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
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
/**********************************************************************
Copyright (C) 2008 by Geoffrey Hutchison
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation version 2 of the License.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
***********************************************************************/
#include <openbabel/babelconfig.h>
#include <openbabel/obmolecformat.h>
#include <openbabel/mol.h>
#include <openbabel/atom.h>
#include <openbabel/elements.h>
#include <openbabel/generic.h>
#include <cstdlib>
#include <sstream>
using namespace std;
namespace OpenBabel
{
class MSIFormat : public OBMoleculeFormat
{
public:
//Register this format type ID
MSIFormat()
{
OBConversion::RegisterFormat("msi", this, "chemical/x-msi-msi");
}
virtual const char* Description() //required
{
return
"Accelrys/MSI Cerius II MSI format\n";
};
virtual const char* SpecificationURL()
{return "http://openbabel.org/wiki/MSI_format";}; //optional
virtual const char* GetMIMEType()
{ return "chemical/x-msi-msi"; };
//Flags() can return be any the following combined by | or be omitted if none apply
// NOTREADABLE READONEONLY NOTWRITABLE WRITEONEONLY
virtual unsigned int Flags()
{
return READONEONLY | NOTWRITABLE;
};
//*** This section identical for most OBMol conversions ***
////////////////////////////////////////////////////
/// The "API" interface functions
virtual bool ReadMolecule(OBBase* pOb, OBConversion* pConv);
};
//***
//Make an instance of the format class
MSIFormat theMSIFormat;
/////////////////////////////////////////////////////////////////
bool MSIFormat::ReadMolecule(OBBase* pOb, OBConversion* pConv)
{
OBMol* pmol = pOb->CastAndClear<OBMol>();
if (pmol == nullptr)
return false;
//Define some references so we can use the old parameter names
istream &ifs = *pConv->GetInStream();
OBMol &mol = *pmol;
const char* title = pConv->GetTitle();
char buffer[BUFF_SIZE];
stringstream errorMsg;
if (!ifs)
return false; // we're attempting to read past the end of the file
if (!ifs.getline(buffer,BUFF_SIZE))
{
obErrorLog.ThrowError(__FUNCTION__,
"Problems reading an MSI file: Cannot read the first line.", obWarning);
return(false);
}
if (!EQn(buffer, "# MSI CERIUS2 DataModel File", 28))
{
obErrorLog.ThrowError(__FUNCTION__,
"Problems reading an MSI file: The first line must contain the MSI header.", obWarning);
return(false);
}
// "records" start with
// (1 Model
// ....
// and end with
// ....
// )
unsigned int openParens = 0; // the count of "open parentheses" tags
unsigned int startBondAtom, endBondAtom, bondOrder;
bool atomRecord = false;
bool bondRecord = false;
OBAtom *atom;
// OBBond *bond;
vector<string> vs;
const SpaceGroup *sg;
bool setSpaceGroup = false;
double x,y,z;
vector3 translationVectors[3];
int numTranslationVectors = 0;
mol.BeginModify();
while (ifs.getline(buffer,BUFF_SIZE))
{
// model record
if (strstr(buffer, "Model") != nullptr) {
openParens++;
continue;
}
// atom record
if (!bondRecord && strstr(buffer, "Atom") != nullptr) {
atomRecord = true;
openParens++;
continue;
}
if (strstr(buffer, "Bond") != nullptr) {
bondRecord = true;
startBondAtom = endBondAtom = 0;
bondOrder = 1;
openParens++;
continue;
}
/* (A I PeriodicType 100)
(A D A3 (6.2380000000000004 0 0))
(A D B3 (0 6.9909999999999997 0))
(A D C3 (0 0 6.9960000000000004))
(A C SpaceGroup "63 5")
*/
if (strstr(buffer, "PeriodicType") != nullptr) {
ifs.getline(buffer,BUFF_SIZE); // next line should be translation vector
tokenize(vs,buffer);
while (vs.size() == 6) {
x = atof((char*)vs[3].erase(0,1).c_str());
y = atof((char*)vs[4].c_str());
z = atof((char*)vs[5].c_str());
translationVectors[numTranslationVectors++].Set(x, y, z);
if (!ifs.getline(buffer,BUFF_SIZE))
break;
tokenize(vs,buffer);
}
}
if (strstr(buffer, "SpaceGroup") != nullptr) {
tokenize(vs, buffer);
if (vs.size() != 5)
continue; // invalid space group
setSpaceGroup = true;
sg = SpaceGroup::GetSpaceGroup(vs[4]); // remove the initial " character
}
// atom information
if (atomRecord) {
if (strstr(buffer, "ACL") != nullptr) {
tokenize(vs, buffer);
// size should be 5 -- need a test here
if (vs.size() != 5) return false; // timvdm 18/06/2008
vs[3].erase(0,1); // "6 => remove the first " character
unsigned int atomicNum = atoi(vs[3].c_str());
if (atomicNum == 0)
atomicNum = 1; // hydrogen ?
// valid element, so create the atom
atom = mol.NewAtom();
atom->SetAtomicNum(atomicNum);
continue;
}
else if (strstr(buffer, "XYZ") != nullptr) {
tokenize(vs, buffer);
// size should be 6 -- need a test here
if (vs.size() != 6) return false; // timvdm 18/06/2008
vs[3].erase(0,1); // remove ( character
vs[5].erase(vs[5].length()-2, 2); // remove trailing )) characters
atom->SetVector(atof(vs[3].c_str()),
atof(vs[4].c_str()),
atof(vs[5].c_str()));
continue;
}
} // end of atom records
// bond information
if (bondRecord) {
if (strstr(buffer, "Atom1") != nullptr) {
tokenize(vs, buffer);
if (vs.size() < 4) return false; // timvdm 18/06/2008
vs[3].erase(vs[3].length()-1,1);
startBondAtom = atoi(vs[3].c_str());
continue;
}
else if (strstr(buffer, "Atom2") != nullptr) {
tokenize(vs, buffer);
if (vs.size() < 4) return false; // timvdm 18/06/2008
vs[3].erase(vs[3].length()-1,1);
endBondAtom = atoi(vs[3].c_str());
continue;
}
else if (strstr(buffer, "Type") != nullptr) {
tokenize(vs, buffer);
if (vs.size() < 4) return false; // timvdm 18/06/2008
vs[3].erase(vs[3].length()-1,1);
bondOrder = atoi(vs[3].c_str());
if (bondOrder == 4) // triple bond?
bondOrder = 3;
else if (bondOrder == 8) // aromatic?
bondOrder = 5;
else if (bondOrder != 2) // 1 OK, 2 OK, others unknown
bondOrder = 1;
continue;
}
}
// ending a "tag" -- a lone ")" on a line
if (strstr(buffer, ")") != nullptr && strstr(buffer, "(") == nullptr) {
openParens--;
if (atomRecord) {
atomRecord = false;
}
if (bondRecord) {
// Bond records appear to be questionable
mol.AddBond(startBondAtom - 1, endBondAtom - 1, bondOrder);
bondRecord = false;
}
if (openParens == 0) {
ifs.getline(buffer, BUFF_SIZE);
break; // closed this molecule
}
}
}
mol.EndModify();
// clean out any remaining blank lines
std::streampos ipos;
do
{
ipos = ifs.tellg();
ifs.getline(buffer,BUFF_SIZE);
}
while(strlen(buffer) == 0 && !ifs.eof() );
ifs.seekg(ipos);
/*
if (!pConv->IsOption("b",OBConversion::INOPTIONS))
mol.ConnectTheDots();
if (!pConv->IsOption("s",OBConversion::INOPTIONS) && !pConv->IsOption("b",OBConversion::INOPTIONS))
mol.PerceiveBondOrders();
*/
if (numTranslationVectors > 0) {
OBUnitCell* uc = new OBUnitCell;
uc->SetData(translationVectors[0], translationVectors[1], translationVectors[2]);
uc->SetOrigin(fileformatInput);
if (setSpaceGroup) {
uc->SetSpaceGroup(sg);
}
mol.SetData(uc);
}
return(true);
}
} //namespace OpenBabel