Fix UBSan implicit-conversion in BSON stream tests

std::string(first, last) over std::uint8_t iterators converts each byte
to char implicitly, which -fsanitize=implicit-conversion reports as soon
as a byte is >= 0x80 (the document size byte of the enlarged test input,
and 0xFF in the new array element name test). Build the string from a
const char* and a size instead.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N5NasCxh8jKXBaa6HBx9Xk
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/input/binary_reader.hpp

@@ -465,15 +465,17 @@ 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)))
+            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
             {
                 return false;
             }
 
-            // an array's elements are named "0", "1", ... in the wire format,
+            if (is_object && !sax->key(key))
-            // and those names are not passed on
-            if (container_stack.back().is_object && !sax->key(key))
             {
                 return false;
             }
@@ -489,14 +491,18 @@ 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)
+    bool get_bson_cstr(string_t& result, const bool store = true)
     {
-        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
+        if (get_bson_cstr_bulk(result, store, std::integral_constant<bool, bulk_scan> {}))
         {
-            return check_string_utf8(result, "key");
+            return !store || check_string_utf8(result, "key");
         }
 
         auto out = std::back_inserter(result);
@@ -509,7 +515,7 @@ class binary_reader
             }
             if (current == 0x00)
             {
-                return check_string_utf8(result, "key");
+                return !store || check_string_utf8(result, "key");
             }
             *out++ = static_cast<typename string_t::value_type>(current);
         }
@@ -519,10 +525,11 @@ 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, std::true_type /*bulk*/)
+    bool get_bson_cstr_bulk(string_t& result, const bool store, std::true_type /*bulk*/)
     {
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
@@ -530,18 +537,15 @@ class binary_reader
             return false;
         }
         const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        // a plain loop rather than std::memchr: most keys are short (array
+        const std::size_t length = find_zero_byte(data, remaining);
-        // 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;
         }
-        result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
+        if (store)
+        {
+            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;
@@ -550,7 +554,7 @@ class binary_reader
     }
 
     /// input that is not contiguous: C-style strings are read byte by byte
-    bool get_bson_cstr_bulk(string_t& /*result*/, std::false_type /*bulk*/) const noexcept
+    bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
     {
         return false;
     }

include/nlohmann/detail/input/string_scan.hpp

@@ -90,6 +90,34 @@ 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 -

include/nlohmann/detail/output/binary_writer.hpp

@@ -2088,8 +2088,7 @@ class binary_writer
         /// arrays: the first index with one more digit; only maintained by
         /// @ref calc_bson_sizes
         std::uint64_t index_boundary = 10;
-        /// @ref calc_bson_sizes: where its size goes in the table; @ref
+        /// @ref calc_bson_sizes only: where its size goes in the table
-        /// write_bson_document_single_pass: the position of its size field
         std::size_t size_slot;
         /// @ref calc_bson_sizes only: the size of its entries seen so far
         std::size_t entries_size = 0;
@@ -2340,197 +2339,6 @@ class binary_writer
         }
     }
 
-    template<typename SinkType>
-    using sink_written_t = decltype(std::declval<const SinkType&>().written());
-
-    /*!
-    @brief whether BSON documents can be written in a single pass: the sink
-           can overwrite what it has written (output_vector_sink), and every
-           integer fits the 64 bits BSON has, so that writing an array of
-           numbers needs no range check
-    */
-    using bson_single_pass_sink = std::integral_constant < bool,
-          is_detected<sink_written_t, OutputSinkType>::value
-          && std::numeric_limits<typename BasicJsonType::number_integer_t>::is_specialized
-          && std::numeric_limits<typename BasicJsonType::number_integer_t>::digits <= std::numeric_limits<std::int64_t>::digits
-          && std::numeric_limits<typename BasicJsonType::number_unsigned_t>::is_specialized
-          && std::numeric_limits<typename BasicJsonType::number_unsigned_t>::digits <= std::numeric_limits<std::uint64_t>::digits >;
-
-    /// write a placeholder for the size of an object or array whose entries
-    /// follow; @return its position, for @ref patch_bson_size
-    std::size_t write_bson_size_placeholder()
-    {
-        const std::size_t pos = oa.written();
-        write_number<std::int32_t>(0, true);
-        return pos;
-    }
-
-    /// end the object or array whose size is at @a pos and write its size
-    /// there: everything from that field to the terminating null byte
-    /// @return false (and the size is not written) if it does not fit
-    bool close_bson_container(const std::size_t pos)
-    {
-        oa.write_character(to_char_type(0x00));
-        const std::size_t size = oa.written() - pos;
-        if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(size)))
-        {
-            return false;
-        }
-        std::array<CharType, sizeof(std::int32_t)> bytes{};
-        store_little_endian<std::int32_t>(bytes.data(), static_cast<std::int32_t>(size));
-        oa.overwrite(pos, bytes.data(), bytes.size());
-        return true;
-    }
-
-    /*!
-    @brief check the value @a j of a BSON entry as @ref calc_bson_value_size
-           does, for @ref write_bson_document_single_pass
-    @return at least the size of the value
-    A number, boolean, or null needs no check there (its integers have at most
-    64 bits) and has at most 8 characters; a discarded value is rejected with
-    the same exception when it is written.
-    */
-    std::size_t check_bson_value(const BasicJsonType& j)
-    {
-        return (j.is_string() || j.is_binary()) ? calc_bson_value_size(j) : 8;
-    }
-
-    /// whether an entry of @a entry_size characters keeps the document that
-    /// begins at @a start, closed by @a open_containers null bytes, within
-    /// the 32-bit size of BSON
-    bool bson_entry_fits(const std::size_t start, const std::size_t entry_size, const std::size_t open_containers) const noexcept
-    {
-        const std::size_t limit = static_cast<std::size_t>((std::numeric_limits<std::int32_t>::max)());
-        const std::size_t written = oa.written() - start;
-        return written <= limit && entry_size <= limit - written && open_containers <= limit - written - entry_size;
-    }
-
-    /*!
-    @brief Serializes the JSON object @a document as a BSON document in a
-           single pass, writing the size of each object and array once it is
-           complete
-
-    Checks every key and value as @ref calc_bson_sizes does, in the same
-    order, so the same exception is thrown; the output written up to then is
-    discarded with the vector it was written to.
-
-    @return false as soon as the document or a string, binary value, object,
-            or array in it would be larger than the 32-bit BSON sizes allow;
-            nothing large has been written then, and the caller writes the
-            document in two passes, which reports that error
-    */
-    template < typename SinkType = OutputSinkType,
-               typename std::enable_if < is_detected<sink_written_t, SinkType>::value, int >::type = 0 >
-    bool write_bson_document_single_pass(const BasicJsonType& document)
-    {
-        const std::size_t start = oa.written();
-        // the object or array whose entries are being written (with the
-        // position of its size), and the ones it is in
-        bson_frame current(&document, write_bson_size_placeholder());
-        std::vector<bson_frame> parents;
-
-        while (true)
-        {
-            const BasicJsonType* nested = nullptr;
-            std::size_t nested_size_pos = 0;
-            if (current.value->is_object())
-            {
-                const auto& object = *current.value->m_data.m_value.object;
-                while (nested == nullptr && current.member != object.cend())
-                {
-                    const auto& el = *current.member;
-                    ++current.member;
-                    const std::size_t header_size = calc_bson_entry_header_size(el.first, el.second);
-                    const std::size_t value_size = el.second.is_structured() ? 0 : check_bson_value(el.second);
-                    if (JSON_HEDLEY_UNLIKELY(!bson_entry_fits(start, header_size + value_size, parents.size() + 1)))
-                    {
-                        return false;
-                    }
-                    if (el.second.is_structured())
-                    {
-                        write_bson_entry_header(el.first, el.second.is_object() ? 0x03 : 0x04);
-                        nested_size_pos = write_bson_size_placeholder();
-                        nested = &el.second;
-                    }
-                    else
-                    {
-                        write_bson_value(el.first, el.second);
-                    }
-                }
-            }
-            else
-            {
-                const auto& array = *current.value->m_data.m_value.array;
-                while (nested == nullptr && current.index < array.size())
-                {
-                    if (is_bson_fixed_size(array[current.index]))
-                    {
-                        write_bson_array_fixed_entries(current);
-                        if (current.index == array.size())
-                        {
-                            break;
-                        }
-                    }
-
-                    // a string, binary value, object or array
-                    const BasicJsonType& el = array[current.index];
-                    const string_t index_name(current.index_name.data(), current.index_name_size);
-                    current.next_index();
-                    const std::size_t value_size = el.is_structured() ? 0 : check_bson_value(el);
-                    if (JSON_HEDLEY_UNLIKELY(!bson_entry_fits(start, 2 + index_name.size() + value_size, parents.size() + 1)))
-                    {
-                        return false;
-                    }
-                    if (el.is_structured())
-                    {
-                        write_bson_entry_header(index_name, el.is_object() ? 0x03 : 0x04);
-                        nested_size_pos = write_bson_size_placeholder();
-                        nested = &el;
-                    }
-                    else
-                    {
-                        write_bson_value(index_name, el);
-                    }
-                }
-            }
-
-            if (nested != nullptr)
-            {
-                if (nested->is_array())
-                {
-                    // an array of booleans, numbers and null is written without a frame on the stack
-                    bson_frame leaf(nested, nested_size_pos);
-                    write_bson_array_fixed_entries(leaf);
-                    if (leaf.index == nested->m_data.m_value.array->size())
-                    {
-                        if (JSON_HEDLEY_UNLIKELY(!close_bson_container(nested_size_pos)))
-                        {
-                            return false;
-                        }
-                        continue;
-                    }
-                    parents.push_back(std::move(current));
-                    current = std::move(leaf);
-                    continue;
-                }
-                parents.push_back(std::move(current));
-                current = bson_frame(nested, nested_size_pos);
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!close_bson_container(current.size_slot)))
-            {
-                return false;
-            }
-            if (parents.empty())
-            {
-                return true;
-            }
-            current = std::move(parents.back());
-            parents.pop_back();
-        }
-    }
-
     /*!
     @brief Serializes the JSON object @a document as a BSON document
 
@@ -2542,39 +2350,6 @@ class binary_writer
     @pre       document.type() == value_t::object
     */
     void write_bson_document(const BasicJsonType& document)
-    {
-        write_bson_document(document, bson_single_pass_sink());
-    }
-
-    /// the sink can overwrite: one pass, unless the error handler replaces or
-    /// drops ill-formed UTF-8, which changes the sizes the checks compute
-    void write_bson_document(const BasicJsonType& document, std::true_type /*single_pass*/)
-    {
-        const std::size_t start = oa.written();
-        if ((error_handler == error_handler_t::keep || error_handler == error_handler_t::strict)
-                && write_bson_document_single_pass(document))
-        {
-            return;
-        }
-        // a length does not fit: start over, so that it is reported as the
-        // two passes report it, before anything is written
-        oa.rewind(start);
-        write_bson_document_two_pass(document);
-    }
-
-    void write_bson_document(const BasicJsonType& document, std::false_type /*single_pass*/)
-    {
-        write_bson_document_two_pass(document);
-    }
-
-    /*!
-    @brief Serializes the JSON object @a document as a BSON document: the
-           sizes of all objects and arrays first, then the entries
-
-    @param[in] document  the JSON object to serialize
-    @pre       document.type() == value_t::object
-    */
-    void write_bson_document_two_pass(const BasicJsonType& document)
     {
         std::vector<std::size_t> nested_sizes;
         const std::size_t document_size = calc_bson_sizes(document, nested_sizes);

include/nlohmann/detail/output/output_adapters.hpp

@@ -227,29 +227,6 @@ class output_vector_sink
     void flush() noexcept
     {}
 
-    /// the number of characters written so far, the position of the next one
-    std::size_t written() const noexcept
-    {
-        return position();
-    }
-
-    /// @brief replace @a length characters written before, from position @a pos
-    ///
-    /// Lets a writer put a length in front of data it has written since, such
-    /// as the size of a BSON document, without computing it in advance.
-    void overwrite(const std::size_t pos, const CharType* s, const std::size_t length) noexcept
-    {
-        JSON_ASSERT(pos + length <= position());
-        std::memcpy(v->data() + pos, s, length * sizeof(CharType));
-    }
-
-    /// drop the characters written from position @a pos on
-    void rewind(const std::size_t pos) noexcept
-    {
-        JSON_ASSERT(pos <= position());
-        cursor = v->data() + pos;
-    }
-
   private:
     /// number of characters of *v written so far
     std::size_t position() const noexcept

single_include/nlohmann/json.hpp

@@ -12458,6 +12458,34 @@ 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 -
@@ -18241,15 +18269,17 @@ 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)))
+            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
             {
                 return false;
             }
 
-            // an array's elements are named "0", "1", ... in the wire format,
+            if (is_object && !sax->key(key))
-            // and those names are not passed on
-            if (container_stack.back().is_object && !sax->key(key))
             {
                 return false;
             }
@@ -18265,14 +18295,18 @@ 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)
+    bool get_bson_cstr(string_t& result, const bool store = true)
     {
-        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
+        if (get_bson_cstr_bulk(result, store, std::integral_constant<bool, bulk_scan> {}))
         {
-            return check_string_utf8(result, "key");
+            return !store || check_string_utf8(result, "key");
         }
 
         auto out = std::back_inserter(result);
@@ -18285,7 +18319,7 @@ class binary_reader
             }
             if (current == 0x00)
             {
-                return check_string_utf8(result, "key");
+                return !store || check_string_utf8(result, "key");
             }
             *out++ = static_cast<typename string_t::value_type>(current);
         }
@@ -18295,10 +18329,11 @@ 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, std::true_type /*bulk*/)
+    bool get_bson_cstr_bulk(string_t& result, const bool store, std::true_type /*bulk*/)
     {
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
@@ -18306,18 +18341,15 @@ class binary_reader
             return false;
         }
         const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        // a plain loop rather than std::memchr: most keys are short (array
+        const std::size_t length = find_zero_byte(data, remaining);
-        // 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;
         }
-        result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
+        if (store)
+        {
+            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;
@@ -18326,7 +18358,7 @@ class binary_reader
     }
 
     /// input that is not contiguous: C-style strings are read byte by byte
-    bool get_bson_cstr_bulk(string_t& /*result*/, std::false_type /*bulk*/) const noexcept
+    bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
     {
         return false;
     }
@@ -26870,29 +26902,6 @@ class output_vector_sink
     void flush() noexcept
     {}
 
-    /// the number of characters written so far, the position of the next one
-    std::size_t written() const noexcept
-    {
-        return position();
-    }
-
-    /// @brief replace @a length characters written before, from position @a pos
-    ///
-    /// Lets a writer put a length in front of data it has written since, such
-    /// as the size of a BSON document, without computing it in advance.
-    void overwrite(const std::size_t pos, const CharType* s, const std::size_t length) noexcept
-    {
-        JSON_ASSERT(pos + length <= position());
-        std::memcpy(v->data() + pos, s, length * sizeof(CharType));
-    }
-
-    /// drop the characters written from position @a pos on
-    void rewind(const std::size_t pos) noexcept
-    {
-        JSON_ASSERT(pos <= position());
-        cursor = v->data() + pos;
-    }
-
   private:
     /// number of characters of *v written so far
     std::size_t position() const noexcept
@@ -29337,8 +29346,7 @@ class binary_writer
         /// arrays: the first index with one more digit; only maintained by
         /// @ref calc_bson_sizes
         std::uint64_t index_boundary = 10;
-        /// @ref calc_bson_sizes: where its size goes in the table; @ref
+        /// @ref calc_bson_sizes only: where its size goes in the table
-        /// write_bson_document_single_pass: the position of its size field
         std::size_t size_slot;
         /// @ref calc_bson_sizes only: the size of its entries seen so far
         std::size_t entries_size = 0;
@@ -29589,197 +29597,6 @@ class binary_writer
         }
     }
 
-    template<typename SinkType>
-    using sink_written_t = decltype(std::declval<const SinkType&>().written());
-
-    /*!
-    @brief whether BSON documents can be written in a single pass: the sink
-           can overwrite what it has written (output_vector_sink), and every
-           integer fits the 64 bits BSON has, so that writing an array of
-           numbers needs no range check
-    */
-    using bson_single_pass_sink = std::integral_constant < bool,
-          is_detected<sink_written_t, OutputSinkType>::value
-          && std::numeric_limits<typename BasicJsonType::number_integer_t>::is_specialized
-          && std::numeric_limits<typename BasicJsonType::number_integer_t>::digits <= std::numeric_limits<std::int64_t>::digits
-          && std::numeric_limits<typename BasicJsonType::number_unsigned_t>::is_specialized
-          && std::numeric_limits<typename BasicJsonType::number_unsigned_t>::digits <= std::numeric_limits<std::uint64_t>::digits >;
-
-    /// write a placeholder for the size of an object or array whose entries
-    /// follow; @return its position, for @ref patch_bson_size
-    std::size_t write_bson_size_placeholder()
-    {
-        const std::size_t pos = oa.written();
-        write_number<std::int32_t>(0, true);
-        return pos;
-    }
-
-    /// end the object or array whose size is at @a pos and write its size
-    /// there: everything from that field to the terminating null byte
-    /// @return false (and the size is not written) if it does not fit
-    bool close_bson_container(const std::size_t pos)
-    {
-        oa.write_character(to_char_type(0x00));
-        const std::size_t size = oa.written() - pos;
-        if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(size)))
-        {
-            return false;
-        }
-        std::array<CharType, sizeof(std::int32_t)> bytes{};
-        store_little_endian<std::int32_t>(bytes.data(), static_cast<std::int32_t>(size));
-        oa.overwrite(pos, bytes.data(), bytes.size());
-        return true;
-    }
-
-    /*!
-    @brief check the value @a j of a BSON entry as @ref calc_bson_value_size
-           does, for @ref write_bson_document_single_pass
-    @return at least the size of the value
-    A number, boolean, or null needs no check there (its integers have at most
-    64 bits) and has at most 8 characters; a discarded value is rejected with
-    the same exception when it is written.
-    */
-    std::size_t check_bson_value(const BasicJsonType& j)
-    {
-        return (j.is_string() || j.is_binary()) ? calc_bson_value_size(j) : 8;
-    }
-
-    /// whether an entry of @a entry_size characters keeps the document that
-    /// begins at @a start, closed by @a open_containers null bytes, within
-    /// the 32-bit size of BSON
-    bool bson_entry_fits(const std::size_t start, const std::size_t entry_size, const std::size_t open_containers) const noexcept
-    {
-        const std::size_t limit = static_cast<std::size_t>((std::numeric_limits<std::int32_t>::max)());
-        const std::size_t written = oa.written() - start;
-        return written <= limit && entry_size <= limit - written && open_containers <= limit - written - entry_size;
-    }
-
-    /*!
-    @brief Serializes the JSON object @a document as a BSON document in a
-           single pass, writing the size of each object and array once it is
-           complete
-
-    Checks every key and value as @ref calc_bson_sizes does, in the same
-    order, so the same exception is thrown; the output written up to then is
-    discarded with the vector it was written to.
-
-    @return false as soon as the document or a string, binary value, object,
-            or array in it would be larger than the 32-bit BSON sizes allow;
-            nothing large has been written then, and the caller writes the
-            document in two passes, which reports that error
-    */
-    template < typename SinkType = OutputSinkType,
-               typename std::enable_if < is_detected<sink_written_t, SinkType>::value, int >::type = 0 >
-    bool write_bson_document_single_pass(const BasicJsonType& document)
-    {
-        const std::size_t start = oa.written();
-        // the object or array whose entries are being written (with the
-        // position of its size), and the ones it is in
-        bson_frame current(&document, write_bson_size_placeholder());
-        std::vector<bson_frame> parents;
-
-        while (true)
-        {
-            const BasicJsonType* nested = nullptr;
-            std::size_t nested_size_pos = 0;
-            if (current.value->is_object())
-            {
-                const auto& object = *current.value->m_data.m_value.object;
-                while (nested == nullptr && current.member != object.cend())
-                {
-                    const auto& el = *current.member;
-                    ++current.member;
-                    const std::size_t header_size = calc_bson_entry_header_size(el.first, el.second);
-                    const std::size_t value_size = el.second.is_structured() ? 0 : check_bson_value(el.second);
-                    if (JSON_HEDLEY_UNLIKELY(!bson_entry_fits(start, header_size + value_size, parents.size() + 1)))
-                    {
-                        return false;
-                    }
-                    if (el.second.is_structured())
-                    {
-                        write_bson_entry_header(el.first, el.second.is_object() ? 0x03 : 0x04);
-                        nested_size_pos = write_bson_size_placeholder();
-                        nested = &el.second;
-                    }
-                    else
-                    {
-                        write_bson_value(el.first, el.second);
-                    }
-                }
-            }
-            else
-            {
-                const auto& array = *current.value->m_data.m_value.array;
-                while (nested == nullptr && current.index < array.size())
-                {
-                    if (is_bson_fixed_size(array[current.index]))
-                    {
-                        write_bson_array_fixed_entries(current);
-                        if (current.index == array.size())
-                        {
-                            break;
-                        }
-                    }
-
-                    // a string, binary value, object or array
-                    const BasicJsonType& el = array[current.index];
-                    const string_t index_name(current.index_name.data(), current.index_name_size);
-                    current.next_index();
-                    const std::size_t value_size = el.is_structured() ? 0 : check_bson_value(el);
-                    if (JSON_HEDLEY_UNLIKELY(!bson_entry_fits(start, 2 + index_name.size() + value_size, parents.size() + 1)))
-                    {
-                        return false;
-                    }
-                    if (el.is_structured())
-                    {
-                        write_bson_entry_header(index_name, el.is_object() ? 0x03 : 0x04);
-                        nested_size_pos = write_bson_size_placeholder();
-                        nested = &el;
-                    }
-                    else
-                    {
-                        write_bson_value(index_name, el);
-                    }
-                }
-            }
-
-            if (nested != nullptr)
-            {
-                if (nested->is_array())
-                {
-                    // an array of booleans, numbers and null is written without a frame on the stack
-                    bson_frame leaf(nested, nested_size_pos);
-                    write_bson_array_fixed_entries(leaf);
-                    if (leaf.index == nested->m_data.m_value.array->size())
-                    {
-                        if (JSON_HEDLEY_UNLIKELY(!close_bson_container(nested_size_pos)))
-                        {
-                            return false;
-                        }
-                        continue;
-                    }
-                    parents.push_back(std::move(current));
-                    current = std::move(leaf);
-                    continue;
-                }
-                parents.push_back(std::move(current));
-                current = bson_frame(nested, nested_size_pos);
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!close_bson_container(current.size_slot)))
-            {
-                return false;
-            }
-            if (parents.empty())
-            {
-                return true;
-            }
-            current = std::move(parents.back());
-            parents.pop_back();
-        }
-    }
-
     /*!
     @brief Serializes the JSON object @a document as a BSON document
 
@@ -29791,39 +29608,6 @@ class binary_writer
     @pre       document.type() == value_t::object
     */
     void write_bson_document(const BasicJsonType& document)
-    {
-        write_bson_document(document, bson_single_pass_sink());
-    }
-
-    /// the sink can overwrite: one pass, unless the error handler replaces or
-    /// drops ill-formed UTF-8, which changes the sizes the checks compute
-    void write_bson_document(const BasicJsonType& document, std::true_type /*single_pass*/)
-    {
-        const std::size_t start = oa.written();
-        if ((error_handler == error_handler_t::keep || error_handler == error_handler_t::strict)
-                && write_bson_document_single_pass(document))
-        {
-            return;
-        }
-        // a length does not fit: start over, so that it is reported as the
-        // two passes report it, before anything is written
-        oa.rewind(start);
-        write_bson_document_two_pass(document);
-    }
-
-    void write_bson_document(const BasicJsonType& document, std::false_type /*single_pass*/)
-    {
-        write_bson_document_two_pass(document);
-    }
-
-    /*!
-    @brief Serializes the JSON object @a document as a BSON document: the
-           sizes of all objects and arrays first, then the entries
-
-    @param[in] document  the JSON object to serialize
-    @pre       document.type() == value_t::object
-    */
-    void write_bson_document_two_pass(const BasicJsonType& document)
     {
         std::vector<std::size_t> nested_sizes;
         const std::size_t document_size = calc_bson_sizes(document, nested_sizes);

tests/src/unit-bson.cpp

@@ -1164,7 +1164,13 @@ 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
-    const json j = {{"", true}, {"k", {1, 2, 3}}, {std::string(40, 'x'), {{"nested key", "value"}}}};
+    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);
 
@@ -1184,7 +1190,7 @@ TEST_CASE("BSON keys from contiguous and stream input")
         }
         try
         {
-            std::istringstream stream(std::string(input.begin(), input.end()));
+            std::istringstream stream(std::string(reinterpret_cast<const char*>(input.data()), input.size()));
             from_stream = json::from_bson(stream).dump();
         }
         catch (const json::parse_error& e)
@@ -1194,6 +1200,33 @@ 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")
@@ -2267,132 +2300,3 @@ TEST_CASE("BSON large strings and binaries (chunked reader)")
         }
     }
 }
-
-TEST_CASE("BSON written in one pass and in two passes")
-{
-    // to_bson() into a returned vector writes each size once the object or
-    // array is complete; through an output adapter, all sizes are computed
-    // first. Both must produce the same bytes and throw the same exceptions.
-    const auto two_pass = [](const json & j, const json::error_handler_t handler)
-    {
-        std::vector<std::uint8_t> result;
-        json::to_bson(j, result, handler);
-        return result;
-    };
-
-    const auto check_same = [&](const json & j, const json::error_handler_t handler)
-    {
-        CAPTURE(j.dump(-1, ' ', true, json::error_handler_t::replace))
-        CAPTURE(static_cast<int>(handler))
-#if !defined(JSON_NOEXCEPTION)
-        std::string one_pass_error;
-        std::string two_pass_error;
-        std::vector<std::uint8_t> one;
-        std::vector<std::uint8_t> two;
-        try
-        {
-            one = json::to_bson(j, handler);
-        }
-        catch (const json::exception& e)
-        {
-            one_pass_error = e.what();
-        }
-        try
-        {
-            two = two_pass(j, handler);
-        }
-        catch (const json::exception& e)
-        {
-            two_pass_error = e.what();
-        }
-        CHECK(one_pass_error == two_pass_error);
-        CHECK(one == two);
-#else
-        CHECK(json::to_bson(j, handler) == two_pass(j, handler));
-#endif
-    };
-
-    const json::error_handler_t handlers[] = {json::error_handler_t::keep, json::error_handler_t::strict,
-                                              json::error_handler_t::replace, json::error_handler_t::ignore
-                                             };
-
-    SECTION("corpus")
-    {
-        for (const auto& value : utils::round_trip_corpus::values())
-        {
-            const json document = value.is_object() ? value : json{{"value", value}};
-            for (const auto handler : handlers)
-            {
-                check_same(document, handler);
-            }
-        }
-    }
-
-    SECTION("nesting and arrays of every length class")
-    {
-        json document = json::object();
-        document["empty object"] = json::object();
-        document["empty array"] = json::array();
-        for (const std::size_t n :
-                {
-                    std::size_t(1), std::size_t(9), std::size_t(10), std::size_t(11), std::size_t(99), std::size_t(100), std::size_t(101), std::size_t(1000)
-                })
-        {
-            json numbers = json::array();
-            json mixed = json::array();
-            for (std::size_t i = 0; i < n; ++i)
-            {
-                numbers.push_back(i % 3 == 0 ? json(static_cast<double>(i) / 3) : json(static_cast<std::int64_t>(i) * 1000003));
-                mixed.push_back(i % 4 == 0 ? json("s" + std::to_string(i)) : i % 4 == 1 ? json::array({i, json::object({{"k", i}})}) : i % 4 == 2 ? json(nullptr) : json(i % 2 == 0));
-            }
-            document["numbers " + std::to_string(n)] = numbers;
-            document["mixed " + std::to_string(n)] = mixed;
-            document["nested " + std::to_string(n)] = json::object({{"a", numbers}, {"b", json::array({mixed, json::object()})}});
-        }
-        document["binary"] = json::binary({1, 2, 3}, 0x80);
-        document["binary old"] = json::binary({1, 2, 3}, 0x02);
-        for (const auto handler : handlers)
-        {
-            check_same(document, handler);
-        }
-    }
-
-    SECTION("errors at every position")
-    {
-        // an entry that cannot be written, at each place among valid ones
-        const std::string bad_utf8 = "\xC3\x28";
-        const json bad_entries[] =
-        {
-            json::object({{std::string("a\0b", 3), 1}}),
-            json::object({{"s", bad_utf8}}),
-            json::object({{bad_utf8, 1}}),
-            json::array({1, 2, bad_utf8}),
-            json::object({{"b", json::binary({1}, 0x100)}}),
-            json::object({{"d", json(json::value_t::discarded)}}),
-            json::array({json(json::value_t::discarded)}),
-        };
-        for (const auto& bad : bad_entries)
-        {
-            for (std::size_t pos = 0; pos < 4; ++pos)
-            {
-                json document = json::object();
-                json list = json::array();
-                for (std::size_t i = 0; i < 4; ++i)
-                {
-                    if (i == pos)
-                    {
-                        document["x" + std::to_string(i)] = bad;
-                        list.push_back(bad);
-                    }
-                    document["n" + std::to_string(i)] = json::array({i, "str", json::object({{"k", i}})});
-                    list.push_back(i);
-                }
-                document["list"] = list;
-                for (const auto handler : handlers)
-                {
-                    check_same(document, handler);
-                }
-            }
-        }
-    }
-}