Proposal: ~2.5–3× faster parsing, conformance-preserving

#!/usr/bin/env python3
"""Standalone, dependency-free parse benchmark for tomlkit.

Run it on `main`, then on the optimization branch, and compare the medians:

    python bench_standalone.py            # default: 500 iters x 15 runs
    python bench_standalone.py --iters 1000 --runs 25

Only stdlib + the locally-installed `tomlkit` are used, so the numbers are
trivially reproducible. The sample document below is embedded (no external
files) and exercises the common value kinds: strings, ints/floats, bools,
datetimes, arrays, inline tables, nested tables, AoT and comments.

Methodology: warmup, then `runs` timed batches of `iters` parses each;
we report the median batch time (robust to OS scheduling noise) and stdev.
"""
from __future__ import annotations

import argparse
import statistics
import time

import tomlkit

# Representative ~3 KB TOML covering the value kinds the parser dispatches on.
SAMPLE = """\
# A representative TOML document
title = "tomlkit benchmark"
version = 2
ratio = 3.14159
enabled = true
created = 2024-01-15T08:30:00Z
tags = ["alpha", "beta", "gamma", "delta"]
matrix = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
inline = { x = 1, y = 2, z = 3 }

[server]
host = "localhost"
port = 8080
timeout = 30.5
backends = ["10.0.0.1", "10.0.0.2", "10.0.0.3"]

[server.tls]
enabled = true
ciphers = ["TLS_AES_256", "TLS_CHACHA20"]

[database]
url = "postgres://localhost:5432/app"  # inline comment
pool_size = 20
read_only = false

[[products]]
name = "Widget"
sku = 738594937
price = 19.99

[[products]]
name = "Gadget"
sku = 284758393
price = 49.95
in_stock = false

[logging]
level = "info"
format = "%(asctime)s %(message)s"
rotate_mb = 100
"""


def measure(content: str, iters: int) -> float:
    t0 = time.perf_counter()
    for _ in range(iters):
        tomlkit.parse(content)
    return (time.perf_counter() - t0) * 1000.0  # ms


def main() -> None:
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("--iters", type=int, default=500)
    ap.add_argument("--runs", type=int, default=15)
    ap.add_argument("--warmup", type=int, default=3)
    args = ap.parse_args()

    for _ in range(args.warmup):
        measure(SAMPLE, args.iters)

    samples = sorted(measure(SAMPLE, args.iters) for _ in range(args.runs))
    median = samples[len(samples) // 2]
    stdev = statistics.stdev(samples) if len(samples) > 1 else 0.0

    print(f"tomlkit {tomlkit.__version__ if hasattr(tomlkit, '__version__') else '?'}")
    print(f"{args.iters} parses x {args.runs} runs (warmup x{args.warmup})")
    print(f"  median : {median:8.1f} ms   ({median / args.iters * 1000:.1f} us/parse)")
    print(f"  stdev  : {stdev:8.1f} ms")
    print(f"  min/max: {samples[0]:.1f} / {samples[-1]:.1f} ms")


if __name__ == "__main__":
    main()