Std :: hash value on char * value, not memory address?

Question

As indicated in this link :

There is no specialization for strings C. std :: hash creates a hash of the pointer value (memory address), it does not check the contents of any character array.

This means that char*different hash codes can be generated with the same value . For example, having this code:

//MOK and MOV are template arguments
void emit(MOK key, MOV value) {
    auto h = hash<MOK>()(key);
    cout<<"key="<<key<<" h="<<h<<endl;
    ...

This is the result caused by a call 4 times emit()in the same value key(s MOK=char*) (but 4 different token / string objects):

key=hello h=140311481289184
key=hello h=140311414180320
key=hello h=140311414180326
key=hello h=140311481289190

How can I get the same hash code for char*? I would rather not useboost

Answer 1

, ( ) std::string . , , -. , ++ , -, . ( - , .)

,

std::size_t
hash_bytes(const void * data, std::size_t size) noexcept;

, , .

template <typename T>
struct myhash
{
  std::size_t
  operator()(const T& obj) const noexcept
  {
    // Fallback implementation.
    auto hashfn = std::hash<T> {};
    return hashfn(obj);
  }
};

.

template <>
struct myhash<std::string>
{
  std::size_t
  operator()(const std::string& s) const noexcept
  {
    return hash_bytes(s.data(), s.size());
  }
};

template <>
struct myhash<const char *>
{
  std::size_t
  operator()(const char *const s) const noexcept
  {
    return hash_bytes(s, std::strlen(s));
  }
};

hash_bytes. , -, . Fowler-Noll-Vo. ; . .

, . -, template, - FNV-1a.

template <typename ResultT, ResultT OffsetBasis, ResultT Prime>
class basic_fnv1a final
{

  static_assert(std::is_unsigned<ResultT>::value, "need unsigned integer");

public:

  using result_type = ResultT;

private:

  result_type state_ {};

public:

  constexpr
  basic_fnv1a() noexcept : state_ {OffsetBasis}
  {
  }

  constexpr void
  update(const void *const data, const std::size_t size) noexcept
  {
    const auto cdata = static_cast<const unsigned char *>(data);
    auto acc = this->state_;
    for (auto i = std::size_t {}; i < size; ++i)
      {
        const auto next = std::size_t {cdata[i]};
        acc = (acc ^ next) * Prime;
      }
    this->state_ = acc;
  }

  constexpr result_type
  digest() const noexcept
  {
    return this->state_;
  }

};

32- 64- . .

using fnv1a_32 = basic_fnv1a<std::uint32_t,
                             UINT32_C(2166136261),
                             UINT32_C(16777619)>;

using fnv1a_64 = basic_fnv1a<std::uint64_t,
                             UINT64_C(14695981039346656037),
                             UINT64_C(1099511628211)>;

, - .

template <std::size_t Bits>
struct fnv1a;

template <>
struct fnv1a<32>
{
  using type = fnv1a_32;
};

template <>
struct fnv1a<64>
{
  using type = fnv1a_64;
};

template <std::size_t Bits>
using fnv1a_t = typename fnv1a<Bits>::type;

.

constexpr std::size_t
hash_bytes(const void *const data, const std::size_t size) noexcept
{
  auto hashfn = fnv1a_t<CHAR_BIT * sizeof(std::size_t)> {};
  hashfn.update(data, size);
  return hashfn.digest();
}

, , std::size_t 32 64 .

Answer 2

, , Java

size_t hash_c_string(const char* p, size_t s) {
    size_t result = 0;
    const size_t prime = 31;
    for (size_t i = 0; i < s; ++i) {
        result = p[i] + (result * prime);
    }
    return result;
}

, , .