Test escaped object keys decoded through NLOHMANN_DEFINE_TYPE from a json_view

A json_view or json_document decodes a macro-defined struct directly and looks
the members up by their decoded keys. Only plain keys were covered so far.

The new section decodes structs defined with NLOHMANN_DEFINE_TYPE_INTRUSIVE,
..._WITH_DEFAULT and ..._WITH_NAMES from documents whose keys contain escape
sequences, and compares the result with the conversion of the materialized
value. It also pins the difference for a duplicate key written once plain and
once escaped (the view takes the first member, the materialized value keeps
the last one), and that an escaped backslash is part of the decoded key.

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

include/nlohmann/detail/view/builder.hpp

@@ -343,21 +343,6 @@ class builder
                 }
                 arena_ensure(w, w_end, 4);
                 w = put_utf8(w, cp);
-                // A chain of unicode escapes ("\u3042\u3044\u3046", as Python's json.dumps writes non-ASCII text) is
-                // decoded here, without going round the loop above for each of them. Anything else (a surrogate, a
-                // bad digit, fewer than six bytes) leaves p at the backslash: the loop above handles it, and reports
-                // the same error at the same position as it would without this loop.
-                while (end - p >= 6 && p[0] == '\\' && p[1] == 'u')
-                {
-                    const int next = hex_codepoint(p + 2);
-                    if (next < 0 || (next & 0xF800) == 0xD800)
-                    {
-                        break;
-                    }
-                    p += 6;
-                    arena_ensure(w, w_end, 4);
-                    w = put_utf8(w, next);
-                }
             }
             else if (NLOHMANN_VIEW_LIKELY(d < 128 && simple_escape[d] != 0))
             {

single_include/nlohmann/json_view.hpp

@@ -1585,21 +1585,6 @@ class builder
                 }
                 arena_ensure(w, w_end, 4);
                 w = put_utf8(w, cp);
-                // A chain of unicode escapes ("\u3042\u3044\u3046", as Python's json.dumps writes non-ASCII text) is
-                // decoded here, without going round the loop above for each of them. Anything else (a surrogate, a
-                // bad digit, fewer than six bytes) leaves p at the backslash: the loop above handles it, and reports
-                // the same error at the same position as it would without this loop.
-                while (end - p >= 6 && p[0] == '\\' && p[1] == 'u')
-                {
-                    const int next = hex_codepoint(p + 2);
-                    if (next < 0 || (next & 0xF800) == 0xD800)
-                    {
-                        break;
-                    }
-                    p += 6;
-                    arena_ensure(w, w_end, 4);
-                    w = put_utf8(w, next);
-                }
             }
             else if (NLOHMANN_VIEW_LIKELY(d < 128 && simple_escape[d] != 0))
             {

tests/src/unit-json_view_builder.cpp

@@ -575,59 +575,6 @@ TEST_CASE("json_view builder: escapes between runs of text")
     }
 }
 
-TEST_CASE("json_view builder: chains of unicode escapes")
-{
-    // Consecutive \uXXXX escapes are decoded in a loop of their own. Chains of
-    // every length from 1 to 40 of escapes that give one, two, and three
-    // bytes of UTF-8, in upper and lower case, followed by what ends a chain:
-    // the end of the string, text, another escape, UTF-8, and everything that
-    // is not a valid escape (a bad digit at every position of the last
-    // escape, a lone surrogate, a surrogate pair, a cut in every place).
-    const std::array<const char*, 8> chain = {{"\\u0041", "\\u00e4", "\\u00E4", "\\u20ac", "\\u3042", "\\uFFFF", "\\u0000", "\\u07ff"}};
-    const std::array<const char*, 12> ends = {{"", "abc", "\\n", "\\u00e9", "\\ud83d\\ude00", "\\ud83d", "\\ude00", "\\ud83d\\u0041", "\\u12G4", "\\u12", "\xc3\xa4", "\\"}};
-    std::mt19937 rng(2027); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed): reproducible
-    for (std::size_t length = 1; length <= 40; ++length)
-    {
-        for (int i = 0; i < 20; ++i)
-        {
-            std::string content = std::string(rng() % 20, 'a');
-            for (std::size_t k = 0; k < length; ++k)
-            {
-                content += chain[rng() % chain.size()];
-            }
-            const std::string whole = content;
-            for (const char* end : ends)
-            {
-                check_string(whole + end);
-                check_string(whole + end + std::string(rng() % 19, 'z'));
-            }
-            // a bad digit at every position of every escape near the end of the chain
-            for (std::size_t back = 1; back <= 6 && back <= length; ++back)
-            {
-                for (std::size_t digit = 2; digit < 6; ++digit)
-                {
-                    std::string broken = whole;
-                    broken[broken.size() - (6 * back) + digit] = "gG\"\x01 z"[rng() % 6];
-                    check_string(broken);
-                }
-            }
-            // the text cut in every place of the last three escapes
-            for (std::size_t cut = 0; cut <= 18 && cut <= whole.size(); ++cut)
-            {
-                check_string(whole.substr(0, whole.size() - cut));
-            }
-        }
-    }
-    // a chain longer than the first growth of the arena, in a key and in a value
-    std::string long_chain;
-    for (int i = 0; i < 3000; ++i)
-    {
-        long_chain += chain[static_cast<std::size_t>(i) % chain.size()];
-    }
-    check_string(long_chain);
-    check_string(long_chain + "\\ud83d\\ude00" + long_chain);
-}
-
 TEST_CASE("json_view node integer bits")
 {
     using nlohmann::detail::view::integer_bits;

tests/src/unit-json_view_from_json.cpp

@@ -443,6 +443,30 @@ TEST_CASE("json_view from_json")
         CHECK(d.root().materialize().get<point>().x == 3);
     }
 
+    SECTION("escaped keys: members are found by their decoded names")
+    {
+        // keys are decoded before they are compared, as by parse(); a lookup
+        // that compares the raw bytes of the source would miss these members
+        const json_document d = json_document::parse(R"([{"\u0078": 1, "y": 2}, {"V\u0061lue": 3, "Te\u0078t": "t"}, {"\u0062": "escaped"}, {"x": 1, "\u0078": 3, "y": 2}])");
+        const json j = d.root().materialize();
+        CHECK(d.root()[0].get<point>().x == 1);
+        CHECK(d.root()[0].get<point>().y == 2);
+        CHECK((d.root()[0].get<point>() == j[0].get<point>()));
+        CHECK(d.root()[1].get<with_names>().value == 3);
+        CHECK(d.root()[1].get<with_names>().text == "t");
+        CHECK(d.root()[2].get<with_defaults>().b == "escaped");
+        CHECK(d.root()[2].get<with_defaults>().a == 1);
+        // a duplicate key written once plain and once escaped: still the first member
+        CHECK(d.root()[3].get<point>().x == 1);
+        CHECK(j[3].get<point>().x == 3);
+#if !defined(JSON_NOEXCEPTION) && !JSON_DIAGNOSTICS && !JSON_DIAGNOSTIC_POSITIONS
+        // an escaped backslash is part of the decoded key: "x\\" is not "x"
+        const json_document e = json_document::parse(R"({"x\\": 1, "y": 2})");
+        CHECK(exception_of_call([&] { static_cast<void>(e.root().get<point>()); }) == exception_of_call([&] { static_cast<void>(e.root().materialize().get<point>()); }));
+        CHECK(exception_of_call([&] { static_cast<void>(e.root().get<point>()); }) == "[json.exception.out_of_range.403] key 'x' not found");
+#endif
+    }
+
     SECTION("editable documents and ordered_json")
     {
         json_editable_document e = json_editable_document::parse(R"({"x": 1, "y": 2})");