Compare commits

..
Author SHA1 Message Date
Niels Lohmann a3c2b0897e Fix -Weffc++ errors in the #5198 locale test
GCC's -Weffc++ (an error in ci_test_gcc and ci_test_standards_gcc)
rejected LocaleSwitchingSax: it has a pointer data member but does not
declare its copy operations, and its vectors are not initialized in the
member initializer list. Store the locale name as a std::string and give
the vectors brace initializers, like SaxEventLogger in
unit-deserialization.cpp.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-28 04:19:20 +02:00
Niels Lohmann cfe7c9e732 Merge branch 'develop' into claude/issue-5198-84c9fe
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-27 20:57:56 +02:00
Niels Lohmann f37492a6d6 Stop the strtod retry loop when the decimal point is unchanged
convert_float_locale_aware() repeated the conversion until strtod
consumed the whole token, assuming an early stop can only mean a locale
change. Under a locale whose decimal point is not a single character
(e.g. the two-byte U+066B of ar_EG.UTF-8, ar_SA.UTF-8, or fa_IR.UTF-8,
all available on macOS), the in-place substitution can never succeed,
so parsing any float that reaches the strtod fallback (for example
3.14159265358979323846 at C++11) hung forever. Before this branch, the
same input was truncated.

Retry only if the decimal point changed since the previous attempt;
otherwise keep the value strtod parsed so far, as before. Add a test
that parses such numbers under a multi-byte decimal point locale; it
hangs without this change.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-27 18:22:43 +02:00
Niels Lohmann b69794bd80 Look up the locale decimal point at conversion time, not lexer construction
The lexer read localeconv()->decimal_point once in its constructor and wrote
that character into token_buffer in place of '.'. The strtod fallback then
used the locale current at conversion time, so an LC_NUMERIC change in
between (parser callback, SAX handler, another thread) truncated the value
in release builds and fired the endptr assertion in debug builds.

token_buffer now always holds '.'. Only the strtof/strtod/strtold fallback
depends on the locale: it looks up the decimal point right before the call,
restores '.' afterwards, and repeats the conversion if the locale changed in
between. As a side effect, std::from_chars and Clinger's fast path now also
apply under locales whose decimal point is not '.'.

Fixes #5198

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-27 17:14:00 +02:00
22 changed files with 394 additions and 415 deletions
+1 -1
View File
@@ -100,7 +100,7 @@ jobs:
container: ubuntu:focal
strategy:
matrix:
target: [ci_cmake_flags, ci_test_diagnostics, ci_test_diagnostic_positions, ci_test_noexceptions, ci_test_noimplicitconversions, ci_test_legacycomparison, ci_test_noglobaludls, ci_test_disableenumserialization, ci_test_disabletuplereferenceconversion, ci_test_skiplibraryversioncheck, ci_test_simdutf, ci_test_strict_nul_handling, ci_test_no_thread_local]
target: [ci_cmake_flags, ci_test_diagnostics, ci_test_diagnostic_positions, ci_test_noexceptions, ci_test_noimplicitconversions, ci_test_legacycomparison, ci_test_noglobaludls, ci_test_disableenumserialization, ci_test_skiplibraryversioncheck, ci_test_simdutf, ci_test_strict_nul_handling, ci_test_no_thread_local]
steps:
- name: Install build-essential
run: apt-get update ; apt-get install -y build-essential unzip wget git libssl-dev
-6
View File
@@ -55,7 +55,6 @@ option(JSON_Diagnostic_Positions "Enable diagnostic positions." OFF)
option(JSON_GlobalUDLs "Place user-defined string literals in the global namespace." ON)
option(JSON_ImplicitConversions "Enable implicit conversions." ON)
option(JSON_DisableEnumSerialization "Disable default integer enum serialization." OFF)
option(JSON_DisableTupleReferenceConversion "Disable conversion from a one-element tuple of a JSON reference." OFF)
option(JSON_LegacyDiscardedValueComparison "Enable legacy discarded value comparison." OFF)
option(JSON_Install "Install CMake targets during install step." ${MAIN_PROJECT})
option(JSON_MultipleHeaders "Use non-amalgamated version of the library." ON)
@@ -102,10 +101,6 @@ if (JSON_DisableEnumSerialization)
message(STATUS "Enum integer serialization is disabled (JSON_DISABLE_ENUM_SERIALIZATION=1)")
endif()
if (JSON_DisableTupleReferenceConversion)
message(STATUS "Tuple reference conversion is disabled (JSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1)")
endif()
if (JSON_LegacyDiscardedValueComparison)
message(STATUS "Legacy discarded value comparison enabled (JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1)")
endif()
@@ -148,7 +143,6 @@ target_compile_definitions(
$<$<NOT:$<BOOL:${JSON_GlobalUDLs}>>:JSON_USE_GLOBAL_UDLS=0>
$<$<NOT:$<BOOL:${JSON_ImplicitConversions}>>:JSON_USE_IMPLICIT_CONVERSIONS=0>
$<$<BOOL:${JSON_DisableEnumSerialization}>:JSON_DISABLE_ENUM_SERIALIZATION=1>
$<$<BOOL:${JSON_DisableTupleReferenceConversion}>:JSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1>
$<$<BOOL:${JSON_Diagnostics}>:JSON_DIAGNOSTICS=1>
$<$<BOOL:${JSON_Diagnostic_Positions}>:JSON_DIAGNOSTIC_POSITIONS=1>
$<$<BOOL:${JSON_LegacyDiscardedValueComparison}>:JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1>
-14
View File
@@ -276,20 +276,6 @@ add_custom_target(ci_test_disableenumserialization
COMMENT "Compile and test with enum serialization disabled"
)
###############################################################################
# Disable conversion from a one-element tuple of a JSON reference.
###############################################################################
add_custom_target(ci_test_disabletuplereferenceconversion
COMMAND ${CMAKE_COMMAND}
-DCMAKE_BUILD_TYPE=Debug -GNinja
-DJSON_BuildTests=ON -DJSON_FastTests=ON -DJSON_DisableTupleReferenceConversion=ON
-S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_disabletuplereferenceconversion
COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_disabletuplereferenceconversion
COMMAND cd ${PROJECT_BINARY_DIR}/build_disabletuplereferenceconversion && ${CMAKE_CTEST_COMMAND} --parallel ${N} --output-on-failure
COMMENT "Compile and test with tuple reference conversion disabled"
)
###############################################################################
# Skip the multiple-inclusion library version check.
###############################################################################
-1
View File
@@ -210,7 +210,6 @@ INSERT INTO searchIndex(name, type, path) VALUES ('JSON_CATCH_USER', 'Macro', 'a
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_DIAGNOSTICS', 'Macro', 'api/macros/json_diagnostics/index.html');
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_DIAGNOSTIC_POSITIONS', 'Macro', 'api/macros/json_diagnostic_positions/index.html');
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_DISABLE_ENUM_SERIALIZATION', 'Macro', 'api/macros/json_disable_enum_serialization/index.html');
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_DISABLE_TUPLE_REFERENCE_CONVERSION', 'Macro', 'api/macros/json_disable_tuple_reference_conversion/index.html');
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_HAS_CPP_11', 'Macro', 'api/macros/json_has_cpp_11/index.html');
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_HAS_CPP_14', 'Macro', 'api/macros/json_has_cpp_11/index.html');
INSERT INTO searchIndex(name, type, path) VALUES ('JSON_HAS_CPP_17', 'Macro', 'api/macros/json_has_cpp_11/index.html');
@@ -159,8 +159,6 @@ basic_json(basic_json&& other) noexcept;
- `CompatibleType` is not `basic_json` (to avoid hijacking copy/move constructors),
- `CompatibleType` is not a different `basic_json` type (i.e. with different template arguments)
- `CompatibleType` is not a `basic_json` nested type (e.g., `json_pointer`, `iterator`, etc.)
- if [`JSON_DISABLE_TUPLE_REFERENCE_CONVERSION`](../macros/json_disable_tuple_reference_conversion.md) is defined
to `1`: `CompatibleType` is not a one-element `std::tuple` holding a reference to `basic_json`
- `json_serializer<U>` (with `U = uncvref_t<CompatibleType>`) has a `to_json(basic_json_t&, CompatibleType&&)`
method
-1
View File
@@ -52,7 +52,6 @@ header. See also the [macro overview page](../../features/macros.md).
- [**JSON_BRACE_INIT_COPY_SEMANTICS**](json_brace_init_copy_semantics.md) - opt in to copy/move semantics for single-element brace initialization
- [**JSON_DISABLE_ENUM_SERIALIZATION**](json_disable_enum_serialization.md) - switch off default serialization/deserialization functions for enums
- [**JSON_DISABLE_TUPLE_REFERENCE_CONVERSION**](json_disable_tuple_reference_conversion.md) - switch off conversion from a one-element tuple of a JSON reference
- [**JSON_USE_IMPLICIT_CONVERSIONS**](json_use_implicit_conversions.md) - control implicit conversions
## Comparison behavior
@@ -1,114 +0,0 @@
# JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
```cpp
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION /* value */
```
When defined to `1`, a `basic_json` value can no longer be constructed from a one-element `std::tuple` whose element is
a reference to that `basic_json` type, such as `std::tuple<json&>`, `std::tuple<const json&>`, or `std::tuple<json&&>`.
These are the tuples created by `std::forward_as_tuple(j)`.
## Default definition
The default value is `0` (disabled — existing behavior is preserved).
```cpp
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION 0
```
## Notes
!!! note "Background"
By default, `basic_json` can be constructed from any `std::tuple` whose elements can be converted to JSON; the result
is an array. This includes `std::tuple<json&>`, which becomes a one-element array.
`std::tuple` only converts another tuple element by element if its element type cannot be constructed from the whole
source tuple. Because `json` *can* be constructed from `std::tuple<json&>`, `std::tuple` instead converts the whole
tuple into a single `json` value. This has two surprising effects:
```cpp
json j = true;
// rejected by some standard libraries (e.g., libc++); with others, the
// reference binds to a temporary that is destroyed right away
std::tuple<const json&> t1(std::forward_as_tuple(j));
// compiles, but std::get<0>(t2) is [true], not true
std::tuple<json> t2(std::forward_as_tuple(j));
```
Enabling this macro removes the conversion, so both tuples are converted element by element: `std::get<0>(t1)`
refers to `j`, and `std::get<0>(t2)` is a copy of `j` (see [#2226](https://github.com/nlohmann/json/issues/2226)).
!!! warning "Opt-in only"
This macro must be defined **before** including `<nlohmann/json.hpp>`. Defining it after the include has no effect.
!!! note "Affected conversions"
Only one-element tuples holding a reference to the **same** `basic_json` type are affected. Constructing a JSON value
from them no longer compiles:
```cpp
json j = true;
json a = std::forward_as_tuple(j); // error with the macro enabled
json b = json::array({j}); // use this instead: [true]
```
Tuples holding a JSON value (`std::make_tuple(j)`), tuples with more than one element, and tuples holding references
to other types (including other `basic_json` specializations) are converted to arrays as before.
!!! hint "CMake option"
This behavior can also be controlled with the CMake option
[`JSON_DisableTupleReferenceConversion`](../../integration/cmake.md#json_disabletuplereferenceconversion)
(`OFF` by default) which defines `JSON_DISABLE_TUPLE_REFERENCE_CONVERSION` accordingly.
## Examples
??? example "Default behavior (macro not defined)"
```cpp
#include <nlohmann/json.hpp>
using json = nlohmann::json;
int main()
{
json j = true;
std::tuple<json> t(std::forward_as_tuple(j));
// std::get<0>(t) is [true] -- the whole tuple was converted
}
```
??? example "Conversion disabled (macro defined to 1)"
```cpp
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION 1
#include <nlohmann/json.hpp>
using json = nlohmann::json;
int main()
{
json j = true;
std::tuple<json> t(std::forward_as_tuple(j));
// std::get<0>(t) is true -- a copy of j
std::tuple<const json&> r(std::forward_as_tuple(j));
// std::get<0>(r) refers to j
}
```
## See also
- [**basic_json(CompatibleType&&)**](../basic_json/basic_json.md) - the affected constructor
- [:simple-cmake: JSON_DisableTupleReferenceConversion](../../integration/cmake.md#json_disabletuplereferenceconversion) -
CMake option to control the macro
## Version history
- Added in version 3.13.0.
-7
View File
@@ -83,13 +83,6 @@ When defined, default parse and serialize functions for enums are excluded and h
See [full documentation of `JSON_DISABLE_ENUM_SERIALIZATION`](../api/macros/json_disable_enum_serialization.md).
## `JSON_DISABLE_TUPLE_REFERENCE_CONVERSION`
When defined to `1`, a JSON value can no longer be created from a one-element `std::tuple` holding a reference to a JSON
value, such as the result of `std::forward_as_tuple(j)`. This lets `std::tuple` convert such tuples element-wise.
See [full documentation of `JSON_DISABLE_TUPLE_REFERENCE_CONVERSION`](../api/macros/json_disable_tuple_reference_conversion.md).
## `JSON_NO_IO`
When defined, headers `<cstdio>`, `<ios>`, `<iosfwd>`, `<istream>`, and `<ostream>` are not included and parse functions
-6
View File
@@ -169,12 +169,6 @@ Enable position diagnostics by defining macro [`JSON_DIAGNOSTIC_POSITIONS`](../a
Disable default `enum` serialization by defining the macro
[`JSON_DISABLE_ENUM_SERIALIZATION`](../api/macros/json_disable_enum_serialization.md). This option is `OFF` by default.
### `JSON_DisableTupleReferenceConversion`
Disable the conversion from a one-element `std::tuple` holding a reference to a JSON value by defining the macro
[`JSON_DISABLE_TUPLE_REFERENCE_CONVERSION`](../api/macros/json_disable_tuple_reference_conversion.md). This option is
`OFF` by default.
### `JSON_FastTests`
Skip expensive/slow test suites. This option is `OFF` by default. Depends on `JSON_BuildTests`.
-1
View File
@@ -287,7 +287,6 @@ nav:
- 'JSON_DIAGNOSTICS': api/macros/json_diagnostics.md
- 'JSON_DIAGNOSTIC_POSITIONS': api/macros/json_diagnostic_positions.md
- 'JSON_DISABLE_ENUM_SERIALIZATION': api/macros/json_disable_enum_serialization.md
- 'JSON_DISABLE_TUPLE_REFERENCE_CONVERSION': api/macros/json_disable_tuple_reference_conversion.md
- 'JSON_HAS_CPP_11, JSON_HAS_CPP_14, JSON_HAS_CPP_17, JSON_HAS_CPP_20': api/macros/json_has_cpp_11.md
- 'JSON_HAS_EXPERIMENTAL_FILESYSTEM, JSON_HAS_FILESYSTEM': api/macros/json_has_filesystem.md
- 'JSON_HAS_RANGES': api/macros/json_has_ranges.md
@@ -471,13 +471,11 @@ inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& t, index_sequence<
j = { std::get<Idx>(t)... };
}
// A one-element braced list does not reliably wrap its element: with
// JSON_BRACE_INIT_COPY_SEMANTICS it copies it, which would serialize
// std::tuple<int>{5} as 5 rather than [5], and some compilers (e.g., Apple clang
// 15 and 16) copy an element that is itself a basic_json even without it, so
// std::tuple<json>{true} became true rather than [true]. Build what the default
// deduction builds instead: an object if the element is a [string, value] pair,
// a one-element array otherwise.
#if JSON_BRACE_INIT_COPY_SEMANTICS
// JSON_BRACE_INIT_COPY_SEMANTICS makes a one-element braced list copy its
// element instead of wrapping it, which would serialize std::tuple<int>{5} as 5
// rather than [5]. Build what the default deduction builds instead: an object
// if the element is a [string, value] pair, a one-element array otherwise.
template<typename BasicJsonType, typename Tuple>
inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& t, index_sequence<0> /*unused*/)
{
@@ -495,6 +493,7 @@ inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& t, index_sequence<
j = BasicJsonType::array({std::move(element)});
}
}
#endif
template<typename BasicJsonType, typename Tuple>
inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& /*unused*/, index_sequence<> /*unused*/)
+76 -39
View File
@@ -206,7 +206,6 @@ class lexer : public lexer_base<BasicJsonType>
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
: ia(std::move(adapter))
, ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{}
@@ -222,8 +221,7 @@ class lexer : public lexer_base<BasicJsonType>
// locales
/////////////////////
/// return the locale-dependent decimal point
JSON_HEDLEY_PURE
/// return the decimal point of the current locale
static char get_decimal_point() noexcept
{
const auto* loc = localeconv();
@@ -1092,9 +1090,10 @@ class lexer : public lexer_base<BasicJsonType>
token_type::value_float if number could be successfully scanned,
token_type::parse_error otherwise
@note The scanner is independent of the current locale. Internally, the
locale's decimal point is used instead of `.` to work with the
locale-dependent converters.
@note The scanner is independent of the current locale: token_buffer
always holds `.`. Only the std::strtod fallback of convert_number()
depends on the locale, and it looks up the decimal point right
before converting (see convert_float_locale_aware()).
*/
token_type scan_number() // lgtm [cpp/use-of-goto] `goto` is used in this function to implement the number-parsing state machine described above. By design, any finite input will eventually reach the "done" state or return token_type::parse_error. In each intermediate state, 1 byte of the input is appended to the token_buffer vector, and only the already initialized variables token_buffer, number_type, and error_message are manipulated.
{
@@ -1183,7 +1182,7 @@ scan_number_zero:
{
case '.':
{
add(decimal_point_char);
add(current);
decimal_point_position = token_buffer.size() - 1;
goto scan_number_decimal1;
}
@@ -1220,7 +1219,7 @@ scan_number_any1:
case '.':
{
add(decimal_point_char);
add(current);
decimal_point_position = token_buffer.size() - 1;
goto scan_number_decimal1;
}
@@ -1462,9 +1461,9 @@ scan_number_done:
// Only a number below 1 can carry further insignificant zeros, and only
// while the count stays at the limit does removing them change the
// answer - so this loop is skipped for all but a few tokens. Note
// token_buffer holds the locale's decimal point, so the fraction is
// located through decimal_point_position rather than by searching '.'.
// answer - so this loop is skipped for all but a few tokens. The
// fraction is located through decimal_point_position rather than by
// searching '.'.
if (lead_zero != 0)
{
JSON_ASSERT(has_dot != 0); // an integer "0" cannot reach the limit
@@ -1482,8 +1481,8 @@ scan_number_done:
@brief convert the number text in token_buffer to its value and token type
The digit sequence in token_buffer has already been validated (by the
scan_number() state machine or by the contiguous fast path) and holds the
locale decimal point in place of '.'. Integers are parsed first and fall
scan_number() state machine or by the contiguous fast path) and holds '.'
as decimal point, independent of the locale. Integers are parsed first and fall
back to floating point on overflow. This is shared so both scanners produce
identical results.
@@ -1563,7 +1562,7 @@ scan_number_done:
// integer conversion above overflowed. Prefer std::from_chars
// (Eisel-Lemire, locale-independent, correctly rounded) when available;
// otherwise the exact Clinger fast path (double only); otherwise the
// locale-aware strtof/strtod.
// locale-aware strtof/strtod/strtold.
if (parse_float_from_chars(num_begin, num_end, value_float))
{
return token_type::value_float;
@@ -1572,26 +1571,75 @@ scan_number_done:
// extra pass over the token's bytes, which otherwise shows up on
// high-precision inputs such as canada.json
if (mantissa_fits_clinger(mantissa_end)
&& parse_float_fast(num_begin, num_end, decimal_point_char, value_float))
&& parse_float_fast(num_begin, num_end, value_float))
{
return token_type::value_float;
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
strtof(value_float, token_buffer.data(), &endptr);
// we checked the number format before
JSON_ASSERT(endptr == token_buffer.data() + token_buffer.size());
convert_float_locale_aware();
return token_type::value_float;
}
/*!
@brief convert the float in token_buffer with strtof/strtod/strtold
These functions expect the decimal point of the *current* locale, so it is
looked up right before the conversion instead of once when the lexer is
constructed: a locale change in between (by a parser callback, a SAX
handler, or another thread) must not truncate the value (#5198). The
token has been validated before, so if the conversion stops early and the
decimal point changed in the meantime, the locale changed between the
lookup and the call, and the conversion is repeated with the new decimal
point. If the decimal point did not change, a retry cannot succeed: the
locale's decimal point is not a single character (e.g., the two-byte
U+066B of ar_EG.UTF-8 or fa_IR.UTF-8) and cannot be substituted in place.
The value strtod parsed up to that point is kept, as before this change.
Note that changing the locale in another thread *while* strtod runs is
undefined behavior of the C library, which this function cannot prevent.
*/
void convert_float_locale_aware()
{
const bool has_dot = decimal_point_position != std::string::npos;
char decimal_point = get_decimal_point();
for (;;)
{
const bool substitute = has_dot && decimal_point != '.';
if (substitute)
{
token_buffer[decimal_point_position] = static_cast<typename string_t::value_type>(decimal_point);
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
strtof(value_float, token_buffer.data(), &endptr);
if (substitute)
{
// get_string() hands the token to the SAX interface with '.'
token_buffer[decimal_point_position] = '.';
}
if (JSON_HEDLEY_LIKELY(endptr == token_buffer.data() + token_buffer.size()))
{
return;
}
// retry only if the locale changed; otherwise, this would loop forever
const char current_decimal_point = get_decimal_point();
if (current_decimal_point == decimal_point)
{
return;
}
decimal_point = current_decimal_point;
}
}
/*!
@brief contiguous fast path for scanning a number
Parses the whole number token straight from the input buffer, avoiding the
per-character get()/add() of scan_number(). On success it fills token_buffer
(with the locale decimal point substituted, as scan_number() does) and
(as scan_number() does) and
returns the token type. On anything it does not fully recognize as a
well-formed number it makes no state change and returns
token_type::uninitialized, so the caller falls back to scan_number(), which
@@ -1707,16 +1755,11 @@ scan_number_done:
}
#endif
// materialize the token exactly as scan_number() would, substituting the
// locale decimal point so convert_number()'s strtof fallback stays valid.
// reset() already cleared token_buffer, so append() fills it (assign() is
// avoided because custom string_t types need not provide it)
// materialize the token exactly as scan_number() would. reset() already
// cleared token_buffer, so append() fills it (assign() is avoided
// because custom string_t types need not provide it)
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
if (dot_index != std::string::npos)
{
token_buffer[dot_index] = static_cast<typename string_t::value_type>(decimal_point_char);
decimal_point_position = dot_index;
}
decimal_point_position = dot_index;
ia.bulk_skip(len - 1);
position.chars_read_total += (len - 1);
@@ -1983,11 +2026,7 @@ scan_number_done:
/// return current string value (implicitly resets the token; useful only once)
string_t& get_string()
{
// translate decimal points from locale back to '.' (#4084)
if (decimal_point_char != '.' && decimal_point_position != std::string::npos)
{
token_buffer[decimal_point_position] = '.';
}
// a number token holds '.' regardless of the locale (#4084)
return token_buffer;
}
@@ -2283,9 +2322,7 @@ scan_number_done:
number_unsigned_t value_unsigned = 0;
number_float_t value_float = 0;
/// the decimal point
const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input
/// the position of the decimal point in token_buffer
std::size_t decimal_point_position = std::string::npos;
/// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
+8 -13
View File
@@ -118,14 +118,12 @@ std::strtod. The parser only activates for number_float_t == double; float and
long double keep the std::strtof/std::strtold paths (see the templated overload
below).
@param[in] first pointer to the first character of the number
@param[in] last pointer past the last character
@param[in] decimal_point the (locale-dependent) decimal point character
@param[out] out the parsed value on success
@param[in] first pointer to the first character of the number
@param[in] last pointer past the last character
@param[out] out the parsed value on success
@return true if the value was parsed exactly; false to fall back to strtod
*/
template<typename DecimalPointType>
bool parse_float_fast(const char* first, const char* last, DecimalPointType decimal_point, double& out) noexcept
inline bool parse_float_fast(const char* first, const char* last, double& out) noexcept
{
#if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
// Clinger's fast path is only exact when double operations are evaluated in
@@ -136,7 +134,6 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
// std::from_chars / std::strtod path.
static_cast<void>(first);
static_cast<void>(last);
static_cast<void>(decimal_point);
static_cast<void>(out);
return false;
#else
@@ -175,7 +172,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
++num_digits;
fractional_digits += static_cast<int>(seen_dot);
}
else if (static_cast<DecimalPointType>(c) == decimal_point)
else if (c == '.')
{
if (JSON_HEDLEY_UNLIKELY(seen_dot))
{
@@ -260,8 +257,8 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
}
/// fast float path is only exact for `double`; decline for float/long double
template<typename DecimalPointType, typename FloatType>
bool parse_float_fast(const char* /*first*/, const char* /*last*/, DecimalPointType /*decimal_point*/, FloatType& /*out*/) noexcept
template<typename FloatType>
bool parse_float_fast(const char* /*first*/, const char* /*last*/, FloatType& /*out*/) noexcept
{
return false;
}
@@ -273,9 +270,7 @@ std::from_chars is locale-independent, correctly rounded, and - via the
Eisel-Lemire algorithm in modern standard libraries - much faster than strtod
over the whole value range (not just the Clinger subset). It is used only when
__cpp_lib_to_chars indicates full floating-point support and only when it
consumes the entire token ([first, last)); a partial parse means the buffer
uses a non-'.' locale decimal point, in which case the caller falls back to the
locale-aware path. An under-/overflow (result_out_of_range) also declines, so
consumes the entire token ([first, last)). An under-/overflow (result_out_of_range) also declines, so
the caller's strtod fallback supplies the well-defined ±inf/0 result the parser
expects (side-stepping the P4168 divergence between implementations).
-4
View File
@@ -916,10 +916,6 @@ void templated_json_throw(ExceptionType exception)
#define JSON_DISABLE_ENUM_SERIALIZATION 0
#endif
#ifndef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION 0
#endif
#ifndef JSON_USE_GLOBAL_UDLS
#define JSON_USE_GLOBAL_UDLS 1
#endif
@@ -25,7 +25,6 @@
#undef JSON_INLINE_VARIABLE
#undef JSON_NO_UNIQUE_ADDRESS
#undef JSON_DISABLE_ENUM_SERIALIZATION
#undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#undef JSON_USE_GLOBAL_UDLS
#ifndef JSON_TEST_KEEP_MACROS
@@ -636,18 +636,6 @@ template<typename BasicJsonType, typename CompatibleType>
struct is_compatible_type
: is_compatible_type_impl<BasicJsonType, CompatibleType> {};
// a one-element std::tuple holding a reference to BasicJsonType, as created by
// std::forward_as_tuple(j); see JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
template<typename BasicJsonType, typename T>
struct is_basic_json_reference_tuple : std::false_type {};
template<typename BasicJsonType, typename T>
struct is_basic_json_reference_tuple<BasicJsonType, std::tuple<T>>
{
static constexpr bool value =
std::is_reference<T>::value && std::is_same<uncvref_t<T>, BasicJsonType>::value;
};
template<typename BasicJsonType, typename CompatibleArrayType>
struct is_compatible_binary_type
{
+1 -6
View File
@@ -1595,12 +1595,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
template < typename CompatibleType,
typename U = detail::uncvref_t<CompatibleType>,
detail::enable_if_t <
!detail::is_basic_json<U>::value && detail::is_compatible_type<basic_json_t, U>::value
#if JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
// see https://github.com/nlohmann/json/issues/2226
&& !detail::is_basic_json_reference_tuple<basic_json_t, U>::value
#endif
, int > = 0 >
!detail::is_basic_json<U>::value && detail::is_compatible_type<basic_json_t, U>::value, int > = 0 >
basic_json(CompatibleType && val) noexcept(noexcept( // NOLINT(bugprone-forwarding-reference-overload,bugprone-exception-escape)
JSONSerializer<U>::to_json(std::declval<basic_json_t&>(),
std::forward<CompatibleType>(val))))
+91 -82
View File
@@ -3327,10 +3327,6 @@ void templated_json_throw(ExceptionType exception)
#define JSON_DISABLE_ENUM_SERIALIZATION 0
#endif
#ifndef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION 0
#endif
#ifndef JSON_USE_GLOBAL_UDLS
#define JSON_USE_GLOBAL_UDLS 1
#endif
@@ -4650,18 +4646,6 @@ template<typename BasicJsonType, typename CompatibleType>
struct is_compatible_type
: is_compatible_type_impl<BasicJsonType, CompatibleType> {};
// a one-element std::tuple holding a reference to BasicJsonType, as created by
// std::forward_as_tuple(j); see JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
template<typename BasicJsonType, typename T>
struct is_basic_json_reference_tuple : std::false_type {};
template<typename BasicJsonType, typename T>
struct is_basic_json_reference_tuple<BasicJsonType, std::tuple<T>>
{
static constexpr bool value =
std::is_reference<T>::value && std::is_same<uncvref_t<T>, BasicJsonType>::value;
};
template<typename BasicJsonType, typename CompatibleArrayType>
struct is_compatible_binary_type
{
@@ -7016,13 +7000,11 @@ inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& t, index_sequence<
j = { std::get<Idx>(t)... };
}
// A one-element braced list does not reliably wrap its element: with
// JSON_BRACE_INIT_COPY_SEMANTICS it copies it, which would serialize
// std::tuple<int>{5} as 5 rather than [5], and some compilers (e.g., Apple clang
// 15 and 16) copy an element that is itself a basic_json even without it, so
// std::tuple<json>{true} became true rather than [true]. Build what the default
// deduction builds instead: an object if the element is a [string, value] pair,
// a one-element array otherwise.
#if JSON_BRACE_INIT_COPY_SEMANTICS
// JSON_BRACE_INIT_COPY_SEMANTICS makes a one-element braced list copy its
// element instead of wrapping it, which would serialize std::tuple<int>{5} as 5
// rather than [5]. Build what the default deduction builds instead: an object
// if the element is a [string, value] pair, a one-element array otherwise.
template<typename BasicJsonType, typename Tuple>
inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& t, index_sequence<0> /*unused*/)
{
@@ -7040,6 +7022,7 @@ inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& t, index_sequence<
j = BasicJsonType::array({std::move(element)});
}
}
#endif
template<typename BasicJsonType, typename Tuple>
inline void to_json_tuple_impl(BasicJsonType& j, const Tuple& /*unused*/, index_sequence<> /*unused*/)
@@ -8622,14 +8605,12 @@ std::strtod. The parser only activates for number_float_t == double; float and
long double keep the std::strtof/std::strtold paths (see the templated overload
below).
@param[in] first pointer to the first character of the number
@param[in] last pointer past the last character
@param[in] decimal_point the (locale-dependent) decimal point character
@param[out] out the parsed value on success
@param[in] first pointer to the first character of the number
@param[in] last pointer past the last character
@param[out] out the parsed value on success
@return true if the value was parsed exactly; false to fall back to strtod
*/
template<typename DecimalPointType>
bool parse_float_fast(const char* first, const char* last, DecimalPointType decimal_point, double& out) noexcept
inline bool parse_float_fast(const char* first, const char* last, double& out) noexcept
{
#if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
// Clinger's fast path is only exact when double operations are evaluated in
@@ -8640,7 +8621,6 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
// std::from_chars / std::strtod path.
static_cast<void>(first);
static_cast<void>(last);
static_cast<void>(decimal_point);
static_cast<void>(out);
return false;
#else
@@ -8679,7 +8659,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
++num_digits;
fractional_digits += static_cast<int>(seen_dot);
}
else if (static_cast<DecimalPointType>(c) == decimal_point)
else if (c == '.')
{
if (JSON_HEDLEY_UNLIKELY(seen_dot))
{
@@ -8764,8 +8744,8 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
}
/// fast float path is only exact for `double`; decline for float/long double
template<typename DecimalPointType, typename FloatType>
bool parse_float_fast(const char* /*first*/, const char* /*last*/, DecimalPointType /*decimal_point*/, FloatType& /*out*/) noexcept
template<typename FloatType>
bool parse_float_fast(const char* /*first*/, const char* /*last*/, FloatType& /*out*/) noexcept
{
return false;
}
@@ -8777,9 +8757,7 @@ std::from_chars is locale-independent, correctly rounded, and - via the
Eisel-Lemire algorithm in modern standard libraries - much faster than strtod
over the whole value range (not just the Clinger subset). It is used only when
__cpp_lib_to_chars indicates full floating-point support and only when it
consumes the entire token ([first, last)); a partial parse means the buffer
uses a non-'.' locale decimal point, in which case the caller falls back to the
locale-aware path. An under-/overflow (result_out_of_range) also declines, so
consumes the entire token ([first, last)). An under-/overflow (result_out_of_range) also declines, so
the caller's strtod fallback supplies the well-defined ±inf/0 result the parser
expects (side-stepping the P4168 divergence between implementations).
@@ -9320,7 +9298,6 @@ class lexer : public lexer_base<BasicJsonType>
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
: ia(std::move(adapter))
, ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{}
@@ -9336,8 +9313,7 @@ class lexer : public lexer_base<BasicJsonType>
// locales
/////////////////////
/// return the locale-dependent decimal point
JSON_HEDLEY_PURE
/// return the decimal point of the current locale
static char get_decimal_point() noexcept
{
const auto* loc = localeconv();
@@ -10206,9 +10182,10 @@ class lexer : public lexer_base<BasicJsonType>
token_type::value_float if number could be successfully scanned,
token_type::parse_error otherwise
@note The scanner is independent of the current locale. Internally, the
locale's decimal point is used instead of `.` to work with the
locale-dependent converters.
@note The scanner is independent of the current locale: token_buffer
always holds `.`. Only the std::strtod fallback of convert_number()
depends on the locale, and it looks up the decimal point right
before converting (see convert_float_locale_aware()).
*/
token_type scan_number() // lgtm [cpp/use-of-goto] `goto` is used in this function to implement the number-parsing state machine described above. By design, any finite input will eventually reach the "done" state or return token_type::parse_error. In each intermediate state, 1 byte of the input is appended to the token_buffer vector, and only the already initialized variables token_buffer, number_type, and error_message are manipulated.
{
@@ -10297,7 +10274,7 @@ scan_number_zero:
{
case '.':
{
add(decimal_point_char);
add(current);
decimal_point_position = token_buffer.size() - 1;
goto scan_number_decimal1;
}
@@ -10334,7 +10311,7 @@ scan_number_any1:
case '.':
{
add(decimal_point_char);
add(current);
decimal_point_position = token_buffer.size() - 1;
goto scan_number_decimal1;
}
@@ -10576,9 +10553,9 @@ scan_number_done:
// Only a number below 1 can carry further insignificant zeros, and only
// while the count stays at the limit does removing them change the
// answer - so this loop is skipped for all but a few tokens. Note
// token_buffer holds the locale's decimal point, so the fraction is
// located through decimal_point_position rather than by searching '.'.
// answer - so this loop is skipped for all but a few tokens. The
// fraction is located through decimal_point_position rather than by
// searching '.'.
if (lead_zero != 0)
{
JSON_ASSERT(has_dot != 0); // an integer "0" cannot reach the limit
@@ -10596,8 +10573,8 @@ scan_number_done:
@brief convert the number text in token_buffer to its value and token type
The digit sequence in token_buffer has already been validated (by the
scan_number() state machine or by the contiguous fast path) and holds the
locale decimal point in place of '.'. Integers are parsed first and fall
scan_number() state machine or by the contiguous fast path) and holds '.'
as decimal point, independent of the locale. Integers are parsed first and fall
back to floating point on overflow. This is shared so both scanners produce
identical results.
@@ -10677,7 +10654,7 @@ scan_number_done:
// integer conversion above overflowed. Prefer std::from_chars
// (Eisel-Lemire, locale-independent, correctly rounded) when available;
// otherwise the exact Clinger fast path (double only); otherwise the
// locale-aware strtof/strtod.
// locale-aware strtof/strtod/strtold.
if (parse_float_from_chars(num_begin, num_end, value_float))
{
return token_type::value_float;
@@ -10686,26 +10663,75 @@ scan_number_done:
// extra pass over the token's bytes, which otherwise shows up on
// high-precision inputs such as canada.json
if (mantissa_fits_clinger(mantissa_end)
&& parse_float_fast(num_begin, num_end, decimal_point_char, value_float))
&& parse_float_fast(num_begin, num_end, value_float))
{
return token_type::value_float;
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
strtof(value_float, token_buffer.data(), &endptr);
// we checked the number format before
JSON_ASSERT(endptr == token_buffer.data() + token_buffer.size());
convert_float_locale_aware();
return token_type::value_float;
}
/*!
@brief convert the float in token_buffer with strtof/strtod/strtold
These functions expect the decimal point of the *current* locale, so it is
looked up right before the conversion instead of once when the lexer is
constructed: a locale change in between (by a parser callback, a SAX
handler, or another thread) must not truncate the value (#5198). The
token has been validated before, so if the conversion stops early and the
decimal point changed in the meantime, the locale changed between the
lookup and the call, and the conversion is repeated with the new decimal
point. If the decimal point did not change, a retry cannot succeed: the
locale's decimal point is not a single character (e.g., the two-byte
U+066B of ar_EG.UTF-8 or fa_IR.UTF-8) and cannot be substituted in place.
The value strtod parsed up to that point is kept, as before this change.
Note that changing the locale in another thread *while* strtod runs is
undefined behavior of the C library, which this function cannot prevent.
*/
void convert_float_locale_aware()
{
const bool has_dot = decimal_point_position != std::string::npos;
char decimal_point = get_decimal_point();
for (;;)
{
const bool substitute = has_dot && decimal_point != '.';
if (substitute)
{
token_buffer[decimal_point_position] = static_cast<typename string_t::value_type>(decimal_point);
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
strtof(value_float, token_buffer.data(), &endptr);
if (substitute)
{
// get_string() hands the token to the SAX interface with '.'
token_buffer[decimal_point_position] = '.';
}
if (JSON_HEDLEY_LIKELY(endptr == token_buffer.data() + token_buffer.size()))
{
return;
}
// retry only if the locale changed; otherwise, this would loop forever
const char current_decimal_point = get_decimal_point();
if (current_decimal_point == decimal_point)
{
return;
}
decimal_point = current_decimal_point;
}
}
/*!
@brief contiguous fast path for scanning a number
Parses the whole number token straight from the input buffer, avoiding the
per-character get()/add() of scan_number(). On success it fills token_buffer
(with the locale decimal point substituted, as scan_number() does) and
(as scan_number() does) and
returns the token type. On anything it does not fully recognize as a
well-formed number it makes no state change and returns
token_type::uninitialized, so the caller falls back to scan_number(), which
@@ -10821,16 +10847,11 @@ scan_number_done:
}
#endif
// materialize the token exactly as scan_number() would, substituting the
// locale decimal point so convert_number()'s strtof fallback stays valid.
// reset() already cleared token_buffer, so append() fills it (assign() is
// avoided because custom string_t types need not provide it)
// materialize the token exactly as scan_number() would. reset() already
// cleared token_buffer, so append() fills it (assign() is avoided
// because custom string_t types need not provide it)
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
if (dot_index != std::string::npos)
{
token_buffer[dot_index] = static_cast<typename string_t::value_type>(decimal_point_char);
decimal_point_position = dot_index;
}
decimal_point_position = dot_index;
ia.bulk_skip(len - 1);
position.chars_read_total += (len - 1);
@@ -11097,11 +11118,7 @@ scan_number_done:
/// return current string value (implicitly resets the token; useful only once)
string_t& get_string()
{
// translate decimal points from locale back to '.' (#4084)
if (decimal_point_char != '.' && decimal_point_position != std::string::npos)
{
token_buffer[decimal_point_position] = '.';
}
// a number token holds '.' regardless of the locale (#4084)
return token_buffer;
}
@@ -11397,9 +11414,7 @@ scan_number_done:
number_unsigned_t value_unsigned = 0;
number_float_t value_float = 0;
/// the decimal point
const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input
/// the position of the decimal point in token_buffer
std::size_t decimal_point_position = std::string::npos;
/// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
@@ -27495,12 +27510,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
template < typename CompatibleType,
typename U = detail::uncvref_t<CompatibleType>,
detail::enable_if_t <
!detail::is_basic_json<U>::value && detail::is_compatible_type<basic_json_t, U>::value
#if JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
// see https://github.com/nlohmann/json/issues/2226
&& !detail::is_basic_json_reference_tuple<basic_json_t, U>::value
#endif
, int > = 0 >
!detail::is_basic_json<U>::value && detail::is_compatible_type<basic_json_t, U>::value, int > = 0 >
basic_json(CompatibleType && val) noexcept(noexcept( // NOLINT(bugprone-forwarding-reference-overload,bugprone-exception-escape)
JSONSerializer<U>::to_json(std::declval<basic_json_t&>(),
std::forward<CompatibleType>(val))))
@@ -32550,7 +32560,6 @@ struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-c
#undef JSON_INLINE_VARIABLE
#undef JSON_NO_UNIQUE_ADDRESS
#undef JSON_DISABLE_ENUM_SERIALIZATION
#undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#undef JSON_USE_GLOBAL_UDLS
#ifndef JSON_TEST_KEEP_MACROS
+1 -1
View File
@@ -666,7 +666,7 @@ TEST_CASE("parse_float_fast declines what it cannot convert exactly")
// always safe: the caller then falls back to a slower, exact conversion.
const auto fast = [](const std::string & s, double & out)
{
return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), '.', out);
return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), out);
};
double out = 0;
@@ -1,79 +0,0 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++ (supporting code)
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#include "doctest_compatibility.h"
// This file tests the opt-in JSON_DISABLE_TUPLE_REFERENCE_CONVERSION, so it
// defines the macro itself rather than relying on a -D flag, and runs in every
// build.
#ifdef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#endif
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION 1
#include <nlohmann/json.hpp>
using nlohmann::json;
using nlohmann::ordered_json;
#include <string>
#include <tuple>
#include <type_traits>
#include <utility>
TEST_CASE("JSON_DISABLE_TUPLE_REFERENCE_CONVERSION")
{
SECTION("json is not constructible from a one-element tuple of a json reference")
{
CHECK_FALSE(std::is_constructible<json, std::tuple<json&>>::value);
CHECK_FALSE(std::is_constructible<json, std::tuple<const json&>>::value);
CHECK_FALSE(std::is_constructible < json, std::tuple < json && >>::value);
CHECK_FALSE(std::is_constructible<json, const std::tuple<json&>&>::value);
CHECK_FALSE(std::is_constructible<ordered_json, std::tuple<ordered_json&>>::value);
}
SECTION("issue #2226 - tuple<const json&> from tuple<json&> keeps the reference")
{
json j = true;
const std::tuple<const json&> tup(std::forward_as_tuple(j));
CHECK(&std::get<0>(tup) == &j);
}
SECTION("tuple<json> from tuple<json&> copies the element")
{
const json j = {{"key", "value"}};
const std::tuple<json> t1(std::forward_as_tuple(j));
CHECK(std::get<0>(t1) == j);
json j2 = "text";
const std::tuple<json> t2(std::forward_as_tuple(std::move(j2)));
CHECK(std::get<0>(t2) == "text");
}
SECTION("other tuple conversions are not affected")
{
const json j = true;
// one-element tuple holding a json value
CHECK(json(std::make_tuple(j)) == json::array({true}));
// tuples with more than one element, even when holding references
int i = 1;
CHECK(json(std::forward_as_tuple(i, j)) == json::array({1, true}));
CHECK(json(std::forward_as_tuple(j, j)) == json::array({true, true}));
// one-element tuples holding references to other types
std::string s = "text";
CHECK(json(std::forward_as_tuple(s)) == json::array({"text"}));
CHECK(json(std::forward_as_tuple(i)) == json::array({1}));
// a reference to a different basic_json specialization
ordered_json oj = true;
CHECK(json(std::forward_as_tuple(oj)) == json::array({true}));
}
}
+210
View File
@@ -12,7 +12,12 @@
#include <nlohmann/json.hpp>
using nlohmann::json;
#include <array>
#include <clocale>
#include <map>
#include <string>
#include <utility>
#include <vector>
struct ParserImpl final: public nlohmann::json_sax<json>
{
@@ -175,3 +180,208 @@ TEST_CASE("locale-dependent test (LC_NUMERIC=de_DE)")
MESSAGE("locale de_DE is not usable");
}
}
namespace
{
// records the numbers of a flat array and switches LC_NUMERIC to the given
// locale once the array opens - after the lexer was constructed, but before
// any number in the array is lexed
struct LocaleSwitchingSax final: public nlohmann::json_sax<json>
{
explicit LocaleSwitchingSax(const char* switch_to)
: locale_after_open(switch_to)
{}
bool null() override
{
return true;
}
bool boolean(bool /*val*/) override
{
return true;
}
bool number_integer(json::number_integer_t /*val*/) override
{
return true;
}
bool number_unsigned(json::number_unsigned_t /*val*/) override
{
return true;
}
bool number_float(json::number_float_t val, const json::string_t& s) override
{
values.push_back(val);
strings.push_back(s);
return true;
}
bool string(json::string_t& /*val*/) override
{
return true;
}
bool binary(json::binary_t& /*val*/) override
{
return true;
}
bool start_object(std::size_t /*val*/) override
{
return true;
}
bool key(json::string_t& /*val*/) override
{
return true;
}
bool end_object() override
{
return true;
}
bool start_array(std::size_t /*val*/) override
{
switched = std::setlocale(LC_NUMERIC, locale_after_open.c_str()) != nullptr;
return true;
}
bool end_array() override
{
return true;
}
bool parse_error(std::size_t /*val*/, const std::string& /*val*/, const nlohmann::detail::exception& /*val*/) override
{
return false;
}
std::string locale_after_open;
bool switched = false;
std::vector<json::number_float_t> values {}; // NOLINT(readability-redundant-member-init)
std::vector<json::string_t> strings {}; // NOLINT(readability-redundant-member-init)
};
} // namespace
TEST_CASE("locale changes between lexer construction and number conversion (#5198)")
{
// The numbers are chosen so that the conversion also takes the strtod
// fallback, which honors the locale that is current at conversion time:
// too many significant digits for Clinger's fast path, an underflow that
// std::from_chars rejects, and a plain value.
const std::vector<std::string> numbers = {"3.14159265358979323846", "1.5e-400", "12.34", "-0.000123456789012345678"};
std::string text = "[";
for (const auto& n : numbers)
{
text += (text.size() == 1 ? "" : ",") + n;
}
text += "]";
using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
// reference values, parsed without a locale switch
REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
const json expected = json::parse(text);
const long_double_json expected_ld = long_double_json::parse(text);
const std::array<std::pair<const char*, const char*>, 2> transitions =
{
{
{"C", "de_DE"},
{"de_DE", "C"}
}
};
for (const auto& transition : transitions)
{
CAPTURE(transition.first);
CAPTURE(transition.second);
if (std::setlocale(LC_NUMERIC, transition.first) == nullptr)
{
MESSAGE("locale is not usable");
continue;
}
// SAX parsing
{
LocaleSwitchingSax sax(transition.second);
CHECK(json::sax_parse(text, &sax));
if (sax.switched)
{
CHECK(sax.values == expected.get<std::vector<json::number_float_t>>());
CHECK(sax.strings == numbers);
}
}
// DOM parsing with a callback
{
bool switched = false;
const auto cb = [&](int /*depth*/, json::parse_event_t event, json& /*parsed*/)
{
if (event == json::parse_event_t::array_start)
{
switched = std::setlocale(LC_NUMERIC, transition.second) != nullptr;
}
return true;
};
const json j = json::parse(text, cb);
if (switched)
{
CHECK(j == expected);
}
}
// a long double goes through std::strtold unless std::from_chars supports it
{
bool switched = false;
const auto cb = [&](int /*depth*/, long_double_json::parse_event_t event, long_double_json& /*parsed*/)
{
if (event == long_double_json::parse_event_t::array_start)
{
switched = std::setlocale(LC_NUMERIC, transition.second) != nullptr;
}
return true;
};
const long_double_json j = long_double_json::parse(text, cb);
if (switched)
{
CHECK(j == expected_ld);
}
}
}
std::setlocale(LC_NUMERIC, "C");
}
TEST_CASE("locale with a multi-byte decimal point")
{
// Some locales use a decimal point that is not a single character, e.g.
// U+066B ARABIC DECIMAL SEPARATOR (two bytes in UTF-8). It cannot be
// substituted in place for '.', so the strtod fallback stops early. The
// conversion must still terminate rather than retry forever.
const std::array<const char*, 6> names = {{"ar_EG.UTF-8", "ar_SA.UTF-8", "fa_IR.UTF-8", "ps_AF.UTF-8", "ar_EG", "fa_IR"}};
bool tested = false;
for (const char* name : names)
{
if (std::setlocale(LC_NUMERIC, name) == nullptr)
{
continue;
}
const std::string decimal_point = std::localeconv()->decimal_point;
if (decimal_point.size() < 2)
{
continue;
}
CAPTURE(name);
tested = true;
// too many significant digits for Clinger's fast path, and an underflow
// that std::from_chars rejects: both reach the strtod fallback
json j;
CHECK_NOTHROW(j = json::parse("[3.14159265358979323846, 1.5e-400, -0.000123456789012345678]"));
CHECK(j.is_array());
CHECK(json::accept("3.14159265358979323846"));
// a value the locale-independent paths convert is not affected
CHECK(json::parse("12.5") == 12.5);
}
if (!tested)
{
MESSAGE("no locale with a multi-byte decimal point is usable");
}
std::setlocale(LC_NUMERIC, "C");
}
-18
View File
@@ -18,11 +18,6 @@
// for some reason including this after the json header leads to linker errors with VS 2017...
#include <locale>
// skip tests if JSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1 (#2226)
#if defined(JSON_DISABLE_TUPLE_REFERENCE_CONVERSION) && (JSON_DISABLE_TUPLE_REFERENCE_CONVERSION == 1)
#define SKIP_TESTS_FOR_TUPLE_REFERENCE_CONVERSION
#endif
#define JSON_TESTS_PRIVATE
#include <nlohmann/json.hpp>
using json = nlohmann::json;
@@ -33,7 +28,6 @@ using ordered_json = nlohmann::ordered_json;
#include <cstdio>
#include <list>
#include <tuple>
#include <type_traits>
#include <utility>
@@ -548,18 +542,6 @@ TEST_CASE("regression tests 2")
)));
}
#ifndef SKIP_TESTS_FOR_TUPLE_REFERENCE_CONVERSION
SECTION("issue #2226 - std::tuple dangling reference - implicit conversion")
{
// by default, a one-element tuple holding a json reference converts to
// a one-element array; JSON_DISABLE_TUPLE_REFERENCE_CONVERSION removes
// this conversion (see unit-disable-tuple-reference-conversion.cpp)
const json j = true;
CHECK(std::is_constructible<json, std::tuple<const json&>>::value);
CHECK(json(std::forward_as_tuple(j)) == json::array({true}));
}
#endif
SECTION("PR #2181 - regression bug with lvalue")
{
// see https://github.com/nlohmann/json/pull/2181#issuecomment-653326060