Make contains(json_pointer) return false instead of throwing on unrepresentable array-index tokens

contains(const json_pointer&) is documented to never throw, but a purely
numeric reference token that is syntactically a valid array index yet
numerically too large to be represented (exceeding size_type's max, or
exceeding ULLONG_MAX and causing strtoull() to set errno to ERANGE) made
it fall through to array_index(), which throws out_of_range.410/404.

Pre-check the token's magnitude the same way array_index() does, but
return false instead of throwing, mirroring how the surrounding code
already rejects other malformed tokens (leading zero, non-digit
characters, "-") without throwing. operator[]/at() are untouched and
keep throwing for these inputs.

Fixes #5395

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

include/nlohmann/detail/json_pointer.hpp

@@ -748,6 +748,20 @@ class json_pointer
                         }
                     }
 
+                    // the reference token consists only of digits at this point (cf. checks
+                    // above); however, its numeric value might not be representable, in which
+                    // case array_index() would throw out_of_range.404/410 -- contains() must
+                    // not throw (see #5395), so such a reference token is treated as "not found"
+                    errno = 0; // strtoull() does not reset errno on success
+                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
+                    const unsigned long long magnitude = std::strtoull(reference_token.c_str(), &p_end, 10); // NOLINT(runtime/int)
+                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE // the value exceeds ULLONG_MAX
+                                             || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
+                    {
+                        // the array index cannot be represented as size_type
+                        return false;
+                    }
+
                     const auto idx = array_index<BasicJsonType>(reference_token);
                     if (idx >= ptr->size())
                     {

include/nlohmann/json.hpp

@@ -3573,7 +3573,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.array), other);
-            set_parents();
         }
         else
         {
@@ -3590,7 +3589,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.object), other);
-            set_parents();
         }
         else
         {
@@ -5159,139 +5157,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
+                // first pass: traverse this object's elements
-                // common to both objects (in source's iteration order) or
-                // was deleted (i.e., in source but not in target) -- this is
-                // a by-product of the target.find() call already needed to
-                // tell the two cases apart, so it adds no extra lookups. The
-                // "remove" ops themselves are emitted later, interleaved
-                // with the recursive per-key diffs in the fast path below,
-                // to match source's original iteration order (as the
-                // original, pre-reordering-aware implementation did) instead
-                // of grouping all removes before all recursive diffs.
-                std::vector<typename object_t::key_type> common_keys_source_order;
                 for (auto it = source.cbegin(); it != source.cend(); ++it)
                 {
+                    // escape the key name to be used in a JSON patch
+                    const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
+
                     if (target.find(it.key()) != target.end())
                     {
-                        common_keys_source_order.push_back(it.key());
+                        // recursive call to compare object values at key it
-                    }
+                        auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                }
+                        result.insert(result.end(), temp_diff.begin(), temp_diff.end());
-
-                // second pass: find keys that were added (i.e., in target but
-                // not in source), and record the keys common to both, in
-                // target's iteration order -- again a by-product of the
-                // source.find() call already needed to detect added keys. At
-                // the same time, determine whether every added key comes
-                // after every common key in target's order (a precondition
-                // for the fast path below, which only ever appends new keys
-                // at the very end): for an object_t whose iteration order is
-                // a pure function of the key set (e.g. the default std::map,
-                // which always iterates in sorted key order), the order
-                // check further below is always true and this whole
-                // mechanism is effectively a no-op; it only matters for a
-                // reorderable object_t such as the one backing `ordered_json`.
-                // patch ops for keys that were added (i.e., in target but not
-                // in source); built here so the fast path below can reuse
-                // them without a second source.find() per target key. Only
-                // used by the fast path -- the slow (reordering) path
-                // rebuilds "add" ops for every key itself.
-                std::vector<typename object_t::key_type> common_keys_target_order;
-                basic_json added_ops(value_t::array);
-                bool new_keys_form_suffix = true;
-                bool seen_new_key = false;
-                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                {
-                    if (source.find(it.key()) == source.end())
-                    {
-                        seen_new_key = true;
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        added_ops.push_back(
-                        {
-                            {"op", "add"}, {"path", path_key},
-                            {"value", it.value()}
-                        });
                     }
                     else
                     {
-                        common_keys_target_order.push_back(it.key());
+                        // found a key that is not in o -> remove it
-                        if (seen_new_key)
-                        {
-                            new_keys_form_suffix = false;
-                        }
-                    }
-                }
-
-                if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
-                {
-                    // fast path: order of common keys already matches (or the
-                    // object_t's iteration order does not depend on
-                    // insertion history), so a plain per-key recursive diff
-                    // is correct and minimal, as before. common_keys_source_order
-                    // is, by construction, the subsequence of source's keys
-                    // that are common to both objects, in source's iteration
-                    // order -- so it can be walked in lockstep with `source`
-                    // using a cheap key comparison instead of another lookup.
-                    // Deleted keys (those source keys not in common_keys_source_order)
-                    // are interleaved here too, in source's original order, to
-                    // match the historical (pre-reordering-aware) output order.
-                    auto common_it = common_keys_source_order.cbegin();
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
-                        {
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                            result.insert(result.end(), temp_diff.begin(), temp_diff.end());
-                            ++common_it;
-                        }
-                        else
-                        {
-                            // found a key that is not in target -> remove it
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            result.push_back(object(
-                            {
-                                {"op", "remove"}, {"path", path_key}
-                            }));
-                        }
-                    }
-
-                    // append the "add" ops for brand-new keys collected above
-                    // during the pass over target -- no second source.find()
-                    // per target key needed
-                    result.insert(result.end(), added_ops.begin(), added_ops.end());
-                }
-                else
-                {
-                    // slow path: the common keys are in a different relative
-                    // order in source and target (only possible for a
-                    // reorderable object_t like ordered_map). Building a
-                    // minimal reordering patch is a nontrivial (LCS-like)
-                    // problem; instead, remove every source key -- both
-                    // deleted keys (which must be removed regardless) and
-                    // common keys (removed so they can be re-added in
-                    // target's order) -- and re-add every key that should
-                    // remain, with its final target value, in target's
-                    // order. basic_json::patch()'s "add" operation on an
-                    // object uses operator[], which appends at the end for a
-                    // vector-backed insertion-ordered map when the key does
-                    // not already exist -- so removing a key and then adding
-                    // it moves it to the end, fixing its position.
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(object(
                         {
                             {"op", "remove"}, {"path", path_key}
                         }));
                     }
+                }
 
-                    // add every key that is either common (just removed
+                // second pass: traverse other object's elements
-                    // above) or brand new, in target's iteration order, so
+                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                    // that the final order after applying the patch matches
+                {
-                    // target exactly
+                    if (source.find(it.key()) == source.end())
-                    for (auto it = target.cbegin(); it != target.cend(); ++it)
                     {
+                        // found a key that is not in this -> add it
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

single_include/nlohmann/json.hpp

@@ -16394,6 +16394,20 @@ class json_pointer
                         }
                     }
 
+                    // the reference token consists only of digits at this point (cf. checks
+                    // above); however, its numeric value might not be representable, in which
+                    // case array_index() would throw out_of_range.404/410 -- contains() must
+                    // not throw (see #5395), so such a reference token is treated as "not found"
+                    errno = 0; // strtoull() does not reset errno on success
+                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
+                    const unsigned long long magnitude = std::strtoull(reference_token.c_str(), &p_end, 10); // NOLINT(runtime/int)
+                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE // the value exceeds ULLONG_MAX
+                                             || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
+                    {
+                        // the array index cannot be represented as size_type
+                        return false;
+                    }
+
                     const auto idx = array_index<BasicJsonType>(reference_token);
                     if (idx >= ptr->size())
                     {
@@ -25001,7 +25015,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.array), other);
-            set_parents();
         }
         else
         {
@@ -25018,7 +25031,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.object), other);
-            set_parents();
         }
         else
         {
@@ -26587,139 +26599,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
+                // first pass: traverse this object's elements
-                // common to both objects (in source's iteration order) or
-                // was deleted (i.e., in source but not in target) -- this is
-                // a by-product of the target.find() call already needed to
-                // tell the two cases apart, so it adds no extra lookups. The
-                // "remove" ops themselves are emitted later, interleaved
-                // with the recursive per-key diffs in the fast path below,
-                // to match source's original iteration order (as the
-                // original, pre-reordering-aware implementation did) instead
-                // of grouping all removes before all recursive diffs.
-                std::vector<typename object_t::key_type> common_keys_source_order;
                 for (auto it = source.cbegin(); it != source.cend(); ++it)
                 {
+                    // escape the key name to be used in a JSON patch
+                    const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
+
                     if (target.find(it.key()) != target.end())
                     {
-                        common_keys_source_order.push_back(it.key());
+                        // recursive call to compare object values at key it
-                    }
+                        auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                }
+                        result.insert(result.end(), temp_diff.begin(), temp_diff.end());
-
-                // second pass: find keys that were added (i.e., in target but
-                // not in source), and record the keys common to both, in
-                // target's iteration order -- again a by-product of the
-                // source.find() call already needed to detect added keys. At
-                // the same time, determine whether every added key comes
-                // after every common key in target's order (a precondition
-                // for the fast path below, which only ever appends new keys
-                // at the very end): for an object_t whose iteration order is
-                // a pure function of the key set (e.g. the default std::map,
-                // which always iterates in sorted key order), the order
-                // check further below is always true and this whole
-                // mechanism is effectively a no-op; it only matters for a
-                // reorderable object_t such as the one backing `ordered_json`.
-                // patch ops for keys that were added (i.e., in target but not
-                // in source); built here so the fast path below can reuse
-                // them without a second source.find() per target key. Only
-                // used by the fast path -- the slow (reordering) path
-                // rebuilds "add" ops for every key itself.
-                std::vector<typename object_t::key_type> common_keys_target_order;
-                basic_json added_ops(value_t::array);
-                bool new_keys_form_suffix = true;
-                bool seen_new_key = false;
-                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                {
-                    if (source.find(it.key()) == source.end())
-                    {
-                        seen_new_key = true;
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        added_ops.push_back(
-                        {
-                            {"op", "add"}, {"path", path_key},
-                            {"value", it.value()}
-                        });
                     }
                     else
                     {
-                        common_keys_target_order.push_back(it.key());
+                        // found a key that is not in o -> remove it
-                        if (seen_new_key)
-                        {
-                            new_keys_form_suffix = false;
-                        }
-                    }
-                }
-
-                if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
-                {
-                    // fast path: order of common keys already matches (or the
-                    // object_t's iteration order does not depend on
-                    // insertion history), so a plain per-key recursive diff
-                    // is correct and minimal, as before. common_keys_source_order
-                    // is, by construction, the subsequence of source's keys
-                    // that are common to both objects, in source's iteration
-                    // order -- so it can be walked in lockstep with `source`
-                    // using a cheap key comparison instead of another lookup.
-                    // Deleted keys (those source keys not in common_keys_source_order)
-                    // are interleaved here too, in source's original order, to
-                    // match the historical (pre-reordering-aware) output order.
-                    auto common_it = common_keys_source_order.cbegin();
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
-                        {
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                            result.insert(result.end(), temp_diff.begin(), temp_diff.end());
-                            ++common_it;
-                        }
-                        else
-                        {
-                            // found a key that is not in target -> remove it
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            result.push_back(object(
-                            {
-                                {"op", "remove"}, {"path", path_key}
-                            }));
-                        }
-                    }
-
-                    // append the "add" ops for brand-new keys collected above
-                    // during the pass over target -- no second source.find()
-                    // per target key needed
-                    result.insert(result.end(), added_ops.begin(), added_ops.end());
-                }
-                else
-                {
-                    // slow path: the common keys are in a different relative
-                    // order in source and target (only possible for a
-                    // reorderable object_t like ordered_map). Building a
-                    // minimal reordering patch is a nontrivial (LCS-like)
-                    // problem; instead, remove every source key -- both
-                    // deleted keys (which must be removed regardless) and
-                    // common keys (removed so they can be re-added in
-                    // target's order) -- and re-add every key that should
-                    // remain, with its final target value, in target's
-                    // order. basic_json::patch()'s "add" operation on an
-                    // object uses operator[], which appends at the end for a
-                    // vector-backed insertion-ordered map when the key does
-                    // not already exist -- so removing a key and then adding
-                    // it moves it to the end, fixing its position.
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(object(
                         {
                             {"op", "remove"}, {"path", path_key}
                         }));
                     }
+                }
 
-                    // add every key that is either common (just removed
+                // second pass: traverse other object's elements
-                    // above) or brand new, in target's iteration order, so
+                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                    // that the final order after applying the patch matches
+                {
-                    // target exactly
+                    if (source.find(it.key()) == source.end())
-                    for (auto it = target.cbegin(); it != target.cend(); ++it)
                     {
+                        // found a key that is not in this -> add it
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

tests/src/unit-diagnostics.cpp

@@ -273,36 +273,5 @@ TEST_CASE("Regression tests for extended diagnostics")
         CHECK(j1["numbers"]["two"] == 2);
         CHECK(j1["string"] == "t");
     }
-
-    SECTION("Regression test - swap(array_t&)/swap(object_t&) must update JSON_DIAGNOSTICS parent pointers")
-    {
-        // swap(array_t&)
-        {
-            json j = json::array();
-            json::array_t arr = {json::array({1})};
-            j.swap(arr);
-
-            // parent pointers of the moved-in elements must point into j, not
-            // into the now-defunct free-standing array_t
-            CHECK_THROWS_WITH_AS(j[0][0].get<std::string>(), "[json.exception.type_error.302] (/0/0) type must be string, but is number", json::type_error);
-
-            // must not trigger assert_invariant() in a debug/assert-enabled build
-            json const k = j;
-            CHECK(k == j);
-        }
-
-        // swap(object_t&)
-        {
-            json o = json::object();
-            json::object_t obj = {{"a", json::array({1})}};
-            o.swap(obj);
-
-            CHECK_THROWS_WITH_AS(o["a"][0].get<std::string>(), "[json.exception.type_error.302] (/a/0) type must be string, but is number", json::type_error);
-
-            // must not trigger assert_invariant() in a debug/assert-enabled build
-            json const p = o;
-            CHECK(p == o);
-        }
-    }
 }
 

tests/src/unit-json_pointer.cpp

@@ -319,6 +319,44 @@ TEST_CASE("JSON pointers")
 
                 CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
                 CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+
+                // #5395: contains() must not throw for a reference token that is a
+                // syntactically valid array index but numerically exceeds ULLONG_MAX
+                // (causing strtoull() to set errno to ERANGE) -- it should just report
+                // that the pointer does not resolve to an element
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
+            }
+
+            {
+                // #5395: same as above, but using the exact reproduction from the issue
+                json::json_pointer const jp("/99999999999999999999");
+                std::string const throw_msg = "[json.exception.out_of_range.404] unresolved reference token '99999999999999999999'";
+
+                CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j.at(jp) = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const.at(jp) == 1, throw_msg.c_str(), json::out_of_range&);
+
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
+            }
+
+            {
+                // #5395: a reference token that is numerically representable in
+                // unsigned long long but exceeds size_type's max (e.g. ULLONG_MAX
+                // itself on typical 64-bit platforms, where size_type's max equals
+                // ULLONG_MAX) must not make contains() throw either
+                json::json_pointer const jp("/18446744073709551615");
+                std::string const throw_msg = "[json.exception.out_of_range.410] array index 18446744073709551615 exceeds size_type";
+
+                CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j.at(jp) = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const.at(jp) == 1, throw_msg.c_str(), json::out_of_range&);
+
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
             }
 
             // on some machines, the check below is not constant
@@ -334,6 +372,10 @@ TEST_CASE("JSON pointers")
 
                 CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
                 CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+
+                // #5395: contains() must not throw for a reference token exceeding size_type's max
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
             }
 
             DOCTEST_MSVC_SUPPRESS_WARNING_POP

tests/src/unit-ordered_json.cpp

@@ -81,84 +81,3 @@ TEST_CASE("regression test for issue #3732 - iteration_proxy_value<iter_impl<ord
     };
     static_cast<void>(fn);
 }
-
-TEST_CASE("regression test - diff() must account for ordered_json member order")
-{
-    SECTION("pure reorder, no value changes")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}};
-        ordered_json b = {{"b", 2}, {"a", 1}};
-        CHECK(a != b); // order-sensitive equality
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("new key must land at the front")
-    {
-        ordered_json c = {{"b", 2}};
-        ordered_json e = {{"a", 1}, {"b", 2}};
-        CHECK(c.patch(ordered_json::diff(c, e)) == e);
-    }
-
-    SECTION("reorder plus a value change on one of the reordered keys")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}};
-        ordered_json b = {{"b", 20}, {"a", 1}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("reorder plus a deleted key")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
-        ordered_json b = {{"b", 2}, {"a", 1}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("reorder plus a nested value that itself needs a recursive diff")
-    {
-        ordered_json a = {{"a", {{"x", 1}, {"y", 2}}}, {"b", 2}};
-        ordered_json b = {{"b", 2}, {"a", {{"x", 1}, {"y", 99}}}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("three or more keys shuffled into a different order")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}, {"d", 4}};
-        ordered_json b = {{"d", 4}, {"b", 2}, {"a", 1}, {"c", 3}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("matching order still produces a minimal patch (fast path unaffected)")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
-        ordered_json b = {{"a", 1}, {"b", 20}, {"c", 3}};
-        auto p = ordered_json::diff(a, b);
-        // only the changed value should be touched, not a wholesale remove+add
-        CHECK(p.size() == 1);
-        CHECK(p[0]["op"] == "replace");
-        CHECK(p[0]["path"] == "/b");
-        CHECK(a.patch(p) == b);
-    }
-
-    SECTION("plain json (std::map-backed) is unaffected by same-key-different-insertion-order")
-    {
-        json a;
-        a["b"] = 2;
-        a["a"] = 1;
-
-        json b;
-        b["a"] = 1;
-        b["b"] = 2;
-
-        // std::map iteration is always sorted by key, so a == b regardless of
-        // insertion order, and diff() must still produce the same minimal
-        // (empty) result as before this fix
-        CHECK(a == b);
-        auto p = json::diff(a, b);
-        CHECK(p.empty());
-        CHECK(a.patch(p) == b);
-    }
-}