"""Reproduce the README benchmark numbers. pip install tiktoken for exact counts.""" import random from lessismore import compress, count_tokens def bench(name, text, level): b, a = count_tokens(text), count_tokens(compress(text, level)) print(f"{name:22} level {level} {b:>7,} -> {a:>6,} ({b / a:4.1f}x, {1 - a / b:.0%} saved)") # mixed log: 85% repeated ERROR line, 15% INFO lines differing only in numbers, one JWT random.seed(1) lines = [] for i in range(2000): ts = f"2026-07-07T10:{i // 60 % 60:02d}:{i % 60:02d}.{random.randint(100, 999)}Z" if random.random() < 0.85: lines.append(f"{ts} ERROR [pool-3] psycopg2.OperationalError: connection to " f"server at 10.0.0.5 failed: Connection refused") else: lines.append(f"{ts} INFO [worker-{random.randint(1, 4)}] processed batch {i} ok") lines.insert(500, "2026-07-07T10:08:20.123Z DEBUG auth token=" + "eyJhbGciOiJIUzI1NiJ9" * 8) bench("mixed error log", "\n".join(lines), 2) # interleaved log: three services alternating — zero consecutive runs, dedupe-proof random.seed(2) msgs = ["ERROR [pool-3] psycopg2.OperationalError: connection to server at " "10.0.0.5 failed: Connection refused", "WARN [redis-1] retry queue depth exceeded threshold, backing off 500ms", "ERROR [worker-2] TimeoutError: upstream api.example.com did not respond within 30s"] bench("interleaved log", "\n".join( f"2026-07-07T10:{i // 60 % 60:02d}:{i % 60:02d}Z " + msgs[i % 3] for i in range(1500)), 2) # chatty prose: levels 3 vs 4 show where filler stripping ends and caveman starts prose = ("So basically what happened was that the team had been trying to get the " "deployment pipeline working for about three weeks, and it turned out that the " "main problem was that the configuration file was pointing to the wrong database " "server. I think we should also mention that the staging environment has been " "flaky and there are a couple of monitoring alerts that have not been " "investigated yet. ") * 6 bench("chatty prose", prose, 3) bench("chatty prose", prose, 4)