Compare commits

..
Author SHA1 Message Date
Niels Lohmann 31b51c95db Name the UTF-8 cut helpers after what they do to the buffer
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-11-17 16:43:55 +01:00
Niels Lohmann 04fbced73d Cut long tokens in parse error messages at UTF-8 character boundaries
A parse error message shows a token of more than 8192 bytes by its
first and its last 4096 bytes around "...". The cuts were at fixed byte
offsets, so they could split a UTF-8 character: for valid UTF-8 input,
what() and the last token passed to SAX parse_error() were not valid
UTF-8, and storing the message in a json value and dumping it threw
type_error.316.

Move the end of the first part back and the start of the last part
forward to a character boundary, by at most three bytes each. The
lexer always reads bytes (wide strings are converted to UTF-8 first),
and the decision depends only on bytes inside the two parts, so the
message stays the same for every kind of input. Both parts only get
shorter, so the buffers that keep the token need no more room.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-11-16 08:12:02 +01:00
10 changed files with 232 additions and 25 deletions

No files matched your search

+1 -1
View File
@@ -140,7 +140,7 @@ Exceptions have ids 1xx.
This error indicates a syntax error while deserializing a JSON text. The error message describes that an unexpected token (character) was encountered, and the member `byte` indicates the error position. This error indicates a syntax error while deserializing a JSON text. The error message describes that an unexpected token (character) was encountered, and the member `byte` indicates the error position.
The message ends with the last read token (`last read: '...'`), with control characters written as `<U+XXXX>`. A token of more than 8192 characters is shown by its first and its last 4096 characters, separated by `...`. The message ends with the last read token (`last read: '...'`), with control characters written as `<U+XXXX>`. A token of more than 8192 bytes is shown by its first and its last 4096 bytes, separated by `...`; each part is shortened by up to three bytes so that it does not end or begin within a UTF-8 character.
!!! failure "Example message" !!! failure "Example message"
@@ -48,11 +48,10 @@ namespace detail
{ {
/*! /*!
@brief implements binary to decimal floating-point conversion: the shortest @brief implements the Grisu2 algorithm for binary to decimal floating-point
digits of Zmij (see zmij.hpp) for IEEE 754 binary64 numbers, and the Grisu2 conversion.
algorithm for all other formats.
The Grisu2 implementation is a slightly modified version of the reference This implementation is a slightly modified version of the reference
implementation which may be obtained from implementation which may be obtained from
http://florian.loitsch.com/publications (bench.tar.gz). http://florian.loitsch.com/publications (bench.tar.gz).
+56 -2
View File
@@ -2279,9 +2279,14 @@ scan_number_done:
std::string result; std::string result;
if (chars.size() > 2 * shown) if (chars.size() > 2 * shown)
{ {
append_escaped(result, chars.begin(), chars.begin() + static_cast<std::ptrdiff_t>(shown)); // the lexer reads bytes (wide characters arrive as UTF-8), so
// move both cuts to character boundaries to keep the message
// valid UTF-8; this only shortens the two parts
const auto head_end = chars.begin() + static_cast<std::ptrdiff_t>(length_without_partial_utf8_at_end(chars.data(), shown));
const auto tail_begin = chars.end() - static_cast<std::ptrdiff_t>(shown);
append_escaped(result, chars.begin(), head_end);
result += "..."; result += "...";
append_escaped(result, chars.end() - static_cast<std::ptrdiff_t>(shown), chars.end()); append_escaped(result, tail_begin + static_cast<std::ptrdiff_t>(partial_utf8_length_at_start(&*tail_begin)), chars.end());
} }
else else
{ {
@@ -2291,6 +2296,55 @@ scan_number_done:
} }
private: private:
/// whether @a c is a UTF-8 continuation byte
static bool is_utf8_continuation(const char_type c) noexcept
{
return (static_cast<unsigned char>(c) & 0xC0u) == 0x80u;
}
/*!
@brief the length of the first @a n characters at @a data without a UTF-8
character that begins there but does not end there
Looks only at the last 4 of these characters: in valid UTF-8, at most 3
bytes of a character can be before the cut.
*/
static std::size_t length_without_partial_utf8_at_end(const char_type* data, const std::size_t n) noexcept
{
std::size_t lead = n - 1;
while (lead > n - 4 && is_utf8_continuation(data[lead]))
{
--lead;
}
const auto c = static_cast<unsigned char>(data[lead]);
std::size_t length = 1;
if (c >= 0xF0u)
{
length = 4;
}
else if (c >= 0xE0u)
{
length = 3;
}
else if (c >= 0xC0u)
{
length = 2;
}
return lead + length > n ? lead : n;
}
/// the number of UTF-8 continuation bytes (at most 3) at the start of @a data, which
/// belong to a character that begins before it
static std::size_t partial_utf8_length_at_start(const char_type* data) noexcept
{
std::size_t skip = 0;
while (skip < 3 && is_utf8_continuation(data[skip]))
{
++skip;
}
return skip;
}
/// append the characters [first, last) to @a result, escaping control characters /// append the characters [first, last) to @a result, escaping control characters
template<typename Iterator> template<typename Iterator>
static void append_escaped(std::string& result, Iterator first, Iterator last) static void append_escaped(std::string& result, Iterator first, Iterator last)
@@ -257,7 +257,7 @@ struct ieee_binary_format<53> // binary64
These formats (float, double, and long double where it is binary64, e.g. These formats (float, double, and long double where it is binary64, e.g.
with MSVC or on Apple arm64) are converted by parse_float_native(). The with MSVC or on Apple arm64) are converted by parse_float_native(). The
predicate is the one the serializer uses to choose to_chars() over snprintf. predicate is the one the serializer uses to choose Grisu2.
*/ */
template<typename FloatType> template<typename FloatType>
struct has_native_float_format struct has_native_float_format
@@ -915,7 +915,7 @@ class binary_writer
JSON_THROW(out_of_range::create(exception_id::subtype_out_of_range, concat("subtype ", std::to_string(subtype), " is too large for ", what, " (max 255)"), &j)); JSON_THROW(out_of_range::create(exception_id::subtype_out_of_range, concat("subtype ", std::to_string(subtype), " is too large for ", what, " (max 255)"), &j));
} }
/// @throw other_error.502 always /// @throw other_error.407 always
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE
static void throw_size_marker_required(const BasicJsonType& j) static void throw_size_marker_required(const BasicJsonType& j)
{ {
@@ -2033,9 +2033,8 @@ class serializer
} }
// If number_float_t is an IEEE-754 single or double precision number, // If number_float_t is an IEEE-754 single or double precision number,
// use to_chars() to produce short numbers which are guaranteed to // use the Grisu2 algorithm to produce short numbers which are
// round-trip, using strtof and strtod, resp. (the shortest digits of // guaranteed to round-trip, using strtof and strtod, resp.
// Zmij for binary64, the Grisu2 algorithm for binary32).
// //
// NB: The test below works if <long double> == <double>. // NB: The test below works if <long double> == <double>.
static constexpr bool is_ieee_single_or_double static constexpr bool is_ieee_single_or_double
+1 -1
View File
@@ -849,7 +849,7 @@ class basic_json_view
return !navigation::editable() || m_doc->edits == nullptr; return !navigation::editable() || m_doc->edits == nullptr;
} }
/// the member of this object with @a key (the first one if the key occurs more than once), or nullptr /// the member of this object with @a key (the last one if the key occurs more than once), or nullptr
NLOHMANN_VIEW_ALWAYS_INLINE const node* find_key(string_view_t key) const NLOHMANN_VIEW_ALWAYS_INLINE const node* find_key(string_view_t key) const
{ {
return find_key(key, std::integral_constant<bool, is_editable> {}); return find_key(key, std::integral_constant<bool, is_editable> {});
+63 -11
View File
@@ -11642,7 +11642,7 @@ struct ieee_binary_format<53> // binary64
These formats (float, double, and long double where it is binary64, e.g. These formats (float, double, and long double where it is binary64, e.g.
with MSVC or on Apple arm64) are converted by parse_float_native(). The with MSVC or on Apple arm64) are converted by parse_float_native(). The
predicate is the one the serializer uses to choose to_chars() over snprintf. predicate is the one the serializer uses to choose Grisu2.
*/ */
template<typename FloatType> template<typename FloatType>
struct has_native_float_format struct has_native_float_format
@@ -15782,9 +15782,14 @@ scan_number_done:
std::string result; std::string result;
if (chars.size() > 2 * shown) if (chars.size() > 2 * shown)
{ {
append_escaped(result, chars.begin(), chars.begin() + static_cast<std::ptrdiff_t>(shown)); // the lexer reads bytes (wide characters arrive as UTF-8), so
// move both cuts to character boundaries to keep the message
// valid UTF-8; this only shortens the two parts
const auto head_end = chars.begin() + static_cast<std::ptrdiff_t>(length_without_partial_utf8_at_end(chars.data(), shown));
const auto tail_begin = chars.end() - static_cast<std::ptrdiff_t>(shown);
append_escaped(result, chars.begin(), head_end);
result += "..."; result += "...";
append_escaped(result, chars.end() - static_cast<std::ptrdiff_t>(shown), chars.end()); append_escaped(result, tail_begin + static_cast<std::ptrdiff_t>(partial_utf8_length_at_start(&*tail_begin)), chars.end());
} }
else else
{ {
@@ -15794,6 +15799,55 @@ scan_number_done:
} }
private: private:
/// whether @a c is a UTF-8 continuation byte
static bool is_utf8_continuation(const char_type c) noexcept
{
return (static_cast<unsigned char>(c) & 0xC0u) == 0x80u;
}
/*!
@brief the length of the first @a n characters at @a data without a UTF-8
character that begins there but does not end there
Looks only at the last 4 of these characters: in valid UTF-8, at most 3
bytes of a character can be before the cut.
*/
static std::size_t length_without_partial_utf8_at_end(const char_type* data, const std::size_t n) noexcept
{
std::size_t lead = n - 1;
while (lead > n - 4 && is_utf8_continuation(data[lead]))
{
--lead;
}
const auto c = static_cast<unsigned char>(data[lead]);
std::size_t length = 1;
if (c >= 0xF0u)
{
length = 4;
}
else if (c >= 0xE0u)
{
length = 3;
}
else if (c >= 0xC0u)
{
length = 2;
}
return lead + length > n ? lead : n;
}
/// the number of UTF-8 continuation bytes (at most 3) at the start of @a data, which
/// belong to a character that begins before it
static std::size_t partial_utf8_length_at_start(const char_type* data) noexcept
{
std::size_t skip = 0;
while (skip < 3 && is_utf8_continuation(data[skip]))
{
++skip;
}
return skip;
}
/// append the characters [first, last) to @a result, escaping control characters /// append the characters [first, last) to @a result, escaping control characters
template<typename Iterator> template<typename Iterator>
static void append_escaped(std::string& result, Iterator first, Iterator last) static void append_escaped(std::string& result, Iterator first, Iterator last)
@@ -31147,7 +31201,7 @@ class binary_writer
JSON_THROW(out_of_range::create(exception_id::subtype_out_of_range, concat("subtype ", std::to_string(subtype), " is too large for ", what, " (max 255)"), &j)); JSON_THROW(out_of_range::create(exception_id::subtype_out_of_range, concat("subtype ", std::to_string(subtype), " is too large for ", what, " (max 255)"), &j));
} }
/// @throw other_error.502 always /// @throw other_error.407 always
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE
static void throw_size_marker_required(const BasicJsonType& j) static void throw_size_marker_required(const BasicJsonType& j)
{ {
@@ -36006,11 +36060,10 @@ namespace detail
{ {
/*! /*!
@brief implements binary to decimal floating-point conversion: the shortest @brief implements the Grisu2 algorithm for binary to decimal floating-point
digits of Zmij (see zmij.hpp) for IEEE 754 binary64 numbers, and the Grisu2 conversion.
algorithm for all other formats.
The Grisu2 implementation is a slightly modified version of the reference This implementation is a slightly modified version of the reference
implementation which may be obtained from implementation which may be obtained from
http://florian.loitsch.com/publications (bench.tar.gz). http://florian.loitsch.com/publications (bench.tar.gz).
@@ -39520,9 +39573,8 @@ class serializer
} }
// If number_float_t is an IEEE-754 single or double precision number, // If number_float_t is an IEEE-754 single or double precision number,
// use to_chars() to produce short numbers which are guaranteed to // use the Grisu2 algorithm to produce short numbers which are
// round-trip, using strtof and strtod, resp. (the shortest digits of // guaranteed to round-trip, using strtof and strtod, resp.
// Zmij for binary64, the Grisu2 algorithm for binary32).
// //
// NB: The test below works if <long double> == <double>. // NB: The test below works if <long double> == <double>.
static constexpr bool is_ieee_single_or_double static constexpr bool is_ieee_single_or_double
+1 -1
View File
@@ -11016,7 +11016,7 @@ class basic_json_view
return !navigation::editable() || m_doc->edits == nullptr; return !navigation::editable() || m_doc->edits == nullptr;
} }
/// the member of this object with @a key (the first one if the key occurs more than once), or nullptr /// the member of this object with @a key (the last one if the key occurs more than once), or nullptr
NLOHMANN_VIEW_ALWAYS_INLINE const node* find_key(string_view_t key) const NLOHMANN_VIEW_ALWAYS_INLINE const node* find_key(string_view_t key) const
{ {
return find_key(key, std::integral_constant<bool, is_editable> {}); return find_key(key, std::integral_constant<bool, is_editable> {});
+103
View File
@@ -3380,5 +3380,108 @@ TEST_CASE("parse error message of a long token")
CHECK(message(text, kind) == "no error"); CHECK(message(text, kind) == "no error");
} }
} }
SECTION("a long string of multi-byte characters")
{
// the parts of a long token are cut at character boundaries, so the
// message of valid UTF-8 input is valid UTF-8, also for wide strings
const auto last_read = [](const std::string & m) -> std::string
{
const auto pos = m.find("last read: '");
return pos == std::string::npos ? std::string() : m.substr(pos + 12, m.size() - pos - 13);
};
const auto utf8 = [](const char32_t c) -> std::string
{
std::string result;
if (c < 0x800)
{
result.push_back(static_cast<char>(0xC0 | (c >> 6)));
}
else if (c < 0x10000)
{
result.push_back(static_cast<char>(0xE0 | (c >> 12)));
result.push_back(static_cast<char>(0x80 | ((c >> 6) & 0x3F)));
}
else
{
result.push_back(static_cast<char>(0xF0 | (c >> 18)));
result.push_back(static_cast<char>(0x80 | ((c >> 12) & 0x3F)));
result.push_back(static_cast<char>(0x80 | ((c >> 6) & 0x3F)));
}
result.push_back(static_cast<char>(0x80 | (c & 0x3F)));
return result;
};
// characters of 2, 3, and 4 bytes
const std::vector<char32_t> characters = {0xE9, 0x20AC, 0x1F600};
for (const char32_t c : characters)
{
for (std::size_t offset = 0; offset < 4; ++offset)
{
CAPTURE(static_cast<std::uint32_t>(c))
CAPTURE(offset)
// an unterminated string: the token is the whole input
std::string text = "\"" + std::string(offset, 'a');
std::u32string text32 = U"\"" + std::u32string(offset, U'a');
while (text.size() < 9000)
{
text += utf8(c);
text32.push_back(c);
}
std::u16string text16;
for (const char32_t c32 : text32)
{
if (c32 < 0x10000)
{
text16.push_back(static_cast<char16_t>(c32));
}
else
{
text16.push_back(static_cast<char16_t>(0xD800 + ((c32 - 0x10000) >> 10)));
text16.push_back(static_cast<char16_t>(0xDC00 + ((c32 - 0x10000) & 0x3FF)));
}
}
const std::string shown = last_read(message(text, 0));
const auto dots = shown.find("...");
REQUIRE(dots != std::string::npos);
// the first and the last at most 4096 bytes, without parts of characters
CHECK(dots <= 4096);
CHECK(dots > 4092);
CHECK(text.compare(0, dots, shown, 0, dots) == 0);
const std::size_t tail = shown.size() - dots - 3;
CHECK(tail <= 4096);
CHECK(tail > 4092);
CHECK(text.compare(text.size() - tail, tail, shown, dots + 3, tail) == 0);
CHECK_NOTHROW(json(shown).dump());
for (int kind = 1; kind < 4; ++kind)
{
CAPTURE(kind)
CHECK(last_read(message(text, kind)) == shown);
}
json _;
std::string m32;
std::string m16;
try
{
_ = json::parse(text32);
}
catch (const json::parse_error& e)
{
m32 = e.what();
}
try
{
_ = json::parse(text16);
}
catch (const json::parse_error& e)
{
m16 = e.what();
}
CHECK(last_read(m32) == shown);
CHECK(last_read(m16) == shown);
}
}
}
} }
#endif #endif