⚡ validate only newly read bytes of binary-format strings

get_string() validated the whole result after each call, but get_bytes()
appends to it and CBOR indefinite-length strings collect all chunks in
the same result, so every chunk re-validated everything read before it.
An input of many small chunks took quadratic time (80000 one-byte chunks,
160 KB of input, took about 7 seconds). Only the newly read bytes are
validated now, which also matches RFC 8949's requirement that every
chunk is valid UTF-8 on its own.

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

docs/mkdocs/docs/features/binary_formats/bson.md

@@ -109,6 +109,15 @@ The library maps BSON record types to JSON value types as follows:
     If BSON input must be validated for strict specification compliance, validate it separately before passing it to
     `from_bson()`.
 
+!!! warning "UTF-8 validation of string values"
+
+    The BSON specification requires `string` values (type `0x02`) to be valid UTF-8. This library validates the
+    bytes of every such string at decode time and rejects ill-formed UTF-8 with a
+    [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with `allow_exceptions`
+    set to `false`, a discarded value), rather than only failing later when the resulting value is dumped. Element
+    (key) names and `binary` values (type `0x05`) are unaffected and are never validated, since they are read
+    byte-by-byte as a C string, or are not required to hold text, respectively.
+
 ??? example
 
     ```cpp

docs/mkdocs/docs/features/binary_formats/cbor.md

@@ -176,6 +176,16 @@ The library maps CBOR types to JSON value types as follows:
 
     CBOR allows map keys of any type, whereas JSON only allows strings as keys in object values. Therefore, CBOR maps with keys other than UTF-8 strings are rejected.
 
+!!! warning "UTF-8 validation of text strings"
+
+    [RFC 8949, Section 3.1](https://www.rfc-editor.org/rfc/rfc8949.html#section-3.1) requires CBOR text strings
+    (major type 3) to be valid UTF-8. This library validates the bytes of every text string (object keys included) at
+    decode time and rejects ill-formed UTF-8 with a
+    [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with
+    `allow_exceptions` set to `false`, a discarded value), rather than only failing later when the resulting value is
+    dumped. Byte strings (major type 2) are unaffected and are never validated, since they are not required to hold
+    text.
+
 !!! warning "Tagged items"
 
     Tagged items (0xC0..0xDB) will throw a parse error by default. They can be ignored by passing `cbor_tag_handler_t::ignore` to function `from_cbor`, in which case the tag is skipped and the enclosed data item is parsed on its own. They can be stored by passing `cbor_tag_handler_t::store` to function `from_cbor`. Note that no tag is ever interpreted: for instance, a text string tagged with tag 0 (date/time) stays a string.

docs/mkdocs/docs/features/binary_formats/messagepack.md

@@ -136,6 +136,14 @@ The library maps MessagePack types to JSON value types as follows:
 
     Any MessagePack output created by `to_msgpack` can be successfully parsed by `from_msgpack`.
 
+!!! warning "UTF-8 validation of string values"
+
+    The MessagePack specification requires `str` values (`fixstr`, `str 8`, `str 16`, `str 32`) to be valid UTF-8.
+    This library validates the bytes of every such string (object keys included) at decode time and rejects
+    ill-formed UTF-8 with a [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or,
+    with `allow_exceptions` set to `false`, a discarded value), rather than only failing later when the resulting
+    value is dumped. `bin`/`ext`/`fixext` values are unaffected and are never validated, since they are not required
+    to hold text.
 
 ??? example
 

docs/mkdocs/docs/home/exceptions.md

@@ -340,7 +340,8 @@ An unexpected byte was read in a [binary format](../features/binary_formats/inde
 ### json.exception.parse_error.113
 
 A string could not be read from a [binary format](../features/binary_formats/index.md): either a value that is not a
-string was read where one was required (for instance as a map key), or the string's length specification is invalid.
+string was read where one was required (for instance as a map key), the string's length specification is invalid, or
+the string's bytes are not valid UTF-8.
 
 !!! failure "Example messages"
 
@@ -356,6 +357,9 @@ string was read where one was required (for instance as a map key), or the strin
     ```
     [json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData string: string length must not be negative
     ```
+    ```
+    [json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte
+    ```
 
 ### json.exception.parse_error.114
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -32,6 +32,7 @@
 #include <nlohmann/detail/meta/is_sax.hpp>
 #include <nlohmann/detail/meta/type_traits.hpp>
 #include <nlohmann/detail/string_concat.hpp>
+#include <nlohmann/detail/string_utils.hpp>
 #include <nlohmann/detail/value_t.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -432,7 +433,21 @@ class binary_reader
                                     exception_message(input_format_t::bson, concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
         }
 
-        return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) && get() != char_traits<char_type>::eof();
+        if (JSON_HEDLEY_UNLIKELY(!get_string(input_format_t::bson, len - static_cast<NumberType>(1), result)))
+        {
+            return false;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(get() != 0x00))
+        {
+            auto last_token = get_token_string();
+            return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
+                                    exception_message(input_format_t::bson,
+                                            "BSON string is not null-terminated",
+                                            "string"), nullptr));
+        }
+
+        return true;
     }
 
     /*!
@@ -550,8 +565,6 @@ class binary_reader
         }
     }
 
-
-
     //////////
     // CBOR //
     //////////
@@ -3301,7 +3314,28 @@ class binary_reader
                     const NumberType len,
                     string_t& result)
     {
-        return get_bytes(format, len, "string", result);
+        // get_bytes() appends to result, and CBOR indefinite-length strings
+        // collect all their chunks in the same result; validating only the
+        // newly read bytes keeps the check linear in the input size
+        const std::size_t old_size = result.size();
+        if (JSON_HEDLEY_UNLIKELY(!get_bytes(format, len, "string", result)))
+        {
+            return false;
+        }
+
+        // RFC 8949 (CBOR) §3.1 and the MessagePack/BSON/UBJSON specifications
+        // all require text strings to be valid UTF-8; reject anything else
+        // right here so malformed input is caught at decode time instead of
+        // only surfacing later as a type_error.316 when the value is dumped
+        // (which would defeat allow_exceptions=false / strict discarding).
+        if (JSON_HEDLEY_UNLIKELY(!is_valid_utf8(result, old_size)))
+        {
+            return sax->parse_error(chars_read, get_token_string(),
+                                    parse_error::create(113, chars_read,
+                                            exception_message(format, "invalid string: ill-formed UTF-8 byte", "string"), nullptr));
+        }
+
+        return true;
     }
 
     /*!

include/nlohmann/detail/output/serializer.hpp

@@ -31,6 +31,7 @@
 #include <nlohmann/detail/output/binary_writer.hpp>
 #include <nlohmann/detail/output/output_adapters.hpp>
 #include <nlohmann/detail/string_concat.hpp>
+#include <nlohmann/detail/string_utils.hpp>
 #include <nlohmann/detail/value_t.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -57,8 +58,6 @@ class serializer
     using number_integer_t = typename BasicJsonType::number_integer_t;
     using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
     using binary_char_t = typename BasicJsonType::binary_t::value_type;
-    static constexpr std::uint8_t UTF8_ACCEPT = 0;
-    static constexpr std::uint8_t UTF8_REJECT = 1;
 
   public:
     /*!
@@ -1584,62 +1583,6 @@ class serializer
         }
     }
 
-    /*!
-    @brief check whether a string is UTF-8 encoded
-
-    The function checks each byte of a string whether it is UTF-8 encoded. The
-    result of the check is stored in the @a state parameter. The function must
-    be called initially with state 0 (accept). State 1 means the string must
-    be rejected, because the current byte is not allowed. If the string is
-    completely processed, but the state is non-zero, the string ended
-    prematurely; that is, the last byte indicated more bytes should have
-    followed.
-
-    @param[in,out] state  the state of the decoding
-    @param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)
-    @param[in] byte       next byte to decode
-    @return               new state
-
-    @note The function has been edited: a std::array is used.
-
-    @copyright Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
-    @sa http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
-    */
-    static std::uint8_t decode(std::uint8_t& state, std::uint32_t& codep, const std::uint8_t byte) noexcept
-    {
-        static const std::array<std::uint8_t, 400> utf8d =
-        {
-            {
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 00..1F
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 20..3F
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 40..5F
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 60..7F
-                1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 80..9F
-                7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // A0..BF
-                8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // C0..DF
-                0xA, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, // E0..EF
-                0xB, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, // F0..FF
-                0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, // s0..s0
-                1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, // s1..s2
-                1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, // s3..s4
-                1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, // s5..s6
-                1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // s7..s8
-            }
-        };
-
-        JSON_ASSERT(static_cast<std::size_t>(byte) < utf8d.size());
-        const std::uint8_t type = utf8d[byte];
-
-        codep = (state != UTF8_ACCEPT)
-                ? (byte & 0x3fu) | (codep << 6u)
-                : (0xFFu >> type) & (byte);
-
-        const std::size_t index = 256u + (static_cast<size_t>(state) * 16u) + static_cast<size_t>(type);
-        JSON_ASSERT(index < utf8d.size());
-        state = utf8d[index];
-        return state;
-    }
-
     /*
      * Overload to make the compiler happy while it is instantiating
      * dump_integer for number_unsigned_t.

include/nlohmann/detail/string_utils.hpp

@@ -8,10 +8,13 @@
 
 #pragma once
 
+#include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint8_t, uint32_t
 #include <string> // string, to_string
 
 #include <nlohmann/detail/abi_macros.hpp>
+#include <nlohmann/detail/macro_scope.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -33,5 +36,102 @@ StringType to_string(std::size_t value)
     return result;
 }
 
+///////////////////
+// UTF-8 decoding //
+///////////////////
+
+// UTF-8 decoder states used by decode() below
+static constexpr std::uint8_t UTF8_ACCEPT = 0;
+static constexpr std::uint8_t UTF8_REJECT = 1;
+
+/*!
+@brief process a byte of a UTF-8 sequence
+
+This is a single-byte step of a "shift-based" UTF-8 decoder originally
+written by Björn Hoehrmann. See
+http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
+
+This decoder is the single source of truth for UTF-8 validation in this
+library: it is used both by the serializer (to escape and, in strict mode,
+reject ill-formed UTF-8 when dumping a string) and by the binary readers
+(to reject ill-formed UTF-8 in CBOR/MessagePack/BSON/UBJSON text strings at
+decode time; see @ref is_valid_utf8 below).
+
+@param[in,out] state  the current decoder state
+@param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)
+@param[in] byte       next byte to decode
+@return               new state
+
+@note Original source: http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+@sa http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+*/
+inline std::uint8_t decode(std::uint8_t& state, std::uint32_t& codep, const std::uint8_t byte) noexcept
+{
+    static const std::array<std::uint8_t, 400> utf8d =
+    {
+        {
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 00..1F
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 20..3F
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 40..5F
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 60..7F
+            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 80..9F
+            7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // A0..BF
+            8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // C0..DF
+            0xA, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, // E0..EF
+            0xB, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, // F0..FF
+            0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, // s0..s0
+            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, // s1..s2
+            1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, // s3..s4
+            1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, // s5..s6
+            1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // s7..s8
+        }
+    };
+
+    JSON_ASSERT(static_cast<std::size_t>(byte) < utf8d.size());
+    const std::uint8_t type = utf8d[byte];
+
+    codep = (state != UTF8_ACCEPT)
+            ? (byte & 0x3fu) | (codep << 6u)
+            : (0xFFu >> type) & (byte);
+
+    const std::size_t index = 256u + (static_cast<std::size_t>(state) * 16u) + static_cast<std::size_t>(type);
+    JSON_ASSERT(index < utf8d.size());
+    state = utf8d[index];
+    return state;
+}
+
+/*!
+@brief check whether a string consists solely of valid UTF-8
+
+Used by the CBOR/MessagePack/BSON/UBJSON binary readers to reject text
+strings that are not valid UTF-8 at decode time (RFC 8949 §3.1 and the
+MessagePack/BSON specifications all require text strings to be UTF-8), so
+that malformed input is caught immediately instead of only surfacing later
+as a type_error.316 when the resulting value is dumped.
+
+@param[in] s      the string to check
+@param[in] first  index of the first byte to check; the bytes before it are
+                  assumed to have been validated already and to end on a
+                  code point boundary
+@return whether @a s (from index @a first on) is valid UTF-8
+*/
+template<typename StringType>
+inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noexcept
+{
+    std::uint8_t state = UTF8_ACCEPT;
+    std::uint32_t codepoint = 0;
+
+    for (std::size_t i = first; i < s.size(); ++i)
+    {
+        decode(state, codepoint, static_cast<std::uint8_t>(s[i]));
+        if (state == UTF8_REJECT)
+        {
+            return false;
+        }
+    }
+
+    return state == UTF8_ACCEPT;
+}
+
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

single_include/nlohmann/json.hpp

@@ -6002,11 +6002,15 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
+#include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint8_t, uint32_t
 #include <string> // string, to_string
 
 // #include <nlohmann/detail/abi_macros.hpp>
 
+// #include <nlohmann/detail/macro_scope.hpp>
+
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -6028,6 +6032,103 @@ StringType to_string(std::size_t value)
     return result;
 }
 
+///////////////////
+// UTF-8 decoding //
+///////////////////
+
+// UTF-8 decoder states used by decode() below
+static constexpr std::uint8_t UTF8_ACCEPT = 0;
+static constexpr std::uint8_t UTF8_REJECT = 1;
+
+/*!
+@brief process a byte of a UTF-8 sequence
+
+This is a single-byte step of a "shift-based" UTF-8 decoder originally
+written by Björn Hoehrmann. See
+http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
+
+This decoder is the single source of truth for UTF-8 validation in this
+library: it is used both by the serializer (to escape and, in strict mode,
+reject ill-formed UTF-8 when dumping a string) and by the binary readers
+(to reject ill-formed UTF-8 in CBOR/MessagePack/BSON/UBJSON text strings at
+decode time; see @ref is_valid_utf8 below).
+
+@param[in,out] state  the current decoder state
+@param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)
+@param[in] byte       next byte to decode
+@return               new state
+
+@note Original source: http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+@sa http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+*/
+inline std::uint8_t decode(std::uint8_t& state, std::uint32_t& codep, const std::uint8_t byte) noexcept
+{
+    static const std::array<std::uint8_t, 400> utf8d =
+    {
+        {
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 00..1F
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 20..3F
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 40..5F
+            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 60..7F
+            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 80..9F
+            7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // A0..BF
+            8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // C0..DF
+            0xA, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, // E0..EF
+            0xB, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, // F0..FF
+            0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, // s0..s0
+            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, // s1..s2
+            1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, // s3..s4
+            1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, // s5..s6
+            1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // s7..s8
+        }
+    };
+
+    JSON_ASSERT(static_cast<std::size_t>(byte) < utf8d.size());
+    const std::uint8_t type = utf8d[byte];
+
+    codep = (state != UTF8_ACCEPT)
+            ? (byte & 0x3fu) | (codep << 6u)
+            : (0xFFu >> type) & (byte);
+
+    const std::size_t index = 256u + (static_cast<std::size_t>(state) * 16u) + static_cast<std::size_t>(type);
+    JSON_ASSERT(index < utf8d.size());
+    state = utf8d[index];
+    return state;
+}
+
+/*!
+@brief check whether a string consists solely of valid UTF-8
+
+Used by the CBOR/MessagePack/BSON/UBJSON binary readers to reject text
+strings that are not valid UTF-8 at decode time (RFC 8949 §3.1 and the
+MessagePack/BSON specifications all require text strings to be UTF-8), so
+that malformed input is caught immediately instead of only surfacing later
+as a type_error.316 when the resulting value is dumped.
+
+@param[in] s      the string to check
+@param[in] first  index of the first byte to check; the bytes before it are
+                  assumed to have been validated already and to end on a
+                  code point boundary
+@return whether @a s (from index @a first on) is valid UTF-8
+*/
+template<typename StringType>
+inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noexcept
+{
+    std::uint8_t state = UTF8_ACCEPT;
+    std::uint32_t codepoint = 0;
+
+    for (std::size_t i = first; i < s.size(); ++i)
+    {
+        decode(state, codepoint, static_cast<std::uint8_t>(s[i]));
+        if (state == UTF8_REJECT)
+        {
+            return false;
+        }
+    }
+
+    return state == UTF8_ACCEPT;
+}
+
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END
 
@@ -12016,6 +12117,8 @@ NLOHMANN_JSON_NAMESPACE_END
 
 // #include <nlohmann/detail/string_concat.hpp>
 
+// #include <nlohmann/detail/string_utils.hpp>
+
 // #include <nlohmann/detail/value_t.hpp>
 
 
@@ -12417,7 +12520,21 @@ class binary_reader
                                     exception_message(input_format_t::bson, concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
         }
 
-        return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) && get() != char_traits<char_type>::eof();
+        if (JSON_HEDLEY_UNLIKELY(!get_string(input_format_t::bson, len - static_cast<NumberType>(1), result)))
+        {
+            return false;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(get() != 0x00))
+        {
+            auto last_token = get_token_string();
+            return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
+                                    exception_message(input_format_t::bson,
+                                            "BSON string is not null-terminated",
+                                            "string"), nullptr));
+        }
+
+        return true;
     }
 
     /*!
@@ -12535,8 +12652,6 @@ class binary_reader
         }
     }
 
-
-
     //////////
     // CBOR //
     //////////
@@ -15286,7 +15401,28 @@ class binary_reader
                     const NumberType len,
                     string_t& result)
     {
-        return get_bytes(format, len, "string", result);
+        // get_bytes() appends to result, and CBOR indefinite-length strings
+        // collect all their chunks in the same result; validating only the
+        // newly read bytes keeps the check linear in the input size
+        const std::size_t old_size = result.size();
+        if (JSON_HEDLEY_UNLIKELY(!get_bytes(format, len, "string", result)))
+        {
+            return false;
+        }
+
+        // RFC 8949 (CBOR) §3.1 and the MessagePack/BSON/UBJSON specifications
+        // all require text strings to be valid UTF-8; reject anything else
+        // right here so malformed input is caught at decode time instead of
+        // only surfacing later as a type_error.316 when the value is dumped
+        // (which would defeat allow_exceptions=false / strict discarding).
+        if (JSON_HEDLEY_UNLIKELY(!is_valid_utf8(result, old_size)))
+        {
+            return sax->parse_error(chars_read, get_token_string(),
+                                    parse_error::create(113, chars_read,
+                                            exception_message(format, "invalid string: ill-formed UTF-8 byte", "string"), nullptr));
+        }
+
+        return true;
     }
 
     /*!
@@ -21751,6 +21887,8 @@ NLOHMANN_JSON_NAMESPACE_END
 
 // #include <nlohmann/detail/string_concat.hpp>
 
+// #include <nlohmann/detail/string_utils.hpp>
+
 // #include <nlohmann/detail/value_t.hpp>
 
 
@@ -21778,8 +21916,6 @@ class serializer
     using number_integer_t = typename BasicJsonType::number_integer_t;
     using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
     using binary_char_t = typename BasicJsonType::binary_t::value_type;
-    static constexpr std::uint8_t UTF8_ACCEPT = 0;
-    static constexpr std::uint8_t UTF8_REJECT = 1;
 
   public:
     /*!
@@ -23305,62 +23441,6 @@ class serializer
         }
     }
 
-    /*!
-    @brief check whether a string is UTF-8 encoded
-
-    The function checks each byte of a string whether it is UTF-8 encoded. The
-    result of the check is stored in the @a state parameter. The function must
-    be called initially with state 0 (accept). State 1 means the string must
-    be rejected, because the current byte is not allowed. If the string is
-    completely processed, but the state is non-zero, the string ended
-    prematurely; that is, the last byte indicated more bytes should have
-    followed.
-
-    @param[in,out] state  the state of the decoding
-    @param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)
-    @param[in] byte       next byte to decode
-    @return               new state
-
-    @note The function has been edited: a std::array is used.
-
-    @copyright Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
-    @sa http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
-    */
-    static std::uint8_t decode(std::uint8_t& state, std::uint32_t& codep, const std::uint8_t byte) noexcept
-    {
-        static const std::array<std::uint8_t, 400> utf8d =
-        {
-            {
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 00..1F
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 20..3F
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 40..5F
-                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 60..7F
-                1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 80..9F
-                7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // A0..BF
-                8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // C0..DF
-                0xA, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, // E0..EF
-                0xB, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, // F0..FF
-                0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, // s0..s0
-                1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, // s1..s2
-                1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, // s3..s4
-                1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, // s5..s6
-                1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // s7..s8
-            }
-        };
-
-        JSON_ASSERT(static_cast<std::size_t>(byte) < utf8d.size());
-        const std::uint8_t type = utf8d[byte];
-
-        codep = (state != UTF8_ACCEPT)
-                ? (byte & 0x3fu) | (codep << 6u)
-                : (0xFFu >> type) & (byte);
-
-        const std::size_t index = 256u + (static_cast<size_t>(state) * 16u) + static_cast<size_t>(type);
-        JSON_ASSERT(index < utf8d.size());
-        state = utf8d[index];
-        return state;
-    }
-
     /*
      * Overload to make the compiler happy while it is instantiating
      * dump_integer for number_unsigned_t.

tests/src/unit-bson.cpp

@@ -1688,3 +1688,76 @@ TEST_CASE("BSON roundtrips" * doctest::skip())
         }
     }
 }
+
+TEST_CASE("Invalid document size handling")
+{
+    SECTION("document size must be at least 5")
+    {
+        std::vector<std::uint8_t> const v = {0x04, 0x00, 0x00, 0x00, 0x00};
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 4 does not match the number of bytes read (5)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("declared document size must match consumed bytes (extra trailing element)")
+    {
+        // Declares 5-byte empty document but appends an int32 element after the declared end.
+        std::vector<std::uint8_t> const v =
+        {
+            0x05, 0x00, 0x00, 0x00,
+            0x10, 'a', 'd', 'm', 'i', 'n', 0x00,
+            0x01, 0x00, 0x00, 0x00,
+            0x00
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 16: syntax error while parsing BSON document: document size 5 does not match the number of bytes read (16)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("declared document size must match consumed bytes (premature terminator)")
+    {
+        // Declares 32-byte document but only contains the size field followed by an immediate terminator.
+        std::vector<std::uint8_t> const v =
+        {
+            0x20, 0x00, 0x00, 0x00,
+            0x00
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 32 does not match the number of bytes read (5)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("array declared size must match consumed bytes")
+    {
+        // Outer object contains an array "a" that declares 5 bytes (empty) but
+        // actually contains an int32 element before its terminator.
+        std::vector<std::uint8_t> const v =
+        {
+            0x14, 0x00, 0x00, 0x00,                         // object size = 20
+            0x04, 'a', 0x00,                                // key "a", array type
+            0x05, 0x00, 0x00, 0x00,                         // array declared size = 5 (empty)
+            0x10, '0', 0x00, 0x01, 0x00, 0x00, 0x00,        // extra int32 element "0" = 1
+            0x00,                                           // array terminator
+            0x00                                            // object terminator
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 19: syntax error while parsing BSON document: document size 5 does not match the number of bytes read (12)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("BSON string must end with 0x00")
+    {
+        // Length-prefixed string whose terminator byte is 'X' (0x58), not 0x00.
+        std::vector<std::uint8_t> const v =
+        {
+            0x0F, 0x00, 0x00, 0x00,
+            0x02, 's', 0x00,
+            0x02, 0x00, 0x00, 0x00,
+            'A', 'X',
+            0x00
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 13: syntax error while parsing BSON string: BSON string is not null-terminated", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+}

tests/src/unit-cbor.cpp

@@ -1833,6 +1833,59 @@ TEST_CASE("CBOR")
             CHECK(json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01}), true, false).is_discarded());
         }
 
+        SECTION("invalid UTF-8 in string (see #5529)")
+        {
+            // a two-character text string (major type 3) whose bytes are not
+            // valid UTF-8 (0xC0 0xAE is an overlong encoding of '.') must be
+            // rejected at decode time, matching every other kind of
+            // malformed binary input, rather than only failing later when
+            // the resulting value is dumped
+            json _;
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x62, 0xc0, 0xae})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+            CHECK(json::from_cbor(std::vector<uint8_t>({0x62, 0xc0, 0xae}), true, false).is_discarded());
+
+            // a CBOR byte string (major type 2) with the very same bytes is
+            // NOT text and must still be accepted as-is
+            CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x42, 0xc0, 0xae})));
+            CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
+
+            // valid UTF-8 must still round-trip
+            const json j = "h\xc3\xa9llo, w\xc3\xb6rld! \xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e"; // héllo, wörld! 日本語
+            CHECK(json::from_cbor(json::to_cbor(j)) == j);
+        }
+
+        SECTION("invalid UTF-8 in indefinite-length string")
+        {
+            json _;
+
+            // every chunk must be valid UTF-8 on its own (RFC 8949, Section
+            // 3.2.3), so a code point split across two chunks is rejected
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+            CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff}), true, false).is_discarded());
+
+            // an ill-formed later chunk is rejected after valid ones
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc0, 0xae, 0xff})), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+
+            // valid multi-byte chunks are accepted
+            CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc3, 0xb6, 0xff})) == "\xc3\xa9\xc3\xb6");
+        }
+
+        SECTION("many chunks in indefinite-length string")
+        {
+            // only the newly read chunk is validated, not the whole string
+            // collected so far; validating the latter made this input take
+            // quadratic time (about ten seconds for 100000 chunks)
+            constexpr std::size_t chunks = 100000;
+            std::vector<uint8_t> v{0x7f};
+            for (std::size_t i = 0; i < chunks; ++i)
+            {
+                v.push_back(0x61);
+                v.push_back('a');
+            }
+            v.push_back(0xff);
+            CHECK(json::from_cbor(v) == std::string(chunks, 'a'));
+        }
+
         SECTION("strict mode")
         {
             std::vector<uint8_t> const vec = {0xf6, 0xf6};

tests/src/unit-msgpack.cpp

@@ -1554,6 +1554,27 @@ TEST_CASE("MessagePack")
             CHECK(json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01}), true, false).is_discarded());
         }
 
+        SECTION("invalid UTF-8 in string (see #5529)")
+        {
+            // a fixstr of length 2 (0xA0 | 2) whose bytes are not valid UTF-8
+            // (0xC0 0xAE is an overlong encoding of '.') must be rejected at
+            // decode time, matching every other kind of malformed binary
+            // input, rather than only failing later when the resulting
+            // value is dumped
+            json _;
+            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0xa2, 0xc0, 0xae})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing MessagePack string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+            CHECK(json::from_msgpack(std::vector<uint8_t>({0xa2, 0xc0, 0xae}), true, false).is_discarded());
+
+            // a MessagePack bin8 blob with the very same bytes is NOT text
+            // and must still be accepted as-is
+            CHECK_NOTHROW(_ = json::from_msgpack(std::vector<uint8_t>({0xc4, 0x02, 0xc0, 0xae})));
+            CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
+
+            // valid UTF-8 must still round-trip
+            const json j = "h\xc3\xa9llo, w\xc3\xb6rld! \xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e"; // héllo, wörld! 日本語
+            CHECK(json::from_msgpack(json::to_msgpack(j)) == j);
+        }
+
         SECTION("strict mode")
         {
             std::vector<uint8_t> const vec = {0xc0, 0xc0};

tests/src/unit-serialization.cpp

@@ -94,6 +94,16 @@ TEST_CASE("serialization")
             CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"\\u00e4\\ufffd\\u00fc\"");
         }
 
+        SECTION("invalid character (regression guard for shared UTF-8 decoder, see #5529)")
+        {
+            // dump_escaped_impl() now calls the UTF-8 decoder shared with the
+            // binary readers (detail::decode() in string_utils.hpp) instead
+            // of a private copy; the exact type_error.316 message/behavior
+            // must stay byte-for-byte the same as before that extraction
+            const json j = "ä\xA9ü";
+            CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
+        }
+
         SECTION("ending with incomplete character")
         {
             const json j = "123\xC2";