Boost.Intrusive associative containers offer an interface similar to STL associative containers. However, STL's ordered and unordered simple associative containers (std::set, std::multiset, std::unordered_set and std::unordered_multiset) have some inefficiencies caused by the interface in several search, insertion or erasure functions (equal_range, lower_bound, upper_bound, find, insert, erase...): the user can only operate with value_type objects or (starting from C++11), heterogeneous comparison lookups which are not flexible enough as key_compare shall support the comparison between the provided key and value_type, which precludes the use of user-defined comparison objects that can partition the search in a compatible but advanced way.

To solve these problems, Boost.Intrusive containers offers functions where a key type different from key_type and a comparison object are provided by the user. This applies to: * equal_range * lower_bound * upper_bound * count * find * erase

Requirements for such functions are:

For more details, see Requires clauses of such functions in the reference.

#include <boost/intrusive/set.hpp>
#include <boost/intrusive/unordered_set.hpp>
#include <cstring>

using namespace boost::intrusive;

// Hash function for strings
struct StrHasher
{
   std::size_t operator()(const char *str) const
   {
      std::size_t seed = 0;
      for(; *str; ++str)   boost::hash_combine(seed, *str);
      return seed;
   }
};

class Expensive : public set_base_hook<>, public unordered_set_base_hook<>
{
   std::string key_;
   // Other members...

   public:
   Expensive(const char *key)
      :  key_(key)
      {}  //other expensive initializations...

   const std::string & get_key() const
      {  return key_;   }

   friend bool operator <  (const Expensive &a, const Expensive &b)
      {  return a.key_ < b.key_;  }

   friend bool operator == (const Expensive &a, const Expensive &b)
      {  return a.key_ == b.key_;  }

   friend std::size_t hash_value(const Expensive &object)
      {  return StrHasher()(object.get_key().c_str());  }
};

// A set and unordered_set that store Expensive objects
typedef set<Expensive>           Set;
typedef unordered_set<Expensive> UnorderedSet;

// Search functions
Expensive *get_from_set(const char* key, Set &set_object)
{
   Set::iterator it = set_object.find(Expensive(key));
   if( it == set_object.end() )     return 0;
   return &*it;
}

Expensive *get_from_uset(const char* key, UnorderedSet &uset_object)
{
   UnorderedSet::iterator it = uset_object.find(Expensive (key));
   if( it == uset_object.end() )  return 0;
   return &*it;
}

// These compare Expensive and a c-string
struct StrExpComp
{
   bool operator()(const char *str, const Expensive &c) const
   {  return std::strcmp(str, c.get_key().c_str()) < 0;  }

   bool operator()(const Expensive &c, const char *str) const
   {  return std::strcmp(c.get_key().c_str(), str) < 0;  }
};

struct StrExpEqual
{
   bool operator()(const char *str, const Expensive &c) const
   {  return std::strcmp(str, c.get_key().c_str()) == 0;  }

   bool operator()(const Expensive &c, const char *str) const
   {  return std::strcmp(c.get_key().c_str(), str) == 0;  }
};

// Optimized search functions
Expensive *get_from_set_optimized(const char* key, Set &set_object)
{
   Set::iterator it = set_object.find(key, StrExpComp());
   if( it == set_object.end() )   return 0;
   return &*it;
}

Expensive *get_from_uset_optimized(const char* key, UnorderedSet &uset_object)
{
   UnorderedSet::iterator it = uset_object.find(key, StrHasher(), StrExpEqual());
   if( it == uset_object.end() )  return 0;
   return &*it;
}

A similar issue happens with insertions in simple ordered and unordered associative containers with unique keys (std::set and std::unordered_set). In these containers, if a value is already present, the value to be inserted is discarded. With expensive values, if the value is already present, we can suffer efficiency problems.

set and unordered_set-like containers have insertion functions (insert_check, insert_unique_check,...) to check efficiently, without constructing the value, if a value is present or not and if it's not present, a function to insert it immediately (insert_commit) without any further lookup. Requirements for functions that check the existence of such value are:

To sum up, insert_check is similar to a normal insert but:

These functions must be used with care, no other insertion or erasure must be executed between an insert_check and an insert_commit pair. Otherwise, the behaviour is undefined.

See set and unordered_set-like containers' reference for more information about insert_check and insert_commit.

With multiple ordered and unordered associative containers (multiset and unordered_multiset) there is no need for these advanced insertion functions, since insertions are always successful.

// Insertion functions
bool insert_to_set(const char* key, Set &set_object)
{
   Expensive *pobject = new Expensive(key);
   bool success = set_object.insert(*pobject).second;
   if(!success)   delete pobject;
   return success;
}

bool insert_to_uset(const char* key, UnorderedSet &uset_object)
{
   Expensive *pobject = new Expensive(key);
   bool success = uset_object.insert(*pobject).second;
   if(!success)   delete pobject;
   return success;
}

// Optimized insertion functions
bool insert_to_set_optimized(const char* key, Set &set_object)
{
   Set::insert_commit_data insert_data;
   bool success = set_object.insert_check(key, StrExpComp(), insert_data).second;
   if(success) set_object.insert_commit(*new Expensive(key), insert_data);
   return success;
}

bool insert_to_uset_optimized(const char* key, UnorderedSet &uset_object)
{
   UnorderedSet::insert_commit_data insert_data;
   bool success = uset_object.insert_check
      (key, StrHasher(), StrExpEqual(), insert_data).second;
   if(success) uset_object.insert_commit(*new Expensive(key), insert_data);
   return success;
}

Some ordered associative containers offer low-level functions to bypass ordering checks and insert nodes directly in desired tree positions. These functions are provided for performance reasons when values to be inserted in the container are known to fulfill order (sets and multisets) and uniqueness (sets) invariants. A typical usage of these functions is when intrusive associative containers are used to build non-intrusive containers and the programmer wants to speed up assignments from other associative containers: if the ordering and uniqueness properties are the same, there is no need to waste time checking the position of each source value, because values are already ordered: back insertions will be much more efficient.

Note: These functions don't check preconditions so they must used with care. They are low-level operations that will break container invariants if ordering and uniqueness preconditions are not assured by the caller.

Let's see an example:

#include <boost/intrusive/set.hpp>
#include <vector>
#include <functional>
#include <cassert>

using namespace boost::intrusive;

//A simple class with a set hook
class MyClass : public set_base_hook<>
{
   public:
   int int_;

   MyClass(int i) :  int_(i) {}
   friend bool operator< (const MyClass &a, const MyClass &b)
      {  return a.int_ < b.int_;  }
   friend bool operator> (const MyClass &a, const MyClass &b)
      {  return a.int_ > b.int_;  }
};

int main()
{
   //Create some ORDERED elements
   std::vector<MyClass> values;
   for(int i = 0; i < 100; ++i)  values.push_back(MyClass(i));

   {  //Data is naturally ordered in the vector with the same criteria
      //as multiset's comparison predicate, so we can just push back
      //all elements, which is more efficient than normal insertion
      multiset<MyClass> mset;
      for(std::size_t i = 0; i != 100u; ++i)  mset.push_back(values[i]);

      //Now check orderd invariant
      multiset<MyClass>::const_iterator next(mset.cbegin()), it(next++);
      for(std::size_t i = 0; i < 99u; ++i, ++it, ++next) assert(*it < *next);
   }
   {  //Now the correct order for the set is the reverse order
      //so let's push front all elements
      multiset<MyClass, compare< std::greater<MyClass> > > mset;
      for(std::size_t i = 0; i < 100u; ++i)  mset.push_front(values[i]);

      //Now check orderd invariant
      multiset<MyClass, compare< std::greater<MyClass> > >::
         const_iterator next(mset.cbegin()), it(next++);
      for(std::size_t i = 0; i < 99u; ++i, ++it, ++next) assert(*it > *next);
   }
   {  //Now push the first and the last and insert the rest
      //before the last position using "insert_before"
      multiset<MyClass> mset;
      mset.insert_before(mset.begin(), values[0]);
      multiset<MyClass>::const_iterator pos =
         mset.insert_before(mset.end(), values[99]);
      for(std::size_t i = 1; i < 99u; ++i)  mset.insert_before(pos, values[i]);

      //Now check orderd invariant
      multiset<MyClass>::const_iterator next(mset.cbegin()), it(next++);
      for(int i = 0; i < 99; ++i, ++it, ++next) assert(*it < *next);
   }

   return 0;
}