Files
rdkit/Code/GraphMol/Wrap/substructmethods.h
Paolo Tosco 350370abe3 - Changed all unsigned to unsigned int for clarity (#6646)
- Switched from dynamic to static allocation for an instance of `MCSParameters`
- Switched to using `auto` where possible
- Added a few `CHECK_INVARIANT` where appropriate before dereferencing pointers
- Moved some inline comments to the previous line to improve readability
- Added a early check for `CompleteRingsOnly` in `checkBondRingMatch()` to improve computational efficiency
- Removed `RingMatchTableSet` entirely as 1) it is unnecessary since its functionality is already provided by `RingInfo` 2) it abused the `userData` pointer. This allows cleaning up and simplifying the code, particularly the Python wrappers which had a significant amount of added complexity to support it
- Removed all the code that was deprecated several releases ago
- Reimplemented ringFusionCheck() from scratch to address several bug reports; also switched from std::set to boost::dynamic_bitset for better efficiency
- Replaced boost::tie with boost::make_iterator_range
- Modernized `for` loops where possible
- Removed entirely the QueryRings structure as its functionality is already available in RingInfo
- Removed entirely the _DFS() function since the same algorithm can be implemented in a simpler and more efficient way using RingInfo (from 2m28.441s to 2m9.859s for the same task)
- Replaced std::vector<bool> with boost::dynamic_bitset
- Replaced C-style casts with C++ casts
- Replaced some size_t with unsigned int
- Refactored checkIfRingsAreClosed() such that checkNoLoneRingAtoms() is not needed anymore
- Added a test for slow runtimes with CompleteRingsOnly
- Setting Timeout to 0 means no timeout, as it should be
- Removed unused `steps` variable from `MaximumCommonSubgraph::growSeeds`
- Storing both Atom and Bond pointers and their indices on Seed and MCS data structures is time-consuming and a potential source of incons
istencies; storing pointers is sufficient
- Promoted `MaximumCommonSubgraph::match` from `private` to `public`
- `NewBonds` was declared `mutable`, but `Seed::fillNewBonds()` was incorrectly declared as `non-const`, which caused the need for an ugly
(and unnecessary) `const_cast`.
I have now removed the `const_cast` and correctly declared functions that alter `NewBonds` as `const`, since `NewBonds` is explicitly `mut
able`
- Removed some useless random scoping that was peppering the MCS code
- Removed a significant amount of duplicate code from the Python wrappers by inheriting from a base `PyMCSWrapper` class
- Fixed #6082
- Fixed #5510
- Fixed #5457
- Fixed #5440
- Fixed #5411
- Fixed #3965
- Fixed #6578

Co-authored-by: ptosco <paolo.tosco@novartis.com>
2023-08-25 06:09:19 +02:00

132 lines
4.3 KiB
C++

//
// Copyright (C) 2017 Greg Landrum
//
// @@ 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 <RDGeneral/export.h>
#ifndef RDKIT_SUBSTRUCT_METHODS_H
#define RDKIT_SUBSTRUCT_METHODS_H
#include <boost/python.hpp>
#include <RDBoost/Wrap.h>
#include <GraphMol/Substruct/SubstructMatch.h>
namespace RDKit {
inline PyObject *convertMatches(const MatchVectType &matches) {
PyObject *res = PyTuple_New(matches.size());
std::for_each(matches.begin(), matches.end(), [res](const auto &pair) {
PyTuple_SetItem(res, pair.first, PyInt_FromLong(pair.second));
});
return res;
}
inline PyObject *convertMatchesToTupleOfPairs(const MatchVectType &matches) {
PyObject *res = PyTuple_New(matches.size());
std::for_each(matches.begin(), matches.end(),
[res, &matches](const auto &pair) {
PyObject *pyPair = PyTuple_New(2);
PyTuple_SetItem(pyPair, 0, PyInt_FromLong(pair.first));
PyTuple_SetItem(pyPair, 1, PyInt_FromLong(pair.second));
PyTuple_SetItem(res, &pair - &matches.front(), pyPair);
});
return res;
}
template <typename T1, typename T2>
bool HasSubstructMatch(T1 &mol, T2 &query, bool recursionPossible = true,
bool useChirality = false,
bool useQueryQueryMatches = false) {
NOGIL gil;
MatchVectType res;
return SubstructMatch(mol, query, res, recursionPossible, useChirality,
useQueryQueryMatches);
}
template <typename T1, typename T2>
PyObject *GetSubstructMatch(T1 &mol, T2 &query, bool useChirality = false,
bool useQueryQueryMatches = false) {
MatchVectType matches;
{
NOGIL gil;
SubstructMatch(mol, query, matches, true, useChirality,
useQueryQueryMatches);
}
return convertMatches(matches);
}
template <typename T1, typename T2>
PyObject *GetSubstructMatches(T1 &mol, T2 &query, bool uniquify = true,
bool useChirality = false,
bool useQueryQueryMatches = false,
unsigned int maxMatches = 1000) {
std::vector<MatchVectType> matches;
int matched;
{
NOGIL gil;
matched = SubstructMatch(mol, query, matches, uniquify, true, useChirality,
useQueryQueryMatches, maxMatches);
}
PyObject *res = PyTuple_New(matched);
for (int idx = 0; idx < matched; idx++) {
PyTuple_SetItem(res, idx, convertMatches(matches[idx]));
}
return res;
}
template <typename T1, typename T2>
void pySubstructHelper(T1 &mol, T2 &query,
const SubstructMatchParameters &params,
std::vector<MatchVectType> &matches) {
if (params.extraFinalCheck) {
// NOTE: Because we are going into/out of python here, we can't
// run with NOGIL
matches = SubstructMatch(mol, query, params);
} else {
NOGIL gil;
matches = SubstructMatch(mol, query, params);
}
}
template <typename T1, typename T2>
bool helpHasSubstructMatch(T1 &mol, T2 &query,
const SubstructMatchParameters &params) {
SubstructMatchParameters ps = params;
ps.maxMatches = 1;
std::vector<MatchVectType> matches;
pySubstructHelper(mol, query, params, matches);
return matches.size() != 0;
}
template <typename T1, typename T2>
PyObject *helpGetSubstructMatch(T1 &mol, T2 &query,
const SubstructMatchParameters &params) {
SubstructMatchParameters ps = params;
ps.maxMatches = 1;
std::vector<MatchVectType> matches;
pySubstructHelper(mol, query, params, matches);
MatchVectType match;
if (matches.size()) {
match = matches[0];
}
return convertMatches(match);
}
template <typename T1, typename T2>
PyObject *helpGetSubstructMatches(T1 &mol, T2 &query,
const SubstructMatchParameters &params) {
std::vector<MatchVectType> matches;
pySubstructHelper(mol, query, params, matches);
PyObject *res = PyTuple_New(matches.size());
for (size_t idx = 0; idx < matches.size(); idx++) {
PyTuple_SetItem(res, idx, convertMatches(matches[idx]));
}
return res;
}
} // namespace RDKit
#endif