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
|
#! /bin/sh
#------------------------------------------------------------------------------
#$Author: antanas $
#$Date: 2020-07-09 21:12:32 +0300 (Thu, 09 Jul 2020) $
#$Revision: 8170 $
#$URL: svn+ssh://www.crystallography.net/home/coder/svn-repositories/cod-tools/tags/v3.1.0/scripts/codcif2sdf $
#------------------------------------------------------------------------------
#*
#* Convert CIFs with crystal description (similar to those obtained from
#* the COD) to an SDF file with a molecule description.
#* Intended to be suitable for upload to PubChem.
#*
#* USAGE:
#* $0 --options < file1.cif
#* $0 --options file1.cif
#* $0 --options file1.cif file2*.cif
#**
TMP_DIR="${TMPDIR}"
set -ue
## set -x
script() { echo "# $*"; cat; }
setvar() { eval $1="'$3'"; }
setvar Id = '$Id: codcif2sdf 8170 2020-07-09 18:12:32Z antanas $'
setvar FILES = ""
setvar BASENAME = "`basename $0`"
setvar IGNORE_BUMPS_OPT = ""
#* OPTIONS:
#* -i, --ignore-bumps
#* Ignore atomic bumps while running cif_molecule.
#*
#* --tmp-dir /tmp
#* Use the specified temporary directory (default: '/tmp').
#*
#* --help, --usage
#* Output a short help message (this message) and exit.
#* --version
#* Output version information and exit.
#**
while [ $# -gt 0 ]
do
case $1 in
-i|--ignore-bumps|--ignore-bump|--ignore-bum|--ignore-bu|--ignore-b|\
--ignore|--ignor|--igno|--ign|--ig|--i)
IGNORE_BUMPS_OPT="-i"
;;
--tmp-dir|--tmp-di|--tmp-d|--tmp|--tm|--t)
TMP_DIR="$2"
shift
;;
--options|--option|--optio|--opti|--opt|--op|--o)
echo "`basename $0`:: The '--options' option is a placeholder."
echo "`basename $0`:: It should be replaced by one of the following options:"
awk '/#\* OPTIONS:/,/#\*\*/ {
sub("OPTIONS:", ""); \
sub("^ *#[*]?[*]?", ""); \
gsub("\\$0","'$0'"); \
print $0
}' $0
exit
;;
--help|--hel|--he|--h|--usage)
awk '/#\*/,/#\*\*/ {
sub("^ *#[*]?[*]?", ""); \
gsub("\\$0","'$0'"); \
print $0
}' $0
exit
;;
--version)
$(dirname $0)/cod-tools-version
exit
;;
-*) echo "`basename $0`:: ERROR, unknown option '$1'." >&2 ; exit 1 ;;
*) FILES="$FILES '$1'" ;;
esac
shift
done
## echo ${FILES}
eval set -- "${FILES}"
test -n "${FILES}" && FILES="-"
test -z "${TMP_DIR}" && TMP_DIR="/tmp"
TMP_DIR="${TMP_DIR}/tmp-${BASENAME}-$$"
mkdir "${TMP_DIR}"
TMP_SPLIT_DIR="${TMP_DIR}/split"
mkdir ${TMP_SPLIT_DIR}
TMP_CIF="${TMP_DIR}/-"
## set -x
for CIF in ${1+"$@"}
do
if [ ${CIF} = "-" ]
then
echo $0: $CIF: reading CIF from STDIN... >&2
cat > ${TMP_CIF}
CIF=${TMP_CIF}
else
if [ ! -e ${CIF} ]
then
echo $0: $CIF: file does not exist. >&2
continue
fi
fi
cif_molecule \
--preserve-stoichiometry \
--one-datablock-output \
--split-disorder-groups \
--largest-molecule-only \
${IGNORE_BUMPS_OPT} \
"${CIF}" \
| molcif2sdf --cod-cif "${CIF}" --tmp-dir "${TMP_DIR}"
done
## set -x
rm -rf "${TMP_DIR}"
|
