C++ algorithm like python's 'groupby' - c++

Are there any C++ transformations which are similar to itertools.groupby()?
Of course I could easily write my own, but I'd prefer to leverage the idiomatic behavior or compose one from the features provided by the STL or boost.
#include <cstdlib>
#include <map>
#include <algorithm>
#include <string>
#include <vector>
struct foo
{
int x;
std::string y;
float z;
};
bool lt_by_x(const foo &a, const foo &b)
{
return a.x < b.x;
}
void list_by_x(const std::vector<foo> &foos, std::map<int, std::vector<foo> > &foos_by_x)
{
/* ideas..? */
}
int main(int argc, const char *argv[])
{
std::vector<foo> foos;
std::map<int, std::vector<foo> > foos_by_x;
std::vector<foo> sorted_foos;
std::sort(foos.begin(), foos.end(), lt_by_x);
list_by_x(sorted_foos, foos_by_x);
return EXIT_SUCCESS;
}

This doesn't really answer your question, but for the fun of it, I implemented a group_by iterator. Maybe someone will find it useful:
#include <assert.h>
#include <iostream>
#include <set>
#include <sstream>
#include <string>
#include <vector>
using std::cout;
using std::cerr;
using std::multiset;
using std::ostringstream;
using std::pair;
using std::vector;
struct Foo
{
int x;
std::string y;
float z;
};
struct FooX {
typedef int value_type;
value_type operator()(const Foo &f) const { return f.x; }
};
template <typename Iterator,typename KeyFunc>
struct GroupBy {
typedef typename KeyFunc::value_type KeyValue;
struct Range {
Range(Iterator begin,Iterator end)
: iter_pair(begin,end)
{
}
Iterator begin() const { return iter_pair.first; }
Iterator end() const { return iter_pair.second; }
private:
pair<Iterator,Iterator> iter_pair;
};
struct Group {
KeyValue value;
Range range;
Group(KeyValue value,Range range)
: value(value), range(range)
{
}
};
struct GroupIterator {
typedef Group value_type;
GroupIterator(Iterator iter,Iterator end,KeyFunc key_func)
: range_begin(iter), range_end(iter), end(end), key_func(key_func)
{
advance_range_end();
}
bool operator==(const GroupIterator &that) const
{
return range_begin==that.range_begin;
}
bool operator!=(const GroupIterator &that) const
{
return !(*this==that);
}
GroupIterator operator++()
{
range_begin = range_end;
advance_range_end();
return *this;
}
value_type operator*() const
{
return value_type(key_func(*range_begin),Range(range_begin,range_end));
}
private:
void advance_range_end()
{
if (range_end!=end) {
typename KeyFunc::value_type value = key_func(*range_end++);
while (range_end!=end && key_func(*range_end)==value) {
++range_end;
}
}
}
Iterator range_begin;
Iterator range_end;
Iterator end;
KeyFunc key_func;
};
GroupBy(Iterator begin_iter,Iterator end_iter,KeyFunc key_func)
: begin_iter(begin_iter),
end_iter(end_iter),
key_func(key_func)
{
}
GroupIterator begin() { return GroupIterator(begin_iter,end_iter,key_func); }
GroupIterator end() { return GroupIterator(end_iter,end_iter,key_func); }
private:
Iterator begin_iter;
Iterator end_iter;
KeyFunc key_func;
};
template <typename Iterator,typename KeyFunc>
inline GroupBy<Iterator,KeyFunc>
group_by(
Iterator begin,
Iterator end,
const KeyFunc &key_func = KeyFunc()
)
{
return GroupBy<Iterator,KeyFunc>(begin,end,key_func);
}
static void test()
{
vector<Foo> foos;
foos.push_back({5,"bill",2.1});
foos.push_back({5,"rick",3.7});
foos.push_back({3,"tom",2.5});
foos.push_back({7,"joe",3.4});
foos.push_back({5,"bob",7.2});
ostringstream out;
for (auto group : group_by(foos.begin(),foos.end(),FooX())) {
out << group.value << ":";
for (auto elem : group.range) {
out << " " << elem.y;
}
out << "\n";
}
assert(out.str()==
"5: bill rick\n"
"3: tom\n"
"7: joe\n"
"5: bob\n"
);
}
int main(int argc,char **argv)
{
test();
return 0;
}

Eric Niebler's ranges library provides a group_by view.
according to the docs it is a header only library and can be included easily.
It's supposed to go into the standard C++ space, but can be used with a recent C++11 compiler.
minimal working example:
#include <map>
#include <vector>
#include <range/v3/all.hpp>
using namespace std;
using namespace ranges;
int main(int argc, char **argv) {
vector<int> l { 0,1,2,3,6,5,4,7,8,9 };
ranges::v3::sort(l);
auto x = l | view::group_by([](int x, int y) { return x / 5 == y / 5; });
map<int, vector<int>> res;
auto i = x.begin();
auto e = x.end();
for (;i != e; ++i) {
auto first = *((*i).begin());
res[first / 5] = to_vector(*i);
}
// res = { 0 : [0,1,2,3,4], 1: [5,6,7,8,9] }
}
(I compiled this with clang 3.9.0. and --std=c++11)

I recently discovered cppitertools.
It fulfills this need exactly as described.
https://github.com/ryanhaining/cppitertools#groupby

What is the point of bloating standard C++ library with an algorithm that is one line of code?
for (const auto & foo : foos) foos_by_x[foo.x].push_back(foo);
Also, take a look at std::multimap, it might be just what you need.
UPDATE:
The one-liner I have provided is not well-optimized for the case when your vector is already sorted. A number of map lookups can be reduced if we remember the iterator of previously inserted object, so it the "key" of the next object and do a lookup only when the key is changing. For example:
#include <map>
#include <vector>
#include <string>
#include <algorithm>
#include <iostream>
struct foo {
int x;
std::string y;
float z;
};
class optimized_inserter {
public:
typedef std::map<int, std::vector<foo> > map_type;
optimized_inserter(map_type & map) : map(&map), it(map.end()) {}
void operator()(const foo & obj) {
typedef map_type::value_type value_type;
if (it != map->end() && last_x == obj.x) {
it->second.push_back(obj);
return;
}
last_x = obj.x;
it = map->insert(value_type(obj.x, std::vector<foo>({ obj }))).first;
}
private:
map_type *map;
map_type::iterator it;
int last_x;
};
int main()
{
std::vector<foo> foos;
std::map<int, std::vector<foo>> foos_by_x;
foos.push_back({ 1, "one", 1.0 });
foos.push_back({ 3, "third", 2.5 });
foos.push_back({ 1, "one.. but third", 1.5 });
foos.push_back({ 2, "second", 1.8 });
foos.push_back({ 1, "one.. but second", 1.5 });
std::sort(foos.begin(), foos.end(), [](const foo & lhs, const foo & rhs) {
return lhs.x < rhs.x;
});
std::for_each(foos.begin(), foos.end(), optimized_inserter(foos_by_x));
for (const auto & p : foos_by_x) {
std::cout << "--- " << p.first << "---\n";
for (auto & f : p.second) {
std::cout << '\t' << f.x << " '" << f.y << "' / " << f.z << '\n';
}
}
}

How about this?
template <typename StructType, typename FieldSelectorUnaryFn>
auto GroupBy(const std::vector<StructType>& instances, const FieldSelectorUnaryFn& fieldChooser)
{
StructType _;
using FieldType = decltype(fieldChooser(_));
std::map<FieldType, std::vector<StructType>> instancesByField;
for (auto& instance : instances)
{
instancesByField[fieldChooser(instance)].push_back(instance);
}
return instancesByField;
}
and use it like this:
auto itemsByX = GroupBy(items, [](const auto& item){ return item.x; });

I wrote a C++ library to address this problem in an elegant way. Given your struct
struct foo
{
int x;
std::string y;
float z;
};
To group by y you simply do:
std::vector<foo> dataframe;
...
auto groups = group_by(dataframe, &foo::y);
You can also group by more than one variable:
auto groups = group_by(dataframe, &foo::y, &foo::x);
And then iterate through the groups normally:
for(auto& [key, group]: groups)
{
// do something
}
It also has other operations such as: subset, concat, and others.

I would simply use boolinq.h, which includes all of LINQ. No documentation, but very simple to use.

Related

Is there anything like C++ default object method

I have the following templated merge sort program:
#include <iostream>
#include <vector>
#include <string>
// trying to create a default method call
class CInstance {
private:
std::string str_;
public:
CInstance(const std::string& str) : str_(str) {}
bool const operator>(const CInstance& that){ return (this->str_.size() > that.str_.size());}
};
template<class T>
class CObj {
private:
T val;
public:
CObj(const T n) : val(n) {}
T Get() { return val; }
};
template<class T>
using vcobj = std::vector<CObj<T>>;
template<class T>
void display(vcobj<T>& v) {
for (auto &i : v) {
std::cout << i.Get() << " ";
}
std::cout << "\n";
}
template<class T>
vcobj<T> Merge(vcobj<T>& lv, vcobj<T>& rv) {
vcobj<T> ret;
auto lsize = lv.size();
auto rsize = rv.size();
unsigned int lpin = 0,
rpin = 0;
while(lpin < lsize && rpin < rsize) {
if(lv.at(lpin).Get() > rv.at(rpin).Get()) {
ret.emplace_back(rv.at(rpin).Get());
rpin++;
}
else {
ret.emplace_back(lv.at(lpin).Get());
lpin++;
}
}
for (auto i=lpin; i<lsize; i++) {
ret.emplace_back(lv.at(i).Get());
}
for (auto i=rpin; i<rsize; i++) {
ret.emplace_back(rv.at(i).Get());
}
return ret;
}
template<class T>
vcobj<T> Sort(const vcobj<T>& v) {
vcobj<T> ret;
auto size = v.size();
if(size == 0) {
return ret;
}
if(size > 1) {
auto mid = size / 2;
vcobj<T> l(v.begin(), v.begin()+mid);
auto lv = Sort(l);
vcobj<T> r(v.begin()+mid, v.end());
auto rv = Sort(r);
ret = Merge(lv, rv);
}
else {
ret = v;
}
return ret;
}
int main() {
{
vcobj<int> v = {4, 5, 2, 1, 9, 6, 10, 8, 15, 3, 7};
display(v);
auto sorted = Sort(v);
display(sorted);
}
{
vcobj<float> v = {0.01, 0.001, 0.002, 0.009, 0.010, 0.0003, 0.00001};
display(v);
auto sorted = Sort(v);
display(sorted);
}
{
vcobj<std::string> v = {{"pineapple"}, {"jackfruit"}, {"mango"}, {"apple"}, {"banana"}};
display(v);
auto sorted = Sort(v);
display(sorted);
}
// causing problem
{
vcobj<CInstance> v = {{"pineapple"}, {"jackfruit"}, {"mango"}, {"apple"}, {"banana"}};
display(v);
auto sorted = Sort(v);
display(sorted);
}
return 0;
}
In all of the above types, I can simply call the object and it extracts the data which looks like calling a default get() method. Is there a way to make objects of class CInstance trigger a methos, when used just alone.
example:
I could do something like
CInstance obj;
std::cout << obj;
And that will call a default method in CInstance what every it may be.
As already mentioned in the other answer you can create your own operator<< function:
std::ostream & operator<<(std::ostream &stream, const CInstance &obj) {
// stream << whatever you want to output
return stream;
}
You could also define a conversion operator. But you should think twice before you use them. They can lead to problems that are not easy to debug, especially when explicit is omitted. You generally should not use those for logging/debugging purposes. If your type represents a string and you use it to allow an easy conversion to an std::string then it might be fine.
#include <iostream>
#include <string>
class CInstance {
std::string str_ = "test";
public:
explicit operator const std::string () const { return str_; }
};
int main() {
CInstance obj;
std::cout << (std::string)obj << std::endl;
return 0;
}
If you can guarantee that the lifetime of the returned const char * is still valid after the call you could also do something like (but I would avoid that solution):
#include <iostream>
#include <string>
class CInstance {
std::string str_ = "test";
public:
operator const char *() const { return str_.c_str(); }
};
int main() {
CInstance t;
std::cout << t << std::endl;
return 0;
}
Personally, I would go with the first solution. But that really depends if you actually have a string representation of CInstance or if you want to display something for debugging purposes in a different format. I however would avoid the last non-explicit version with the const char * conversion operator.
In this exact case, you define an operator<< method like so:
std::ostream & operator<<(std::ostream &stream, const CInstance &obj) {
... output obj however you want to the stream. For instance:
stream << obj.getAge();
return stream;
}

Python's enumerate in c++

In Python , instead of
colors = ['red', 'green', 'blue', 'yellow']
for i in range(len(colors)):
print i, '--->', colors[i]
One can write
for i, color in enumerate(colors):
print i, '--->', color
Is there a similar thing in c++?
You can actually implement something similar in c++17.
Here is a sketch(c++-ish pseudocode), I use values everywhere and they should be replaced by appropriate references/forwarding, also you should fix how you get types (use iterator_traits), may be support unknown size, may be implement proper iterator interface etc
template <typename T>
struct EnumeratedIterator {
size_t index;
T iterator;
void operator++() {
++iterator;
}
std::pair<size_t, T>() {
return {index, *iterator};
}
bool operator !=(EnumeratedIterator o) {
return iterator != o.iterator;
}
}
template <typename T>
struct Enumerated {
T collection;
EnumeratedIterator<typename T::iterator> begin() {
return {0, collection.begin()};
}
EnumeratedIterator<typename T::iterator> end() {
return {collection.size(), collection.end()};
}
}
auto enumerate(T col) {
return Enumerated<T>(col);
}
and then use it like
for (auto [index, color] : enumerate(vector<int>{5, 7, 10})) {
assert(index < color);
}
Boost provides an adaptor which allows to do something similiar:
http://www.boost.org/doc/libs/1_63_0/libs/range/doc/html/range/reference/adaptors/reference/indexed.html
The following code is taken from the link above
#include <boost/range/adaptor/indexed.hpp>
#include <boost/assign.hpp>
#include <iterator>
#include <iostream>
#include <vector>
int main(int argc, const char* argv[])
{
using namespace boost::assign;
using namespace boost::adaptors;
std::vector<int> input;
input += 10,20,30,40,50,60,70,80,90;
for (const auto& element : input | indexed(0))
{
std::cout << "Element = " << element.value()
<< " Index = " << element.index()
<< std::endl;
}
return 0;
}
Maybe you can emulate it like this:
int i = 0;
for (auto color : { "red", "green", "blue", "yellow" })
std::cout << i++ << "--->" << color << std::endl;

implement iterator on every elements of value containers against each key of map using boost iterator

How to implement an iterator of just on values of a map/unordered_map using boost::iterator_adaptor? I've tried following code but it does not work because of the line with comment.
Is there a solution to avoid the problem?
The question here is slightly different from map_values adapter example shown in boost code as here the value field in map is another container like list or vector and the requirement here is to iterate over all elements of those lists for every key of the map.
The deref of iterator is of type of value_type of those list/vector.The end of iterator is the end of list of last key
#include <vector>
#include <boost/unordered_map.hpp>
#include <cassert>
#include <iostream>
#include <boost/iterator/iterator_adaptor.hpp>
class DS {
public:
DS() : _map() {}
~DS() {
for (Map::iterator it = _map.begin(); it != _map.end(); ++it) {
delete (it->second);
}
}
void add(int key_, const std::vector< int > &value_)
{
IntList *ptr = new IntList(value_);
assert(ptr);
_map.insert(Map::value_type(key_, ptr));
}
private:
typedef std::vector< int > IntList;
typedef boost::unordered_map< int, IntList* > Map;
Map _map;
public:
class KeyIter : public boost::iterator_adaptor< KeyIter,
Map::const_iterator,
int,
boost::forward_traversal_tag,
int>
{
public:
KeyIter() : KeyIter::iterator_adaptor_() {}
private:
friend class DS;
friend class boost::iterator_core_access;
explicit KeyIter(Map::const_iterator it) : KeyIter::iterator_adaptor_(it) {}
explicit KeyIter(Map::iterator it) : KeyIter::iterator_adaptor_(it) {}
int dereference() const { return this->base()->first; }
};
class ValueIter : public boost::iterator_adaptor< ValueIter,
Map::const_iterator,
int,
boost::forward_traversal_tag,
int>
{
public:
ValueIter()
: ValueIter::iterator_adaptor_()
, _lIt()
{}
private:
friend class DS;
friend class boost::iterator_core_access;
explicit ValueIter(Map::const_iterator it)
: ValueIter::iterator_adaptor_(it)
, _lIt()
, _mIt(it)
{
IntList *pt = it->second; // <<-- issue here is I can't find if I've already reached the end of the map
if (pt) {
_lIt = it->second->begin();
}
}
int dereference() const { return *_lIt; }
void increment()
{
if (_lIt == _mIt->second->end()) {
++_mIt;
_lIt = _mIt->second->begin();
} else {
++_lIt;
}
}
IntList::iterator _lIt;
Map::const_iterator _mIt;
};
KeyIter beginKey() const { return KeyIter(_map.begin()); }
KeyIter endKey() const { return KeyIter(_map.end()); }
ValueIter beginValue() const { return ValueIter(_map.begin()); }
ValueIter endValue() const { return ValueIter(_map.end()); }
};
int main(int argc, char** argv)
{
DS ds;
std::vector< int > v1;
v1.push_back(10);
v1.push_back(30);
v1.push_back(50);
ds.add(90, v1);
std::vector< int > v2;
v2.push_back(20);
v2.push_back(40);
v2.push_back(60);
ds.add(120, v2);
std::cout << "------------ keys ---------------" << std::endl;
for (DS::KeyIter it = ds.beginKey(); it != ds.endKey(); ++it) {
std::cout << (*it) << std::endl;
}
std::cout << "------------ values ---------------" << std::endl;
// std::cout << (*(ds.beginValue())) << std::endl;
for (DS::ValueIter it = ds.beginValue(); it != ds.endValue(); ++it) {
std::cout << (*it) << std::endl;
}
return 0;
}
Implemented in c++11. You should be able to do the conversion to boost/c++03 fairly simply.
This iterator is FORWARD ONLY and it's quite fragile (see the comparison operator).
user discretion advised.
#include <iostream>
#include <vector>
#include <unordered_map>
typedef std::vector< int > IntList;
typedef std::unordered_map< int, IntList* > Map;
struct whole_map_const_iterator
{
using C1 = IntList;
using C2 = Map;
using I1 = C1::const_iterator;
using I2 = C2::const_iterator;
using value_type = I1::value_type;
using reference = I1::reference;
whole_map_const_iterator(I2 i2) : _i2(i2) {}
bool operator==(const whole_map_const_iterator& r) const {
if (_i2 != r._i2)
return false;
if (deferred_i1 && r.deferred_i1)
return true;
if (deferred_i1 != r.deferred_i1)
return false;
return _i1 == r._i1;
}
bool operator!=(const whole_map_const_iterator& r) const { return !(*this == r); }
reference operator*() const {
check_deferred();
return *_i1;
}
void check_deferred() const {
if (deferred_i1) {
_i1 = _i2->second->begin();
_i1limit = _i2->second->end();
deferred_i1 = false;
}
}
void go_next()
{
check_deferred();
if (++_i1 == _i1limit) {
++_i2;
deferred_i1 = true;
}
}
whole_map_const_iterator& operator++() {
go_next();
return *this;
}
whole_map_const_iterator operator++(int) {
auto result = *this;
go_next();
return result;
}
I2 _i2;
mutable I1 _i1 = {}, _i1limit = {};
mutable bool deferred_i1 = true;
};
IntList a { 1, 2, 3, 4, 5 };
IntList b { 6, 7, 8, 9, 10 };
Map m { { 1, &a }, { 2, &b } };
int main()
{
using namespace std;
auto from = whole_map_const_iterator(m.begin());
auto to = whole_map_const_iterator(m.end());
for ( ; from != to ; ++from) {
std::cout << *from << std::endl;
}
return 0;
}
example output:
6
7
8
9
10
1
2
3
4
5
For bonus points, answer this question:
Q: Why all that damn complication over the deferred flag?

Design operator++ for iterating over certain elements of a multimap

I have the following class declaration:
class Dictionnary{
private:
map< int,list<string> > data;
public:
bool isPrime();
class prime_iterator{
private:
map< int,list<string> >::iterator it;
public:
iterator(){}
prime_iterator & operator++(){
++it;
while(it != data.end() && !isPrime(it->first)){
++it;
}
return it;
}
...
};
which is intended to provide an iterator over prime keys of a map<int,list<string>>. I'm not sure operator++ is well implemented.
First, is it a good design to do it != data.end()accessing the outer class? Second, is operator++ returning the right thing or should return only prime_iterator?. Also, can you think about any better solution?
My advice is to always try to find solution elsewhere - if not found - then only create by yourself:
You can use boost::fiter_iterator
For your case it would look in this way:
#include <boost/iterator/filter_iterator.hpp>
using DataMap = std::map<int, std::list<std::string>>;
struct is_prime_number {
bool operator()(const DataMap::value_type& x) { return x.first % 2 == 0; }
}; // I know this is just is_even - not is_prime :D
using DataMapPrimeIter = boost::filter_iterator<is_prime_number, DataMap::iterator>;
inline DataMapPrimeIter only_prime_begin(DataMap& dataMap)
{
return boost::make_filter_iterator<is_prime_number>(dataMap.begin(), dataMap.end());
}
inline DataMapPrimeIter only_prime_end(DataMap& dataMap)
{
return boost::make_filter_iterator<is_prime_number>(dataMap.end(), dataMap.end());
}
And usage:
int main()
{
DataMap dataMap{{1,{"A","B"}}, {2,{"C", "D", "E"}}};
for (auto i = only_prime_begin(dataMap), end = only_prime_end(dataMap); i != end; ++i)
{
std::cout << i->first << i->second.front() << std::endl;
}
}
If you want to have your own implementation, or you cannot use boost in your project - then look at boost implementation - it is for free to look at...
My humble solution. The typedef is just for convenience.
#include <iterator>
#include <iostream>
#include <map>
#include <string>
#include <vector>
#include <algorithm>
typedef std::map<int, std::string> map_t;
class Dictionary {
private:
map_t& m_map;
public:
class prime_iterator {
public:
prime_iterator( map_t::iterator begin, map_t::iterator end )
: m_current(begin), m_end(end) {
runUntilPrime();
}
prime_iterator& operator++() {
m_current++;
runUntilPrime();
return *this;
}
bool operator != (prime_iterator other) {
return other.m_current != m_current;
}
map_t::value_type& operator* () {
return *m_current;
}
private:
map_t::iterator m_current;
map_t::iterator m_end;
bool isPrime(int x) {
std::vector<int> primes = { 1, 2, 3, 5, 7, 11, 13, 17 };
return std::find( primes.begin(), primes.end(), x ) != primes.end();
}
void runUntilPrime() {
while( m_current != m_end && !isPrime(m_current->first) ) {
m_current++;
}
}
};
Dictionary( map_t& tmap )
: m_map(tmap) {}
prime_iterator begin() {
return prime_iterator( m_map.begin(), m_map.end() );
}
prime_iterator end () {
return prime_iterator(m_map.end(), m_map.end());
}
};
int main( int argc, char** argv ) {
map_t map;
map.emplace(0, "zero");
map.emplace(1, "one");
map.emplace(2, "two");
map.emplace(3, "three");
map.emplace(4, "four");
map.emplace(5, "five");
map.emplace(6, "six");
map.emplace(7, "seven");
map.emplace(8, "eight");
map.emplace(9, "nine");
map.emplace(10, "ten");
map.emplace(13, "thirteen");
Dictionary dict( map );
for( auto p : dict ) {
std::cout << p.first << "\t" << p.second << std::endl;
}
return 0;
}

boost bimap with unordered_set_of and custom types

I want to create a bidirectional map between custom classes using bimap, this is what I do (class A and B are simplifications, they don't store just integers):
class A
{
private:
int value1;
int value2;
public:
int get_value1() const { return this->value1;}
int get_value2() const { return this->value2;}
A(int value1, int value2): value1(value1), value2(value2) {};
};
struct AHash
{
size_t operator()(const A& a) const {
size_t seed = 0;
hash_combine(seed, a.get_value1());
hash_combine(seed, a.get_value2());
return seed;
}
};
struct AComp
{
bool operator()(const A& lhs, const A& rhs) const {
return lhs.get_value1() == rhs.get_value1() &&
lhs.get_value2() == rhs.get_value2();
}
};
Class B same as A, then I created the map:
typedef bimap<
unordered_set_of<A, AHash, AComp>,
unordered_set_of<B, BHash, BComp>
> CustomMap;
CustomMap my_map;
It compiles but crashes without a meaningful log.
Any clue about what I'm doing wrong?
BTW: I'm using c++03
I suspect you have undefined behaviour elsewhere (e.g. memory management, or the actual types A and B). Here's my own self-contained test based on your sample with a lot of random insertions and lookups:
Live On Coliru
#include <boost/tuple/tuple.hpp>
#include <boost/tuple/tuple_comparison.hpp>
#include <boost/bimap.hpp>
#include <boost/bimap/unordered_set_of.hpp>
#include <iostream>
#include <boost/random.hpp> // for test
#include <boost/range/empty.hpp>
#include <boost/range/iterator_range.hpp>
template <typename>
class Obj
{
private:
int value1;
int value2;
boost::tuple<int const&, int const&> key() const { return boost::tie(value1, value2); }
public:
int get_value1() const { return this->value1;}
int get_value2() const { return this->value2;}
Obj(int value1, int value2): value1(value1), value2(value2) {};
struct Hash {
size_t operator()(const Obj& a) const {
size_t seed = 0;
boost::hash_combine(seed, a.get_value1());
boost::hash_combine(seed, a.get_value2());
return seed;
}
};
struct Equality {
bool operator()(const Obj& lhs, const Obj& rhs) const {
return lhs.key() == rhs.key();
}
};
};
typedef Obj<struct TagA> A;
typedef Obj<struct TagB> B;
int myrandom() {
static boost::mt19937 prng(42);
static boost::uniform_int<> dist(0, 1000);
return dist(prng);
}
int main() {
typedef boost::bimaps::bimap<
boost::bimaps::unordered_set_of<A, A::Hash, A::Equality>,
boost::bimaps::unordered_set_of<B, B::Hash, B::Equality>
> CustomMap;
CustomMap map;
int dupes = 0;
for (int i=0; i < 10000; ++i)
{
A a(myrandom(), myrandom());
B b(myrandom(), myrandom());
if (!map.insert(CustomMap::value_type(a, b)).second)
++dupes;
}
std::cout << dupes << " duplicate insertions were skipped\n";
int left_hits = 0;
for (int i=0; i <= 10000; ++i)
if (!boost::empty(boost::make_iterator_range(map.left.equal_range(A(i,i)))))
++left_hits;
int right_hits = 0;
for (int i=0; i <= 10000; ++i)
if (!boost::empty(boost::make_iterator_range(map.right.equal_range(B(i,i)))))
++right_hits;
std::cout << "Random hits (left, right): (" << left_hits << ", " << right_hits << ")\n";
}
Prints (for the given seed and random implementation):
112 duplicate insertions were skipped
Random hits (left, right): (11, 7)
It runs clean under valgrind even in optimized builds.