examples/run_benchmark.py

"""Minimal benchmark runner placeholder."""

from __future__ import annotations

import argparse
from pathlib import Path
from time import perf_counter

from zsgdp import parse_document
from zsgdp.benchmarks.throughput import pages_per_second


def main() -> int:
    parser = argparse.ArgumentParser()
    parser.add_argument("input")
    parser.add_argument("output")
    args = parser.parse_args()

    input_dir = Path(args.input)
    output_dir = Path(args.output)
    output_dir.mkdir(parents=True, exist_ok=True)
    total_pages = 0
    started = perf_counter()
    for path in sorted(item for item in input_dir.iterdir() if item.is_file()):
        parsed = parse_document(path, output_dir / path.stem)
        total_pages += len(parsed.pages)
    elapsed = perf_counter() - started
    print(f"pages={total_pages} seconds={elapsed:.2f} pages_per_second={pages_per_second(total_pages, elapsed):.2f}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())