Read BSON keys in bulk from contiguous input

BSON keys (and array indices) are C-style strings, which were read byte
by byte. For contiguous input they are now read up to their \x00-byte in
one step, using the same bulk_scan flag as BON8 strings: twitter.json is
read in 1.46 instead of 2.01 ms, citm_catalog.json in 2.93 instead of
3.33 ms, jeopardy.json in 182 instead of 207 ms. canada.json, whose keys
are almost all one-digit array indices, takes 2 % longer.

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -411,6 +411,11 @@ class binary_reader
     */
     bool get_bson_cstr(string_t& result)
     {
+        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
+        {
+            return true;
+        }
+
         auto out = std::back_inserter(result);
         while (true)
         {
@@ -427,6 +432,46 @@ class binary_reader
         }
     }
 
+    /*!
+    @brief read a C-style string from contiguous input in one step
+
+    @param[in,out] result  the string to append to
+    @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*/)
+    {
+        const std::size_t remaining = ia.bulk_remaining();
+        if (remaining == 0)
+        {
+            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
+        // 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);
+        // consume the string and its \x00-byte, as the byte-wise path does
+        ia.bulk_skip(length + 1);
+        chars_read += length + 1;
+        current = 0x00;
+        return true;
+    }
+
+    /// 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
+    {
+        return false;
+    }
+
     /*!
     @brief Parses a zero-terminated string of length @a len from the BSON
            input.

single_include/nlohmann/json.hpp

@@ -12930,6 +12930,11 @@ class binary_reader
     */
     bool get_bson_cstr(string_t& result)
     {
+        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
+        {
+            return true;
+        }
+
         auto out = std::back_inserter(result);
         while (true)
         {
@@ -12946,6 +12951,46 @@ class binary_reader
         }
     }
 
+    /*!
+    @brief read a C-style string from contiguous input in one step
+
+    @param[in,out] result  the string to append to
+    @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*/)
+    {
+        const std::size_t remaining = ia.bulk_remaining();
+        if (remaining == 0)
+        {
+            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
+        // 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);
+        // consume the string and its \x00-byte, as the byte-wise path does
+        ia.bulk_skip(length + 1);
+        chars_read += length + 1;
+        current = 0x00;
+        return true;
+    }
+
+    /// 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
+    {
+        return false;
+    }
+
     /*!
     @brief Parses a zero-terminated string of length @a len from the BSON
            input.

tests/src/unit-bson.cpp

@@ -1066,6 +1066,42 @@ TEST_CASE("Incomplete BSON Input")
     }
 }
 
+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"}}}};
+    const std::vector<std::uint8_t> bson = json::to_bson(j);
+    CHECK(json::from_bson(bson) == j);
+
+    for (std::size_t length = 0; length <= bson.size(); ++length)
+    {
+        CAPTURE(length)
+        const std::vector<std::uint8_t> input(bson.begin(), bson.begin() + static_cast<std::ptrdiff_t>(length));
+        std::string from_vector;
+        std::string from_stream;
+        try
+        {
+            from_vector = json::from_bson(input).dump();
+        }
+        catch (const json::parse_error& e)
+        {
+            from_vector = e.what();
+        }
+        try
+        {
+            std::istringstream stream(std::string(input.begin(), input.end()));
+            from_stream = json::from_bson(stream).dump();
+        }
+        catch (const json::parse_error& e)
+        {
+            from_stream = e.what();
+        }
+        CHECK(from_vector == from_stream);
+    }
+}
+
 TEST_CASE("Negative size of binary value")
 {
     // invalid BSON: the size of the binary value is -1