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
|
#! /bin/sh
#!perl -w # --*- Perl -*--
eval 'exec perl -x $0 ${1+"$@"}'
if 0;
#------------------------------------------------------------------------------
#$Author: antanas $
#$Date: 2021-08-01 22:40:00 +0300 (Sun, 01 Aug 2021) $
#$Revision: 8844 $
#$URL: svn+ssh://www.crystallography.net/home/coder/svn-repositories/cod-tools/tags/v3.7.0/scripts/cif_cell_contents $
#------------------------------------------------------------------------------
#*
#* Calculate cell contents from atom coordinates and symmetry information.
#*
#* USAGE:
#* $0 --options input1.cif input*.cif
#**
use strict;
use warnings;
use COD::CIF::Parser qw( parse_cif );
use COD::CIF::Data::CellContents qw( cif_cell_contents );
use COD::CIF::Tags::CanonicalNames qw( canonicalize_all_names );
use COD::SOptions qw( getOptions );
use COD::SUsage qw( usage options );
use COD::ErrorHandler qw( process_warnings
process_errors
process_parser_messages );
use COD::ToolsVersion qw( get_version_string );
my $use_parser = 'c';
my $die_on_error_level = {
ERROR => 1,
WARNING => 0,
NOTE => 0
};
my $Z_value;
my $use_attached_hydrogens = 1;
my $assume_full_occupancies = 0;
my $die_on_errors = 1;
my $die_on_warnings = 0;
my $die_on_notes = 0;
my $print_datablock_name = 0;
#* OPTIONS:
#* -c, --continue-on-errors
#* Keep processing subsequent data blocks even if one data
#* block had fatal processing errors.
#* -c-, --die-on-errors, --no-continue-on-errors,
#* --dont-continue-on-errors, --do-not-continue-on-errors
#* Terminate script immediately if some data block could
#* not be processed (default).
#*
#* --continue-on-warnings
#* Do not terminate script if warnings are raised (default)
#* --die-on-warnings
#* Terminate script immediately if warnings are raised
#*
#* --continue-on-notes
#* Do not terminate script if notes are raised (default)
#* --die-on-notes
#* Terminate script immediately if notes are raised
#*
#* -Z, --cell-formula-units-Z 1
#* Specify number of formula sum units in the unit cell.
#* Default: taken from the input CIF if present, otherwise
#* assumed to be 1.
#*
#* --use-attached-hydrogens
#* Include number of implicit hydrogens, specified using
#* _atom_site_attached_hydrogens tag, into the formula
#* sum (default).
#* --no-use-attached-hydrogens,
#* --dont-use-attached-hydrogens,
#* --ignore-attached-hydrogens
#* Ignore number of implicit hydrogens, specified using
#* _atom_site_attached_hydrogens tag, in calculation of
#* the formula sum.
#*
#* --assume-full-occupancies
#* Assume that all atoms have full (1.0) occupancies.
#* --no-assume-full-occupancies,
#* --dont-assume-full-occupancies,
#* --use-original-occupancies
#* Use original atom site occupancies, as given in CIF file
#* (default).
#*
#* --print-datablock-name
#* Print data block name, tab-separated, before each formula.
#* --no-print-datablock-name,
#* --dont-print-datablock-name,
#* --do-not-print-datablock-name
#* Do not print data block name (default).
#*
#* --use-perl-parser
#* Use Perl parser to parse CIF files.
#* --use-c-parser
#* Use C parser to parse CIF files (default).
#*
#* --help, --usage
#* Output a short usage message (this message) and exit.
#* --version
#* Output version information and exit.
#**
@ARGV = getOptions(
"-c,--continue-on-errors" => sub { $die_on_errors = 0 },
"-c-,--dont-continue-on-errors" => sub { $die_on_errors = 1 },
"--die-on-errors" => sub { $die_on_errors = 1 },
"--do-not-continue-on-errors" => sub { $die_on_errors = 1 },
"--no-continue-on-errors" => sub { $die_on_errors = 1 },
"--continue-on-warnings" => sub { $die_on_warnings = 0 },
"--die-on-warnings" => sub { $die_on_warnings = 1 },
"--continue-on-notes" => sub { $die_on_notes = 0 },
"--die-on-notes" => sub { $die_on_notes = 1 },
"-Z,--cell-formula-units-Z" => \$Z_value,
"--use-attached-hydrogens" => sub { $use_attached_hydrogens = 1 },
"--dont-use-attached-hydrogens" => sub { $use_attached_hydrogens = 0 },
"--no-use-attached-hydrogens" => sub { $use_attached_hydrogens = 0 },
"--ignore-attached-hydrogens" => sub { $use_attached_hydrogens = 0 },
"--assume-full-occupancies" => sub { $assume_full_occupancies = 1 },
"--dont-assume-full-occupancies" => sub { $assume_full_occupancies = 0 },
"--no-assume-full-occupancies" => sub { $assume_full_occupancies = 0 },
"--use-original-occupancies" => sub { $assume_full_occupancies = 0 },
"--print-datablock-name" => sub{ $print_datablock_name = 1 },
"--no-print-datablock-name" => sub{ $print_datablock_name = 0 },
"--dont-print-datablock-name" => sub{ $print_datablock_name = 0 },
"--do-not-print-datablock-name" => sub{ $print_datablock_name = 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 get_version_string(), "\n"; exit }
);
@ARGV = ( "-" ) unless @ARGV;
binmode STDOUT, ':encoding(UTF-8)';
binmode STDERR, ':encoding(UTF-8)';
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 );
canonicalize_all_names( $data );
for my $dataset (@$data) {
my $dataname = 'data_' . $dataset->{name};
my $values = $dataset->{values};
local $SIG{__WARN__} = sub { process_warnings( {
'message' => @_,
'program' => $0,
'filename' => $filename,
'add_pos' => $dataname
}, {
'WARNING' => $die_on_warnings,
'NOTE' => $die_on_notes
} ) };
my $formula;
eval {
if ( defined $Z_value &&
exists $values->{'_cell_formula_units_Z'} ) {
my $file_Z = $values->{_cell_formula_units_Z}[0];
if( $Z_value != $file_Z ) {
warn "WARNING, overriding _cell_formula_units_Z ($file_Z) " .
"with command-line value $Z_value" . "\n";
}
}
$formula = cif_cell_contents ( $dataset, $Z_value,
$use_attached_hydrogens,
$assume_full_occupancies );
};
if ( $@ ) {
process_errors( {
'message' => $@,
'program' => $0,
'filename' => $filename,
'add_pos' => $dataname
}, $die_on_errors )
};
if( defined $formula ) {
if( $print_datablock_name ) {
print $dataset->{name}, "\t";
}
print $formula, "\n";
}
}
}
|
