From 100f676b3e9d85cedbf90e2995cadf9473b6b0e5 Mon Sep 17 00:00:00 2001 From: Niels Lohmann Date: Mon, 2 Nov 2026 18:23:44 +0100 Subject: [PATCH] Restore the two commits of #6005 that the stack merge dropped (fixes the build of develop) (#6012) * basic_json, iterators, serializer: remove checks that invariants make dead Branch coverage of the test suite and of 24k mutated inputs showed these conditions as never taken; each is implied by the code around it: - copy_object_level(): `src_it != src_object.cend()`; dst was built from exactly src_object.size() unique keys and src_it advances at most once per member - the general comparison operators (equal_general, less_general, three_way_general): the five same-type scalar cases, which the inline fast path of every operator handles before calling them (now an assert); and the NaN half of compares_unordered() in the mixed-type branch, reached only after all six number pairs returned, where only a discarded operand is unordered - serializer, ensure_ascii: the reset of `bytes` under error_handler_t::keep and the surrogate-pair escape in the UTF8_ACCEPT case; every well-formed multi-byte character is escaped by write_u_escapes() before decode() sees it, so decode() only ever accepts DEL here, a single byte of which nothing was buffered (now asserts) - iter_impl(pointer): the if/else chain assigned value-initialized iterators to the value-initialized m_it No change in behaviour: a build that aborts on each removed side passes the test suite, the fuzz corpora and 23.2M dumps of all 1-, 2- and boundary 4-byte strings in both ensure_ascii modes. Signed-off-by: Niels Lohmann * iter_impl: keep the type-dependent initialization in the constructor The check is not needed for correctness (m_it is value-initialized), but without it GCC 13 generates slower iteration loops: a recursive walk over a parsed document takes 0.5-2.7 % longer (callgrind: +1.9 % instructions on twitter.json, +0.95 % on canada.json). Clang generates identical code either way. See the measurements in #6005. Signed-off-by: Niels Lohmann --------- Signed-off-by: Niels Lohmann --- .../nlohmann/detail/iterators/iter_impl.hpp | 3 ++ include/nlohmann/detail/output/serializer.hpp | 17 +++------ include/nlohmann/json.hpp | 15 +++++--- single_include/nlohmann/json.hpp | 35 ++++++++++--------- 4 files changed, 38 insertions(+), 32 deletions(-) diff --git a/include/nlohmann/detail/iterators/iter_impl.hpp b/include/nlohmann/detail/iterators/iter_impl.hpp index 84a850356..6e6cc0ef6 100644 --- a/include/nlohmann/detail/iterators/iter_impl.hpp +++ b/include/nlohmann/detail/iterators/iter_impl.hpp @@ -108,6 +108,9 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci { JSON_ASSERT(m_object != nullptr); + // m_it is already value-initialized, so this is not needed for + // correctness; it is kept because GCC generates faster loops with it + // (iterating a parsed document is 0.5-2.7 % slower without it, #6005) if (m_object->is_object()) { m_it.object_iterator = typename object_t::iterator(); diff --git a/include/nlohmann/detail/output/serializer.hpp b/include/nlohmann/detail/output/serializer.hpp index fc8e2b384..0c004c491 100644 --- a/include/nlohmann/detail/output/serializer.hpp +++ b/include/nlohmann/detail/output/serializer.hpp @@ -1113,21 +1113,14 @@ class serializer { // the code point is at least 0x60 (smaller ones are handled // above) and is not printable ASCII (which the scanner - // copies): it is DEL (0x7F) under EnsureAscii or a non-ASCII - // character + // copies). Under EnsureAscii it is DEL (0x7F): every + // well-formed multi-byte character is escaped by + // write_u_escapes() above, so decode() only ever accepts a + // single byte here, and nothing of it was buffered if (EnsureAscii) { JSON_ASSERT(codepoint == 0x7F); - if (error_handler == error_handler_t::keep) - { - // this character was buffered as raw bytes below - // in case it turned out to be part of an - // ill-formed sequence (which is kept as is); now - // that it decoded to a well-formed code point, - // undo that and \u-escape it like any other - // character instead - bytes = bytes_after_last_accept; - } + JSON_ASSERT(bytes == bytes_after_last_accept); write_u_escape(bytes, static_cast(codepoint)); } else diff --git a/include/nlohmann/json.hpp b/include/nlohmann/json.hpp index 33ea53a08..9be8a8c6c 100644 --- a/include/nlohmann/json.hpp +++ b/include/nlohmann/json.hpp @@ -1579,7 +1579,7 @@ public: auto src_it = src_object.cbegin(); for (auto& element : *dst.m_data.m_value.object) { - if (JSON_HEDLEY_LIKELY(src_it != src_object.cend() && copy_keys_equal(src_it->first, element.first))) + if (JSON_HEDLEY_LIKELY(copy_keys_equal(src_it->first, element.first))) { copy_shallow(src_it->second, element.second, worklist); ++src_it; @@ -5438,8 +5438,15 @@ public: return (*lhs.m_data.m_value.object) op (*rhs.m_data.m_value.object); \ } \ \ - JSON_IMPLEMENT_SCALAR_CASES(op, null_result) \ - \ + /* same-type scalars never get here: the inline fast path of the operator handles them */ \ + case value_t::null: \ + case value_t::boolean: \ + case value_t::number_integer: \ + case value_t::number_unsigned: \ + case value_t::number_float: \ + JSON_ASSERT(false); /* NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) */ \ + return (unordered_result); \ + \ case value_t::string: \ return (*lhs.m_data.m_value.string) op (*rhs.m_data.m_value.string); \ \ @@ -5479,7 +5486,7 @@ public: ? (number_integer_t(-1) op number_integer_t(1)) \ : (static_cast(lhs.m_data.m_value.number_integer) op rhs.m_data.m_value.number_unsigned); \ } \ - else if(compares_unordered(lhs, rhs))\ + else if(lhs_type == value_t::discarded || rhs_type == value_t::discarded)\ {\ return (unordered_result);\ }\ diff --git a/single_include/nlohmann/json.hpp b/single_include/nlohmann/json.hpp index d953b047f..1d7df6d99 100644 --- a/single_include/nlohmann/json.hpp +++ b/single_include/nlohmann/json.hpp @@ -24104,6 +24104,9 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci { JSON_ASSERT(m_object != nullptr); + // m_it is already value-initialized, so this is not needed for + // correctness; it is kept because GCC generates faster loops with it + // (iterating a parsed document is 0.5-2.7 % slower without it, #6005) if (m_object->is_object()) { m_it.object_iterator = typename object_t::iterator(); @@ -36306,21 +36309,14 @@ class serializer { // the code point is at least 0x60 (smaller ones are handled // above) and is not printable ASCII (which the scanner - // copies): it is DEL (0x7F) under EnsureAscii or a non-ASCII - // character + // copies). Under EnsureAscii it is DEL (0x7F): every + // well-formed multi-byte character is escaped by + // write_u_escapes() above, so decode() only ever accepts a + // single byte here, and nothing of it was buffered if (EnsureAscii) { JSON_ASSERT(codepoint == 0x7F); - if (error_handler == error_handler_t::keep) - { - // this character was buffered as raw bytes below - // in case it turned out to be part of an - // ill-formed sequence (which is kept as is); now - // that it decoded to a well-formed code point, - // undo that and \u-escape it like any other - // character instead - bytes = bytes_after_last_accept; - } + JSON_ASSERT(bytes == bytes_after_last_accept); write_u_escape(bytes, static_cast(codepoint)); } else @@ -39347,7 +39343,7 @@ public: auto src_it = src_object.cbegin(); for (auto& element : *dst.m_data.m_value.object) { - if (JSON_HEDLEY_LIKELY(src_it != src_object.cend() && copy_keys_equal(src_it->first, element.first))) + if (JSON_HEDLEY_LIKELY(copy_keys_equal(src_it->first, element.first))) { copy_shallow(src_it->second, element.second, worklist); ++src_it; @@ -43206,8 +43202,15 @@ public: return (*lhs.m_data.m_value.object) op (*rhs.m_data.m_value.object); \ } \ \ - JSON_IMPLEMENT_SCALAR_CASES(op, null_result) \ - \ + /* same-type scalars never get here: the inline fast path of the operator handles them */ \ + case value_t::null: \ + case value_t::boolean: \ + case value_t::number_integer: \ + case value_t::number_unsigned: \ + case value_t::number_float: \ + JSON_ASSERT(false); /* NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) */ \ + return (unordered_result); \ + \ case value_t::string: \ return (*lhs.m_data.m_value.string) op (*rhs.m_data.m_value.string); \ \ @@ -43247,7 +43250,7 @@ public: ? (number_integer_t(-1) op number_integer_t(1)) \ : (static_cast(lhs.m_data.m_value.number_integer) op rhs.m_data.m_value.number_unsigned); \ } \ - else if(compares_unordered(lhs, rhs))\ + else if(lhs_type == value_t::discarded || rhs_type == value_t::discarded)\ {\ return (unordered_result);\ }\