Fast & simple JSONLines processor in C++ using boost::json

This example will parse a jsonlines file (a file with one JSON object per line) and print the name field of each object.

This code has not specifically been optimized for performance but rather as a trade-off between performance and readability. It should be fast enough for most use cases.

#include <iostream>
#include <fstream>
#include <string>
#include <boost/json.hpp>

class JSONLineProcessor {
public:
    JSONLineProcessor(const std::string& filename) : file(filename) {
        if (!file.is_open()) {
            throw std::runtime_error("Error: Could not open file.");
        }
    }

    void process_lines() {
        std::string line;
        while (std::getline(file, line)) {
            process_line(line);
        }
    }

private:
    std::ifstream file;

    void process_line(const std::string& line) {
        try {
            // Parse the JSON line
            boost::json::value json_value = boost::json::parse(line);

            // Check if it's a JSON object
            if (json_value.is_object()) {
                process_json(json_value.as_object());
            } else {
                std::cerr << "Error: Parsed value is not a JSON object." << std::endl;
            }
        } catch (const boost::json::system_error& e) {
            // Handle parsing errors
            std::cerr << "Error parsing JSON line: " << e.what() << std::endl;
        }
    }

    void process_json(const boost::json::object& obj) {
        // For the sake of example, just print the json["timestamp"] value
        auto _timestamp = obj.at("timestamp");
        if (_timestamp.is_double()) {
            double timestamp = obj.at("timestamp").as_double();

            std::cout << obj.at("timestamp").as_double() << std::endl;
        }
    }
};

int main(int argc, char** argv) {
    if(argc <= 1) {
        std::cerr << "Usage: " << argv[0] << std::endl;
        return 1;
    }

    try {
        JSONLineProcessor processor(argv[1]);
        processor.process_lines();
    } catch (const std::exception& e) {
        std::cerr << e.what() << std::endl;
        return 1;
    }

    return 0;
}

How to compile

g++ -O3 -std=c++17 -lboost_json -o jsonlines_processor jsonlines_processor.cpp

Performance

Compiling with

g++ -march=native -O2 -std=gnu++17 -lboost_json -o jsonlines_processor jsonlines_processor.cpp

and running with

time ./jsonlines_processor filename.jsonlines > /dev/null

on a 4.5GB jsonlines file with 4442720 (4.4M) lines takes 36.4 seconds (best of 3 runs), yielding a throughput of 123.6 MB/s and 122k JSON lines per second on my Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz.

This program does not utilize multi-threading