mirror of
https://github.com/nlohmann/json.git
synced 2026-10-03 13:10:33 +00:00
Repair complete items in binary formats when parse_error() returns true (#3989)
When the SAX parser asks to recover, the binary readers now repair an item whose end is known and read on after it, as RFC 8949, Section 5.3 describes for CBOR: - CBOR: tags are ignored, and simple values other than false, true, and null become null (RFC 8949, Section 6.1); a negative integer below the range of number_integer_t becomes the nearest floating-point number. - Strings that are not valid UTF-8 get U+FFFD for each ill-formed sequence, as in JSON text; so does a UBJSON/BJData char above 0x7F. - UBJSON/BJData high-precision numbers keep their longest valid beginning (via the lexer's recover_token()), or become infinity. - Members whose key is not a string are skipped (CBOR, MessagePack, BON8), like members without a key in JSON text. - BSON elements of types the library does not read (ObjectId, datetime, decimal128, ...) become null; a string without its terminator and a document whose size does not match are kept. Where the end of an item is unknown, reading stops as before, except that BSON skips to the end of the document, whose size it knows. The value read before such an error is now completed by the reader from its container stack, as the JSON parser does, instead of by a proxy SAX parser, which is removed. Like the parser, binary_reader gets an AllowRecovery template parameter, so that from_*() compile without the new code. Tests: a table of repairs, numbers out of range, errors that stop, and a sweep over changed and removed bytes of eight encodings that checks balanced events and that the first error is the one from_*() reports. All fuzzers now run a recovering checker; the binary ones also check that it reports an error exactly when from_*() fails. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
@@ -143,7 +143,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
friend class ::nlohmann::detail::iter_impl;
|
||||
template<typename BasicJsonType, typename CharType, typename OutputSinkType>
|
||||
friend class ::nlohmann::detail::binary_writer;
|
||||
template<typename BasicJsonType, typename InputType, typename SAX>
|
||||
template<typename BasicJsonType, typename InputType, typename SAX, bool AllowRecovery>
|
||||
friend class ::nlohmann::detail::binary_reader;
|
||||
template<typename BasicJsonType, typename InputAdapterType>
|
||||
friend class ::nlohmann::detail::json_sax_dom_parser;
|
||||
@@ -4979,26 +4979,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
|
||||
}
|
||||
|
||||
private:
|
||||
/// read a binary format and pass it to a SAX parser; if the SAX parser
|
||||
/// asks to recover from an error, the value read so far is completed
|
||||
/// (see detail::json_sax_salvager and #3989)
|
||||
template<typename InputAdapterType, typename SAX>
|
||||
static bool sax_parse_binary(InputAdapterType ia, SAX* sax,
|
||||
const input_format_t format, const bool strict)
|
||||
{
|
||||
(void)detail::is_sax_static_asserts<SAX, basic_json> {};
|
||||
using salvager_t = detail::json_sax_salvager<basic_json, SAX>;
|
||||
salvager_t salvager(sax);
|
||||
const bool result = detail::binary_reader<basic_json, InputAdapterType, salvager_t>(std::move(ia), format).sax_parse(format, &salvager, strict);
|
||||
if (!result)
|
||||
{
|
||||
salvager.close_open_containers();
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
public:
|
||||
/// @brief generate SAX events
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/sax_parse/
|
||||
template <typename InputType, typename SAX>
|
||||
@@ -5012,7 +4992,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
auto ia = detail::input_adapter(std::forward<InputType>(i));
|
||||
return format == input_format_t::json
|
||||
? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
|
||||
: sax_parse_binary(std::move(ia), sax, format, strict);
|
||||
: detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(format, sax, strict);
|
||||
}
|
||||
|
||||
/// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -5029,7 +5009,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
auto ia = detail::input_adapter(std::move(first), std::move(last));
|
||||
return format == input_format_t::json
|
||||
? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
|
||||
: sax_parse_binary(std::move(ia), sax, format, strict);
|
||||
: detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(format, sax, strict);
|
||||
}
|
||||
|
||||
/// @brief generate SAX events
|
||||
@@ -5051,7 +5031,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
|
||||
? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
|
||||
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
|
||||
: sax_parse_binary(std::move(ia), sax, format, strict);
|
||||
: detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(format, sax, strict);
|
||||
}
|
||||
#ifndef JSON_NO_IO
|
||||
/// @brief deserialize from stream
|
||||
|
||||
Reference in New Issue
Block a user