json/include/nlohmann/detail/input/input_adapters.hpp

#pragma once

#include <array> // array
#include <cassert> // assert
#include <cstddef> // size_t
#include <cstdio> //FILE *
#include <cstring> // strlen
#include <istream> // istream
#include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next
#include <memory> // shared_ptr, make_shared, addressof
#include <numeric> // accumulate
#include <string> // string, char_traits
#include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
#include <utility> // pair, declval

#include <nlohmann/detail/iterators/iterator_traits.hpp>
#include <nlohmann/detail/macro_scope.hpp>

namespace nlohmann
{
namespace detail
{
/// the supported input formats
enum class input_format_t { json, cbor, msgpack, ubjson, bson };

////////////////////
// input adapters //
////////////////////

/*!
Input adapter for stdio file access. This adapter read only 1 byte and do not use any
 buffer. This adapter is a very low level adapter.
*/
class file_input_adapter
{
  public:
    using char_type = char;

    JSON_HEDLEY_NON_NULL(2)
    explicit file_input_adapter(std::FILE* f)  noexcept
        : m_file(f)
    {}

    // make class move-only
    file_input_adapter(const file_input_adapter&) = delete;
    file_input_adapter(file_input_adapter&&) = default;
    file_input_adapter& operator=(const file_input_adapter&) = delete;
    file_input_adapter& operator=(file_input_adapter&&) = delete;

    std::char_traits<char>::int_type get_character() noexcept
    {
        return std::fgetc(m_file);
    }

  private:
    /// the file pointer to read from
    std::FILE* m_file;
};


/*!
Input adapter for a (caching) istream. Ignores a UFT Byte Order Mark at
beginning of input. Does not support changing the underlying std::streambuf
in mid-input. Maintains underlying std::istream and std::streambuf to support
subsequent use of standard std::istream operations to process any input
characters following those used in parsing the JSON input.  Clears the
std::istream flags; any input errors (e.g., EOF) will be detected by the first
subsequent call for input from the std::istream.
*/
class input_stream_adapter
{
  public:
    using char_type = char;

    ~input_stream_adapter()
    {
        // clear stream flags; we use underlying streambuf I/O, do not
        // maintain ifstream flags, except eof
        if (is)
        {
            is->clear(is->rdstate() & std::ios::eofbit);
        }
    }

    explicit input_stream_adapter(std::istream& i)
        : is(&i), sb(i.rdbuf())
    {}

    // delete because of pointer members
    input_stream_adapter(const input_stream_adapter&) = delete;
    input_stream_adapter& operator=(input_stream_adapter&) = delete;
    input_stream_adapter& operator=(input_stream_adapter&& rhs) = delete;

    input_stream_adapter(input_stream_adapter&& rhs) : is(rhs.is), sb(rhs.sb)
    {
        rhs.is = nullptr;
        rhs.sb = nullptr;
    }

    // std::istream/std::streambuf use std::char_traits<char>::to_int_type, to
    // ensure that std::char_traits<char>::eof() and the character 0xFF do not
    // end up as the same value, eg. 0xFFFFFFFF.
    std::char_traits<char>::int_type get_character()
    {
        auto res = sb->sbumpc();
        // set eof manually, as we don't use the istream interface.
        if (res == EOF)
        {
            is->clear(is->rdstate() | std::ios::eofbit);
        }
        return res;
    }

  private:
    /// the associated input stream
    std::istream* is = nullptr;
    std::streambuf* sb = nullptr;
};

// General-purpose iterator-based adapter. It might not be as fast as
// theoretically possible for some containers, but it is extremely versatile.
template<typename IteratorType>
class iterator_input_adapter
{
  public:
    using char_type = typename std::iterator_traits<IteratorType>::value_type;

    iterator_input_adapter(IteratorType first, IteratorType last)
        : current(std::move(first)), end(std::move(last)) {}

    typename std::char_traits<char_type>::int_type get_character()
    {
        if (current != end)
        {
            auto result = std::char_traits<char_type>::to_int_type(*current);
            std::advance(current, 1);
            return result;
        }
        else
        {
            return std::char_traits<char_type>::eof();
        }
    }

  private:
    IteratorType current;
    IteratorType end;

    template<typename BaseInputAdapter, size_t T>
    friend class wide_string_input_helper;

    bool empty() const
    {
        return current == end;
    }

};


template<typename BaseInputAdapter, size_t T>
struct wide_string_input_helper;

template<typename BaseInputAdapter>
struct wide_string_input_helper<BaseInputAdapter, 4>
{
    // UTF-32
    static void fill_buffer(BaseInputAdapter& input,
                            std::array<std::char_traits<char>::int_type, 4>& utf8_bytes,
                            size_t& utf8_bytes_index,
                            size_t& utf8_bytes_filled)
    {
        utf8_bytes_index = 0;

        if (input.empty())
        {
            utf8_bytes[0] = std::char_traits<char>::eof();
            utf8_bytes_filled = 1;
        }
        else
        {
            // get the current character
            const auto wc = input.get_character();

            // UTF-32 to UTF-8 encoding
            if (wc < 0x80)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                utf8_bytes_filled = 1;
            }
            else if (wc <= 0x7FF)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xC0u | ((wc >> 6u) & 0x1Fu));
                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | (wc & 0x3Fu));
                utf8_bytes_filled = 2;
            }
            else if (wc <= 0xFFFF)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xE0u | ((wc >> 12u) & 0x0Fu));
                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((wc >> 6u) & 0x3Fu));
                utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | (wc & 0x3Fu));
                utf8_bytes_filled = 3;
            }
            else if (wc <= 0x10FFFF)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | ((wc >> 18u) & 0x07u));
                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((wc >> 12u) & 0x3Fu));
                utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((wc >> 6u) & 0x3Fu));
                utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (wc & 0x3Fu));
                utf8_bytes_filled = 4;
            }
            else
            {
                // unknown character
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                utf8_bytes_filled = 1;
            }
        }
    }
};

template<typename BaseInputAdapter>
struct wide_string_input_helper<BaseInputAdapter, 2>
{
    // UTF-16
    static void fill_buffer(BaseInputAdapter& input,
                            std::array<std::char_traits<char>::int_type, 4>& utf8_bytes,
                            size_t& utf8_bytes_index,
                            size_t& utf8_bytes_filled)
    {
        utf8_bytes_index = 0;

        if (input.empty())
        {
            utf8_bytes[0] = std::char_traits<char>::eof();
            utf8_bytes_filled = 1;
        }
        else
        {
            // get the current character
            const auto wc = input.get_character();

            // UTF-16 to UTF-8 encoding
            if (wc < 0x80)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                utf8_bytes_filled = 1;
            }
            else if (wc <= 0x7FF)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xC0u | ((wc >> 6u)));
                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | (wc & 0x3Fu));
                utf8_bytes_filled = 2;
            }
            else if (0xD800 > wc or wc >= 0xE000)
            {
                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xE0u | ((wc >> 12u)));
                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((wc >> 6u) & 0x3Fu));
                utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | (wc & 0x3Fu));
                utf8_bytes_filled = 3;
            }
            else
            {
                if (!input.empty())
                {
                    const auto wc2 = static_cast<unsigned int>(input.get_character());
                    const auto charcode = 0x10000u + (((wc & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
                    utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
                    utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
                    utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 6u) & 0x3Fu));
                    utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (charcode & 0x3Fu));
                    utf8_bytes_filled = 4;
                }
                else
                {
                    utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                    utf8_bytes_filled = 1;
                }
            }
        }
    }
};

// Wraps another input apdater to convert wide character types into individual bytes.
template<typename BaseInputAdapter, typename WideCharType>
class wide_string_input_adapter
{
  public:
    wide_string_input_adapter(BaseInputAdapter base)
        : base_adapter(base) {}

    typename std::char_traits<char>::int_type get_character() noexcept
    {
        // check if buffer needs to be filled
        if (utf8_bytes_index == utf8_bytes_filled)
        {
            fill_buffer<sizeof(WideCharType)>();

            assert(utf8_bytes_filled > 0);
            assert(utf8_bytes_index == 0);
        }

        // use buffer
        assert(utf8_bytes_filled > 0);
        assert(utf8_bytes_index < utf8_bytes_filled);
        return utf8_bytes[utf8_bytes_index++];
    }

  private:
    BaseInputAdapter base_adapter;

    template<size_t T>
    void fill_buffer()
    {
        wide_string_input_helper<BaseInputAdapter, T>::fill_buffer(base_adapter, utf8_bytes, utf8_bytes_index, utf8_bytes_filled);
    }

    /// a buffer for UTF-8 bytes
    std::array<std::char_traits<char>::int_type, 4> utf8_bytes = {{0, 0, 0, 0}};

    /// index to the utf8_codes array for the next valid byte
    std::size_t utf8_bytes_index = 0;
    /// number of valid bytes in the utf8_codes array
    std::size_t utf8_bytes_filled = 0;
};


template<typename IteratorType, typename Enable = void>
struct iterator_input_adapter_factory
{
    using iterator_type = IteratorType;
    using char_type = typename std::iterator_traits<iterator_type>::value_type;
    using adapter_type = iterator_input_adapter<iterator_type>;

    static adapter_type create(IteratorType begin, IteratorType end)
    {
        return adapter_type(std::move(begin), std::move(end));
    }
};

template<typename IteratorType>
struct iterator_input_adapter_factory<IteratorType,
       typename std::enable_if<(sizeof(typename std::iterator_traits<IteratorType>::value_type)>1)>::type >
       {

           using iterator_type = IteratorType;
           using char_type = typename std::iterator_traits<iterator_type>::value_type;
           using base_adapter_type = iterator_input_adapter<iterator_type>;
           using adapter_type = wide_string_input_adapter<base_adapter_type, char_type>;

           static adapter_type create(IteratorType begin, IteratorType end)
{
    return adapter_type(base_adapter_type(std::move(begin), std::move(end)));
}
       };

// General purpose iterator-based input
template<typename IteratorType>
typename iterator_input_adapter_factory<IteratorType>::adapter_type input_adapter(IteratorType begin, IteratorType end)
{
    using factory_type = iterator_input_adapter_factory<IteratorType>;
    return factory_type::create(begin, end);
}

// Convenience shorthand from container to iterator
template<typename ContainerType>
auto input_adapter(const ContainerType& container) -> decltype(input_adapter(begin(container), end(container)))
{
    return input_adapter(begin(container), end(container));
}

// Special cases with fast paths
inline file_input_adapter input_adapter(std::FILE* file)
{
    return file_input_adapter(file);
}

inline input_stream_adapter input_adapter(std::istream& stream)
{
    return input_stream_adapter(stream);
}

inline input_stream_adapter input_adapter(std::istream&& stream)
{
    return input_stream_adapter(stream);
}

using contiguous_bytes_input_adapter = decltype(input_adapter(std::declval<const char*>(), std::declval<const char*>()));

// Null-delimited strings, and the like.
template<typename CharT,
         typename std::enable_if<
             std::is_pointer<CharT>::value and
             std::is_integral<typename std::remove_pointer<CharT>::type>::value and
             sizeof(typename std::remove_pointer<CharT>::type) == 1,
             int>::type = 0>
contiguous_bytes_input_adapter input_adapter(CharT b)
{
    auto length = std::strlen(reinterpret_cast<const char*>(b));
    auto ptr = reinterpret_cast<const char*>(b);
    return input_adapter(ptr, ptr + length);
}


// This class only handles inputs of input_buffer_adapter type.
// It's required so that expressions like {ptr, len} can be implicitely casted
// to the correct adapter.
class span_input_adapter
{
  public:
    template<typename CharT,
             typename std::enable_if<
                 std::is_pointer<CharT>::value and
                 std::is_integral<typename std::remove_pointer<CharT>::type>::value and
                 sizeof(typename std::remove_pointer<CharT>::type) == 1,
                 int>::type = 0>
    span_input_adapter(CharT b, std::size_t l)
        : ia(reinterpret_cast<const char*>(b), reinterpret_cast<const char*>(b) + l) {}

    template<typename CharT,
             typename std::enable_if<
                 std::is_pointer<CharT>::value and
                 std::is_integral<typename std::remove_pointer<CharT>::type>::value and
                 sizeof(typename std::remove_pointer<CharT>::type) == 1,
                 int>::type = 0>
    span_input_adapter(CharT b)
        : span_input_adapter(b, std::strlen(reinterpret_cast<const char*>(b))) {}

    template<class IteratorType,
             typename std::enable_if<
                 std::is_same<typename iterator_traits<IteratorType>::iterator_category, std::random_access_iterator_tag>::value,
                 int>::type = 0>
    span_input_adapter(IteratorType first, IteratorType last)
        : ia(input_adapter(first, last)) {}

    template<class T, std::size_t N>
    span_input_adapter(T (&array)[N])
        : span_input_adapter(std::begin(array), std::end(array)) {}

    /// input adapter for contiguous container
    template<class ContiguousContainer, typename
             std::enable_if<not std::is_pointer<ContiguousContainer>::value and
                            std::is_base_of<std::random_access_iterator_tag, typename iterator_traits<decltype(std::begin(std::declval<ContiguousContainer const>()))>::iterator_category>::value,
                            int>::type = 0>
    span_input_adapter(const ContiguousContainer& c)
        : span_input_adapter(std::begin(c), std::end(c)) {}

    contiguous_bytes_input_adapter&& get()
    {
        return std::move(ia);
    }

  private:
    contiguous_bytes_input_adapter ia;
};
}  // namespace detail
}  // namespace nlohmann