Copy the text of float tokens only when a SAX handler asks for it

After the digits are converted while scanning, copying the token text into
token_buffer (an out-of-line std::string::append) was about 10% of parsing
canada.json. The only reader is the string argument of
json_sax::number_float(), and the library's own handlers
(json_sax_dom_parser, json_sax_dom_callback_parser, json_sax_acceptor)
ignore it.

For contiguous input, the fast path now keeps a pointer to the token in the
input, and get_string() copies it on first use. The parser passes an empty
string to the handlers marked by the new internal trait
sax_ignores_number_text instead of calling get_string(), so json::parse()
and json::accept() never copy float text. User handlers, and
JSON_DIAGNOSTIC_POSITIONS (which reads get_string().size()), still see the
exact text. Keys and strings, which never have pending text, use the
unchecked get_string_token(). Input read through a window into a stream
(std::istream, FILE*) copies the text right away, because the next read may
refill the window.

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

include/nlohmann/detail/input/lexer.hpp

@@ -1734,10 +1734,6 @@ scan_number_done:
         }
 #endif
 
-        // materialize the token exactly as scan_number() would. reset() already
-        // cleared token_buffer, so append() fills it (assign() is avoided
-        // because custom string_t types need not provide it)
-        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         decimal_point_position = dot_index;
 
         bulk_consume(data + 1, len - 1);
@@ -1753,10 +1749,27 @@ scan_number_done:
             s.negative = data[0] == '-';
             if (convert_accumulated_float(s, std::integral_constant<bool, has_native_float_format<number_float_t>::value> {}))
             {
+                // the token text is only copied into token_buffer when
+                // get_string() asks for it; the library's own SAX handlers
+                // ignore it. A window into a stream may be refilled by the
+                // next read, so there the text is copied right away.
+                if (bulk_window)
+                {
+                    token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
+                }
+                else
+                {
+                    pending_number_text = data;
+                    pending_number_length = len;
+                }
                 return token_type::value_float;
             }
         }
 
+        // materialize the token exactly as scan_number() would. reset() already
+        // cleared token_buffer, so append() fills it (assign() is avoided
+        // because custom string_t types need not provide it)
+        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         return convert_number(number_type, mantissa_end);
     }
 
@@ -1856,6 +1869,7 @@ scan_number_done:
     void reset() noexcept
     {
         token_buffer.clear();
+        pending_number_text = nullptr;
         decimal_point_position = std::string::npos;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -2115,10 +2129,30 @@ scan_number_done:
     /// return current string value
     string_t& get_string()
     {
+        if (pending_number_text != nullptr)
+        {
+            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(pending_number_text), pending_number_length);
+            pending_number_text = nullptr;
+        }
         // a number token holds '.' regardless of the locale (#4084)
         return token_buffer;
     }
 
+    /// the value of a string token (key or string), which never has pending
+    /// number text, so get_string()'s check is not needed
+    string_t& get_string_token() noexcept
+    {
+        JSON_ASSERT(pending_number_text == nullptr);
+        return token_buffer;
+    }
+
+    /// the text of a float token for a SAX handler that ignores it (the
+    /// library's own handlers): empty, without copying the token
+    const string_t& get_ignored_number_text() const noexcept
+    {
+        return token_buffer;
+    }
+
     /////////////////////
     // diagnostics
     /////////////////////
@@ -2514,6 +2548,11 @@ scan_number_done:
     /// whether the next get() call should just return current
     bool next_unget = false;
 
+    /// the text of the current float token in the input, not yet copied into
+    /// token_buffer (see get_string()), or nullptr
+    const char* pending_number_text = nullptr;
+    std::size_t pending_number_length = 0;
+
     /// the start position of the current token
     position_t position {};
 

include/nlohmann/detail/input/parser.hpp

@@ -51,6 +51,20 @@ template<typename BasicJsonType>
 using parser_callback_t =
     std::function<bool(int /*depth*/, parse_event_t /*event*/, BasicJsonType& /*parsed*/)>;
 
+/// whether a SAX handler ignores the text of float tokens (the library's own
+/// handlers do), so that the parser need not materialize it
+template<typename SAX>
+struct sax_ignores_number_text : std::false_type {};
+
+template<typename BasicJsonType, typename InputAdapterType>
+struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+
+template<typename BasicJsonType, typename InputAdapterType>
+struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+
+template<typename BasicJsonType>
+struct sax_ignores_number_text<json_sax_acceptor<BasicJsonType>> : std::true_type {};
+
 /*!
 @brief syntax analysis
 
@@ -171,6 +185,23 @@ class parser
     }
 
   private:
+    /// the text of the current float token for @a sax (see sax_ignores_number_text)
+    template<typename SAX>
+    const string_t& number_float_text(SAX* /*sax*/)
+    {
+        return number_float_text(std::integral_constant<bool, sax_ignores_number_text<SAX>::value> {});
+    }
+
+    const string_t& number_float_text(std::true_type /*ignored*/) const noexcept
+    {
+        return m_lexer.get_ignored_number_text();
+    }
+
+    string_t& number_float_text(std::false_type /*ignored*/)
+    {
+        return m_lexer.get_string();
+    }
+
     /*!
     @brief run a DOM SAX parser to completion and position the lexer
 
@@ -247,7 +278,7 @@ class parser
                         {
                             return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                         }
-                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                         {
                             return false;
                         }
@@ -301,7 +332,7 @@ class parser
                                                     out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
                         }
 
-                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, number_float_text(sax))))
                         {
                             return false;
                         }
@@ -347,7 +378,7 @@ class parser
 
                     case token_type::value_string:
                     {
-                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string_token())))
                         {
                             return false;
                         }
@@ -456,7 +487,7 @@ class parser
                         return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                     }
 
-                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
+                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                     {
                         return false;
                     }

single_include/nlohmann/json.hpp

@@ -12900,10 +12900,6 @@ scan_number_done:
         }
 #endif
 
-        // materialize the token exactly as scan_number() would. reset() already
-        // cleared token_buffer, so append() fills it (assign() is avoided
-        // because custom string_t types need not provide it)
-        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         decimal_point_position = dot_index;
 
         bulk_consume(data + 1, len - 1);
@@ -12919,10 +12915,27 @@ scan_number_done:
             s.negative = data[0] == '-';
             if (convert_accumulated_float(s, std::integral_constant<bool, has_native_float_format<number_float_t>::value> {}))
             {
+                // the token text is only copied into token_buffer when
+                // get_string() asks for it; the library's own SAX handlers
+                // ignore it. A window into a stream may be refilled by the
+                // next read, so there the text is copied right away.
+                if (bulk_window)
+                {
+                    token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
+                }
+                else
+                {
+                    pending_number_text = data;
+                    pending_number_length = len;
+                }
                 return token_type::value_float;
             }
         }
 
+        // materialize the token exactly as scan_number() would. reset() already
+        // cleared token_buffer, so append() fills it (assign() is avoided
+        // because custom string_t types need not provide it)
+        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         return convert_number(number_type, mantissa_end);
     }
 
@@ -13022,6 +13035,7 @@ scan_number_done:
     void reset() noexcept
     {
         token_buffer.clear();
+        pending_number_text = nullptr;
         decimal_point_position = std::string::npos;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -13281,10 +13295,30 @@ scan_number_done:
     /// return current string value
     string_t& get_string()
     {
+        if (pending_number_text != nullptr)
+        {
+            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(pending_number_text), pending_number_length);
+            pending_number_text = nullptr;
+        }
         // a number token holds '.' regardless of the locale (#4084)
         return token_buffer;
     }
 
+    /// the value of a string token (key or string), which never has pending
+    /// number text, so get_string()'s check is not needed
+    string_t& get_string_token() noexcept
+    {
+        JSON_ASSERT(pending_number_text == nullptr);
+        return token_buffer;
+    }
+
+    /// the text of a float token for a SAX handler that ignores it (the
+    /// library's own handlers): empty, without copying the token
+    const string_t& get_ignored_number_text() const noexcept
+    {
+        return token_buffer;
+    }
+
     /////////////////////
     // diagnostics
     /////////////////////
@@ -13680,6 +13714,11 @@ scan_number_done:
     /// whether the next get() call should just return current
     bool next_unget = false;
 
+    /// the text of the current float token in the input, not yet copied into
+    /// token_buffer (see get_string()), or nullptr
+    const char* pending_number_text = nullptr;
+    std::size_t pending_number_length = 0;
+
     /// the start position of the current token
     position_t position {};
 
@@ -19482,6 +19521,20 @@ template<typename BasicJsonType>
 using parser_callback_t =
     std::function<bool(int /*depth*/, parse_event_t /*event*/, BasicJsonType& /*parsed*/)>;
 
+/// whether a SAX handler ignores the text of float tokens (the library's own
+/// handlers do), so that the parser need not materialize it
+template<typename SAX>
+struct sax_ignores_number_text : std::false_type {};
+
+template<typename BasicJsonType, typename InputAdapterType>
+struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+
+template<typename BasicJsonType, typename InputAdapterType>
+struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+
+template<typename BasicJsonType>
+struct sax_ignores_number_text<json_sax_acceptor<BasicJsonType>> : std::true_type {};
+
 /*!
 @brief syntax analysis
 
@@ -19602,6 +19655,23 @@ class parser
     }
 
   private:
+    /// the text of the current float token for @a sax (see sax_ignores_number_text)
+    template<typename SAX>
+    const string_t& number_float_text(SAX* /*sax*/)
+    {
+        return number_float_text(std::integral_constant<bool, sax_ignores_number_text<SAX>::value> {});
+    }
+
+    const string_t& number_float_text(std::true_type /*ignored*/) const noexcept
+    {
+        return m_lexer.get_ignored_number_text();
+    }
+
+    string_t& number_float_text(std::false_type /*ignored*/)
+    {
+        return m_lexer.get_string();
+    }
+
     /*!
     @brief run a DOM SAX parser to completion and position the lexer
 
@@ -19678,7 +19748,7 @@ class parser
                         {
                             return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                         }
-                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                         {
                             return false;
                         }
@@ -19732,7 +19802,7 @@ class parser
                                                     out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
                         }
 
-                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, number_float_text(sax))))
                         {
                             return false;
                         }
@@ -19778,7 +19848,7 @@ class parser
 
                     case token_type::value_string:
                     {
-                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string_token())))
                         {
                             return false;
                         }
@@ -19887,7 +19957,7 @@ class parser
                         return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                     }
 
-                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
+                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                     {
                         return false;
                     }

tests/src/unit-class_parser.cpp

@@ -30,7 +30,9 @@ using nlohmann::json;
 #include <valarray>
 #include <algorithm>
 #include <cstdio>
+#include <cstdint>
 #include <fstream>
+#include <iterator>
 #include <list>
 #include <sstream>
 #include <string>
@@ -2450,6 +2452,79 @@ std::string parse_error_message_range(IteratorType first, IteratorType last)
 }
 } // namespace
 
+TEST_CASE("text of float tokens")
+{
+    // For contiguous input, the lexer copies the text of a float token into
+    // its buffer only when a SAX handler asks for it (the library's own
+    // handlers do not). A user handler must still see the exact text, for
+    // every input adapter and in every position of a document.
+    const std::string doc = R"([1.5, -0.0, 0.1, 1e5, -2.5E-4, 12345678901234567890.5, 0.12345678901234567890123,
+                              {"a": 3.25, "b": [6.02e23, 1]}, "x", true, 7e-1])";
+    const std::vector<std::string> expected_floats =
+    {
+        "number_float(1.5)", "number_float(-0.0)", "number_float(0.1)", "number_float(1e5)", "number_float(-2.5E-4)",
+        "number_float(12345678901234567890.5)", "number_float(0.12345678901234567890123)", "number_float(3.25)",
+        "number_float(6.02e23)", "number_float(7e-1)"
+    };
+
+    const auto floats = [](const std::vector<std::string>& events)
+    {
+        std::vector<std::string> result;
+        std::copy_if(events.begin(), events.end(), std::back_inserter(result), [](const std::string & e)
+        {
+            return e.compare(0, 13, "number_float(") == 0;
+        });
+        return result;
+    };
+
+    SECTION("contiguous input")
+    {
+        SaxEventLogger l;
+        CHECK(json::sax_parse(doc, &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("byte input")
+    {
+        const std::vector<std::uint8_t> bytes(doc.begin(), doc.end());
+        SaxEventLogger l;
+        CHECK(json::sax_parse(bytes, &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("stream input")
+    {
+        std::istringstream is(doc);
+        SaxEventLogger l;
+        CHECK(json::sax_parse(is, &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("non-contiguous iterators")
+    {
+        const std::list<char> chars(doc.begin(), doc.end());
+        SaxEventLogger l;
+        CHECK(json::sax_parse(chars.begin(), chars.end(), &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("the library's own handlers do not need the text")
+    {
+        using lexer_adapter = nlohmann::detail::iterator_input_adapter<const char*>;
+        CHECK(nlohmann::detail::sax_ignores_number_text<nlohmann::detail::json_sax_dom_parser<json, lexer_adapter>>::value);
+        CHECK(nlohmann::detail::sax_ignores_number_text<nlohmann::detail::json_sax_dom_callback_parser<json, lexer_adapter>>::value);
+        CHECK(nlohmann::detail::sax_ignores_number_text<nlohmann::detail::json_sax_acceptor<json>>::value);
+        CHECK_FALSE(nlohmann::detail::sax_ignores_number_text<SaxEventLogger>::value);
+
+        // and the values are the same as when the text is read
+        const json j = json::parse(doc);
+        CHECK(j[0] == 1.5);
+        CHECK(j[5].get<double>() == 12345678901234567890.5);
+        CHECK(j[7]["b"][0] == 6.02e23);
+        CHECK(json::accept(doc));
+    }
+}
+
 TEST_CASE("last-read diagnostics are identical across input adapters")
 {
     // The lexer reconstructs the "last read" token lazily for seekable adapters