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
|
# -*- coding: utf-8 -*-
#
# Copyright (c) 2017, the cclib development team
#
# This file is part of cclib (http://cclib.github.io) and is distributed under
# the terms of the BSD 3-Clause License.
"""A writer for chemical markup language (CML) files."""
import xml.etree.cElementTree as ET
from cclib.io import filewriter
from cclib.parser.utils import find_package
_has_openbabel = find_package("openbabel")
class CML(filewriter.Writer):
"""A writer for chemical markup language (CML) files."""
def __init__(self, ccdata, *args, **kwargs):
"""Initialize the CML writer object.
Inputs:
ccdata - An instance of ccData, parsed from a logfile.
"""
# Call the __init__ method of the superclass
super(CML, self).__init__(ccdata, *args, **kwargs)
def generate_repr(self):
"""Generate the CML representation of the logfile data."""
# Create the base molecule.
molecule = ET.Element('molecule')
d = {
# Write the namespace directly.
'xmlns': 'http://www.xml-cml.org/schema',
}
if self.jobfilename is not None:
d['id'] = self.jobfilename
_set_attrs(molecule, d)
# Form the listing of all the atoms present.
atomArray = ET.SubElement(molecule, 'atomArray')
if hasattr(self.ccdata, 'atomcoords') and hasattr(self.ccdata, 'atomnos'):
elements = [self.pt.element[Z] for Z in self.ccdata.atomnos]
for atomid in range(self.ccdata.natom):
atom = ET.SubElement(atomArray, 'atom')
x, y, z = self.ccdata.atomcoords[-1][atomid].tolist()
d = {
'id': 'a{}'.format(atomid + 1),
'elementType': elements[atomid],
'x3': '{:.10f}'.format(x),
'y3': '{:.10f}'.format(y),
'z3': '{:.10f}'.format(z),
}
_set_attrs(atom, d)
# Form the listing of all the bonds present.
bondArray = ET.SubElement(molecule, 'bondArray')
if _has_openbabel:
for bc in self.bond_connectivities:
bond = ET.SubElement(bondArray, 'bond')
d = {
'atomRefs2': 'a{} a{}'.format(bc[0] + 1, bc[1] + 1),
'order': str(bc[2]),
}
_set_attrs(bond, d)
_indent(molecule)
return _tostring(molecule)
def _set_attrs(element, d):
"""Set all the key-value pairs from a dictionary as element
attributes.
"""
for (k, v) in d.items():
element.set(k, v)
return
def _indent(elem, level=0):
"""An in-place pretty-print indenter for XML."""
i = "\n" + (level * " ")
if len(elem):
if not elem.text or not elem.text.strip():
elem.text = i + " "
if not elem.tail or not elem.tail.strip():
elem.tail = i
for elem in elem:
_indent(elem, level+1)
if not elem.tail or not elem.tail.strip():
elem.tail = i
else:
if level and (not elem.tail or not elem.tail.strip()):
elem.tail = i
def _tostring(element, xml_declaration=True, encoding='utf-8', method='xml'):
"""A reimplementation of tostring() found in ElementTree."""
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ET.ElementTree(element).write(file,
xml_declaration=xml_declaration,
encoding=encoding,
method=method)
return b''.join(data).decode(encoding)
del find_package
|
