Files
json/include/nlohmann/detail/view/input.hpp
Niels Lohmann 09879b6b5d Address the review of the view builder and document
Changes promised in the replies to the review of #5620:

- read() reuses the owned copy: a copied input (an rvalue byte container,
  a stream, FILE*, wide characters, an iterator range) is appended to the
  cleared owned buffer instead of a fresh std::string being move-assigned
  over it. A moved-in std::string still replaces it.
- The error replay runs the library parser with a SAX handler that stores
  nothing and throws the reported exception, instead of
  BasicJsonType::parse(), which built a DOM up to the error.
- Pointers to and arrays of wide characters, and FILE*, take the input
  adapter path (converted to UTF-8 into an owned buffer) instead of
  failing a static_assert. Wide pointers are NUL-terminated.
- Streams are read in blocks through rdbuf() into the buffer, instead of
  character by character through the input adapter; eofbit is set at the
  end, as by the library's stream adapter.
- tape/tape_size/tape_cap are now nodes/node_count/node_capacity.
- The builder's members get descriptive, m_-prefixed names.
- The shallow frame stack is a std::array (in a wrapper with a
  user-provided constructor: -Weffc++ wants the member initialized, and
  value-initializing the 64 frames costs up to 30 % on small documents).
- The value dispatch macro has no NEXT parameter; the switch is left with
  break, and the macro is undefined after its last use.
- literal() and digits_exceed() deduce the length from the string literal;
  each literal has one helper; the two `if (!is_float)` blocks are merged.
- arena_ensure() sits right before the writes; the decode arena is a
  std::vector<char>.
- The builder records the deepest nesting, and materialize() sizes its
  stack from it once (growing it only if a subtree is deeper).
- Comment fixes (hex4, slow_string, the NUL rule, put_utf8, 0 - m, the
  arena resize, grow()) and formatting (macro backslashes, digit cases,
  one power of ten per line, value_t assertion next to is_container()).
- build_with's template parameters follow the builder's order.

Greg's idea of keeping the source offset in `off` and the arena offset in
`next` for escaped strings was measured and not adopted: string access got
7-18 % slower with a select, and 3.5-18 % slower with a branch-free field
pick (Apple M-series, clang -O3), parsing was unchanged.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-10-16 08:14:20 +02:00

161 lines
6.1 KiB
C++

// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#pragma once
#include <algorithm> // max
#include <cstddef> // size_t
#include <istream> // istream, streambuf
#include <string> // basic_string, char_traits, string
#include <type_traits> // decay, integral_constant, is_array, is_const, is_integral, is_lvalue_reference, is_pointer, is_same, remove_cv, remove_extent, remove_pointer, remove_reference
#include <utility> // forward
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#if NLOHMANN_VIEW_HAS_CPP_17
#include <string_view> // string_view
#endif
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// how a document takes its input
enum class input_kind
{
move_string, ///< non-const rvalue std::string: owned without a copy
c_string, ///< pointer to single-byte characters (NUL-terminated): borrowed
char_array, ///< array of single-byte characters (e.g. a string literal): borrowed
borrow_range, ///< lvalue contiguous byte container, or std::string_view: borrowed
copy_range, ///< rvalue contiguous byte container (a const rvalue std::string too): copied
wide_c_string, ///< pointer to wide characters (NUL-terminated): converted to UTF-8 into a buffer
adapter, ///< streams, FILE*, wide strings and arrays, and the rest of what the library's input adapter reads: read into a buffer
};
/// a single-byte character type (char, signed/unsigned char, char8_t, std::uint8_t, ...)
template<typename T>
struct is_byte_char : std::integral_constant < bool, std::is_integral<T>::value && sizeof(T) == 1 > {}; // NOLINT(bugprone-sizeof-expression): T is any pointee or element type
/// a character type the library's input adapter converts to UTF-8
template<typename T>
struct is_wide_char : std::integral_constant < bool, std::is_same<T, wchar_t>::value || std::is_same<T, char16_t>::value
|| std::is_same<T, char32_t>::value > {};
template<typename InputType>
struct classify_input
{
using R = typename std::remove_reference<InputType>::type;
using D = typename std::decay<InputType>::type;
using element = typename std::remove_cv<typename std::remove_extent<R>::type>::type;
using pointee = typename std::remove_cv<typename std::remove_pointer<D>::type>::type;
static constexpr bool is_rvalue = !std::is_lvalue_reference<InputType>::value;
static constexpr bool is_bytes = is_contiguous_byte_container<D>::value;
#if NLOHMANN_VIEW_HAS_CPP_17
static constexpr bool is_string_view = std::is_same<D, std::string_view>::value;
#else
static constexpr bool is_string_view = false;
#endif
// NOLINTBEGIN(readability-avoid-nested-conditional-operator): a constant expression of C++11
// (arrays and pointers of other types, such as wide-character arrays and
// FILE*, go to the library's input adapter)
static constexpr input_kind value =
(std::is_array<R>::value && is_byte_char<element>::value) ? input_kind::char_array
: std::is_array<R>::value ? input_kind::adapter
: (std::is_pointer<D>::value && is_byte_char<pointee>::value) ? input_kind::c_string
: (std::is_pointer<D>::value && is_wide_char<pointee>::value) ? input_kind::wide_c_string
: std::is_pointer<D>::value ? input_kind::adapter
: (is_rvalue && !std::is_const<R>::value && std::is_same<D, std::string>::value) ? input_kind::move_string
: (is_bytes && (!is_rvalue || is_string_view)) ? input_kind::borrow_range
: is_bytes ? input_kind::copy_range
: input_kind::adapter;
// NOLINTEND(readability-avoid-nested-conditional-operator)
};
/// an integer type other than bool: a length passed where a flag is expected
template<typename T>
struct is_integer_not_bool : std::is_integral<T> {};
template<>
struct is_integer_not_bool<bool> : std::false_type {};
/// std::basic_string guarantees a NUL at data()[size()] (the parser's sentinel)
template<typename T>
struct is_std_string : std::false_type {};
template<typename Traits, typename Alloc>
struct is_std_string<std::basic_string<char, Traits, Alloc>> : std::true_type {};
/// append what a json input adapter yields (UTF-16/32 inputs arrive as UTF-8)
template<typename Adapter>
void append_adapter(std::string& buf, Adapter ia)
{
for (;;)
{
const auto ch = ia.get_character();
if (ch == std::char_traits<char>::eof())
{
break;
}
buf.push_back(static_cast<char>(ch));
}
}
/// an input adapter made by the document for an input that the library's
/// input_adapter() does not take as one argument (an iterator range, a wide C
/// string), to be appended with append_adapter()
template<typename Adapter>
struct adapter_input
{
Adapter ia;
};
template<typename T>
struct is_adapter_input : std::false_type {};
template<typename Adapter>
struct is_adapter_input<adapter_input<Adapter>> : std::true_type {};
template<typename Adapter>
adapter_input<typename std::decay<Adapter>::type> make_adapter_input(Adapter&& ia)
{
return {std::forward<Adapter>(ia)};
}
/// append the rest of a stream: its characters need no conversion, so they are
/// read in blocks from the stream buffer, straight into buf (reusing its
/// capacity). As the library's stream adapter, this reads the stream buffer
/// directly and sets eofbit at the end.
inline void append_stream(std::string& buf, std::istream& is)
{
std::streambuf* const sb = is.rdbuf();
if (sb == nullptr)
{
return;
}
for (;;)
{
const std::size_t used = buf.size();
const std::size_t room = (std::max)(buf.capacity() - used, std::size_t{4096});
buf.resize(used + room);
const std::streamsize got = sb->sgetn(&buf[used], static_cast<std::streamsize>(room));
buf.resize(used + static_cast<std::size_t>(got > 0 ? got : 0));
if (got <= 0)
{
break;
}
}
is.clear(is.rdstate() | std::ios::eofbit);
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END