amorfo77/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-24 23:08:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' into claude/fix-issue-3989-db7e45

Browse Source 
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-23 06:35:52 +02:00
2 parents 510ee0ab4f ace1030107
commit 5c2aba70f9
60 files changed
+7977 -595357
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/input/lexer.hpp
+72 -39
View File
@@ -12,6 +12,7 @@
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint32_t
#include <cstdio> // snprintf
#include <cstring> // memcmp
#include <initializer_list> // initializer_list
#include <string> // char_traits, string
#include <utility> // move
@@ -432,30 +433,43 @@ class lexer : public lexer_base<BasicJsonType>
}
/// contiguous input: bulk-append the run of ordinary characters and complete
/// well-formed UTF-8 sequences starting at the current read position, leaving
/// the first byte that needs individual handling (the closing quote, an
/// escape, a control character, or an ill-formed UTF-8 byte) for get()
void scan_string_bulk(std::true_type /*bulk*/)
/// well-formed UTF-8 sequences starting at the current read position, then
/// read the first byte that needs individual handling (the closing quote, an
/// escape, a control character, or an ill-formed UTF-8 byte) like get().
/// That byte is taken from the buffer that was just scanned. Through get(),
/// Apple Clang merged this read with the other get() calls of the scan
/// function, which load the read position again right after it was stored
/// (3% of json::accept() on jeopardy.json on Apple M1).
char_int_type get_after_string_run(std::true_type /*bulk*/)
{
// a pending unget must be consumed through the normal path first
if (next_unget)
{
return;
return get();
}
const std::size_t remaining = ia.bulk_remaining();
if (remaining == 0)
{
return;
return get();
}
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
const auto* const raw = ia.bulk_data();
const auto* const data = reinterpret_cast<const unsigned char*>(raw);
const std::size_t pos = string_bulk_run(data, remaining);
if (pos == 0)
const std::size_t pos = lexer_string_bulk_run(data, remaining);
if (pos != 0)
{
return;
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
bulk_consume(reinterpret_cast<const char*>(data), pos);
}
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
bulk_consume(reinterpret_cast<const char*>(data), pos);
if (pos == remaining)
{
return get(); // end of the contiguous input
}
// what get() does, with the byte at hand
advance_position();
ia.bulk_skip(1);
current = char_traits<char_type>::to_int_type(raw[pos]);
return track_after_read();
}
/// consume @a n characters at @a data (the adapter's bulk_data()) and do
@@ -488,7 +502,10 @@ class lexer : public lexer_base<BasicJsonType>
}
/// streaming input: no bulk fast path
void scan_string_bulk(std::false_type /*bulk*/) const noexcept {}
char_int_type get_after_string_run(std::false_type /*bulk*/)
{
return get();
}
/*!
@brief scan a string literal
@@ -516,11 +533,8 @@ class lexer : public lexer_base<BasicJsonType>
while (true)
{
// bulk-consume ordinary characters from contiguous input, then
// handle the next special byte through the switch below
scan_string_bulk(std::integral_constant<bool, bulk_scan> {});
// get the next character
switch (get())
// get the next character, the one that ends the run
switch (get_after_string_run(std::integral_constant<bool, bulk_scan>()))
{
// end of file while parsing the string
case char_traits<char_type>::eof():
@@ -1906,18 +1920,23 @@ scan_number_done:
}
/*!
@param[in] literal_text the literal text to expect
@param[in] length the length of the passed literal text
@param[in] return_type the token type to return on success
@param[in] rest the literal text after its first character, which
is current (its length is a template parameter, so
that the comparison of the contiguous fast path is
a fixed-size load, not a call of memcmp)
@param[in] return_type the token type to return on success
*/
JSON_HEDLEY_NON_NULL(2)
token_type scan_literal(const char_type* literal_text, const std::size_t length,
token_type return_type)
template<std::size_t N>
JSON_HEDLEY_NEVER_INLINE token_type scan_literal(const char (&rest)[N], token_type return_type) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
{
JSON_ASSERT(char_traits<char_type>::to_char_type(current) == literal_text[0]);
for (std::size_t i = 1; i < length; ++i)
constexpr std::size_t length = N - 1;
if (scan_literal_bulk(rest, length, std::integral_constant<bool, bulk_scan> {}))
{
if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != literal_text[i]))
return return_type;
}
for (std::size_t i = 0; i < length; ++i)
{
if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != static_cast<char_type>(rest[i])))
{
error_message = "invalid literal";
error_cause = error_kind::other;
@@ -1927,6 +1946,27 @@ scan_number_done:
return return_type;
}
/// contiguous input: compare the rest of a literal at once; false (and
/// nothing consumed) if it does not match, so that the byte path reports
/// the error at the right character
JSON_HEDLEY_ALWAYS_INLINE bool scan_literal_bulk(const char* rest, const std::size_t length, std::true_type /*bulk*/)
{
if (next_unget || ia.bulk_remaining() < length
|| std::memcmp(ia.bulk_data(), rest, length) != 0)
{
return false;
}
bulk_consume(reinterpret_cast<const char*>(ia.bulk_data()), length);
current = static_cast<char_int_type>(static_cast<unsigned char>(rest[length - 1]));
return true;
}
/// streaming input: no bulk fast path
bool scan_literal_bulk(const char* /*rest*/, const std::size_t /*length*/, std::false_type /*bulk*/) const noexcept
{
return false;
}
/////////////////////
// input management
/////////////////////
@@ -2561,21 +2601,14 @@ scan_number_done:
return token_type::value_separator;
// literals
// (the text after the first character; no local arrays, which
// would give this function a stack canary on every token)
case 't':
{
std::array<char_type, 4> true_literal = {{static_cast<char_type>('t'), static_cast<char_type>('r'), static_cast<char_type>('u'), static_cast<char_type>('e')}};
return scan_literal(true_literal.data(), true_literal.size(), token_type::literal_true);
}
return scan_literal("rue", token_type::literal_true);
case 'f':
{
std::array<char_type, 5> false_literal = {{static_cast<char_type>('f'), static_cast<char_type>('a'), static_cast<char_type>('l'), static_cast<char_type>('s'), static_cast<char_type>('e')}};
return scan_literal(false_literal.data(), false_literal.size(), token_type::literal_false);
}
return scan_literal("alse", token_type::literal_false);
case 'n':
{
std::array<char_type, 4> null_literal = {{static_cast<char_type>('n'), static_cast<char_type>('u'), static_cast<char_type>('l'), static_cast<char_type>('l')}};
return scan_literal(null_literal.data(), null_literal.size(), token_type::literal_null);
}
return scan_literal("ull", token_type::literal_null);
// string
case '\"':