smartbotic-database/tests/bench_json_parse.cpp

// Parse-time micro-benchmark — Phase A v1.10 yyjson swap.
//
// Compares nlohmann::json::parse against smartbotic::db::parse_to_nlohmann
// on a corpus of JSON documents loaded from a file (one document per line).
// Not a regression gate — informational, run by hand to capture the
// parse-speed delta of the Phase A swap.

#include <algorithm>
#include <chrono>
#include <fstream>
#include <iostream>
#include <string>
#include <vector>

#include <nlohmann/json.hpp>

#include "json_parse.hpp"

int main(int argc, char** argv) {
    if (argc < 2) {
        std::cerr << "usage: bench_json_parse <path-to-json-corpus>\n"
                  << "  corpus = one JSON document per line\n";
        return 1;
    }
    std::ifstream f(argv[1]);
    if (!f) {
        std::cerr << "cannot open " << argv[1] << "\n";
        return 1;
    }
    std::vector<std::string> docs;
    std::string line;
    while (std::getline(f, line)) {
        if (!line.empty()) docs.push_back(line);
    }
    if (docs.empty()) {
        std::cerr << "empty corpus\n";
        return 1;
    }
    std::cerr << "corpus: " << docs.size() << " documents\n";

    constexpr int kIters = 5;
    auto bench = [&](const char* name, auto fn) {
        double best = 1e18;
        for (int i = 0; i < kIters; ++i) {
            auto t0 = std::chrono::steady_clock::now();
            size_t sink = 0;
            for (const auto& s : docs) {
                auto j = fn(s);
                sink += j.size();
            }
            auto t1 = std::chrono::steady_clock::now();
            double ms = std::chrono::duration<double, std::milli>(t1 - t0).count();
            best = std::min(best, ms);
            std::cerr << "  " << name << " iter " << i << ": " << ms
                      << " ms  (sink=" << sink << ")\n";
        }
        return best;
    };

    double nl = bench("nlohmann", [](const std::string& s) {
        return nlohmann::json::parse(s);
    });
    double yy = bench("yyjson  ", [](const std::string& s) {
        return smartbotic::db::parse_to_nlohmann(s);
    });

    std::cout << "best nlohmann: " << nl << " ms\n";
    std::cout << "best yyjson:   " << yy << " ms\n";
    std::cout << "speedup:       " << (nl / yy) << "x\n";
    return 0;
}