File: FeatureParser.cpp

package info (click to toggle)
rdkit 201809.1%2Bdfsg-6
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 123,688 kB
  • sloc: cpp: 230,509; python: 70,501; java: 6,329; ansic: 5,427; sql: 1,899; yacc: 1,739; lex: 1,243; makefile: 445; xml: 229; fortran: 183; sh: 123; cs: 93
file content (317 lines) | stat: -rw-r--r-- 10,770 bytes parent folder | download
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
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
// $Id$
//
//  Copyright (C) 2004-2008 Greg Landrum and Rational Discovery LLC
//
//   @@ All Rights Reserved @@
//  This file is part of the RDKit.
//  The contents are covered by the terms of the BSD license
//  which is included in the file license.txt, found at the root
//  of the RDKit source tree.
//
#include "FeatureParser.h"
#include "MolChemicalFeatureDef.h"
#include <RDGeneral/StreamOps.h>
#include <GraphMol/RDKitBase.h>
#include <GraphMol/SmilesParse/SmilesParse.h>

#include <boost/shared_ptr.hpp>
#include <boost/tokenizer.hpp>
#include <boost/algorithm/string.hpp>
#include <boost/lexical_cast.hpp>
#include <boost/tokenizer.hpp>
typedef boost::tokenizer<boost::char_separator<char> > tokenizer;

#include <fstream>
#include <sstream>
#include <map>

namespace RDKit {
namespace Local {
typedef boost::tokenizer<boost::escaped_list_separator<char> > CommaTokenizer;

void getNextLine(std::istream &inStream, std::string &line,
                 unsigned int &lineNo) {
  if (inStream.eof()) return;
  line = "";
  bool continuationLine = false;
  while (!inStream.eof()) {
    std::string tmpLine;
    std::getline(inStream, tmpLine);
    lineNo++;
    // std::cerr << ">> " << lineNo << " " << tmpLine << std::endl;
    if (tmpLine == "") continue;
    if (tmpLine[0] != '#') {
      // strip space at the end to check for a continuation line:
      std::string stripLine =
          boost::trim_right_copy_if(tmpLine, boost::is_any_of(" \t\r\n"));
      if (stripLine == "") continue;
      if (stripLine[stripLine.size() - 1] != '\\') {
        if (continuationLine) {
          // if it's a continuation line, strip any whitespace:
          boost::trim_if(tmpLine, boost::is_any_of(" \t\r\n"));
        }
        line += tmpLine;
        return;
      } else {
        continuationLine = true;
        boost::trim_if(tmpLine, boost::is_any_of(" \t\r\n"));
        line += tmpLine.substr(0, tmpLine.size() - 1);
      }
    }
  }
}

// ------------------------------------------------------
bool expandAndTestSmarts(
    std::string &smarts,
    const std::map<std::string, std::string> &atomTypeDefs) {
  for (const auto &atomTypeDef : atomTypeDefs) {
    std::string atomName = atomTypeDef.first;
    std::string atomSma = atomTypeDef.second;
    boost::replace_all(smarts, atomName, atomSma);
  }

  RWMol *mol = nullptr;
  try {
    mol = SmartsToMol(smarts);
  } catch (SmilesParseException &) {
    return false;
  }
  if (mol) {
    delete mol;
  } else {
    return false;
  }
  return true;
}

// ------------------------------------------------------
void parseAtomType(const std::string &inLine,
                   std::map<std::string, std::string> &atomTypeDefs,
                   const unsigned int &lineNo) {
  boost::char_separator<char> sep(" \t");
  boost::tokenizer<boost::char_separator<char> > tok(inLine, sep);
  boost::tokenizer<boost::char_separator<char> >::iterator tokIt = tok.begin();
  if (tokIt == tok.end()) {
    throw FeatureFileParseException(lineNo, inLine,
                                    "empty input line for AtomType");
  }
  std::string keyword = boost::to_upper_copy(*tokIt);
  if (keyword != "ATOMTYPE") {
    throw FeatureFileParseException(lineNo, inLine,
                                    "bad input line for AtomType");
  }

  tokIt++;
  if (tokIt == tok.end()) {
    throw FeatureFileParseException(lineNo, inLine,
                                    "bad AtomType line, missing label");
  }
  std::string atomType = *tokIt;
  bool negater = false;
  if (atomType[0] == '!') {
    atomType.erase(0, 1);
    negater = true;
  }
  atomType = "{" + atomType + "}";
  tokIt++;
  if (tokIt == tok.end()) {
    throw FeatureFileParseException(lineNo, inLine,
                                    "bad AtomType line, missing definition");
  }
  std::string sma;
  if (atomTypeDefs.count(atomType)) {
    std::string base = atomTypeDefs[atomType];
    sma = "$(" + *tokIt + ")";
    if (negater) {
      std::string toAdd = "[!" + sma + ";";
      boost::replace_first(base, "[", toAdd);
    } else {
      std::string toAdd = "," + sma + "]";
      boost::replace_last(base, "]", toAdd);
    }
    sma = base;
  } else {
    sma = "$(" + *tokIt + ")";
  }
  // make it a valid smarts definition for an atom:
  sma = "[" + sma + "]";
  // make sure we get sensible SMARTS:
  if (!expandAndTestSmarts(sma, atomTypeDefs)) {
    std::string msg = "invalid SMARTS in AtomType (" + atomType + "): " + sma;
    throw FeatureFileParseException(lineNo, inLine, msg);
  }
  // now cut the brackets back off:
  sma = sma.substr(1, sma.size() - 2);
  atomTypeDefs[atomType] = sma;
}

// ------------------------------------------------------
MolChemicalFeatureDef *parseFeatureDef(
    std::istream &inStream, const std::string &inLine, unsigned int &lineNo,
    const std::map<std::string, std::string> &atomTypeDefs) {
  std::string nextLine = inLine;
  MolChemicalFeatureDef *res = nullptr;

  // handle a blank or comment first line:
  boost::trim_if(nextLine, boost::is_any_of(" \t\r\n"));
  while (nextLine == "" || nextLine[0] == '#') {
    Local::getNextLine(inStream, nextLine, lineNo);
    // need to check for EOS before we strip:
    if (nextLine == "") {
      // we hit EOS:
      throw FeatureFileParseException(lineNo, inLine,
                                      "EOF hit parsing feature definition");
    }
    boost::trim_if(nextLine, boost::is_any_of(" \t\r\n"));
  }

  boost::char_separator<char> sep(" \t");
  boost::tokenizer<boost::char_separator<char> > tok(nextLine, sep);
  if (tok.begin() == tok.end()) {
    throw FeatureFileParseException(lineNo, inLine,
                                    "bad DefineFeature line, no tokens found");
  }
  boost::tokenizer<boost::char_separator<char> >::iterator tokIt = tok.begin();
  tokIt++;
  if (tokIt == tok.end()) {
    throw FeatureFileParseException(lineNo, inLine,
                                    "bad DefineFeature line, missing subtype");
  }
  std::string subType = *tokIt;
  tokIt++;
  if (tokIt == tok.end()) {
    throw FeatureFileParseException(lineNo, inLine,
                                    "bad DefineFeature line, missing pattern");
  }
  std::string pattern = *tokIt;

  //---------------
  // make sure we get sensible SMARTS:
  //
  if (!expandAndTestSmarts(pattern, atomTypeDefs)) {
    std::string msg =
        "invalid SMARTS in DefineFeature for type " + subType + ": " + pattern;
    throw FeatureFileParseException(lineNo, inLine, msg);
  }

  //---------------
  // read out the rest of the definition
  //
  std::vector<double> weights;
  std::string family = "";
  bool foundEnd = false;
  Local::getNextLine(inStream, nextLine, lineNo);
  // std::getline(inStream,nextLine);
  while (nextLine != "") {
    boost::trim_if(nextLine, boost::is_any_of(" \t\r\n"));
    if (nextLine != "" && nextLine[0] != '#') {
      tok.assign(nextLine, sep);
      tokIt = tok.begin();
      std::string token = boost::to_upper_copy(*tokIt);
      if (token == "ENDFEATURE") {
        foundEnd = true;
        break;
      } else if (token == "FAMILY") {
        tokIt++;
        if (tokIt == tok.end()) {
          std::string msg = "bad Type line for feature: " + subType;
          throw FeatureFileParseException(lineNo, inLine, msg);
        }
        family = *tokIt;
      } else if (token == "WEIGHTS") {
        tokIt++;
        if (tokIt == tok.end()) {
          std::string msg = "bad Weights line for feature: " + subType;
          throw FeatureFileParseException(lineNo, inLine, msg);
        }
        CommaTokenizer commaTok(*tokIt);
        for (CommaTokenizer::const_iterator commaTokIt = commaTok.begin();
             commaTokIt != commaTok.end(); commaTokIt++) {
          std::string number = *commaTokIt;
          try {
            weights.push_back(boost::lexical_cast<double>(number));
          } catch (boost::bad_lexical_cast &) {
            std::string msg =
                "bad weight value (" + number + ") for feature: " + subType;
            throw FeatureFileParseException(lineNo, inLine, msg);
          }
        }
      } else {
        std::string msg = "bad input line for feature: " + subType;
        throw FeatureFileParseException(lineNo, inLine, msg);
      }
    }
    Local::getNextLine(inStream, nextLine, lineNo);
    // std::getline(inStream,nextLine);
  }
  if (!foundEnd) {
    std::string msg = "could not find EndFeature line for feature: " + subType;
    throw FeatureFileParseException(lineNo, inLine, msg);
  }
  if (family == "") {
    std::string msg = "did not find Family definition for feature: " + subType;
    throw FeatureFileParseException(lineNo, inLine, msg);
  }

  //---------------
  // Build the feature definition
  //
  res = new MolChemicalFeatureDef(pattern, family, subType);
  if (weights.size()) {
    res->setWeights(weights);
    res->normalizeWeights();
  }

  return res;
}
}  // end of namespace Local

// ------------------------------------------------------
int parseFeatureData(const std::string &defnText,
                     MolChemicalFeatureDef::CollectionType &featDefs) {
  std::stringstream ss(defnText);
  return parseFeatureData(ss, featDefs);
}

// ------------------------------------------------------
int parseFeatureData(std::istream &inStream,
                     MolChemicalFeatureDef::CollectionType &res) {
  unsigned int lineNo = 0;
  std::string inLine;
  Local::getNextLine(inStream, inLine, lineNo);
  std::map<std::string, std::string> atomTypeDefs;
  while (!inStream.eof()) {
    // clean any whitespace off the line:
    boost::trim_if(inLine, boost::is_any_of(" \t\r\n"));
    if (inLine != "" && inLine[0] != '#' && inLine[0] != '\n') {
      boost::tokenizer<> tok(inLine);
      boost::tokenizer<>::iterator tokIt = tok.begin();
      std::string token = boost::to_upper_copy(*tokIt);
      if (token == "ATOMTYPE") {
        Local::parseAtomType(inLine, atomTypeDefs, lineNo);
      } else if (token == "DEFINEFEATURE") {
        MolChemicalFeatureDef *fDef =
            Local::parseFeatureDef(inStream, inLine, lineNo, atomTypeDefs);
        if (fDef) res.push_back(boost::shared_ptr<MolChemicalFeatureDef>(fDef));
      } else {
        throw FeatureFileParseException(lineNo, inLine,
                                        "bad or missing keyword");
      }
    }
    // std::getline(inStream,inLine);
    Local::getNextLine(inStream, inLine, lineNo);
  }
  return 0;
}

// ------------------------------------------------------
int parseFeatureFile(const std::string &fileName,
                     MolChemicalFeatureDef::CollectionType &res) {
  std::ifstream inStream(fileName.c_str());
  if (!inStream || inStream.eof()) {
    return -1;
  }
  return parseFeatureData(inStream, res);
}
}