libtext-recordparser-perl 1.5.0-1 / usr / bin / tabmerge

#!/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