Skip to content

J
json
Unverified Commit 14881cf9 authored by Niels Lohmann's avatar Niels Lohmann Committed by GitHub
Browse files
Options

Merge pull request #2178 from nlohmann/input_adapter_tests 

Add input adapter tests
parents 28048d82 ae04426c
Hide whitespace changes
Inline Side-by-side
Showing with 91 additions and 28 deletions
include/nlohmann/detail/input/input_adapters.hpp
View file @ 14881cf9
......@@ -247,15 +247,15 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
}
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[0] = static_cast<std::char_traits<char>::int_type>(0xC0u | ((static_cast<unsigned int>(wc) >> 6u)));
utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(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[0] = static_cast<std::char_traits<char>::int_type>(0xE0u | ((static_cast<unsigned int>(wc) >> 12u)));
utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((static_cast<unsigned int>(wc) >> 6u) & 0x3Fu));
utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
utf8_bytes_filled = 3;
}
else
......@@ -263,7 +263,7 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
if (JSON_HEDLEY_UNLIKELY(not input.empty()))
{
const auto wc2 = static_cast<unsigned int>(input.get_character());
const auto charcode = 0x10000u + (((wc & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
const auto charcode = 0x10000u + (((static_cast<unsigned int>(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));
......@@ -339,15 +339,18 @@ struct iterator_input_adapter_factory
}
};
// This test breaks astyle formatting when inlined in a template specialization.
template<typename T>
inline constexpr bool is_iterator_of_multibyte()
struct is_iterator_of_multibyte
{
return sizeof(typename std::iterator_traits<T>::value_type) > 1;
}
using value_type = typename std::iterator_traits<T>::value_type;
enum
{
value = sizeof(value_type) > 1
};
};
template<typename IteratorType>
struct iterator_input_adapter_factory<IteratorType, enable_if_t<is_iterator_of_multibyte<IteratorType>()>>
struct iterator_input_adapter_factory<IteratorType, enable_if_t<is_iterator_of_multibyte<IteratorType>::value>>
{
using iterator_type = IteratorType;
using char_type = typename std::iterator_traits<iterator_type>::value_type;
......
include/nlohmann/detail/input/lexer.hpp
View file @ 14881cf9
......@@ -113,7 +113,7 @@ class lexer : public lexer_base<BasicJsonType>
using token_type = typename lexer_base<BasicJsonType>::token_type;
explicit lexer(InputAdapterType&& adapter)
: ia(std::move(adapter)), decimal_point_char(static_cast<char_type>(get_decimal_point())) {}
: ia(std::move(adapter)), decimal_point_char(static_cast<char_int_type>(get_decimal_point())) {}
// delete because of pointer members
lexer(const lexer&) = delete;
......@@ -1218,7 +1218,7 @@ scan_number_done:
token_type scan_literal(const char_type* literal_text, const std::size_t length,
token_type return_type)
{
assert(current == literal_text[0]);
assert(std::char_traits<char_type>::to_char_type(current) == literal_text[0]);
for (std::size_t i = 1; i < length; ++i)
{
if (JSON_HEDLEY_UNLIKELY(std::char_traits<char_type>::to_char_type(get()) != literal_text[i]))
......@@ -1523,7 +1523,7 @@ scan_number_done:
number_float_t value_float = 0;
/// the decimal point
const char_type decimal_point_char = '.';
const char_int_type decimal_point_char = '.';
};
} // namespace detail
} // namespace nlohmann
single_include/nlohmann/json.hpp
View file @ 14881cf9
......@@ -4669,15 +4669,15 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
}
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[0] = static_cast<std::char_traits<char>::int_type>(0xC0u | ((static_cast<unsigned int>(wc) >> 6u)));
utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(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[0] = static_cast<std::char_traits<char>::int_type>(0xE0u | ((static_cast<unsigned int>(wc) >> 12u)));
utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((static_cast<unsigned int>(wc) >> 6u) & 0x3Fu));
utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
utf8_bytes_filled = 3;
}
else
......@@ -4685,7 +4685,7 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
if (JSON_HEDLEY_UNLIKELY(not input.empty()))
{
const auto wc2 = static_cast<unsigned int>(input.get_character());
const auto charcode = 0x10000u + (((wc & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
const auto charcode = 0x10000u + (((static_cast<unsigned int>(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));
......@@ -4761,15 +4761,18 @@ struct iterator_input_adapter_factory
}
};
// This test breaks astyle formatting when inlined in a template specialization.
template<typename T>
inline constexpr bool is_iterator_of_multibyte()
struct is_iterator_of_multibyte
{
return sizeof(typename std::iterator_traits<T>::value_type) > 1;
}
using value_type = typename std::iterator_traits<T>::value_type;
enum
{
value = sizeof(value_type) > 1
};
};
template<typename IteratorType>
struct iterator_input_adapter_factory<IteratorType, enable_if_t<is_iterator_of_multibyte<IteratorType>()>>
struct iterator_input_adapter_factory<IteratorType, enable_if_t<is_iterator_of_multibyte<IteratorType>::value>>
{
using iterator_type = IteratorType;
using char_type = typename std::iterator_traits<iterator_type>::value_type;
......@@ -8177,7 +8180,7 @@ class lexer : public lexer_base<BasicJsonType>
using token_type = typename lexer_base<BasicJsonType>::token_type;
explicit lexer(InputAdapterType&& adapter)
: ia(std::move(adapter)), decimal_point_char(static_cast<char_type>(get_decimal_point())) {}
: ia(std::move(adapter)), decimal_point_char(static_cast<char_int_type>(get_decimal_point())) {}
// delete because of pointer members
lexer(const lexer&) = delete;
......@@ -9282,7 +9285,7 @@ scan_number_done:
token_type scan_literal(const char_type* literal_text, const std::size_t length,
token_type return_type)
{
assert(current == literal_text[0]);
assert(std::char_traits<char_type>::to_char_type(current) == literal_text[0]);
for (std::size_t i = 1; i < length; ++i)
{
if (JSON_HEDLEY_UNLIKELY(std::char_traits<char_type>::to_char_type(get()) != literal_text[i]))
......@@ -9587,7 +9590,7 @@ scan_number_done:
number_float_t value_float = 0;
/// the decimal point
const char_type decimal_point_char = '.';
const char_int_type decimal_point_char = '.';
};
} // namespace detail
} // namespace nlohmann
......
test/src/unit-deserialization.cpp
View file @ 14881cf9
......@@ -1039,3 +1039,60 @@ TEST_CASE("deserialization")
}));
}
}
TEST_CASE_TEMPLATE("deserialization of different character types (ASCII)", T,
char, unsigned char, signed char,
wchar_t,
char16_t, char32_t,
std::uint8_t, std::int8_t,
std::int16_t, std::uint16_t,
std::int32_t, std::uint32_t)
{
std::vector<T> v = {'t', 'r', 'u', 'e'};
CHECK(json::parse(v) == json(true));
CHECK(json::accept(v));
SaxEventLogger l;
CHECK(json::sax_parse(v, &l));
CHECK(l.events.size() == 1);
CHECK(l.events == std::vector<std::string>({"boolean(true)"}));
}
TEST_CASE_TEMPLATE("deserialization of different character types (UTF-8)", T,
char, unsigned char, std::uint8_t)
{
// a star emoji
std::vector<T> v = {'"', static_cast<T>(0xe2), static_cast<T>(0xad), static_cast<T>(0x90), static_cast<T>(0xef), static_cast<T>(0xb8), static_cast<T>(0x8f), '"'};
CHECK(json::parse(v).dump(-1, ' ', true) == "\"\\u2b50\\ufe0f\"");
CHECK(json::accept(v));
SaxEventLogger l;
CHECK(json::sax_parse(v, &l));
CHECK(l.events.size() == 1);
}
TEST_CASE_TEMPLATE("deserialization of different character types (UTF-16)", T,
char16_t, std::uint16_t)
{
// a star emoji
std::vector<T> v = {static_cast<T>('"'), static_cast<T>(0x2b50), static_cast<T>(0xfe0f), static_cast<T>('"')};
CHECK(json::parse(v).dump(-1, ' ', true) == "\"\\u2b50\\ufe0f\"");
CHECK(json::accept(v));
SaxEventLogger l;
CHECK(json::sax_parse(v, &l));
CHECK(l.events.size() == 1);
}
TEST_CASE_TEMPLATE("deserialization of different character types (UTF-32)", T,
char32_t, std::uint32_t)
{
// a star emoji
std::vector<T> v = {static_cast<T>('"'), static_cast<T>(0x2b50), static_cast<T>(0xfe0f), static_cast<T>('"')};
CHECK(json::parse(v).dump(-1, ' ', true) == "\"\\u2b50\\ufe0f\"");
CHECK(json::accept(v));
SaxEventLogger l;
CHECK(json::sax_parse(v, &l));
CHECK(l.events.size() == 1);
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment