Related
I am implementing a kind of dataframe and I want to define a RandomAccessIterator over it, in order to execute the different std algorithms, such as the sorting one. The dataframe of the example contains two column "a" and "b":
a; b;
20; 21;
20; 19;
10; 11;
40; 41;
10; 11;
After sorting with a trivial selection sort this is the result:
a; b;
10; 11;
10; 11;
20; 19;
20; 21;
40; 41;
The problem that I am facing is that the std::sort does not work properly. And I don't know weather the implementation of the iterator is sound or not.
This is the code.
File: dataframe.hpp
#pragma once
#include <iostream>
#include <charconv>
#include <vector>
#include <memory>
#include <cstring>
#include <numeric>
#include "iterator.hpp"
namespace df
{
class Record;
class Column;
class Dataframe;
namespace types
{
enum class Base : char
{
CHAR = 'A',
UNSIGNED = 'U',
// Other types..
};
class Dtype
{
public:
Dtype(types::Base base, std::size_t size) : m_base_dtype{base}, m_size{size} {}
[[nodiscard]] auto name() const
{
return std::string{static_cast<char>(m_base_dtype)} + std::to_string(m_size);
}
[[nodiscard]] auto base() const { return m_base_dtype; }
[[nodiscard]] auto size() const { return m_size; }
[[nodiscard]] auto is_primitive() const
{
switch (base())
{
case types::Base::CHAR:
return size() == 1;
case types::Base::UNSIGNED:
return size() == 1 or size() == 2 or size() == 4 or size() == 8;
}
return false;
}
private:
types::Base m_base_dtype;
std::size_t m_size;
};
[[nodiscard]] static auto CHAR(const std::size_t size) { return Dtype(types::Base::CHAR, size); }
[[nodiscard]] static auto UNSIGNED(const std::size_t size) { return Dtype(types::Base::UNSIGNED, size); }
}
class Column
{
public:
Column(std::vector<char> &raw, const types::Dtype dtype) : m_raw{std::move(raw)}, m_dtype{dtype} {}
Column &operator=(Column &&c) = default; // Move constructor
[[nodiscard]] const auto &dtype() const { return m_dtype; }
[[nodiscard]] auto &raw() { return m_raw; }
[[nodiscard]] const auto &raw() const { return m_raw; }
[[nodiscard]] auto *data() { return m_raw.data(); }
[[nodiscard]] const auto *data() const { return m_raw.data(); }
private:
std::vector<char> m_raw;
types::Dtype m_dtype;
};
class Dataframe
{
public:
Dataframe(std::vector<char> &raw, std::vector<std::string> names, std::vector<types::Dtype> dtypes)
{
m_raw = std::move(raw);
m_column_dtypes = dtypes;
m_column_names = names;
m_record_size = 0;
for (const auto dt : dtypes)
{
m_column_offsets.emplace_back(m_record_size);
m_record_size += dt.size();
}
m_record_count = m_raw.size() / m_record_size;
}
Dataframe(std::vector<char> &raw, std::vector<types::Dtype> dtypes) : Dataframe(raw, {}, dtypes) {}
Dataframe &operator=(Dataframe &&c) = default; // Move constructor
[[nodiscard]] auto &raw() { return m_raw; }
[[nodiscard]] const auto &raw() const { return m_raw; }
[[nodiscard]] auto *data() { return m_raw.data(); }
[[nodiscard]] const auto *data() const { return m_raw.data(); }
// Iterators
[[nodiscard]] df::Iterator begin()
{
return df::Iterator{m_raw.data(), m_record_size};
}
[[nodiscard]] df::Iterator end()
{
return df::Iterator{m_raw.data() + m_raw.size(), m_record_size};
}
[[nodiscard]] auto shape() const { return std::make_pair(m_record_count, m_column_dtypes.size()); }
[[nodiscard]] auto record_count() const { return m_record_count; }
[[nodiscard]] auto record_size() const { return m_record_size; }
[[nodiscard]] const auto &names() const { return m_column_names; }
[[nodiscard]] const auto &dtypes() const { return m_column_dtypes; }
[[nodiscard]] const auto &offsets() const { return m_column_offsets; }
void print() { print(m_record_count); }
void print(const std::size_t initial_records)
{
// Print header
for (auto column_name : m_column_names)
{
std::cout << column_name << "; ";
}
std::cout << std::endl;
// Print rows
std::size_t records_to_print = std::min(initial_records, m_record_count);
for (std::size_t i = 0; i < records_to_print; i++)
{
const auto start_p = i * record_size();
auto start_field = 0;
auto end_field = 0;
for (auto field : m_column_dtypes)
{
end_field += field.size();
switch (field.base())
{
case types::Base::UNSIGNED:
{
std::uint64_t uint_value = 0;
memcpy(&uint_value, m_raw.data() + start_p + start_field, field.size());
std::cout << uint_value;
break;
}
case types::Base::CHAR:
{
std::string str_value = std::string(m_raw.data() + start_p + start_field, field.size());
std::cout << str_value;
break;
}
}
start_field = end_field;
// New column
std::cout << "; ";
}
// New row
std::cout << std::endl;
}
}
std::shared_ptr<Dataframe> copy() const
{
auto x = std::vector<char>(m_raw);
return std::make_shared<Dataframe>(x, std::vector<std::string>(m_column_names), std::vector<types::Dtype>(m_column_dtypes));
}
private:
std::vector<char> m_raw = {};
std::vector<std::string> m_column_names = {};
std::vector<types::Dtype> m_column_dtypes = {};
std::vector<std::size_t> m_column_offsets = {};
std::size_t m_record_size = {};
std::size_t m_record_count = {};
};
using namespace types;
static std::shared_ptr<Dataframe> read_from_vector(const std::vector<std::vector<std::string>> values, const std::vector<std::string> names, const std::vector<Dtype> dtypes)
{
const auto record_size = std::accumulate(dtypes.begin(), dtypes.end(), std::size_t{0},
[](std::size_t accum, const auto &m)
{ return accum + m.size(); });
const auto total_size = values.size() * record_size;
const std::size_t INCR_RECORDS = std::max(total_size / (10 * record_size), std::size_t{65536});
auto raw = std::vector<char>{};
std::size_t written_records = 0;
auto offsets = std::vector<std::size_t>{};
for (int offset = 0; const auto &kd : dtypes)
{
offsets.push_back(offset);
offset += kd.size();
}
for (auto value : values)
{
if (written_records >= raw.size() / record_size)
{
raw.resize(raw.size() + INCR_RECORDS * record_size, char{' '});
}
for (int i = 0; i < names.size(); i++)
{
const auto name = names[i];
const auto dtype = dtypes[i];
const auto offset = offsets[i];
const auto pos = written_records * record_size + offset;
switch (dtype.base())
{
case df::Base::CHAR:
{
const auto v = value[i];
const auto byte_to_copy = std::min(v.size(), dtype.size());
std::memcpy(raw.data() + pos,
v.data() + v.size() - byte_to_copy, byte_to_copy); // Prendo gli ultimi byte
break;
}
case df::Base::UNSIGNED:
{
const auto v = std::stoull(value[i]);
const auto byte_to_copy = dtype.size();
std::memcpy(raw.data() + pos, &v, byte_to_copy); // Prendo gli ultimi byte
break;
}
default:
throw std::runtime_error("ColumnType non riconosciuto");
}
}
written_records++;
}
raw.resize(written_records * record_size);
raw.shrink_to_fit();
return std::make_shared<Dataframe>(raw, names, dtypes);
}
}
File: iterator.hpp
#pragma once
#include <iostream>
#include <cstring>
namespace df
{
class Iterator
{
std::size_t size;
char *ptr;
public:
struct record_reference;
struct record_value
{
std::size_t size;
char *ptr;
record_value(const record_reference &t) : record_value(t.size, t.ptr){};
record_value(const std::size_t m_size, char *m_ptr)
{
this->size = m_size;
this->ptr = new char[this->size];
std::memcpy(ptr, m_ptr, this->size);
}
~record_value()
{
delete[] this->ptr;
}
};
struct record_reference
{
std::size_t size;
char *ptr;
record_reference(const std::size_t m_size, char *m_ptr)
{
this->size = m_size;
this->ptr = m_ptr;
}
record_reference(const record_reference &t)
{
this->size = t.size;
this->ptr = t.ptr;
}
// record_reference(const record_value &t) : record_reference(t.size, t.ptr) {};
record_reference &operator=(const record_value &t)
{
std::memcpy(ptr, t.ptr, size);
return *this;
}
record_reference &operator=(const record_reference &t)
{
std::memcpy(ptr, t.ptr, size);
return *this;
}
record_reference &operator=(char *t)
{
std::memcpy(ptr, t, size);
return *this;
}
operator char *()
{
return ptr;
}
operator const char *() const { return ptr; }
};
using iterator_category = std::random_access_iterator_tag;
using value_type = record_value;
using reference = record_reference;
using difference_type = std::ptrdiff_t;
// default constructible
Iterator() : size(0), ptr(nullptr)
{
}
// copy assignable
Iterator &operator=(const Iterator &t)
{
size = t.size;
ptr = t.ptr;
return *this;
}
Iterator(char *ptr, const std::size_t size) : size{size}, ptr(ptr)
{
}
record_reference operator*() const
{
return {size, ptr};
}
// Prefix
Iterator &operator++()
{
ptr += size;
return *this;
}
// Postfix
Iterator operator++(int)
{
auto tmp = *this;
++*this;
return tmp;
}
Iterator &operator--()
{
ptr -= size;
return *this;
}
difference_type operator-(const Iterator &it) const
{
return (this->ptr - it.ptr) / size;
}
Iterator operator+(const difference_type &offset) const
{
return Iterator(ptr + offset * size, size);
}
friend Iterator operator+(const difference_type &diff, const Iterator &it)
{
return it + diff;
}
Iterator operator-(const difference_type &diff) const
{
return Iterator(ptr - diff * size, size);
}
reference operator[](const difference_type &offset) const
{
return {size, ptr + offset * size};
}
bool operator==(const Iterator &it) const
{
return this->ptr == it.ptr;
}
bool operator!=(const Iterator &it) const
{
return !(*this == it);
}
bool operator<(const Iterator &it) const
{
return this->ptr < it.ptr;
}
bool operator>=(const Iterator &it) const
{
return this->ptr >= it.ptr;
}
bool operator>(const Iterator &it) const
{
return this->ptr > it.ptr;
}
bool operator<=(const Iterator &it) const
{
return this->ptr <= it.ptr;
}
Iterator &operator+=(const difference_type &diff)
{
ptr += diff * size;
return *this;
}
operator Iterator() const
{
return Iterator(ptr, size);
}
};
void swap(df::Iterator::record_reference a, df::Iterator::record_reference b)
{
unsigned char *p;
unsigned char *q;
unsigned char *const sentry = (unsigned char *)a.ptr + a.size;
for (p = (unsigned char *)a.ptr, q = (unsigned char *)b.ptr; p < sentry; ++p, ++q)
{
const unsigned char t = *p;
*p = *q;
*q = t;
}
}
}
File: comparator.hpp
#pragma once
#include <memory>
#include <functional>
#include "dataframe.hpp"
#include "iterator.hpp"
namespace compare
{
using comparator_fn = std::function<int(const df::Iterator::record_reference, const df::Iterator::record_reference)>;
template <typename T, std::size_t offset = 0, std::size_t size = sizeof(T)>
static inline comparator_fn make_comparator()
{
if constexpr (size == 3 or size == 5 or size == 7 or size > 8)
return [=](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{ return std::memcmp(a + offset, b + offset, size); };
return [](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{ return *(T *)(a + offset) < *(T *)(b + offset) ? -1 : *(T *)(b + offset) < *(T *)(a + offset) ? +1
: 0; };
}
template <typename T>
static inline comparator_fn make_comparator(const std::size_t offset)
{
return [=](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{ return *(T *)(a + offset) < *(T *)(b + offset) ? -1 : *(T *)(b + offset) < *(T *)(a + offset) ? +1
: 0; };
}
static inline comparator_fn make_column_comparator(const df::Dtype dtype, const std::size_t offset)
{
switch (dtype.base())
{
case df::Base::CHAR:
{
if (dtype.size() == 1)
return make_comparator<std::uint8_t>(offset);
else if (dtype.size() == 2)
return [=](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{ return std::memcmp(a + offset, b + offset, 2); }; // C'� qualche beneficio a fissare il 2? o conviene trattarlo come uno unsigned short?
return [=](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{ return std::memcmp(a + offset, b + offset, dtype.size()); };
}
case df::Base::UNSIGNED:
{
return [=](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{
std::uint64_t uint_value_a = 0;
std::uint64_t uint_value_b = 0;
std::memcpy(&uint_value_a, a + offset, dtype.size());
std::memcpy(&uint_value_b, b + offset, dtype.size());
return (uint_value_a < uint_value_b ? -1 : uint_value_a > uint_value_b ? +1
: 0);
};
}
default:
throw std::runtime_error("Unsupported dtype");
break;
}
}
static inline comparator_fn make_composite_two_way_comparator(const std::shared_ptr<df::Dataframe> &T)
{
const auto K = T->dtypes().size();
std::vector<comparator_fn> F;
for (int i = 0; i < K; i++)
{
F.emplace_back(make_column_comparator(T->dtypes()[i], T->offsets()[i]));
}
const auto comparator = [=](const df::Iterator::record_reference a, const df::Iterator::record_reference b)
{
for (int i = 0; i < K; i++)
{
// If equal go to the next column, otherwise return the result
// The return value is true if the first argument is less than the second
// and false otherwise
if (const auto result = F[i](a, b); result != 0)
return result < 0;
}
return false;
};
return comparator;
}
}
File: main.cpp
#include <iostream>
#include <vector>
#include "dataframe.hpp"
#include "comparator.hpp"
template <typename RandomAccessIterator, typename Comparator>
static void selection_sort(RandomAccessIterator first, RandomAccessIterator last, Comparator comp)
{
for (auto i = first; i != last; ++i)
{
auto min = i;
for (auto j = i + 1; j != last; ++j)
{
if (comp(*j, *min))
min = j;
}
df::Iterator::value_type temp = *i;
*i = *min;
*min = temp;
// Alternative
// std::iter_swap(i, min);
}
}
int main(int argc, char const *argv[])
{
std::vector<std::string> values{"20", "21", "20", "19", "10", "11", "40", "41", "10", "11"};
// Create a vector that contains values grouped by 2
std::vector<std::vector<std::string>> v;
for (int i = 0; i < values.size(); i += 2)
{
std::vector<std::string> temp;
temp.push_back(values[i]);
temp.push_back(values[i + 1]);
v.push_back(temp);
}
std::vector<std::string> column_names = {"a", "b"};
df::Dtype d = df::Dtype(df::Base::UNSIGNED, 4);
std::vector dtypes = {d, d};
// Create a dataframe
std::shared_ptr<df::Dataframe> df = df::read_from_vector(v, column_names, dtypes);
std::cout << "Before sorting" << std::endl;
df->print();
// This comparator sorts the dataframe first by column a and then by column b in ascending order
auto comparator = compare::make_composite_two_way_comparator(df);
selection_sort(df->begin(), df->end(), comparator);
std::cout << "\nAfter sorting" << std::endl;
df->print();
// With the std::sort it does not work
std::sort(df->begin(), df->end(), comparator);
return 0;
}
Your type is not a C++17 RandomAccessIterator, because it isn't a C++17 ForwardIterator, because reference is an object type, not a reference type.
The type It satisfies ForwardIterator if
Let T be the value type of It. The type std::iterator_traits<It>::reference must be either
T& or T&& if It satisfies OutputIterator (It is mutable), or
const T& or const T&& otherwise (It is constant),
(Other requirements elided)
You will be able to satisfy the C++20 concept std::random_access_iterator, because that relaxes the requirement on It::reference.
In C++17, the reference type of an iterator must be precisely value_type& in order for that iterator to be random access. Only input iterators can have the reference type be something other than value_type&. So in C++17, proxy iterators are limited to input iterators. And every algorithm written against C++17 has this expectation.
The C++20 ranges library adds the ability to have random access proxy iterators. And the C++20 algorithms that use those range concepts will respect them.
I'm just going to come out and ask. I have 500 arrays[127]. I need to sort them all by the value of the very last element in descending order. How would you do this in the most efficient way possible?
EXAMPLE:
float arr1[] = {3,1,4,5};
float arr2[] = {1,2,5,8};
float arr3[] = {102,4,132,2};
OUTPUT:
{arr2,
arr1,
arr3}
Your could create a lightweight wrapper that just stores the begin and end iterators of an array.
#include <iterator>
template<class T>
struct span {
template<size_t N>
span(T (&arr)[N]) : m_begin(std::begin(arr)), m_end(std::end(arr)) {}
T* begin() const { return m_begin; }
T* end() const { return m_end; }
T& front() const { return *m_begin; }
T& back() const { return *std::prev(m_end); }
private:
T* m_begin;
T* m_end;
};
You could then put these lightweight wrappers in a std::vector<span<int>> and sort that. Note that this will not affect the original arrays in any way and since sorting the vector only moves the spans around and not the actual array data, it should be reasonably fast.
#include <algorithm>
#include <iostream>
#include <vector>
int main() {
int arr1[] = {3,1,4,5};
int arr2[] = {1,2,5,8};
int arr3[] = {102,4,132,2};
std::vector<span<int>> arrs{
arr1, arr2, arr3
};
// sort on the last element, decending:
std::sort(arrs.begin(), arrs.end(),[](const auto& lhs, const auto& rhs) {
return rhs.back() < lhs.back();
});
for(auto& arr : arrs) {
for(auto v : arr) std::cout << v << ' ';
std::cout << '\n';
}
}
Output:
1 2 5 8
3 1 4 5
102 4 132 2
Since a raw array is a pointer without size information carried out, your job isn't automatic.
Either you convert all your arrays to std::vector<float> so you can have the last element and then have a std::vector<std::vector<float>> with a custom sort operator to test, or you create a structure that contains the raw array along with size information.
std::vector<float> arr1 = {3,1,4,5}
std::vector<float> arr2 = {1,2,5,8};
std::vector<float> arr3 = {102,4,132,2};
std::vector<std::vector<float>> arrays = {arr1,arr2,arr3};
std::sort(arrays.begin(),arrays.end(),[](const std::vector<float>& r1,const std::vector<float>& r2) -> bool
{
if (r1[r1.size() - 1] < r2[r2.size() - 1]) return true;
return false;
});
struct ArrAndSize { float* arr; size_t sz; };
ArrAndSize arr1 = {{3,1,4,5},4};
ArrAndSize arr2 = {{1,2,5,8},4};
ArrAndSize arr3 = {{102,4,132,2},4};
std::vector<ArrAndSize> arrays = {arr1,arr2,arr3};
std::sort(arrays.begin(),arrays.end(),[](const ArrAndSize& r1,const ArrAndSize& r2) -> bool
{
if (r1.arr[r1.sz - 1] < r2.arr[r2.sz - 1]) return true;
return false;
});
In both cases, check if the array has size 0.
is there a way to declare a range based array in c++ arduino for example instad of writing
const int array[] = {2,3,4,5,6};
why isn't it possible to declare an array like this?
const int array[] = {2:6};
I assume that you are not using the Arduino STL, so you could create a simple array wrapping class template, similar to std::array, that takes two template parameters: The type, T, and the size, N.
Example:
template<class T, size_t N>
struct array {
// misc typedef's:
using value_type = T;
using const_pointer = const value_type*;
using pointer = value_type*;
using const_iterator = const value_type*;
using iterator = value_type*;
size_t size() const { return N; } // the fixed size of the array
// subscripting:
const T& operator[](size_t idx) const { return data[idx]; }
T& operator[](size_t idx) { return data[idx]; }
// implicit conversions when passed to functions:
operator const_pointer () const { return data; }
operator pointer () { return data; }
// iterator support:
const_iterator cbegin() const { return data; }
const_iterator cend() const { return data + N; }
const_iterator begin() const { return cbegin(); }
const_iterator end() const { return cend(); }
iterator begin() { return data; }
iterator end() { return data + N; }
T data[N]; // the actual array
};
You could then create a small helper function to create arrays and fill them with a range of values like in your question:
template<class T, T min, T max>
array<T, max - min + 1> make_array_min_max() {
array<T, max - min + 1> rv;
for(T i = min; i <= max; ++i) rv[i - min] = i;
return rv;
}
The creation would just be slightly different, but you could then use it pretty much like you use a normal array.
void func(const int* a, size_t s) { // C-style interface
for(size_t i = 0; i < s; ++i)
std::cout << a[i] << ' ';
std::cout << '\n';
}
int main() {
const auto arr = make_array_min_max<int, 2, 6>(); // create the range you want
func(arr, arr.size()); // implicit conversion to `const int*` for `arr`
for(auto v : arr) // range-based for loop
std::cout << v << ' ';
std::cout << '\n';
for(size_t i = 0; i < arr.size(); ++i) // classing loop
std::cout << arr[i] << ' ';
std::cout << '\n';
}
Output:
2 3 4 5 6
2 3 4 5 6
2 3 4 5 6
I want to construct a class of an array whose size is not known,
i want to make objects of array whose size would be initialized at the time when i would create an object(runtime)
class array_class{
public:
int size_of_array;
int arr[size_of_array];
array_class(int p_size_of_array){ //constructor
this->size_of_array=p_size_of_array;
}
};
it say's error of invalid use of non static data member, what wrong am i doing(what should i have known)?.
You can't have something like
void foo(int n)
{
int vals[n];
}
in C++.
The thing is called variable-length array and it's supported in C99.
By the way, it is the only thing I know which is supported in C99 and not supported in C++17 :).
std::vector is a nice alternative.
If you know the size of an array at the compile time, you may use std::array.
I want to construct a class of an array whose size is not known
(what should i have known)?
You should have known that is not not possible in C++. The size of all classes is compile time constant.
i want to make objects of array whose size would be initialized at the time when i would create an object(runtime)
You need to allocate the array dynamically.
A simple solution:
struct array_class {
std::vector<int> arr;
array_class(int p_size_of_array) : arr(p_size_of_array) {}
};
#eerorika and #Nestor have good answers. To add to them here is a simple implementation of a vector i did some time ago you can take as a reference.
As you will see a basic way to have a variable length data structure, is to delete the underlying array and create a larger one if more or less memory is needed.
#pragma once
#include <ostream>
#include <string>
#include <initializer_list>
#include <stdexcept>
static constexpr size_t min_sz = 5;
template<typename T>
class Vector
{
public:
class ConstIterator;
class Iterator;
using value_type = T;
using size_type = std::size_t;
using difference_type = std::ptrdiff_t;
using reference = value_type&;
using const_reference = const value_type &;
using pointer = value_type *;
using const_pointer = const value_type *;
using iterator = Vector::Iterator;
using const_iterator = Vector::ConstIterator;
/// constructors, destructor, assign
Vector()
{
allocEmpty(min_sz);
}
Vector(Vector<value_type> &vec)
{
allocEmpty(vec.max_sz);
for (size_type i = 0; i < vec.sz; ++i)
values[i] = vec.values[i];
sz = vec.sz;
}
Vector(size_type size)
{
allocEmpty(size);
}
Vector(const std::initializer_list<value_type> &list)
{
allocEmpty(list.size());
size_type i = 0;
for (const auto &val : list)
{
values[i] = val;
++i;
}
sz = list.size();
}
~Vector()
{
delete[] values;
}
Vector &operator=(const Vector &other)
{
reserve(other.sz);
for (size_type i = 0; i < other.sz; ++i)
values[i] = other.values[i];
sz = other.sz;
return *this;
}
/// element access
reference operator[](size_type position)
{
if (position >= sz)
throw std::out_of_range ("operator[] out of range: sz = " + std::to_string(sz) + " but position = " + std::to_string(position));
return values[position];
}
const_reference operator[](size_type position) const
{
if (position >= sz)
throw std::out_of_range ("operator[] out of range: sz = " + std::to_string(sz) + " but position = " + std::to_string(position));
return values[position];
}
const_reference front() const
{
if (sz == 0)
throw std::out_of_range ("front called on empty container");
return values[0];
}
const_reference back() const
{
if (sz == 0)
throw std::out_of_range ("back called on empty container");
return values[sz - 1];
}
pointer data()
{
if (sz > 0)
return values;
return nullptr;
}
const_pointer data() const
{
if (sz > 0)
return values;
return nullptr;
}
/// capacity
size_type size() const
{
return sz;
}
size_type capacity() const
{
return max_sz;
}
bool empty() const
{
return (sz == 0);
}
void reserve(size_type size)
{
if (size <= min_sz)
return;
value_type *newArray = new value_type[size];
for (size_type i = 0; i < sz; ++i)
newArray[i] = values[i];
delete[] values;
values = newArray;
max_sz = size;
}
void shrink_to_fit()
{
size_type newSize = (sz >= min_sz) ? sz : min_sz;
value_type *newArray = new value_type[newSize];
for (size_type i = 0; i < sz; ++i)
newArray[i] = values[i];
delete[] values;
values = newArray;
max_sz = newSize;
}
/// modifiers
void push_back(const value_type &value)
{
if (sz >= max_sz)
reserve(max_sz * 2);
values[sz] = value;
++sz;
}
void resize(size_type count)
{
reserve(count);
sz = count;
}
void resize(size_type count, const value_type &value)
{
reserve(count);
for (size_type i = sz; i < count; ++i)
values[i] = value;
sz = count;
}
void insert(size_type position, const value_type &value)
{
if (position > sz)
throw std::out_of_range ("insert out of range: sz = " + std::to_string(sz) + " but position = " + std::to_string(position));
if (sz >= max_sz)
reserve(max_sz * 2);
for (size_type i = sz; i > position; --i)
values[i] = values[i - 1];
values[position] = value;
++sz;
}
iterator insert(const_iterator pos, const_reference val)
{
auto diff = pos - begin();
if (diff < 0 || static_cast<size_type>(diff) > sz)
throw std::runtime_error("Iterator out of bounds");
size_type current = static_cast<size_type>(diff);
if (sz >= max_sz)
reserve(max_sz * 2);
for (size_t i = sz; i-->current;)
values[i + 1] = values[i];
values[current] = val;
++sz;
return iterator(values + current);
}
void erase(size_type position)
{
if (position >= sz)
throw std::out_of_range ("erase out of range: sz = " + std::to_string(sz) + " but position = " + std::to_string(position));
for (size_type i = position; i < sz - 1; ++i)
values[i] = values[i + 1];
--sz;
}
iterator erase(const_iterator pos)
{
auto diff = pos - begin();
if (diff < 0 || static_cast<size_type>(diff) >= sz)
throw std::runtime_error("Iterator out of bounds");
size_type current = static_cast<size_type>(diff);
for (size_type i = current; i < sz - 1; ++i)
values[i] = values[i + 1];
--sz;
return iterator(values + current);
}
void pop_back()
{
if (sz == 0)
throw std::out_of_range ("pop_back on empty container");
if (sz > 0) --sz;
}
void clear()
{
sz = 0;
}
/// iterators
iterator begin()
{
if (sz == 0)
return end();
return iterator(values);
}
iterator end()
{
return iterator(values + sz);
}
const_iterator begin() const
{
if (sz == 0)
return end();
return ConstIterator(values);
}
const_iterator end() const
{
return ConstIterator(values + sz);
}
/// private section
private:
void allocEmpty(size_type size)
{
auto newSize = (size > min_sz) ? size : min_sz;
sz = 0;
values = new value_type[newSize];
max_sz = newSize;
}
private:
value_type *values;
size_type sz;
size_type max_sz;
/// iterator implementations
public:
class Iterator
{
public:
using value_type = Vector::value_type;
using reference = Vector::reference;
using pointer = Vector::pointer;
using difference_type = Vector::difference_type;
using iterator_category = std::forward_iterator_tag;
public:
Iterator()
{
ptr = nullptr;
}
Iterator(pointer ptr)
{
this->ptr = ptr;
}
reference operator*() const
{
return *ptr;
}
pointer operator->() const
{
return ptr;
}
iterator& operator++()
{
++ptr;
return *this;
}
iterator operator++(int)
{
iterator it = *this;
++ptr;
return it;
}
iterator operator+ (difference_type difference) const
{
return iterator(ptr + difference);
}
bool operator==(const const_iterator &it) const
{
return it == ptr;
}
bool operator!=(const const_iterator &it) const
{
return it != ptr;
}
operator const_iterator() const
{
return const_iterator(ptr);
}
private:
pointer ptr;
};
class ConstIterator
{
public:
using value_type = Vector::value_type;
using reference = Vector::const_reference;
using pointer = Vector::const_pointer;
using difference_type = Vector::difference_type;
using iterator_category = std::forward_iterator_tag;
public:
ConstIterator()
{
ptr = nullptr;
}
ConstIterator(pointer ptr)
{
this->ptr = ptr;
}
reference operator*() const
{
return *ptr;
}
pointer operator->() const
{
return ptr;
}
const_iterator& operator++()
{
++ptr;
return *this;
}
const_iterator operator++(int)
{
const_iterator it = *this;
++ptr;
return it;
}
bool operator==(const const_iterator &it) const
{
return it.ptr == ptr;
}
bool operator!=(const const_iterator &it) const
{
return it.ptr != ptr;
}
Vector::difference_type operator-(const const_iterator &rop)
{
return ptr - rop.ptr;
}
private:
pointer ptr;
};
};
/// non-member functions
template<typename T>
bool operator==(const Vector<T> &lop, const Vector<T> &rop)
{
if (lop.size() != rop.size()) return false;
for (size_t i = 0; i < lop.size(); ++i)
{
if (lop[i] != rop[i])
return false;
}
return true;
}
template<typename T>
std::ostream& operator<<(std::ostream &out, const Vector<T> &vec)
{
out << '[';
for (size_t i = 0; i < vec.size(); ++i)
{
if (i > 0) out << ", ";
out << vec[i];
}
out << ']';
return out;
}
I've been thinking if it is possible to actually let the user decide how many "dimensions" an array should have, based on a number given.
Let n be the number of dimensions, the user will type in its value.
It will create an array with n dimensions.
Example: for n=5, it will create an array called list, like that: int list[size1][size2][size3][size4][size5].
size variables will still be mentioned by the user, but that's actually part 2.
I want to know if I can add more dimensions to an array, after I have declared it. And if not, I want to find a solution to this problem.
The C++ language does not have provision for variable-sized or variable-dimensioned arrays.
You can, however, create a class to encapsulate these behaviors.
The important characteristic is the dimensions. You can use a std::vector<int> to track the number of elements per dimension; for example, {3, 4, 5} to represent a three-dimensional matrix where the rank of the innermost dimension is 3, the middle 4, and the outer 5.
Use a templated vector or deque to allocate space for the elements. The number of elements required is the product of the dimension ranks. (You can use std::accumulate with a multiplication operator to compute this over your ranks vector.)
Next, you'll need a method that takes some object (say, a vector of int) that provides all the indices into the MD-array necessary to access an element. You can provide overloads that take a variable number of arguments using some fancy template metaprogramming.
All of this is overkill outside of some very specialized uses, such as: you are writing Mathematica-like software that allows users to play with these things.
You may be interested in an array class I implemented a few months ago that aims to provide a syntax for arrays that mimics that of matlab arrays. It utilizes initilizer_list syntax to allow for arbitrary dimensional arrays to be created using
Array<double> array({10, 20, 30});
You can then access and modify individual elements using
double d = array[{1, 2, 3}];
array[{1, 2, 3}] = 10;
And even slice the matrix up into pieces using
array.getSlice({___, 3, 4});
where "___" is used as a wildcard.
See more on: http://www.second-quantization.com/Array.html
Implementation: https://github.com/dafer45/TBTK/blob/master/Lib/include/Utilities/TBTK/Array.h
Solution for object let's the user choose the number of dimensions. A little robust, my C++ maybe is not the best, but it was fun implementing. nvector<T> represents resizable (in dimensions and count of elements in each dimension) array of element of T type, although only some resize functions are implemented. narray<T> is the same, but the number of dimensions is not resizable. This works around the idea of recalculating index position of a multidimensional array using a single continuous array.
#include <cstdio>
#include <vector>
#include <iostream>
#include <cstddef>
#include <cstdarg>
#include <algorithm>
#include <numeric>
#include <cassert>
#include <memory>
#include <cstring>
using namespace std;
template<typename T>
class narray {
public:
static size_t compute_size(initializer_list<size_t>& dims) {
return accumulate(dims.begin(), dims.end(), 1, multiplies<size_t>());
}
static size_t compute_size(vector<size_t>& dims) {
return accumulate(dims.begin(), dims.end(), 1, multiplies<size_t>());
}
static size_t compute_distance(vector<size_t>& dims) {
return dims.size() > 1 ? dims[1] : 1;
}
static vector<size_t> remove_one_dim(vector<size_t> dims_) {
return vector<size_t>(dims_.begin() + 1, dims_.end());
}
narray(initializer_list<size_t> dims, T* data) :
dims_(dims), data_(data) {}
narray(vector<size_t> dims, T* data) :
dims_(dims), data_(data) {}
T operator*() {
return *data_;
}
T* operator&() {
return data_;
}
void operator=(T v) {
if (dims_.size() != 0)
throw runtime_error(__PRETTY_FUNCTION__);
*data_ = v;
}
void operator=(initializer_list<T> v) {
if (v.size() > size())
throw runtime_error(__PRETTY_FUNCTION__);
copy(v.begin(), v.end(), data_);
}
T* data() {
return data_;
}
T* data_last() {
return &data()[compute_size(dims_)];
}
size_t size() {
return compute_size(dims_);
}
size_t size(size_t idx) {
return dims_[idx];
}
narray<T> operator[](size_t idx) {
if (dims_.size() == 0)
throw runtime_error(__PRETTY_FUNCTION__);
return narray<T>(remove_one_dim(dims_),
&data_[idx * compute_distance(dims_)]);
}
class iterator {
public:
iterator(initializer_list<size_t>& dims, T* data) :
dims_(dims), data_(data) { }
iterator(vector<size_t>& dims, T* data) :
dims_(dims), data_(data) { }
iterator operator++() {
iterator i = *this;
data_ += compute_distance(dims_);
return i;
}
narray<T> operator*() {
return narray<T>(remove_one_dim(dims_), data_);
}
bool operator!=(const iterator& rhs) {
if (dims_ != rhs.dims_)
throw runtime_error(__PRETTY_FUNCTION__);
return data_ != rhs.data_;
}
private:
vector<size_t> dims_;
T* data_;
};
iterator begin() {
return iterator(dims_, data());
}
iterator end() {
return iterator(dims_, data_last());
}
private:
vector<size_t> dims_;
T* data_;
};
template<typename T>
class nvector {
public:
nvector(initializer_list<size_t> dims) :
dims_(dims), data_(narray<T>::compute_size(dims)) {}
nvector(vector<size_t> dims) :
dims_(dims), data_(narray<T>::compute_size(dims)) {}
nvector(initializer_list<size_t> dims, T* data) :
dims_(dims), data_(data) {}
nvector(vector<size_t> dims, T* data) :
dims_(dims), data_(data) {}
T* data() {
return data_.data();
}
T* data_last() {
return &data()[narray<T>::compute_size(dims_)];
}
size_t size() {
return narray<T>::compute_size(dims_);
}
narray<T> operator&() {
return narray<T>(dims_, data());
}
narray<T> operator[](size_t idx) {
if (dims_.size() == 0)
throw runtime_error(__PRETTY_FUNCTION__);
return narray<T>(narray<T>::remove_one_dim(dims_),
&data()[idx * narray<T>::compute_distance(dims_)]);
}
void operator=(initializer_list<T> v) {
if (v.size() > size())
throw runtime_error(__PRETTY_FUNCTION__);
copy(v.begin(), v.end(), data_.begin());
}
auto begin() {
return typename narray<T>::iterator(dims_, data());
}
auto end() {
return typename narray<T>::iterator(dims_, data_last());
}
// add and remove dimensions
void dimension_push_back(size_t dimsize) {
dims_.push_back(dimsize);
data_.resize(size());
}
void dimension_pop_back() {
dims_.pop_back();
data_.resize(size());
}
// TODO: resize dimension of index idx?
private:
vector<size_t> dims_;
vector<T> data_;
};
int main()
{
nvector<int> A({2, 3});
A = { 1,2,3, 4,5,6 };
assert(A.size() == 6);
assert(&A[0] == &A.data()[0]);
assert(&A[0][0] == &A.data()[0]);
assert(&A[1] == &A.data()[3]);
assert(&A[0][1] == &A.data()[1]);
assert(&A[1][1] == &A.data()[4]);
cout << "Currently array has " << A.size() << " elements: " << endl;
for(narray<int> arr1 : A) { // we iterate over arrays/dimensions
for(narray<int> arr2 : arr1) { // the last array has no dimensions
cout << "elem: " << *arr2 << endl;
}
}
cout << endl;
// assigment example
cout << "Now it is 4: " << *A[1][0] << endl;
A[1][0] = 10;
cout << "Now it is 10: " << *A[1][0] << endl;
return 0;
}
This code needs still much more work. It works only as a simple example. Maybe use shared_ptr in narray? Implement better exceptions?
So creating an array of n=5 dimensions with sizes size1, size2, size3, size4 and size5 would like this:
narray<int> arr({size1, size2, size3, size4, size5});
arr[0][1][2][3][4] = 5; // yay!