#!/usr/bin/env python3 """Seed cdn.db with random packages/versions/files for benchmarking.""" import gzip import os import random import sqlite3 import string import sys DB_PATH = sys.argv[1] if len(sys.argv) > 1 else "cdn.db" N_PACKAGES = int(os.environ.get("N_PACKAGES", 500)) VERSIONS_PER_PKG = int(os.environ.get("VERSIONS_PER_PKG", 5)) MIN_SIZE = int(os.environ.get("MIN_SIZE", 512)) MAX_SIZE = int(os.environ.get("MAX_SIZE", 8192)) random.seed(42) if os.path.exists(DB_PATH): os.remove(DB_PATH) conn = sqlite3.connect(DB_PATH) conn.execute("""CREATE TABLE IF NOT EXISTS packages ( name TEXT PRIMARY KEY, archived INTEGER NOT NULL DEFAULT 0 )""") conn.execute("""CREATE TABLE IF NOT EXISTS versions ( package TEXT NOT NULL REFERENCES packages(name), version TEXT NOT NULL, filename TEXT NOT NULL, mime_type TEXT NOT NULL, gzipped_bytes BLOB NOT NULL, archived INTEGER NOT NULL DEFAULT 0, PRIMARY KEY (package, version) )""") def rand_name(n=10): return "".join(random.choices(string.ascii_lowercase, k=n)) def rand_body(size): chars = string.ascii_letters + string.digits + " \n" return "".join(random.choices(chars, k=size)).encode() manifest = [] # (package, version, filename) for the load generator pkg_names = [f"pkg-{rand_name(8)}-{i}" for i in range(N_PACKAGES)] for name in pkg_names: conn.execute("INSERT INTO packages (name, archived) VALUES (?, 0)", (name,)) for v in range(VERSIONS_PER_PKG): version = f"{v+1}.0.0" filename = f"{rand_name(6)}.js" size = random.randint(MIN_SIZE, MAX_SIZE) raw = rand_body(size) gz = gzip.compress(raw, compresslevel=6) conn.execute( "INSERT INTO versions (package, version, filename, mime_type, gzipped_bytes, archived) " "VALUES (?, ?, ?, 'application/javascript', ?, 0)", (name, version, filename, gz), ) manifest.append((name, version, filename)) conn.commit() conn.close() with open("bench/urls.txt", "w") as f: for pkg, ver, fn in manifest: f.write(f"/assets/{pkg}/{ver}/{fn}\n") print(f"seeded {len(pkg_names)} packages, {len(manifest)} versions -> {DB_PATH}") print(f"wrote {len(manifest)} urls -> bench/urls.txt")