File: SparseBitVect.cpp

package info (click to toggle)
rdkit 201203-3
  • links: PTS, VCS
  • area: main
  • in suites: wheezy
  • size: 37,840 kB
  • sloc: cpp: 93,902; python: 51,897; java: 5,192; ansic: 3,497; xml: 2,499; sql: 1,641; yacc: 1,518; lex: 1,076; makefile: 325; fortran: 183; sh: 153; cs: 51
file content (348 lines) | stat: -rw-r--r-- 9,543 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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
// $Id: SparseBitVect.cpp 1625 2011-01-13 04:22:56Z glandrum $
//
// Copyright (c) 2001-2008 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 "SparseBitVect.h"
#include <RDBoost/Exceptions.h>

#include "base64.h"
#include <RDGeneral/StreamOps.h>
#include <sstream>
#include <limits>

#ifdef WIN32
#include <ios>
#endif
#include <boost/cstdint.hpp>


// """ -------------------------------------------------------
//
// Construct a SparseBitVect from a binary string.
//   The format of the string should be
//   the format produced by SparseBitVect::toString
//
// """ -------------------------------------------------------
SparseBitVect::SparseBitVect(const std::string &s)
{
  d_size=0;dp_bits = 0;
  initFromText(s.c_str(),s.length());
}


// """ -------------------------------------------------------
//
// Construct a SparseBitVect from a binary string stored as a char *.
//   The format of the string should be
//   the format produced by SparseBitVect::toString
//
// """ -------------------------------------------------------
SparseBitVect::SparseBitVect(const char *data,const unsigned int dataLen)
{
  d_size=0;dp_bits = 0;
  initFromText(data,dataLen);
}

// """ -------------------------------------------------------
//
//  Operator[]
//   Returns the state of the ith bit.
//
//   **C++ NOTE** The state of BitVects cannot be changed using
//    operator&.  So this will not work:
//     SBV[i] = 0;
//    In Python this type of assignment **is** valid.
//
// """ -------------------------------------------------------
bool
SparseBitVect::operator[](const unsigned int which) const
{
  if(which >= d_size){
    throw IndexErrorException(which);
  }
  if(dp_bits->count(which)) return true;
  else return false;
}

// """ -------------------------------------------------------
//
//  Assignment operator
//    The bits of the other SBV are copied.
//
// """ -------------------------------------------------------
SparseBitVect&
SparseBitVect::operator=(const SparseBitVect& other)
{
  IntSet *bv=other.dp_bits;
  if(dp_bits) delete dp_bits;
  d_size = other.getNumBits();
  dp_bits = new IntSet;
  std::copy(bv->begin(),bv->end(),std::inserter(*dp_bits,dp_bits->end()));

  return *this;
}


// -------------------------------------------------------
//
//  Operator|
//   allows SBV3 = SBV1|SBV2;
//
// -------------------------------------------------------
SparseBitVect
SparseBitVect::operator| (const SparseBitVect &other) const
{
  SparseBitVect ans(d_size);
  std::set_union(dp_bits->begin(),dp_bits->end(),
                 other.dp_bits->begin(),other.dp_bits->end(),
                 std::inserter(*(ans.dp_bits),ans.dp_bits->end()));
  return ans;
}

// """ -------------------------------------------------------
//
//  Operator&
//   allows SBV3 = SBV1&SBV2;
//
// """ -------------------------------------------------------
SparseBitVect
SparseBitVect::operator& (const SparseBitVect &other) const
{
  SparseBitVect ans(d_size);
  std::set_intersection(dp_bits->begin(),dp_bits->end(),
                        other.dp_bits->begin(),other.dp_bits->end(),
                        std::inserter(*(ans.dp_bits),ans.dp_bits->end()));
  return ans;
}

// """ -------------------------------------------------------
//
//  Operator^
//   allows SBV3 = SBV1^SBV2;
//
// """ -------------------------------------------------------
SparseBitVect
SparseBitVect::operator^ (const SparseBitVect &other) const
{
  SparseBitVect ans(d_size);
  std::set_symmetric_difference(dp_bits->begin(),dp_bits->end(),
                                other.dp_bits->begin(),other.dp_bits->end(),
                                std::inserter(*(ans.dp_bits),ans.dp_bits->end()));
  return(ans);
}

// """ -------------------------------------------------------
//
//  Operator~  (the negation operator)
//   allows SBV2 = ~SBV1;
//
// """ -------------------------------------------------------
SparseBitVect
SparseBitVect::operator~ () const
{
  SparseBitVect ans(d_size);
  for(unsigned int i=0;i<d_size;i++){
    if(!getBit(i)) ans.setBit(i);
  }
  
  return(ans);
}

// """ -------------------------------------------------------
//
// getBit(int which)
//   Returns the state of bit which
//
// """ -------------------------------------------------------
bool
SparseBitVect::getBit(const unsigned int which) const
{
  if(which >= d_size){
    throw IndexErrorException(which);
  }
  if(dp_bits->count(which)) return true;
  else return false;
}


// """ -------------------------------------------------------
//
// getBit(const IntVectIter which)  (C++ SPECIFIC)
//   Returns the state of bit which
//
// """ -------------------------------------------------------
bool
SparseBitVect::getBit (const IntVectIter which) const
{
  if(*which < 0 || static_cast<unsigned int>(*which) >= d_size){
    throw IndexErrorException(*which);
  }
  if(dp_bits->count(*which)) return true;
  else return false;

}

// """ -------------------------------------------------------
//
// getBit(const IntSetIter which)  (C++ SPECIFIC)
//   Returns the state of bit which
//
// """ -------------------------------------------------------
bool
SparseBitVect::getBit (const IntSetIter which) const
{
  if(*which < 0 || static_cast<unsigned int>(*which) >= d_size){
    throw IndexErrorException(*which);
  }
  if(dp_bits->count(*which)) return true;
  else return false;

}

// """ -------------------------------------------------------
//
//  Sets bit which to be on.
//
//  Returns the original state of the bit
//
// """ -------------------------------------------------------
bool
SparseBitVect::setBit(const unsigned int which)
{
  if(!dp_bits){
    throw ValueErrorException("BitVect not properly initialized.");
  }
  std::pair<IntSetIter,bool> res;
  if(which >= d_size){
    throw IndexErrorException(which);
  }
  res = dp_bits->insert(which);
  return !(res.second);
}

// """ -------------------------------------------------------
//
// setBit(const IntSetIter which)  (C++ SPECIFIC)
//  Sets bit which to be on.
//
//  Returns the original state of the bit
//
// """ -------------------------------------------------------
bool
SparseBitVect::setBit(const IntSetIter which)
{
  if(!dp_bits){
    throw ValueErrorException("BitVect not properly initialized.");
  }
  std::pair<IntSetIter,bool> res;
  if(*which < 0 || static_cast<unsigned int>(*which) >= d_size){
    throw IndexErrorException(*which);
  }
  res = dp_bits->insert(*which);
  return !(res.second);
}

// """ -------------------------------------------------------
//
//  Sets bit which to be off.
//
//  Returns the original state of the bit
//
// """ -------------------------------------------------------
bool
SparseBitVect::unsetBit(const unsigned int which)
{
  if(!dp_bits){
    throw ValueErrorException("BitVect not properly initialized.");
  }
  if(which >= d_size){
    throw IndexErrorException(which);
  }

  if(dp_bits->count(which)){
    dp_bits->erase(dp_bits->find(which));
    return true;
  }
  else{
    return false;
  }
}

// """ -------------------------------------------------------
//
// getOnBits(IntVect &which)
//  C++: Passes the set of on bits out in the IntVect passed in.
//   The contents of IntVect are destroyed.
//
//  Python: Returns the tuple of on bits
//
// """ -------------------------------------------------------
void
SparseBitVect::getOnBits(IntVect& v) const
{
  if(!dp_bits){
    throw ValueErrorException("BitVect not properly initialized.");
  }
  unsigned int nOn = getNumOnBits();
  if(!v.empty()) IntVect().swap(v);
  v.reserve(nOn);
  v.resize(nOn);
  std::copy(dp_bits->begin(),dp_bits->end(),v.begin());
};

// """ -------------------------------------------------------
//
// toString()
//  Returns a binary string with the contents of the BitVector
//
// """ -------------------------------------------------------
std::string SparseBitVect::toString() const {
  // This Function replaces the older version (version 16) of writing the onbits to
  // a string
  // the old version does not perform any run length encoding, it only checks to see if 
  // the length of the bitvect can be short ints and writes the on bits as shorts 
  // other wise the onbits are all written as ints

  // here we do run length encoding and the version number has been bumped to 32 as well. 
  // only the reader needs to take care of readinf all legacy versions
  // also in this scheme each bit number written to the string is checked to see how many 
  // bytes it needs
  std::stringstream ss(std::ios_base::binary|std::ios_base::out|std::ios_base::in);

  boost::int32_t tInt = ci_BITVECT_VERSION*-1;
  RDKit::streamWrite(ss,tInt);
std::cerr<<"version: "<<tInt<<std::endl;
  tInt=d_size;
  RDKit::streamWrite(ss,tInt);
std::cerr<<"size: "<<tInt<<std::endl;

  tInt=getNumOnBits();
  RDKit::streamWrite(ss,tInt);
std::cerr<<"nOn: "<<tInt<<std::endl;


  int prev = -1;
  unsigned int zeroes;
  for (IntSetIter i=dp_bits->begin(); i!=dp_bits->end(); i++) {
    zeroes = *i - prev -1;
    RDKit::appendPackedIntToStream(ss, zeroes);
    prev = *i;
  }
  zeroes = d_size - prev -1;
  RDKit::appendPackedIntToStream(ss, zeroes);
  
  std::string res(ss.str());
  return res;
  }

void SparseBitVect::_initForSize(unsigned int size){
  d_size=size;
  if(dp_bits) delete dp_bits;
  dp_bits=new IntSet;
};