Readonly my $TAB         => qq{\t};
Readonly my $NEWLINE     => qq{\n};

my $fs = $TAB;
my $rs = $NEWLINE;
my ( $fields, $min, $max, $list, $sort, $stdout, 
    $help, $man_page, $show_version );

GetOptions(
    'f|fields:s' => \$fields,
    'help'       => \$help,
    'fs:s'       => \$fs,
    'l|list'     => \$list,
    'man'        => \$man_page,
    'min'        => \$min,
    'max'        => \$max,
    'rs:s'       => \$rs,
    's|sort:s'   => \$sort,
    'stdout'     => \$stdout,
    'version'    => \$show_version,
) or pod2usage;

if ( $help || $man_page ) {
    pod2usage({
        -exitval => 0,
        -verbose => $man_page ? 2 : 1
    });
};

if ( $show_version ) {
    my $prog = basename( $PROGRAM_NAME );
    print "$prog $VERSION\n";
    exit 0;
}

if ( scalar @ARGV < 2 ) {
    pod2usage('Please supply two or more files');
}

my @files = @ARGV or pod2usage('No input files');

$min = 1 unless $max or $fields;

my $p = Text::RecordParser->new(
    field_separator  => $fs,
    record_separator => $rs,
);

if ( $list ) {
    list( $p, @files ); 
}
elsif ( $min || $max || $fields ) {
    intersection( 
        fields => $fields, 
        files  => \@files,
        parser => $p, 
        sort   => $sort,
        type   => $min ? 'min' : 'max', 
    );
}
else {
    pod2usage(q[Can't figure out what to do.]);
}

# -------------------------------------------------------------------
sub intersection {
    my %args    = @_;
    my $p       = $args{'parser'};
    my $type    = $args{'type'};
    my $files   = $args{'files'};
    my $fields  = $args{'fields'} || $EMPTY_STR; # optional
    my $sort    = $args{'sort'}   || $EMPTY_STR; # optional

    my %fields;
    for my $file ( @$files ) {
        $p->filename( $file );
        $p->bind_header;
        $fields{ $_ }++ for $p->field_list;
    }

    my @intersect;
    if ( $fields ) {
        @intersect = map { s/^\s+|\s+$//g; $_ } split /$COMMA/, $fields;
        die_if_bad( \%fields, \@intersect );
    }
    else {
        my $no_files = scalar @$files;
        for my $fld ( keys %fields ) {
            push @intersect, $fld if 
                ( $type eq 'max' ) || 
                ( $type eq 'min' && $fields{ $fld } == $no_files )
            ;
        } 

        @intersect = sort @intersect;
    }

    die "No intersection!\n" unless @intersect;

    my @data;
    for my $file ( @$files ) {
        $p->filename( $file );
        $p->bind_header;
        while ( my $rec = $p->fetchrow_hashref ) {
            push @data, { map { $_, $rec->{ $_ } } @intersect };
        }
    }

    if ( my @sort = map { s/^\s+|\s+$//g; $_ } split /$COMMA/, $sort ) {
        die_if_bad( \%fields, \@sort );

        @data = 
            map  { $_->[1] }
            sort { $a->[0] cmp $b->[0] }
            map  { [ join($DASH, @{ $_ }{ @sort } ), $_ ] }
            @data;
    }

    if ( $stdout ) {
        print join( $fs, @intersect ), $rs;
        for my $rec ( @data ) {
            print join( $fs, 
                map { defined $rec->{$_} ? $rec->{$_} : $EMPTY_STR } @intersect 
            ), $rs;
        }
    }
    else {
        my $tab = Text::TabularDisplay->new( @intersect );
        for my $rec ( @data ) {
            $tab->add( map { $rec->{ $_ } } @intersect );
        }
        print $tab->render, $NEWLINE;
    }
}

# -------------------------------------------------------------------
sub list {
    my ( $p, @files ) = @_;

    my %fields;
    for my $file ( @files ) {
        $p->filename( $file );
        $p->bind_header;
        $fields{ $_ }++ for $p->field_list;
    }

    my $tab = Text::TabularDisplay->new('Field', 'No. Times Present');
    $tab->add( $_, $fields{ $_ } ) for sort keys %fields;
    print $tab->render, $NEWLINE;
}

# -------------------------------------------------------------------
sub die_if_bad {
    my ( $fields, $check ) = @_;

    my @bad;
    for my $fld ( @$check ) {
        push @bad, $fld unless $fields->{ $fld };
    }

    if ( @bad ) {
        die sprintf "Bad field name%s: %s$NEWLINE", 
            scalar @bad > 1 ? 's' : $EMPTY_STR,
            join $COMMA_SPACE, @bad 
        ;
    }
    else {
        return 1;
    }
}

__END__

# -------------------------------------------------------------------

# $Id: tabmerge,v 1.11 2006/03/07 17:20:00 kclark Exp $

=pod

=head1 NAME

tabmerge - unify delimited files on common fields

=head1 SYNOPSIS

  tabmerge [action] [options] file1 file2 [...]

Actions:

  --min                Take only fields present in all files [DEFAULT]
  --max                Take all fields present
  -f|--fields=f1[,f2]  Take only the fields mentioned in the 
                       comma-separated list

Options:

  -l|--list            List available fields
  --fs=x               Use "x" as the field separator 
                       (default is tab "\t")
  --rs=x               Use "x" as the record separator 
                       (default is newline "\n")
  -s|--sort=f1[,f2]    Sort data ASCII-betically on field(s)
  --stdout             Print data in original delimited format
                       (i.e., not in a table format)

  --help               Show brief help and quit
  --man                Show full documentation

=head1 DESCRIPTION

This program merges the fields -- not the rows -- of delimited text
files.  That is, if several files are almost but not quite entirely
unlike each other in their structure (in their field names, numbers or
orders), this script allows you to easily unify the files into one
file with all the same fields.  The output can be based on fields as
determined by the three "action" flags.

For the following examples, consider three files that contain the
following fields:

  +------------+---------------------------------+
  | File       | Fields                          |
  +------------+---------------------------------+
  | merge1.tab | name, type, position            |
  | merge2.tab | name, type, position, lod_score |
  | merge3.tab | name, position                  |
  +------------+---------------------------------+

To list all available fields in the files and the number of times they
are present:

  $ tabmerge --list merge*
  +-----------+-------------------+
  | Field     | No. Times Present |
  +-----------+-------------------+
  | lod_score | 1                 |
  | name      | 3                 |
  | position  | 3                 |
  | type      | 2                 |
  +-----------+-------------------+

To merge the files on the minimum overlapping fields:

  $ tabmerge merge*
  +----------+----------+
  | name     | position |
  +----------+----------+
  | RM104    | 2.30     |
  | RM105    | 4.5      |
  | TX5509   | 10.4     |
  | UU189    | 19.0     |
  | Xpsm122  | 3.3      |
  | Xpsr9556 | 4.5      |
  | DRTL     | 2.30     |
  | ALTX     | 4.5      |
  | DWRF     | 10.4     |
  +----------+----------+

To merge the files and include all the fields:

  $ tabmerge --max merge*
  +-----------+----------+----------+--------+
  | lod_score | name     | position | type   |
  +-----------+----------+----------+--------+
  |           | RM104    | 2.30     | RFLP   |
  |           | RM105    | 4.5      | RFLP   |
  |           | TX5509   | 10.4     | AFLP   |
  | 2.4       | UU189    | 19.0     | SSR    |
  | 1.2       | Xpsm122  | 3.3      | Marker |
  | 1.2       | Xpsr9556 | 4.5      | Marker |
  |           | DRTL     | 2.30     |        |
  |           | ALTX     | 4.5      |        |
  |           | DWRF     | 10.4     |        |
  +-----------+----------+----------+--------+

To merge and extract just the "name" and "type" fields:

  $ tabmerge -f name,type merge*
  +----------+--------+
  | name     | type   |
  +----------+--------+
  | RM104    | RFLP   |
  | RM105    | RFLP   |
  | TX5509   | AFLP   |
  | UU189    | SSR    |
  | Xpsm122  | Marker |
  | Xpsr9556 | Marker |
  | DRTL     |        |
  | ALTX     |        |
  | DWRF     |        |
  +----------+--------+

To merge the files on just the "name" and "lod_score" fields and sort on 
the name:

  $ tabmerge -f name,lod_score -s name merge*
  +----------+-----------+
  | name     | lod_score |
  +----------+-----------+
  | ALTX     |           |
  | DRTL     |           |
  | DWRF     |           |
  | RM104    |           |
  | RM105    |           |
  | TX5509   |           |
  | UU189    | 2.4       |
  | Xpsm122  | 1.2       |
  | Xpsr9556 | 1.2       |
  +----------+-----------+

To do the same but mimic the original tab-delimited input:

  $ tabmerge -f name,lod_score -s name --stdout merge*
  name    lod_score
  ALTX
  DRTL
  DWRF
  RM104
  RM105
  TX5509
  UU189   2.4
  Xpsm122 1.2
  Xpsr9556        1.2

Why would you want to do this?  Suppose you have several delimited text
files with nearly the same structure and want to create just one file
from them, but the fields may be in a different order in each file
and/or some files may contain more or fewer fields than others.  (As
far-fetched as it may seem, it happens to the author more than he'd
like.)

=head1 SEE ALSO

=over 4

=item * Text::RecordParser

=item * Text::TabularDisplay

=back

=head1 AUTHOR

Ken Youens-Clark E<lt>kclark@cpan.orgE<gt>.

=head1 LICENSE AND COPYRIGHT

Copyright (C) 2006-10 Ken Youens-Clark.  All rights reserved.

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
the Free Software Foundation; version 2.

This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of 
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
General Public License for more details.

=cut