Use and extend the detail helpers to remove duplicated code (#5783)

* Use and extend the detail helpers to remove duplicated code

Library:
- binary_reader: format bytes with hex_byte() instead of snprintf
- add throw_type_must_be() for the 20 copies of type_error.302
- binary_reader: add last_byte_error()/unexpected_byte() for the 32
  "parse error at the last read byte" sites (replaces bon8_error)
- json_sax: add check_container_size() for out_of_range.408 and
  diagnostic_positions::set_container_start/_end()
- json_pointer: add throw_no_parent() (405) and throw_unresolved() (404)

Tests:
- unit-class_parser uses the shared utils::SaxCountdown
- move SaxEventLogger (and its ExitAfter* variants) from unit-class_parser
  and unit-deserialization into the new tests/src/test_sax.hpp

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Factor out more repeated error paths and test boilerplate

Library:
- add throw_cannot_use_with() for the 34 copies of type_error.304-312
  "cannot use X with Y"
- iter_impl: add throw_cannot_get_value() (invalid_iterator.214)
- parser: add syntax_error() for the 12 parse_error.101 sites
- ordered_map: share the four at() bodies via at_impl()
- json_sax_dom_callback_parser: add pop_container() for end_object()
  and end_array()
- binary_reader: build the two UBJSON/BJData length-type messages with
  concat() and last_byte_error()

Tests:
- move same_value(), the NDEBUG guard, and step 0 (parse without
  exceptions) of the seven fuzzer drivers into tests/src/fuzzer_common.hpp

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Name the exception ids and address review comments

Add detail::exception_id, a scoped enum with one named enumerator per
documented exception id, and use it for every id in the library. The
create() functions get an overload for it; the int overloads stay for
user code.

Following the review of #5783: add binary_reader::invalid_byte() and
length_type_error(), basic_json::throw_subscript_wrong_type(), move the
fuzzer includes and the using-declaration into fuzzer_common.hpp, and
rename test_sax.hpp to sax_event_loggers.hpp.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Silence -Wweak-vtables for the SAX event loggers

The loggers moved from anonymous namespaces in the test files into
sax_event_loggers.hpp, so clang now warns that their vtables are
emitted in every translation unit.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Silence MSVC 2015 C4100 in parser::syntax_error for static SAX::parse_error

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Inline invalid_byte() into its call sites

The wrapper only fixed the message string of unexpected_byte(), which is
the same kind of per-argument helper that was declined for
throw_type_must_be(). Call unexpected_byte("invalid byte", ...) directly.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

---------

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann authored and GitHub committed 2026-10-11 08:21:13 +02:00
1 parent f8b47ff6f6
commit 1649d9eda4
26 files changed
+1329 -1391

No files matched your search

+28 -39
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))
{
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 +509,21 @@ 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);
return sax.parse_error(m_lexer.get_position(), m_lexer.get_token_string(),
parse_error::create(exception_id::syntax_error, m_lexer.get_position(), message, nullptr));
}
std::string exception_message(const token_type expected, const std::string& context)
{
std::string error_msg = "syntax error ";