PhilipRoman

--[[
  detect.lua — distinguish UTF-8 from Shift-JIS

  Strategy (three layers):

  1. Grammar validation
     Parse the byte stream under each encoding's formal rules.
     A single invalid byte or sequence is decisive: the string
     cannot belong to that encoding.

PhilipRoman

#!/bin/sh
# Put in gitconfig:
# [alias]
# 	bvd = difftool -d -x bettervimdiff
dirA="$1"
dirB="$2"
if ! [ -d "$dirA" -a -d "$dirB" ]; then
	echo 'Usage: bettervimdiff DIR1 DIR2' >&2
	exit 1
fi

PhilipRoman

import java.net.*;
import java.io.*;

import org.java_websocket.server.*;
import org.java_websocket.*;
import org.java_websocket.handshake.*;

public class Main extends WebSocketServer {
	public static final int PORT = Integer.getInteger("port", 3141);

PhilipRoman

import java.lang.reflect.Field;
import java.nio.ByteBuffer;

public class Main {
	private static final int N = 1_000_000;
	private static Field stringBytes;
	private static String testString;

	static {
		// setup test string: