Merge branch 'develop' of https://github.com/nlohmann/json into clang_windows
Conflicts: include/nlohmann/detail/input/binary_reader.hpp include/nlohmann/detail/input/input_adapters.hpp include/nlohmann/detail/input/lexer.hpp include/nlohmann/detail/output/binary_writer.hpp include/nlohmann/json.hpp single_include/nlohmann/json.hpp
This commit is contained in:
Niels Lohmann
commit
ac3922c7aa
128 changed files with 7773 additions and 2268 deletions
|
|
@ -106,12 +106,17 @@ class lexer : public lexer_base<BasicJsonType>
|
|||
using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
|
||||
using number_float_t = typename BasicJsonType::number_float_t;
|
||||
using string_t = typename BasicJsonType::string_t;
|
||||
using char_type = typename InputAdapterType::char_type;
|
||||
using char_int_type = typename std::char_traits<char_type>::int_type;
|
||||
|
||||
public:
|
||||
using token_type = typename lexer_base<BasicJsonType>::token_type;
|
||||
|
||||
explicit lexer(InputAdapterType&& adapter)
|
||||
: ia(std::move(adapter)), decimal_point_char(get_decimal_point()) {}
|
||||
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false)
|
||||
: ia(std::move(adapter))
|
||||
, ignore_comments(ignore_comments_)
|
||||
, decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
|
||||
{}
|
||||
|
||||
// delete because of pointer members
|
||||
lexer(const lexer&) = delete;
|
||||
|
|
@ -129,7 +134,7 @@ class lexer : public lexer_base<BasicJsonType>
|
|||
JSON_HEDLEY_PURE
|
||||
static char get_decimal_point() noexcept
|
||||
{
|
||||
const auto loc = localeconv();
|
||||
const auto* loc = localeconv();
|
||||
assert(loc != nullptr);
|
||||
return (loc->decimal_point == nullptr) ? '.' : *(loc->decimal_point);
|
||||
}
|
||||
|
|
@ -201,7 +206,7 @@ class lexer : public lexer_base<BasicJsonType>
|
|||
|
||||
@return true if and only if no range violation was detected
|
||||
*/
|
||||
bool next_byte_in_range(std::initializer_list<int> ranges)
|
||||
bool next_byte_in_range(std::initializer_list<char_int_type> ranges)
|
||||
{
|
||||
assert(ranges.size() == 2 || ranges.size() == 4 || ranges.size() == 6);
|
||||
add(current);
|
||||
|
|
@ -252,7 +257,7 @@ class lexer : public lexer_base<BasicJsonType>
|
|||
switch (get())
|
||||
{
|
||||
// end of file while parsing string
|
||||
case std::char_traits<char>::eof():
|
||||
case std::char_traits<char_type>::eof():
|
||||
{
|
||||
error_message = "invalid string: missing closing quote";
|
||||
return token_type::parse_error;
|
||||
|
|
@ -370,28 +375,28 @@ class lexer : public lexer_base<BasicJsonType>
|
|||
if (codepoint < 0x80)
|
||||
{
|
||||
// 1-byte characters: 0xxxxxxx (ASCII)
|
||||
add(codepoint);
|
||||
add(static_cast<char_int_type>(codepoint));
|
||||
}
|
||||
else if (codepoint <= 0x7FF)
|
||||
{
|
||||
// 2-byte characters: 110xxxxx 10xxxxxx
|
||||
add(static_cast<int>(0xC0u | (static_cast<unsigned int>(codepoint) >> 6u)));
|
||||
add(static_cast<int>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
|
||||
add(static_cast<char_int_type>(0xC0u | (static_cast<unsigned int>(codepoint) >> 6u)));
|
||||
add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
|
||||
}
|
||||
else if (codepoint <= 0xFFFF)
|
||||
{
|
||||
// 3-byte characters: 1110xxxx 10xxxxxx 10xxxxxx
|
||||
add(static_cast<int>(0xE0u | (static_cast<unsigned int>(codepoint) >> 12u)));
|
||||
add(static_cast<int>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
|
||||
add(static_cast<int>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
|
||||
add(static_cast<char_int_type>(0xE0u | (static_cast<unsigned int>(codepoint) >> 12u)));
|
||||
add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
|
||||
add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
|
||||
}
|
||||
else
|
||||
{
|
||||
// 4-byte characters: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
|
||||
add(static_cast<int>(0xF0u | (static_cast<unsigned int>(codepoint) >> 18u)));
|
||||
add(static_cast<int>(0x80u | ((static_cast<unsigned int>(codepoint) >> 12u) & 0x3Fu)));
|
||||
add(static_cast<int>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
|
||||
add(static_cast<int>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
|
||||
add(static_cast<char_int_type>(0xF0u | (static_cast<unsigned int>(codepoint) >> 18u)));
|
||||
add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 12u) & 0x3Fu)));
|
||||
add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
|
||||
add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
|
||||
}
|
||||
|
||||
break;
|
||||
|
|
@ -824,6 +829,77 @@ class lexer : public lexer_base<BasicJsonType>
|
|||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
* @brief scan a comment
|
||||
* @return whether comment could be scanned successfully
|
||||
*/
|
||||
bool scan_comment()
|
||||
{
|
||||
switch (get())
|
||||
{
|
||||
// single-line comments skip input until a newline or EOF is read
|
||||
case '/':
|
||||
{
|
||||
while (true)
|
||||
{
|
||||
switch (get())
|
||||
{
|
||||
case '\n':
|
||||
case '\r':
|
||||
case std::char_traits<char_type>::eof():
|
||||
case '\0':
|
||||
return true;
|
||||
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// multi-line comments skip input until */ is read
|
||||
case '*':
|
||||
{
|
||||
while (true)
|
||||
{
|
||||
switch (get())
|
||||
{
|
||||
case std::char_traits<char_type>::eof():
|
||||
case '\0':
|
||||
{
|
||||
error_message = "invalid comment; missing closing '*/'";
|
||||
return false;
|
||||
}
|
||||
|
||||
case '*':
|
||||
{
|
||||
switch (get())
|
||||
{
|
||||
case '/':
|
||||
return true;
|
||||
|
||||
default:
|
||||
{
|
||||
unget();
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// unexpected character after reading '/'
|
||||
default:
|
||||
{
|
||||
error_message = "invalid comment; expecting '/' or '*' after '/'";
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
JSON_HEDLEY_NON_NULL(2)
|
||||
static void strtof(float& f, const char* str, char** endptr) noexcept
|
||||
{
|
||||
|
|
@ -1213,13 +1289,13 @@ scan_number_done:
|
|||
@param[in] return_type the token type to return on success
|
||||
*/
|
||||
JSON_HEDLEY_NON_NULL(2)
|
||||
token_type scan_literal(const char* literal_text, const std::size_t length,
|
||||
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(get() != literal_text[i]))
|
||||
if (JSON_HEDLEY_UNLIKELY(std::char_traits<char_type>::to_char_type(get()) != literal_text[i]))
|
||||
{
|
||||
error_message = "invalid literal";
|
||||
return token_type::parse_error;
|
||||
|
|
@ -1237,7 +1313,7 @@ scan_number_done:
|
|||
{
|
||||
token_buffer.clear();
|
||||
token_string.clear();
|
||||
token_string.push_back(std::char_traits<char>::to_char_type(current));
|
||||
token_string.push_back(std::char_traits<char_type>::to_char_type(current));
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1250,7 +1326,7 @@ scan_number_done:
|
|||
|
||||
@return character read from the input
|
||||
*/
|
||||
std::char_traits<char>::int_type get()
|
||||
char_int_type get()
|
||||
{
|
||||
++position.chars_read_total;
|
||||
++position.chars_read_current_line;
|
||||
|
|
@ -1265,9 +1341,9 @@ scan_number_done:
|
|||
current = ia.get_character();
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_LIKELY(current != std::char_traits<char>::eof()))
|
||||
if (JSON_HEDLEY_LIKELY(current != std::char_traits<char_type>::eof()))
|
||||
{
|
||||
token_string.push_back(std::char_traits<char>::to_char_type(current));
|
||||
token_string.push_back(std::char_traits<char_type>::to_char_type(current));
|
||||
}
|
||||
|
||||
if (current == '\n')
|
||||
|
|
@ -1306,7 +1382,7 @@ scan_number_done:
|
|||
--position.chars_read_current_line;
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_LIKELY(current != std::char_traits<char>::eof()))
|
||||
if (JSON_HEDLEY_LIKELY(current != std::char_traits<char_type>::eof()))
|
||||
{
|
||||
assert(!token_string.empty());
|
||||
token_string.pop_back();
|
||||
|
|
@ -1314,9 +1390,9 @@ scan_number_done:
|
|||
}
|
||||
|
||||
/// add a character to token_buffer
|
||||
void add(int c)
|
||||
void add(char_int_type c)
|
||||
{
|
||||
token_buffer.push_back(std::char_traits<char>::to_char_type(c));
|
||||
token_buffer.push_back(static_cast<typename string_t::value_type>(c));
|
||||
}
|
||||
|
||||
public:
|
||||
|
|
@ -1377,7 +1453,7 @@ scan_number_done:
|
|||
else
|
||||
{
|
||||
// add character as is
|
||||
result.push_back(c);
|
||||
result.push_back(static_cast<std::string::value_type>(c));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -1413,6 +1489,15 @@ scan_number_done:
|
|||
return true;
|
||||
}
|
||||
|
||||
void skip_whitespace()
|
||||
{
|
||||
do
|
||||
{
|
||||
get();
|
||||
}
|
||||
while (current == ' ' or current == '\t' or current == '\n' or current == '\r');
|
||||
}
|
||||
|
||||
token_type scan()
|
||||
{
|
||||
// initially, skip the BOM
|
||||
|
|
@ -1423,9 +1508,18 @@ scan_number_done:
|
|||
}
|
||||
|
||||
// read next character and ignore whitespace
|
||||
do
|
||||
skip_whitespace();
|
||||
|
||||
// ignore comments
|
||||
if (ignore_comments and current == '/')
|
||||
{
|
||||
get();
|
||||
if (not scan_comment())
|
||||
{
|
||||
return token_type::parse_error;
|
||||
}
|
||||
|
||||
// skip following whitespace
|
||||
skip_whitespace();
|
||||
}
|
||||
while (current == ' ' || current == '\t' || current == '\n' || current == '\r');
|
||||
|
||||
|
|
@ -1447,11 +1541,20 @@ scan_number_done:
|
|||
|
||||
// literals
|
||||
case 't':
|
||||
return scan_literal("true", 4, token_type::literal_true);
|
||||
{
|
||||
std::array<char_type, 4> true_literal = {{'t', 'r', 'u', 'e'}};
|
||||
return scan_literal(true_literal.data(), true_literal.size(), token_type::literal_true);
|
||||
}
|
||||
case 'f':
|
||||
return scan_literal("false", 5, token_type::literal_false);
|
||||
{
|
||||
std::array<char_type, 5> false_literal = {{'f', 'a', 'l', 's', 'e'}};
|
||||
return scan_literal(false_literal.data(), false_literal.size(), token_type::literal_false);
|
||||
}
|
||||
case 'n':
|
||||
return scan_literal("null", 4, token_type::literal_null);
|
||||
{
|
||||
std::array<char_type, 4> null_literal = {{'n', 'u', 'l', 'l'}};
|
||||
return scan_literal(null_literal.data(), null_literal.size(), token_type::literal_null);
|
||||
}
|
||||
|
||||
// string
|
||||
case '\"':
|
||||
|
|
@ -1474,7 +1577,7 @@ scan_number_done:
|
|||
// end of input (the null byte is needed when parsing from
|
||||
// string literals)
|
||||
case '\0':
|
||||
case std::char_traits<char>::eof():
|
||||
case std::char_traits<char_type>::eof():
|
||||
return token_type::end_of_input;
|
||||
|
||||
// error
|
||||
|
|
@ -1488,8 +1591,11 @@ scan_number_done:
|
|||
/// input adapter
|
||||
InputAdapterType ia;
|
||||
|
||||
/// whether comments should be ignored (true) or signaled as errors (false)
|
||||
const bool ignore_comments = false;
|
||||
|
||||
/// the current character
|
||||
std::char_traits<char>::int_type current = std::char_traits<char>::eof();
|
||||
char_int_type current = std::char_traits<char_type>::eof();
|
||||
|
||||
/// whether the next get() call should just return current
|
||||
bool next_unget = false;
|
||||
|
|
@ -1498,7 +1604,7 @@ scan_number_done:
|
|||
position_t position {};
|
||||
|
||||
/// raw input token string (for error messages)
|
||||
std::vector<char> token_string {};
|
||||
std::vector<char_type> token_string {};
|
||||
|
||||
/// buffer for variable-length tokens (numbers, strings)
|
||||
string_t token_buffer {};
|
||||
|
|
@ -1512,7 +1618,7 @@ scan_number_done:
|
|||
number_float_t value_float = 0;
|
||||
|
||||
/// the decimal point
|
||||
const char decimal_point_char = '.';
|
||||
const char_int_type decimal_point_char = '.';
|
||||
};
|
||||
} // namespace detail
|
||||
} // namespace nlohmann
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue