amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-02-17 09:03:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

json start/end position implementation (#4517)

Browse Source 
* Add implementation to retrieve start and end positions of json during parse

* Add more unit tests and add start/stop parsing for arrays

* Add raw value for all types

* Add more tests and fix compiler warning

* Amalgamate

* Fix CLang GCC warnings

* Fix error in build

* Style using astyle 3.1

* Fix whitespace changes

* revert

* more whitespace reverts

* Address PR comments

* Fix failing issues

* More whitespace reverts

* Address remaining PR comments

* Address comments

* Switch to using custom base class instead of default basic_json

* Adding a basic using for a json using the new base class. Also address PR comments and fix CI failures

* Address decltype comments

* Diagnostic positions macro (#4)

Co-authored-by: Sush Shringarputale <sushring@linux.microsoft.com>

* Fix missed include deletion

* Add docs and address other PR comments (#5)

* Add docs and address other PR comments

---------

Co-authored-by: Sush Shringarputale <sushring@linux.microsoft.com>

* Address new PR comments and fix CI tests for documentation

* Update documentation based on feedback (#6)

---------

Co-authored-by: Sush Shringarputale <sushring@linux.microsoft.com>

* Address std::size_t and other comments

* Fix new CI issues

* Fix lcov

* Improve lcov case with update to handle_diagnostic_positions call for discarded values

* Fix indentation of LCOV_EXCL_STOP comments

* fix amalgamation astyle issue

---------

Co-authored-by: Sush Shringarputale <sushring@linux.microsoft.com>
This commit is contained in:
Sushrut Shringarputale
2024-12-18 13:46:14 -08:00
committed by GitHub
parent 733c59588d
commit 58f5f25968
20 changed files with 3545 additions and 787 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
include/nlohmann/detail/abi_macros.hpp
View File

@@ -26,6 +26,10 @@
#define JSON_DIAGNOSTICS 0
#endif
#ifndef JSON_DIAGNOSTIC_POSITIONS
#define JSON_DIAGNOSTIC_POSITIONS 0
#endif
#ifndef JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
#define JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON 0
#endif
@@ -36,6 +40,12 @@
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS
#endif
#if JSON_DIAGNOSTIC_POSITIONS
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTIC_POSITIONS _dp
#else
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTIC_POSITIONS
#endif
#if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
#define NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON _ldvcmp
#else
@@ -47,14 +57,15 @@
#endif
// Construct the namespace ABI tags component
#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b) json_abi ## a ## b
#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b) \
NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b)
#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c) json_abi ## a ## b ## c
#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c) \
NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c)
#define NLOHMANN_JSON_ABI_TAGS \
NLOHMANN_JSON_ABI_TAGS_CONCAT( \
NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS, \
NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON)
NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON, \
NLOHMANN_JSON_ABI_TAG_DIAGNOSTIC_POSITIONS)
// Construct the namespace version component
#define NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT_EX(major, minor, patch) \

2
include/nlohmann/detail/input/binary_reader.hpp
View File

@@ -65,7 +65,7 @@ static inline bool little_endianness(int num = 1) noexcept
/*!
@brief deserialization of CBOR, MessagePack, and UBJSON values
*/
template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_parser<BasicJsonType>>
template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_parser<BasicJsonType, InputAdapterType>>
class binary_reader
{
using number_integer_t = typename BasicJsonType::number_integer_t;

3
include/nlohmann/detail/input/input_adapters.hpp
View File

@@ -462,6 +462,9 @@ typename container_input_adapter_factory_impl::container_input_adapter_factory<C
return container_input_adapter_factory_impl::container_input_adapter_factory<ContainerType>::create(container);
}
// specialization for std::string
using string_input_adapter_type = decltype(input_adapter(std::declval<std::string>()));
#ifndef JSON_NO_IO
// Special cases with fast paths
inline file_input_adapter input_adapter(std::FILE* file)

282
include/nlohmann/detail/input/json_sax.hpp
View File

@@ -10,13 +10,14 @@
#include <cstddef>
#include <string> // string
#include <type_traits> // enable_if_t
#include <utility> // move
#include <vector> // vector
#include <nlohmann/detail/exceptions.hpp>
#include <nlohmann/detail/input/lexer.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/string_concat.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
/*!
@@ -157,7 +158,7 @@ constructor contains the parsed value.
@tparam BasicJsonType the JSON type
*/
template<typename BasicJsonType>
template<typename BasicJsonType, typename InputAdapterType>
class json_sax_dom_parser
{
public:
@@ -166,14 +167,15 @@ class json_sax_dom_parser
using number_float_t = typename BasicJsonType::number_float_t;
using string_t = typename BasicJsonType::string_t;
using binary_t = typename BasicJsonType::binary_t;
using lexer_t = lexer<BasicJsonType, InputAdapterType>;
/*!
@param[in,out] r reference to a JSON value that is manipulated while
parsing
@param[in] allow_exceptions_ whether parse errors yield exceptions
*/
explicit json_sax_dom_parser(BasicJsonType& r, const bool allow_exceptions_ = true)
: root(r), allow_exceptions(allow_exceptions_)
explicit json_sax_dom_parser(BasicJsonType& r, const bool allow_exceptions_ = true, lexer_t* lexer_ = nullptr)
: root(r), allow_exceptions(allow_exceptions_), m_lexer_ref(lexer_)
{}
// make class move-only
@@ -229,6 +231,17 @@ 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;
}
#endif
if (JSON_HEDLEY_UNLIKELY(len != static_cast<std::size_t>(-1) && len > ref_stack.back()->max_size()))
{
JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
@@ -252,6 +265,14 @@ class json_sax_dom_parser
JSON_ASSERT(!ref_stack.empty());
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();
}
#endif
ref_stack.back()->set_parents();
ref_stack.pop_back();
return true;
@@ -261,6 +282,15 @@ 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;
}
#endif
if (JSON_HEDLEY_UNLIKELY(len != static_cast<std::size_t>(-1) && len > ref_stack.back()->max_size()))
{
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
@@ -274,6 +304,14 @@ class json_sax_dom_parser
JSON_ASSERT(!ref_stack.empty());
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();
}
#endif
ref_stack.back()->set_parents();
ref_stack.pop_back();
return true;
@@ -298,6 +336,75 @@ class json_sax_dom_parser
}
private:
#if JSON_DIAGNOSTIC_POSITIONS
void handle_diagnostic_positions_for_json_value(BasicJsonType& v)
{
if (m_lexer_ref)
{
// 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 = m_lexer_ref->get_position();
switch (v.type())
{
case value_t::boolean:
{
// 4 and 5 are the string length of "true" and "false"
v.start_position = v.end_position - (v.m_data.m_value.boolean ? 4 : 5);
break;
}
case value_t::null:
{
// 4 is the string length of "null"
v.start_position = v.end_position - 4;
break;
}
case value_t::string:
{
// include the length of the quotes, which is 2
v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
break;
}
// As we handle the start and end positions for values created during parsing,
// we do not expect the following value type to be called. Regardless, set the positions
// in case this is created manually or through a different constructor. Exclude from lcov
// since the exact condition of this switch is esoteric.
// LCOV_EXCL_START
case value_t::discarded:
{
v.end_position = std::string::npos;
v.start_position = v.end_position;
break;
}
// LCOV_EXCL_STOP
case value_t::binary:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
{
v.start_position = v.end_position - m_lexer_ref->get_string().size();
break;
}
case value_t::object:
case value_t::array:
{
// object and array are handled in start_object() and start_array() handlers
// skip setting the values here.
break;
}
default: // LCOV_EXCL_LINE
// Handle all possible types discretely, default handler should never be reached.
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert,-warnings-as-errors) LCOV_EXCL_LINE
}
}
}
#endif
/*!
@invariant If the ref stack is empty, then the passed value will be the new
root.
@@ -311,6 +418,11 @@ class json_sax_dom_parser
if (ref_stack.empty())
{
root = BasicJsonType(std::forward<Value>(v));
#if JSON_DIAGNOSTIC_POSITIONS
handle_diagnostic_positions_for_json_value(root);
#endif
return &root;
}
@@ -319,12 +431,22 @@ class json_sax_dom_parser
if (ref_stack.back()->is_array())
{
ref_stack.back()->m_data.m_value.array->emplace_back(std::forward<Value>(v));
#if JSON_DIAGNOSTIC_POSITIONS
handle_diagnostic_positions_for_json_value(ref_stack.back()->m_data.m_value.array->back());
#endif
return &(ref_stack.back()->m_data.m_value.array->back());
}
JSON_ASSERT(ref_stack.back()->is_object());
JSON_ASSERT(object_element);
*object_element = BasicJsonType(std::forward<Value>(v));
#if JSON_DIAGNOSTIC_POSITIONS
handle_diagnostic_positions_for_json_value(*object_element);
#endif
return object_element;
}
@@ -338,9 +460,11 @@ class json_sax_dom_parser
bool errored = false;
/// whether to throw exceptions in case of errors
const bool allow_exceptions = true;
/// the lexer reference to obtain the current position
lexer_t* m_lexer_ref = nullptr;
};
template<typename BasicJsonType>
template<typename BasicJsonType, typename InputAdapterType>
class json_sax_dom_callback_parser
{
public:
@@ -351,11 +475,13 @@ class json_sax_dom_callback_parser
using binary_t = typename BasicJsonType::binary_t;
using parser_callback_t = typename BasicJsonType::parser_callback_t;
using parse_event_t = typename BasicJsonType::parse_event_t;
using lexer_t = lexer<BasicJsonType, InputAdapterType>;
json_sax_dom_callback_parser(BasicJsonType& r,
parser_callback_t cb,
const bool allow_exceptions_ = true)
: root(r), callback(std::move(cb)), allow_exceptions(allow_exceptions_)
const bool allow_exceptions_ = true,
lexer_t* lexer_ = nullptr)
: root(r), callback(std::move(cb)), allow_exceptions(allow_exceptions_), m_lexer_ref(lexer_)
{
keep_stack.push_back(true);
}
@@ -418,12 +544,26 @@ class json_sax_dom_callback_parser
auto val = handle_value(BasicJsonType::value_t::object, true);
ref_stack.push_back(val.second);
// check object limit
if (ref_stack.back() && JSON_HEDLEY_UNLIKELY(len != static_cast<std::size_t>(-1) && len > ref_stack.back()->max_size()))
if (ref_stack.back())
{
JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
}
#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;
}
#endif
// check object limit
if (JSON_HEDLEY_UNLIKELY(len != static_cast<std::size_t>(-1) && len > ref_stack.back()->max_size()))
{
JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
}
}
return true;
}
@@ -452,9 +592,23 @@ class json_sax_dom_callback_parser
{
// discard object
*ref_stack.back() = discarded;
#if JSON_DIAGNOSTIC_POSITIONS
// Set start/end positions for discarded object.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
#endif
}
else
{
#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();
}
#endif
ref_stack.back()->set_parents();
}
}
@@ -488,10 +642,25 @@ class json_sax_dom_callback_parser
auto val = handle_value(BasicJsonType::value_t::array, true);
ref_stack.push_back(val.second);
// check array limit
if (ref_stack.back() && JSON_HEDLEY_UNLIKELY(len != static_cast<std::size_t>(-1) && len > ref_stack.back()->max_size()))
if (ref_stack.back())
{
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
#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;
}
#endif
// check array limit
if (JSON_HEDLEY_UNLIKELY(len != static_cast<std::size_t>(-1) && len > ref_stack.back()->max_size()))
{
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
}
return true;
@@ -506,12 +675,26 @@ class json_sax_dom_callback_parser
keep = callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::array_end, *ref_stack.back());
if (keep)
{
#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();
}
#endif
ref_stack.back()->set_parents();
}
else
{
// discard array
*ref_stack.back() = discarded;
#if JSON_DIAGNOSTIC_POSITIONS
// Set start/end positions for discarded array.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
#endif
}
}
@@ -548,6 +731,71 @@ class json_sax_dom_callback_parser
}
private:
#if JSON_DIAGNOSTIC_POSITIONS
void handle_diagnostic_positions_for_json_value(BasicJsonType& v)
{
if (m_lexer_ref)
{
// 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 = m_lexer_ref->get_position();
switch (v.type())
{
case value_t::boolean:
{
// 4 and 5 are the string length of "true" and "false"
v.start_position = v.end_position - (v.m_data.m_value.boolean ? 4 : 5);
break;
}
case value_t::null:
{
// 4 is the string length of "null"
v.start_position = v.end_position - 4;
break;
}
case value_t::string:
{
// include the length of the quotes, which is 2
v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
break;
}
case value_t::discarded:
{
v.end_position = std::string::npos;
v.start_position = v.end_position;
break;
}
case value_t::binary:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
{
v.start_position = v.end_position - m_lexer_ref->get_string().size();
break;
}
case value_t::object:
case value_t::array:
{
// object and array are handled in start_object() and start_array() handlers
// skip setting the values here.
break;
}
default: // LCOV_EXCL_LINE
// Handle all possible types discretely, default handler should never be reached.
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert,-warnings-as-errors) LCOV_EXCL_LINE
}
}
}
#endif
/*!
@param[in] v value to add to the JSON value we build during parsing
@param[in] skip_callback whether we should skip calling the callback
@@ -578,6 +826,10 @@ class json_sax_dom_callback_parser
// create value
auto value = BasicJsonType(std::forward<Value>(v));
#if JSON_DIAGNOSTIC_POSITIONS
handle_diagnostic_positions_for_json_value(value);
#endif
// check callback
const bool keep = skip_callback || callback(static_cast<int>(ref_stack.size()), parse_event_t::value, value);
@@ -645,6 +897,8 @@ class json_sax_dom_callback_parser
const bool allow_exceptions = true;
/// a discarded value for the callback
BasicJsonType discarded = BasicJsonType::value_t::discarded;
/// the lexer reference to obtain the current position
lexer_t* m_lexer_ref = nullptr;
};
template<typename BasicJsonType>

4
include/nlohmann/detail/input/parser.hpp
View File

@@ -94,7 +94,7 @@ class parser
{
if (callback)
{
json_sax_dom_callback_parser<BasicJsonType> sdp(result, callback, allow_exceptions);
json_sax_dom_callback_parser<BasicJsonType, InputAdapterType> sdp(result, callback, allow_exceptions, &m_lexer);
sax_parse_internal(&sdp);
// in strict mode, input must be completely read
@@ -122,7 +122,7 @@ class parser
}
else
{
json_sax_dom_parser<BasicJsonType> sdp(result, allow_exceptions);
json_sax_dom_parser<BasicJsonType, InputAdapterType> sdp(result, allow_exceptions, &m_lexer);
sax_parse_internal(&sdp);
// in strict mode, input must be completely read