diff --git a/.gitignore b/.gitignore index bec7f5982..7e5a881e3 100644 --- a/.gitignore +++ b/.gitignore @@ -22,7 +22,7 @@ benchmarks/files/numbers/*.json .wsjcpp/* .idea -cmake-build-debug +/cmake-build-* test/test-* /.vs @@ -32,3 +32,4 @@ doc/mkdocs/docs/images doc/mkdocs/docs/examples doc/mkdocs/site doc/mkdocs/docs/__pycache__/ +doc/xml diff --git a/CMakeLists.txt b/CMakeLists.txt index 1b18b83d3..7ee9381df 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -24,7 +24,7 @@ endif () option(JSON_BuildTests "Build the unit tests when BUILD_TESTING is enabled." ON) option(JSON_Install "Install CMake targets during install step." ON) option(JSON_MultipleHeaders "Use non-amalgamated version of the library." OFF) -option(JSON_ImplicitConversions "Enable implicit conversions" ON) +option(JSON_ImplicitConversions "Enable implicit conversions." ON) ## ## CONFIGURATION @@ -49,6 +49,10 @@ else() message(STATUS "Using the single-header code from ${NLOHMANN_JSON_INCLUDE_BUILD_DIR}") endif() +if (NOT JSON_ImplicitConversions) + message(STATUS "Implicit conversions are disabled") +endif() + ## ## TARGET ## create target and add include path diff --git a/Makefile b/Makefile index fd73a3389..9d26bc9d8 100644 --- a/Makefile +++ b/Makefile @@ -54,13 +54,13 @@ all: ########################################################################## coverage: - rm -fr build_coverage - mkdir build_coverage - cd build_coverage ; cmake .. -GNinja -DCMAKE_BUILD_TYPE=Debug -DJSON_Coverage=ON -DJSON_MultipleHeaders=ON - cd build_coverage ; ninja - cd build_coverage ; ctest -j10 - cd build_coverage ; ninja lcov_html - open build_coverage/test/html/index.html + rm -fr cmake-build-coverage + mkdir cmake-build-coverage + cd cmake-build-coverage ; cmake .. -GNinja -DCMAKE_BUILD_TYPE=Debug -DJSON_Coverage=ON -DJSON_MultipleHeaders=ON + cd cmake-build-coverage ; ninja + cd cmake-build-coverage ; ctest -j10 + cd cmake-build-coverage ; ninja lcov_html + open cmake-build-coverage/test/html/index.html ########################################################################## # documentation tests @@ -88,7 +88,7 @@ doctest: # -Wno-switch-enum -Wno-covered-switch-default: pedantic/contradicting warnings about switches # -Wno-weak-vtables: exception class is defined inline, but has virtual method pedantic_clang: - rm -fr build_pedantic + rm -fr cmake-build-pedantic CXXFLAGS=" \ -std=c++11 -Wno-c++98-compat -Wno-c++98-compat-pedantic \ -Werror \ @@ -103,12 +103,12 @@ pedantic_clang: -Wno-padded \ -Wno-range-loop-analysis \ -Wno-switch-enum -Wno-covered-switch-default \ - -Wno-weak-vtables" cmake -S . -B build_pedantic -GNinja -DCMAKE_BUILD_TYPE=Debug -DJSON_MultipleHeaders=ON -DJSON_BuildTests=On - cmake --build build_pedantic + -Wno-weak-vtables" cmake -S . -B cmake-build-pedantic -GNinja -DCMAKE_BUILD_TYPE=Debug -DJSON_MultipleHeaders=ON -DJSON_BuildTests=On + cmake --build cmake-build-pedantic # calling GCC with most warnings pedantic_gcc: - rm -fr build_pedantic + rm -fr cmake-build-pedantic CXXFLAGS=" \ -std=c++11 \ -pedantic \ @@ -366,19 +366,19 @@ pedantic_gcc: -Wwrite-strings \ -Wzero-as-null-pointer-constant \ -Wzero-length-bounds \ - " cmake -S . -B build_pedantic -GNinja -DCMAKE_BUILD_TYPE=Debug -DJSON_MultipleHeaders=ON -DJSON_BuildTests=On - cmake --build build_pedantic + " cmake -S . -B cmake-build-pedantic -GNinja -DCMAKE_BUILD_TYPE=Debug -DJSON_MultipleHeaders=ON -DJSON_BuildTests=On + cmake --build cmake-build-pedantic ########################################################################## # benchmarks ########################################################################## run_benchmarks: - rm -fr build_benchmarks - mkdir build_benchmarks - cd build_benchmarks ; cmake ../benchmarks -GNinja -DCMAKE_BUILD_TYPE=Release -DJSON_BuildTests=On - cd build_benchmarks ; ninja - cd build_benchmarks ; ./json_benchmarks + rm -fr cmake-build-benchmarks + mkdir cmake-build-benchmarks + cd cmake-build-benchmarks ; cmake ../benchmarks -GNinja -DCMAKE_BUILD_TYPE=Release -DJSON_BuildTests=On + cd cmake-build-benchmarks ; ninja + cd cmake-build-benchmarks ; ./json_benchmarks ########################################################################## # fuzzing @@ -451,14 +451,14 @@ cppcheck: # call Clang Static Analyzer clang_analyze: - rm -fr clang_analyze_build - mkdir clang_analyze_build - cd clang_analyze_build ; CCC_CXX=$(COMPILER_DIR)/clang++ CXX=$(COMPILER_DIR)/clang++ $(COMPILER_DIR)/scan-build cmake .. -GNinja -DJSON_BuildTests=On - cd clang_analyze_build ; \ + rm -fr cmake-build-clang-analyze + mkdir cmake-build-clang-analyze + cd cmake-build-clang-analyze ; CCC_CXX=$(COMPILER_DIR)/clang++ CXX=$(COMPILER_DIR)/clang++ $(COMPILER_DIR)/scan-build cmake .. -GNinja -DJSON_BuildTests=On + cd cmake-build-clang-analyze ; \ $(COMPILER_DIR)/scan-build \ -enable-checker alpha.core.BoolAssignment,alpha.core.CallAndMessageUnInitRefArg,alpha.core.CastSize,alpha.core.CastToStruct,alpha.core.Conversion,alpha.core.DynamicTypeChecker,alpha.core.FixedAddr,alpha.core.PointerArithm,alpha.core.PointerSub,alpha.core.SizeofPtr,alpha.core.StackAddressAsyncEscape,alpha.core.TestAfterDivZero,alpha.deadcode.UnreachableCode,core.builtin.BuiltinFunctions,core.builtin.NoReturnFunctions,core.CallAndMessage,core.DivideZero,core.DynamicTypePropagation,core.NonnilStringConstants,core.NonNullParamChecker,core.NullDereference,core.StackAddressEscape,core.UndefinedBinaryOperatorResult,core.uninitialized.ArraySubscript,core.uninitialized.Assign,core.uninitialized.Branch,core.uninitialized.CapturedBlockVariable,core.uninitialized.UndefReturn,core.VLASize,cplusplus.InnerPointer,cplusplus.Move,cplusplus.NewDelete,cplusplus.NewDeleteLeaks,cplusplus.SelfAssignment,deadcode.DeadStores,nullability.NullableDereferenced,nullability.NullablePassedToNonnull,nullability.NullableReturnedFromNonnull,nullability.NullPassedToNonnull,nullability.NullReturnedFromNonnull \ --use-c++=$(COMPILER_DIR)/clang++ -analyze-headers -o report ninja - open clang_analyze_build/report/*/index.html + open cmake-build-clang-analyze/report/*/index.html # call cpplint # Note: some errors expected due to false positives @@ -473,18 +473,18 @@ clang_tidy: # call PVS-Studio Analyzer pvs_studio: - rm -fr pvs_studio_build - mkdir pvs_studio_build - cd pvs_studio_build ; cmake .. -DCMAKE_EXPORT_COMPILE_COMMANDS=On -DJSON_MultipleHeaders=ON - cd pvs_studio_build ; pvs-studio-analyzer analyze -j 10 - cd pvs_studio_build ; plog-converter -a'GA:1,2;64:1;CS' -t fullhtml PVS-Studio.log -o pvs - open pvs_studio_build/pvs/index.html + rm -fr cmake-build-pvs-studio + mkdir cmake-build-pvs-studio + cd cmake-build-pvs-studio ; cmake .. -DCMAKE_EXPORT_COMPILE_COMMANDS=On -DJSON_MultipleHeaders=ON + cd cmake-build-pvs-studio ; pvs-studio-analyzer analyze -j 10 + cd cmake-build-pvs-studio ; plog-converter -a'GA:1,2;64:1;CS' -t fullhtml PVS-Studio.log -o pvs + open cmake-build-pvs-studio/pvs/index.html # call Infer static analyzer infer: - rm -fr infer_build - mkdir infer_build - cd infer_build ; infer compile -- cmake .. -DJSON_MultipleHeaders=ON ; infer run -- make -j 4 + rm -fr cmake-build-infer + mkdir cmake-build-infer + cd cmake-build-infer ; infer compile -- cmake .. -DJSON_MultipleHeaders=ON ; infer run -- make -j 4 # call OCLint static analyzer oclint: @@ -493,11 +493,11 @@ oclint: # execute the test suite with Clang sanitizers (address and undefined behavior) clang_sanitize: - rm -fr clang_sanitize_build - mkdir clang_sanitize_build - cd clang_sanitize_build ; CXX=$(COMPILER_DIR)/clang++ cmake .. -DJSON_Sanitizer=On -DJSON_MultipleHeaders=ON -DJSON_BuildTests=On -GNinja - cd clang_sanitize_build ; ninja - cd clang_sanitize_build ; ctest -j10 + rm -fr cmake-build-clang-sanitize + mkdir cmake-build-clang-sanitize + cd cmake-build-clang-sanitize ; CXX=$(COMPILER_DIR)/clang++ cmake .. -DJSON_Sanitizer=On -DJSON_MultipleHeaders=ON -DJSON_BuildTests=On -GNinja + cd cmake-build-clang-sanitize ; ninja + cd cmake-build-clang-sanitize ; ctest -j10 ########################################################################## @@ -525,7 +525,7 @@ pretty: --preserve-date \ --suffix=none \ --formatted \ - $(SRCS) $(AMALGAMATED_FILE) test/src/*.cpp benchmarks/src/benchmarks.cpp doc/examples/*.cpp + $(SRCS) $(AMALGAMATED_FILE) test/src/*.cpp test/utils/*.hpp benchmarks/src/benchmarks.cpp doc/examples/*.cpp # create single header file amalgamate: $(AMALGAMATED_FILE) @@ -625,7 +625,7 @@ clean: rm -fr json_unit json_benchmarks fuzz fuzz-testing *.dSYM test/*.dSYM oclint_report.html rm -fr benchmarks/files/numbers/*.json rm -fr cmake-3.1.0-Darwin64.tar.gz cmake-3.1.0-Darwin64 - rm -fr build_coverage build_benchmarks fuzz-testing clang_analyze_build pvs_studio_build infer_build clang_sanitize_build cmake_build + rm -fr cmake-build-coverage cmake-build-benchmarks fuzz-testing cmake-build-clang-analyze cmake-build-pvs-studio cmake-build-infer cmake-build-clang-sanitize cmake_build $(MAKE) clean -Cdoc ########################################################################## diff --git a/README.md b/README.md index c1463349e..eb9c268e9 100644 --- a/README.md +++ b/README.md @@ -762,6 +762,7 @@ Supported types can be implicitly converted to JSON values. It is recommended to **NOT USE** implicit conversions **FROM** a JSON value. You can find more details about this recommendation [here](https://www.github.com/nlohmann/json/issues/958). +You can switch off implicit conversions by defining `JSON_USE_IMPLICIT_CONVERSIONS` to `0` before including the `json.hpp` header. When using CMake, you can also achieve this by setting the option `JSON_ImplicitConversions` to `OFF`. ```cpp // strings diff --git a/doc/mkdocs/docs/features/arbitrary_types.md b/doc/mkdocs/docs/features/arbitrary_types.md index 7bd7adf7d..23913bba2 100644 --- a/doc/mkdocs/docs/features/arbitrary_types.md +++ b/doc/mkdocs/docs/features/arbitrary_types.md @@ -92,6 +92,10 @@ There are two macros to make your life easier as long as you (1) want to use a J In both macros, the first parameter is the name of the class/struct, and all remaining parameters name the members. +!!! note + + At most 64 member variables can be passed to `NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE` or `NLOHMANN_DEFINE_TYPE_INTRUSIVE`. + ??? example The `to_json`/`from_json` functions for the `person` struct above can be created with: diff --git a/doc/mkdocs/docs/features/macros.md b/doc/mkdocs/docs/features/macros.md index 7147be7e1..48a5159b4 100644 --- a/doc/mkdocs/docs/features/macros.md +++ b/doc/mkdocs/docs/features/macros.md @@ -32,6 +32,26 @@ This macro overrides `#!cpp try` calls inside the library. It has no arguments a See [Switch off exceptions](../home/exceptions.md#switch-off-exceptions) for an example. +## `JSON_USE_IMPLICIT_CONVERSIONS` + +When defined to `0`, implicit conversions are switched off. By default, implicit conversions are switched on. + +??? example + + This is an example for an implicit conversion: + + ```cpp + json j = "Hello, world!"; + std::string s = j; + ``` + + When `JSON_USE_IMPLICIT_CONVERSIONS` is defined to `0`, the code above does no longer compile. Instead, it must be written like this: + + ```cpp + json j = "Hello, world!"; + auto s = j.get(); + ``` + ## `NLOHMANN_DEFINE_TYPE_INTRUSIVE(type, member...)` This macro can be used to simplify the serialization/deserialization of types if (1) want to use a JSON object as serialization and (2) want to use the member variable names as object keys in that object. diff --git a/include/nlohmann/detail/input/binary_reader.hpp b/include/nlohmann/detail/input/binary_reader.hpp index fc6791ec9..4c94d1ccf 100644 --- a/include/nlohmann/detail/input/binary_reader.hpp +++ b/include/nlohmann/detail/input/binary_reader.hpp @@ -394,14 +394,14 @@ class binary_reader /*! @param[in] get_char whether a new character should be retrieved from the - input (true, default) or whether the last read - character should be considered instead + input (true) or whether the last read character should + be considered instead (false) @param[in] tag_handler how CBOR tags should be treated @return whether a valid CBOR value was passed to the SAX parser */ - bool parse_cbor_internal(const bool get_char = true, - cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error) + bool parse_cbor_internal(const bool get_char, + const cbor_tag_handler_t tag_handler) { switch (get_char ? get() : current) { @@ -607,34 +607,34 @@ class binary_reader case 0x95: case 0x96: case 0x97: - return get_cbor_array(static_cast(static_cast(current) & 0x1Fu)); + return get_cbor_array(static_cast(static_cast(current) & 0x1Fu), tag_handler); case 0x98: // array (one-byte uint8_t for n follows) { std::uint8_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); } case 0x99: // array (two-byte uint16_t for n follow) { std::uint16_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); } case 0x9A: // array (four-byte uint32_t for n follow) { std::uint32_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); } case 0x9B: // array (eight-byte uint64_t for n follow) { std::uint64_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); } case 0x9F: // array (indefinite length) - return get_cbor_array(std::size_t(-1)); + return get_cbor_array(std::size_t(-1), tag_handler); // map (0x00..0x17 pairs of data items follow) case 0xA0: @@ -661,34 +661,34 @@ class binary_reader case 0xB5: case 0xB6: case 0xB7: - return get_cbor_object(static_cast(static_cast(current) & 0x1Fu)); + return get_cbor_object(static_cast(static_cast(current) & 0x1Fu), tag_handler); case 0xB8: // map (one-byte uint8_t for n follows) { std::uint8_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); } case 0xB9: // map (two-byte uint16_t for n follow) { std::uint16_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); } case 0xBA: // map (four-byte uint32_t for n follow) { std::uint32_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); } case 0xBB: // map (eight-byte uint64_t for n follow) { std::uint64_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); } case 0xBF: // map (indefinite length) - return get_cbor_object(std::size_t(-1)); + return get_cbor_object(std::size_t(-1), tag_handler); case 0xC6: // tagged item case 0xC7: @@ -1031,9 +1031,11 @@ class binary_reader /*! @param[in] len the length of the array or std::size_t(-1) for an array of indefinite size + @param[in] tag_handler how CBOR tags should be treated @return whether array creation completed */ - bool get_cbor_array(const std::size_t len) + bool get_cbor_array(const std::size_t len, + const cbor_tag_handler_t tag_handler) { if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len))) { @@ -1044,7 +1046,7 @@ class binary_reader { for (std::size_t i = 0; i < len; ++i) { - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal())) + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(true, tag_handler))) { return false; } @@ -1054,7 +1056,7 @@ class binary_reader { while (get() != 0xFF) { - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(false))) + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(false, tag_handler))) { return false; } @@ -1067,9 +1069,11 @@ class binary_reader /*! @param[in] len the length of the object or std::size_t(-1) for an object of indefinite size + @param[in] tag_handler how CBOR tags should be treated @return whether object creation completed */ - bool get_cbor_object(const std::size_t len) + bool get_cbor_object(const std::size_t len, + const cbor_tag_handler_t tag_handler) { if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len))) { @@ -1087,7 +1091,7 @@ class binary_reader return false; } - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal())) + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(true, tag_handler))) { return false; } @@ -1103,7 +1107,7 @@ class binary_reader return false; } - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal())) + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(true, tag_handler))) { return false; } diff --git a/include/nlohmann/detail/macro_scope.hpp b/include/nlohmann/detail/macro_scope.hpp index c32a46d17..8c9f63296 100644 --- a/include/nlohmann/detail/macro_scope.hpp +++ b/include/nlohmann/detail/macro_scope.hpp @@ -264,8 +264,8 @@ #define NLOHMANN_JSON_PASTE63(func, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62) NLOHMANN_JSON_PASTE2(func, v1) NLOHMANN_JSON_PASTE62(func, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62) #define NLOHMANN_JSON_PASTE64(func, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62, v63) NLOHMANN_JSON_PASTE2(func, v1) NLOHMANN_JSON_PASTE63(func, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62, v63) -#define NLOHMANN_JSON_TO(v1) j[#v1] = t.v1; -#define NLOHMANN_JSON_FROM(v1) j.at(#v1).get_to(t.v1); +#define NLOHMANN_JSON_TO(v1) nlohmann_json_j[#v1] = nlohmann_json_t.v1; +#define NLOHMANN_JSON_FROM(v1) nlohmann_json_j.at(#v1).get_to(nlohmann_json_t.v1); /*! @brief macro @@ -273,8 +273,8 @@ @since version 3.9.0 */ #define NLOHMANN_DEFINE_TYPE_INTRUSIVE(Type, ...) \ - friend void to_json(nlohmann::json& j, const Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ - friend void from_json(const nlohmann::json& j, Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } + friend void to_json(nlohmann::json& nlohmann_json_j, const Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ + friend void from_json(const nlohmann::json& nlohmann_json_j, Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } /*! @brief macro @@ -282,8 +282,8 @@ @since version 3.9.0 */ #define NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE(Type, ...) \ - void to_json(nlohmann::json& j, const Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ - void from_json(const nlohmann::json& j, Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } + inline void to_json(nlohmann::json& nlohmann_json_j, const Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ + inline void from_json(const nlohmann::json& nlohmann_json_j, Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } #ifndef JSON_USE_IMPLICIT_CONVERSIONS #define JSON_USE_IMPLICIT_CONVERSIONS 1 diff --git a/single_include/nlohmann/json.hpp b/single_include/nlohmann/json.hpp index 9770712a6..68198efb5 100644 --- a/single_include/nlohmann/json.hpp +++ b/single_include/nlohmann/json.hpp @@ -2281,8 +2281,8 @@ JSON_HEDLEY_DIAGNOSTIC_POP #define NLOHMANN_JSON_PASTE63(func, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62) NLOHMANN_JSON_PASTE2(func, v1) NLOHMANN_JSON_PASTE62(func, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62) #define NLOHMANN_JSON_PASTE64(func, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62, v63) NLOHMANN_JSON_PASTE2(func, v1) NLOHMANN_JSON_PASTE63(func, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28, v29, v30, v31, v32, v33, v34, v35, v36, v37, v38, v39, v40, v41, v42, v43, v44, v45, v46, v47, v48, v49, v50, v51, v52, v53, v54, v55, v56, v57, v58, v59, v60, v61, v62, v63) -#define NLOHMANN_JSON_TO(v1) j[#v1] = t.v1; -#define NLOHMANN_JSON_FROM(v1) j.at(#v1).get_to(t.v1); +#define NLOHMANN_JSON_TO(v1) nlohmann_json_j[#v1] = nlohmann_json_t.v1; +#define NLOHMANN_JSON_FROM(v1) nlohmann_json_j.at(#v1).get_to(nlohmann_json_t.v1); /*! @brief macro @@ -2290,8 +2290,8 @@ JSON_HEDLEY_DIAGNOSTIC_POP @since version 3.9.0 */ #define NLOHMANN_DEFINE_TYPE_INTRUSIVE(Type, ...) \ - friend void to_json(nlohmann::json& j, const Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ - friend void from_json(const nlohmann::json& j, Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } + friend void to_json(nlohmann::json& nlohmann_json_j, const Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ + friend void from_json(const nlohmann::json& nlohmann_json_j, Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } /*! @brief macro @@ -2299,8 +2299,8 @@ JSON_HEDLEY_DIAGNOSTIC_POP @since version 3.9.0 */ #define NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE(Type, ...) \ - void to_json(nlohmann::json& j, const Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ - void from_json(const nlohmann::json& j, Type& t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } + inline void to_json(nlohmann::json& nlohmann_json_j, const Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_TO, __VA_ARGS__)) } \ + inline void from_json(const nlohmann::json& nlohmann_json_j, Type& nlohmann_json_t) { NLOHMANN_JSON_EXPAND(NLOHMANN_JSON_PASTE(NLOHMANN_JSON_FROM, __VA_ARGS__)) } #ifndef JSON_USE_IMPLICIT_CONVERSIONS #define JSON_USE_IMPLICIT_CONVERSIONS 1 @@ -2403,7 +2403,6 @@ json.exception.parse_error.110 | parse error at 1: cannot read 2 bytes from vect json.exception.parse_error.112 | parse error at 1: error reading CBOR; last byte: 0xF8 | Not all types of CBOR or MessagePack are supported. This exception occurs if an unsupported byte was read. json.exception.parse_error.113 | parse error at 2: expected a CBOR string; last byte: 0x98 | While parsing a map key, a value that is not a string has been read. json.exception.parse_error.114 | parse error: Unsupported BSON record type 0x0F | The parsing of the corresponding BSON record type is not implemented (yet). -json.exception.parse_error.115 | parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text: 1A | A UBJSON high-precision number could not be parsed. @note For an input with n bytes, 1 is the index of the first character and n+1 is the index of the terminating null byte or the end of file. This also @@ -2592,7 +2591,7 @@ json.exception.out_of_range.403 | key 'foo' not found | The provided key was not json.exception.out_of_range.404 | unresolved reference token 'foo' | A reference token in a JSON Pointer could not be resolved. json.exception.out_of_range.405 | JSON pointer has no parent | The JSON Patch operations 'remove' and 'add' can not be applied to the root element of the JSON value. json.exception.out_of_range.406 | number overflow parsing '10E1000' | A parsed number could not be stored as without changing it to NaN or INF. -json.exception.out_of_range.407 | number overflow serializing '9223372036854775808' | UBJSON and BSON only support integer numbers up to 9223372036854775807. (until version 3.8.0) | +json.exception.out_of_range.407 | number overflow serializing '9223372036854775808' | UBJSON and BSON only support integer numbers up to 9223372036854775807. | json.exception.out_of_range.408 | excessive array size: 8658170730974374167 | The size (following `#`) of an UBJSON array or object exceeds the maximal capacity. | json.exception.out_of_range.409 | BSON key cannot contain code point U+0000 (at byte 2) | Key identifiers to be serialized to BSON cannot contain code point U+0000, since the key is stored as zero-terminated c-string | @@ -5871,6 +5870,2550 @@ class json_sax_acceptor } // namespace nlohmann +// #include + +// #include + + +#include // size_t +#include // declval +#include // string + +// #include + +// #include + + +namespace nlohmann +{ +namespace detail +{ +template +using null_function_t = decltype(std::declval().null()); + +template +using boolean_function_t = + decltype(std::declval().boolean(std::declval())); + +template +using number_integer_function_t = + decltype(std::declval().number_integer(std::declval())); + +template +using number_unsigned_function_t = + decltype(std::declval().number_unsigned(std::declval())); + +template +using number_float_function_t = decltype(std::declval().number_float( + std::declval(), std::declval())); + +template +using string_function_t = + decltype(std::declval().string(std::declval())); + +template +using binary_function_t = + decltype(std::declval().binary(std::declval())); + +template +using start_object_function_t = + decltype(std::declval().start_object(std::declval())); + +template +using key_function_t = + decltype(std::declval().key(std::declval())); + +template +using end_object_function_t = decltype(std::declval().end_object()); + +template +using start_array_function_t = + decltype(std::declval().start_array(std::declval())); + +template +using end_array_function_t = decltype(std::declval().end_array()); + +template +using parse_error_function_t = decltype(std::declval().parse_error( + std::declval(), std::declval(), + std::declval())); + +template +struct is_sax +{ + private: + static_assert(is_basic_json::value, + "BasicJsonType must be of type basic_json<...>"); + + using number_integer_t = typename BasicJsonType::number_integer_t; + using number_unsigned_t = typename BasicJsonType::number_unsigned_t; + using number_float_t = typename BasicJsonType::number_float_t; + using string_t = typename BasicJsonType::string_t; + using binary_t = typename BasicJsonType::binary_t; + using exception_t = typename BasicJsonType::exception; + + public: + static constexpr bool value = + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value && + is_detected_exact::value; +}; + +template +struct is_sax_static_asserts +{ + private: + static_assert(is_basic_json::value, + "BasicJsonType must be of type basic_json<...>"); + + using number_integer_t = typename BasicJsonType::number_integer_t; + using number_unsigned_t = typename BasicJsonType::number_unsigned_t; + using number_float_t = typename BasicJsonType::number_float_t; + using string_t = typename BasicJsonType::string_t; + using binary_t = typename BasicJsonType::binary_t; + using exception_t = typename BasicJsonType::exception; + + public: + static_assert(is_detected_exact::value, + "Missing/invalid function: bool null()"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool boolean(bool)"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool boolean(bool)"); + static_assert( + is_detected_exact::value, + "Missing/invalid function: bool number_integer(number_integer_t)"); + static_assert( + is_detected_exact::value, + "Missing/invalid function: bool number_unsigned(number_unsigned_t)"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool number_float(number_float_t, const string_t&)"); + static_assert( + is_detected_exact::value, + "Missing/invalid function: bool string(string_t&)"); + static_assert( + is_detected_exact::value, + "Missing/invalid function: bool binary(binary_t&)"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool start_object(std::size_t)"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool key(string_t&)"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool end_object()"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool start_array(std::size_t)"); + static_assert(is_detected_exact::value, + "Missing/invalid function: bool end_array()"); + static_assert( + is_detected_exact::value, + "Missing/invalid function: bool parse_error(std::size_t, const " + "std::string&, const exception&)"); +}; +} // namespace detail +} // namespace nlohmann + +// #include + + +namespace nlohmann +{ +namespace detail +{ + +/// how to treat CBOR tags +enum class cbor_tag_handler_t +{ + error, ///< throw a parse_error exception in case of a tag + ignore ///< ignore tags +}; + +/*! +@brief determine system byte order + +@return true if and only if system's byte order is little endian + +@note from https://stackoverflow.com/a/1001328/266378 +*/ +static inline bool little_endianess(int num = 1) noexcept +{ + return *reinterpret_cast(&num) == 1; +} + + +/////////////////// +// binary reader // +/////////////////// + +/*! +@brief deserialization of CBOR, MessagePack, and UBJSON values +*/ +template> +class binary_reader +{ + using number_integer_t = typename BasicJsonType::number_integer_t; + using number_unsigned_t = typename BasicJsonType::number_unsigned_t; + using number_float_t = typename BasicJsonType::number_float_t; + using string_t = typename BasicJsonType::string_t; + using binary_t = typename BasicJsonType::binary_t; + using json_sax_t = SAX; + using char_type = typename InputAdapterType::char_type; + using char_int_type = typename std::char_traits::int_type; + + public: + /*! + @brief create a binary reader + + @param[in] adapter input adapter to read from + */ + explicit binary_reader(InputAdapterType&& adapter) : ia(std::move(adapter)) + { + (void)detail::is_sax_static_asserts {}; + } + + // make class move-only + binary_reader(const binary_reader&) = delete; + binary_reader(binary_reader&&) = default; + binary_reader& operator=(const binary_reader&) = delete; + binary_reader& operator=(binary_reader&&) = default; + ~binary_reader() = default; + + /*! + @param[in] format the binary format to parse + @param[in] sax_ a SAX event processor + @param[in] strict whether to expect the input to be consumed completed + @param[in] tag_handler how to treat CBOR tags + + @return + */ + JSON_HEDLEY_NON_NULL(3) + bool sax_parse(const input_format_t format, + json_sax_t* sax_, + const bool strict = true, + const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error) + { + sax = sax_; + bool result = false; + + switch (format) + { + case input_format_t::bson: + result = parse_bson_internal(); + break; + + case input_format_t::cbor: + result = parse_cbor_internal(true, tag_handler); + break; + + case input_format_t::msgpack: + result = parse_msgpack_internal(); + break; + + case input_format_t::ubjson: + result = parse_ubjson_internal(); + break; + + default: // LCOV_EXCL_LINE + JSON_ASSERT(false); // LCOV_EXCL_LINE + } + + // strict mode: next byte must be EOF + if (result && strict) + { + if (format == input_format_t::ubjson) + { + get_ignore_noop(); + } + else + { + get(); + } + + if (JSON_HEDLEY_UNLIKELY(current != std::char_traits::eof())) + { + return sax->parse_error(chars_read, get_token_string(), + parse_error::create(110, chars_read, exception_message(format, "expected end of input; last byte: 0x" + get_token_string(), "value"))); + } + } + + return result; + } + + private: + ////////// + // BSON // + ////////// + + /*! + @brief Reads in a BSON-object and passes it to the SAX-parser. + @return whether a valid BSON-value was passed to the SAX parser + */ + bool parse_bson_internal() + { + std::int32_t document_size{}; + get_number(input_format_t::bson, document_size); + + if (JSON_HEDLEY_UNLIKELY(!sax->start_object(std::size_t(-1)))) + { + return false; + } + + if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_list(/*is_array*/false))) + { + return false; + } + + return sax->end_object(); + } + + /*! + @brief Parses a C-style string from the BSON input. + @param[in, out] result A reference to the string variable where the read + string is to be stored. + @return `true` if the \x00-byte indicating the end of the string was + encountered before the EOF; false` indicates an unexpected EOF. + */ + bool get_bson_cstr(string_t& result) + { + auto out = std::back_inserter(result); + while (true) + { + get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::bson, "cstring"))) + { + return false; + } + if (current == 0x00) + { + return true; + } + *out++ = static_cast(current); + } + } + + /*! + @brief Parses a zero-terminated string of length @a len from the BSON + input. + @param[in] len The length (including the zero-byte at the end) of the + string to be read. + @param[in, out] result A reference to the string variable where the read + string is to be stored. + @tparam NumberType The type of the length @a len + @pre len >= 1 + @return `true` if the string was successfully parsed + */ + template + bool get_bson_string(const NumberType len, string_t& result) + { + 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(input_format_t::bson, "string length must be at least 1, is " + std::to_string(len), "string"))); + } + + return get_string(input_format_t::bson, len - static_cast(1), result) && get() != std::char_traits::eof(); + } + + /*! + @brief Parses a byte array input of length @a len from the BSON input. + @param[in] len The length of the byte array to be read. + @param[in, out] result A reference to the binary variable where the read + array is to be stored. + @tparam NumberType The type of the length @a len + @pre len >= 0 + @return `true` if the byte array was successfully parsed + */ + template + bool get_bson_binary(const NumberType len, binary_t& result) + { + 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(input_format_t::bson, "byte array length cannot be negative, is " + std::to_string(len), "binary"))); + } + + // All BSON binary values have a subtype + std::uint8_t subtype{}; + get_number(input_format_t::bson, subtype); + result.set_subtype(subtype); + + return get_binary(input_format_t::bson, len, result); + } + + /*! + @brief Read a BSON document element of the given @a element_type. + @param[in] element_type The BSON element type, c.f. http://bsonspec.org/spec.html + @param[in] element_type_parse_position The position in the input stream, + where the `element_type` was read. + @warning Not all BSON element types are supported yet. An unsupported + @a element_type will give rise to a parse_error.114: + Unsupported BSON record type 0x... + @return whether a valid BSON-object/array was passed to the SAX parser + */ + bool parse_bson_element_internal(const char_int_type element_type, + const std::size_t element_type_parse_position) + { + switch (element_type) + { + case 0x01: // double + { + double number{}; + return get_number(input_format_t::bson, number) && sax->number_float(static_cast(number), ""); + } + + case 0x02: // string + { + std::int32_t len{}; + string_t value; + return get_number(input_format_t::bson, len) && get_bson_string(len, value) && sax->string(value); + } + + case 0x03: // object + { + return parse_bson_internal(); + } + + case 0x04: // array + { + return parse_bson_array(); + } + + case 0x05: // binary + { + std::int32_t len{}; + binary_t value; + return get_number(input_format_t::bson, len) && get_bson_binary(len, value) && sax->binary(value); + } + + case 0x08: // boolean + { + return sax->boolean(get() != 0); + } + + case 0x0A: // null + { + return sax->null(); + } + + case 0x10: // int32 + { + std::int32_t value{}; + return get_number(input_format_t::bson, value) && sax->number_integer(value); + } + + case 0x12: // int64 + { + std::int64_t value{}; + return get_number(input_format_t::bson, value) && sax->number_integer(value); + } + + default: // anything else not supported (yet) + { + std::array cr{{}}; + (std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast(element_type)); + return sax->parse_error(element_type_parse_position, std::string(cr.data()), parse_error::create(114, element_type_parse_position, "Unsupported BSON record type 0x" + std::string(cr.data()))); + } + } + } + + /*! + @brief Read a BSON element list (as specified in the BSON-spec) + + The same binary layout is used for objects and arrays, hence it must be + indicated with the argument @a is_array which one is expected + (true --> array, false --> object). + + @param[in] is_array Determines if the element list being read is to be + treated as an object (@a is_array == false), or as an + array (@a is_array == true). + @return whether a valid BSON-object/array was passed to the SAX parser + */ + bool parse_bson_element_list(const bool is_array) + { + string_t key; + + while (auto element_type = get()) + { + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::bson, "element list"))) + { + return false; + } + + const std::size_t element_type_parse_position = chars_read; + if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key))) + { + return false; + } + + if (!is_array && !sax->key(key)) + { + return false; + } + + if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_internal(element_type, element_type_parse_position))) + { + return false; + } + + // get_bson_cstr only appends + key.clear(); + } + + return true; + } + + /*! + @brief Reads an array from the BSON input and passes it to the SAX-parser. + @return whether a valid BSON-array was passed to the SAX parser + */ + bool parse_bson_array() + { + std::int32_t document_size{}; + get_number(input_format_t::bson, document_size); + + if (JSON_HEDLEY_UNLIKELY(!sax->start_array(std::size_t(-1)))) + { + return false; + } + + if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_list(/*is_array*/true))) + { + return false; + } + + return sax->end_array(); + } + + ////////// + // CBOR // + ////////// + + /*! + @param[in] get_char whether a new character should be retrieved from the + input (true) or whether the last read character should + be considered instead (false) + @param[in] tag_handler how CBOR tags should be treated + + @return whether a valid CBOR value was passed to the SAX parser + */ + bool parse_cbor_internal(const bool get_char, + const cbor_tag_handler_t tag_handler) + { + switch (get_char ? get() : current) + { + // EOF + case std::char_traits::eof(): + return unexpect_eof(input_format_t::cbor, "value"); + + // Integer 0x00..0x17 (0..23) + case 0x00: + case 0x01: + case 0x02: + case 0x03: + case 0x04: + case 0x05: + case 0x06: + case 0x07: + case 0x08: + case 0x09: + case 0x0A: + case 0x0B: + case 0x0C: + case 0x0D: + case 0x0E: + case 0x0F: + case 0x10: + case 0x11: + case 0x12: + case 0x13: + case 0x14: + case 0x15: + case 0x16: + case 0x17: + return sax->number_unsigned(static_cast(current)); + + case 0x18: // Unsigned integer (one-byte uint8_t follows) + { + std::uint8_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); + } + + case 0x19: // Unsigned integer (two-byte uint16_t follows) + { + std::uint16_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); + } + + case 0x1A: // Unsigned integer (four-byte uint32_t follows) + { + std::uint32_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); + } + + case 0x1B: // Unsigned integer (eight-byte uint64_t follows) + { + std::uint64_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); + } + + // Negative integer -1-0x00..-1-0x17 (-1..-24) + case 0x20: + case 0x21: + case 0x22: + case 0x23: + case 0x24: + case 0x25: + case 0x26: + case 0x27: + case 0x28: + case 0x29: + case 0x2A: + case 0x2B: + case 0x2C: + case 0x2D: + case 0x2E: + case 0x2F: + case 0x30: + case 0x31: + case 0x32: + case 0x33: + case 0x34: + case 0x35: + case 0x36: + case 0x37: + return sax->number_integer(static_cast(0x20 - 1 - current)); + + case 0x38: // Negative integer (one-byte uint8_t follows) + { + std::uint8_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - number); + } + + case 0x39: // Negative integer -1-n (two-byte uint16_t follows) + { + std::uint16_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - number); + } + + case 0x3A: // Negative integer -1-n (four-byte uint32_t follows) + { + std::uint32_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - number); + } + + case 0x3B: // Negative integer -1-n (eight-byte uint64_t follows) + { + std::uint64_t number{}; + return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) + - static_cast(number)); + } + + // Binary data (0x00..0x17 bytes follow) + case 0x40: + case 0x41: + case 0x42: + case 0x43: + case 0x44: + case 0x45: + case 0x46: + case 0x47: + case 0x48: + case 0x49: + case 0x4A: + case 0x4B: + case 0x4C: + case 0x4D: + case 0x4E: + case 0x4F: + case 0x50: + case 0x51: + case 0x52: + case 0x53: + case 0x54: + case 0x55: + case 0x56: + case 0x57: + case 0x58: // Binary data (one-byte uint8_t for n follows) + case 0x59: // Binary data (two-byte uint16_t for n follow) + case 0x5A: // Binary data (four-byte uint32_t for n follow) + case 0x5B: // Binary data (eight-byte uint64_t for n follow) + case 0x5F: // Binary data (indefinite length) + { + binary_t b; + return get_cbor_binary(b) && sax->binary(b); + } + + // UTF-8 string (0x00..0x17 bytes follow) + case 0x60: + case 0x61: + case 0x62: + case 0x63: + case 0x64: + case 0x65: + case 0x66: + case 0x67: + case 0x68: + case 0x69: + case 0x6A: + case 0x6B: + case 0x6C: + case 0x6D: + case 0x6E: + case 0x6F: + case 0x70: + case 0x71: + case 0x72: + case 0x73: + case 0x74: + case 0x75: + case 0x76: + case 0x77: + case 0x78: // UTF-8 string (one-byte uint8_t for n follows) + case 0x79: // UTF-8 string (two-byte uint16_t for n follow) + case 0x7A: // UTF-8 string (four-byte uint32_t for n follow) + case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow) + case 0x7F: // UTF-8 string (indefinite length) + { + string_t s; + return get_cbor_string(s) && sax->string(s); + } + + // array (0x00..0x17 data items follow) + case 0x80: + case 0x81: + case 0x82: + case 0x83: + case 0x84: + case 0x85: + case 0x86: + case 0x87: + case 0x88: + case 0x89: + case 0x8A: + case 0x8B: + case 0x8C: + case 0x8D: + case 0x8E: + case 0x8F: + case 0x90: + case 0x91: + case 0x92: + case 0x93: + case 0x94: + case 0x95: + case 0x96: + case 0x97: + return get_cbor_array(static_cast(static_cast(current) & 0x1Fu), tag_handler); + + case 0x98: // array (one-byte uint8_t for n follows) + { + std::uint8_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); + } + + case 0x99: // array (two-byte uint16_t for n follow) + { + std::uint16_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); + } + + case 0x9A: // array (four-byte uint32_t for n follow) + { + std::uint32_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); + } + + case 0x9B: // array (eight-byte uint64_t for n follow) + { + std::uint64_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len), tag_handler); + } + + case 0x9F: // array (indefinite length) + return get_cbor_array(std::size_t(-1), tag_handler); + + // map (0x00..0x17 pairs of data items follow) + case 0xA0: + case 0xA1: + case 0xA2: + case 0xA3: + case 0xA4: + case 0xA5: + case 0xA6: + case 0xA7: + case 0xA8: + case 0xA9: + case 0xAA: + case 0xAB: + case 0xAC: + case 0xAD: + case 0xAE: + case 0xAF: + case 0xB0: + case 0xB1: + case 0xB2: + case 0xB3: + case 0xB4: + case 0xB5: + case 0xB6: + case 0xB7: + return get_cbor_object(static_cast(static_cast(current) & 0x1Fu), tag_handler); + + case 0xB8: // map (one-byte uint8_t for n follows) + { + std::uint8_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); + } + + case 0xB9: // map (two-byte uint16_t for n follow) + { + std::uint16_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); + } + + case 0xBA: // map (four-byte uint32_t for n follow) + { + std::uint32_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); + } + + case 0xBB: // map (eight-byte uint64_t for n follow) + { + std::uint64_t len{}; + return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len), tag_handler); + } + + case 0xBF: // map (indefinite length) + return get_cbor_object(std::size_t(-1), tag_handler); + + case 0xC6: // tagged item + case 0xC7: + case 0xC8: + case 0xC9: + case 0xCA: + case 0xCB: + case 0xCC: + case 0xCD: + case 0xCE: + case 0xCF: + case 0xD0: + case 0xD1: + case 0xD2: + case 0xD3: + case 0xD4: + case 0xD8: // tagged item (1 bytes follow) + case 0xD9: // tagged item (2 bytes follow) + case 0xDA: // tagged item (4 bytes follow) + case 0xDB: // tagged item (8 bytes follow) + { + switch (tag_handler) + { + 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(input_format_t::cbor, "invalid byte: 0x" + last_token, "value"))); + } + + case cbor_tag_handler_t::ignore: + { + switch (current) + { + case 0xD8: + { + std::uint8_t len{}; + get_number(input_format_t::cbor, len); + break; + } + case 0xD9: + { + std::uint16_t len{}; + get_number(input_format_t::cbor, len); + break; + } + case 0xDA: + { + std::uint32_t len{}; + get_number(input_format_t::cbor, len); + break; + } + case 0xDB: + { + std::uint64_t len{}; + get_number(input_format_t::cbor, len); + break; + } + default: + break; + } + return parse_cbor_internal(true, tag_handler); + } + + default: // LCOV_EXCL_LINE + JSON_ASSERT(false); // LCOV_EXCL_LINE + } + } + + case 0xF4: // false + return sax->boolean(false); + + case 0xF5: // true + return sax->boolean(true); + + case 0xF6: // null + return sax->null(); + + case 0xF9: // Half-Precision Float (two-byte IEEE 754) + { + const auto byte1_raw = get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number"))) + { + return false; + } + const auto byte2_raw = get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number"))) + { + return false; + } + + const auto byte1 = static_cast(byte1_raw); + const auto byte2 = static_cast(byte2_raw); + + // code from RFC 7049, Appendix D, Figure 3: + // As half-precision floating-point numbers were only added + // to IEEE 754 in 2008, today's programming platforms often + // still only have limited support for them. It is very + // easy to include at least decoding support for them even + // without such support. An example of a small decoder for + // half-precision floating-point numbers in the C language + // is shown in Fig. 3. + const auto half = static_cast((byte1 << 8u) + byte2); + const double val = [&half] + { + const int exp = (half >> 10u) & 0x1Fu; + const unsigned int mant = half & 0x3FFu; + JSON_ASSERT(0 <= exp&& exp <= 32); + JSON_ASSERT(mant <= 1024); + switch (exp) + { + case 0: + return std::ldexp(mant, -24); + case 31: + return (mant == 0) + ? std::numeric_limits::infinity() + : std::numeric_limits::quiet_NaN(); + default: + return std::ldexp(mant + 1024, exp - 25); + } + }(); + return sax->number_float((half & 0x8000u) != 0 + ? static_cast(-val) + : static_cast(val), ""); + } + + case 0xFA: // Single-Precision Float (four-byte IEEE 754) + { + float number{}; + return get_number(input_format_t::cbor, number) && sax->number_float(static_cast(number), ""); + } + + case 0xFB: // Double-Precision Float (eight-byte IEEE 754) + { + double number{}; + return get_number(input_format_t::cbor, number) && sax->number_float(static_cast(number), ""); + } + + 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(input_format_t::cbor, "invalid byte: 0x" + last_token, "value"))); + } + } + } + + /*! + @brief reads a CBOR string + + This function first reads starting bytes to determine the expected + string length and then copies this number of bytes into a string. + Additionally, CBOR's strings with indefinite lengths are supported. + + @param[out] result created string + + @return whether string creation completed + */ + bool get_cbor_string(string_t& result) + { + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string"))) + { + return false; + } + + switch (current) + { + // UTF-8 string (0x00..0x17 bytes follow) + case 0x60: + case 0x61: + case 0x62: + case 0x63: + case 0x64: + case 0x65: + case 0x66: + case 0x67: + case 0x68: + case 0x69: + case 0x6A: + case 0x6B: + case 0x6C: + case 0x6D: + case 0x6E: + case 0x6F: + case 0x70: + case 0x71: + case 0x72: + case 0x73: + case 0x74: + case 0x75: + case 0x76: + case 0x77: + { + return get_string(input_format_t::cbor, static_cast(current) & 0x1Fu, result); + } + + case 0x78: // UTF-8 string (one-byte uint8_t for n follows) + { + std::uint8_t len{}; + return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); + } + + case 0x79: // UTF-8 string (two-byte uint16_t for n follow) + { + std::uint16_t len{}; + return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); + } + + case 0x7A: // UTF-8 string (four-byte uint32_t for n follow) + { + std::uint32_t len{}; + return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); + } + + case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow) + { + std::uint64_t len{}; + return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); + } + + case 0x7F: // UTF-8 string (indefinite length) + { + while (get() != 0xFF) + { + string_t chunk; + if (!get_cbor_string(chunk)) + { + return false; + } + result.append(chunk); + } + return true; + } + + default: + { + auto last_token = get_token_string(); + return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::cbor, "expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x" + last_token, "string"))); + } + } + } + + /*! + @brief reads a CBOR byte array + + This function first reads starting bytes to determine the expected + byte array length and then copies this number of bytes into the byte array. + Additionally, CBOR's byte arrays with indefinite lengths are supported. + + @param[out] result created byte array + + @return whether byte array creation completed + */ + bool get_cbor_binary(binary_t& result) + { + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary"))) + { + return false; + } + + switch (current) + { + // Binary data (0x00..0x17 bytes follow) + case 0x40: + case 0x41: + case 0x42: + case 0x43: + case 0x44: + case 0x45: + case 0x46: + case 0x47: + case 0x48: + case 0x49: + case 0x4A: + case 0x4B: + case 0x4C: + case 0x4D: + case 0x4E: + case 0x4F: + case 0x50: + case 0x51: + case 0x52: + case 0x53: + case 0x54: + case 0x55: + case 0x56: + case 0x57: + { + return get_binary(input_format_t::cbor, static_cast(current) & 0x1Fu, result); + } + + case 0x58: // Binary data (one-byte uint8_t for n follows) + { + std::uint8_t len{}; + return get_number(input_format_t::cbor, len) && + get_binary(input_format_t::cbor, len, result); + } + + case 0x59: // Binary data (two-byte uint16_t for n follow) + { + std::uint16_t len{}; + return get_number(input_format_t::cbor, len) && + get_binary(input_format_t::cbor, len, result); + } + + case 0x5A: // Binary data (four-byte uint32_t for n follow) + { + std::uint32_t len{}; + return get_number(input_format_t::cbor, len) && + get_binary(input_format_t::cbor, len, result); + } + + case 0x5B: // Binary data (eight-byte uint64_t for n follow) + { + std::uint64_t len{}; + return get_number(input_format_t::cbor, len) && + get_binary(input_format_t::cbor, len, result); + } + + case 0x5F: // Binary data (indefinite length) + { + while (get() != 0xFF) + { + binary_t chunk; + if (!get_cbor_binary(chunk)) + { + return false; + } + result.insert(result.end(), chunk.begin(), chunk.end()); + } + return true; + } + + default: + { + auto last_token = get_token_string(); + return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::cbor, "expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x" + last_token, "binary"))); + } + } + } + + /*! + @param[in] len the length of the array or std::size_t(-1) for an + array of indefinite size + @param[in] tag_handler how CBOR tags should be treated + @return whether array creation completed + */ + bool get_cbor_array(const std::size_t len, + const cbor_tag_handler_t tag_handler) + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len))) + { + return false; + } + + if (len != std::size_t(-1)) + { + for (std::size_t i = 0; i < len; ++i) + { + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(true, tag_handler))) + { + return false; + } + } + } + else + { + while (get() != 0xFF) + { + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(false, tag_handler))) + { + return false; + } + } + } + + return sax->end_array(); + } + + /*! + @param[in] len the length of the object or std::size_t(-1) for an + object of indefinite size + @param[in] tag_handler how CBOR tags should be treated + @return whether object creation completed + */ + bool get_cbor_object(const std::size_t len, + const cbor_tag_handler_t tag_handler) + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len))) + { + return false; + } + + string_t key; + if (len != std::size_t(-1)) + { + for (std::size_t i = 0; i < len; ++i) + { + get(); + if (JSON_HEDLEY_UNLIKELY(!get_cbor_string(key) || !sax->key(key))) + { + return false; + } + + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(true, tag_handler))) + { + return false; + } + key.clear(); + } + } + else + { + while (get() != 0xFF) + { + if (JSON_HEDLEY_UNLIKELY(!get_cbor_string(key) || !sax->key(key))) + { + return false; + } + + if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(true, tag_handler))) + { + return false; + } + key.clear(); + } + } + + return sax->end_object(); + } + + ///////////// + // MsgPack // + ///////////// + + /*! + @return whether a valid MessagePack value was passed to the SAX parser + */ + bool parse_msgpack_internal() + { + switch (get()) + { + // EOF + case std::char_traits::eof(): + return unexpect_eof(input_format_t::msgpack, "value"); + + // positive fixint + case 0x00: + case 0x01: + case 0x02: + case 0x03: + case 0x04: + case 0x05: + case 0x06: + case 0x07: + case 0x08: + case 0x09: + case 0x0A: + case 0x0B: + case 0x0C: + case 0x0D: + case 0x0E: + case 0x0F: + case 0x10: + case 0x11: + case 0x12: + case 0x13: + case 0x14: + case 0x15: + case 0x16: + case 0x17: + case 0x18: + case 0x19: + case 0x1A: + case 0x1B: + case 0x1C: + case 0x1D: + case 0x1E: + case 0x1F: + case 0x20: + case 0x21: + case 0x22: + case 0x23: + case 0x24: + case 0x25: + case 0x26: + case 0x27: + case 0x28: + case 0x29: + case 0x2A: + case 0x2B: + case 0x2C: + case 0x2D: + case 0x2E: + case 0x2F: + case 0x30: + case 0x31: + case 0x32: + case 0x33: + case 0x34: + case 0x35: + case 0x36: + case 0x37: + case 0x38: + case 0x39: + case 0x3A: + case 0x3B: + case 0x3C: + case 0x3D: + case 0x3E: + case 0x3F: + case 0x40: + case 0x41: + case 0x42: + case 0x43: + case 0x44: + case 0x45: + case 0x46: + case 0x47: + case 0x48: + case 0x49: + case 0x4A: + case 0x4B: + case 0x4C: + case 0x4D: + case 0x4E: + case 0x4F: + case 0x50: + case 0x51: + case 0x52: + case 0x53: + case 0x54: + case 0x55: + case 0x56: + case 0x57: + case 0x58: + case 0x59: + case 0x5A: + case 0x5B: + case 0x5C: + case 0x5D: + case 0x5E: + case 0x5F: + case 0x60: + case 0x61: + case 0x62: + case 0x63: + case 0x64: + case 0x65: + case 0x66: + case 0x67: + case 0x68: + case 0x69: + case 0x6A: + case 0x6B: + case 0x6C: + case 0x6D: + case 0x6E: + case 0x6F: + case 0x70: + case 0x71: + case 0x72: + case 0x73: + case 0x74: + case 0x75: + case 0x76: + case 0x77: + case 0x78: + case 0x79: + case 0x7A: + case 0x7B: + case 0x7C: + case 0x7D: + case 0x7E: + case 0x7F: + return sax->number_unsigned(static_cast(current)); + + // fixmap + case 0x80: + case 0x81: + case 0x82: + case 0x83: + case 0x84: + case 0x85: + case 0x86: + case 0x87: + case 0x88: + case 0x89: + case 0x8A: + case 0x8B: + case 0x8C: + case 0x8D: + case 0x8E: + case 0x8F: + return get_msgpack_object(static_cast(static_cast(current) & 0x0Fu)); + + // fixarray + case 0x90: + case 0x91: + case 0x92: + case 0x93: + case 0x94: + case 0x95: + case 0x96: + case 0x97: + case 0x98: + case 0x99: + case 0x9A: + case 0x9B: + case 0x9C: + case 0x9D: + case 0x9E: + case 0x9F: + return get_msgpack_array(static_cast(static_cast(current) & 0x0Fu)); + + // fixstr + case 0xA0: + case 0xA1: + case 0xA2: + case 0xA3: + case 0xA4: + case 0xA5: + case 0xA6: + case 0xA7: + case 0xA8: + case 0xA9: + case 0xAA: + case 0xAB: + case 0xAC: + case 0xAD: + case 0xAE: + case 0xAF: + case 0xB0: + case 0xB1: + case 0xB2: + case 0xB3: + case 0xB4: + case 0xB5: + case 0xB6: + case 0xB7: + case 0xB8: + case 0xB9: + case 0xBA: + case 0xBB: + case 0xBC: + case 0xBD: + case 0xBE: + case 0xBF: + case 0xD9: // str 8 + case 0xDA: // str 16 + case 0xDB: // str 32 + { + string_t s; + return get_msgpack_string(s) && sax->string(s); + } + + case 0xC0: // nil + return sax->null(); + + case 0xC2: // false + return sax->boolean(false); + + case 0xC3: // true + return sax->boolean(true); + + case 0xC4: // bin 8 + case 0xC5: // bin 16 + case 0xC6: // bin 32 + case 0xC7: // ext 8 + case 0xC8: // ext 16 + case 0xC9: // ext 32 + case 0xD4: // fixext 1 + case 0xD5: // fixext 2 + case 0xD6: // fixext 4 + case 0xD7: // fixext 8 + case 0xD8: // fixext 16 + { + binary_t b; + return get_msgpack_binary(b) && sax->binary(b); + } + + case 0xCA: // float 32 + { + float number{}; + return get_number(input_format_t::msgpack, number) && sax->number_float(static_cast(number), ""); + } + + case 0xCB: // float 64 + { + double number{}; + return get_number(input_format_t::msgpack, number) && sax->number_float(static_cast(number), ""); + } + + case 0xCC: // uint 8 + { + std::uint8_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); + } + + case 0xCD: // uint 16 + { + std::uint16_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); + } + + case 0xCE: // uint 32 + { + std::uint32_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); + } + + case 0xCF: // uint 64 + { + std::uint64_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); + } + + case 0xD0: // int 8 + { + std::int8_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_integer(number); + } + + case 0xD1: // int 16 + { + std::int16_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_integer(number); + } + + case 0xD2: // int 32 + { + std::int32_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_integer(number); + } + + case 0xD3: // int 64 + { + std::int64_t number{}; + return get_number(input_format_t::msgpack, number) && sax->number_integer(number); + } + + case 0xDC: // array 16 + { + std::uint16_t len{}; + return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast(len)); + } + + case 0xDD: // array 32 + { + std::uint32_t len{}; + return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast(len)); + } + + case 0xDE: // map 16 + { + std::uint16_t len{}; + return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast(len)); + } + + case 0xDF: // map 32 + { + std::uint32_t len{}; + return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast(len)); + } + + // negative fixint + case 0xE0: + case 0xE1: + case 0xE2: + case 0xE3: + case 0xE4: + case 0xE5: + case 0xE6: + case 0xE7: + case 0xE8: + case 0xE9: + case 0xEA: + case 0xEB: + case 0xEC: + case 0xED: + case 0xEE: + case 0xEF: + case 0xF0: + case 0xF1: + case 0xF2: + case 0xF3: + case 0xF4: + case 0xF5: + case 0xF6: + case 0xF7: + case 0xF8: + case 0xF9: + case 0xFA: + case 0xFB: + case 0xFC: + case 0xFD: + case 0xFE: + case 0xFF: + return sax->number_integer(static_cast(current)); + + 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(input_format_t::msgpack, "invalid byte: 0x" + last_token, "value"))); + } + } + } + + /*! + @brief reads a MessagePack string + + This function first reads starting bytes to determine the expected + string length and then copies this number of bytes into a string. + + @param[out] result created string + + @return whether string creation completed + */ + bool get_msgpack_string(string_t& result) + { + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::msgpack, "string"))) + { + return false; + } + + switch (current) + { + // fixstr + case 0xA0: + case 0xA1: + case 0xA2: + case 0xA3: + case 0xA4: + case 0xA5: + case 0xA6: + case 0xA7: + case 0xA8: + case 0xA9: + case 0xAA: + case 0xAB: + case 0xAC: + case 0xAD: + case 0xAE: + case 0xAF: + case 0xB0: + case 0xB1: + case 0xB2: + case 0xB3: + case 0xB4: + case 0xB5: + case 0xB6: + case 0xB7: + case 0xB8: + case 0xB9: + case 0xBA: + case 0xBB: + case 0xBC: + case 0xBD: + case 0xBE: + case 0xBF: + { + return get_string(input_format_t::msgpack, static_cast(current) & 0x1Fu, result); + } + + case 0xD9: // str 8 + { + std::uint8_t len{}; + return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result); + } + + case 0xDA: // str 16 + { + std::uint16_t len{}; + return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result); + } + + case 0xDB: // str 32 + { + std::uint32_t len{}; + return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result); + } + + default: + { + auto last_token = get_token_string(); + return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::msgpack, "expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0x" + last_token, "string"))); + } + } + } + + /*! + @brief reads a MessagePack byte array + + This function first reads starting bytes to determine the expected + byte array length and then copies this number of bytes into a byte array. + + @param[out] result created byte array + + @return whether byte array creation completed + */ + bool get_msgpack_binary(binary_t& result) + { + // helper function to set the subtype + auto assign_and_return_true = [&result](std::int8_t subtype) + { + result.set_subtype(static_cast(subtype)); + return true; + }; + + switch (current) + { + case 0xC4: // bin 8 + { + std::uint8_t len{}; + return get_number(input_format_t::msgpack, len) && + get_binary(input_format_t::msgpack, len, result); + } + + case 0xC5: // bin 16 + { + std::uint16_t len{}; + return get_number(input_format_t::msgpack, len) && + get_binary(input_format_t::msgpack, len, result); + } + + case 0xC6: // bin 32 + { + std::uint32_t len{}; + return get_number(input_format_t::msgpack, len) && + get_binary(input_format_t::msgpack, len, result); + } + + case 0xC7: // ext 8 + { + std::uint8_t len{}; + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, len) && + get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, len, result) && + assign_and_return_true(subtype); + } + + case 0xC8: // ext 16 + { + std::uint16_t len{}; + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, len) && + get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, len, result) && + assign_and_return_true(subtype); + } + + case 0xC9: // ext 32 + { + std::uint32_t len{}; + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, len) && + get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, len, result) && + assign_and_return_true(subtype); + } + + case 0xD4: // fixext 1 + { + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, 1, result) && + assign_and_return_true(subtype); + } + + case 0xD5: // fixext 2 + { + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, 2, result) && + assign_and_return_true(subtype); + } + + case 0xD6: // fixext 4 + { + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, 4, result) && + assign_and_return_true(subtype); + } + + case 0xD7: // fixext 8 + { + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, 8, result) && + assign_and_return_true(subtype); + } + + case 0xD8: // fixext 16 + { + std::int8_t subtype{}; + return get_number(input_format_t::msgpack, subtype) && + get_binary(input_format_t::msgpack, 16, result) && + assign_and_return_true(subtype); + } + + default: // LCOV_EXCL_LINE + return false; // LCOV_EXCL_LINE + } + } + + /*! + @param[in] len the length of the array + @return whether array creation completed + */ + bool get_msgpack_array(const std::size_t len) + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len))) + { + return false; + } + + for (std::size_t i = 0; i < len; ++i) + { + if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal())) + { + return false; + } + } + + return sax->end_array(); + } + + /*! + @param[in] len the length of the object + @return whether object creation completed + */ + bool get_msgpack_object(const std::size_t len) + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len))) + { + return false; + } + + string_t key; + for (std::size_t i = 0; i < len; ++i) + { + get(); + if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key))) + { + return false; + } + + if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal())) + { + return false; + } + key.clear(); + } + + return sax->end_object(); + } + + //////////// + // UBJSON // + //////////// + + /*! + @param[in] get_char whether a new character should be retrieved from the + input (true, default) or whether the last read + character should be considered instead + + @return whether a valid UBJSON value was passed to the SAX parser + */ + bool parse_ubjson_internal(const bool get_char = true) + { + return get_ubjson_value(get_char ? get_ignore_noop() : current); + } + + /*! + @brief reads a UBJSON string + + This function is either called after reading the 'S' byte explicitly + indicating a string, or in case of an object key where the 'S' byte can be + left out. + + @param[out] result created string + @param[in] get_char whether a new character should be retrieved from the + input (true, default) or whether the last read + character should be considered instead + + @return whether string creation completed + */ + bool get_ubjson_string(string_t& result, const bool get_char = true) + { + if (get_char) + { + get(); // TODO(niels): may we ignore N here? + } + + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "value"))) + { + return false; + } + + switch (current) + { + case 'U': + { + std::uint8_t len{}; + return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); + } + + case 'i': + { + std::int8_t len{}; + return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); + } + + case 'I': + { + std::int16_t len{}; + return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); + } + + case 'l': + { + std::int32_t len{}; + return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); + } + + case 'L': + { + std::int64_t len{}; + return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); + } + + default: + auto last_token = get_token_string(); + return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::ubjson, "expected length type specification (U, i, I, l, L); last byte: 0x" + last_token, "string"))); + } + } + + /*! + @param[out] result determined size + @return whether size determination completed + */ + bool get_ubjson_size_value(std::size_t& result) + { + switch (get_ignore_noop()) + { + case 'U': + { + std::uint8_t number{}; + if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) + { + return false; + } + result = static_cast(number); + return true; + } + + case 'i': + { + std::int8_t number{}; + if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) + { + return false; + } + result = static_cast(number); + return true; + } + + case 'I': + { + std::int16_t number{}; + if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) + { + return false; + } + result = static_cast(number); + return true; + } + + case 'l': + { + std::int32_t number{}; + if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) + { + return false; + } + result = static_cast(number); + return true; + } + + case 'L': + { + std::int64_t number{}; + if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) + { + return false; + } + result = static_cast(number); + return true; + } + + default: + { + auto last_token = get_token_string(); + return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::ubjson, "expected length type specification (U, i, I, l, L) after '#'; last byte: 0x" + last_token, "size"))); + } + } + } + + /*! + @brief determine the type and size for a container + + In the optimized UBJSON format, a type and a size can be provided to allow + for a more compact representation. + + @param[out] result pair of the size and the type + + @return whether pair creation completed + */ + bool get_ubjson_size_type(std::pair& result) + { + result.first = string_t::npos; // size + result.second = 0; // type + + get_ignore_noop(); + + if (current == '$') + { + result.second = get(); // must not ignore 'N', because 'N' maybe the type + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "type"))) + { + return false; + } + + get_ignore_noop(); + if (JSON_HEDLEY_UNLIKELY(current != '#')) + { + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "value"))) + { + return false; + } + auto last_token = get_token_string(); + return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read, exception_message(input_format_t::ubjson, "expected '#' after type information; last byte: 0x" + last_token, "size"))); + } + + return get_ubjson_size_value(result.first); + } + + if (current == '#') + { + return get_ubjson_size_value(result.first); + } + + return true; + } + + /*! + @param prefix the previously read or set type prefix + @return whether value creation completed + */ + bool get_ubjson_value(const char_int_type prefix) + { + switch (prefix) + { + case std::char_traits::eof(): // EOF + return unexpect_eof(input_format_t::ubjson, "value"); + + case 'T': // true + return sax->boolean(true); + case 'F': // false + return sax->boolean(false); + + case 'Z': // null + return sax->null(); + + case 'U': + { + std::uint8_t number{}; + return get_number(input_format_t::ubjson, number) && sax->number_unsigned(number); + } + + case 'i': + { + std::int8_t number{}; + return get_number(input_format_t::ubjson, number) && sax->number_integer(number); + } + + case 'I': + { + std::int16_t number{}; + return get_number(input_format_t::ubjson, number) && sax->number_integer(number); + } + + case 'l': + { + std::int32_t number{}; + return get_number(input_format_t::ubjson, number) && sax->number_integer(number); + } + + case 'L': + { + std::int64_t number{}; + return get_number(input_format_t::ubjson, number) && sax->number_integer(number); + } + + case 'd': + { + float number{}; + return get_number(input_format_t::ubjson, number) && sax->number_float(static_cast(number), ""); + } + + case 'D': + { + double number{}; + return get_number(input_format_t::ubjson, number) && sax->number_float(static_cast(number), ""); + } + + case 'C': // char + { + get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "char"))) + { + return false; + } + 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(input_format_t::ubjson, "byte after 'C' must be in range 0x00..0x7F; last byte: 0x" + last_token, "char"))); + } + string_t s(1, static_cast(current)); + return sax->string(s); + } + + case 'S': // string + { + string_t s; + return get_ubjson_string(s) && sax->string(s); + } + + case '[': // array + return get_ubjson_array(); + + case '{': // object + return get_ubjson_object(); + + 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(input_format_t::ubjson, "invalid byte: 0x" + last_token, "value"))); + } + } + } + + /*! + @return whether array creation completed + */ + bool get_ubjson_array() + { + std::pair size_and_type; + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type))) + { + return false; + } + + if (size_and_type.first != string_t::npos) + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_array(size_and_type.first))) + { + return false; + } + + if (size_and_type.second != 0) + { + if (size_and_type.second != 'N') + { + for (std::size_t i = 0; i < size_and_type.first; ++i) + { + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_value(size_and_type.second))) + { + return false; + } + } + } + } + else + { + for (std::size_t i = 0; i < size_and_type.first; ++i) + { + if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal())) + { + return false; + } + } + } + } + else + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_array(std::size_t(-1)))) + { + return false; + } + + while (current != ']') + { + if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal(false))) + { + return false; + } + get_ignore_noop(); + } + } + + return sax->end_array(); + } + + /*! + @return whether object creation completed + */ + bool get_ubjson_object() + { + std::pair size_and_type; + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type))) + { + return false; + } + + string_t key; + if (size_and_type.first != string_t::npos) + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_object(size_and_type.first))) + { + return false; + } + + if (size_and_type.second != 0) + { + for (std::size_t i = 0; i < size_and_type.first; ++i) + { + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key) || !sax->key(key))) + { + return false; + } + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_value(size_and_type.second))) + { + return false; + } + key.clear(); + } + } + else + { + for (std::size_t i = 0; i < size_and_type.first; ++i) + { + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key) || !sax->key(key))) + { + return false; + } + if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal())) + { + return false; + } + key.clear(); + } + } + } + else + { + if (JSON_HEDLEY_UNLIKELY(!sax->start_object(std::size_t(-1)))) + { + return false; + } + + while (current != '}') + { + if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key, false) || !sax->key(key))) + { + return false; + } + if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal())) + { + return false; + } + get_ignore_noop(); + key.clear(); + } + } + + return sax->end_object(); + } + + // Note, no reader for UBJSON binary types is implemented because they do + // not exist + + /////////////////////// + // Utility functions // + /////////////////////// + + /*! + @brief get next character from the input + + This function provides the interface to the used input adapter. It does + not throw in case the input reached EOF, but returns a -'ve valued + `std::char_traits::eof()` in that case. + + @return character read from the input + */ + char_int_type get() + { + ++chars_read; + return current = ia.get_character(); + } + + /*! + @return character read from the input after ignoring all 'N' entries + */ + char_int_type get_ignore_noop() + { + do + { + get(); + } + while (current == 'N'); + + return current; + } + + /* + @brief read a number from the input + + @tparam NumberType the type of the number + @param[in] format the current format (for diagnostics) + @param[out] result number of type @a NumberType + + @return whether conversion completed + + @note This function needs to respect the system's endianess, because + bytes in CBOR, MessagePack, and UBJSON are stored in network order + (big endian) and therefore need reordering on little endian systems. + */ + template + bool get_number(const input_format_t format, NumberType& result) + { + // step 1: read input into array with system's byte order + std::array vec; + for (std::size_t i = 0; i < sizeof(NumberType); ++i) + { + get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "number"))) + { + return false; + } + + // reverse byte order prior to conversion if necessary + if (is_little_endian != InputIsLittleEndian) + { + vec[sizeof(NumberType) - i - 1] = static_cast(current); + } + else + { + vec[i] = static_cast(current); // LCOV_EXCL_LINE + } + } + + // step 2: convert array into number of type T and return + std::memcpy(&result, vec.data(), sizeof(NumberType)); + return true; + } + + /*! + @brief create a string by reading characters from the input + + @tparam NumberType the type of the number + @param[in] format the current format (for diagnostics) + @param[in] len number of characters to read + @param[out] result string created by reading @a len bytes + + @return whether string creation completed + + @note We can not reserve @a len bytes for the result, because @a len + may be too large. Usually, @ref unexpect_eof() detects the end of + the input before we run out of string memory. + */ + template + bool get_string(const input_format_t format, + const NumberType len, + string_t& result) + { + bool success = true; + for (NumberType i = 0; i < len; i++) + { + get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "string"))) + { + success = false; + break; + } + result.push_back(static_cast(current)); + }; + return success; + } + + /*! + @brief create a byte array by reading bytes from the input + + @tparam NumberType the type of the number + @param[in] format the current format (for diagnostics) + @param[in] len number of bytes to read + @param[out] result byte array created by reading @a len bytes + + @return whether byte array creation completed + + @note We can not reserve @a len bytes for the result, because @a len + may be too large. Usually, @ref unexpect_eof() detects the end of + the input before we run out of memory. + */ + template + bool get_binary(const input_format_t format, + const NumberType len, + binary_t& result) + { + bool success = true; + for (NumberType i = 0; i < len; i++) + { + get(); + if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "binary"))) + { + success = false; + break; + } + result.push_back(static_cast(current)); + } + return success; + } + + /*! + @param[in] format the current format (for diagnostics) + @param[in] context further context information (for diagnostics) + @return whether the last read character is not EOF + */ + JSON_HEDLEY_NON_NULL(3) + bool unexpect_eof(const input_format_t format, const char* context) const + { + if (JSON_HEDLEY_UNLIKELY(current == std::char_traits::eof())) + { + return sax->parse_error(chars_read, "", + parse_error::create(110, chars_read, exception_message(format, "unexpected end of input", context))); + } + return true; + } + + /*! + @return a string representation of the last read byte + */ + std::string get_token_string() const + { + std::array cr{{}}; + (std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast(current)); + return std::string{cr.data()}; + } + + /*! + @param[in] format the current format + @param[in] detail a detailed error message + @param[in] context further context information + @return a message string to use in the parse_error exceptions + */ + std::string exception_message(const input_format_t format, + const std::string& detail, + const std::string& context) const + { + std::string error_msg = "syntax error while parsing "; + + switch (format) + { + case input_format_t::cbor: + error_msg += "CBOR"; + break; + + case input_format_t::msgpack: + error_msg += "MessagePack"; + break; + + case input_format_t::ubjson: + error_msg += "UBJSON"; + break; + + case input_format_t::bson: + error_msg += "BSON"; + break; + + default: // LCOV_EXCL_LINE + JSON_ASSERT(false); // LCOV_EXCL_LINE + } + + return error_msg + " " + context + ": " + detail; + } + + private: + /// input adapter + InputAdapterType ia; + + /// the current character + char_int_type current = std::char_traits::eof(); + + /// the number of characters read + std::size_t chars_read = 0; + + /// whether we can assume little endianess + const bool is_little_endian = little_endianess(); + + /// the SAX parser + json_sax_t* sax = nullptr; +}; +} // namespace detail +} // namespace nlohmann + +// #include + // #include @@ -7499,2602 +10042,6 @@ scan_number_done: } // namespace detail } // namespace nlohmann -// #include - -// #include - - -#include // size_t -#include // declval -#include // string - -// #include - -// #include - - -namespace nlohmann -{ -namespace detail -{ -template -using null_function_t = decltype(std::declval().null()); - -template -using boolean_function_t = - decltype(std::declval().boolean(std::declval())); - -template -using number_integer_function_t = - decltype(std::declval().number_integer(std::declval())); - -template -using number_unsigned_function_t = - decltype(std::declval().number_unsigned(std::declval())); - -template -using number_float_function_t = decltype(std::declval().number_float( - std::declval(), std::declval())); - -template -using string_function_t = - decltype(std::declval().string(std::declval())); - -template -using binary_function_t = - decltype(std::declval().binary(std::declval())); - -template -using start_object_function_t = - decltype(std::declval().start_object(std::declval())); - -template -using key_function_t = - decltype(std::declval().key(std::declval())); - -template -using end_object_function_t = decltype(std::declval().end_object()); - -template -using start_array_function_t = - decltype(std::declval().start_array(std::declval())); - -template -using end_array_function_t = decltype(std::declval().end_array()); - -template -using parse_error_function_t = decltype(std::declval().parse_error( - std::declval(), std::declval(), - std::declval())); - -template -struct is_sax -{ - private: - static_assert(is_basic_json::value, - "BasicJsonType must be of type basic_json<...>"); - - using number_integer_t = typename BasicJsonType::number_integer_t; - using number_unsigned_t = typename BasicJsonType::number_unsigned_t; - using number_float_t = typename BasicJsonType::number_float_t; - using string_t = typename BasicJsonType::string_t; - using binary_t = typename BasicJsonType::binary_t; - using exception_t = typename BasicJsonType::exception; - - public: - static constexpr bool value = - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value && - is_detected_exact::value; -}; - -template -struct is_sax_static_asserts -{ - private: - static_assert(is_basic_json::value, - "BasicJsonType must be of type basic_json<...>"); - - using number_integer_t = typename BasicJsonType::number_integer_t; - using number_unsigned_t = typename BasicJsonType::number_unsigned_t; - using number_float_t = typename BasicJsonType::number_float_t; - using string_t = typename BasicJsonType::string_t; - using binary_t = typename BasicJsonType::binary_t; - using exception_t = typename BasicJsonType::exception; - - public: - static_assert(is_detected_exact::value, - "Missing/invalid function: bool null()"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool boolean(bool)"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool boolean(bool)"); - static_assert( - is_detected_exact::value, - "Missing/invalid function: bool number_integer(number_integer_t)"); - static_assert( - is_detected_exact::value, - "Missing/invalid function: bool number_unsigned(number_unsigned_t)"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool number_float(number_float_t, const string_t&)"); - static_assert( - is_detected_exact::value, - "Missing/invalid function: bool string(string_t&)"); - static_assert( - is_detected_exact::value, - "Missing/invalid function: bool binary(binary_t&)"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool start_object(std::size_t)"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool key(string_t&)"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool end_object()"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool start_array(std::size_t)"); - static_assert(is_detected_exact::value, - "Missing/invalid function: bool end_array()"); - static_assert( - is_detected_exact::value, - "Missing/invalid function: bool parse_error(std::size_t, const " - "std::string&, const exception&)"); -}; -} // namespace detail -} // namespace nlohmann - -// #include - - -namespace nlohmann -{ -namespace detail -{ - -/// how to treat CBOR tags -enum class cbor_tag_handler_t -{ - error, ///< throw a parse_error exception in case of a tag - ignore ///< ignore tags -}; - -/*! -@brief determine system byte order - -@return true if and only if system's byte order is little endian - -@note from https://stackoverflow.com/a/1001328/266378 -*/ -static inline bool little_endianess(int num = 1) noexcept -{ - return *reinterpret_cast(&num) == 1; -} - - -/////////////////// -// binary reader // -/////////////////// - -/*! -@brief deserialization of CBOR, MessagePack, and UBJSON values -*/ -template> -class binary_reader -{ - using number_integer_t = typename BasicJsonType::number_integer_t; - using number_unsigned_t = typename BasicJsonType::number_unsigned_t; - using number_float_t = typename BasicJsonType::number_float_t; - using string_t = typename BasicJsonType::string_t; - using binary_t = typename BasicJsonType::binary_t; - using json_sax_t = SAX; - using char_type = typename InputAdapterType::char_type; - using char_int_type = typename std::char_traits::int_type; - - public: - /*! - @brief create a binary reader - - @param[in] adapter input adapter to read from - */ - explicit binary_reader(InputAdapterType&& adapter) : ia(std::move(adapter)) - { - (void)detail::is_sax_static_asserts {}; - } - - // make class move-only - binary_reader(const binary_reader&) = delete; - binary_reader(binary_reader&&) = default; - binary_reader& operator=(const binary_reader&) = delete; - binary_reader& operator=(binary_reader&&) = default; - ~binary_reader() = default; - - /*! - @param[in] format the binary format to parse - @param[in] sax_ a SAX event processor - @param[in] strict whether to expect the input to be consumed completed - @param[in] tag_handler how to treat CBOR tags - - @return - */ - JSON_HEDLEY_NON_NULL(3) - bool sax_parse(const input_format_t format, - json_sax_t* sax_, - const bool strict = true, - const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error) - { - sax = sax_; - bool result = false; - - switch (format) - { - case input_format_t::bson: - result = parse_bson_internal(); - break; - - case input_format_t::cbor: - result = parse_cbor_internal(true, tag_handler); - break; - - case input_format_t::msgpack: - result = parse_msgpack_internal(); - break; - - case input_format_t::ubjson: - result = parse_ubjson_internal(); - break; - - default: // LCOV_EXCL_LINE - JSON_ASSERT(false); // LCOV_EXCL_LINE - } - - // strict mode: next byte must be EOF - if (result && strict) - { - if (format == input_format_t::ubjson) - { - get_ignore_noop(); - } - else - { - get(); - } - - if (JSON_HEDLEY_UNLIKELY(current != std::char_traits::eof())) - { - return sax->parse_error(chars_read, get_token_string(), - parse_error::create(110, chars_read, exception_message(format, "expected end of input; last byte: 0x" + get_token_string(), "value"))); - } - } - - return result; - } - - private: - ////////// - // BSON // - ////////// - - /*! - @brief Reads in a BSON-object and passes it to the SAX-parser. - @return whether a valid BSON-value was passed to the SAX parser - */ - bool parse_bson_internal() - { - std::int32_t document_size{}; - get_number(input_format_t::bson, document_size); - - if (JSON_HEDLEY_UNLIKELY(!sax->start_object(std::size_t(-1)))) - { - return false; - } - - if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_list(/*is_array*/false))) - { - return false; - } - - return sax->end_object(); - } - - /*! - @brief Parses a C-style string from the BSON input. - @param[in, out] result A reference to the string variable where the read - string is to be stored. - @return `true` if the \x00-byte indicating the end of the string was - encountered before the EOF; false` indicates an unexpected EOF. - */ - bool get_bson_cstr(string_t& result) - { - auto out = std::back_inserter(result); - while (true) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::bson, "cstring"))) - { - return false; - } - if (current == 0x00) - { - return true; - } - *out++ = static_cast(current); - } - } - - /*! - @brief Parses a zero-terminated string of length @a len from the BSON - input. - @param[in] len The length (including the zero-byte at the end) of the - string to be read. - @param[in, out] result A reference to the string variable where the read - string is to be stored. - @tparam NumberType The type of the length @a len - @pre len >= 1 - @return `true` if the string was successfully parsed - */ - template - bool get_bson_string(const NumberType len, string_t& result) - { - 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(input_format_t::bson, "string length must be at least 1, is " + std::to_string(len), "string"))); - } - - return get_string(input_format_t::bson, len - static_cast(1), result) && get() != std::char_traits::eof(); - } - - /*! - @brief Parses a byte array input of length @a len from the BSON input. - @param[in] len The length of the byte array to be read. - @param[in, out] result A reference to the binary variable where the read - array is to be stored. - @tparam NumberType The type of the length @a len - @pre len >= 0 - @return `true` if the byte array was successfully parsed - */ - template - bool get_bson_binary(const NumberType len, binary_t& result) - { - 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(input_format_t::bson, "byte array length cannot be negative, is " + std::to_string(len), "binary"))); - } - - // All BSON binary values have a subtype - std::uint8_t subtype{}; - get_number(input_format_t::bson, subtype); - result.set_subtype(subtype); - - return get_binary(input_format_t::bson, len, result); - } - - /*! - @brief Read a BSON document element of the given @a element_type. - @param[in] element_type The BSON element type, c.f. http://bsonspec.org/spec.html - @param[in] element_type_parse_position The position in the input stream, - where the `element_type` was read. - @warning Not all BSON element types are supported yet. An unsupported - @a element_type will give rise to a parse_error.114: - Unsupported BSON record type 0x... - @return whether a valid BSON-object/array was passed to the SAX parser - */ - bool parse_bson_element_internal(const char_int_type element_type, - const std::size_t element_type_parse_position) - { - switch (element_type) - { - case 0x01: // double - { - double number{}; - return get_number(input_format_t::bson, number) && sax->number_float(static_cast(number), ""); - } - - case 0x02: // string - { - std::int32_t len{}; - string_t value; - return get_number(input_format_t::bson, len) && get_bson_string(len, value) && sax->string(value); - } - - case 0x03: // object - { - return parse_bson_internal(); - } - - case 0x04: // array - { - return parse_bson_array(); - } - - case 0x05: // binary - { - std::int32_t len{}; - binary_t value; - return get_number(input_format_t::bson, len) && get_bson_binary(len, value) && sax->binary(value); - } - - case 0x08: // boolean - { - return sax->boolean(get() != 0); - } - - case 0x0A: // null - { - return sax->null(); - } - - case 0x10: // int32 - { - std::int32_t value{}; - return get_number(input_format_t::bson, value) && sax->number_integer(value); - } - - case 0x12: // int64 - { - std::int64_t value{}; - return get_number(input_format_t::bson, value) && sax->number_integer(value); - } - - default: // anything else not supported (yet) - { - std::array cr{{}}; - (std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast(element_type)); - return sax->parse_error(element_type_parse_position, std::string(cr.data()), parse_error::create(114, element_type_parse_position, "Unsupported BSON record type 0x" + std::string(cr.data()))); - } - } - } - - /*! - @brief Read a BSON element list (as specified in the BSON-spec) - - The same binary layout is used for objects and arrays, hence it must be - indicated with the argument @a is_array which one is expected - (true --> array, false --> object). - - @param[in] is_array Determines if the element list being read is to be - treated as an object (@a is_array == false), or as an - array (@a is_array == true). - @return whether a valid BSON-object/array was passed to the SAX parser - */ - bool parse_bson_element_list(const bool is_array) - { - string_t key; - - while (auto element_type = get()) - { - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::bson, "element list"))) - { - return false; - } - - const std::size_t element_type_parse_position = chars_read; - if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key))) - { - return false; - } - - if (!is_array && !sax->key(key)) - { - return false; - } - - if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_internal(element_type, element_type_parse_position))) - { - return false; - } - - // get_bson_cstr only appends - key.clear(); - } - - return true; - } - - /*! - @brief Reads an array from the BSON input and passes it to the SAX-parser. - @return whether a valid BSON-array was passed to the SAX parser - */ - bool parse_bson_array() - { - std::int32_t document_size{}; - get_number(input_format_t::bson, document_size); - - if (JSON_HEDLEY_UNLIKELY(!sax->start_array(std::size_t(-1)))) - { - return false; - } - - if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_list(/*is_array*/true))) - { - return false; - } - - return sax->end_array(); - } - - ////////// - // CBOR // - ////////// - - /*! - @param[in] get_char whether a new character should be retrieved from the - input (true, default) or whether the last read - character should be considered instead - @param[in] tag_handler how CBOR tags should be treated - - @return whether a valid CBOR value was passed to the SAX parser - */ - bool parse_cbor_internal(const bool get_char = true, - cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error) - { - switch (get_char ? get() : current) - { - // EOF - case std::char_traits::eof(): - return unexpect_eof(input_format_t::cbor, "value"); - - // Integer 0x00..0x17 (0..23) - case 0x00: - case 0x01: - case 0x02: - case 0x03: - case 0x04: - case 0x05: - case 0x06: - case 0x07: - case 0x08: - case 0x09: - case 0x0A: - case 0x0B: - case 0x0C: - case 0x0D: - case 0x0E: - case 0x0F: - case 0x10: - case 0x11: - case 0x12: - case 0x13: - case 0x14: - case 0x15: - case 0x16: - case 0x17: - return sax->number_unsigned(static_cast(current)); - - case 0x18: // Unsigned integer (one-byte uint8_t follows) - { - std::uint8_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); - } - - case 0x19: // Unsigned integer (two-byte uint16_t follows) - { - std::uint16_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); - } - - case 0x1A: // Unsigned integer (four-byte uint32_t follows) - { - std::uint32_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); - } - - case 0x1B: // Unsigned integer (eight-byte uint64_t follows) - { - std::uint64_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_unsigned(number); - } - - // Negative integer -1-0x00..-1-0x17 (-1..-24) - case 0x20: - case 0x21: - case 0x22: - case 0x23: - case 0x24: - case 0x25: - case 0x26: - case 0x27: - case 0x28: - case 0x29: - case 0x2A: - case 0x2B: - case 0x2C: - case 0x2D: - case 0x2E: - case 0x2F: - case 0x30: - case 0x31: - case 0x32: - case 0x33: - case 0x34: - case 0x35: - case 0x36: - case 0x37: - return sax->number_integer(static_cast(0x20 - 1 - current)); - - case 0x38: // Negative integer (one-byte uint8_t follows) - { - std::uint8_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - number); - } - - case 0x39: // Negative integer -1-n (two-byte uint16_t follows) - { - std::uint16_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - number); - } - - case 0x3A: // Negative integer -1-n (four-byte uint32_t follows) - { - std::uint32_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - number); - } - - case 0x3B: // Negative integer -1-n (eight-byte uint64_t follows) - { - std::uint64_t number{}; - return get_number(input_format_t::cbor, number) && sax->number_integer(static_cast(-1) - - static_cast(number)); - } - - // Binary data (0x00..0x17 bytes follow) - case 0x40: - case 0x41: - case 0x42: - case 0x43: - case 0x44: - case 0x45: - case 0x46: - case 0x47: - case 0x48: - case 0x49: - case 0x4A: - case 0x4B: - case 0x4C: - case 0x4D: - case 0x4E: - case 0x4F: - case 0x50: - case 0x51: - case 0x52: - case 0x53: - case 0x54: - case 0x55: - case 0x56: - case 0x57: - case 0x58: // Binary data (one-byte uint8_t for n follows) - case 0x59: // Binary data (two-byte uint16_t for n follow) - case 0x5A: // Binary data (four-byte uint32_t for n follow) - case 0x5B: // Binary data (eight-byte uint64_t for n follow) - case 0x5F: // Binary data (indefinite length) - { - binary_t b; - return get_cbor_binary(b) && sax->binary(b); - } - - // UTF-8 string (0x00..0x17 bytes follow) - case 0x60: - case 0x61: - case 0x62: - case 0x63: - case 0x64: - case 0x65: - case 0x66: - case 0x67: - case 0x68: - case 0x69: - case 0x6A: - case 0x6B: - case 0x6C: - case 0x6D: - case 0x6E: - case 0x6F: - case 0x70: - case 0x71: - case 0x72: - case 0x73: - case 0x74: - case 0x75: - case 0x76: - case 0x77: - case 0x78: // UTF-8 string (one-byte uint8_t for n follows) - case 0x79: // UTF-8 string (two-byte uint16_t for n follow) - case 0x7A: // UTF-8 string (four-byte uint32_t for n follow) - case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow) - case 0x7F: // UTF-8 string (indefinite length) - { - string_t s; - return get_cbor_string(s) && sax->string(s); - } - - // array (0x00..0x17 data items follow) - case 0x80: - case 0x81: - case 0x82: - case 0x83: - case 0x84: - case 0x85: - case 0x86: - case 0x87: - case 0x88: - case 0x89: - case 0x8A: - case 0x8B: - case 0x8C: - case 0x8D: - case 0x8E: - case 0x8F: - case 0x90: - case 0x91: - case 0x92: - case 0x93: - case 0x94: - case 0x95: - case 0x96: - case 0x97: - return get_cbor_array(static_cast(static_cast(current) & 0x1Fu)); - - case 0x98: // array (one-byte uint8_t for n follows) - { - std::uint8_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); - } - - case 0x99: // array (two-byte uint16_t for n follow) - { - std::uint16_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); - } - - case 0x9A: // array (four-byte uint32_t for n follow) - { - std::uint32_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); - } - - case 0x9B: // array (eight-byte uint64_t for n follow) - { - std::uint64_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_array(static_cast(len)); - } - - case 0x9F: // array (indefinite length) - return get_cbor_array(std::size_t(-1)); - - // map (0x00..0x17 pairs of data items follow) - case 0xA0: - case 0xA1: - case 0xA2: - case 0xA3: - case 0xA4: - case 0xA5: - case 0xA6: - case 0xA7: - case 0xA8: - case 0xA9: - case 0xAA: - case 0xAB: - case 0xAC: - case 0xAD: - case 0xAE: - case 0xAF: - case 0xB0: - case 0xB1: - case 0xB2: - case 0xB3: - case 0xB4: - case 0xB5: - case 0xB6: - case 0xB7: - return get_cbor_object(static_cast(static_cast(current) & 0x1Fu)); - - case 0xB8: // map (one-byte uint8_t for n follows) - { - std::uint8_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); - } - - case 0xB9: // map (two-byte uint16_t for n follow) - { - std::uint16_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); - } - - case 0xBA: // map (four-byte uint32_t for n follow) - { - std::uint32_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); - } - - case 0xBB: // map (eight-byte uint64_t for n follow) - { - std::uint64_t len{}; - return get_number(input_format_t::cbor, len) && get_cbor_object(static_cast(len)); - } - - case 0xBF: // map (indefinite length) - return get_cbor_object(std::size_t(-1)); - - case 0xC6: // tagged item - case 0xC7: - case 0xC8: - case 0xC9: - case 0xCA: - case 0xCB: - case 0xCC: - case 0xCD: - case 0xCE: - case 0xCF: - case 0xD0: - case 0xD1: - case 0xD2: - case 0xD3: - case 0xD4: - case 0xD8: // tagged item (1 bytes follow) - case 0xD9: // tagged item (2 bytes follow) - case 0xDA: // tagged item (4 bytes follow) - case 0xDB: // tagged item (8 bytes follow) - { - switch (tag_handler) - { - 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(input_format_t::cbor, "invalid byte: 0x" + last_token, "value"))); - } - - case cbor_tag_handler_t::ignore: - { - switch (current) - { - case 0xD8: - { - std::uint8_t len{}; - get_number(input_format_t::cbor, len); - break; - } - case 0xD9: - { - std::uint16_t len{}; - get_number(input_format_t::cbor, len); - break; - } - case 0xDA: - { - std::uint32_t len{}; - get_number(input_format_t::cbor, len); - break; - } - case 0xDB: - { - std::uint64_t len{}; - get_number(input_format_t::cbor, len); - break; - } - default: - break; - } - return parse_cbor_internal(true, tag_handler); - } - - default: // LCOV_EXCL_LINE - JSON_ASSERT(false); // LCOV_EXCL_LINE - } - } - - case 0xF4: // false - return sax->boolean(false); - - case 0xF5: // true - return sax->boolean(true); - - case 0xF6: // null - return sax->null(); - - case 0xF9: // Half-Precision Float (two-byte IEEE 754) - { - const auto byte1_raw = get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number"))) - { - return false; - } - const auto byte2_raw = get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number"))) - { - return false; - } - - const auto byte1 = static_cast(byte1_raw); - const auto byte2 = static_cast(byte2_raw); - - // code from RFC 7049, Appendix D, Figure 3: - // As half-precision floating-point numbers were only added - // to IEEE 754 in 2008, today's programming platforms often - // still only have limited support for them. It is very - // easy to include at least decoding support for them even - // without such support. An example of a small decoder for - // half-precision floating-point numbers in the C language - // is shown in Fig. 3. - const auto half = static_cast((byte1 << 8u) + byte2); - const double val = [&half] - { - const int exp = (half >> 10u) & 0x1Fu; - const unsigned int mant = half & 0x3FFu; - JSON_ASSERT(0 <= exp&& exp <= 32); - JSON_ASSERT(mant <= 1024); - switch (exp) - { - case 0: - return std::ldexp(mant, -24); - case 31: - return (mant == 0) - ? std::numeric_limits::infinity() - : std::numeric_limits::quiet_NaN(); - default: - return std::ldexp(mant + 1024, exp - 25); - } - }(); - return sax->number_float((half & 0x8000u) != 0 - ? static_cast(-val) - : static_cast(val), ""); - } - - case 0xFA: // Single-Precision Float (four-byte IEEE 754) - { - float number{}; - return get_number(input_format_t::cbor, number) && sax->number_float(static_cast(number), ""); - } - - case 0xFB: // Double-Precision Float (eight-byte IEEE 754) - { - double number{}; - return get_number(input_format_t::cbor, number) && sax->number_float(static_cast(number), ""); - } - - 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(input_format_t::cbor, "invalid byte: 0x" + last_token, "value"))); - } - } - } - - /*! - @brief reads a CBOR string - - This function first reads starting bytes to determine the expected - string length and then copies this number of bytes into a string. - Additionally, CBOR's strings with indefinite lengths are supported. - - @param[out] result created string - - @return whether string creation completed - */ - bool get_cbor_string(string_t& result) - { - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string"))) - { - return false; - } - - switch (current) - { - // UTF-8 string (0x00..0x17 bytes follow) - case 0x60: - case 0x61: - case 0x62: - case 0x63: - case 0x64: - case 0x65: - case 0x66: - case 0x67: - case 0x68: - case 0x69: - case 0x6A: - case 0x6B: - case 0x6C: - case 0x6D: - case 0x6E: - case 0x6F: - case 0x70: - case 0x71: - case 0x72: - case 0x73: - case 0x74: - case 0x75: - case 0x76: - case 0x77: - { - return get_string(input_format_t::cbor, static_cast(current) & 0x1Fu, result); - } - - case 0x78: // UTF-8 string (one-byte uint8_t for n follows) - { - std::uint8_t len{}; - return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); - } - - case 0x79: // UTF-8 string (two-byte uint16_t for n follow) - { - std::uint16_t len{}; - return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); - } - - case 0x7A: // UTF-8 string (four-byte uint32_t for n follow) - { - std::uint32_t len{}; - return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); - } - - case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow) - { - std::uint64_t len{}; - return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); - } - - case 0x7F: // UTF-8 string (indefinite length) - { - while (get() != 0xFF) - { - string_t chunk; - if (!get_cbor_string(chunk)) - { - return false; - } - result.append(chunk); - } - return true; - } - - default: - { - auto last_token = get_token_string(); - return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::cbor, "expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x" + last_token, "string"))); - } - } - } - - /*! - @brief reads a CBOR byte array - - This function first reads starting bytes to determine the expected - byte array length and then copies this number of bytes into the byte array. - Additionally, CBOR's byte arrays with indefinite lengths are supported. - - @param[out] result created byte array - - @return whether byte array creation completed - */ - bool get_cbor_binary(binary_t& result) - { - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary"))) - { - return false; - } - - switch (current) - { - // Binary data (0x00..0x17 bytes follow) - case 0x40: - case 0x41: - case 0x42: - case 0x43: - case 0x44: - case 0x45: - case 0x46: - case 0x47: - case 0x48: - case 0x49: - case 0x4A: - case 0x4B: - case 0x4C: - case 0x4D: - case 0x4E: - case 0x4F: - case 0x50: - case 0x51: - case 0x52: - case 0x53: - case 0x54: - case 0x55: - case 0x56: - case 0x57: - { - return get_binary(input_format_t::cbor, static_cast(current) & 0x1Fu, result); - } - - case 0x58: // Binary data (one-byte uint8_t for n follows) - { - std::uint8_t len{}; - return get_number(input_format_t::cbor, len) && - get_binary(input_format_t::cbor, len, result); - } - - case 0x59: // Binary data (two-byte uint16_t for n follow) - { - std::uint16_t len{}; - return get_number(input_format_t::cbor, len) && - get_binary(input_format_t::cbor, len, result); - } - - case 0x5A: // Binary data (four-byte uint32_t for n follow) - { - std::uint32_t len{}; - return get_number(input_format_t::cbor, len) && - get_binary(input_format_t::cbor, len, result); - } - - case 0x5B: // Binary data (eight-byte uint64_t for n follow) - { - std::uint64_t len{}; - return get_number(input_format_t::cbor, len) && - get_binary(input_format_t::cbor, len, result); - } - - case 0x5F: // Binary data (indefinite length) - { - while (get() != 0xFF) - { - binary_t chunk; - if (!get_cbor_binary(chunk)) - { - return false; - } - result.insert(result.end(), chunk.begin(), chunk.end()); - } - return true; - } - - default: - { - auto last_token = get_token_string(); - return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::cbor, "expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x" + last_token, "binary"))); - } - } - } - - /*! - @param[in] len the length of the array or std::size_t(-1) for an - array of indefinite size - @return whether array creation completed - */ - bool get_cbor_array(const std::size_t len) - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len))) - { - return false; - } - - if (len != std::size_t(-1)) - { - for (std::size_t i = 0; i < len; ++i) - { - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal())) - { - return false; - } - } - } - else - { - while (get() != 0xFF) - { - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal(false))) - { - return false; - } - } - } - - return sax->end_array(); - } - - /*! - @param[in] len the length of the object or std::size_t(-1) for an - object of indefinite size - @return whether object creation completed - */ - bool get_cbor_object(const std::size_t len) - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len))) - { - return false; - } - - string_t key; - if (len != std::size_t(-1)) - { - for (std::size_t i = 0; i < len; ++i) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!get_cbor_string(key) || !sax->key(key))) - { - return false; - } - - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal())) - { - return false; - } - key.clear(); - } - } - else - { - while (get() != 0xFF) - { - if (JSON_HEDLEY_UNLIKELY(!get_cbor_string(key) || !sax->key(key))) - { - return false; - } - - if (JSON_HEDLEY_UNLIKELY(!parse_cbor_internal())) - { - return false; - } - key.clear(); - } - } - - return sax->end_object(); - } - - ///////////// - // MsgPack // - ///////////// - - /*! - @return whether a valid MessagePack value was passed to the SAX parser - */ - bool parse_msgpack_internal() - { - switch (get()) - { - // EOF - case std::char_traits::eof(): - return unexpect_eof(input_format_t::msgpack, "value"); - - // positive fixint - case 0x00: - case 0x01: - case 0x02: - case 0x03: - case 0x04: - case 0x05: - case 0x06: - case 0x07: - case 0x08: - case 0x09: - case 0x0A: - case 0x0B: - case 0x0C: - case 0x0D: - case 0x0E: - case 0x0F: - case 0x10: - case 0x11: - case 0x12: - case 0x13: - case 0x14: - case 0x15: - case 0x16: - case 0x17: - case 0x18: - case 0x19: - case 0x1A: - case 0x1B: - case 0x1C: - case 0x1D: - case 0x1E: - case 0x1F: - case 0x20: - case 0x21: - case 0x22: - case 0x23: - case 0x24: - case 0x25: - case 0x26: - case 0x27: - case 0x28: - case 0x29: - case 0x2A: - case 0x2B: - case 0x2C: - case 0x2D: - case 0x2E: - case 0x2F: - case 0x30: - case 0x31: - case 0x32: - case 0x33: - case 0x34: - case 0x35: - case 0x36: - case 0x37: - case 0x38: - case 0x39: - case 0x3A: - case 0x3B: - case 0x3C: - case 0x3D: - case 0x3E: - case 0x3F: - case 0x40: - case 0x41: - case 0x42: - case 0x43: - case 0x44: - case 0x45: - case 0x46: - case 0x47: - case 0x48: - case 0x49: - case 0x4A: - case 0x4B: - case 0x4C: - case 0x4D: - case 0x4E: - case 0x4F: - case 0x50: - case 0x51: - case 0x52: - case 0x53: - case 0x54: - case 0x55: - case 0x56: - case 0x57: - case 0x58: - case 0x59: - case 0x5A: - case 0x5B: - case 0x5C: - case 0x5D: - case 0x5E: - case 0x5F: - case 0x60: - case 0x61: - case 0x62: - case 0x63: - case 0x64: - case 0x65: - case 0x66: - case 0x67: - case 0x68: - case 0x69: - case 0x6A: - case 0x6B: - case 0x6C: - case 0x6D: - case 0x6E: - case 0x6F: - case 0x70: - case 0x71: - case 0x72: - case 0x73: - case 0x74: - case 0x75: - case 0x76: - case 0x77: - case 0x78: - case 0x79: - case 0x7A: - case 0x7B: - case 0x7C: - case 0x7D: - case 0x7E: - case 0x7F: - return sax->number_unsigned(static_cast(current)); - - // fixmap - case 0x80: - case 0x81: - case 0x82: - case 0x83: - case 0x84: - case 0x85: - case 0x86: - case 0x87: - case 0x88: - case 0x89: - case 0x8A: - case 0x8B: - case 0x8C: - case 0x8D: - case 0x8E: - case 0x8F: - return get_msgpack_object(static_cast(static_cast(current) & 0x0Fu)); - - // fixarray - case 0x90: - case 0x91: - case 0x92: - case 0x93: - case 0x94: - case 0x95: - case 0x96: - case 0x97: - case 0x98: - case 0x99: - case 0x9A: - case 0x9B: - case 0x9C: - case 0x9D: - case 0x9E: - case 0x9F: - return get_msgpack_array(static_cast(static_cast(current) & 0x0Fu)); - - // fixstr - case 0xA0: - case 0xA1: - case 0xA2: - case 0xA3: - case 0xA4: - case 0xA5: - case 0xA6: - case 0xA7: - case 0xA8: - case 0xA9: - case 0xAA: - case 0xAB: - case 0xAC: - case 0xAD: - case 0xAE: - case 0xAF: - case 0xB0: - case 0xB1: - case 0xB2: - case 0xB3: - case 0xB4: - case 0xB5: - case 0xB6: - case 0xB7: - case 0xB8: - case 0xB9: - case 0xBA: - case 0xBB: - case 0xBC: - case 0xBD: - case 0xBE: - case 0xBF: - case 0xD9: // str 8 - case 0xDA: // str 16 - case 0xDB: // str 32 - { - string_t s; - return get_msgpack_string(s) && sax->string(s); - } - - case 0xC0: // nil - return sax->null(); - - case 0xC2: // false - return sax->boolean(false); - - case 0xC3: // true - return sax->boolean(true); - - case 0xC4: // bin 8 - case 0xC5: // bin 16 - case 0xC6: // bin 32 - case 0xC7: // ext 8 - case 0xC8: // ext 16 - case 0xC9: // ext 32 - case 0xD4: // fixext 1 - case 0xD5: // fixext 2 - case 0xD6: // fixext 4 - case 0xD7: // fixext 8 - case 0xD8: // fixext 16 - { - binary_t b; - return get_msgpack_binary(b) && sax->binary(b); - } - - case 0xCA: // float 32 - { - float number{}; - return get_number(input_format_t::msgpack, number) && sax->number_float(static_cast(number), ""); - } - - case 0xCB: // float 64 - { - double number{}; - return get_number(input_format_t::msgpack, number) && sax->number_float(static_cast(number), ""); - } - - case 0xCC: // uint 8 - { - std::uint8_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); - } - - case 0xCD: // uint 16 - { - std::uint16_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); - } - - case 0xCE: // uint 32 - { - std::uint32_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); - } - - case 0xCF: // uint 64 - { - std::uint64_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number); - } - - case 0xD0: // int 8 - { - std::int8_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_integer(number); - } - - case 0xD1: // int 16 - { - std::int16_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_integer(number); - } - - case 0xD2: // int 32 - { - std::int32_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_integer(number); - } - - case 0xD3: // int 64 - { - std::int64_t number{}; - return get_number(input_format_t::msgpack, number) && sax->number_integer(number); - } - - case 0xDC: // array 16 - { - std::uint16_t len{}; - return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast(len)); - } - - case 0xDD: // array 32 - { - std::uint32_t len{}; - return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast(len)); - } - - case 0xDE: // map 16 - { - std::uint16_t len{}; - return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast(len)); - } - - case 0xDF: // map 32 - { - std::uint32_t len{}; - return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast(len)); - } - - // negative fixint - case 0xE0: - case 0xE1: - case 0xE2: - case 0xE3: - case 0xE4: - case 0xE5: - case 0xE6: - case 0xE7: - case 0xE8: - case 0xE9: - case 0xEA: - case 0xEB: - case 0xEC: - case 0xED: - case 0xEE: - case 0xEF: - case 0xF0: - case 0xF1: - case 0xF2: - case 0xF3: - case 0xF4: - case 0xF5: - case 0xF6: - case 0xF7: - case 0xF8: - case 0xF9: - case 0xFA: - case 0xFB: - case 0xFC: - case 0xFD: - case 0xFE: - case 0xFF: - return sax->number_integer(static_cast(current)); - - 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(input_format_t::msgpack, "invalid byte: 0x" + last_token, "value"))); - } - } - } - - /*! - @brief reads a MessagePack string - - This function first reads starting bytes to determine the expected - string length and then copies this number of bytes into a string. - - @param[out] result created string - - @return whether string creation completed - */ - bool get_msgpack_string(string_t& result) - { - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::msgpack, "string"))) - { - return false; - } - - switch (current) - { - // fixstr - case 0xA0: - case 0xA1: - case 0xA2: - case 0xA3: - case 0xA4: - case 0xA5: - case 0xA6: - case 0xA7: - case 0xA8: - case 0xA9: - case 0xAA: - case 0xAB: - case 0xAC: - case 0xAD: - case 0xAE: - case 0xAF: - case 0xB0: - case 0xB1: - case 0xB2: - case 0xB3: - case 0xB4: - case 0xB5: - case 0xB6: - case 0xB7: - case 0xB8: - case 0xB9: - case 0xBA: - case 0xBB: - case 0xBC: - case 0xBD: - case 0xBE: - case 0xBF: - { - return get_string(input_format_t::msgpack, static_cast(current) & 0x1Fu, result); - } - - case 0xD9: // str 8 - { - std::uint8_t len{}; - return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result); - } - - case 0xDA: // str 16 - { - std::uint16_t len{}; - return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result); - } - - case 0xDB: // str 32 - { - std::uint32_t len{}; - return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result); - } - - default: - { - auto last_token = get_token_string(); - return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::msgpack, "expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0x" + last_token, "string"))); - } - } - } - - /*! - @brief reads a MessagePack byte array - - This function first reads starting bytes to determine the expected - byte array length and then copies this number of bytes into a byte array. - - @param[out] result created byte array - - @return whether byte array creation completed - */ - bool get_msgpack_binary(binary_t& result) - { - // helper function to set the subtype - auto assign_and_return_true = [&result](std::int8_t subtype) - { - result.set_subtype(static_cast(subtype)); - return true; - }; - - switch (current) - { - case 0xC4: // bin 8 - { - std::uint8_t len{}; - return get_number(input_format_t::msgpack, len) && - get_binary(input_format_t::msgpack, len, result); - } - - case 0xC5: // bin 16 - { - std::uint16_t len{}; - return get_number(input_format_t::msgpack, len) && - get_binary(input_format_t::msgpack, len, result); - } - - case 0xC6: // bin 32 - { - std::uint32_t len{}; - return get_number(input_format_t::msgpack, len) && - get_binary(input_format_t::msgpack, len, result); - } - - case 0xC7: // ext 8 - { - std::uint8_t len{}; - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, len) && - get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, len, result) && - assign_and_return_true(subtype); - } - - case 0xC8: // ext 16 - { - std::uint16_t len{}; - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, len) && - get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, len, result) && - assign_and_return_true(subtype); - } - - case 0xC9: // ext 32 - { - std::uint32_t len{}; - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, len) && - get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, len, result) && - assign_and_return_true(subtype); - } - - case 0xD4: // fixext 1 - { - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, 1, result) && - assign_and_return_true(subtype); - } - - case 0xD5: // fixext 2 - { - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, 2, result) && - assign_and_return_true(subtype); - } - - case 0xD6: // fixext 4 - { - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, 4, result) && - assign_and_return_true(subtype); - } - - case 0xD7: // fixext 8 - { - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, 8, result) && - assign_and_return_true(subtype); - } - - case 0xD8: // fixext 16 - { - std::int8_t subtype{}; - return get_number(input_format_t::msgpack, subtype) && - get_binary(input_format_t::msgpack, 16, result) && - assign_and_return_true(subtype); - } - - default: // LCOV_EXCL_LINE - return false; // LCOV_EXCL_LINE - } - } - - /*! - @param[in] len the length of the array - @return whether array creation completed - */ - bool get_msgpack_array(const std::size_t len) - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len))) - { - return false; - } - - for (std::size_t i = 0; i < len; ++i) - { - if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal())) - { - return false; - } - } - - return sax->end_array(); - } - - /*! - @param[in] len the length of the object - @return whether object creation completed - */ - bool get_msgpack_object(const std::size_t len) - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len))) - { - return false; - } - - string_t key; - for (std::size_t i = 0; i < len; ++i) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key))) - { - return false; - } - - if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal())) - { - return false; - } - key.clear(); - } - - return sax->end_object(); - } - - //////////// - // UBJSON // - //////////// - - /*! - @param[in] get_char whether a new character should be retrieved from the - input (true, default) or whether the last read - character should be considered instead - - @return whether a valid UBJSON value was passed to the SAX parser - */ - bool parse_ubjson_internal(const bool get_char = true) - { - return get_ubjson_value(get_char ? get_ignore_noop() : current); - } - - /*! - @brief reads a UBJSON string - - This function is either called after reading the 'S' byte explicitly - indicating a string, or in case of an object key where the 'S' byte can be - left out. - - @param[out] result created string - @param[in] get_char whether a new character should be retrieved from the - input (true, default) or whether the last read - character should be considered instead - - @return whether string creation completed - */ - bool get_ubjson_string(string_t& result, const bool get_char = true) - { - if (get_char) - { - get(); // TODO(niels): may we ignore N here? - } - - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "value"))) - { - return false; - } - - switch (current) - { - case 'U': - { - std::uint8_t len{}; - return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); - } - - case 'i': - { - std::int8_t len{}; - return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); - } - - case 'I': - { - std::int16_t len{}; - return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); - } - - case 'l': - { - std::int32_t len{}; - return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); - } - - case 'L': - { - std::int64_t len{}; - return get_number(input_format_t::ubjson, len) && get_string(input_format_t::ubjson, len, result); - } - - default: - auto last_token = get_token_string(); - return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::ubjson, "expected length type specification (U, i, I, l, L); last byte: 0x" + last_token, "string"))); - } - } - - /*! - @param[out] result determined size - @return whether size determination completed - */ - bool get_ubjson_size_value(std::size_t& result) - { - switch (get_ignore_noop()) - { - case 'U': - { - std::uint8_t number{}; - if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) - { - return false; - } - result = static_cast(number); - return true; - } - - case 'i': - { - std::int8_t number{}; - if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) - { - return false; - } - result = static_cast(number); - return true; - } - - case 'I': - { - std::int16_t number{}; - if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) - { - return false; - } - result = static_cast(number); - return true; - } - - case 'l': - { - std::int32_t number{}; - if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) - { - return false; - } - result = static_cast(number); - return true; - } - - case 'L': - { - std::int64_t number{}; - if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::ubjson, number))) - { - return false; - } - result = static_cast(number); - return true; - } - - default: - { - auto last_token = get_token_string(); - return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format_t::ubjson, "expected length type specification (U, i, I, l, L) after '#'; last byte: 0x" + last_token, "size"))); - } - } - } - - /*! - @brief determine the type and size for a container - - In the optimized UBJSON format, a type and a size can be provided to allow - for a more compact representation. - - @param[out] result pair of the size and the type - - @return whether pair creation completed - */ - bool get_ubjson_size_type(std::pair& result) - { - result.first = string_t::npos; // size - result.second = 0; // type - - get_ignore_noop(); - - if (current == '$') - { - result.second = get(); // must not ignore 'N', because 'N' maybe the type - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "type"))) - { - return false; - } - - get_ignore_noop(); - if (JSON_HEDLEY_UNLIKELY(current != '#')) - { - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "value"))) - { - return false; - } - auto last_token = get_token_string(); - return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read, exception_message(input_format_t::ubjson, "expected '#' after type information; last byte: 0x" + last_token, "size"))); - } - - return get_ubjson_size_value(result.first); - } - - if (current == '#') - { - return get_ubjson_size_value(result.first); - } - - return true; - } - - /*! - @param prefix the previously read or set type prefix - @return whether value creation completed - */ - bool get_ubjson_value(const char_int_type prefix) - { - switch (prefix) - { - case std::char_traits::eof(): // EOF - return unexpect_eof(input_format_t::ubjson, "value"); - - case 'T': // true - return sax->boolean(true); - case 'F': // false - return sax->boolean(false); - - case 'Z': // null - return sax->null(); - - case 'U': - { - std::uint8_t number{}; - return get_number(input_format_t::ubjson, number) && sax->number_unsigned(number); - } - - case 'i': - { - std::int8_t number{}; - return get_number(input_format_t::ubjson, number) && sax->number_integer(number); - } - - case 'I': - { - std::int16_t number{}; - return get_number(input_format_t::ubjson, number) && sax->number_integer(number); - } - - case 'l': - { - std::int32_t number{}; - return get_number(input_format_t::ubjson, number) && sax->number_integer(number); - } - - case 'L': - { - std::int64_t number{}; - return get_number(input_format_t::ubjson, number) && sax->number_integer(number); - } - - case 'd': - { - float number{}; - return get_number(input_format_t::ubjson, number) && sax->number_float(static_cast(number), ""); - } - - case 'D': - { - double number{}; - return get_number(input_format_t::ubjson, number) && sax->number_float(static_cast(number), ""); - } - - case 'H': - { - return get_ubjson_high_precision_number(); - } - - case 'C': // char - { - get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "char"))) - { - return false; - } - 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(input_format_t::ubjson, "byte after 'C' must be in range 0x00..0x7F; last byte: 0x" + last_token, "char"))); - } - string_t s(1, static_cast(current)); - return sax->string(s); - } - - case 'S': // string - { - string_t s; - return get_ubjson_string(s) && sax->string(s); - } - - case '[': // array - return get_ubjson_array(); - - case '{': // object - return get_ubjson_object(); - - 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(input_format_t::ubjson, "invalid byte: 0x" + last_token, "value"))); - } - } - } - - /*! - @return whether array creation completed - */ - bool get_ubjson_array() - { - std::pair size_and_type; - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type))) - { - return false; - } - - if (size_and_type.first != string_t::npos) - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_array(size_and_type.first))) - { - return false; - } - - if (size_and_type.second != 0) - { - if (size_and_type.second != 'N') - { - for (std::size_t i = 0; i < size_and_type.first; ++i) - { - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_value(size_and_type.second))) - { - return false; - } - } - } - } - else - { - for (std::size_t i = 0; i < size_and_type.first; ++i) - { - if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal())) - { - return false; - } - } - } - } - else - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_array(std::size_t(-1)))) - { - return false; - } - - while (current != ']') - { - if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal(false))) - { - return false; - } - get_ignore_noop(); - } - } - - return sax->end_array(); - } - - /*! - @return whether object creation completed - */ - bool get_ubjson_object() - { - std::pair size_and_type; - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type))) - { - return false; - } - - string_t key; - if (size_and_type.first != string_t::npos) - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_object(size_and_type.first))) - { - return false; - } - - if (size_and_type.second != 0) - { - for (std::size_t i = 0; i < size_and_type.first; ++i) - { - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key) || !sax->key(key))) - { - return false; - } - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_value(size_and_type.second))) - { - return false; - } - key.clear(); - } - } - else - { - for (std::size_t i = 0; i < size_and_type.first; ++i) - { - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key) || !sax->key(key))) - { - return false; - } - if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal())) - { - return false; - } - key.clear(); - } - } - } - else - { - if (JSON_HEDLEY_UNLIKELY(!sax->start_object(std::size_t(-1)))) - { - return false; - } - - while (current != '}') - { - if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key, false) || !sax->key(key))) - { - return false; - } - if (JSON_HEDLEY_UNLIKELY(!parse_ubjson_internal())) - { - return false; - } - get_ignore_noop(); - key.clear(); - } - } - - return sax->end_object(); - } - - // Note, no reader for UBJSON binary types is implemented because they do - // not exist - - bool get_ubjson_high_precision_number() - { - // get size of following number string - std::size_t size{}; - auto res = get_ubjson_size_value(size); - if (JSON_HEDLEY_UNLIKELY(!res)) - { - return res; - } - - // get number string - std::vector number_vector; - for (std::size_t i = 0; i < size; ++i) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::ubjson, "number"))) - { - return false; - } - number_vector.push_back(static_cast(current)); - } - - // parse number string - auto number_ia = detail::input_adapter(std::forward(number_vector)); - auto number_lexer = detail::lexer(std::move(number_ia), false); - const auto result_number = number_lexer.scan(); - const auto number_string = number_lexer.get_token_string(); - const auto result_remainder = number_lexer.scan(); - - using token_type = typename detail::lexer_base::token_type; - - 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, exception_message(input_format_t::ubjson, "invalid number text: " + number_lexer.get_token_string(), "high-precision number"))); - } - - switch (result_number) - { - case token_type::value_integer: - return sax->number_integer(number_lexer.get_number_integer()); - case token_type::value_unsigned: - return sax->number_unsigned(number_lexer.get_number_unsigned()); - case token_type::value_float: - return sax->number_float(number_lexer.get_number_float(), std::move(number_string)); - default: - return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read, exception_message(input_format_t::ubjson, "invalid number text: " + number_lexer.get_token_string(), "high-precision number"))); - } - } - - /////////////////////// - // Utility functions // - /////////////////////// - - /*! - @brief get next character from the input - - This function provides the interface to the used input adapter. It does - not throw in case the input reached EOF, but returns a -'ve valued - `std::char_traits::eof()` in that case. - - @return character read from the input - */ - char_int_type get() - { - ++chars_read; - return current = ia.get_character(); - } - - /*! - @return character read from the input after ignoring all 'N' entries - */ - char_int_type get_ignore_noop() - { - do - { - get(); - } - while (current == 'N'); - - return current; - } - - /* - @brief read a number from the input - - @tparam NumberType the type of the number - @param[in] format the current format (for diagnostics) - @param[out] result number of type @a NumberType - - @return whether conversion completed - - @note This function needs to respect the system's endianess, because - bytes in CBOR, MessagePack, and UBJSON are stored in network order - (big endian) and therefore need reordering on little endian systems. - */ - template - bool get_number(const input_format_t format, NumberType& result) - { - // step 1: read input into array with system's byte order - std::array vec; - for (std::size_t i = 0; i < sizeof(NumberType); ++i) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "number"))) - { - return false; - } - - // reverse byte order prior to conversion if necessary - if (is_little_endian != InputIsLittleEndian) - { - vec[sizeof(NumberType) - i - 1] = static_cast(current); - } - else - { - vec[i] = static_cast(current); // LCOV_EXCL_LINE - } - } - - // step 2: convert array into number of type T and return - std::memcpy(&result, vec.data(), sizeof(NumberType)); - return true; - } - - /*! - @brief create a string by reading characters from the input - - @tparam NumberType the type of the number - @param[in] format the current format (for diagnostics) - @param[in] len number of characters to read - @param[out] result string created by reading @a len bytes - - @return whether string creation completed - - @note We can not reserve @a len bytes for the result, because @a len - may be too large. Usually, @ref unexpect_eof() detects the end of - the input before we run out of string memory. - */ - template - bool get_string(const input_format_t format, - const NumberType len, - string_t& result) - { - bool success = true; - for (NumberType i = 0; i < len; i++) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "string"))) - { - success = false; - break; - } - result.push_back(static_cast(current)); - }; - return success; - } - - /*! - @brief create a byte array by reading bytes from the input - - @tparam NumberType the type of the number - @param[in] format the current format (for diagnostics) - @param[in] len number of bytes to read - @param[out] result byte array created by reading @a len bytes - - @return whether byte array creation completed - - @note We can not reserve @a len bytes for the result, because @a len - may be too large. Usually, @ref unexpect_eof() detects the end of - the input before we run out of memory. - */ - template - bool get_binary(const input_format_t format, - const NumberType len, - binary_t& result) - { - bool success = true; - for (NumberType i = 0; i < len; i++) - { - get(); - if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "binary"))) - { - success = false; - break; - } - result.push_back(static_cast(current)); - } - return success; - } - - /*! - @param[in] format the current format (for diagnostics) - @param[in] context further context information (for diagnostics) - @return whether the last read character is not EOF - */ - JSON_HEDLEY_NON_NULL(3) - bool unexpect_eof(const input_format_t format, const char* context) const - { - if (JSON_HEDLEY_UNLIKELY(current == std::char_traits::eof())) - { - return sax->parse_error(chars_read, "", - parse_error::create(110, chars_read, exception_message(format, "unexpected end of input", context))); - } - return true; - } - - /*! - @return a string representation of the last read byte - */ - std::string get_token_string() const - { - std::array cr{{}}; - (std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast(current)); - return std::string{cr.data()}; - } - - /*! - @param[in] format the current format - @param[in] detail a detailed error message - @param[in] context further context information - @return a message string to use in the parse_error exceptions - */ - std::string exception_message(const input_format_t format, - const std::string& detail, - const std::string& context) const - { - std::string error_msg = "syntax error while parsing "; - - switch (format) - { - case input_format_t::cbor: - error_msg += "CBOR"; - break; - - case input_format_t::msgpack: - error_msg += "MessagePack"; - break; - - case input_format_t::ubjson: - error_msg += "UBJSON"; - break; - - case input_format_t::bson: - error_msg += "BSON"; - break; - - default: // LCOV_EXCL_LINE - JSON_ASSERT(false); // LCOV_EXCL_LINE - } - - return error_msg + " " + context + ": " + detail; - } - - private: - /// input adapter - InputAdapterType ia; - - /// the current character - char_int_type current = std::char_traits::eof(); - - /// the number of characters read - std::size_t chars_read = 0; - - /// whether we can assume little endianess - const bool is_little_endian = little_endianess(); - - /// the SAX parser - json_sax_t* sax = nullptr; -}; -} // namespace detail -} // namespace nlohmann - -// #include - -// #include - // #include @@ -14038,17 +13985,7 @@ class binary_writer } else { - if (add_prefix) - { - oa->write_character(to_char_type('H')); // high-precision number - } - - const auto number = BasicJsonType(n).dump(); - write_number_with_ubjson_prefix(number.size(), true); - for (std::size_t i = 0; i < number.size(); ++i) - { - oa->write_character(to_char_type(static_cast(number[i]))); - } + JSON_THROW(out_of_range::create(407, "integer number " + std::to_string(n) + " cannot be represented by UBJSON as it does not fit int64")); } } @@ -14102,23 +14039,19 @@ class binary_writer // LCOV_EXCL_START else { - if (add_prefix) - { - oa->write_character(to_char_type('H')); // high-precision number - } - - const auto number = BasicJsonType(n).dump(); - write_number_with_ubjson_prefix(number.size(), true); - for (std::size_t i = 0; i < number.size(); ++i) - { - oa->write_character(to_char_type(static_cast(number[i]))); - } + JSON_THROW(out_of_range::create(407, "integer number " + std::to_string(n) + " cannot be represented by UBJSON as it does not fit int64")); } // LCOV_EXCL_STOP } /*! @brief determine the type prefix of container values + + @note This function does not need to be 100% accurate when it comes to + integer limits. In case a number exceeds the limits of int64_t, + this will be detected by a later call to function + write_number_with_ubjson_prefix. Therefore, we return 'L' for any + value that does not fit the previous limits. */ CharType ubjson_prefix(const BasicJsonType& j) const noexcept { @@ -14148,12 +14081,8 @@ class binary_writer { return 'l'; } - if ((std::numeric_limits::min)() <= j.m_value.number_integer && j.m_value.number_integer <= (std::numeric_limits::max)()) - { - return 'L'; - } - // anything else is treated as high-precision number - return 'H'; // LCOV_EXCL_LINE + // no check and assume int64_t (see note above) + return 'L'; } case value_t::number_unsigned: @@ -14174,12 +14103,8 @@ class binary_writer { return 'l'; } - if (j.m_value.number_unsigned <= static_cast((std::numeric_limits::max)())) - { - return 'L'; - } - // anything else is treated as high-precision number - return 'H'; // LCOV_EXCL_LINE + // no check and assume int64_t (see note above) + return 'L'; } case value_t::number_float: @@ -16580,7 +16505,7 @@ class basic_json detail::parser_callback_tcb = nullptr, const bool allow_exceptions = true, const bool ignore_comments = false - ) + ) { return ::nlohmann::detail::parser(std::move(adapter), std::move(cb), allow_exceptions, ignore_comments); @@ -23583,7 +23508,6 @@ class basic_json number_unsigned | 256..32767 | int16 | `I` number_unsigned | 32768..2147483647 | int32 | `l` number_unsigned | 2147483648..9223372036854775807 | int64 | `L` - number_unsigned | 2147483649..18446744073709551615 | high-precision | `H` number_float | *any value* | float64 | `D` string | *with shortest length indicator* | string | `S` array | *see notes on optimized format* | array | `[` @@ -23594,6 +23518,7 @@ class basic_json @note The following values can **not** be converted to a UBJSON value: - strings with more than 9223372036854775807 bytes (theoretical) + - unsigned integer numbers above 9223372036854775807 @note The following markers are not used in the conversion: - `Z`: no-op values are not created. @@ -24069,7 +23994,6 @@ class basic_json int16 | number_integer | `I` int32 | number_integer | `l` int64 | number_integer | `L` - high-precision number | number_integer, number_unsigned, or number_float - depends on number string | 'H' string | string | `S` char | string | `C` array | array (optimized values are supported) | `[` @@ -25123,7 +25047,7 @@ template<> inline void swap(nlohmann::json& j1, nlohmann::json& j2) noexcept( is_nothrow_move_constructible::value&& is_nothrow_move_assignable::value - ) +) { j1.swap(j2); } diff --git a/test/CMakeLists.txt b/test/CMakeLists.txt index 76ba31d88..9ce1594c1 100644 --- a/test/CMakeLists.txt +++ b/test/CMakeLists.txt @@ -151,7 +151,7 @@ foreach(file ${files}) $<$>:-Wno-deprecated;-Wno-float-equal> $<$:-Wno-deprecated-declarations> ) - target_include_directories(${testcase} PRIVATE ${CMAKE_BINARY_DIR}/include thirdparty/doctest thirdparty/fifo_map) + target_include_directories(${testcase} PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/utils ${CMAKE_BINARY_DIR}/include thirdparty/doctest thirdparty/fifo_map) target_link_libraries(${testcase} PRIVATE ${NLOHMANN_JSON_TARGET_NAME}) if (JSON_Coverage) diff --git a/test/cmake_target_include_directories/project/Bar.cpp b/test/cmake_target_include_directories/project/Bar.cpp new file mode 100644 index 000000000..ed39e284c --- /dev/null +++ b/test/cmake_target_include_directories/project/Bar.cpp @@ -0,0 +1,3 @@ +#include "Bar.hpp" + +class Bar; diff --git a/test/cmake_target_include_directories/project/Bar.hpp b/test/cmake_target_include_directories/project/Bar.hpp new file mode 100644 index 000000000..bdb1d9b5c --- /dev/null +++ b/test/cmake_target_include_directories/project/Bar.hpp @@ -0,0 +1,4 @@ +#include +#include "Foo.hpp" + +class Bar : public Foo{}; diff --git a/test/cmake_target_include_directories/project/CMakeLists.txt b/test/cmake_target_include_directories/project/CMakeLists.txt index 20e971a0d..f56786c09 100644 --- a/test/cmake_target_include_directories/project/CMakeLists.txt +++ b/test/cmake_target_include_directories/project/CMakeLists.txt @@ -9,3 +9,13 @@ set_target_properties(with_private_target PROPERTIES CXX_STANDARD 11) add_executable(with_private_system_target main.cpp) target_include_directories(with_private_system_target PRIVATE SYSTEM ${nlohmann_json_source}/include) set_target_properties(with_private_system_target PROPERTIES CXX_STANDARD 11) + +# regression from https://github.com/nlohmann/json/discussions/2281 +add_library(Foo STATIC Foo.cpp Bar.cpp) +target_include_directories(Foo PUBLIC ${CMAKE_CURRENT_SOURCE_DIR} ${nlohmann_json_source}/include) +set_target_properties(Foo PROPERTIES CXX_STANDARD 11) + +add_library(Bar STATIC Bar.cpp) +target_link_libraries(Bar PRIVATE Foo) +target_include_directories(Bar PUBLIC ${CMAKE_CURRENT_SOURCE_DIR} ${nlohmann_json_source}/include) +set_target_properties(Bar PROPERTIES CXX_STANDARD 11) diff --git a/test/cmake_target_include_directories/project/Foo.cpp b/test/cmake_target_include_directories/project/Foo.cpp new file mode 100644 index 000000000..6a2ff91ac --- /dev/null +++ b/test/cmake_target_include_directories/project/Foo.cpp @@ -0,0 +1,3 @@ +#include "Foo.hpp" + +class Foo; diff --git a/test/cmake_target_include_directories/project/Foo.hpp b/test/cmake_target_include_directories/project/Foo.hpp new file mode 100644 index 000000000..fd6b1ffac --- /dev/null +++ b/test/cmake_target_include_directories/project/Foo.hpp @@ -0,0 +1,4 @@ +#pragma once +#include + +class Foo{}; diff --git a/test/src/unit-bson.cpp b/test/src/unit-bson.cpp index aa3acbc30..80a8012df 100644 --- a/test/src/unit-bson.cpp +++ b/test/src/unit-bson.cpp @@ -35,6 +35,7 @@ using nlohmann::json; #include #include #include +#include TEST_CASE("BSON") { @@ -1263,10 +1264,7 @@ TEST_CASE("BSON roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse BSON file - std::ifstream f_bson(filename + ".bson", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_bson)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".bson"); json j2; CHECK_NOTHROW(j2 = json::from_bson(packed)); @@ -1296,10 +1294,7 @@ TEST_CASE("BSON roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse BSON file - std::ifstream f_bson(filename + ".bson", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_bson)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".bson"); json j2; CHECK_NOTHROW(j2 = json::from_bson({packed.data(), packed.size()})); @@ -1314,10 +1309,7 @@ TEST_CASE("BSON roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse BSON file - std::ifstream f_bson(filename + ".bson", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_bson)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".bson"); { INFO_WITH_TEMP(filename + ": output adapters: std::vector"); diff --git a/test/src/unit-cbor.cpp b/test/src/unit-cbor.cpp index 7eaba84a9..b0c2b04df 100644 --- a/test/src/unit-cbor.cpp +++ b/test/src/unit-cbor.cpp @@ -39,6 +39,7 @@ using nlohmann::json; #include #include #include +#include namespace { @@ -1920,9 +1921,7 @@ TEST_CASE("single CBOR roundtrip") json j1 = json::parse(f_json); // parse CBOR file - std::ifstream f_cbor(filename + ".cbor", std::ios::binary); - std::vector packed((std::istreambuf_iterator(f_cbor)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".cbor"); json j2; CHECK_NOTHROW(j2 = json::from_cbor(packed)); @@ -1994,10 +1993,7 @@ TEST_CASE("CBOR regressions") try { // parse CBOR file - std::ifstream f_cbor(filename, std::ios::binary); - std::vector vec1( - (std::istreambuf_iterator(f_cbor)), - std::istreambuf_iterator()); + auto vec1 = utils::read_binary_file(filename); json j1 = json::from_cbor(vec1); try @@ -2204,10 +2200,7 @@ TEST_CASE("CBOR roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse CBOR file - std::ifstream f_cbor(filename + ".cbor", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_cbor)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".cbor"); json j2; CHECK_NOTHROW(j2 = json::from_cbor(packed)); @@ -2237,10 +2230,7 @@ TEST_CASE("CBOR roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse CBOR file - std::ifstream f_cbor(filename + ".cbor", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_cbor)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".cbor"); json j2; CHECK_NOTHROW(j2 = json::from_cbor({packed.data(), packed.size()})); @@ -2255,10 +2245,7 @@ TEST_CASE("CBOR roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse CBOR file - std::ifstream f_cbor(filename + ".cbor", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_cbor)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".cbor"); if (!exclude_packed.count(filename)) { @@ -2493,15 +2480,11 @@ TEST_CASE("examples from RFC 7049 Appendix A") SECTION("byte arrays") { - std::ifstream f_cbor(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.cbor", std::ios::binary); - std::vector packed((std::istreambuf_iterator(f_cbor)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.cbor"); json j; CHECK_NOTHROW(j = json::from_cbor(packed)); - std::ifstream f_bin(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.out", std::ios::binary); - std::vector expected((std::istreambuf_iterator(f_bin)), - std::istreambuf_iterator()); + auto expected = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.out"); CHECK(j == json::binary(expected)); CHECK(json::to_cbor(json::binary(std::vector {}, 0x42)) == std::vector {0xd8, 0x42, 0x40}); @@ -2722,4 +2705,25 @@ TEST_CASE("Tagged values") CHECK_THROWS_AS(json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore), json::parse_error); } } + + SECTION("tagged binary") + { + // create a binary value of subtype 42 + json j; + j["binary"] = json::binary({0xCA, 0xFE, 0xBA, 0xBE}, 42); + + // convert to CBOR + const auto v = json::to_cbor(j); + CHECK(v == std::vector {0xA1, 0x66, 0x62, 0x69, 0x6E, 0x61, 0x72, 0x79, 0xD8, 0x2A, 0x44, 0xCA, 0xFE, 0xBA, 0xBE}); + + // parse error when parsing tagged value + CHECK_THROWS_AS(json::from_cbor(v), json::parse_error); + CHECK_THROWS_WITH(json::from_cbor(v), "[json.exception.parse_error.112] parse error at byte 9: syntax error while parsing CBOR value: invalid byte: 0xD8"); + + // binary without subtype when tags are ignored + json jb = json::from_cbor(v, true, true, json::cbor_tag_handler_t::ignore); + CHECK(jb.is_object()); + CHECK(jb["binary"].is_binary()); + CHECK(!jb["binary"].get_binary().has_subtype()); + } } diff --git a/test/src/unit-conversions.cpp b/test/src/unit-conversions.cpp index 97a4e6b6f..7ab0e9a39 100644 --- a/test/src/unit-conversions.cpp +++ b/test/src/unit-conversions.cpp @@ -278,8 +278,8 @@ TEST_CASE("value conversion") SECTION("reserve is called on containers that supports it") { // make sure all values are properly copied - json j({1, 2, 3, 4, 5, 6, 7, 8, 9, 10}); - auto v2 = j.get>(); + json j2({1, 2, 3, 4, 5, 6, 7, 8, 9, 10}); + auto v2 = j2.get>(); CHECK(v2.size() == 10); } #endif diff --git a/test/src/unit-msgpack.cpp b/test/src/unit-msgpack.cpp index 2130c8870..c3761fb5b 100644 --- a/test/src/unit-msgpack.cpp +++ b/test/src/unit-msgpack.cpp @@ -37,6 +37,7 @@ using nlohmann::json; #include #include #include +#include namespace { @@ -514,7 +515,7 @@ TEST_CASE("MessagePack") (static_cast(result[2]) << 020) + (static_cast(result[3]) << 010) + static_cast(result[4]); - CHECK(restored == i); + CHECK(static_cast(restored) == i); // roundtrip CHECK(json::from_msgpack(result) == j); @@ -1609,9 +1610,7 @@ TEST_CASE("single MessagePack roundtrip") json j1 = json::parse(f_json); // parse MessagePack file - std::ifstream f_msgpack(filename + ".msgpack", std::ios::binary); - std::vector packed((std::istreambuf_iterator(f_msgpack)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".msgpack"); json j2; CHECK_NOTHROW(j2 = json::from_msgpack(packed)); @@ -1824,10 +1823,7 @@ TEST_CASE("MessagePack roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse MessagePack file - std::ifstream f_msgpack(filename + ".msgpack", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_msgpack)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".msgpack"); json j2; CHECK_NOTHROW(j2 = json::from_msgpack(packed)); @@ -1857,10 +1853,7 @@ TEST_CASE("MessagePack roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse MessagePack file - std::ifstream f_msgpack(filename + ".msgpack", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_msgpack)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".msgpack"); json j2; CHECK_NOTHROW(j2 = json::from_msgpack({packed.data(), packed.size()})); @@ -1875,10 +1868,7 @@ TEST_CASE("MessagePack roundtrips" * doctest::skip()) json j1 = json::parse(f_json); // parse MessagePack file - std::ifstream f_msgpack(filename + ".msgpack", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_msgpack)), - std::istreambuf_iterator()); + auto packed = utils::read_binary_file(filename + ".msgpack"); if (!exclude_packed.count(filename)) { diff --git a/test/src/unit-regression.cpp b/test/src/unit-regression.cpp index 649ac656a..d70114eef 100644 --- a/test/src/unit-regression.cpp +++ b/test/src/unit-regression.cpp @@ -1516,8 +1516,8 @@ TEST_CASE("regression tests") SECTION("issue #838 - incorrect parse error with binary data in keys") { - uint8_t key1[] = { 103, 92, 117, 48, 48, 48, 55, 92, 114, 215, 126, 214, 95, 92, 34, 174, 40, 71, 38, 174, 40, 71, 38, 223, 134, 247, 127 }; - std::string key1_str(key1, key1 + sizeof(key1) / sizeof(key1[0])); + uint8_t key1[] = { 103, 92, 117, 48, 48, 48, 55, 92, 114, 215, 126, 214, 95, 92, 34, 174, 40, 71, 38, 174, 40, 71, 38, 223, 134, 247, 127, 0 }; + std::string key1_str(reinterpret_cast(key1)); json j = key1_str; CHECK_THROWS_AS(j.dump(), json::type_error&); CHECK_THROWS_WITH(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 10: 0x7E"); diff --git a/test/src/unit-ubjson.cpp b/test/src/unit-ubjson.cpp index d55f52e8e..663d8ec1f 100644 --- a/test/src/unit-ubjson.cpp +++ b/test/src/unit-ubjson.cpp @@ -36,6 +36,7 @@ using nlohmann::json; #include #include #include +#include namespace { @@ -2508,11 +2509,8 @@ TEST_CASE("UBJSON roundtrips" * doctest::skip()) std::ifstream f_json(filename); json j1 = json::parse(f_json); - // parse MessagePack file - std::ifstream f_ubjson(filename + ".ubjson", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_ubjson)), - std::istreambuf_iterator()); + // parse UBJSON file + auto packed = utils::read_binary_file(filename + ".ubjson"); json j2; CHECK_NOTHROW(j2 = json::from_ubjson(packed)); @@ -2526,7 +2524,7 @@ TEST_CASE("UBJSON roundtrips" * doctest::skip()) std::ifstream f_json(filename); json j1 = json::parse(f_json); - // parse MessagePack file + // parse UBJSON file std::ifstream f_ubjson(filename + ".ubjson", std::ios::binary); json j2; CHECK_NOTHROW(j2 = json::from_ubjson(f_ubjson)); @@ -2541,11 +2539,8 @@ TEST_CASE("UBJSON roundtrips" * doctest::skip()) std::ifstream f_json(filename); json j1 = json::parse(f_json); - // parse MessagePack file - std::ifstream f_ubjson(filename + ".ubjson", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_ubjson)), - std::istreambuf_iterator()); + // parse UBJSON file + auto packed = utils::read_binary_file(filename + ".ubjson"); json j2; CHECK_NOTHROW(j2 = json::from_ubjson({packed.data(), packed.size()})); @@ -2559,11 +2554,8 @@ TEST_CASE("UBJSON roundtrips" * doctest::skip()) std::ifstream f_json(filename); json j1 = json::parse(f_json); - // parse MessagePack file - std::ifstream f_ubjson(filename + ".ubjson", std::ios::binary); - std::vector packed( - (std::istreambuf_iterator(f_ubjson)), - std::istreambuf_iterator()); + // parse UBJSON file + auto packed = utils::read_binary_file(filename + ".ubjson"); { INFO_WITH_TEMP(filename + ": output adapters: std::vector"); diff --git a/test/utils/test_utils.hpp b/test/utils/test_utils.hpp new file mode 100644 index 000000000..12c260e7b --- /dev/null +++ b/test/utils/test_utils.hpp @@ -0,0 +1,25 @@ +#pragma once + +#include // uint8_t +#include // ifstream, istreambuf_iterator, ios +#include // vector + +namespace utils +{ + +inline std::vector read_binary_file(const std::string& filename) +{ + std::ifstream file(filename, std::ios::binary); + file.unsetf(std::ios::skipws); + + file.seekg(0, std::ios::end); + const auto size = file.tellg(); + file.seekg(0, std::ios::beg); + + std::vector byte_vector; + byte_vector.reserve(static_cast(size)); + byte_vector.insert(byte_vector.begin(), std::istream_iterator(file), std::istream_iterator()); + return byte_vector; +} + +} // namespace utils