How to implement an STL-style iterator and avoid common pitfalls?

The iterator_facade documentation from Boost.Iterator provides what looks like a nice tutorial on implementing iterators for a linked list. Could you use that as a starting point for building a random-access iterator over your container?

If nothing else, you can take a look at the member functions and typedefs provided by iterator_facade and use it as a starting point for building your own.


Here is sample of raw pointer iterator.

You shouldn't use iterator class to work with raw pointers!

#include <iostream>
#include <vector>
#include <list>
#include <iterator>
#include <assert.h>

template<typename T>
class ptr_iterator
    : public std::iterator<std::forward_iterator_tag, T>
{
    typedef ptr_iterator<T>  iterator;
    pointer pos_;
public:
    ptr_iterator() : pos_(nullptr) {}
    ptr_iterator(T* v) : pos_(v) {}
    ~ptr_iterator() {}

    iterator  operator++(int) /* postfix */         { return pos_++; }
    iterator& operator++()    /* prefix */          { ++pos_; return *this; }
    reference operator* () const                    { return *pos_; }
    pointer   operator->() const                    { return pos_; }
    iterator  operator+ (difference_type v)   const { return pos_ + v; }
    bool      operator==(const iterator& rhs) const { return pos_ == rhs.pos_; }
    bool      operator!=(const iterator& rhs) const { return pos_ != rhs.pos_; }
};

template<typename T>
ptr_iterator<T> begin(T *val) { return ptr_iterator<T>(val); }


template<typename T, typename Tsize>
ptr_iterator<T> end(T *val, Tsize size) { return ptr_iterator<T>(val) + size; }

Raw pointer range based loop workaround. Please, correct me, if there is better way to make range based loop from raw pointer.

template<typename T>
class ptr_range
{
    T* begin_;
    T* end_;
public:
    ptr_range(T* ptr, size_t length) : begin_(ptr), end_(ptr + length) { assert(begin_ <= end_); }
    T* begin() const { return begin_; }
    T* end() const { return end_; }
};

template<typename T>
ptr_range<T> range(T* ptr, size_t length) { return ptr_range<T>(ptr, length); }

And simple test

void DoIteratorTest()
{
    const static size_t size = 10;
    uint8_t *data = new uint8_t[size];
    {
        // Only for iterator test
        uint8_t n = '0';
        auto first = begin(data);
        auto last = end(data, size);
        for (auto it = first; it != last; ++it)
        {
            *it = n++;
        }

        // It's prefer to use the following way:
        for (const auto& n : range(data, size))
        {
            std::cout << " char: " << static_cast<char>(n) << std::endl;
        }
    }
    {
        // Only for iterator test
        ptr_iterator<uint8_t> first(data);
        ptr_iterator<uint8_t> last(first + size);
        std::vector<uint8_t> v1(first, last);

        // It's prefer to use the following way:
        std::vector<uint8_t> v2(data, data + size);
    }
    {
        std::list<std::vector<uint8_t>> queue_;
        queue_.emplace_back(begin(data), end(data, size));
        queue_.emplace_back(data, data + size);
    }
}

http://www.cplusplus.com/reference/std/iterator/ has a handy chart that details the specs of § 24.2.2 of the C++11 standard. Basically, the iterators have tags that describe the valid operations, and the tags have a hierarchy. Below is purely symbolic, these classes don't actually exist as such.

iterator {
    iterator(const iterator&);
    ~iterator();
    iterator& operator=(const iterator&);
    iterator& operator++(); //prefix increment
    reference operator*() const;
    friend void swap(iterator& lhs, iterator& rhs); //C++11 I think
};

input_iterator : public virtual iterator {
    iterator operator++(int); //postfix increment
    value_type operator*() const;
    pointer operator->() const;
    friend bool operator==(const iterator&, const iterator&);
    friend bool operator!=(const iterator&, const iterator&); 
};
//once an input iterator has been dereferenced, it is 
//undefined to dereference one before that.

output_iterator : public virtual iterator {
    reference operator*() const;
    iterator operator++(int); //postfix increment
};
//dereferences may only be on the left side of an assignment
//once an output iterator has been dereferenced, it is 
//undefined to dereference one before that.

forward_iterator : input_iterator, output_iterator {
    forward_iterator();
};
//multiple passes allowed

bidirectional_iterator : forward_iterator {
    iterator& operator--(); //prefix decrement
    iterator operator--(int); //postfix decrement
};

random_access_iterator : bidirectional_iterator {
    friend bool operator<(const iterator&, const iterator&);
    friend bool operator>(const iterator&, const iterator&);
    friend bool operator<=(const iterator&, const iterator&);
    friend bool operator>=(const iterator&, const iterator&);

    iterator& operator+=(size_type);
    friend iterator operator+(const iterator&, size_type);
    friend iterator operator+(size_type, const iterator&);
    iterator& operator-=(size_type);  
    friend iterator operator-(const iterator&, size_type);
    friend difference_type operator-(iterator, iterator);

    reference operator[](size_type) const;
};

contiguous_iterator : random_access_iterator { //C++17
}; //elements are stored contiguously in memory.

You can either specialize std::iterator_traits<youriterator>, or put the same typedefs in the iterator itself, or inherit from std::iterator (which has these typedefs). I prefer the second option, to avoid changing things in the std namespace, and for readability, but most people inherit from std::iterator.

struct std::iterator_traits<youriterator> {        
    typedef ???? difference_type; //almost always ptrdiff_t
    typedef ???? value_type; //almost always T
    typedef ???? reference; //almost always T& or const T&
    typedef ???? pointer; //almost always T* or const T*
    typedef ???? iterator_category;  //usually std::forward_iterator_tag or similar
};

Note the iterator_category should be one of std::input_iterator_tag, std::output_iterator_tag, std::forward_iterator_tag, std::bidirectional_iterator_tag, or std::random_access_iterator_tag, depending on which requirements your iterator satisfies. Depending on your iterator, you may choose to specialize std::next, std::prev, std::advance, and std::distance as well, but this is rarely needed. In extremely rare cases you may wish to specialize std::begin and std::end.

Your container should probably also have a const_iterator, which is a (possibly mutable) iterator to constant data that is similar to your iterator except it should be implicitly constructable from a iterator and users should be unable to modify the data. It is common for its internal pointer to be a pointer to non-constant data, and have iterator inherit from const_iterator so as to minimize code duplication.

My post at Writing your own STL Container has a more complete container/iterator prototype.