Discover gists

Not all random values are created equal - for security-related code, you need a specific kind of random value.

A summary of this article, if you don't want to read the entire thing:

Don't use Math.random(). There are extremely few cases where Math.random() is the right answer. Don't use it, unless you've read this entire article, and determined that it's necessary for your case.
Don't use crypto.getRandomBytes directly. While it's a CSPRNG, it's easy to bias the result when 'transforming' it, such that the output becomes more predictable.
If you want to generate random tokens or API keys: Use uuid, specifically the uuid.v4() method. Avoid node-uuid - it's not the same package, and doesn't produce reliably secure random values.
If you want to generate random numbers in a range: Use random-number-csprng.

You should seriously consider reading the entire article, though - it's

	#include <stdio.h>
	#include <string.h>
	#include <errno.h>
	#include <dirent.h>
	#include <linux/limits.h>
	#include <regex.h>
	#include <stdbool.h>
	#include <stdlib.h>

	#define DATADIR "/sys/class/power_supply"

	#!/usr/bin/python
	#--coding:utf-8 --
	# E-HentaiのページURLをもとにギャラリー画像を取得するスクリプト


	# パッケージのインポート
	import os
	import sys
	import re
	import urllib2

	{
	"messages": [
	{
	"content": "You are an advanced, reliable, candid AI system that takes user search queries, converts them into questions, and answers them, using specific facts and details sourced from webpages to prove your answer. You admit when you're unsure or don't know, and you never make a statement without providing a fact or instance to back it up. You answer questions directly and clearly, then provide more detail later. You follow the JSON schema exactly.",
	"role": "system"
	},
	{
	"content": "# CONTEXT\nCurrent date: #{DATE_TIME}.\n\nHere are result from a web search for '#{QUERY}':\nBEGIN WEB PAGE #{HOST_1} #{MARKDOWN_1}END WEB PAGE\nBEGIN WEB PAGE #{HOST_2} #{MARKDOWN_2}END WEB PAGE\nBEGIN WEB PAGE #{HOST_3} #{MARKDOWN_3}END WEB PAGE\nBEGIN WEB PAGE #{HOST_4} #{MARKDOWN_4}END WEB PAGE\nBEGIN WEB PAGE #{HOST_5} #{MARKDOWN_5}END WEB PAGE\nBEGIN WEB PAGE #{HOST_6} #{MARKDOWN_6}END WEB PAGE",
	"role": "system"
	},

	// build all: $ zig build
	// clean up: $ zig build dist-clean
	const builtin = @import("builtin"); // list-up the content with `zig builtin` command
	const Builder = @import("std").build.Builder;

	//NOTE: this build code is for zig-0.4.0, maybe incompatible with zig >= 0.5
	pub fn build(b: *Builder) void {
	{ //[case: WebAssembly wasm] build fft.wasm
	const wasmStep = b.step("fft.wasm", "build fft.wasm");
	const wasm = b.addExecutable("fft.wasm", "fft.zig");

	package dev.abd3lraouf.learn.myapplication

	import android.os.Bundle
	import androidx.activity.ComponentActivity
	import androidx.activity.compose.setContent
	import androidx.activity.enableEdgeToEdge
	import androidx.compose.foundation.layout.Column
	import androidx.compose.foundation.layout.ExperimentalLayoutApi
	import androidx.compose.foundation.layout.WindowInsets
	import androidx.compose.foundation.layout.fillMaxSize

	#!/usr/bin/env zsh

	# Note:
	# CMake, Clang, clang-format, Ninja, git and sed are required to build
	#
	# Note that currently there is a bug (https://github.com/google/binexport/issues/117)
	# that requires applying this patch, remove when resolved
	#

	if [ -d ~/Downloads ]

	#!/usr/bin/env python3
	import sys
	import json
	import os

	def find_account_inclusion_object(eligibles, eth_address):
	for account in eligibles:
	if account["identity"].lower() == eth_address.lower():
	return account
	return None