Binary readers and writers: faster UTF-8 checks of strings (#5982)

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

tests/src/unit-unicode.cpp

@@ -13,6 +13,7 @@ using nlohmann::json;
 
 #include <algorithm>
 #include <fstream>
+#include <random>
 #include <string>
 #include "make_test_data_available.hpp"
 #include "test_utils.hpp"
@@ -1631,3 +1632,40 @@ TEST_CASE("Unicode RFC 3629")
 }
 
 DOCTEST_CLANG_SUPPRESS_WARNING_POP
+
+TEST_CASE("UTF-8 check of whole strings")
+{
+    // valid_utf8_string() decides short strings with a word test and long ones
+    // 16 bytes at a time where a vector check is available; it must agree with
+    // the byte-wise check for every mix of ASCII, sequences of each length,
+    // ill-formed and truncated sequences, at every length and offset
+    const char* const pieces[] = // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+        "a", "\x7F", "\xC3\xA9", "\xE2\x82\xAC", "\xE0\xA0\x80", "\xEF\xBF\xBF", "\xF0\x9F\x98\x80", "\xF4\x8F\xBF\xBF",
+        "\x80", "\xC0\xAF", "\xC3", "\xE2\x82", "\xED\xA0\x80", "\xF0\x9F", "\xF4\x90\x80\x80", "\xFF"
+    };
+    // std::mt19937's sequence is fixed by the standard; no distribution is used
+    std::mt19937 rng(5); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
+    std::size_t valid = 0;
+    for (int i = 0; i < 100000; ++i)
+    {
+        std::string s;
+        const std::size_t length = rng() % 100;
+        const auto ascii = static_cast<std::uint32_t>(rng() % 101);
+        while (s.size() < length)
+        {
+            // mostly well-formed pieces (the first eight), so that long valid
+            // strings are common
+            s += (rng() % 100 < ascii) ? std::string("x") : std::string(pieces[rng() % (rng() % 8 == 0 ? 16 : 8)]);
+        }
+        const auto* data = reinterpret_cast<const unsigned char*>(s.data());
+        const bool expected = nlohmann::detail::is_valid_utf8(s);
+        valid += expected ? 1 : 0;
+        CAPTURE(s)
+        CHECK(nlohmann::detail::valid_utf8_string(data, s.size()) == expected);
+        CHECK((nlohmann::detail::valid_utf8_prefix(data, s.size()) == s.size()) == expected);
+    }
+    // both outcomes are common enough to be tested
+    CHECK(valid > 20000);
+    CHECK(valid < 80000);
+}