amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-09-30 03:30:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/develop' into claude/issue-5340-restore-unget

Browse Source 
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-08-19 22:41:46 +02:00
parent a13902a33f b5378e8deb
commit 43b689b9b6
33 changed files with 470 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/nlohmann/detail/input/binary_reader.hpp
+23 -11
View File
@@ -465,15 +465,6 @@ class binary_reader
// CBOR //
//////////
/*!
@param[in] get_char whether a new character should be retrieved from the
input (true) or whether the last read character should
be considered instead (false)
@param[in] tag_handler how CBOR tags should be treated
@return whether a valid CBOR value was passed to the SAX parser
*/
template<typename NumberType>
bool get_cbor_negative_integer()
{
@@ -492,6 +483,14 @@ class binary_reader
return sax->number_integer(static_cast<number_integer_t>(-1) - static_cast<number_integer_t>(number));
}
/*!
@param[in] get_char whether a new character should be retrieved from the
input (true) or whether the last read character should
be considered instead (false)
@param[in] tag_handler how CBOR tags should be treated
@return whether a valid CBOR value was passed to the SAX parser
*/
bool parse_cbor_internal(const bool get_char,
const cbor_tag_handler_t tag_handler)
{
@@ -774,7 +773,13 @@ class binary_reader
case 0xBF: // map (indefinite length)
return get_cbor_object(detail::unknown_size(), tag_handler);
case 0xC6: // tagged item
case 0xC0: // tagged item
case 0xC1:
case 0xC2:
case 0xC3:
case 0xC4:
case 0xC5:
case 0xC6:
case 0xC7:
case 0xC8:
case 0xC9:
@@ -789,6 +794,9 @@ class binary_reader
case 0xD2:
case 0xD3:
case 0xD4:
case 0xD5:
case 0xD6:
case 0xD7:
case 0xD8: // tagged item (1 byte follows)
case 0xD9: // tagged item (2 bytes follow)
case 0xDA: // tagged item (4 bytes follow)
@@ -1988,7 +1996,11 @@ class binary_reader
{
if (get_char)
{
get(); // TODO(niels): may we ignore N here?
// no get_ignore_noop() here: the byte read next must be a string
// length type specification, and a no-op ('N') is not valid in
// that position. No-ops at positions where a value may appear are
// already consumed by the callers via get_ignore_noop().
get();
}
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "value")))
include/nlohmann/detail/input/input_adapters.hpp
+6 -2
View File
@@ -393,8 +393,12 @@ struct wide_string_input_helper<BaseInputAdapter, 4>
}
else
{
// unknown character
utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
// A code point above U+10FFFF has no UTF-8 encoding. Passing the
// unit through would narrow it to int, where 0xFFFFFFFF becomes
// char_traits<char>::eof() and would end the input silently, so
// emit a byte that is never valid UTF-8 and let the decoder
// reject it.
utf8_bytes[0] = 0xFF;
utf8_bytes_filled = 1;
}
}
include/nlohmann/detail/input/json_sax.hpp
+8 -4
View File
@@ -370,8 +370,10 @@ class json_sax_dom_parser
case value_t::string:
{
// include the length of the quotes, which is 2
v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
// escape sequences make the token longer than the value it
// parses to, so the start position cannot be derived from
// the value; use the offset the lexer recorded instead
v.start_position = m_lexer_ref->get_token_start_position();
break;
}
@@ -769,8 +771,10 @@ class json_sax_dom_callback_parser
case value_t::string:
{
// include the length of the quotes, which is 2
v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
// escape sequences make the token longer than the value it
// parses to, so the start position cannot be derived from
// the value; use the offset the lexer recorded instead
v.start_position = m_lexer_ref->get_token_start_position();
break;
}
include/nlohmann/detail/input/lexer.hpp
+20
View File
@@ -1381,6 +1381,11 @@ scan_number_done:
token_buffer.clear();
decimal_point_position = std::string::npos;
#if JSON_DIAGNOSTIC_POSITIONS
// the first character of the token has already been read, hence the -1
token_start_position = position.chars_read_total - 1;
#endif
note_token_start(std::integral_constant<bool, lazy_token_string> {});
}
@@ -1581,6 +1586,15 @@ scan_number_done:
release_lookahead_impl(std::integral_constant<bool, can_release_lookahead> {});
}
#if JSON_DIAGNOSTIC_POSITIONS
/// return the offset of the first character of the last read token; unlike
/// the token's parsed value, this accounts for escape sequences
constexpr std::size_t get_token_start_position() const noexcept
{
return token_start_position;
}
#endif
/// seekable adapter: rebuild the last read token from the input on demand
const std::vector<char_type>& collect_token_chars(std::vector<char_type>& out, std::true_type /*lazy*/) const
{
@@ -1781,6 +1795,12 @@ scan_number_done:
/// the last read token on error for seekable adapters (see collect_token_chars)
std::size_t token_string_start = 0;
#if JSON_DIAGNOSTIC_POSITIONS
/// start offset of the current token within the input, used to report
/// diagnostic positions (see reset())
std::size_t token_start_position = 0;
#endif
/// buffer for variable-length tokens (numbers, strings)
string_t token_buffer {};