Make std::hash<basic_json> consistent with operator== for numbers

operator== converts between number_integer, number_unsigned, and
number_float before comparing, so json(0), json(0U), and json(0.0)
all compare equal. hash() folded the specific value_t into the
result for each of the three numeric cases, giving each a distinct
hash and breaking the standard Hash requirement that a == b implies
hash(a) == hash(b). A std::unordered_set could therefore hold all
three as separate elements even though they compare equal.

hash() now treats all three numeric variants the same way: it
converts the value to number_float_t and combines it with a single
shared type tag, so any two numbers operator== considers equal hash
identically regardless of which internal type actually holds them.

Updated the accompanying test to check this consistency directly
(including via an actual unordered_set) instead of asserting that 0,
0U, and 0.0 hash differently, since that assumption was the bug.
Also corrected the function's own doc comment and the std::hash API
docs, which described the old behavior as intended.

Fixes #5400

Signed-off-by: Afonso Januário <afonso-januario@hotmail.com>
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

docs/mkdocs/docs/api/basic_json/std_hash.md

@@ -7,8 +7,9 @@ namespace std {
 ```
 
 Return a hash value for a JSON object. The hash function tries to rely on `std::hash` where possible. Furthermore, the
-type of the JSON value is taken into account to have different hash values for `#!json null`, `#!cpp 0`, `#!cpp 0U`, and
-`#!cpp false`, etc.
+type of the JSON value is taken into account, so `#!json null`, `#!cpp false`, and numbers all hash differently from
+each other. Numbers that compare equal under [`operator==`](operator_eq.md) always hash equally, regardless of
+whether they are stored as `#!cpp 0`, `#!cpp 0U`, or `#!cpp 0.0`.
 
 ## Examples
 

docs/mkdocs/docs/examples/std_hash.output

@@ -1,8 +1,8 @@
 hash(null) = 2654435769
 hash(false) = 2654436030
-hash(0) = 2654436095
-hash(0U) = 2654436156
-hash("") = 6142509191626859748
+hash(0) = 2654436221
+hash(0U) = 2654436221
+hash("") = 11160318156688833227
 hash({}) = 2654435832
 hash([]) = 2654435899
-hash({"hello": "world"}) = 4469488738203676328
+hash({"hello": "world"}) = 3701319991624763853

include/nlohmann/detail/hash.hpp

@@ -35,8 +35,10 @@ std::size_t hash_iteratively(const BasicJsonType& j);
 @brief hash a JSON value
 
 The hash function tries to rely on std::hash where possible. Furthermore, the
-type of the JSON value is taken into account to have different hash values for
-null, 0, 0U, and false, etc.
+type of the JSON value is taken into account, so null, false, and numbers all
+hash differently from each other, but any two numbers that compare equal
+under operator== hash equally regardless of which of number_integer,
+number_unsigned, or number_float actually holds the value.
 
 Hashing an array or an object hashes its elements, which used to call this
 function again once per nesting level, so a value nested deeply enough
@@ -113,21 +115,18 @@ std::size_t hash(const BasicJsonType& j, const std::size_t depth = 0)
         }
 
         case BasicJsonType::value_t::number_integer:
-        {
-            const auto h = std::hash<number_integer_t> {}(j.template get<number_integer_t>());
-            return combine(type, h);
-        }
-
         case BasicJsonType::value_t::number_unsigned:
-        {
-            const auto h = std::hash<number_unsigned_t> {}(j.template get<number_unsigned_t>());
-            return combine(type, h);
-        }
-
         case BasicJsonType::value_t::number_float:
         {
+            // operator== converts between number_integer, number_unsigned, and
+            // number_float before comparing, so equal numbers of different
+            // internal types (0, 0U, 0.0) must hash the same. Combining a
+            // single shared type tag with the value converted to
+            // number_float_t keeps the hash consistent with operator== for
+            // every pair of numbers it considers equal.
+            const auto number_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
             const auto h = std::hash<number_float_t> {}(j.template get<number_float_t>());
-            return combine(type, h);
+            return combine(number_type, h);
         }
 
         case BasicJsonType::value_t::binary:

single_include/nlohmann/json.hpp

@@ -7583,8 +7583,10 @@ std::size_t hash_iteratively(const BasicJsonType& j);
 @brief hash a JSON value
 
 The hash function tries to rely on std::hash where possible. Furthermore, the
-type of the JSON value is taken into account to have different hash values for
-null, 0, 0U, and false, etc.
+type of the JSON value is taken into account, so null, false, and numbers all
+hash differently from each other, but any two numbers that compare equal
+under operator== hash equally regardless of which of number_integer,
+number_unsigned, or number_float actually holds the value.
 
 Hashing an array or an object hashes its elements, which used to call this
 function again once per nesting level, so a value nested deeply enough
@@ -7661,21 +7663,18 @@ std::size_t hash(const BasicJsonType& j, const std::size_t depth = 0)
         }
 
         case BasicJsonType::value_t::number_integer:
-        {
-            const auto h = std::hash<number_integer_t> {}(j.template get<number_integer_t>());
-            return combine(type, h);
-        }
-
         case BasicJsonType::value_t::number_unsigned:
-        {
-            const auto h = std::hash<number_unsigned_t> {}(j.template get<number_unsigned_t>());
-            return combine(type, h);
-        }
-
         case BasicJsonType::value_t::number_float:
         {
+            // operator== converts between number_integer, number_unsigned, and
+            // number_float before comparing, so equal numbers of different
+            // internal types (0, 0U, 0.0) must hash the same. Combining a
+            // single shared type tag with the value converted to
+            // number_float_t keeps the hash consistent with operator== for
+            // every pair of numbers it considers equal.
+            const auto number_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
             const auto h = std::hash<number_float_t> {}(j.template get<number_float_t>());
-            return combine(type, h);
+            return combine(number_type, h);
         }
 
         case BasicJsonType::value_t::binary:

tests/src/unit-hash.cpp

@@ -14,6 +14,7 @@ using ordered_json = nlohmann::ordered_json;
 
 #include <set>
 #include <string>
+#include <unordered_set>
 
 namespace
 {
@@ -91,6 +92,9 @@ TEST_CASE("hash<nlohmann::json>")
     // Collect hashes for different JSON values and make sure that they are distinct
     // We cannot compare against fixed values, because the implementation of
     // std::hash may differ between compilers.
+    //
+    // numbers that compare equal under operator== (0 == 0U == 0.0) must hash
+    // equally, so they are only inserted once below and checked separately.
 
     std::set<std::size_t> hashes;
 
@@ -107,10 +111,7 @@ TEST_CASE("hash<nlohmann::json>")
 
     // number
     hashes.insert(std::hash<json> {}(json(0)));
-    hashes.insert(std::hash<json> {}(json(static_cast<unsigned>(0))));
-
     hashes.insert(std::hash<json> {}(json(-1)));
-    hashes.insert(std::hash<json> {}(json(0.0)));
     hashes.insert(std::hash<json> {}(json(42.23)));
 
     // array
@@ -132,7 +133,20 @@ TEST_CASE("hash<nlohmann::json>")
     // discarded
     hashes.insert(std::hash<json> {}(json(json::value_t::discarded)));
 
-    CHECK(hashes.size() == 21);
+    CHECK(hashes.size() == 19);
+
+    // numbers that compare equal under operator== must hash equally,
+    // regardless of which of number_integer, number_unsigned, or
+    // number_float actually holds the value
+    CHECK(json(0) == json(static_cast<unsigned>(0)));
+    CHECK(json(0) == json(0.0));
+    CHECK(std::hash<json> {}(json(0)) == std::hash<json> {}(json(static_cast<unsigned>(0))));
+    CHECK(std::hash<json> {}(json(0)) == std::hash<json> {}(json(0.0)));
+    CHECK(std::hash<json> {}(json(-1)) == std::hash<json> {}(json(-1.0)));
+
+    // a std::unordered_set relies on this same consistency between == and hash
+    std::unordered_set<json> numbers {json(0), json(static_cast<unsigned>(0)), json(0.0)};
+    CHECK(numbers.size() == 1);
 }
 
 TEST_CASE("hash<nlohmann::ordered_json>")
@@ -156,10 +170,7 @@ TEST_CASE("hash<nlohmann::ordered_json>")
 
     // number
     hashes.insert(std::hash<ordered_json> {}(ordered_json(0)));
-    hashes.insert(std::hash<ordered_json> {}(ordered_json(static_cast<unsigned>(0))));
-
     hashes.insert(std::hash<ordered_json> {}(ordered_json(-1)));
-    hashes.insert(std::hash<ordered_json> {}(ordered_json(0.0)));
     hashes.insert(std::hash<ordered_json> {}(ordered_json(42.23)));
 
     // array
@@ -181,7 +192,10 @@ TEST_CASE("hash<nlohmann::ordered_json>")
     // discarded
     hashes.insert(std::hash<ordered_json> {}(ordered_json(ordered_json::value_t::discarded)));
 
-    CHECK(hashes.size() == 21);
+    CHECK(hashes.size() == 19);
+
+    CHECK(std::hash<ordered_json> {}(ordered_json(0)) == std::hash<ordered_json> {}(ordered_json(static_cast<unsigned>(0))));
+    CHECK(std::hash<ordered_json> {}(ordered_json(0)) == std::hash<ordered_json> {}(ordered_json(0.0)));
 }
 
 TEST_CASE("hash of deeply nested values")