编码主要都是跟着buffer走的

  • http://nodejs.cn/api/buffer.html
  • https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/TypedArray
  • buffer可以认为是typedarray的Uint8Array的一种实现, 对应于c语言的uint8_t
  • 不要new, 哈哈, 正合吾意.
  • 用这三个函数: Buffer.from()、Buffer.alloc()、和 Buffer.allocUnsafe()

编码:

  • 'ascii' - 仅支持 7 位 ASCII 数据。如果设置去掉高位的话，这种编码是非常快的。
  • 'utf8' - 多字节编码的 Unicode 字符。许多网页和其他文档格式都使用 UTF-8 。
  • 'utf16le' - 2 或 4 个字节，小字节序编码的 Unicode 字符。支持代理对（U+10000 至 U+10FFFF）。
  • 'ucs2' - 'utf16le' 的别名。
  • 'base64' - Base64 编码。当从字符串创建 Buffer 时，按照 RFC4648 第 5 章的规定，这种编码也将正确地接受“URL 与文件名安全字母表”。
  • 'latin1' - 一种把 Buffer 编码成一字节编码的字符串的方式（由 IANA 定义在 RFC1345 第 63 页，用作 Latin-1 补充块与 C0/C1 控制码）。
  • 'binary' - 'latin1' 的别名。
  • 'hex' - 将每个字节编码为两个十六进制字符。

如果一个文件我们不知道编码, 那么就要尝试最后的三种编码

16进制hex编码显示

const s="测试"
//charCodeAt可以
log(s.charCodeAt(0).toString(16))
//codePointAt也可以
for(var y=0; y<s.length; y++){	
	log(s.codePointAt(y).toString(16))
}

//貌似用正则更加简单明了.
function ASCIIToHexa (str) {
if (typeof str !== 'string') str += '';
return str.replace(/\w/g , (text) => text.charCodeAt().toString(16));
}


// int to hex 
let yourNumber=100

hexString = yourNumber.toString(16); //int to hex string


yourNumber = parseInt(hexString, 16); // hex string back to int, reverse the process

log(hexString + " ====== " + yourNumber);  

// hex to ascII
var input  = '32343630';
var output = new Buffer(input, 'hex');
log(input + " -> " + output);  // Result: 32343630 -> 2460

//或者下面用正则
var asciiVal = "32343630".match(/.{1,2}/g).map(function(v){
      return String.fromCharCode(parseInt(v, 16));
    }).join('');
    
log(asciiVal);


//一堆%的中文转码的处理, 仅仅处理了百分号
let ss=encodeURIComponent('中文编码').split('%').join('');
log(ss)

中文处理 iconv-lite

require('fs').createReadStream('4season.mp3').setEncoding('binary')
console.log('Line from file:', iconv.decode(line, 'gbk'))
var lineReader = require('readline').createInterface({

    
 var iconv = require('iconv-lite');

// Convert from an encoded buffer to js string.
str = iconv.decode(new Buffer([0x68, 0x65, 0x6c, 0x6c, 0x6f]), 'win1251');

// Convert from js string to an encoded buffer.
buf = iconv.encode("Sample input string", 'win1251');

// Check if encoding is supported
iconv.encodingExists("us-ascii")
    
先新建一个binary的buffer再去处理是否能有更好的结果?

参考

  • https://github.com/ashtuchkin/iconv-lite/wiki/Supported-Encodings

16进制的直接表示:

  • A decimal integer literal consists of a sequence of digits without a leading 0 (zero).
  • A leading 0 (zero) on an integer literal, or a leading 0o (or 0O) indicates it is in octal. Octal integers can include only the digits 0-7.
  • A leading 0x (or 0X) indicates a hexadecimal integer literal. Hexadecimal integers can include digits (0-9) and the letters a-f and A-F. (The case of a character does not change it’s value, e.g. 0xa = 0xA = 10 and 0xf = 0xF = 15.)
  • A leading 0b (or 0B) indicates a binary integer literal. Binary integers can only include the digits 0 and 1.
0, 117 and -345 (decimal, base 10)
015, 0001 and -0o77 (octal, base 8) 
0x1123, 0x00111 and -0xF1A7 (hexadecimal, "hex" or base 16)
0b11, 0b0011 and -0b11 (binary, base 2)

按位运算

很多时候, 这个很有用, 因为傻乎乎的直接计算总是显得很愚蠢, 实际上也确实很愚蠢. mdn上面的内容真的很棒, 直接去看就好了.

  • https://developer.mozilla.org/zh-CN/docs/Web/JavaScript/Reference/Operators/Bitwise_Operators
>> 右移, << 左移. 适合做拼字节的运算.
|按位或, &按位与. 适合做掩码.

从int到char

String.fromCharCode(97)  //这个能得到'a'
"ABC".charCodeAt(0) //这个是逆函数

{
"31": "",      "32": " ",     "33": "!",     "34": "\"",    "35": "#",    
"36": "$",     "37": "%",     "38": "&",     "39": "'",     "40": "(",    
"41": ")",     "42": "*",     "43": "+",     "44": ",",     "45": "-",    
"46": ".",     "47": "/",     "48": "0",     "49": "1",     "50": "2",    
"51": "3",     "52": "4",     "53": "5",     "54": "6",     "55": "7",    
"56": "8",     "57": "9",     "58": ":",     "59": ";",     "60": "<",    
"61": "=",     "62": ">",     "63": "?",     "64": "@",     "65": "A",    
"66": "B",     "67": "C",     "68": "D",     "69": "E",     "70": "F",    
"71": "G",     "72": "H",     "73": "I",     "74": "J",     "75": "K",    
"76": "L",     "77": "M",     "78": "N",     "79": "O",     "80": "P",    
"81": "Q",     "82": "R",     "83": "S",     "84": "T",     "85": "U",    
"86": "V",     "87": "W",     "88": "X",     "89": "Y",     "90": "Z",    
"91": "[",     "92": "\\",    "93": "]",     "94": "^",     "95": "_",    
"96": "`",     "97": "a",     "98": "b",     "99": "c",     "100": "d",    
"101": "e",    "102": "f",    "103": "g",    "104": "h",    "105": "i",    
"106": "j",    "107": "k",    "108": "l",    "109": "m",    "110": "n",    
"111": "o",    "112": "p",    "113": "q",    "114": "r",    "115": "s",    
"116": "t",    "117": "u",    "118": "v",    "119": "w",    "120": "x",    
"121": "y",    "122": "z",    "123": "{",    "124": "|",    "125": "}",    
"126": "~",    "127": ""
}

==和===

  • ==很多时候很诡异.
  • === 是所有情况下都建议使用的方法.
  • https://stackoverflow.com/questions/3586775/what-is-the-correct-way-to-check-for-string-equality-in-javascript
  • Mr. Douglas Crockford: http://www.youtube.com/watch?v=hQVTIJBZook
  • Kyle Simpson: https://github.com/getify/You-Dont-Know-JS
  • 这个结论有趣, 不要试图去理解js: I still recommend Crockford’s talk for developers who don’t want to invest the time to really understand Javascript—it’s good advice for a developer who only occasionally works in Javascript.
  • 别用new, 哈哈哈这个建议深得我心.
  • 举个例子: 0==”” //is true https://medium.com/@ludico8/identity-vs-equality-battle-of-understanding-vs-758d396e922