Keep full byte2 x byte3 combinatorics in the wrong-fourth-byte sections

The maintainer wants exhaustive coverage of every byte combination here
rather than the representative-prefix reduction, matching the style of
the sibling "wrong second/third byte" sections in the same files.

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

docs/mkdocs/docs/features/binary_formats/bjdata.md

@@ -125,6 +125,7 @@ The library uses the following mapping from JSON values types to BJData types ac
 
     - `"_ArrayType_"` is one of `uint8`, `int8`, `uint16`, `int16`, `uint32`, `int32`, `uint64`, `int64`, `single`,
       `double`, `char`, or `byte`,
+    - `"_ArraySize_"` is an array, since the dimensions are written as the ND-array header's length,
     - every entry of `"_ArraySize_"` is a non-negative integer, and their product is representable as a `std::size_t`,
     - `"_ArrayData_"` holds exactly that many elements, and
     - every element of `"_ArrayData_"` is a number of the kind named by `"_ArrayType_"` (a floating-point number for

include/nlohmann/detail/output/binary_writer.hpp

@@ -1668,6 +1668,15 @@ class binary_writer
         CharType dtype = it->second;
 
         key = "_ArraySize_";
+        // the dimensions are written verbatim as the header length below, so a
+        // value that is not an array cannot produce a valid one: null emits 'Z'
+        // and an object emits '{', neither of which a reader accepts after '#'.
+        // Such an object is not a valid ndarray and falls back to a plain object.
+        if (!value.at(key).is_array())
+        {
+            return true;
+        }
+
         std::size_t len = (value.at(key).empty() ? 0 : 1);
         for (const auto& el : value.at(key))
         {

single_include/nlohmann/json.hpp

@@ -18676,6 +18676,15 @@ class binary_writer
         CharType dtype = it->second;
 
         key = "_ArraySize_";
+        // the dimensions are written verbatim as the header length below, so a
+        // value that is not an array cannot produce a valid one: null emits 'Z'
+        // and an object emits '{', neither of which a reader accepts after '#'.
+        // Such an object is not a valid ndarray and falls back to a plain object.
+        if (!value.at(key).is_array())
+        {
+            return true;
+        }
+
         std::size_t len = (value.at(key).empty() ? 0 : 1);
         for (const auto& el : value.at(key))
         {

tests/src/unit-bjdata.cpp

@@ -2751,6 +2751,31 @@ TEST_CASE("BJData")
                 CHECK(json::to_bjdata(j_ok) == std::vector<uint8_t>({'[', '$', 'U', '#', '[', 'i', 2, 'i', 3, ']', 1, 2, 3, 4, 5, 6}));
                 CHECK(json::from_bjdata(json::to_bjdata(j_ok), true, true) == j_ok);
             }
+
+            SECTION("ndarray whose _ArraySize_ is not an array stays as object")
+            {
+                // the shape is written verbatim as the header length, so a
+                // value that is not an array cannot produce a valid one: null
+                // would emit 'Z' and an object '{', neither of which a reader
+                // accepts after '#'. Both have to stay plain objects.
+                json const j_null = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", nullptr}, {"_ArrayData_", json::array()}});
+                const auto out_null = json::to_bjdata(j_null);
+                CHECK(out_null.at(0) == '{');
+                CHECK(json::from_bjdata(out_null) == j_null);
+
+                // an object shape passes the per-entry check by iterating its
+                // values rather than dimensions, so it needs rejecting too
+                json const j_obj = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {{"a", 1}}}, {"_ArrayData_", {1}}});
+                const auto out_obj = json::to_bjdata(j_obj);
+                CHECK(out_obj.at(0) == '{');
+                CHECK(json::from_bjdata(out_obj) == j_obj);
+
+                // a scalar shape is not a dimension list either
+                json const j_num = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", 1}, {"_ArrayData_", {1}}});
+                const auto out_num = json::to_bjdata(j_num);
+                CHECK(out_num.at(0) == '{');
+                CHECK(json::from_bjdata(out_num) == j_num);
+            }
         }
     }
 

tests/src/unit-unicode3.cpp

@@ -304,8 +304,8 @@ TEST_CASE("Unicode (3/5)" * doctest::skip())
                         {
                             for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
                             {
-                                // skip fourth second byte
-                                if (0x80 <= byte3 && byte3 <= 0xBF)
+                                // skip correct fourth byte
+                                if (0x80 <= byte4 && byte4 <= 0xBF)
                                 {
                                     continue;
                                 }

tests/src/unit-unicode4.cpp

@@ -305,7 +305,7 @@ TEST_CASE("Unicode (4/5)" * doctest::skip())
                             for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
                             {
                                 // skip correct fourth byte
-                                if (0x80 <= byte3 && byte3 <= 0xBF)
+                                if (0x80 <= byte4 && byte4 <= 0xBF)
                                 {
                                     continue;
                                 }

tests/src/unit-unicode5.cpp

@@ -305,7 +305,7 @@ TEST_CASE("Unicode (5/5)" * doctest::skip())
                             for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
                             {
                                 // skip correct fourth byte
-                                if (0x80 <= byte3 && byte3 <= 0xBF)
+                                if (0x80 <= byte4 && byte4 <= 0xBF)
                                 {
                                     continue;
                                 }