amorfo77/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-22 14:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' into claude/todo-191-plan-508110

Browse Source 
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-21 10:51:41 +02:00
2 parents d13c9e7212 bd5227c2ec
commit 9222763ab9
495 files changed
+623375 -6453
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/input/binary_reader.hpp
+147 -142
View File
@@ -12,7 +12,6 @@
#include <cmath> // ldexp
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint16_t, uint32_t, uint64_t, uintmax_t
#include <cstdio> // snprintf
#include <cstring> // memcpy
#include <iterator> // back_inserter
#include <limits> // numeric_limits
@@ -196,8 +195,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(current != char_traits<char_type>::eof()))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(110, chars_read,
exception_message(concat("expected end of input; last byte: 0x", get_token_string()), "value"), nullptr));
return last_byte_error(exception_id::unexpected_end_of_input, "expected end of input", "value", "");
}
}
@@ -319,8 +317,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(document_size < 0 || static_cast<std::size_t>(document_size) != chars_read - document_start))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
exception_message(concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(chars_read - document_start), ")"), "document"), nullptr));
return bson_document_size_error(document_size, chars_read - document_start);
}
return true;
}
@@ -512,9 +509,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(len < 1))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
return bson_length_error("string length must be at least 1, is ", len, "string");
}
if (JSON_HEDLEY_UNLIKELY(!get_string(len - static_cast<NumberType>(1), result)))
@@ -524,10 +519,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(get() != 0x00))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("BSON string is not null-terminated",
"string"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "BSON string is not null-terminated", "string");
}
return check_string_utf8(result, "string");
@@ -547,9 +539,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(len < 0))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("byte array length cannot be negative, is ", std::to_string(len)), "binary"), nullptr));
return bson_length_error("byte array length cannot be negative, is ", len, "binary");
}
// All BSON binary values have a subtype
@@ -639,11 +629,7 @@ class binary_reader
default: // anything else is not supported (yet)
{
std::array<char, 3> cr{{}};
static_cast<void>((std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(element_type))); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
const std::string cr_str{cr.data()};
return sax->parse_error(element_type_parse_position, cr_str,
parse_error::create(114, element_type_parse_position, concat("Unsupported BSON record type 0x", cr_str), nullptr));
return bson_unsupported_type_error(element_type_parse_position, element_type);
}
}
}
@@ -967,9 +953,7 @@ class binary_reader
{
if (tag_handler == cbor_tag_handler_t::error)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
// ignore and store: the tag value is already in the head, so
@@ -989,9 +973,7 @@ class binary_reader
{
case cbor_tag_handler_t::error:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
case cbor_tag_handler_t::ignore:
@@ -1065,9 +1047,7 @@ class binary_reader
default: // anything else (0xFF is handled inside the other types)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
}
}
@@ -1078,12 +1058,10 @@ class binary_reader
@param[in] context parsing context for the error message
@return whether the SAX consumer accepts the parse error
*/
JSON_HEDLEY_NEVER_INLINE
bool cbor_indefinite_string_error(const char* type_name, const char* context)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("indefinite-length ", type_name,
" is not allowed inside indefinite-length ", type_name, "; last byte: 0x", last_token), context), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, concat("indefinite-length ", type_name, " is not allowed inside indefinite-length ", type_name, "; last byte: 0x", get_token_string()), context);
}
/*!
@@ -1160,9 +1138,7 @@ class binary_reader
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("expected length specification (0x60-0x7B)", inside_indefinite ? "" : " or indefinite string type (0x7F)", "; last byte: 0x", last_token), "string"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "expected length specification (0x60-0x7B)", "string", inside_indefinite ? "" : " or indefinite string type (0x7F)");
}
}
}
@@ -1292,9 +1268,7 @@ class binary_reader
break;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
}
/*!
@@ -1375,9 +1349,7 @@ class binary_reader
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("expected length specification (0x40-0x5B)", inside_indefinite ? "" : " or indefinite binary array type (0x5F)", "; last byte: 0x", last_token), "binary"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "expected length specification (0x40-0x5B)", "binary", inside_indefinite ? "" : " or indefinite binary array type (0x5F)");
}
}
}
@@ -1523,8 +1495,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(len) || len == detail::unknown_size()))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message(concat("excessive ", context, " size"), "size"), nullptr));
return container_size_error(context);
}
result = conditional_static_cast<std::size_t>(len);
return true;
@@ -2011,9 +1982,7 @@ class binary_reader
default: // anything else
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
}
}
@@ -2094,9 +2063,7 @@ class binary_reader
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0x", last_token), "string"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "expected length specification (0xA0-0xBF, 0xD9-0xDB)", "string", "");
}
}
}
@@ -2188,9 +2155,7 @@ class binary_reader
break;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
}
/*!
@@ -2499,8 +2464,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(len < 0))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message("string length must not be negative", "string"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "string length must not be negative", "string");
}
return true;
}
@@ -2600,18 +2564,7 @@ class binary_reader
default:
break;
}
auto last_token = get_token_string();
std::string message;
if (input_format != input_format_t::bjdata)
{
message = "expected length type specification (U, i, I, l, L); last byte: 0x" + last_token;
}
else
{
message = "expected length type specification (U, i, u, I, m, l, M, L); last byte: 0x" + last_token;
}
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(message, "string"), nullptr));
return length_type_error("", "string");
}
/*!
@@ -2696,13 +2649,11 @@ class binary_reader
}
if (JSON_HEDLEY_UNLIKELY(number < 0))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message("count in an optimized container must be positive", "size"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "count in an optimized container must be positive", "size");
}
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(number)))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message("integer value overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "integer value overflow", "size");
}
result = static_cast<std::size_t>(number); // NOLINT(bugprone-signed-char-misuse,cert-str34-c): number is not a char
return true;
@@ -2799,8 +2750,7 @@ class binary_reader
}
if (!value_in_range_of<std::size_t>(number))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message("integer value overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "integer value overflow", "size");
}
result = detail::conditional_static_cast<std::size_t>(number);
return true;
@@ -2814,7 +2764,7 @@ class binary_reader
}
if (is_ndarray) // ndarray dimensional vector can only contain integers and cannot embed another array
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read, exception_message("ndarray dimensional vector is not allowed", "size"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "ndarray dimensional vector is not allowed", "size");
}
std::vector<size_t> dim;
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_ndarray_size(dim)))
@@ -2850,9 +2800,7 @@ class binary_reader
const char* type_name = bjd_type_name(ndarray_dtype);
if (JSON_HEDLEY_UNLIKELY(type_name == nullptr))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("invalid byte: 0x" + last_token, "type"), nullptr));
return unexpected_byte("invalid byte", "type");
}
string_t type_key = "_ArrayType_";
@@ -2880,7 +2828,7 @@ class binary_reader
// or SIZE_MAX.
if (JSON_HEDLEY_UNLIKELY(result > (std::numeric_limits<std::size_t>::max)() / i))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message("excessive ndarray size caused overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "excessive ndarray size caused overflow", "size");
}
result *= i;
// the pre-check above already rules out result becoming 0
@@ -2889,7 +2837,7 @@ class binary_reader
// unknown-size container (see get_ubjson_size_type())
if (result == npos)
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message("excessive ndarray size caused overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "excessive ndarray size caused overflow", "size");
}
if (JSON_HEDLEY_UNLIKELY(!emit_unsigned(i)))
{
@@ -2906,18 +2854,7 @@ class binary_reader
default:
break;
}
auto last_token = get_token_string();
std::string message;
if (input_format != input_format_t::bjdata)
{
message = "expected length type specification (U, i, I, l, L) after '#'; last byte: 0x" + last_token;
}
else
{
message = "expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x" + last_token;
}
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(message, "size"), nullptr));
return length_type_error(" after '#'", "size");
}
/*!
@@ -2950,9 +2887,7 @@ class binary_reader
if (input_format == input_format_t::bjdata
&& JSON_HEDLEY_UNLIKELY(is_bjd_excluded_optimized_type(result.second)))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("marker 0x", last_token, " is not a permitted optimized array type"), "type"), nullptr));
return optimized_type_error();
}
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof("type")))
@@ -2967,9 +2902,7 @@ class binary_reader
{
return false;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("expected '#' after type information; last byte: 0x", last_token), "size"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "expected '#' after type information", "size", "");
}
const bool is_error = get_ubjson_size_value(result.first, is_ndarray, 0, result.second);
@@ -2988,8 +2921,7 @@ class binary_reader
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
exception_message("ndarray requires both type and size", "size"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "ndarray requires both type and size", "size");
}
return is_error;
}
@@ -3121,9 +3053,7 @@ class binary_reader
}
if (JSON_HEDLEY_UNLIKELY(current > 127))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("byte after 'C' must be in range 0x00..0x7F; last byte: 0x", last_token), "char"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "byte after 'C' must be in range 0x00..0x7F", "char", "");
}
string_t s(1, static_cast<typename string_t::value_type>(current));
return sax->string(s);
@@ -3144,8 +3074,7 @@ class binary_reader
default: // anything else
break;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read, exception_message("invalid byte: 0x" + last_token, "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
/*!
@@ -3208,8 +3137,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
&& size_and_type.first > max_valueless_container_size))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message("excessive array size", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "excessive array size", "size");
}
if (JSON_HEDLEY_UNLIKELY(!enter_array(size_and_type.first, size_and_type.second)))
@@ -3244,9 +3172,7 @@ class binary_reader
// do not accept ND-array size in objects in BJData
if (input_format == input_format_t::bjdata && size_and_type.first != npos && (size_and_type.second & (1 << 8)) != 0)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("BJData object does not support ND-array size in optimized format", "object"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "BJData object does not support ND-array size in optimized format", "object");
}
if (size_and_type.first != npos)
@@ -3283,7 +3209,7 @@ class binary_reader
// the lexer would stop at a NUL and accept the digits before it
if (JSON_HEDLEY_UNLIKELY(current == '\0'))
{
return sax->parse_error(chars_read, "00", parse_error::create(115, chars_read,
return sax->parse_error(chars_read, "00", parse_error::create(exception_id::invalid_high_precision_number, chars_read,
exception_message("invalid number text; last byte: 0x00", "high-precision number"), nullptr));
}
number_vector.push_back(static_cast<char>(current));
@@ -3300,7 +3226,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(result_remainder != token_type::end_of_input))
{
return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read,
return sax->parse_error(chars_read, number_string, parse_error::create(exception_id::invalid_high_precision_number, chars_read,
exception_message(concat("invalid number text: ", number_lexer.get_token_string()), "high-precision number"), nullptr));
}
@@ -3318,7 +3244,7 @@ class binary_reader
return sax->parse_error(
chars_read,
number_string,
out_of_range::create(406, concat("number overflow parsing '", number_string, '\''), nullptr));
out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", number_string, '\''), nullptr));
}
// number_string is a std::string, while the SAX interface takes a
// string_t; convert explicitly, as the two are only implicitly
@@ -3340,7 +3266,7 @@ class binary_reader
case token_type::end_of_input:
case token_type::literal_or_value:
default:
return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read,
return sax->parse_error(chars_read, number_string, parse_error::create(exception_id::invalid_high_precision_number, chars_read,
exception_message(concat("invalid number text: ", number_lexer.get_token_string()), "high-precision number"), nullptr));
}
}
@@ -3399,20 +3325,6 @@ class binary_reader
return 0x80 <= c && c <= 0xBF;
}
/*!
@brief report a parse error at the last read byte
@param[in] detail a detailed error message
@param[in] context further context information
@return false
*/
bool bon8_error(const std::string& detail, const char* context)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat(detail, ": 0x", last_token), context), nullptr));
}
/*!
@brief read a BON8 value and everything nested inside it
@@ -3628,7 +3540,7 @@ class binary_reader
}
// 0xFE: end of container where a value is expected
return bon8_error("invalid byte", "value");
return unexpected_byte("invalid byte", "value");
}
/*!
@@ -3755,7 +3667,7 @@ class binary_reader
current = byte;
}
return bon8_error("expected a string; last byte", "key");
return unexpected_byte("expected a string; last byte", "key");
}
/*!
@@ -3878,7 +3790,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(!valid_second))
{
return bon8_error("invalid UTF-8 byte", "string");
return unexpected_byte("invalid UTF-8 byte", "string");
}
result.push_back(static_cast<typename string_t::value_type>(byte));
@@ -3892,7 +3804,7 @@ class binary_reader
}
if (JSON_HEDLEY_UNLIKELY(!is_bon8_continuation(current)))
{
return bon8_error("invalid UTF-8 byte", "string");
return unexpected_byte("invalid UTF-8 byte", "string");
}
result.push_back(static_cast<typename string_t::value_type>(current));
}
@@ -3937,7 +3849,7 @@ class binary_reader
{
// in case of failure, advance position by 1 to report the failing location
++chars_read;
sax->parse_error(chars_read, "<end of file>", parse_error::create(110, chars_read, exception_message("unexpected end of input", context), nullptr));
static_cast<void>(report_eof(context));
return false;
}
return true;
@@ -4090,8 +4002,7 @@ class binary_reader
const auto result = static_cast<number_float_t>(number);
if (JSON_HEDLEY_UNLIKELY(std::isfinite(number) && !std::isfinite(result)))
{
return sax->parse_error(chars_read, get_token_string(),
out_of_range::create(406, exception_message("number overflow", "value"), nullptr));
return out_of_range_error(exception_id::number_overflow, "number overflow", "value");
}
return sax->number_float(result, "");
}
@@ -4211,9 +4122,7 @@ class binary_reader
if (error_handler == error_handler_t::strict)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message("invalid string: ill-formed UTF-8 byte", context), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "invalid string: ill-formed UTF-8 byte", context);
}
result = sanitize_utf8(result, error_handler);
@@ -4308,20 +4217,116 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(current == char_traits<char_type>::eof()))
{
return sax->parse_error(chars_read, "<end of file>",
parse_error::create(110, chars_read, exception_message("unexpected end of input", context), nullptr));
return report_eof(context);
}
return true;
}
/*!
@brief reports an unexpected end of input (out of line to keep the exception
construction out of the hot reading functions)
@param[in] context further context information (for diagnostics)
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NON_NULL(2)
JSON_HEDLEY_NEVER_INLINE
bool report_eof(const char* context) const
{
return sax->parse_error(chars_read, "<end of file>",
parse_error::create(exception_id::unexpected_end_of_input, chars_read, exception_message("unexpected end of input", context), nullptr));
}
/*!
@brief reports an out_of_range error at the last read byte (out of line)
*/
JSON_HEDLEY_NEVER_INLINE
bool out_of_range_error(const exception_id id_, const char* detail, const char* context) const
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(id_, exception_message(detail, context), nullptr));
}
JSON_HEDLEY_NEVER_INLINE
bool container_size_error(const char* what) const
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(exception_id::container_too_large,
exception_message(concat("excessive ", what, " size"), "size"), nullptr));
}
JSON_HEDLEY_NEVER_INLINE
bool optimized_type_error() const
{
return last_byte_error(exception_id::unexpected_byte, concat("marker 0x", get_token_string(), " is not a permitted optimized array type"), "type");
}
template<typename NumberType>
JSON_HEDLEY_NEVER_INLINE
bool bson_length_error(const char* prefix, const NumberType len, const char* context) const
{
return last_byte_error(exception_id::unexpected_byte, concat(prefix, std::to_string(len)), context);
}
JSON_HEDLEY_NEVER_INLINE
bool bson_document_size_error(const std::int32_t document_size, const std::size_t bytes_read) const
{
return last_byte_error(exception_id::unexpected_byte, concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(bytes_read), ")"), "document");
}
JSON_HEDLEY_NEVER_INLINE
bool bson_unsupported_type_error(const std::size_t position, const char_int_type element_type) const
{
const std::string cr_str = hex_byte(static_cast<std::uint8_t>(element_type));
return sax->parse_error(position, cr_str,
parse_error::create(exception_id::bson_unsupported_type, position, concat("Unsupported BSON record type 0x", cr_str), nullptr));
}
/*!
@brief reports a parse error at the last read byte
@param[in] id_ the id of the parse_error exception
@param[in] detail a detailed error message
@param[in] context further context information
@param[in] tail optional text appended to the detail, followed by "; last byte: 0x<token>"
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NEVER_INLINE
bool last_byte_error(const exception_id id_, const std::string& detail, const char* context, const char* tail = nullptr) const
{
// with a tail, the message reads "<detail><tail>; last byte: 0x<token>"
return sax->parse_error(chars_read, get_token_string(), parse_error::create(id_, chars_read,
exception_message(tail == nullptr ? detail : concat(detail, tail, "; last byte: 0x", get_token_string()), context), nullptr));
}
/*!
@brief reports the last read byte as unexpected (parse_error.112)
@param[in] detail what is wrong with the byte, e.g. "invalid byte"
@param[in] context further context information
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NEVER_INLINE
bool unexpected_byte(const char* detail, const char* context) const
{
return last_byte_error(exception_id::unexpected_byte, concat(detail, ": 0x", get_token_string()), context);
}
/*!
@brief reports that the last read byte is not a UBJSON/BJData length type (parse_error.113)
@param[in] position where the length type was expected, e.g. " after '#'"
@param[in] context further context information
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NEVER_INLINE
bool length_type_error(const char* position, const char* context) const
{
const char* types = input_format == input_format_t::bjdata ? "U, i, u, I, m, l, M, L" : "U, i, I, l, L";
return last_byte_error(exception_id::invalid_string_or_size,
concat("expected length type specification (", types, ")", position, "; last byte: 0x", get_token_string()), context);
}
/*!
@return a string representation of the last read byte
*/
std::string get_token_string() const
{
std::array<char, 3> cr{{}};
static_cast<void>((std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(current))); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
return std::string{cr.data()};
return hex_byte(static_cast<std::uint8_t>(current));
}
/*!
include/nlohmann/detail/input/input_adapters.hpp
+333 -17
View File
@@ -8,16 +8,18 @@
#pragma once
#include <algorithm> // min
#include <algorithm> // count, find, min
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint32_t
#include <cstring> // strlen
#include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next
#include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next, reverse_iterator
#include <limits> // numeric_limits
#include <streambuf> // streambuf
#include <string> // string, char_traits
#include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
#include <utility> // pair, declval
#include <vector> // vector
#ifndef JSON_NO_IO
#include <cstdio> // FILE *
@@ -30,6 +32,33 @@
#include <nlohmann/detail/meta/type_traits.hpp>
#include <nlohmann/detail/string_utils.hpp>
#ifndef JSON_NO_IO
// Which unlocked stdio functions file_input_adapter uses (see
// JSON_DISABLE_UNLOCKED_FILE_IO): 1 = POSIX flockfile/getc_unlocked,
// 2 = Microsoft CRT _lock_file/_fgetc_nolock, 0 = none (std::fgetc, which
// locks the file for every character). Only C libraries known to declare
// the functions are listed; the macros are tested after <cstdio>, which
// defines __GLIBC__. MemorySanitizer builds always use std::fgetc: glibc's
// inline getc_unlocked reads the stdio buffer directly, which glibc (not
// instrumented) filled, so MemorySanitizer would report a false positive.
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
#define JSON_UNLOCKED_FILE_IO_MSAN 1
#endif
#endif
#if JSON_DISABLE_UNLOCKED_FILE_IO || defined(JSON_UNLOCKED_FILE_IO_MSAN)
#define JSON_UNLOCKED_FILE_IO 0
#elif defined(_MSC_VER)
#define JSON_UNLOCKED_FILE_IO 2
#elif defined(__GLIBC__) || defined(__APPLE__) || defined(__ANDROID__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__)
#define JSON_UNLOCKED_FILE_IO 1
#else
#define JSON_UNLOCKED_FILE_IO 0
#endif
#undef JSON_UNLOCKED_FILE_IO_MSAN
#endif // JSON_NO_IO
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
@@ -56,18 +85,35 @@ class file_input_adapter
: m_file(f)
{
JSON_ASSERT(m_file != nullptr);
lock();
}
// make class move-only
file_input_adapter(const file_input_adapter&) = delete;
file_input_adapter(file_input_adapter&&) noexcept = default;
file_input_adapter(file_input_adapter&& rhs) noexcept
: m_file(rhs.m_file)
{
// the lock is owned by the thread, not the adapter: hand it over
rhs.m_file = nullptr;
}
file_input_adapter& operator=(const file_input_adapter&) = delete;
file_input_adapter& operator=(file_input_adapter&&) = delete;
~file_input_adapter() = default;
~file_input_adapter()
{
unlock();
}
std::char_traits<char>::int_type get_character() noexcept
{
// the file is locked for the lifetime of the adapter, so the
// per-character lock of std::fgetc can be skipped
#if JSON_UNLOCKED_FILE_IO == 1
return getc_unlocked(m_file);
#elif JSON_UNLOCKED_FILE_IO == 2
return _fgetc_nolock(m_file);
#else
return std::fgetc(m_file);
#endif
}
// returns the number of characters successfully read
@@ -78,6 +124,32 @@ class file_input_adapter
}
private:
// Lock the file once for the whole parse instead of once per character.
// The lock is recursive, so fread() and the user's own stdio calls on the
// same thread keep working.
void lock() noexcept
{
#if JSON_UNLOCKED_FILE_IO == 1
flockfile(m_file);
#elif JSON_UNLOCKED_FILE_IO == 2
_lock_file(m_file);
#endif
}
void unlock() noexcept
{
// a moved-from adapter has no file and holds no lock
if (m_file == nullptr)
{
return;
}
#if JSON_UNLOCKED_FILE_IO == 1
funlockfile(m_file);
#elif JSON_UNLOCKED_FILE_IO == 2
_unlock_file(m_file);
#endif
}
/// the file pointer to read from
std::FILE* m_file;
};
@@ -127,15 +199,26 @@ class input_stream_adapter
input_stream_adapter& operator=(input_stream_adapter&) = delete;
input_stream_adapter& operator=(input_stream_adapter&&) = delete;
#if JSON_PRECISE_STREAM_POSITION
input_stream_adapter(input_stream_adapter&& rhs) noexcept
: is(rhs.is), sb(rhs.sb), lookahead(rhs.lookahead)
: is(rhs.is), sb(rhs.sb)
#if JSON_PRECISE_STREAM_POSITION
, lookahead(rhs.lookahead)
#endif
#if !JSON_DISABLE_STREAM_BULK_SCAN
, token_carry(std::move(rhs.token_carry))
, token_segment(rhs.token_segment)
, current_in_get_area(rhs.current_in_get_area)
, tracking_token(rhs.tracking_token)
#endif
{
rhs.is = nullptr;
rhs.sb = nullptr;
#if JSON_PRECISE_STREAM_POSITION
rhs.lookahead = false;
#endif
}
#if JSON_PRECISE_STREAM_POSITION
// Whether the character last returned by get_character() can be given back
// to the input with release_lookahead().
static constexpr bool supports_lookahead = true;
@@ -155,17 +238,41 @@ class input_stream_adapter
sb->sbumpc();
}
#if !JSON_DISABLE_STREAM_BULK_SCAN
// sgetc() refills the get area if it is exhausted
const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
if (JSON_HEDLEY_UNLIKELY(refill))
{
save_token_segment();
}
#endif
auto res = sb->sgetc();
// set eof manually, as we don't use the istream interface.
if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
{
// there is nothing to step over next time
lookahead = false;
#if !JSON_DISABLE_STREAM_BULK_SCAN
current_in_get_area = false;
#endif
is->clear(is->rdstate() | std::ios::eofbit);
}
else
{
lookahead = true;
#if !JSON_DISABLE_STREAM_BULK_SCAN
if (JSON_HEDLEY_UNLIKELY(refill))
{
// the peeked character is at gptr(), unless the streambuf has
// no get area
after_refill(res, streambuf_access::get_ptr(sb) != streambuf_access::get_end(sb));
}
else
{
current_in_get_area = true;
}
#endif
}
return res;
}
@@ -179,13 +286,6 @@ class input_stream_adapter
lookahead = false;
}
#else
input_stream_adapter(input_stream_adapter&& rhs) noexcept
: is(rhs.is), sb(rhs.sb)
{
rhs.is = nullptr;
rhs.sb = nullptr;
}
// std::istream/std::streambuf use std::char_traits<char>::to_int_type, to
// ensure that std::char_traits<char>::eof() and the character 0xFF do not
// end up as the same value, e.g., 0xFFFFFFFF.
@@ -194,12 +294,37 @@ class input_stream_adapter
// stays consumed after parsing; see JSON_PRECISE_STREAM_POSITION.
std::char_traits<char>::int_type get_character()
{
#if !JSON_DISABLE_STREAM_BULK_SCAN
// sbumpc() refills the get area if it is exhausted
const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
if (JSON_HEDLEY_UNLIKELY(refill))
{
save_token_segment();
}
#endif
auto res = sb->sbumpc();
// set eof manually, as we don't use the istream interface.
if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
{
#if !JSON_DISABLE_STREAM_BULK_SCAN
current_in_get_area = false;
#endif
is->clear(is->rdstate() | std::ios::eofbit);
}
#if !JSON_DISABLE_STREAM_BULK_SCAN
else if (JSON_HEDLEY_UNLIKELY(refill))
{
// the consumed character is at gptr() - 1, unless the streambuf
// has no get area and returned it from uflow()
const char* const next = streambuf_access::get_ptr(sb);
after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
}
else
{
current_in_get_area = true;
}
#endif
return res;
}
#endif
@@ -218,7 +343,165 @@ class input_stream_adapter
return res;
}
#if !JSON_DISABLE_STREAM_BULK_SCAN
// The lexer may scan the characters in the get area of the streambuf
// directly (SWAR fast paths). The get area is only a window into the
// input: it ends wherever the streambuf's buffer ends, and is refilled by
// the next get_character(). The lexer therefore keeps counting the
// position itself and treats the end of the window as "unknown", not as
// the end of the input.
static constexpr bool supports_bulk_scan = true;
static constexpr bool bulk_window = true;
// Pointer to the next unread character; only valid when
// bulk_remaining() > 0. The character before it is the one last returned
// by get_character().
const char* bulk_data() const
{
return current_end();
}
// Number of unread characters in the get area.
std::size_t bulk_remaining() const
{
if (!current_in_get_area)
{
return 0;
}
return static_cast<std::size_t>(streambuf_access::get_end(sb) - current_end());
}
// Consume @a n characters previously inspected via bulk_data(); the last
// of them becomes the character last returned by get_character().
void bulk_skip(std::size_t n)
{
JSON_ASSERT(n <= bulk_remaining());
// gbump() takes an int, but a get area (e.g., of a std::stringbuf) can
// be larger
constexpr auto max_bump = static_cast<std::size_t>((std::numeric_limits<int>::max)());
for (; n > max_bump; n -= max_bump)
{
streambuf_access::bump(sb, static_cast<int>(max_bump));
}
streambuf_access::bump(sb, static_cast<int>(n));
}
// The adapter keeps the current token for the lexer's error messages: the
// part in the get area is only remembered as a pointer, and copied out
// when the get area is about to be refilled.
static constexpr bool supports_token_tracking = true;
// Start a token with the characters read from now on. Until this is
// called, nothing is tracked (the binary readers never call it).
void begin_token() noexcept
{
tracking_token = true;
token_carry.clear();
token_segment = current_end();
}
// Start a new token with the character @a c last returned by
// get_character().
void mark_token_start(std::char_traits<char>::int_type c)
{
tracking_token = true;
token_carry.clear();
if (current_in_get_area)
{
token_segment = current_end() - 1;
}
else
{
token_segment = nullptr;
token_carry.push_back(std::char_traits<char>::to_char_type(c));
}
}
// Copy the characters read since mark_token_start() to @a out, without the
// last one if @a drop_last.
void copy_token(std::vector<char>& out, bool drop_last) const
{
out = token_carry;
if (token_segment != nullptr)
{
out.insert(out.end(), token_segment, current_end());
}
if (drop_last && !out.empty())
{
out.pop_back();
}
}
#endif
private:
#if !JSON_DISABLE_STREAM_BULK_SCAN
// Reads the protected get-area pointers of any std::streambuf. Naming the
// members through a derived class makes forming the member pointers
// accessible; calling them on another streambuf object is then ordinary
// member access through a pointer to member.
struct streambuf_access : std::streambuf
{
static const char* get_ptr(std::streambuf* s)
{
return (s->*(&streambuf_access::gptr))();
}
static const char* get_end(std::streambuf* s)
{
return (s->*(&streambuf_access::egptr))();
}
static const char* get_begin(std::streambuf* s)
{
return (s->*(&streambuf_access::eback))();
}
static void bump(std::streambuf* s, int n)
{
(s->*(&streambuf_access::gbump))(n);
}
};
// one past the character last returned by get_character(), if that is in
// the get area
const char* current_end() const
{
#if JSON_PRECISE_STREAM_POSITION
// the character is peeked at gptr() and not stepped over yet, unless
// it was given back with release_lookahead()
return streambuf_access::get_ptr(sb) + (lookahead ? 1 : 0);
#else
return streambuf_access::get_ptr(sb);
#endif
}
// the get area is about to be replaced: copy the token's part in it
void save_token_segment()
{
if (token_segment != nullptr)
{
token_carry.insert(token_carry.end(), token_segment, streambuf_access::get_end(sb));
token_segment = nullptr;
}
}
// character @a c was just read into a new get area (@a in_get_area) or
// returned without one
void after_refill(std::char_traits<char>::int_type c, bool in_get_area)
{
current_in_get_area = in_get_area;
if (!tracking_token)
{
return;
}
if (in_get_area)
{
token_segment = current_end() - 1;
}
else
{
token_carry.push_back(std::char_traits<char>::to_char_type(c));
}
}
#endif
#if JSON_PRECISE_STREAM_POSITION
// Step over the character last returned by get_character(). The character
// has already been peeked successfully, so for every streambuf with a get
@@ -240,6 +523,16 @@ class input_stream_adapter
/// whether get_character() peeked a character that is not consumed yet
bool lookahead = false;
#endif
#if !JSON_DISABLE_STREAM_BULK_SCAN
/// the part of the current token that was in earlier get areas
std::vector<char> token_carry{}; // NOLINT(readability-redundant-member-init)
/// start of the current token's part in the get area, or nullptr
const char* token_segment = nullptr;
/// whether the character last returned by get_character() is in the get area
bool current_in_get_area = false;
/// whether a token is tracked at all; the binary readers never start one
bool tracking_token = false;
#endif
};
#endif // JSON_NO_IO
@@ -297,6 +590,7 @@ class iterator_input_adapter
return result;
}
++eof_reads;
return char_traits<char_type>::eof();
}
@@ -306,6 +600,26 @@ class iterator_input_adapter
return static_cast<std::size_t>(std::distance(begin, current));
}
// number of get_character() calls so far, including those that returned
// EOF; the lexer derives its position from it (see lexer::lazy_position)
std::size_t get_read_count() const
{
return get_consumed_count() + eof_reads;
}
// number of newlines in the consumed range [0, last_index); @a line_start
// is set to the index after the last of them (0 if there is none); only
// valid when supports_seek
std::size_t count_consumed_lines(std::size_t last_index, std::size_t& line_start) const
{
const auto to = std::next(begin, static_cast<typename std::iterator_traits<IteratorType>::difference_type>(last_index));
const auto newline = char_traits<char_type>::to_char_type('\n');
using reverse_it = std::reverse_iterator<IteratorType>;
const auto last_newline = std::find(reverse_it(to), reverse_it(begin), newline);
line_start = static_cast<std::size_t>(std::distance(begin, last_newline.base()));
return static_cast<std::size_t>(std::count(begin, last_newline.base(), newline));
}
// append the already-consumed characters in the half-open range
// [first_index, last_index) to @a out; only valid when supports_seek
template<typename ContainerType>
@@ -422,6 +736,8 @@ class iterator_input_adapter
IteratorType begin;
IteratorType current;
SentinelType end;
/// number of get_character() calls that returned EOF
std::size_t eof_reads = 0;
template<typename BaseInputAdapter, size_t T>
friend struct wide_string_input_helper;
@@ -581,7 +897,7 @@ class wide_string_input_adapter
template<class T>
JSON_HEDLEY_NO_RETURN std::size_t get_elements(T* /*dest*/, std::size_t /*count*/ = 1)
{
JSON_THROW(parse_error::create(112, 1, "wide string type cannot be interpreted as binary data", nullptr));
JSON_THROW(parse_error::create(exception_id::unexpected_byte, 1, "wide string type cannot be interpreted as binary data", nullptr));
}
private:
@@ -793,7 +1109,7 @@ inline file_input_adapter input_adapter(std::FILE* file)
{
if (file == nullptr)
{
JSON_THROW(parse_error::create(101, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
}
return file_input_adapter(file);
}
@@ -802,7 +1118,7 @@ inline input_stream_adapter input_adapter(std::istream& stream)
{
if (stream.rdbuf() == nullptr)
{
JSON_THROW(parse_error::create(101, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
}
return input_stream_adapter(stream);
}
@@ -827,7 +1143,7 @@ contiguous_bytes_input_adapter input_adapter(CharT b)
{
if (b == nullptr)
{
JSON_THROW(parse_error::create(101, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
}
auto length = std::strlen(reinterpret_cast<const char*>(b));
const auto* ptr = reinterpret_cast<const char*>(b);
include/nlohmann/detail/input/json_sax.hpp
+97 -80
View File
@@ -200,6 +200,34 @@ template<typename ArrayType>
inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
{}
/*!
@brief reports an object or array whose announced size exceeds max_size()
Shared by json_sax_dom_parser and json_sax_dom_callback_parser.
@param[in] sax the SAX parser to report the error to
@param[in] len the number of elements announced by the input, or unknown_size()
@param[in] kind "object" or "array"
@param[in] ref the object or array that was just created
@return whether parsing should continue (false after reporting out_of_range.408)
*/
template<typename SAX, typename BasicJsonType>
JSON_HEDLEY_NEVER_INLINE
bool container_too_large_error(SAX& sax, std::size_t len, const char* kind, BasicJsonType* ref)
{
return sax.parse_error(0, "", out_of_range::create(exception_id::container_too_large, concat("excessive ", kind, " size: ", std::to_string(len)), ref));
}
template<typename SAX, typename BasicJsonType>
bool check_container_size(SAX& sax, std::size_t len, const char* kind, BasicJsonType* ref)
{
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref->max_size()))
{
return container_too_large_error(sax, len, kind, ref);
}
return true;
}
#if JSON_DIAGNOSTIC_POSITIONS
/*!
@brief set the diagnostic positions of a value the DOM SAX parsers just stored
@@ -209,6 +237,35 @@ befriends this struct, as the position members are private.
*/
struct diagnostic_positions
{
/*!
@param[in,out] v the object or array whose opening brace or bracket was just read
@param[in] lexer the lexer that read it, or nullptr to leave @a v alone
*/
template<typename BasicJsonType, typename LexerType>
static void set_container_start(BasicJsonType& v, LexerType* lexer)
{
if (lexer)
{
// Lexer has read the first character of the container, so
// subtract 1 from the position to get the correct start position.
v.start_position = lexer->get_chars_read_total() - 1;
}
}
/*!
@param[in,out] v the object or array whose closing brace or bracket was just read
@param[in] lexer the lexer that read it, or nullptr to leave @a v alone
*/
template<typename BasicJsonType, typename LexerType>
static void set_container_end(BasicJsonType& v, LexerType* lexer)
{
if (lexer)
{
// Lexer's position is past the closing brace or bracket, so set that as the end position.
v.end_position = lexer->get_chars_read_total();
}
}
/*!
@param[in,out] v the value that was just parsed
@param[in] lexer the lexer that read it, or nullptr to leave @a v alone
@@ -221,7 +278,7 @@ struct diagnostic_positions
// Lexer has read past the current field value, so set the end position to the current position.
// The start position will be set below based on the length of the string representation
// of the value.
v.end_position = lexer->get_position();
v.end_position = lexer->get_chars_read_total();
switch (v.type())
{
@@ -373,22 +430,11 @@ class json_sax_dom_parser
ref_stack.push_back(handle_value(BasicJsonType::value_t::object));
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the object here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
// Lexer has read the first character of the object, so
// subtract 1 from the position to get the correct start position.
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
}
return true;
return check_container_size(*this, len, "object", ref_stack.back());
}
bool key(string_t& val)
@@ -407,11 +453,7 @@ class json_sax_dom_parser
JSON_ASSERT(ref_stack.back()->is_object());
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing brace, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -424,17 +466,13 @@ class json_sax_dom_parser
ref_stack.push_back(handle_value(BasicJsonType::value_t::array));
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the array here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
if (JSON_HEDLEY_UNLIKELY(!check_container_size(*this, len, "array", ref_stack.back())))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
return false;
}
if (len != detail::unknown_size())
@@ -451,11 +489,7 @@ class json_sax_dom_parser
JSON_ASSERT(ref_stack.back()->is_array());
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing bracket, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -635,21 +669,11 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the object here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
// Lexer has read the first character of the object, so
// subtract 1 from the position to get the correct start position.
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
// check object limit
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
}
return check_container_size(*this, len, "object", ref_stack.back());
}
return true;
}
@@ -681,16 +705,19 @@ class json_sax_dom_callback_parser
if (keep && ref_stack.back())
{
auto& obj = *ref_stack.back()->m_data.m_value.object;
const auto it = obj.find(val);
if (it != obj.end())
// a single lookup: insert the placeholder, or find the existing member
const auto inserted = obj.emplace(val, discarded);
const auto it = inserted.first;
if (!inserted.second)
{
// this is a duplicate key (legal in JSON); remember its
// current value so it can be restored later if the new
// value is rejected by the callback, instead of being
// erased together with the discarded placeholder
duplicate_key_stash.emplace_back(&(it->second), it->second);
it->second = discarded;
}
object_element = &(obj[val] = discarded);
object_element = &(it->second);
}
return true;
@@ -719,11 +746,7 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing brace, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -734,13 +757,7 @@ class json_sax_dom_callback_parser
}
}
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(!keep_stack.empty());
JSON_ASSERT(!container_key_stack.empty());
ref_stack.pop_back();
keep_stack.pop_back();
const string_t object_key = std::move(container_key_stack.back());
container_key_stack.pop_back();
const string_t object_key = pop_container();
if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_structured())
{
@@ -766,20 +783,13 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the array here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
// Lexer has read the first character of the array, so
// subtract 1 from the position to get the correct start position.
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
// check array limit
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
if (JSON_HEDLEY_UNLIKELY(!check_container_size(*this, len, "array", ref_stack.back())))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
return false;
}
if (len != detail::unknown_size())
@@ -803,11 +813,7 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing bracket, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -833,13 +839,7 @@ class json_sax_dom_callback_parser
}
}
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(!keep_stack.empty());
JSON_ASSERT(!container_key_stack.empty());
ref_stack.pop_back();
keep_stack.pop_back();
const string_t object_key = std::move(container_key_stack.back());
container_key_stack.pop_back();
const string_t object_key = pop_container();
// remove discarded value
if (!ref_stack.empty() && ref_stack.back())
@@ -926,6 +926,23 @@ class json_sax_dom_callback_parser
return string_t{};
}
/*!
@brief leave the object or array that end_object()/end_array() just closed
@return the key the container is stored under in its parent (see
container_key_stack)
*/
string_t pop_container()
{
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(!keep_stack.empty());
JSON_ASSERT(!container_key_stack.empty());
ref_stack.pop_back();
keep_stack.pop_back();
string_t object_key = std::move(container_key_stack.back());
container_key_stack.pop_back();
return object_key;
}
/*!
@brief remove the discarded value the callback rejected from its parent,
unless it is a duplicate key's slot with a stashed previous value, in
include/nlohmann/detail/input/lexer.hpp
+351 -40
View File
@@ -17,6 +17,7 @@
#include <utility> // move
#include <vector> // vector
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/input/input_adapters.hpp>
#include <nlohmann/detail/input/number_parse.hpp>
#include <nlohmann/detail/input/position_t.hpp>
@@ -165,6 +166,43 @@ constexpr bool input_adapter_supports_bulk_scan(std::false_type /*detected*/)
return false;
}
// Detect whether an input adapter keeps the current token itself and can
// hand it out on demand (see input_stream_adapter::supports_token_tracking),
// so the lexer need not copy every scanned character into token_string.
template<typename InputAdapterType>
using detect_supports_token_tracking = decltype(InputAdapterType::supports_token_tracking);
template<typename InputAdapterType>
constexpr bool input_adapter_supports_token_tracking(std::true_type /*detected*/)
{
return InputAdapterType::supports_token_tracking;
}
template<typename InputAdapterType>
constexpr bool input_adapter_supports_token_tracking(std::false_type /*detected*/)
{
return false;
}
// Detect whether the contiguous block of a bulk-scan adapter is only a window
// into the input (see input_stream_adapter::bulk_window): its end is not the
// end of the input, so a token that touches it must be finished character by
// character.
template<typename InputAdapterType>
using detect_bulk_window = decltype(InputAdapterType::bulk_window);
template<typename InputAdapterType>
constexpr bool input_adapter_bulk_window(std::true_type /*detected*/)
{
return InputAdapterType::bulk_window;
}
template<typename InputAdapterType>
constexpr bool input_adapter_bulk_window(std::false_type /*detected*/)
{
return false;
}
/*!
@brief lexical analysis
@@ -183,9 +221,29 @@ class lexer : public lexer_base<BasicJsonType>
/// whether the last read token can be reconstructed from the input adapter
/// on demand (in error paths) instead of being copied on every scanned
/// character; see input_adapter_supports_seek
static constexpr bool lazy_token_string =
static constexpr bool seekable =
input_adapter_supports_seek<InputAdapterType>(is_detected<detect_supports_seek, InputAdapterType> {});
/// whether the adapter keeps the token itself (mark_token_start() /
/// copy_token()); see input_adapter_supports_token_tracking
static constexpr bool adapter_token =
!seekable && input_adapter_supports_token_tracking<InputAdapterType>(is_detected<detect_supports_token_tracking, InputAdapterType> {});
/// whether the last read token is obtained from the input adapter on
/// demand (in error paths) instead of being copied on every scanned
/// character: seekable adapters reconstruct it from the consumed input,
/// token-tracking adapters keep it themselves
static constexpr bool lazy_token_string = seekable || adapter_token;
/// whether the read position is derived from the input adapter on demand
/// instead of being counted on every scanned character. Seekable adapters
/// know how much input they consumed and can revisit it, so
/// chars_read_total is the adapter's read count (minus a pending unget),
/// and line and column are recomputed from the consumed input only when
/// get_position() is called (errors). Counting per character kept two
/// increments and a newline check in the hot path of every get().
static constexpr bool lazy_position = seekable;
/// whether a simulated unget can be passed on to the input adapter, which
/// then leaves the character in the input; see
/// input_adapter_supports_lookahead
@@ -193,12 +251,17 @@ class lexer : public lexer_base<BasicJsonType>
input_adapter_supports_lookahead<InputAdapterType>(is_detected<detect_supports_lookahead, InputAdapterType> {});
/// whether string scanning may bulk-consume runs of ordinary characters
/// directly from a contiguous input buffer (SWAR fast path). This requires
/// the token to be reconstructible lazily (lazy_token_string), so bypassing
/// the per-character capture in get() cannot lose error diagnostics.
/// directly from a contiguous input buffer (SWAR fast path). Without
/// lazy_token_string / lazy_position, the bulk paths copy the consumed
/// characters into token_string and advance the position counters
/// themselves (see bulk_consume).
static constexpr bool bulk_scan =
lazy_token_string
&& input_adapter_supports_bulk_scan<InputAdapterType>(is_detected<detect_supports_bulk_scan, InputAdapterType> {});
input_adapter_supports_bulk_scan<InputAdapterType>(is_detected<detect_supports_bulk_scan, InputAdapterType> {});
/// whether the contiguous block is only a window into the input, so that
/// its end does not end a token; see input_adapter_bulk_window
static constexpr bool bulk_window =
input_adapter_bulk_window<InputAdapterType>(is_detected<detect_bulk_window, InputAdapterType> {});
public:
using token_type = typename lexer_base<BasicJsonType>::token_type;
@@ -207,7 +270,11 @@ class lexer : public lexer_base<BasicJsonType>
: ia(std::move(adapter))
, ignore_comments(ignore_comments_)
, discard_number_values(discard_number_values_)
{}
{
// the token string of an error before the first token is everything
// read so far
begin_token(std::integral_constant<bool, adapter_token> {});
}
// deleted because of pointer members
lexer(const lexer&) = delete;
@@ -221,6 +288,41 @@ class lexer : public lexer_base<BasicJsonType>
// scan functions
/////////////////////
/// contiguous input: try to decode the 4 hex digits following `\\u`
/// directly from the input buffer via hex_codepoint(), instead of 4 calls
/// to get(). On success, advances the adapter exactly as those 4 get()
/// calls would (including the position and token bookkeeping of a
/// streaming adapter, see bulk_consume) and leaves @a current holding the last of
/// the 4 digits, just as the last such get() would; the codepoint is
/// written to @a out. Makes no state change and returns false for a
/// pending unget, fewer than 4 remaining bytes, or any of the 4 bytes not
/// being a hex digit, so the caller falls back unchanged to the
/// per-character loop, which then reports the same diagnostic (stopping
/// at the first invalid digit) as before this optimization.
bool get_codepoint_bulk(std::true_type /*bulk*/, int& out)
{
if (next_unget || ia.bulk_remaining() < 4)
{
return false;
}
const char_type* const raw = ia.bulk_data();
const int codepoint = hex_codepoint(reinterpret_cast<const unsigned char*>(raw));
if (codepoint < 0)
{
return false;
}
bulk_consume(reinterpret_cast<const char*>(raw), 4);
current = char_traits<char_type>::to_int_type(raw[3]);
out = codepoint;
return true;
}
/// streaming input: no bulk fast path
bool get_codepoint_bulk(std::false_type /*bulk*/, int& /*out*/) const noexcept
{
return false;
}
/*!
@brief get codepoint from 4 hex characters following `\\u`
@@ -240,6 +342,14 @@ class lexer : public lexer_base<BasicJsonType>
{
// this function only makes sense after reading `\u`
JSON_ASSERT(current == 'u');
// contiguous input: decode all 4 hex digits directly from the buffer
int fast_codepoint = 0;
if (get_codepoint_bulk(std::integral_constant<bool, bulk_scan> {}, fast_codepoint))
{
return fast_codepoint;
}
int codepoint = 0;
const auto factors = { 12u, 8u, 4u, 0u };
@@ -330,11 +440,36 @@ class lexer : public lexer_base<BasicJsonType>
return;
}
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
ia.bulk_skip(pos);
// the run contains no newline (all bytes < 0x20 are treated as special),
// so only the flat character counters advance
position.chars_read_total += pos;
position.chars_read_current_line += pos;
bulk_consume(reinterpret_cast<const char*>(data), pos);
}
/// consume @a n characters at @a data (the adapter's bulk_data()) and do
/// the bookkeeping get() would have done for them; the characters are
/// never newlines
void bulk_consume(const char* data, std::size_t n)
{
bulk_track_position(n, std::integral_constant<bool, lazy_position> {});
bulk_track_token(data, n, std::integral_constant<bool, lazy_token_string> {});
ia.bulk_skip(n);
}
/// seekable adapter: the position is derived from the adapter
void bulk_track_position(std::size_t /*n*/, std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: count the characters
void bulk_track_position(std::size_t n, std::false_type /*lazy*/) noexcept
{
position.chars_read_total += n;
position.chars_read_current_line += n;
}
/// the token is obtained from the adapter
void bulk_track_token(const char* /*data*/, std::size_t /*n*/, std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: capture the characters
void bulk_track_token(const char* data, std::size_t n, std::false_type /*lazy*/)
{
token_string.insert(token_string.end(), data, data + n);
}
/// streaming input: no bulk fast path
@@ -1044,9 +1179,11 @@ class lexer : public lexer_base<BasicJsonType>
token_type::parse_error otherwise
@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 detail::convert_float_locale_aware()).
always holds `.`. The conversion of float and double does not use
the locale either. Only the std::strtold fallback of
convert_number() for long double formats other than binary64
depends on it, and it looks up the decimal point right before
converting (see detail::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.
{
@@ -1059,7 +1196,7 @@ class lexer : public lexer_base<BasicJsonType>
// offset just past the last mantissa byte in token_buffer (i.e. the
// index of 'e'/'E', or the whole token when there is no exponent).
// convert_number() uses it to count significant digits; npos means
// convert_number() uses it to split the token; npos means
// "not seen an exponent yet" and is resolved at scan_number_done
std::size_t mantissa_end = std::string::npos;
@@ -1389,8 +1526,8 @@ scan_number_done:
@param[in] mantissa_end offset just past the last mantissa byte in
token_buffer (the index of 'e'/'E', or
token_buffer.size() when there is no exponent);
used to skip Clinger's fast path when it cannot
possibly succeed - see detail::mantissa_fits_clinger()
with decimal_point_position, it locates the parts
of a float token without scanning it again
*/
token_type convert_number(token_type number_type, std::size_t mantissa_end)
{
@@ -1444,10 +1581,11 @@ scan_number_done:
}
// this code is reached if we parse a floating-point number or if an
// 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/strtold.
// integer conversion above overflowed. float and double (and long
// double where it is binary64) are converted by the library itself,
// correctly rounded and independent of the locale; other long double
// formats use std::from_chars when available, otherwise the
// locale-aware strtold.
if (convert_float_fast(num_begin, num_end, decimal_point_position, mantissa_end, value_float))
{
return token_type::value_float;
@@ -1549,6 +1687,10 @@ scan_number_done:
}
}
const std::size_t len = i;
if (number_may_continue(len == avail, std::integral_constant<bool, bulk_window> {}))
{
return token_type::uninitialized;
}
// reset() records where this token starts (for diagnostics), so it has
// to run before the input position advances below
@@ -1566,9 +1708,8 @@ scan_number_done:
const token_type integer_result = convert_integer(number_type, data, data + len);
if (JSON_HEDLEY_LIKELY(integer_result != token_type::uninitialized))
{
ia.bulk_skip(len - 1);
position.chars_read_total += (len - 1);
position.chars_read_current_line += (len - 1);
bulk_consume(data + 1, len - 1);
read_number_terminator(std::integral_constant<bool, bulk_window> {});
return integer_result;
}
// The value does not fit an integer, so this token converts as a
@@ -1584,13 +1725,37 @@ scan_number_done:
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
decimal_point_position = dot_index;
ia.bulk_skip(len - 1);
position.chars_read_total += (len - 1);
position.chars_read_current_line += (len - 1);
bulk_consume(data + 1, len - 1);
read_number_terminator(std::integral_constant<bool, bulk_window> {});
return convert_number(number_type, mantissa_end);
}
/// window adapter: a number that reaches the end of the window may continue
/// after it, so scan_number() has to read it character by character
static constexpr bool number_may_continue(bool at_end, std::true_type /*window*/) noexcept
{
return at_end;
}
/// the end of the block is the end of the input, which ends the number
static constexpr bool number_may_continue(bool /*at_end*/, std::false_type /*window*/) noexcept
{
return false;
}
/// window adapter: read the character after a bulk-scanned number and unget
/// it, as scan_number() does. The adapter is a stream that is handed back to
/// the user, who must find the same input consumed either way.
void read_number_terminator(std::true_type /*window*/)
{
get();
unget();
}
/// the input is not handed back, so the terminator can stay unread
void read_number_terminator(std::false_type /*window*/) const noexcept {}
/// contiguous input: try the number fast path, else the byte-path scanner
token_type scan_number_dispatch(std::true_type /*bulk*/)
{
@@ -1637,7 +1802,7 @@ scan_number_done:
#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;
token_start_position = get_chars_read_total() - 1;
#endif
note_token_start(std::integral_constant<bool, lazy_token_string> {});
@@ -1646,11 +1811,30 @@ scan_number_done:
/// seekable adapter: remember where the current token starts so it can be
/// reconstructed from the input on error; current has already been
/// consumed, hence the -1
void note_token_start(std::true_type /*lazy*/) noexcept
void note_token_start(std::true_type /*lazy*/)
{
note_token_start_lazy(std::integral_constant<bool, adapter_token> {});
}
void note_token_start_lazy(std::false_type /*adapter_token*/) noexcept
{
token_string_start = ia.get_consumed_count() - 1;
}
/// token-tracking adapter: start tracking the token at the first character
void begin_token(std::true_type /*adapter_token*/) noexcept
{
ia.begin_token();
}
void begin_token(std::false_type /*adapter_token*/) const noexcept {}
/// token-tracking adapter: the token starts with the current character
void note_token_start_lazy(std::true_type /*adapter_token*/)
{
ia.mark_token_start(current);
}
/// streaming adapter: start copying the token eagerly, beginning with the
/// already-read first character
void note_token_start(std::false_type /*lazy*/) noexcept
@@ -1690,6 +1874,15 @@ scan_number_done:
/// per-character position counters (line-count-on-'\n' bookkeeping is
/// handled afterwards, in track_after_read(), once `current` is known)
void advance_position() noexcept
{
advance_position_impl(std::integral_constant<bool, lazy_position> {});
}
/// seekable adapter: the position is derived from the adapter on demand
void advance_position_impl(std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: count the character
void advance_position_impl(std::false_type /*lazy*/) noexcept
{
++position.chars_read_total;
++position.chars_read_current_line;
@@ -1703,7 +1896,16 @@ scan_number_done:
// seekable adapters reconstruct the token lazily on error (see
// get_token_string), so the eager per-character copy is skipped
capture_char(std::integral_constant<bool, lazy_token_string> {});
track_newline(std::integral_constant<bool, lazy_position> {});
return current;
}
/// seekable adapter: lines are counted on demand in get_position()
void track_newline(std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: start a new line after reading a newline
void track_newline(std::false_type /*lazy*/) noexcept
{
if (current == '\n')
{
++position.lines_read;
@@ -1712,8 +1914,6 @@ scan_number_done:
chars_read_before_newline = position.chars_read_current_line;
position.chars_read_current_line = 0;
}
return current;
}
/*!
@@ -1757,12 +1957,22 @@ scan_number_done:
We implement unget by setting variable next_unget to true. The input is not
changed - we just simulate ungetting by modifying chars_read_total,
chars_read_current_line, and token_string. The next call to get() will
behave as if the unget character is read again.
behave as if the unget character is read again. With lazy_position, the
pending next_unget is all get_chars_read_total() needs.
*/
void unget()
{
next_unget = true;
unget_position(std::integral_constant<bool, lazy_position> {});
uncapture_char(std::integral_constant<bool, lazy_token_string> {});
}
/// seekable adapter: get_chars_read_total() accounts for next_unget
void unget_position(std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: step the counters back over the ungotten character
void unget_position(std::false_type /*lazy*/) noexcept
{
--position.chars_read_total;
// in case we "unget" a newline, we have to also decrement the lines_read
@@ -1785,8 +1995,6 @@ scan_number_done:
{
--position.chars_read_current_line;
}
uncapture_char(std::integral_constant<bool, lazy_token_string> {});
}
/// adapter without lookahead: nothing to do (see release_lookahead)
@@ -1857,10 +2065,21 @@ scan_number_done:
// diagnostics
/////////////////////
/// return position of last read token
constexpr position_t get_position() const noexcept
/*!
@brief return the number of characters read so far
Unlike get_position(), this is O(1) for all adapters, so it may be called
for every value (JSON_DIAGNOSTIC_POSITIONS).
*/
std::size_t get_chars_read_total() const noexcept
{
return position;
return get_chars_read_total_impl(std::integral_constant<bool, lazy_position> {});
}
/// return position of last read token
position_t get_position() const
{
return get_position_impl(std::integral_constant<bool, lazy_position> {});
}
/*!
@@ -1897,8 +2116,59 @@ scan_number_done:
}
#endif
private:
/// seekable adapter: every get() either read from the adapter (including
/// reads at EOF, which get() counts as characters as well) or replayed an
/// ungotten character, so the count is the adapter's read count minus a
/// still pending unget
std::size_t get_chars_read_total_impl(std::true_type /*lazy*/) const noexcept
{
return ia.get_read_count() - (next_unget ? 1u : 0u);
}
/// streaming adapter: the counter is maintained by get() and unget()
std::size_t get_chars_read_total_impl(std::false_type /*lazy*/) const noexcept
{
return position.chars_read_total;
}
/// seekable adapter: count the lines in the consumed input; O(input read
/// so far), but only called on errors
position_t get_position_impl(std::true_type /*lazy*/) const
{
position_t result;
result.chars_read_total = get_chars_read_total();
// reads at EOF count as characters but are not part of the input
const std::size_t consumed = (std::min)(result.chars_read_total, ia.get_consumed_count());
std::size_t line_start = 0;
result.lines_read = ia.count_consumed_lines(consumed, line_start);
result.chars_read_current_line = result.chars_read_total - line_start;
return result;
}
/// streaming adapter: the position is maintained by get() and unget()
position_t get_position_impl(std::false_type /*lazy*/) const noexcept
{
return position;
}
public:
/// 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
{
return collect_token_chars_lazy(out, std::integral_constant<bool, adapter_token> {});
}
/// token-tracking adapter: the adapter hands out everything read since
/// mark_token_start(), except a pending unget (see below)
const std::vector<char_type>& collect_token_chars_lazy(std::vector<char_type>& out, std::true_type /*adapter_token*/) const
{
const bool pending_real_unget = next_unget && current != char_traits<char_type>::eof();
ia.copy_token(out, pending_real_unget);
return out;
}
const std::vector<char_type>& collect_token_chars_lazy(std::vector<char_type>& out, std::false_type /*adapter_token*/) const
{
// a pending unget of a real (non-EOF) character means that character
// was consumed from the input but is not part of the token; EOF is
@@ -2004,15 +2274,56 @@ scan_number_done:
// into one that reloads the pointer from memory every character
do
{
if (current == '\n')
{
skip_indentation(std::integral_constant<bool, bulk_scan> {});
}
get_ignoring_pending_unget();
}
while (current_is_whitespace());
}
/*!
@brief contiguous input: skip the space indentation that follows a newline
8 bytes at a time
Pretty-printed JSON indents every line with a run of spaces, which the loop
in skip_whitespace() would otherwise read one character at a time. The
spaces are skipped 8 bytes at a time; the last 7 bytes of the input and any
other whitespace are left to that loop. Skipping bypasses get();
bulk_consume() does its bookkeeping.
*/
void skip_indentation(std::true_type /*bulk*/)
{
JSON_ASSERT(!next_unget);
const std::size_t remaining = ia.bulk_remaining();
if (remaining < 8)
{
return;
}
const char* const data = reinterpret_cast<const char*>(ia.bulk_data());
std::size_t pos = 0;
for (; pos + 8 <= remaining; pos += 8)
{
// little-endian, so the first byte is the lowest
const std::uint64_t non_space = read_eight_bytes(data + pos) ^ 0x2020202020202020ull;
if (non_space != 0)
{
// skip the spaces before the first other byte of this word
pos += static_cast<std::size_t>(count_trailing_zeros(non_space)) / 8;
break;
}
}
bulk_consume(data, pos);
}
/// streaming input: no bulk fast path
void skip_indentation(std::false_type /*bulk*/) const noexcept {}
token_type scan()
{
// initially, skip the BOM
if (position.chars_read_total == 0 && !skip_bom())
if (get_chars_read_total() == 0 && !skip_bom())
{
error_message = "invalid BOM; must be 0xEF 0xBB 0xBF if given";
return token_type::parse_error;
@@ -2039,7 +2350,7 @@ scan_number_done:
token_type scan_expecting(token_type expected_type)
{
JSON_ASSERT(expected_type == token_type::name_separator || expected_type == token_type::value_separator);
JSON_ASSERT(position.chars_read_total > 0);
JSON_ASSERT(get_chars_read_total() > 0);
const char_int_type expected_char = static_cast<unsigned char>((expected_type == token_type::name_separator) ? ':' : ',');
skip_whitespace();
if (JSON_HEDLEY_LIKELY(current == expected_char))
include/nlohmann/detail/input/number_parse.hpp
+725 -386
View File
File diff suppressed because it is too large. Load diff
include/nlohmann/detail/input/parser.hpp
+31 -40
View File
@@ -156,9 +156,7 @@ class parser
// strict mode: next byte must be EOF
if (get_token() != token_type::end_of_input)
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::end_of_input, "value"));
}
}
else
@@ -197,10 +195,7 @@ class parser
// in strict mode, input must be completely read
if (get_token() != token_type::end_of_input)
{
sdp.parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(),
exception_message(token_type::end_of_input, "value"), nullptr));
syntax_error(sdp, exception_message(token_type::end_of_input, "value"));
}
}
else
@@ -250,9 +245,7 @@ class parser
// parse key
if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
}
if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
{
@@ -262,9 +255,7 @@ class parser
// parse separator (:)
if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
return syntax_error(*sax, exception_message(token_type::name_separator, "object separator"));
}
// remember we are now inside an object
@@ -307,7 +298,7 @@ class parser
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
}
if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
@@ -375,23 +366,16 @@ class parser
case token_type::parse_error:
{
// using "uninitialized" to avoid an "expected" message
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::uninitialized, "value"));
}
case token_type::end_of_input:
{
if (JSON_HEDLEY_UNLIKELY(m_lexer.get_position().chars_read_total == 1))
if (JSON_HEDLEY_UNLIKELY(m_lexer.get_chars_read_total() == 1))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(),
"attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
return syntax_error(*sax, "attempting to parse an empty input; check that your input string or stream contains the expected JSON");
}
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
}
case token_type::uninitialized:
case token_type::end_array:
@@ -401,9 +385,7 @@ class parser
case token_type::literal_or_value:
default: // the last token was unexpected
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
}
}
}
@@ -454,9 +436,7 @@ class parser
continue;
}
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr));
return syntax_error(*sax, exception_message(token_type::end_array, "array"));
}
// states.back() is false -> object
@@ -473,9 +453,7 @@ class parser
// parse key
if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
}
if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
@@ -486,9 +464,7 @@ class parser
// parse separator (:)
if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
return syntax_error(*sax, exception_message(token_type::name_separator, "object separator"));
}
// parse values
@@ -516,9 +492,7 @@ class parser
continue;
}
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr));
return syntax_error(*sax, exception_message(token_type::end_object, "object"));
}
}
@@ -535,6 +509,23 @@ class parser
return (last_token = m_lexer.scan_expecting(expected_type)) == expected_type;
}
/*!
@brief reports a syntax error at the current token (parse_error.101)
@param[in] sax the SAX parser to report the error to
@param[in] message the error message
@return the result of the SAX parser's parse_error()
*/
template<typename SAX>
bool syntax_error(SAX& sax, const std::string& message)
{
// MSVC 2015 reports C4100 (unreferenced parameter) when SAX::parse_error is static
static_cast<void>(sax);
// computing the position is O(input read so far) for seekable input
const position_t position = m_lexer.get_position();
return sax.parse_error(position, m_lexer.get_token_string(),
parse_error::create(exception_id::syntax_error, position, message, nullptr));
}
std::string exception_message(const token_type expected, const std::string& context)
{
std::string error_msg = "syntax error ";
include/nlohmann/detail/input/pow5_table.hpp
+4
View File
@@ -22,6 +22,10 @@ namespace detail
constexpr std::int64_t pow5_128_smallest_power = -342;
constexpr std::int64_t pow5_128_largest_power = 308;
// every entry of pow5_128() holds two 64-bit halves of 5^q, one per covered power of 5
static_assert((pow5_128_largest_power - pow5_128_smallest_power + 1) * 2 == 1302,
"pow5_128_smallest_power/pow5_128_largest_power must match the size of the pow5_128() table");
/*!
@brief 128-bit approximations of 5^q for q in [-342, 308]
include/nlohmann/detail/input/string_scan.hpp
+70 -29
View File
@@ -8,10 +8,12 @@
#pragma once
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint64_t
#include <cstdint> // uint64_t, uint8_t
#include <cstring> // memcpy
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/macro_scope.hpp>
// Optional SIMD backend for bulk UTF-8 validation. This is an opt-in external
@@ -69,18 +71,12 @@ inline std::size_t find_string_special(const unsigned char* data, std::size_t n)
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t word = 0;
std::memcpy(&word, data + i, sizeof(word));
if (swar_string_special(word) != 0)
const std::uint64_t special = swar_string_special(read_eight_bytes(data + i));
if (special != 0)
{
// a special byte is in this word; locate it (endian-agnostic)
for (std::size_t j = 0; j < 8; ++j)
{
if (is_string_special(data[i + j]))
{
return i + j;
}
}
// the lowest flagged byte is the first special one: the borrows of
// the subtractions can only flag bytes above a true hit
return i + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
}
}
for (; i < n; ++i)
@@ -114,8 +110,7 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t v = 0;
std::memcpy(&v, data + i, sizeof(v));
const std::uint64_t v = read_eight_bytes(data + i);
const std::uint64_t q = v ^ 0x2222222222222222ull; // '"' (0x22)
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\' (0x5C)
const std::uint64_t d = v ^ 0x7F7F7F7F7F7F7F7Full; // DEL (0x7F)
@@ -126,7 +121,9 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
| (v & high); // >= 0x80
if (stop != 0)
{
break;
// the lowest flagged byte is the first one to stop at (see
// find_string_special())
return i + (static_cast<std::size_t>(count_trailing_zeros(stop)) / 8);
}
}
for (; i < n; ++i)
@@ -253,12 +250,18 @@ inline std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t
{
break; // end of buffer, or a quote/escape/control byte
}
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
if (seq == 0)
// a run of multi-byte sequences (e.g. CJK text) is validated sequence
// by sequence without searching for the next special byte in between
do
{
break; // ill-formed or truncated: let the byte path diagnose it
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
if (seq == 0)
{
return pos; // ill-formed or truncated: let the byte path diagnose it
}
pos += seq;
}
pos += seq;
while (pos < n && data[pos] >= 0x80u);
}
return pos;
}
@@ -273,8 +276,7 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t v = 0;
std::memcpy(&v, data + i, sizeof(v));
const std::uint64_t v = read_eight_bytes(data + i);
const std::uint64_t q = v ^ 0x2222222222222222ull;
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull;
const std::uint64_t hit = ((q - ones) & ~q & high)
@@ -282,14 +284,8 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
| ((v - 0x2020202020202020ull) & ~v & high);
if (hit != 0)
{
for (std::size_t j = 0; j < 8; ++j)
{
const unsigned char c = data[i + j];
if (c == '\"' || c == '\\' || c < 0x20u)
{
return i + j;
}
}
// the lowest flagged byte is the first delimiter (see find_string_special())
return i + (static_cast<std::size_t>(count_trailing_zeros(hit)) / 8);
}
}
for (; i < n; ++i)
@@ -320,5 +316,50 @@ inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noe
return scalar_string_bulk_run(data, n);
}
// Decode the 4 hex digits at [data, data+4) - the digits following a `\u`
// escape - into a codepoint 0x0000..0xFFFF via one table lookup per byte
// (after yyjson's read_hex_u16), or return -1 if any of the 4 bytes is not a
// hex digit ('0'..'9', 'A'..'F', 'a'..'f'). The caller must already have
// checked that 4 bytes are available; used by lexer::get_codepoint()'s
// contiguous fast path. On -1 it falls back to the byte-at-a-time loop, which
// stops at the first invalid digit, so the reported error and position are
// unaffected by this fast path.
inline int hex_codepoint(const unsigned char* data) noexcept
{
static const std::array<std::uint8_t, 256> hex_digit_table = // NOLINT(cppcoreguidelines-avoid-non-const-global-variables)
{
{
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 00..0F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 10..1F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 20..2F
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 30..3F ('0'..'9')
0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 40..4F ('A'..'F')
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 50..5F
0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 60..6F ('a'..'f')
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 70..7F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 80..8F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 90..9F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // A0..AF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // B0..BF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // C0..CF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // D0..DF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // E0..EF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF // F0..FF
}
};
const std::uint8_t d0 = hex_digit_table[data[0]];
const std::uint8_t d1 = hex_digit_table[data[1]];
const std::uint8_t d2 = hex_digit_table[data[2]];
const std::uint8_t d3 = hex_digit_table[data[3]];
// every valid digit is <= 0xF; the combined OR only exceeds it if at
// least one of the four bytes was not a hex digit (looked up as 0xFF)
if ((d0 | d1 | d2 | d3) > 0x0F)
{
return -1;
}
return (d0 << 12) | (d1 << 8) | (d2 << 4) | d3;
}
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END