Benchmark parsing of pretty-printed JSON

Every input in the benchmark corpus is minified or only lightly spaced, so
none of them exercise the lexer's whitespace handling. Real-world JSON is
frequently indented - configuration files, pretty-printed API responses,
anything kept under version control - where the insignificant whitespace can
outweigh the data itself.

Add a ParseIndented family that re-serializes each document with an
indentation and parses that. The content is identical to the matching
ParseString row, so the pair isolates the cost of the whitespace alone.
Measured here, parsing the indented form costs 16-34% more than the minified
form of the same document, which nothing in the suite currently reports.

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

include/nlohmann/detail/output/serializer.hpp

@@ -850,16 +850,15 @@ class serializer
                 // for the scan. Without it, text whose characters all have to be
                 // escaped - CJK under ensure_ascii, where every byte is >= 0x80 -
                 // runs the scanner once per character only to be told zero.
-                const std::size_t run = [&]() -> std::size_t
+                std::size_t run = 0;
+                if (!EnsureAscii)
                 {
-                    if (EnsureAscii)
+                    run = string_bulk_run(data + i, s.size() - i);
-                    {
+                }
-                        return is_ascii_copyable(data[i])
+                else if (is_ascii_copyable(data[i]))
-                        ? find_ascii_copyable_run(data + i, s.size() - i)
+                {
-                        : 0;
+                    run = find_ascii_copyable_run(data + i, s.size() - i);
-                    }
+                }
-                    return string_bulk_run(data + i, s.size() - i);
-                }();
                 if (run != 0)
                 {
                     // emit any bytes still pending in string_buffer first to

single_include/nlohmann/json.hpp

@@ -21910,16 +21910,15 @@ class serializer
                 // for the scan. Without it, text whose characters all have to be
                 // escaped - CJK under ensure_ascii, where every byte is >= 0x80 -
                 // runs the scanner once per character only to be told zero.
-                const std::size_t run = [&]() -> std::size_t
+                std::size_t run = 0;
+                if (!EnsureAscii)
                 {
-                    if (EnsureAscii)
+                    run = string_bulk_run(data + i, s.size() - i);
-                    {
+                }
-                        return is_ascii_copyable(data[i])
+                else if (is_ascii_copyable(data[i]))
-                        ? find_ascii_copyable_run(data + i, s.size() - i)
+                {
-                        : 0;
+                    run = find_ascii_copyable_run(data + i, s.size() - i);
-                    }
+                }
-                    return string_bulk_run(data + i, s.size() - i);
-                }();
                 if (run != 0)
                 {
                     // emit any bytes still pending in string_buffer first to

tests/benchmarks/src/benchmarks.cpp

@@ -81,6 +81,44 @@ BENCHMARK_CAPTURE(ParseString, signed_ints,       TEST_DATA_DIRECTORY "/regressi
 BENCHMARK_CAPTURE(ParseString, unsigned_ints,     TEST_DATA_DIRECTORY "/regression/unsigned_ints.json");
 BENCHMARK_CAPTURE(ParseString, small_signed_ints, TEST_DATA_DIRECTORY "/regression/small_signed_ints.json");
 
+//////////////////////////////////////////////////////////////////////////////
+// parse pretty-printed JSON from string
+//
+// Every file in the corpus above is minified or only lightly spaced, so none of
+// them exercise the lexer's whitespace handling. Real-world JSON is frequently
+// indented - configuration files, pretty-printed API responses, anything kept
+// under version control - where insignificant whitespace can outweigh the data.
+// Re-serializing a document with an indentation and parsing that keeps the
+// content identical to the ParseString row above, so the pair isolates the cost
+// of the whitespace alone.
+//////////////////////////////////////////////////////////////////////////////
+
+static void ParseIndented(benchmark::State& state, const char* filename, int indent)
+{
+    std::ifstream f(filename);
+    std::string str((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+    const std::string indented = json::parse(str).dump(indent);
+
+    while (state.KeepRunning())
+    {
+        state.PauseTiming();
+        auto* j = new json();
+        state.ResumeTiming();
+
+        *j = json::parse(indented);
+
+        state.PauseTiming();
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * indented.size());
+}
+BENCHMARK_CAPTURE(ParseIndented, jeopardy / 4,     TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json",                 4);
+BENCHMARK_CAPTURE(ParseIndented, canada / 4,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json",       4);
+BENCHMARK_CAPTURE(ParseIndented, citm_catalog / 4, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", 4);
+BENCHMARK_CAPTURE(ParseIndented, twitter / 4,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json",      4);
+
 //////////////////////////////////////////////////////////////////////////////
 // serialize JSON
 //////////////////////////////////////////////////////////////////////////////