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
|
#! /bin/sh
#!perl -w # --*- Perl -*--
eval 'exec perl -x $0 ${1+"$@"}'
if 0;
#------------------------------------------------------------------------------
#$Author: andrius $
#$Date: 2018-09-04 10:49:47 +0300 (An, 04 rugs. 2018) $
#$Revision: 6413 $
#$URL: svn://www.crystallography.net/cod-tools/tags/v2.3/scripts/cif_select $
#------------------------------------------------------------------------------
#*
#* Read CIFs and print out selected tags with their values.
#*
#* USAGE:
#* $0 --options input1.cif input*.cif
#**
use strict;
use warnings;
use COD::CIF::Parser qw( parse_cif );
use COD::CIF::Tags::CanonicalNames qw( canonical_tag_name canonicalize_names );
use COD::CIF::Tags::Manage qw( exclude_tag rename_tag );
use COD::CIF::Tags::Print qw( print_cif );
use COD::SOptions qw( getOptions get_value );
use COD::SUsage qw( usage options );
use COD::ErrorHandler qw( process_errors
process_parser_messages
process_warnings
report_message );
use COD::ToolsVersion;
my $use_parser = 'c';
my $die_on_error_level = {
ERROR => 1,
WARNING => 0,
NOTE => 0
};
my @selected_tags;
my $treat_dots_as_underscores = 0;
my $canonicalize_tag_names = 0;
my $output_tabular = 0;
my $invert = 0;
binmode STDOUT, ':encoding(UTF-8)';
binmode STDERR, ':encoding(UTF-8)';
#* OPTIONS:
#* -t, --tags _tag1,_tag2,_tag3
#* --tags "_tag1 _tag2 _tag3"
#* Print out values of tags _tag1, _tag2, and _tag3;
#* the specified tag list becomes a new list of printed tags.
#*
#* -a, --add-tag _tag4
#* Add tag _tag4 to the list of printed tags.
#*
#* -f, --file-with-tags tag.lst
#* Read tags to be extracted from the file 'tag.lst'.
#* Comments (lines starting with '#') in 'tag.lst' are
#* ignored.
#*
#* -c, --clear-tags
#* Clear the list of printed tags accumulated so far.
#*
#* --invert
#* Invert the sense of selection. Exclude values of
#* the tags from the supplied list.
#*
#* --treat-dots-as-underscores
#* Convert all dots in tag names into underscores.
#*
#* --dont-treat-dots-as-underscores, --no-treat-dots-as-underscores
#* Leave original tags as they are (default).
#*
#* --tabular, --output-tabular
#* Output selected tags and their values in tabular format:
#* <data block name> <tag name> <value> <value> ... <value>
#* --cif, --output-cif
#* Output selected tags and their values in CIF format (default).
#*
#* --canonicalize-tag-names
#* Output tags in the canonical form.
#* --dont-canonicalize-tag-names, --no-canonicalize-tag-names
#* Output tags as they are given in original file(s) (default).
#*
#* --use-perl-parser
#* Use Perl parser for CIF parsing.
#* --use-c-parser
#* Use Perl & C parser for CIF parsing.
#*
#* --help, --usage
#* Output a short usage message (this message) and exit.
#* --version
#* Output version information and exit.
#**
@ARGV = getOptions(
"-t,--tags" => sub { @selected_tags = split( /\s|,/, get_value()) },
"-a,--add-tag" => \@selected_tags,
"-c,--clear-tags" => sub { @selected_tags = () },
"-f,--file-with-tags" => sub {
my $filename = get_value();
eval {
open( my $tags, '<', $filename ) or die 'ERROR, '
. 'could not open file for reading -- '
. lcfirst($!) . "\n";
@selected_tags = ( @selected_tags,
map { s/^\s*|\s*$//g; $_ }
grep { !/^\#/ } <$tags> );
close( $tags ) or die 'ERROR, '
.'could not close file after reading -- '
. lcfirst($!) . "\n";
};
if ($@) {
process_errors( {
'message' => $@,
'program' => $0,
'filename' => $filename
}, $die_on_error_level->{ERROR} );
};
},
"--invert" => sub { $invert = 1 },
"--treat-dots-as-underscores"
=> sub { $treat_dots_as_underscores = 1 },
"--dont-treat-dots-as-underscores"
=> sub { $treat_dots_as_underscores = 0 },
"--no-treat-dots-as-underscores"
=> sub { $treat_dots_as_underscores = 0 },
"--tabular,--output-tabular" => sub { $output_tabular = 1 },
"--cif,--output-cif" => sub { $output_tabular = 0 },
"--canonicalize-tag-names"
=> sub { $canonicalize_tag_names = 1 },
"--dont-canonicalize-tag-names"
=> sub { $canonicalize_tag_names = 0 },
"--no-canonicalize-tag-names"
=> sub { $canonicalize_tag_names = 0 },
"--use-perl-parser" => sub { $use_parser = "perl" },
"--use-c-parser" => sub { $use_parser = "c" },
"--options" => sub { options; exit },
"--help,--usage" => sub { usage; exit },
'--version' => sub { print 'cod-tools version ',
$COD::ToolsVersion::Version, "\n";
exit }
);
sub unique(@);
if( $treat_dots_as_underscores ) {
@selected_tags = map { s/\./_/g; $_ } @selected_tags;
}
@selected_tags = unique map { lc($_) } @selected_tags;
my %selected_tags = map { ($_, $_) } @selected_tags;
@ARGV = ( "-" ) unless @ARGV;
for my $filename (@ARGV) {
my $options = { 'parser' => $use_parser, 'no_print' => 1 };
my ( $data, $err_count, $messages ) = parse_cif( $filename, $options );
process_parser_messages( $messages, $die_on_error_level );
next if ( $err_count > 0 );
if( !@{$data} || !defined $data->[0] || !defined $data->[0]{name} ) {
report_message( {
'program' => $0,
'filename' => $filename,
'err_level' => 'WARNING',
'message' => 'file seems to be empty'
}, $die_on_error_level->{'WARNING'} );
next;
}
for my $dataset (@$data) {
my @values = ();
my $values = $dataset->{values};
my $dataname = 'data_' . $dataset->{name};
local $SIG{__WARN__} = sub {
process_warnings( {
'message' => @_,
'program' => $0,
'add_pos' => $dataname,
'filename' => $filename
}, $die_on_error_level )
};
if( $treat_dots_as_underscores ) {
for my $tag (sort keys %{$values}) {
my $new_tag = $tag;
$new_tag =~ s/\./_/g;
next if $new_tag eq $tag;
if( exists $values->{$new_tag} ) {
warn "WARNING, will not rename data item '$tag' " .
"to '$new_tag': data item '$new_tag' already " .
"exists\n";
next;
}
rename_tag( $dataset, $tag, $new_tag );
}
}
if( $invert ) {
for my $tag (@selected_tags) {
exclude_tag( $dataset, $tag );
}
}
my @printed_tags;
if( !$invert ) {
@printed_tags = @selected_tags;
} else {
@printed_tags = @{ $dataset->{tags} };
}
my %printed_tags = map { ($_, $_) } @printed_tags;
if( $output_tabular ) {
local $, = "\t";
local $\ = "\n";
for my $tag (@printed_tags) {
print $dataset->{name},
( $canonicalize_tag_names
? canonical_tag_name( $tag )
: $tag ),
( exists $dataset->{values}{$tag}
? join( $,, map{ s/[\n\t]/ /g; $_ }
@{$dataset->{values}{$tag}} )
: '?' );
}
} else {
if( $canonicalize_tag_names ) {
canonicalize_names( $dataset );
@printed_tags = map{ canonical_tag_name( $_ ) }
@printed_tags;
%printed_tags = map{ ($_, $_) }
@printed_tags;
}
print_cif( $dataset,
{
dictionary_tags => \%printed_tags,
dictionary_tag_list => \@printed_tags,
exclude_misspelled_tags => 1,
} );
}
}
}
sub unique(@)
{
my %count;
my @unique;
for (@_) {
next if $count{$_};
$count{$_}++;
push @unique, $_;
}
return @unique;
}
|
