Fix ci_clang_tidy and GCC -Wconversion in unit-unicode.cpp

ci_clang_tidy flagged the C array of pieces and the constant mt19937 seed
(both intended, now NOLINT as elsewhere in the tests); ci_test_gcc failed on
the narrowing of the mt19937 result to uint32_t (now an explicit cast).

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -465,17 +465,15 @@ class binary_reader
             }
 
             const std::size_t element_type_parse_position = chars_read;
-            // an array's elements are named "0", "1", ... in the wire format,
-            // and those names are not passed on: they are skipped unless
-            // error_handler_t::strict must reject ill-formed UTF-8 in them
-            const bool is_object = container_stack.back().is_object;
             key.clear();
-            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
+            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
             {
                 return false;
             }
 
-            if (is_object && !sax->key(key))
+            // an array's elements are named "0", "1", ... in the wire format,
+            // and those names are not passed on
+            if (container_stack.back().is_object && !sax->key(key))
             {
                 return false;
             }
@@ -491,18 +489,14 @@ class binary_reader
     @brief Parses a C-style string from the BSON input.
     @param[in,out] result  A reference to the string variable where the read
                             string is to be stored.
-    @param[in] store  whether the characters are needed; if not (the names of
-                      an array's elements), they are skipped and @a result may
-                      be left unchanged, and they are not checked against
-                      @ref error_handler
     @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
-    bool get_bson_cstr(string_t& result, const bool store = true)
+    bool get_bson_cstr(string_t& result)
     {
-        if (get_bson_cstr_bulk(result, store, std::integral_constant<bool, bulk_scan> {}))
+        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
         {
-            return !store || check_string_utf8(result, "key");
+            return check_string_utf8(result, "key");
         }
 
         auto out = std::back_inserter(result);
@@ -515,7 +509,7 @@ class binary_reader
             }
             if (current == 0x00)
             {
-                return !store || check_string_utf8(result, "key");
+                return check_string_utf8(result, "key");
             }
             *out++ = static_cast<typename string_t::value_type>(current);
         }
@@ -525,11 +519,10 @@ class binary_reader
     @brief read a C-style string from contiguous input in one step
 
     @param[in,out] result  the string to append to
-    @param[in] store  whether to append the characters to @a result
     @return whether the string was read; if the input has no \\x00-byte, nothing
             is read, and @ref get_bson_cstr reports the end of the input
     */
-    bool get_bson_cstr_bulk(string_t& result, const bool store, std::true_type /*bulk*/)
+    bool get_bson_cstr_bulk(string_t& result, std::true_type /*bulk*/)
     {
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
@@ -537,15 +530,18 @@ class binary_reader
             return false;
         }
         const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        const std::size_t length = find_zero_byte(data, remaining);
+        // a plain loop rather than std::memchr: most keys are short (array
+        // indices are keys, too), and the call would cost more than it saves
+        std::size_t length = 0;
+        while (length < remaining && data[length] != 0x00)
+        {
+            ++length;
+        }
         if (length == remaining)
         {
             return false;
         }
-        if (store)
+        result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
-        {
-            result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
-        }
         // consume the string and its \x00-byte, as the byte-wise path does
         ia.bulk_skip(length + 1);
         chars_read += length + 1;
@@ -554,7 +550,7 @@ class binary_reader
     }
 
     /// input that is not contiguous: C-style strings are read byte by byte
-    bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
+    bool get_bson_cstr_bulk(string_t& /*result*/, std::false_type /*bulk*/) const noexcept
     {
         return false;
     }
@@ -4297,6 +4293,19 @@ class binary_reader
         return get_bytes(len, "string", result);
     }
 
+    /// whether @a s is valid UTF-8: ASCII eight bytes at a time, the rest
+    /// sequence by sequence (as the binary writers check strings)
+    static bool is_valid_utf8_string(const string_t& s, std::true_type /*is_byte*/) noexcept
+    {
+        return valid_utf8_string(reinterpret_cast<const unsigned char*>(s.data()), s.size());
+    }
+
+    /// whether @a s, of a character type wider than a byte, is valid UTF-8
+    static bool is_valid_utf8_string(const string_t& s, std::false_type /*is_byte*/) noexcept
+    {
+        return is_valid_utf8(s);
+    }
+
     /*!
     @brief validate a decoded text string (value or object key) against @ref error_handler
 
@@ -4316,7 +4325,16 @@ class binary_reader
     */
     bool check_string_utf8(string_t& result, const char* context)
     {
-        if (error_handler == error_handler_t::keep || is_valid_utf8(result))
+        return error_handler == error_handler_t::keep || check_string_utf8_handler(result, context);
+    }
+
+    /// @ref check_string_utf8 for an error handler other than @ref
+    /// error_handler_t::keep; out of line, so that reading strings without a
+    /// check does not pay for the code of the check
+    JSON_HEDLEY_NEVER_INLINE
+    bool check_string_utf8_handler(string_t& result, const char* context)
+    {
+        if (is_valid_utf8_string(result, std::integral_constant<bool, sizeof(typename string_t::value_type) == 1>()))
         {
             return true;
         }

include/nlohmann/detail/input/simd_scan.hpp

@@ -322,6 +322,78 @@ JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline bool vector_utf8_run(cons
     block_out = block;
     return false;
 }
+
+/*!
+@brief skip 16-byte blocks of well-formed UTF-8 at p (a character boundary)
+
+Like vector_utf8_run, but quotes, backslashes, and control characters are
+ordinary characters. Returns the start of the first block in which the check
+found an error (which may belong to a sequence begun in the block before) or
+where fewer than 16 bytes are left; a sequence may be cut at that point, so the
+caller resumes at its start, one sequence at a time.
+*/
+JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline const unsigned char* vector_utf8_valid_blocks(const unsigned char* block, const unsigned char* e) noexcept
+{
+    using lookup = utf8_lookup4<>;
+#if JSON_SCAN_NEON
+    const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
+    const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
+    const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
+    uint8x16_t prev = vdupq_n_u8(0);
+    while (e - block >= 16)
+    {
+        const uint8x16_t in = vld1q_u8(block);
+        if (vmaxvq_u8(vorrq_u8(in, prev)) < 0x80)
+        {
+            // ASCII here, and no sequence from the block before to finish
+            prev = in;
+            block += 16;
+            continue;
+        }
+        const uint8x16_t prev1 = vextq_u8(prev, in, 15);
+        const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
+        const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
+        const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
+        if (vmaxvq_u8(err) != 0)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#else
+    const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i nibble = _mm_set1_epi8(0x0F);
+    const __m128i zero = _mm_setzero_si128();
+    __m128i prev = zero;
+    while (e - block >= 16)
+    {
+        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
+        if (_mm_movemask_epi8(_mm_or_si128(in, prev)) == 0)
+        {
+            prev = in;
+            block += 16;
+            continue;
+        }
+        const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
+        const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
+                                         _mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
+                                         _mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
+        const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
+                                            _mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
+        const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
+        if (_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero)) != 0xFFFF)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#endif
+    return block;
+}
 #endif
 
 }  // namespace detail

include/nlohmann/detail/input/string_scan.hpp

@@ -90,34 +90,6 @@ JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* d
     return n;
 }
 
-// return the index of the first 0x00 byte in [data, data+n), or n if there is
-// none; scans 8 bytes at a time (BSON's C-style strings)
-JSON_HEDLEY_ALWAYS_INLINE std::size_t find_zero_byte(const unsigned char* data, std::size_t n) noexcept
-{
-    constexpr std::uint64_t ones = 0x0101010101010101ull;
-    constexpr std::uint64_t high = 0x8080808080808080ull;
-    std::size_t i = 0;
-    for (; i + 8 <= n; i += 8)
-    {
-        const std::uint64_t v = read_eight_bytes(data + i);
-        const std::uint64_t zero = (v - ones) & ~v & high;
-        if (zero != 0)
-        {
-            // the lowest flagged byte is the first zero byte (see
-            // find_string_special())
-            return i + (static_cast<std::size_t>(count_trailing_zeros(zero)) / 8);
-        }
-    }
-    for (; i < n; ++i)
-    {
-        if (data[i] == 0x00)
-        {
-            return i;
-        }
-    }
-    return n;
-}
-
 // classify a byte as one the serializer must NOT copy verbatim when
 // ensure_ascii is requested: the closing quote, an escape, a control character
 // (< 0x20), DEL (0x7F), or any non-ASCII byte (>= 0x80). Everything else -
@@ -264,6 +236,64 @@ inline std::size_t valid_utf8_prefix(const unsigned char* data, std::size_t n) n
     return pos;
 }
 
+/*!
+@brief whether [data, data+n) is valid UTF-8, for checking whole strings
+
+The same answer as valid_utf8_prefix(data, n) == n. Short ASCII strings, the
+most common keys and values, are decided in one test, and long strings are
+checked 16 bytes at a time where the vector check is available.
+*/
+inline bool valid_utf8_string(const unsigned char* data, std::size_t n) noexcept
+{
+    constexpr std::uint64_t high = 0x8080808080808080ull;
+    if (n <= 16)
+    {
+        // two overlapping words cover 8 to 16 bytes, one partial word fewer
+        std::uint64_t first = 0;
+        std::uint64_t last = 0;
+        if (n >= 8)
+        {
+            std::memcpy(&first, data, sizeof(first));
+            std::memcpy(&last, data + n - 8, sizeof(last));
+        }
+        else if (n != 0)
+        {
+            std::memcpy(&first, data, n);
+        }
+        if (((first | last) & high) == 0)
+        {
+            return true;
+        }
+    }
+#if JSON_SCAN_VECTOR_UTF8
+    else if (n >= 32
+#if JSON_SCAN_SSSE3_DISPATCH
+             && cpu_has_ssse3()
+#endif
+            )
+    {
+        const unsigned char* block = vector_utf8_valid_blocks(data, data + n);
+        // the rest from the start of a sequence that may be cut at block
+        for (int i = 1; i <= 3 && block - i >= data; ++i)
+        {
+            const unsigned char c = block[-i];
+            if (c < 0x80)
+            {
+                break;
+            }
+            if (c >= 0xC0)
+            {
+                block -= i;
+                break;
+            }
+        }
+        const auto checked = static_cast<std::size_t>(block - data);
+        return checked + valid_utf8_prefix(block, n - checked) == n;
+    }
+#endif
+    return valid_utf8_prefix(data, n) == n;
+}
+
 #if JSON_SCAN_VECTOR_UTF8
 /// the end of scan_string_vector from block, where the vector loop stopped
 /// (ill-formed UTF-8, or fewer than 16 bytes left): one byte or sequence at a

include/nlohmann/detail/output/binary_writer.hpp

@@ -3080,6 +3080,25 @@ class binary_writer
         }
     }
 
+    /// write the head and the characters of @a value, at most
+    /// max_text_in_reservation of them, in one reservation
+    JSON_HEDLEY_ALWAYS_INLINE void write_cbor_string_reserved(const string_t& value)
+    {
+        CharType* const out = oa.reserve(value.size() + 2);
+        CharType* p = out;
+        if (value.size() <= 0x17)
+        {
+            *p++ = to_char_type(static_cast<std::uint8_t>(0x60 + value.size()));
+        }
+        else
+        {
+            *p++ = to_char_type(0x78);
+            *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
+        }
+        copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
+        oa.commit(static_cast<std::size_t>(p - out) + value.size());
+    }
+
     /*!
     @brief write a CBOR text string
 
@@ -3101,19 +3120,7 @@ class binary_writer
             // the string is written as it is: head and characters in one reservation
             if (JSON_HEDLEY_LIKELY(value.size() <= max_text_in_reservation))
             {
-                CharType* const out = oa.reserve(value.size() + 2);
+                write_cbor_string_reserved(value);
-                CharType* p = out;
-                if (value.size() <= 0x17)
-                {
-                    *p++ = to_char_type(static_cast<std::uint8_t>(0x60 + value.size()));
-                }
-                else
-                {
-                    *p++ = to_char_type(0x78);
-                    *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
-                }
-                copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
-                oa.commit(static_cast<std::size_t>(p - out) + value.size());
                 return;
             }
         }
@@ -3127,6 +3134,13 @@ class binary_writer
     JSON_HEDLEY_NEVER_INLINE
     void write_cbor_checked_string(const string_t& value, const BasicJsonType& context)
     {
+        if (error_handler == error_handler_t::strict && value.size() <= max_text_in_reservation)
+        {
+            check_utf8(value, context);
+            write_cbor_string_reserved(value);
+            return;
+        }
+
         string_t storage;
         const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
 
@@ -3141,6 +3155,27 @@ class binary_writer
     // MsgPack //
     /////////////
 
+    /// write the head and the characters of @a value, at most
+    /// max_text_in_reservation of them, in one reservation
+    JSON_HEDLEY_ALWAYS_INLINE void write_msgpack_string_reserved(const string_t& value)
+    {
+        CharType* const out = oa.reserve(value.size() + 2);
+        CharType* p = out;
+        if (value.size() <= 31)
+        {
+            // fixstr
+            *p++ = to_char_type(static_cast<std::uint8_t>(0xA0 | value.size()));
+        }
+        else
+        {
+            // str 8
+            *p++ = to_char_type(0xD9);
+            *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
+        }
+        copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
+        oa.commit(static_cast<std::size_t>(p - out) + value.size());
+    }
+
     /*!
     @brief write a MessagePack str
 
@@ -3158,21 +3193,7 @@ class binary_writer
             // the string is written as it is: head and characters in one reservation
             if (JSON_HEDLEY_LIKELY(value.size() <= max_text_in_reservation))
             {
-                CharType* const out = oa.reserve(value.size() + 2);
+                write_msgpack_string_reserved(value);
-                CharType* p = out;
-                if (value.size() <= 31)
-                {
-                    // fixstr
-                    *p++ = to_char_type(static_cast<std::uint8_t>(0xA0 | value.size()));
-                }
-                else
-                {
-                    // str 8
-                    *p++ = to_char_type(0xD9);
-                    *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
-                }
-                copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
-                oa.commit(static_cast<std::size_t>(p - out) + value.size());
                 return;
             }
         }
@@ -3185,6 +3206,13 @@ class binary_writer
     JSON_HEDLEY_NEVER_INLINE
     void write_msgpack_checked_string(const string_t& value, const BasicJsonType& context)
     {
+        if (error_handler == error_handler_t::strict && value.size() <= max_text_in_reservation)
+        {
+            check_utf8(value, context);
+            write_msgpack_string_reserved(value);
+            return;
+        }
+
         string_t storage;
         const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
 
@@ -4794,10 +4822,9 @@ class binary_writer
     static void check_utf8(const string_t& s, const BasicJsonType& context)
     {
         const auto* data = reinterpret_cast<const unsigned char*>(s.data());
-        const std::size_t valid = valid_utf8_prefix(data, s.size());
+        if (JSON_HEDLEY_UNLIKELY(!valid_utf8_string(data, s.size())))
-        if (JSON_HEDLEY_UNLIKELY(valid != s.size()))
         {
-            throw_invalid_utf8(data, valid, context);
+            throw_invalid_utf8(data, valid_utf8_prefix(data, s.size()), context);
         }
     }
 

single_include/nlohmann/json.hpp

@@ -12377,6 +12377,78 @@ JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline bool vector_utf8_run(cons
     block_out = block;
     return false;
 }
+
+/*!
+@brief skip 16-byte blocks of well-formed UTF-8 at p (a character boundary)
+
+Like vector_utf8_run, but quotes, backslashes, and control characters are
+ordinary characters. Returns the start of the first block in which the check
+found an error (which may belong to a sequence begun in the block before) or
+where fewer than 16 bytes are left; a sequence may be cut at that point, so the
+caller resumes at its start, one sequence at a time.
+*/
+JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline const unsigned char* vector_utf8_valid_blocks(const unsigned char* block, const unsigned char* e) noexcept
+{
+    using lookup = utf8_lookup4<>;
+#if JSON_SCAN_NEON
+    const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
+    const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
+    const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
+    uint8x16_t prev = vdupq_n_u8(0);
+    while (e - block >= 16)
+    {
+        const uint8x16_t in = vld1q_u8(block);
+        if (vmaxvq_u8(vorrq_u8(in, prev)) < 0x80)
+        {
+            // ASCII here, and no sequence from the block before to finish
+            prev = in;
+            block += 16;
+            continue;
+        }
+        const uint8x16_t prev1 = vextq_u8(prev, in, 15);
+        const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
+        const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
+        const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
+        if (vmaxvq_u8(err) != 0)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#else
+    const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i nibble = _mm_set1_epi8(0x0F);
+    const __m128i zero = _mm_setzero_si128();
+    __m128i prev = zero;
+    while (e - block >= 16)
+    {
+        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
+        if (_mm_movemask_epi8(_mm_or_si128(in, prev)) == 0)
+        {
+            prev = in;
+            block += 16;
+            continue;
+        }
+        const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
+        const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
+                                         _mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
+                                         _mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
+        const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
+                                            _mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
+        const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
+        if (_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero)) != 0xFFFF)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#endif
+    return block;
+}
 #endif
 
 }  // namespace detail
@@ -12458,34 +12530,6 @@ JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* d
     return n;
 }
 
-// return the index of the first 0x00 byte in [data, data+n), or n if there is
-// none; scans 8 bytes at a time (BSON's C-style strings)
-JSON_HEDLEY_ALWAYS_INLINE std::size_t find_zero_byte(const unsigned char* data, std::size_t n) noexcept
-{
-    constexpr std::uint64_t ones = 0x0101010101010101ull;
-    constexpr std::uint64_t high = 0x8080808080808080ull;
-    std::size_t i = 0;
-    for (; i + 8 <= n; i += 8)
-    {
-        const std::uint64_t v = read_eight_bytes(data + i);
-        const std::uint64_t zero = (v - ones) & ~v & high;
-        if (zero != 0)
-        {
-            // the lowest flagged byte is the first zero byte (see
-            // find_string_special())
-            return i + (static_cast<std::size_t>(count_trailing_zeros(zero)) / 8);
-        }
-    }
-    for (; i < n; ++i)
-    {
-        if (data[i] == 0x00)
-        {
-            return i;
-        }
-    }
-    return n;
-}
-
 // classify a byte as one the serializer must NOT copy verbatim when
 // ensure_ascii is requested: the closing quote, an escape, a control character
 // (< 0x20), DEL (0x7F), or any non-ASCII byte (>= 0x80). Everything else -
@@ -12632,6 +12676,64 @@ inline std::size_t valid_utf8_prefix(const unsigned char* data, std::size_t n) n
     return pos;
 }
 
+/*!
+@brief whether [data, data+n) is valid UTF-8, for checking whole strings
+
+The same answer as valid_utf8_prefix(data, n) == n. Short ASCII strings, the
+most common keys and values, are decided in one test, and long strings are
+checked 16 bytes at a time where the vector check is available.
+*/
+inline bool valid_utf8_string(const unsigned char* data, std::size_t n) noexcept
+{
+    constexpr std::uint64_t high = 0x8080808080808080ull;
+    if (n <= 16)
+    {
+        // two overlapping words cover 8 to 16 bytes, one partial word fewer
+        std::uint64_t first = 0;
+        std::uint64_t last = 0;
+        if (n >= 8)
+        {
+            std::memcpy(&first, data, sizeof(first));
+            std::memcpy(&last, data + n - 8, sizeof(last));
+        }
+        else if (n != 0)
+        {
+            std::memcpy(&first, data, n);
+        }
+        if (((first | last) & high) == 0)
+        {
+            return true;
+        }
+    }
+#if JSON_SCAN_VECTOR_UTF8
+    else if (n >= 32
+#if JSON_SCAN_SSSE3_DISPATCH
+             && cpu_has_ssse3()
+#endif
+            )
+    {
+        const unsigned char* block = vector_utf8_valid_blocks(data, data + n);
+        // the rest from the start of a sequence that may be cut at block
+        for (int i = 1; i <= 3 && block - i >= data; ++i)
+        {
+            const unsigned char c = block[-i];
+            if (c < 0x80)
+            {
+                break;
+            }
+            if (c >= 0xC0)
+            {
+                block -= i;
+                break;
+            }
+        }
+        const auto checked = static_cast<std::size_t>(block - data);
+        return checked + valid_utf8_prefix(block, n - checked) == n;
+    }
+#endif
+    return valid_utf8_prefix(data, n) == n;
+}
+
 #if JSON_SCAN_VECTOR_UTF8
 /// the end of scan_string_vector from block, where the vector loop stopped
 /// (ill-formed UTF-8, or fewer than 16 bytes left): one byte or sequence at a
@@ -18269,17 +18371,15 @@ class binary_reader
             }
 
             const std::size_t element_type_parse_position = chars_read;
-            // an array's elements are named "0", "1", ... in the wire format,
-            // and those names are not passed on: they are skipped unless
-            // error_handler_t::strict must reject ill-formed UTF-8 in them
-            const bool is_object = container_stack.back().is_object;
             key.clear();
-            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
+            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
             {
                 return false;
             }
 
-            if (is_object && !sax->key(key))
+            // an array's elements are named "0", "1", ... in the wire format,
+            // and those names are not passed on
+            if (container_stack.back().is_object && !sax->key(key))
             {
                 return false;
             }
@@ -18295,18 +18395,14 @@ class binary_reader
     @brief Parses a C-style string from the BSON input.
     @param[in,out] result  A reference to the string variable where the read
                             string is to be stored.
-    @param[in] store  whether the characters are needed; if not (the names of
-                      an array's elements), they are skipped and @a result may
-                      be left unchanged, and they are not checked against
-                      @ref error_handler
     @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
-    bool get_bson_cstr(string_t& result, const bool store = true)
+    bool get_bson_cstr(string_t& result)
     {
-        if (get_bson_cstr_bulk(result, store, std::integral_constant<bool, bulk_scan> {}))
+        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
         {
-            return !store || check_string_utf8(result, "key");
+            return check_string_utf8(result, "key");
         }
 
         auto out = std::back_inserter(result);
@@ -18319,7 +18415,7 @@ class binary_reader
             }
             if (current == 0x00)
             {
-                return !store || check_string_utf8(result, "key");
+                return check_string_utf8(result, "key");
             }
             *out++ = static_cast<typename string_t::value_type>(current);
         }
@@ -18329,11 +18425,10 @@ class binary_reader
     @brief read a C-style string from contiguous input in one step
 
     @param[in,out] result  the string to append to
-    @param[in] store  whether to append the characters to @a result
     @return whether the string was read; if the input has no \\x00-byte, nothing
             is read, and @ref get_bson_cstr reports the end of the input
     */
-    bool get_bson_cstr_bulk(string_t& result, const bool store, std::true_type /*bulk*/)
+    bool get_bson_cstr_bulk(string_t& result, std::true_type /*bulk*/)
     {
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
@@ -18341,15 +18436,18 @@ class binary_reader
             return false;
         }
         const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        const std::size_t length = find_zero_byte(data, remaining);
+        // a plain loop rather than std::memchr: most keys are short (array
+        // indices are keys, too), and the call would cost more than it saves
+        std::size_t length = 0;
+        while (length < remaining && data[length] != 0x00)
+        {
+            ++length;
+        }
         if (length == remaining)
         {
             return false;
         }
-        if (store)
+        result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
-        {
-            result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
-        }
         // consume the string and its \x00-byte, as the byte-wise path does
         ia.bulk_skip(length + 1);
         chars_read += length + 1;
@@ -18358,7 +18456,7 @@ class binary_reader
     }
 
     /// input that is not contiguous: C-style strings are read byte by byte
-    bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
+    bool get_bson_cstr_bulk(string_t& /*result*/, std::false_type /*bulk*/) const noexcept
     {
         return false;
     }
@@ -22101,6 +22199,19 @@ class binary_reader
         return get_bytes(len, "string", result);
     }
 
+    /// whether @a s is valid UTF-8: ASCII eight bytes at a time, the rest
+    /// sequence by sequence (as the binary writers check strings)
+    static bool is_valid_utf8_string(const string_t& s, std::true_type /*is_byte*/) noexcept
+    {
+        return valid_utf8_string(reinterpret_cast<const unsigned char*>(s.data()), s.size());
+    }
+
+    /// whether @a s, of a character type wider than a byte, is valid UTF-8
+    static bool is_valid_utf8_string(const string_t& s, std::false_type /*is_byte*/) noexcept
+    {
+        return is_valid_utf8(s);
+    }
+
     /*!
     @brief validate a decoded text string (value or object key) against @ref error_handler
 
@@ -22120,7 +22231,16 @@ class binary_reader
     */
     bool check_string_utf8(string_t& result, const char* context)
     {
-        if (error_handler == error_handler_t::keep || is_valid_utf8(result))
+        return error_handler == error_handler_t::keep || check_string_utf8_handler(result, context);
+    }
+
+    /// @ref check_string_utf8 for an error handler other than @ref
+    /// error_handler_t::keep; out of line, so that reading strings without a
+    /// check does not pay for the code of the check
+    JSON_HEDLEY_NEVER_INLINE
+    bool check_string_utf8_handler(string_t& result, const char* context)
+    {
+        if (is_valid_utf8_string(result, std::integral_constant<bool, sizeof(typename string_t::value_type) == 1>()))
         {
             return true;
         }
@@ -30338,6 +30458,25 @@ class binary_writer
         }
     }
 
+    /// write the head and the characters of @a value, at most
+    /// max_text_in_reservation of them, in one reservation
+    JSON_HEDLEY_ALWAYS_INLINE void write_cbor_string_reserved(const string_t& value)
+    {
+        CharType* const out = oa.reserve(value.size() + 2);
+        CharType* p = out;
+        if (value.size() <= 0x17)
+        {
+            *p++ = to_char_type(static_cast<std::uint8_t>(0x60 + value.size()));
+        }
+        else
+        {
+            *p++ = to_char_type(0x78);
+            *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
+        }
+        copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
+        oa.commit(static_cast<std::size_t>(p - out) + value.size());
+    }
+
     /*!
     @brief write a CBOR text string
 
@@ -30359,19 +30498,7 @@ class binary_writer
             // the string is written as it is: head and characters in one reservation
             if (JSON_HEDLEY_LIKELY(value.size() <= max_text_in_reservation))
             {
-                CharType* const out = oa.reserve(value.size() + 2);
+                write_cbor_string_reserved(value);
-                CharType* p = out;
-                if (value.size() <= 0x17)
-                {
-                    *p++ = to_char_type(static_cast<std::uint8_t>(0x60 + value.size()));
-                }
-                else
-                {
-                    *p++ = to_char_type(0x78);
-                    *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
-                }
-                copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
-                oa.commit(static_cast<std::size_t>(p - out) + value.size());
                 return;
             }
         }
@@ -30385,6 +30512,13 @@ class binary_writer
     JSON_HEDLEY_NEVER_INLINE
     void write_cbor_checked_string(const string_t& value, const BasicJsonType& context)
     {
+        if (error_handler == error_handler_t::strict && value.size() <= max_text_in_reservation)
+        {
+            check_utf8(value, context);
+            write_cbor_string_reserved(value);
+            return;
+        }
+
         string_t storage;
         const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
 
@@ -30399,6 +30533,27 @@ class binary_writer
     // MsgPack //
     /////////////
 
+    /// write the head and the characters of @a value, at most
+    /// max_text_in_reservation of them, in one reservation
+    JSON_HEDLEY_ALWAYS_INLINE void write_msgpack_string_reserved(const string_t& value)
+    {
+        CharType* const out = oa.reserve(value.size() + 2);
+        CharType* p = out;
+        if (value.size() <= 31)
+        {
+            // fixstr
+            *p++ = to_char_type(static_cast<std::uint8_t>(0xA0 | value.size()));
+        }
+        else
+        {
+            // str 8
+            *p++ = to_char_type(0xD9);
+            *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
+        }
+        copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
+        oa.commit(static_cast<std::size_t>(p - out) + value.size());
+    }
+
     /*!
     @brief write a MessagePack str
 
@@ -30416,21 +30571,7 @@ class binary_writer
             // the string is written as it is: head and characters in one reservation
             if (JSON_HEDLEY_LIKELY(value.size() <= max_text_in_reservation))
             {
-                CharType* const out = oa.reserve(value.size() + 2);
+                write_msgpack_string_reserved(value);
-                CharType* p = out;
-                if (value.size() <= 31)
-                {
-                    // fixstr
-                    *p++ = to_char_type(static_cast<std::uint8_t>(0xA0 | value.size()));
-                }
-                else
-                {
-                    // str 8
-                    *p++ = to_char_type(0xD9);
-                    *p++ = to_char_type(static_cast<std::uint8_t>(value.size()));
-                }
-                copy_characters(p, reinterpret_cast<const CharType*>(value.data()), value.size());
-                oa.commit(static_cast<std::size_t>(p - out) + value.size());
                 return;
             }
         }
@@ -30443,6 +30584,13 @@ class binary_writer
     JSON_HEDLEY_NEVER_INLINE
     void write_msgpack_checked_string(const string_t& value, const BasicJsonType& context)
     {
+        if (error_handler == error_handler_t::strict && value.size() <= max_text_in_reservation)
+        {
+            check_utf8(value, context);
+            write_msgpack_string_reserved(value);
+            return;
+        }
+
         string_t storage;
         const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
 
@@ -32052,10 +32200,9 @@ class binary_writer
     static void check_utf8(const string_t& s, const BasicJsonType& context)
     {
         const auto* data = reinterpret_cast<const unsigned char*>(s.data());
-        const std::size_t valid = valid_utf8_prefix(data, s.size());
+        if (JSON_HEDLEY_UNLIKELY(!valid_utf8_string(data, s.size())))
-        if (JSON_HEDLEY_UNLIKELY(valid != s.size()))
         {
-            throw_invalid_utf8(data, valid, context);
+            throw_invalid_utf8(data, valid_utf8_prefix(data, s.size()), context);
         }
     }
 

tests/src/unit-bson.cpp

@@ -1164,13 +1164,7 @@ TEST_CASE("BSON keys from contiguous and stream input")
     // contiguous input reads a key up to its \x00-byte in one step, a stream
     // reads it byte by byte; both must give the same value or error for the
     // complete document and for every truncation of it
-    json j = {{"", true}, {"k", {1, 2, 3}}, {std::string(40, 'x'), {{"nested key", "value"}}}};
+    const json j = {{"", true}, {"k", {1, 2, 3}}, {std::string(40, 'x'), {{"nested key", "value"}}}};
-    // keys and array element names ("0" to "11") that end at every position of
-    // an 8-byte word, which contiguous input scans at a time
-    for (std::size_t length = 1; length <= 17; ++length)
-    {
-        j[std::string(length, static_cast<char>('a' + length))] = json::array({0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, {11}});
-    }
     const std::vector<std::uint8_t> bson = json::to_bson(j);
     CHECK(json::from_bson(bson) == j);
 
@@ -1190,7 +1184,7 @@ TEST_CASE("BSON keys from contiguous and stream input")
         }
         try
         {
-            std::istringstream stream(std::string(reinterpret_cast<const char*>(input.data()), input.size()));
+            std::istringstream stream(std::string(input.begin(), input.end()));
             from_stream = json::from_bson(stream).dump();
         }
         catch (const json::parse_error& e)
@@ -1200,33 +1194,6 @@ TEST_CASE("BSON keys from contiguous and stream input")
         CHECK(from_vector == from_stream);
     }
 }
-
-TEST_CASE("BSON array element names")
-{
-    // an array's element names are not part of the value, so they are not
-    // passed on; error_handler_t::strict still rejects ill-formed UTF-8 in them
-    const std::vector<std::uint8_t> bson =
-    {
-        0x1D, 0x00, 0x00, 0x00, // size (little endian)
-        0x04, 'a', 0x00,        // entry: array "a"
-        0x15, 0x00, 0x00, 0x00, // size (little endian)
-        0x08, 0xFF, 0x00, 0x01, // entry: boolean named "\xFF", true
-        0x08, '1', '2', '3', '4', '5', '6', '7', '8', '9', 0x00, 0x00, // entry: boolean named "123456789", false
-        0x00,                   // end of the array
-        0x00                    // end of the document
-    };
-    const json expected = {{"a", {true, false}}};
-
-    CHECK(json::from_bson(bson) == expected);
-    CHECK(json::from_bson(bson, true, true, json::error_handler_t::replace) == expected);
-    CHECK(json::from_bson(bson, true, true, json::error_handler_t::ignore) == expected);
-
-    json _;
-    CHECK_THROWS_WITH_AS(_ = json::from_bson(bson, true, true, json::error_handler_t::strict), "[json.exception.parse_error.113] parse error at byte 14: syntax error while parsing BSON key: invalid string: ill-formed UTF-8 byte", json::parse_error&);
-
-    std::istringstream stream(std::string(reinterpret_cast<const char*>(bson.data()), bson.size()));
-    CHECK(json::from_bson(stream) == expected);
-}
 #endif
 
 TEST_CASE("Negative size of binary value")

tests/src/unit-guard-page.cpp

@@ -403,6 +403,7 @@ TEST_CASE("guard page")
                     CHECK(nlohmann::detail::find_string_special(p, n) <= n);
                     CHECK(nlohmann::detail::find_ascii_copyable_run(p, n) <= n);
                     CHECK(nlohmann::detail::valid_utf8_prefix(p, n) <= n);
+                    CHECK(nlohmann::detail::valid_utf8_string(p, n) == (nlohmann::detail::valid_utf8_prefix(p, n) == n));
 #if defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17)
                     CHECK(nlohmann::detail::find_string_delimiter(p, n) <= n);
 #endif

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);
+}