| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
package Bio::Roary::ReorderSpreadsheet; |
|
2
|
|
|
|
|
|
|
$Bio::Roary::ReorderSpreadsheet::VERSION = '3.11.0'; |
|
3
|
|
|
|
|
|
|
# ABSTRACT: Take in a tree file and a spreadsheet and output a spreadsheet with reordered columns |
|
4
|
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
|
|
6
|
2
|
|
|
2
|
|
86001
|
use Moose; |
|
|
2
|
|
|
|
|
424817
|
|
|
|
2
|
|
|
|
|
13
|
|
|
7
|
2
|
|
|
2
|
|
12646
|
use Text::CSV; |
|
|
2
|
|
|
|
|
26969
|
|
|
|
2
|
|
|
|
|
79
|
|
|
8
|
2
|
|
|
2
|
|
488
|
use Bio::Roary::SampleOrder; |
|
|
2
|
|
|
|
|
6
|
|
|
|
2
|
|
|
|
|
100
|
|
|
9
|
2
|
|
|
2
|
|
820
|
use Bio::Roary::GroupStatistics; |
|
|
2
|
|
|
|
|
8
|
|
|
|
2
|
|
|
|
|
966
|
|
|
10
|
|
|
|
|
|
|
with 'Bio::Roary::SpreadsheetRole'; |
|
11
|
|
|
|
|
|
|
|
|
12
|
|
|
|
|
|
|
has 'tree_file' => ( is => 'ro', isa => 'Str', required => 1 ); |
|
13
|
|
|
|
|
|
|
has 'spreadsheet' => ( is => 'ro', isa => 'Str', required => 1 ); |
|
14
|
|
|
|
|
|
|
has 'tree_format' => ( is => 'ro', isa => 'Str', default => 'newick' ); |
|
15
|
|
|
|
|
|
|
has 'output_filename' => ( is => 'ro', isa => 'Str', default => 'reordered_groups_stats.csv' ); |
|
16
|
|
|
|
|
|
|
has 'search_strategy' => ( is => 'ro', isa => 'Str', default => 'depth' ); |
|
17
|
|
|
|
|
|
|
has 'sortby' => ( is => 'ro', isa => 'Maybe[Str]'); |
|
18
|
|
|
|
|
|
|
|
|
19
|
|
|
|
|
|
|
has '_sample_order' => ( is => 'ro', isa => 'ArrayRef', lazy => 1, builder => '_build__sample_order' ); |
|
20
|
|
|
|
|
|
|
has '_column_mappings' => ( is => 'ro', isa => 'ArrayRef', lazy => 1, builder => '_build__column_mappings' ); |
|
21
|
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
|
|
23
|
|
|
|
|
|
|
sub BUILD { |
|
24
|
14
|
|
|
14
|
0
|
30
|
my ($self) = @_; |
|
25
|
|
|
|
|
|
|
#Â read the headers first |
|
26
|
14
|
|
|
|
|
361
|
$self->_column_mappings; |
|
27
|
|
|
|
|
|
|
} |
|
28
|
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
|
|
30
|
|
|
|
|
|
|
sub reorder_spreadsheet { |
|
31
|
14
|
|
|
14
|
0
|
29
|
my ($self) = @_; |
|
32
|
|
|
|
|
|
|
|
|
33
|
|
|
|
|
|
|
# make sure the file handle is at the start |
|
34
|
14
|
|
|
|
|
337
|
seek($self->_input_spreadsheet_fh ,0,0); |
|
35
|
14
|
|
|
|
|
323
|
while ( my $row = $self->_csv_parser->getline( $self->_input_spreadsheet_fh ) ) |
|
36
|
|
|
|
|
|
|
{ |
|
37
|
112
|
|
|
|
|
5618
|
$self->_csv_output->print($self->_output_spreadsheet_fh, $self->_remap_columns($row)); |
|
38
|
|
|
|
|
|
|
} |
|
39
|
|
|
|
|
|
|
|
|
40
|
14
|
|
|
|
|
658
|
close($self->_output_spreadsheet_fh); |
|
41
|
14
|
|
|
|
|
368
|
close($self->_input_spreadsheet_fh); |
|
42
|
14
|
|
|
|
|
347
|
return 1; |
|
43
|
|
|
|
|
|
|
} |
|
44
|
|
|
|
|
|
|
|
|
45
|
|
|
|
|
|
|
sub _remap_columns |
|
46
|
|
|
|
|
|
|
{ |
|
47
|
112
|
|
|
112
|
|
185
|
my ($self, $row) = @_; |
|
48
|
|
|
|
|
|
|
|
|
49
|
112
|
|
|
|
|
156
|
my @output_row; |
|
50
|
112
|
|
|
|
|
148
|
for(my $output_index = 0; $output_index < @{$self->_column_mappings}; $output_index++) |
|
|
1680
|
|
|
|
|
31442
|
|
|
51
|
|
|
|
|
|
|
{ |
|
52
|
1568
|
|
|
|
|
28836
|
my $input_index = $self->_column_mappings->[$output_index]; |
|
53
|
1568
|
|
|
|
|
3008
|
push(@output_row, $row->[$input_index]); |
|
54
|
|
|
|
|
|
|
} |
|
55
|
112
|
|
|
|
|
948
|
return \@output_row; |
|
56
|
|
|
|
|
|
|
} |
|
57
|
|
|
|
|
|
|
|
|
58
|
|
|
|
|
|
|
sub _column_mappings_populate_fixed_headers |
|
59
|
|
|
|
|
|
|
{ |
|
60
|
14
|
|
|
14
|
|
37
|
my ($self, $column_mappings,$header_row) = @_; |
|
61
|
14
|
|
|
|
|
21
|
my $column_counter = 0; |
|
62
|
14
|
|
|
|
|
356
|
for($column_counter = 0; $column_counter < $self->_num_fixed_headers; $column_counter++) |
|
63
|
|
|
|
|
|
|
{ |
|
64
|
196
|
|
|
|
|
211
|
push(@{$column_mappings}, $column_counter); |
|
|
196
|
|
|
|
|
289
|
|
|
65
|
196
|
|
|
|
|
194
|
shift(@{$header_row}); |
|
|
196
|
|
|
|
|
3710
|
|
|
66
|
|
|
|
|
|
|
} |
|
67
|
14
|
|
|
|
|
31
|
return $column_counter; |
|
68
|
|
|
|
|
|
|
} |
|
69
|
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
sub _build__column_mappings |
|
71
|
|
|
|
|
|
|
{ |
|
72
|
14
|
|
|
14
|
|
34
|
my ($self) = @_; |
|
73
|
14
|
|
|
|
|
296
|
my $header_row = $self->_csv_parser->getline( $self->_input_spreadsheet_fh ); |
|
74
|
|
|
|
|
|
|
|
|
75
|
14
|
|
|
|
|
575
|
my @column_mappings; |
|
76
|
14
|
|
|
|
|
61
|
my $column_counter = $self->_column_mappings_populate_fixed_headers(\@column_mappings, $header_row); |
|
77
|
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
#Â put the input column names into an array where the key is the name and the value is the order |
|
79
|
14
|
|
|
|
|
27
|
my %input_sample_order; |
|
80
|
14
|
|
|
|
|
32
|
for(my $i = 0; $i < @{$header_row}; $i++) |
|
|
14
|
|
|
|
|
36
|
|
|
81
|
|
|
|
|
|
|
{ |
|
82
|
0
|
|
|
|
|
0
|
$input_sample_order{$header_row->[$i]} = $i + $column_counter; |
|
83
|
|
|
|
|
|
|
} |
|
84
|
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
# Go through the order of the samples from the tree and see if the headers exist |
|
86
|
14
|
|
|
|
|
20
|
for my $sample_name (@{$self->_sample_order}) |
|
|
14
|
|
|
|
|
285
|
|
|
87
|
|
|
|
|
|
|
{ |
|
88
|
56
|
50
|
|
|
|
97
|
if(defined($input_sample_order{$sample_name})) |
|
89
|
|
|
|
|
|
|
{ |
|
90
|
0
|
|
|
|
|
0
|
push(@column_mappings, $input_sample_order{$sample_name}); |
|
91
|
0
|
|
|
|
|
0
|
delete($input_sample_order{$sample_name}); |
|
92
|
|
|
|
|
|
|
} |
|
93
|
56
|
|
|
|
|
69
|
$column_counter++; |
|
94
|
|
|
|
|
|
|
} |
|
95
|
|
|
|
|
|
|
|
|
96
|
|
|
|
|
|
|
#Â Add any columns not in the tree to the end |
|
97
|
14
|
|
|
|
|
38
|
for my $sample_name (keys %input_sample_order) |
|
98
|
|
|
|
|
|
|
{ |
|
99
|
0
|
|
|
|
|
0
|
push(@column_mappings, $input_sample_order{$sample_name}); |
|
100
|
0
|
|
|
|
|
0
|
delete($input_sample_order{$sample_name}); |
|
101
|
0
|
|
|
|
|
0
|
$column_counter++; |
|
102
|
|
|
|
|
|
|
} |
|
103
|
14
|
|
|
|
|
306
|
return \@column_mappings; |
|
104
|
|
|
|
|
|
|
} |
|
105
|
|
|
|
|
|
|
|
|
106
|
|
|
|
|
|
|
sub _build__sample_order { |
|
107
|
14
|
|
|
14
|
|
26
|
my ($self) = @_; |
|
108
|
14
|
|
|
|
|
287
|
my $obj = Bio::Roary::SampleOrder->new( |
|
109
|
|
|
|
|
|
|
tree_file => $self->tree_file, |
|
110
|
|
|
|
|
|
|
tree_format => $self->tree_format, |
|
111
|
|
|
|
|
|
|
search_strategy => $self->search_strategy, |
|
112
|
|
|
|
|
|
|
sortby => $self->sortby |
|
113
|
|
|
|
|
|
|
); |
|
114
|
14
|
|
|
|
|
308
|
return $obj->ordered_samples(); |
|
115
|
|
|
|
|
|
|
} |
|
116
|
|
|
|
|
|
|
|
|
117
|
2
|
|
|
2
|
|
16
|
no Moose; |
|
|
2
|
|
|
|
|
4
|
|
|
|
2
|
|
|
|
|
12
|
|
|
118
|
|
|
|
|
|
|
__PACKAGE__->meta->make_immutable; |
|
119
|
|
|
|
|
|
|
|
|
120
|
|
|
|
|
|
|
1; |
|
121
|
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
__END__ |
|
123
|
|
|
|
|
|
|
|
|
124
|
|
|
|
|
|
|
=pod |
|
125
|
|
|
|
|
|
|
|
|
126
|
|
|
|
|
|
|
=encoding UTF-8 |
|
127
|
|
|
|
|
|
|
|
|
128
|
|
|
|
|
|
|
=head1 NAME |
|
129
|
|
|
|
|
|
|
|
|
130
|
|
|
|
|
|
|
Bio::Roary::ReorderSpreadsheet - Take in a tree file and a spreadsheet and output a spreadsheet with reordered columns |
|
131
|
|
|
|
|
|
|
|
|
132
|
|
|
|
|
|
|
=head1 VERSION |
|
133
|
|
|
|
|
|
|
|
|
134
|
|
|
|
|
|
|
version 3.11.0 |
|
135
|
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
=head1 SYNOPSIS |
|
137
|
|
|
|
|
|
|
|
|
138
|
|
|
|
|
|
|
Take in a tree file and a spreadsheet and output a spreadsheet with reordered columns |
|
139
|
|
|
|
|
|
|
use Bio::Roary::ReorderSpreadsheet; |
|
140
|
|
|
|
|
|
|
|
|
141
|
|
|
|
|
|
|
my $obj = Bio::Roary::ReorderSpreadsheet->new( |
|
142
|
|
|
|
|
|
|
tree_file => $tree_file, |
|
143
|
|
|
|
|
|
|
spreadsheet => 'groups.csv' |
|
144
|
|
|
|
|
|
|
); |
|
145
|
|
|
|
|
|
|
$obj->reorder_spreadsheet(); |
|
146
|
|
|
|
|
|
|
|
|
147
|
|
|
|
|
|
|
=head1 AUTHOR |
|
148
|
|
|
|
|
|
|
|
|
149
|
|
|
|
|
|
|
Andrew J. Page <ap13@sanger.ac.uk> |
|
150
|
|
|
|
|
|
|
|
|
151
|
|
|
|
|
|
|
=head1 COPYRIGHT AND LICENSE |
|
152
|
|
|
|
|
|
|
|
|
153
|
|
|
|
|
|
|
This software is Copyright (c) 2013 by Wellcome Trust Sanger Institute. |
|
154
|
|
|
|
|
|
|
|
|
155
|
|
|
|
|
|
|
This is free software, licensed under: |
|
156
|
|
|
|
|
|
|
|
|
157
|
|
|
|
|
|
|
The GNU General Public License, Version 3, June 2007 |
|
158
|
|
|
|
|
|
|
|
|
159
|
|
|
|
|
|
|
=cut |