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
|
#! /bin/sh
#!perl -w # --*- Perl -*--
eval 'exec perl -x $0 ${1+"$@"}'
if 0;
#------------------------------------------------------------------------------
#$Author: antanas $
#$Revision: 9355 $
#$URL: svn+ssh://www.crystallography.net/home/coder/svn-repositories/cod-tools/tags/v3.11.0/scripts/cif2json $
#$Date: 2022-07-31 23:15:34 +0300 (Sun, 31 Jul 2022) $
#------------------------------------------------------------------------------
#*
#* Parse CIF file and print out the structure generated by CIF parser.
#*
#* USAGE:
#* $0 [options] input.cif [input2.cif ...]
#**
use strict;
use COD::CIF::JSON qw( cif2json );
use COD::CIF::Parser qw( parse_cif );
use COD::CIF::Tags::CanonicalNames qw( canonicalize_all_names );
use COD::UserMessage qw( error );
use COD::SOptions qw( getOptions );
use COD::SUsage qw( usage );
use COD::ToolsVersion qw( get_version_string );
my $use_parser = 'c';
my %options;
my $strict = 0;
my $canonical = 0;
@ARGV = getOptions(
#* OPTIONS:
#* --fix-errors
#* Try to fix syntax errors in the input CIF files that can
#* be corrected unambiguously.
#*
#* --dont-fix-errors, --no-fix-errors
#* Do not try to fix syntax errors in input CIF files (default).
#*
#* --strict
#* Strictly adhere to JSON syntax, i.e., make a top level
#* list container for CIF data blocks and put comma (",")
#* separators between consecutive CIF data blocks.
#* --no-strict, --relaxed, --stream, --concatenate
#* Print stream of JSON objects, where an object stands for
#* a CIF data block. Such output does not include comma (",")
#* separators between top level objects, thus streaming
#* parsers have to be used (default).
#*
#* --canonical
#* Print JSON objects with key-value pairs sorted in a
#* canonical way. The usage of this option is discouraged
#* due to the added overhead.
#* --no-canonical
#* Print JSON object with key-value pairs sorted in the
#* order Perl stores them. Due to this, the outputs might
#* differ between different runs of the script with
#* identical parameters (default).
#*
#* --use-c-parser
#* Use Perl & C parser for CIF parsing (default).
#* --use-perl-parser
#* Use Perl parser for CIF parsing.
#*
#* --help,--usage
#* Output a short usage message (this message) and exit.
#* --version
#* Output version information and exit.
#**
"--use-perl-parser" => sub{ $use_parser = 'perl' },
"--use-c-parser" => sub{ $use_parser = 'c' },
"--strict" => sub{ $strict = 1 },
"--no-strict,--relaxed,--stream,--concatenate" => sub{ $strict = 0 },
'--canonical' => sub { $canonical = 1 },
'--no-canonical' => sub { $canonical = 0 },
"--fix-errors" => sub{ $options{fix_errors} = 1 },
"--no-fix-errors" => sub{ $options{fix_errors} = 0 },
"--dont-fix-errors" => sub{ $options{fix_errors} = 0 },
"--do-not-unprefix-text" => sub{ $options{do_not_unprefix_text} = 1 },
"--do-not-unfold-text" => sub{ $options{do_not_unfold_text} = 1 },
"--fix-duplicate-tags-with-same-values" =>
sub{ $options{fix_duplicate_tags_with_same_values} = 1 },
"--fix-duplicate-tags-with-empty-values" =>
sub{ $options{fix_duplicate_tags_with_empty_values} = 1 },
"--fix-data-header" => sub{ $options{fix_data_header} = 1 },
"--fix-datablock-names" => sub{ $options{fix_datablock_names} = 1 },
"--fix-string-quotes" => sub{ $options{fix_string_quotes} = 1 },
"--fix-missing-closing-double-quote" =>
sub{ $options{fix_missing_closing_double_quote} = 1 },
"--fix-missing-closing-single-quote" =>
sub{ $options{fix_missing_closing_single_quote} = 1 },
"--fix-ctrl-z" => sub{ $options{fix_ctrl_z} = 1 },
"--allow-uqstring-brackets" => sub{ $options{allow_uqstring_brackets} = 1 },
'--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)';
my $json_options = {
'canonical' => $canonical
};
print '[' if $strict;
my $first = 1;
for my $filename (@ARGV) {
my $options = { 'parser' => $use_parser, 'no_print' => 1 };
my ( $data, $err_count, $messages ) = parse_cif( $filename, $options );
if ( $err_count > 0 ) {
print STDERR $_ foreach ( @$messages );
error( {
'program' => $0,
'filename' => $filename,
'message' =>
"$err_count error(s) encountered while parsing the file"
} );
next;
}
print STDERR $_ foreach ( @$messages );
canonicalize_all_names( $data, $options );
foreach( @$data ) {
print ',' if $strict && !$first;
$first = 0;
print cif2json( $_, $json_options );
}
}
print ']' if $strict;
|
